TOP ACTIVATIONS
MAX = 0.110

he was sad . He started walking away when he felt
too expensive . Tim my started to complain and cry .
't find it . Lily started to worry that she would
find her dress . She started to search for it .
later that day , Lily started to feel miserable . She
't have any . Ann started to feel sad and began
find her cup . She started to worry . She looked
jelly . <|endoftext|> John loved k ites . He looked at
to play with his new k ite . He brought it
. " These are your k ites . You can fly
excited . He had his k ite ready to fly in
L ily started to scratch her arm because
, Tim my 's dad started a fire in the backyard
very cold . Tim my started to sh iver because he
get a prize . Everyone started counting to 10 out loud
Tim my 's mom started to prepare the food for
to make breakfast . They started to mix the ingredients together
to be seen . Jane started to feel sad .
broke into pieces . Lily started to weep because she really
there either . Tim my started to feel sad .

MIN ACTIVATIONS
MIN = -0.157

watched the colorful lights in amaz ement , feeling truly lucky
baby le opard watched in amaz ement as the lion flex
stared at the pie in amaz ement . He just couldn
gazed at the butterfly in amaz ement . But
She opened her mouth in amaz ement . She had never
at the red blocks in amaz ement . He couldn 't
watch the big elephant in amaz ement . The
her doll and watched in amaz ement as it slowly flew
just stared at him in amaz ement . So , he
looked at the rainbow in amaz ement and laughed with joy
looked at the rainbow in amaz ement and laughed with joy
line . Billy watched in amaz ement as the ro oster
trick . Everyone watched in amaz ement and applauded the young
. The sheep watched in amaz ement and admired the flower
that made it pause in amaz ement . There , spreading
the bush and watched in amaz ement as it flew away
and pointed at it in amaz ement . The bird stopped
gazed at Ad eline in amaz ement . As she sang
shaking . Mom watched in amaz ement from a distance ,
. The deer stared in amaz ement . He had never

INTERVAL 0.043 - 0.110
CONTAINS 3.303%

. <|endoftext|> M olly was a brave girl , she liked
The hunter was proud of himself and thanked his friends
, " We are sorry . We are happy . We
girl named Lily . She loved to play outside and lay
my . Tim my loved going to the beach to see

INTERVAL -0.024 - 0.043
CONTAINS 82.731%

play in here . The horse might get scared or hurt
them a tissue to wipe their eyes . "
both be more careful with our toys ." From
I love you ". Al ina felt much better
and exciting . So he decided to travel to find something

INTERVAL -0.090 - -0.024
CONTAINS 13.943%

Jake was so thankful for his body 's power to
Lily . That sounds fun ." Max said , as they
the truck out of the trap . The truck was free
her reach her ball in the west . Spot
he was scared that he didn 't belong .

INTERVAL -0.157 - -0.090
CONTAINS 0.023%

if he told them this story . From then on ,
on his paws and listen int ently to her until she
." Lily says , " Really ? You will let me
been big and strong . How could it be shrinking all
a little note on her slice . The note said '
Token he
Token ID339
Feature activation+2.90e-03

Pos logit contributions
burn+0.034
 street+0.031
coat+0.031
ety+0.026
 yard+0.026
Neg logit contributions
ement-0.033
od-0.032
izards-0.032
bridge-0.030
es-0.030
Token was
Token ID373
Feature activation+2.26e-02

Pos logit contributions
burn+0.005
coat+0.005
 street+0.005
ety+0.004
 yard+0.004
Neg logit contributions
ement-0.006
od-0.006
izards-0.005
bridge-0.005
es-0.005
Token sad
Token ID6507
Feature activation+3.63e-02

Pos logit contributions
burn+0.044
coat+0.040
 street+0.040
ety+0.034
 yard+0.034
Neg logit contributions
ement-0.039
od-0.038
izards-0.037
es-0.036
 pounds-0.035
Token.
Token ID13
Feature activation+1.44e-02

Pos logit contributions
burn+0.069
 street+0.062
coat+0.062
 yard+0.052
ety+0.052
Neg logit contributions
ement-0.069
od-0.067
izards-0.066
bridge-0.064
es-0.063
Token He
Token ID679
Feature activation+9.31e-03

Pos logit contributions
burn+0.028
 street+0.026
coat+0.026
 yard+0.022
ety+0.022
Neg logit contributions
ement-0.026
od-0.025
izards-0.025
es-0.024
bridge-0.023
Token started
Token ID2067
Feature activation+1.10e-01

Pos logit contributions
burn+0.017
coat+0.015
 street+0.015
ety+0.013
 yard+0.012
Neg logit contributions
ement-0.019
od-0.018
izards-0.018
es-0.017
bridge-0.017
Token walking
Token ID6155
Feature activation+6.22e-02

Pos logit contributions
burn+0.208
coat+0.192
 street+0.171
ety+0.169
athy+0.152
Neg logit contributions
od-0.190
es-0.177
ement-0.175
izards-0.159
 symbols-0.157
Token away
Token ID1497
Feature activation+1.01e-02

Pos logit contributions
burn+0.115
coat+0.100
 street+0.096
ety+0.084
 yard+0.079
Neg logit contributions
ement-0.123
od-0.119
izards-0.117
es-0.115
bridge-0.111
Token when
Token ID618
Feature activation+1.39e-02

Pos logit contributions
burn+0.021
coat+0.019
 street+0.018
ety+0.016
 yard+0.015
Neg logit contributions
ement-0.018
od-0.017
izards-0.017
es-0.017
bridge-0.015
Token he
Token ID339
Feature activation-3.25e-02

Pos logit contributions
burn+0.035
coat+0.032
 street+0.031
ety+0.028
 yard+0.027
Neg logit contributions
ement-0.018
od-0.017
izards-0.017
es-0.016
bridge-0.016
Token felt
Token ID2936
Feature activation-1.32e-02

Pos logit contributions
ement+0.076
od+0.074
izards+0.074
es+0.071
bridge+0.071
Neg logit contributions
burn-0.046
coat-0.042
 street-0.042
ety-0.034
 yard-0.033
Token too
Token ID1165
Feature activation+1.51e-02

Pos logit contributions
burn+0.022
coat+0.020
 street+0.020
 yard+0.017
 wander+0.017
Neg logit contributions
ement-0.013
izards-0.013
od-0.013
 pounds-0.012
hell-0.012
Token expensive
Token ID5789
Feature activation+1.15e-02

Pos logit contributions
burn+0.030
coat+0.027
 street+0.024
 driveway+0.024
any+0.023
Neg logit contributions
hell-0.025
 pounds-0.025
ement-0.024
 kilograms-0.022
od-0.022
Token.
Token ID13
Feature activation+1.22e-02

Pos logit contributions
burn+0.026
coat+0.024
 street+0.023
ety+0.020
 yard+0.020
Neg logit contributions
ement-0.018
od-0.017
izards-0.016
es-0.016
 pounds-0.015
Token Tim
Token ID5045
Feature activation+1.85e-02

Pos logit contributions
burn+0.026
coat+0.023
 street+0.023
ety+0.019
 wander+0.019
Neg logit contributions
ement-0.021
od-0.019
es-0.018
izards-0.018
hell-0.018
Tokenmy
Token ID1820
Feature activation+1.65e-02

Pos logit contributions
burn+0.019
 street+0.016
coat+0.016
 wander+0.010
 Dog+0.010
Neg logit contributions
ement-0.050
od-0.049
es-0.048
izards-0.047
hell-0.046
Token started
Token ID2067
Feature activation+1.10e-01

Pos logit contributions
burn+0.035
coat+0.032
 street+0.032
ety+0.028
 yard+0.027
Neg logit contributions
ement-0.027
od-0.027
izards-0.026
es-0.025
bridge-0.024
Token to
Token ID284
Feature activation+1.40e-02

Pos logit contributions
burn+0.219
coat+0.205
 street+0.187
ety+0.180
athy+0.175
Neg logit contributions
od-0.157
es-0.153
ement-0.137
 slices-0.133
 it-0.129
Token complain
Token ID13121
Feature activation-6.22e-03

Pos logit contributions
burn+0.028
coat+0.025
 street+0.023
ained+0.023
itty+0.022
Neg logit contributions
od-0.019
hell-0.018
ement-0.018
ts-0.017
 wishes-0.017
Token and
Token ID290
Feature activation+1.66e-02

Pos logit contributions
ement+0.012
od+0.012
izards+0.012
es+0.011
bridge+0.011
Neg logit contributions
burn-0.012
coat-0.010
 street-0.010
ety-0.009
 yard-0.008
Token cry
Token ID3960
Feature activation+4.04e-03

Pos logit contributions
burn+0.033
coat+0.029
 street+0.028
ety+0.025
 yard+0.024
Neg logit contributions
ement-0.029
od-0.029
izards-0.028
es-0.028
bridge-0.026
Token.
Token ID13
Feature activation+1.37e-02

Pos logit contributions
burn+0.008
coat+0.007
 street+0.007
ety+0.006
 yard+0.006
Neg logit contributions
ement-0.007
od-0.007
izards-0.007
bridge-0.007
es-0.007
Token't
Token ID470
Feature activation+3.24e-02

Pos logit contributions
ement+0.063
od+0.061
izards+0.060
es+0.057
bridge+0.056
Neg logit contributions
burn-0.078
coat-0.071
 street-0.070
ety-0.060
 yard-0.060
Token find
Token ID1064
Feature activation-4.02e-03

Pos logit contributions
burn+0.043
 street+0.037
coat+0.037
ety+0.029
 yard+0.028
Neg logit contributions
ement-0.080
od-0.078
izards-0.076
es-0.075
bridge-0.074
Token it
Token ID340
Feature activation-1.34e-02

Pos logit contributions
ement+0.006
od+0.006
izards+0.006
bridge+0.006
es+0.006
Neg logit contributions
burn-0.009
coat-0.008
 street-0.008
ety-0.007
 Dog-0.007
Token.
Token ID13
Feature activation+1.29e-02

Pos logit contributions
ement+0.023
od+0.023
izards+0.022
es+0.021
bridge+0.021
Neg logit contributions
burn-0.028
coat-0.025
 street-0.025
ety-0.022
 yard-0.021
Token Lily
Token ID20037
Feature activation+1.91e-02

Pos logit contributions
burn+0.023
coat+0.020
 street+0.020
ety+0.017
 yard+0.016
Neg logit contributions
ement-0.026
od-0.026
izards-0.025
es-0.024
bridge-0.024
Token started
Token ID2067
Feature activation+1.09e-01

Pos logit contributions
burn+0.039
coat+0.035
 street+0.035
ety+0.030
 yard+0.029
Neg logit contributions
ement-0.034
od-0.033
izards-0.032
es-0.031
bridge-0.031
Token to
Token ID284
Feature activation+1.18e-02

Pos logit contributions
burn+0.188
coat+0.165
 street+0.156
ety+0.131
 yard+0.125
Neg logit contributions
od-0.229
es-0.218
ement-0.217
izards-0.214
ils-0.198
Token worry
Token ID5490
Feature activation+3.72e-03

Pos logit contributions
burn+0.022
coat+0.020
 street+0.018
ety+0.016
ained+0.015
Neg logit contributions
od-0.022
izards-0.022
ement-0.021
es-0.021
hell-0.020
Token that
Token ID326
Feature activation+3.04e-02

Pos logit contributions
burn+0.006
coat+0.005
 street+0.005
 raining+0.004
 yard+0.004
Neg logit contributions
ement-0.008
od-0.008
izards-0.008
bridge-0.008
ils-0.007
Token she
Token ID673
Feature activation+6.09e-03

Pos logit contributions
burn+0.057
coat+0.052
 street+0.051
ety+0.043
 yard+0.042
Neg logit contributions
ement-0.059
od-0.058
izards-0.056
es-0.055
bridge-0.053
Token would
Token ID561
Feature activation+4.10e-04

Pos logit contributions
burn+0.011
coat+0.010
 street+0.010
ety+0.009
 yard+0.009
Neg logit contributions
ement-0.012
od-0.011
izards-0.011
bridge-0.011
 pounds-0.010
Token find
Token ID1064
Feature activation+8.91e-03

Pos logit contributions
burn+0.058
coat+0.049
 street+0.047
 Kathy+0.041
ety+0.040
Neg logit contributions
od-0.068
izards-0.065
ement-0.063
hell-0.062
ocket-0.062
Token her
Token ID607
Feature activation+3.56e-02

Pos logit contributions
burn+0.014
coat+0.012
 street+0.012
ety+0.010
 yard+0.009
Neg logit contributions
ement-0.020
od-0.020
izards-0.019
bridge-0.019
es-0.019
Token dress
Token ID6576
Feature activation-1.85e-03

Pos logit contributions
burn+0.067
coat+0.058
 street+0.058
ety+0.050
 Dog+0.048
Neg logit contributions
ement-0.067
od-0.063
izards-0.062
es-0.059
ocket-0.059
Token.
Token ID13
Feature activation+1.07e-02

Pos logit contributions
ement+0.003
od+0.003
izards+0.003
es+0.003
bridge+0.003
Neg logit contributions
burn-0.004
 street-0.004
coat-0.004
ety-0.003
 yard-0.003
Token She
Token ID1375
Feature activation+7.54e-03

Pos logit contributions
burn+0.019
coat+0.016
 street+0.016
ety+0.013
 yard+0.013
Neg logit contributions
ement-0.022
od-0.021
izards-0.021
es-0.021
bridge-0.020
Token started
Token ID2067
Feature activation+1.09e-01

Pos logit contributions
burn+0.014
coat+0.013
 street+0.013
ety+0.011
 yard+0.011
Neg logit contributions
ement-0.014
od-0.014
izards-0.014
bridge-0.013
es-0.013
Token to
Token ID284
Feature activation+1.10e-02

Pos logit contributions
burn+0.199
coat+0.180
 street+0.168
ety+0.152
 tire+0.144
Neg logit contributions
od-0.205
es-0.192
izards-0.181
ement-0.179
ils-0.173
Token search
Token ID2989
Feature activation+5.76e-03

Pos logit contributions
burn+0.021
coat+0.018
 street+0.017
ety+0.016
 Dog+0.015
Neg logit contributions
od-0.019
izards-0.018
ement-0.018
hell-0.017
es-0.017
Token for
Token ID329
Feature activation-4.55e-02

Pos logit contributions
burn+0.011
coat+0.010
 street+0.010
 yard+0.009
ety+0.009
Neg logit contributions
ement-0.010
od-0.010
izards-0.010
es-0.010
bridge-0.010
Token it
Token ID340
Feature activation-8.12e-03

Pos logit contributions
ement+0.100
od+0.098
izards+0.095
bridge+0.092
es+0.091
Neg logit contributions
burn-0.073
coat-0.064
 street-0.063
 yard-0.052
 rag-0.052
Token.
Token ID13
Feature activation+8.18e-03

Pos logit contributions
ement+0.013
od+0.013
izards+0.013
es+0.013
hell+0.012
Neg logit contributions
burn-0.018
 street-0.016
coat-0.016
ety-0.013
 yard-0.013
Token later
Token ID1568
Feature activation-2.54e-02

Pos logit contributions
ement+0.009
od+0.009
es+0.009
izards+0.009
ils+0.008
Neg logit contributions
burn-0.013
coat-0.012
 street-0.012
 yard-0.010
 wander-0.010
Token that
Token ID326
Feature activation-3.74e-03

Pos logit contributions
izards+0.052
ement+0.052
od+0.051
bridge+0.049
 pounds+0.048
Neg logit contributions
burn-0.044
 street-0.039
coat-0.038
 yard-0.031
ety-0.031
Token day
Token ID1110
Feature activation-7.41e-03

Pos logit contributions
od+0.008
ement+0.008
es+0.007
hell+0.007
ils+0.007
Neg logit contributions
coat-0.006
burn-0.006
 street-0.005
ety-0.004
 Dog-0.004
Token,
Token ID11
Feature activation+9.69e-04

Pos logit contributions
ement+0.015
od+0.014
izards+0.014
es+0.013
bridge+0.013
Neg logit contributions
burn-0.014
coat-0.012
 street-0.012
ety-0.010
 yard-0.010
Token Lily
Token ID20037
Feature activation+1.39e-02

Pos logit contributions
burn+0.002
coat+0.001
 street+0.001
ety+0.001
 raining+0.001
Neg logit contributions
ement-0.002
od-0.002
izards-0.002
es-0.002
 pounds-0.002
Token started
Token ID2067
Feature activation+1.09e-01

Pos logit contributions
burn+0.030
coat+0.027
 street+0.026
ety+0.022
 Kathy+0.022
Neg logit contributions
od-0.022
es-0.022
ement-0.022
izards-0.021
ils-0.020
Token to
Token ID284
Feature activation+1.62e-02

Pos logit contributions
burn+0.201
coat+0.185
 street+0.174
ety+0.153
 Kathy+0.151
Neg logit contributions
od-0.199
es-0.186
ement-0.176
izards-0.173
ils-0.168
Token feel
Token ID1254
Feature activation-7.94e-04

Pos logit contributions
burn+0.030
coat+0.027
 street+0.026
ety+0.023
 passenger+0.022
Neg logit contributions
od-0.028
izards-0.025
es-0.024
hell-0.024
ement-0.024
Token miserable
Token ID22444
Feature activation+2.17e-02

Pos logit contributions
ement+0.002
izards+0.002
od+0.002
es+0.002
hell+0.001
Neg logit contributions
burn-0.001
coat-0.001
 street-0.001
ety-0.001
gy-0.001
Token.
Token ID13
Feature activation+9.03e-03

Pos logit contributions
burn+0.043
coat+0.039
 street+0.039
ety+0.033
 yard+0.033
Neg logit contributions
ement-0.039
od-0.038
izards-0.037
es-0.036
bridge-0.035
Token She
Token ID1375
Feature activation+7.05e-03

Pos logit contributions
burn+0.017
coat+0.015
 street+0.013
ety+0.012
 passenger+0.011
Neg logit contributions
ement-0.018
od-0.017
izards-0.016
boards-0.016
es-0.015
Token't
Token ID470
Feature activation+6.08e-02

Pos logit contributions
ement+0.064
od+0.063
izards+0.060
es+0.059
bridge+0.056
Neg logit contributions
burn-0.101
coat-0.095
 street-0.093
ety-0.084
 yard-0.082
Token have
Token ID423
Feature activation-4.22e-04

Pos logit contributions
burn+0.121
coat+0.108
 street+0.105
 yard+0.090
 Kathy+0.089
Neg logit contributions
od-0.101
izards-0.100
hell-0.100
es-0.093
ocket-0.089
Token any
Token ID597
Feature activation+2.95e-02

Pos logit contributions
ement+0.001
od+0.001
izards+0.001
es+0.001
bridge+0.001
Neg logit contributions
burn-0.001
coat-0.001
 street-0.001
ety-0.001
 raining-0.001
Token.
Token ID13
Feature activation+6.22e-03

Pos logit contributions
burn+0.064
coat+0.058
 street+0.057
ety+0.049
 yard+0.049
Neg logit contributions
ement-0.049
od-0.047
izards-0.046
es-0.044
bridge-0.043
Token Ann
Token ID5506
Feature activation+8.90e-03

Pos logit contributions
burn+0.011
 street+0.010
coat+0.010
 yard+0.009
ety+0.009
Neg logit contributions
ement-0.012
od-0.012
izards-0.012
es-0.011
bridge-0.011
Token started
Token ID2067
Feature activation+1.08e-01

Pos logit contributions
burn+0.017
coat+0.016
 street+0.015
ety+0.014
 yard+0.013
Neg logit contributions
ement-0.015
izards-0.015
od-0.015
bridge-0.015
es-0.014
Token to
Token ID284
Feature activation+1.38e-02

Pos logit contributions
burn+0.196
coat+0.178
 street+0.166
ety+0.149
 yard+0.137
Neg logit contributions
od-0.208
es-0.193
ement-0.191
izards-0.184
ils-0.172
Token feel
Token ID1254
Feature activation+4.61e-04

Pos logit contributions
burn+0.024
coat+0.022
 street+0.020
ety+0.018
 yard+0.017
Neg logit contributions
od-0.026
izards-0.024
ement-0.024
hell-0.023
es-0.023
Token sad
Token ID6507
Feature activation+2.25e-02

Pos logit contributions
burn+0.001
coat+0.001
 street+0.001
ety+0.001
 yard+0.001
Neg logit contributions
ement-0.001
od-0.001
izards-0.001
es-0.001
bridge-0.001
Token and
Token ID290
Feature activation+3.23e-02

Pos logit contributions
burn+0.041
coat+0.036
 street+0.036
ety+0.030
 yard+0.029
Neg logit contributions
ement-0.045
od-0.044
izards-0.043
es-0.042
bridge-0.041
Token began
Token ID2540
Feature activation+9.45e-02

Pos logit contributions
burn+0.057
coat+0.050
 street+0.050
ety+0.041
 yard+0.041
Neg logit contributions
ement-0.066
od-0.065
izards-0.063
es-0.062
bridge-0.061
Token find
Token ID1064
Feature activation+1.19e-02

Pos logit contributions
burn+0.057
coat+0.050
 street+0.049
ety+0.040
 yard+0.039
Neg logit contributions
od-0.074
ement-0.073
izards-0.072
es-0.069
bridge-0.068
Token her
Token ID607
Feature activation+3.82e-02

Pos logit contributions
burn+0.022
coat+0.020
 street+0.020
ety+0.017
 yard+0.016
Neg logit contributions
ement-0.023
od-0.023
izards-0.022
es-0.021
bridge-0.021
Token cup
Token ID6508
Feature activation-1.82e-02

Pos logit contributions
burn+0.071
coat+0.063
 street+0.063
ety+0.053
 wander+0.051
Neg logit contributions
ement-0.073
od-0.070
izards-0.068
es-0.066
ils-0.064
Token.
Token ID13
Feature activation+7.63e-03

Pos logit contributions
ement+0.032
od+0.031
izards+0.030
es+0.029
bridge+0.029
Neg logit contributions
burn-0.037
coat-0.034
 street-0.033
ety-0.029
 yard-0.028
Token She
Token ID1375
Feature activation+5.98e-03

Pos logit contributions
burn+0.010
 street+0.010
coat+0.009
 yard+0.007
ety+0.007
Neg logit contributions
ement-0.018
od-0.018
izards-0.018
es-0.017
bridge-0.017
Token started
Token ID2067
Feature activation+1.08e-01

Pos logit contributions
burn+0.011
 street+0.010
coat+0.010
ety+0.008
 yard+0.008
Neg logit contributions
ement-0.012
od-0.012
izards-0.011
bridge-0.011
es-0.011
Token to
Token ID284
Feature activation+1.24e-02

Pos logit contributions
burn+0.198
coat+0.181
 street+0.169
ety+0.151
 tire+0.146
Neg logit contributions
od-0.198
es-0.193
izards-0.182
ement-0.175
ils-0.174
Token worry
Token ID5490
Feature activation+3.09e-03

Pos logit contributions
burn+0.023
coat+0.020
 street+0.018
ety+0.017
 Dog+0.015
Neg logit contributions
od-0.023
izards-0.022
ement-0.021
es-0.021
ils-0.021
Token.
Token ID13
Feature activation+5.34e-03

Pos logit contributions
burn+0.005
coat+0.005
 street+0.005
 raining+0.004
 yard+0.004
Neg logit contributions
ement-0.006
od-0.006
izards-0.006
bridge-0.006
es-0.006
Token She
Token ID1375
Feature activation+3.98e-03

Pos logit contributions
burn+0.008
 street+0.007
coat+0.007
 yard+0.006
ety+0.006
Neg logit contributions
ement-0.012
od-0.012
izards-0.012
es-0.011
bridge-0.011
Token looked
Token ID3114
Feature activation-2.38e-03

Pos logit contributions
burn+0.007
coat+0.006
 street+0.006
ety+0.005
 yard+0.005
Neg logit contributions
ement-0.008
od-0.008
izards-0.008
es-0.007
bridge-0.007
Token jelly
Token ID27644
Feature activation-6.17e-02

Pos logit contributions
es+0.058
ement+0.057
od+0.057
izards+0.056
bridge+0.053
Neg logit contributions
 street-0.048
burn-0.044
 yard-0.041
coat-0.040
 raining-0.037
Token.
Token ID13
Feature activation-1.13e-02

Pos logit contributions
ement+0.096
od+0.093
izards+0.092
bridge+0.087
 pounds+0.086
Neg logit contributions
 street-0.123
coat-0.117
burn-0.116
 yard-0.111
 swing-0.097
Token<|endoftext|>
Token ID50256
Feature activation-3.58e-02

Pos logit contributions
ement+0.025
izards+0.025
od+0.024
bridge+0.024
ils+0.024
Neg logit contributions
burn-0.017
 street-0.016
coat-0.015
 yard-0.013
ety-0.013
TokenJohn
Token ID7554
Feature activation+4.03e-03

Pos logit contributions
ement+0.082
od+0.079
izards+0.078
 pounds+0.078
ils+0.077
Neg logit contributions
burn-0.050
 street-0.047
coat-0.045
 yard-0.041
ety-0.036
Token loved
Token ID6151
Feature activation+4.01e-02

Pos logit contributions
burn+0.008
coat+0.007
 street+0.007
ety+0.006
 raining+0.006
Neg logit contributions
od-0.007
ement-0.007
es-0.007
izards-0.006
ils-0.006
Token k
Token ID479
Feature activation+1.08e-01

Pos logit contributions
burn+0.068
coat+0.063
 street+0.057
ety+0.051
gy+0.047
Neg logit contributions
od-0.081
ement-0.078
izards-0.077
es-0.073
bridge-0.073
Tokenites
Token ID2737
Feature activation+7.43e-02

Pos logit contributions
burn+0.198
coat+0.175
 street+0.172
ety+0.148
 yard+0.142
Neg logit contributions
ement-0.214
od-0.209
izards-0.204
bridge-0.198
es-0.196
Token.
Token ID13
Feature activation+6.91e-03

Pos logit contributions
burn+0.149
coat+0.135
 street+0.134
ety+0.114
 yard+0.113
Neg logit contributions
ement-0.132
od-0.129
izards-0.127
es-0.121
bridge-0.120
Token He
Token ID679
Feature activation+1.33e-02

Pos logit contributions
burn+0.015
coat+0.014
 street+0.014
ety+0.012
 yard+0.012
Neg logit contributions
ement-0.011
od-0.011
izards-0.010
bridge-0.010
es-0.010
Token looked
Token ID3114
Feature activation-2.83e-03

Pos logit contributions
burn+0.028
 street+0.024
coat+0.024
 yard+0.021
ety+0.021
Neg logit contributions
od-0.022
ement-0.021
es-0.021
izards-0.021
ils-0.020
Token at
Token ID379
Feature activation-1.17e-02

Pos logit contributions
ement+0.005
od+0.005
izards+0.005
es+0.005
bridge+0.005
Neg logit contributions
burn-0.005
coat-0.005
 street-0.005
ety-0.004
 yard-0.004
Token to
Token ID284
Feature activation+1.41e-02

Pos logit contributions
burn+0.037
coat+0.033
 street+0.031
ety+0.027
gy+0.026
Neg logit contributions
od-0.046
ement-0.044
izards-0.044
es-0.041
bridge-0.041
Token play
Token ID711
Feature activation+4.10e-02

Pos logit contributions
burn+0.021
coat+0.018
 street+0.017
ety+0.015
 yard+0.013
Neg logit contributions
od-0.032
ement-0.031
izards-0.031
bridge-0.030
es-0.029
Token with
Token ID351
Feature activation-1.02e-02

Pos logit contributions
burn+0.055
 street+0.053
coat+0.053
 yard+0.046
 jog+0.041
Neg logit contributions
ement-0.096
od-0.094
izards-0.092
 pounds-0.091
 ounces-0.088
Token his
Token ID465
Feature activation+2.45e-02

Pos logit contributions
ement+0.018
od+0.018
izards+0.017
es+0.017
bridge+0.017
Neg logit contributions
burn-0.021
coat-0.018
 street-0.018
ety-0.016
 yard-0.015
Token new
Token ID649
Feature activation+5.38e-02

Pos logit contributions
burn+0.043
coat+0.037
 street+0.034
ety+0.031
 wander+0.028
Neg logit contributions
ement-0.051
od-0.049
izards-0.048
es-0.046
bridge-0.046
Token k
Token ID479
Feature activation+1.08e-01

Pos logit contributions
burn+0.097
coat+0.081
 street+0.076
ety+0.074
 Kathy+0.066
Neg logit contributions
ement-0.105
od-0.101
izards-0.098
es-0.095
bridge-0.095
Tokenite
Token ID578
Feature activation+6.79e-02

Pos logit contributions
burn+0.162
 street+0.147
coat+0.140
 wander+0.113
 raining+0.111
Neg logit contributions
ement-0.245
es-0.235
izards-0.235
od-0.234
hell-0.219
Token.
Token ID13
Feature activation+1.80e-03

Pos logit contributions
burn+0.152
coat+0.137
 street+0.135
ety+0.121
 Kathy+0.115
Neg logit contributions
ement-0.103
od-0.100
es-0.098
izards-0.098
bridge-0.093
Token He
Token ID679
Feature activation+9.72e-04

Pos logit contributions
burn+0.004
coat+0.004
 street+0.004
ety+0.003
 yard+0.003
Neg logit contributions
ement-0.002
od-0.002
bridge-0.002
izards-0.002
es-0.002
Token brought
Token ID3181
Feature activation-2.09e-03

Pos logit contributions
burn+0.002
coat+0.002
 street+0.002
ety+0.002
 yard+0.002
Neg logit contributions
od-0.002
es-0.002
izards-0.002
ement-0.002
bridge-0.001
Token it
Token ID340
Feature activation-7.28e-04

Pos logit contributions
ement+0.003
od+0.003
izards+0.003
olo+0.003
es+0.003
Neg logit contributions
burn-0.005
 street-0.005
coat-0.005
 tire-0.004
 Dog-0.004
Token.
Token ID13
Feature activation+1.15e-02

Pos logit contributions
ement+0.067
izards+0.066
od+0.065
bridge+0.063
ils+0.060
Neg logit contributions
burn-0.064
coat-0.058
 street-0.055
ety-0.047
 Dog-0.045
Token "
Token ID366
Feature activation-8.53e-04

Pos logit contributions
burn+0.024
coat+0.022
 street+0.021
ety+0.019
 wander+0.018
Neg logit contributions
ement-0.020
od-0.019
es-0.018
izards-0.018
bridge-0.017
TokenThese
Token ID4711
Feature activation-2.33e-02

Pos logit contributions
ement+0.002
od+0.002
izards+0.001
es+0.001
bridge+0.001
Neg logit contributions
burn-0.002
coat-0.001
 street-0.001
 yard-0.001
ety-0.001
Token are
Token ID389
Feature activation-1.78e-02

Pos logit contributions
ement+0.033
od+0.032
izards+0.031
bridge+0.029
es+0.029
Neg logit contributions
burn-0.055
 street-0.051
coat-0.050
 yard-0.045
ety-0.044
Token your
Token ID534
Feature activation+4.84e-02

Pos logit contributions
ement+0.036
od+0.035
izards+0.034
es+0.033
bridge+0.032
Neg logit contributions
burn-0.032
coat-0.029
 street-0.029
ety-0.024
 yard-0.024
Token k
Token ID479
Feature activation+1.08e-01

Pos logit contributions
burn+0.086
coat+0.076
 street+0.075
ety+0.063
 yard+0.061
Neg logit contributions
ement-0.098
od-0.095
izards-0.093
es-0.090
bridge-0.089
Tokenites
Token ID2737
Feature activation+7.37e-02

Pos logit contributions
burn+0.157
 street+0.144
coat+0.135
 yard+0.110
 raining+0.108
Neg logit contributions
ement-0.249
izards-0.238
od-0.237
es-0.237
hell-0.223
Token.
Token ID13
Feature activation+3.93e-02

Pos logit contributions
burn+0.156
coat+0.141
 street+0.140
ety+0.121
 yard+0.118
Neg logit contributions
ement-0.124
od-0.120
izards-0.117
es-0.114
bridge-0.111
Token You
Token ID921
Feature activation-4.07e-02

Pos logit contributions
burn+0.088
coat+0.081
 street+0.080
ety+0.070
 yard+0.069
Neg logit contributions
ement-0.061
od-0.059
izards-0.058
es-0.055
bridge-0.054
Token can
Token ID460
Feature activation+8.45e-03

Pos logit contributions
ement+0.080
od+0.073
izards+0.071
 pounds+0.067
es+0.067
Neg logit contributions
burn-0.078
coat-0.073
 street-0.072
ety-0.061
 yard-0.060
Token fly
Token ID6129
Feature activation+3.79e-02

Pos logit contributions
burn+0.014
coat+0.013
 street+0.013
ety+0.011
 yard+0.010
Neg logit contributions
od-0.017
ement-0.017
izards-0.016
es-0.016
bridge-0.015
Token excited
Token ID6568
Feature activation+1.67e-03

Pos logit contributions
burn+0.017
coat+0.015
 street+0.014
ety+0.013
 yard+0.012
Neg logit contributions
ement-0.016
od-0.016
izards-0.015
bridge-0.015
es-0.015
Token.
Token ID13
Feature activation+1.65e-02

Pos logit contributions
burn+0.003
 street+0.003
coat+0.003
 yard+0.002
 raining+0.002
Neg logit contributions
ement-0.003
izards-0.003
od-0.003
bridge-0.003
es-0.003
Token He
Token ID679
Feature activation+1.36e-02

Pos logit contributions
burn+0.037
coat+0.033
 street+0.033
ety+0.029
 yard+0.028
Neg logit contributions
ement-0.026
od-0.025
izards-0.025
es-0.024
bridge-0.023
Token had
Token ID550
Feature activation+1.21e-02

Pos logit contributions
burn+0.027
coat+0.023
 street+0.022
ety+0.020
 yard+0.018
Neg logit contributions
ement-0.025
od-0.025
izards-0.024
es-0.023
bridge-0.023
Token his
Token ID465
Feature activation+4.07e-02

Pos logit contributions
burn+0.022
coat+0.020
 street+0.019
ety+0.016
 yard+0.016
Neg logit contributions
ement-0.024
od-0.024
izards-0.023
es-0.022
bridge-0.022
Token k
Token ID479
Feature activation+1.08e-01

Pos logit contributions
burn+0.077
coat+0.069
 street+0.064
ety+0.060
 Kathy+0.053
Neg logit contributions
ement-0.078
od-0.073
izards-0.071
bridge-0.068
hell-0.067
Tokenite
Token ID578
Feature activation+6.64e-02

Pos logit contributions
burn+0.151
 street+0.132
coat+0.130
 yard+0.099
ety+0.098
Neg logit contributions
ement-0.258
od-0.250
izards-0.247
es-0.243
bridge-0.235
Token ready
Token ID3492
Feature activation-2.64e-02

Pos logit contributions
burn+0.138
coat+0.122
 street+0.120
ety+0.108
 Kathy+0.101
Neg logit contributions
ement-0.110
od-0.108
es-0.104
izards-0.102
bridge-0.101
Token to
Token ID284
Feature activation-8.19e-03

Pos logit contributions
ement+0.060
izards+0.058
od+0.058
bridge+0.056
es+0.056
Neg logit contributions
burn-0.040
coat-0.035
 street-0.035
 yard-0.028
 raining-0.027
Token fly
Token ID6129
Feature activation+2.91e-02

Pos logit contributions
ement+0.018
od+0.018
izards+0.017
es+0.017
bridge+0.017
Neg logit contributions
burn-0.013
coat-0.012
 street-0.011
ety-0.010
 yard-0.009
Token in
Token ID287
Feature activation-7.43e-03

Pos logit contributions
burn+0.050
 street+0.046
coat+0.045
 yard+0.038
 raining+0.037
Neg logit contributions
ement-0.060
izards-0.057
od-0.057
bridge-0.054
sters-0.054
Token
Token ID220
Feature activation-1.15e-02

Pos logit contributions
burn+0.012
coat+0.011
 street+0.011
ety+0.009
 yard+0.009
Neg logit contributions
ement-0.012
od-0.012
izards-0.012
es-0.011
bridge-0.011
Token
Token ID198
Feature activation-1.46e-04

Pos logit contributions
ement+0.024
od+0.024
izards+0.023
bridge+0.023
es+0.022
Neg logit contributions
burn-0.019
coat-0.017
 street-0.017
ety-0.014
 yard-0.014
Token
Token ID198
Feature activation-5.21e-03

Pos logit contributions
ement+0.000
od+0.000
izards+0.000
es+0.000
bridge+0.000
Neg logit contributions
burn-0.000
coat-0.000
 street-0.000
ety-0.000
 yard-0.000
TokenL
Token ID43
Feature activation-1.89e-02

Pos logit contributions
ement+0.009
od+0.009
hell+0.009
es+0.008
izards+0.008
Neg logit contributions
burn-0.011
coat-0.009
 street-0.009
 Dog-0.008
gy-0.008
Tokenily
Token ID813
Feature activation+2.38e-02

Pos logit contributions
ement+0.024
od+0.022
es+0.021
sters+0.020
izards+0.020
Neg logit contributions
burn-0.046
coat-0.044
 street-0.042
ety-0.040
 yard-0.038
Token started
Token ID2067
Feature activation+1.08e-01

Pos logit contributions
burn+0.053
coat+0.048
 street+0.046
ety+0.039
 raining+0.039
Neg logit contributions
ement-0.037
od-0.036
es-0.035
ils-0.034
izards-0.033
Token to
Token ID284
Feature activation+1.44e-02

Pos logit contributions
burn+0.209
coat+0.200
 street+0.183
ety+0.182
 passenger+0.171
Neg logit contributions
od-0.168
es-0.165
ement-0.148
 slices-0.143
ils-0.141
Token scratch
Token ID12692
Feature activation+2.43e-02

Pos logit contributions
burn+0.027
coat+0.024
 street+0.022
ety+0.021
ained+0.020
Neg logit contributions
od-0.024
ement-0.023
 ah-0.022
ts-0.022
es-0.022
Token her
Token ID607
Feature activation+3.44e-02

Pos logit contributions
burn+0.041
coat+0.036
 street+0.035
ety+0.030
 yard+0.028
Neg logit contributions
ement-0.052
od-0.051
izards-0.050
bridge-0.049
es-0.047
Token arm
Token ID3211
Feature activation+1.83e-02

Pos logit contributions
burn+0.069
coat+0.062
 street+0.061
ety+0.052
 yard+0.051
Neg logit contributions
ement-0.063
od-0.060
izards-0.059
es-0.057
bridge-0.055
Token because
Token ID780
Feature activation+3.12e-02

Pos logit contributions
burn+0.036
 street+0.032
coat+0.031
ety+0.028
 yard+0.027
Neg logit contributions
ement-0.033
od-0.032
es-0.031
izards-0.030
hell-0.030
Token,
Token ID11
Feature activation+6.40e-03

Pos logit contributions
burn+0.010
coat+0.010
 street+0.010
ety+0.008
 yard+0.008
Neg logit contributions
ement-0.007
od-0.007
es-0.007
izards-0.007
hell-0.006
Token Tim
Token ID5045
Feature activation+2.41e-02

Pos logit contributions
burn+0.012
coat+0.011
 street+0.011
ety+0.009
 yard+0.009
Neg logit contributions
ement-0.012
od-0.012
izards-0.012
es-0.011
bridge-0.011
Tokenmy
Token ID1820
Feature activation+1.71e-02

Pos logit contributions
burn+0.029
 street+0.029
coat+0.027
 Kathy+0.022
 Dog+0.021
Neg logit contributions
od-0.058
es-0.055
ement-0.053
ils-0.052
hell-0.052
Token's
Token ID338
Feature activation+2.66e-02

Pos logit contributions
burn+0.038
coat+0.036
 street+0.034
 Kathy+0.031
 Dog+0.030
Neg logit contributions
od-0.026
es-0.025
ils-0.022
ement-0.022
bridge-0.021
Token dad
Token ID9955
Feature activation+8.55e-03

Pos logit contributions
burn+0.054
coat+0.047
 street+0.044
ety+0.042
 Kathy+0.042
Neg logit contributions
ement-0.047
od-0.046
bridge-0.041
izards-0.041
sters-0.040
Token started
Token ID2067
Feature activation+1.07e-01

Pos logit contributions
burn+0.018
coat+0.017
 street+0.017
ety+0.014
 yard+0.014
Neg logit contributions
od-0.014
ement-0.014
es-0.013
izards-0.012
bridge-0.012
Token a
Token ID257
Feature activation+5.15e-03

Pos logit contributions
burn+0.199
coat+0.194
 street+0.174
ety+0.166
 Kathy+0.157
Neg logit contributions
od-0.200
es-0.168
ement-0.168
 images-0.160
 symbols-0.159
Token fire
Token ID2046
Feature activation+3.18e-02

Pos logit contributions
burn+0.010
coat+0.009
 street+0.008
ety+0.008
ained+0.008
Neg logit contributions
od-0.009
ement-0.009
hell-0.008
ious-0.008
sters-0.008
Token in
Token ID287
Feature activation+1.05e-02

Pos logit contributions
burn+0.059
coat+0.053
 street+0.052
ety+0.045
 yard+0.043
Neg logit contributions
ement-0.061
od-0.060
izards-0.058
es-0.057
bridge-0.056
Token the
Token ID262
Feature activation-2.42e-02

Pos logit contributions
burn+0.023
coat+0.021
 street+0.020
ety+0.018
 yard+0.017
Neg logit contributions
ement-0.017
od-0.016
es-0.016
izards-0.015
bridge-0.015
Token backyard
Token ID24296
Feature activation+3.40e-02

Pos logit contributions
bridge+0.043
boards+0.041
ement+0.038
als+0.038
 images+0.037
Neg logit contributions
burn-0.044
coat-0.041
ety-0.035
 Kathy-0.034
ido-0.033
Token very
Token ID845
Feature activation-1.99e-03

Pos logit contributions
bridge+0.012
hell+0.011
ement+0.011
izards+0.010
od+0.010
Neg logit contributions
burn-0.027
coat-0.023
 street-0.023
athy-0.022
ety-0.022
Token cold
Token ID4692
Feature activation+4.97e-02

Pos logit contributions
ement+0.004
izards+0.004
od+0.004
hell+0.004
bridge+0.004
Neg logit contributions
burn-0.004
coat-0.003
 street-0.003
 Kathy-0.002
 Dog-0.002
Token.
Token ID13
Feature activation+9.96e-03

Pos logit contributions
burn+0.102
coat+0.092
 street+0.088
ety+0.083
 Kathy+0.081
Neg logit contributions
ement-0.078
od-0.072
boards-0.072
hell-0.071
es-0.070
Token Tim
Token ID5045
Feature activation+2.28e-02

Pos logit contributions
burn+0.025
coat+0.022
 street+0.020
ety+0.019
 wander+0.018
Neg logit contributions
ement-0.014
od-0.013
izards-0.012
es-0.012
boards-0.012
Tokenmy
Token ID1820
Feature activation+2.06e-02

Pos logit contributions
burn+0.027
 street+0.025
coat+0.023
 Dog+0.017
 Kathy+0.017
Neg logit contributions
od-0.055
es-0.054
ement-0.053
izards-0.051
ils-0.051
Token started
Token ID2067
Feature activation+1.07e-01

Pos logit contributions
burn+0.049
coat+0.043
 street+0.042
ety+0.037
 Kathy+0.036
Neg logit contributions
es-0.028
od-0.027
ement-0.026
izards-0.025
ils-0.025
Token to
Token ID284
Feature activation+1.09e-02

Pos logit contributions
burn+0.211
coat+0.199
athy+0.188
 street+0.187
ety+0.186
Neg logit contributions
od-0.148
es-0.145
boards-0.126
 it-0.124
izards-0.123
Token sh
Token ID427
Feature activation-9.45e-03

Pos logit contributions
burn+0.021
coat+0.018
 street+0.017
athy+0.017
ety+0.017
Neg logit contributions
od-0.016
 ah-0.015
ts-0.015
izards-0.015
hell-0.014
Tokeniver
Token ID1428
Feature activation+3.21e-02

Pos logit contributions
ement+0.022
od+0.021
izards+0.020
es+0.020
bridge+0.020
Neg logit contributions
burn-0.014
 street-0.013
coat-0.012
 yard-0.010
ety-0.009
Token because
Token ID780
Feature activation+3.11e-02

Pos logit contributions
burn+0.053
 street+0.047
coat+0.046
 yard+0.037
 raining+0.037
Neg logit contributions
ement-0.070
od-0.069
izards-0.069
bridge-0.065
es-0.065
Token he
Token ID339
Feature activation-8.89e-03

Pos logit contributions
burn+0.078
 street+0.072
coat+0.072
ety+0.063
 yard+0.063
Neg logit contributions
ement-0.041
od-0.039
izards-0.038
es-0.036
bridge-0.035
Token get
Token ID651
Feature activation+3.14e-02

Pos logit contributions
burn+0.021
coat+0.019
 street+0.019
ety+0.015
 yard+0.015
Neg logit contributions
ement-0.027
od-0.027
izards-0.026
es-0.025
bridge-0.025
Token a
Token ID257
Feature activation+1.19e-02

Pos logit contributions
burn+0.057
coat+0.051
 street+0.051
ety+0.042
 yard+0.042
Neg logit contributions
ement-0.062
od-0.061
izards-0.059
es-0.058
bridge-0.056
Token prize
Token ID11596
Feature activation-3.23e-02

Pos logit contributions
burn+0.022
coat+0.020
 street+0.020
ety+0.018
 yard+0.017
Neg logit contributions
ement-0.022
od-0.021
izards-0.020
hell-0.020
es-0.020
Token.
Token ID13
Feature activation+2.19e-02

Pos logit contributions
ement+0.061
od+0.058
izards+0.057
bridge+0.054
es+0.054
Neg logit contributions
burn-0.061
coat-0.056
 street-0.055
 yard-0.046
ety-0.045
Token Everyone
Token ID11075
Feature activation+2.88e-02

Pos logit contributions
burn+0.042
coat+0.037
 street+0.036
ety+0.031
 yard+0.030
Neg logit contributions
ement-0.042
od-0.041
izards-0.040
es-0.039
bridge-0.038
Token started
Token ID2067
Feature activation+1.07e-01

Pos logit contributions
burn+0.051
 street+0.047
coat+0.047
 yard+0.038
ety+0.038
Neg logit contributions
ement-0.056
izards-0.054
od-0.053
bridge-0.052
hell-0.050
Token counting
Token ID14143
Feature activation-5.18e-03

Pos logit contributions
burn+0.160
coat+0.142
 street+0.138
ety+0.116
 yard+0.109
Neg logit contributions
od-0.242
ement-0.239
es-0.232
izards-0.230
bridge-0.216
Token to
Token ID284
Feature activation-1.61e-02

Pos logit contributions
ocket+0.011
izards+0.011
bridge+0.011
ement+0.011
od+0.011
Neg logit contributions
 street-0.007
burn-0.007
coat-0.006
 raining-0.006
 yard-0.005
Token 10
Token ID838
Feature activation-2.64e-02

Pos logit contributions
ement+0.036
izards+0.034
od+0.033
es+0.033
bridge+0.032
Neg logit contributions
burn-0.025
 street-0.024
coat-0.022
 wander-0.019
 yard-0.019
Token out
Token ID503
Feature activation+1.09e-02

Pos logit contributions
ocket+0.052
bridge+0.052
ement+0.051
izards+0.050
vell+0.049
Neg logit contributions
 street-0.039
burn-0.036
coat-0.036
 yard-0.031
 raining-0.030
Token loud
Token ID7812
Feature activation-2.56e-02

Pos logit contributions
 street+0.016
burn+0.016
 raining+0.014
coat+0.014
 yard+0.013
Neg logit contributions
izards-0.021
ocket-0.021
ement-0.020
sters-0.020
olo-0.020
Token
Token ID198
Feature activation+1.58e-03

Pos logit contributions
burn+0.011
coat+0.010
 street+0.010
ety+0.008
 yard+0.008
Neg logit contributions
ement-0.013
od-0.013
izards-0.012
es-0.012
bridge-0.012
TokenTim
Token ID14967
Feature activation+3.17e-02

Pos logit contributions
burn+0.003
coat+0.003
 street+0.003
ety+0.003
 raining+0.002
Neg logit contributions
od-0.002
hell-0.002
bridge-0.002
es-0.002
boards-0.002
Tokenmy
Token ID1820
Feature activation+1.94e-02

Pos logit contributions
burn+0.045
 street+0.041
coat+0.040
 leash+0.031
 Kathy+0.030
Neg logit contributions
es-0.068
od-0.067
ils-0.064
ement-0.061
izards-0.060
Token's
Token ID338
Feature activation+2.80e-02

Pos logit contributions
burn+0.043
coat+0.038
 street+0.036
ety+0.032
ained+0.031
Neg logit contributions
es-0.031
od-0.031
ils-0.028
izards-0.028
ement-0.027
Token mom
Token ID1995
Feature activation+1.97e-02

Pos logit contributions
burn+0.054
coat+0.048
 street+0.047
ety+0.042
 raining+0.038
Neg logit contributions
ement-0.052
od-0.050
izards-0.049
es-0.048
bridge-0.046
Token started
Token ID2067
Feature activation+1.07e-01

Pos logit contributions
burn+0.041
 street+0.037
coat+0.036
ety+0.030
 yard+0.030
Neg logit contributions
od-0.034
ement-0.034
es-0.033
izards-0.031
ils-0.030
Token to
Token ID284
Feature activation+1.61e-02

Pos logit contributions
burn+0.183
coat+0.175
 street+0.163
ety+0.152
 tire+0.135
Neg logit contributions
od-0.206
es-0.200
izards-0.188
ils-0.185
ement-0.183
Token prepare
Token ID8335
Feature activation-7.39e-03

Pos logit contributions
burn+0.028
coat+0.025
 street+0.023
ety+0.023
ained+0.022
Neg logit contributions
od-0.029
 ah-0.028
izards-0.027
olo-0.027
ts-0.026
Token the
Token ID262
Feature activation+1.35e-02

Pos logit contributions
ement+0.015
od+0.015
izards+0.014
bridge+0.014
es+0.014
Neg logit contributions
burn-0.013
 street-0.012
coat-0.011
 yard-0.010
 raining-0.010
Token food
Token ID2057
Feature activation-9.41e-03

Pos logit contributions
burn+0.023
 street+0.020
coat+0.020
 yard+0.017
ety+0.016
Neg logit contributions
ement-0.029
od-0.029
izards-0.028
es-0.027
bridge-0.026
Token for
Token ID329
Feature activation-5.93e-02

Pos logit contributions
ement+0.019
od+0.018
izards+0.017
bridge+0.017
es+0.017
Neg logit contributions
burn-0.017
coat-0.016
 street-0.016
 yard-0.013
ety-0.013
Token to
Token ID284
Feature activation-2.62e-02

Pos logit contributions
burn+0.011
coat+0.010
 street+0.010
ety+0.008
 yard+0.008
Neg logit contributions
ement-0.011
od-0.011
izards-0.011
es-0.010
bridge-0.010
Token make
Token ID787
Feature activation-6.82e-03

Pos logit contributions
ement+0.057
od+0.055
izards+0.054
es+0.053
bridge+0.052
Neg logit contributions
burn-0.043
 street-0.038
coat-0.038
 yard-0.031
ety-0.031
Token breakfast
Token ID12607
Feature activation-3.57e-02

Pos logit contributions
ement+0.013
izards+0.012
bridge+0.012
ocket+0.012
od+0.012
Neg logit contributions
burn-0.012
 street-0.011
coat-0.010
 raining-0.010
 yard-0.010
Token.
Token ID13
Feature activation+5.88e-03

Pos logit contributions
ement+0.074
izards+0.073
od+0.070
ocket+0.067
bridge+0.067
Neg logit contributions
burn-0.061
 street-0.057
coat-0.055
 yard-0.046
 raining-0.043
Token They
Token ID1119
Feature activation+1.49e-02

Pos logit contributions
burn+0.012
coat+0.011
 street+0.011
ety+0.009
 wander+0.009
Neg logit contributions
ement-0.010
od-0.010
izards-0.009
bridge-0.009
es-0.009
Token started
Token ID2067
Feature activation+1.07e-01

Pos logit contributions
burn+0.027
coat+0.024
 street+0.024
ety+0.020
 yard+0.019
Neg logit contributions
ement-0.030
od-0.029
izards-0.029
es-0.028
bridge-0.027
Token to
Token ID284
Feature activation+1.21e-02

Pos logit contributions
burn+0.179
coat+0.169
 street+0.159
ety+0.143
 Kathy+0.125
Neg logit contributions
od-0.210
es-0.207
ement-0.199
izards-0.198
ils-0.194
Token mix
Token ID5022
Feature activation-1.02e-02

Pos logit contributions
burn+0.019
coat+0.016
 street+0.015
ety+0.014
 Dog+0.012
Neg logit contributions
od-0.025
ement-0.025
izards-0.025
bridge-0.024
es-0.024
Token the
Token ID262
Feature activation+1.60e-02

Pos logit contributions
izards+0.021
ocket+0.021
ement+0.021
bridge+0.021
od+0.020
Neg logit contributions
burn-0.015
 street-0.014
coat-0.014
 clean-0.013
 dry-0.012
Token ingredients
Token ID9391
Feature activation-2.01e-02

Pos logit contributions
burn+0.030
 street+0.027
coat+0.027
 yard+0.023
ety+0.022
Neg logit contributions
od-0.031
ement-0.031
izards-0.030
es-0.029
bridge-0.028
Token together
Token ID1978
Feature activation+3.07e-03

Pos logit contributions
ement+0.041
izards+0.041
od+0.039
bridge+0.039
es+0.037
Neg logit contributions
burn-0.035
coat-0.031
 street-0.030
 yard-0.025
ety-0.025
Token to
Token ID284
Feature activation-2.29e-02

Pos logit contributions
burn+0.026
 street+0.022
coat+0.021
 pasture+0.020
 driveway+0.020
Neg logit contributions
od-0.017
es-0.016
izards-0.015
hell-0.015
ement-0.014
Token be
Token ID307
Feature activation-4.44e-03

Pos logit contributions
od+0.047
ement+0.046
izards+0.045
bridge+0.044
es+0.043
Neg logit contributions
burn-0.039
coat-0.035
 street-0.033
ety-0.027
 yard-0.026
Token seen
Token ID1775
Feature activation+6.05e-04

Pos logit contributions
od+0.008
ement+0.008
es+0.008
izards+0.008
bridge+0.007
Neg logit contributions
burn-0.009
 street-0.008
coat-0.008
ety-0.007
 Kathy-0.006
Token.
Token ID13
Feature activation+3.92e-03

Pos logit contributions
burn+0.001
 street+0.001
coat+0.001
ety+0.001
 wander+0.001
Neg logit contributions
ement-0.001
od-0.001
es-0.001
izards-0.001
bridge-0.001
Token Jane
Token ID12091
Feature activation+2.15e-03

Pos logit contributions
 street+0.006
coat+0.005
burn+0.005
 yard+0.005
 raining+0.004
Neg logit contributions
izards-0.009
od-0.008
ement-0.008
es-0.008
 pounds-0.008
Token started
Token ID2067
Feature activation+1.07e-01

Pos logit contributions
burn+0.004
coat+0.004
 street+0.004
 yard+0.003
ety+0.003
Neg logit contributions
ement-0.004
od-0.004
es-0.004
izards-0.004
ils-0.003
Token to
Token ID284
Feature activation+1.11e-02

Pos logit contributions
burn+0.187
coat+0.163
 street+0.154
ety+0.135
 yard+0.127
Neg logit contributions
od-0.219
es-0.207
ement-0.206
izards-0.203
ils-0.186
Token feel
Token ID1254
Feature activation-1.78e-03

Pos logit contributions
burn+0.021
coat+0.018
 street+0.016
ety+0.015
athy+0.014
Neg logit contributions
od-0.021
izards-0.019
ement-0.019
es-0.018
hell-0.018
Token sad
Token ID6507
Feature activation+1.92e-02

Pos logit contributions
ement+0.004
od+0.004
izards+0.004
es+0.004
bridge+0.004
Neg logit contributions
burn-0.003
coat-0.002
 street-0.002
ety-0.002
 yard-0.002
Token.
Token ID13
Feature activation+1.25e-02

Pos logit contributions
burn+0.035
coat+0.031
 street+0.031
ety+0.026
 yard+0.026
Neg logit contributions
ement-0.038
od-0.037
izards-0.036
es-0.035
bridge-0.035
Token
Token ID220
Feature activation-9.93e-03

Pos logit contributions
burn+0.018
 street+0.016
coat+0.016
 yard+0.013
ety+0.013
Neg logit contributions
ement-0.029
od-0.028
izards-0.028
es-0.027
bridge-0.027
Token broke
Token ID6265
Feature activation+1.14e-02

Pos logit contributions
ement+0.062
izards+0.060
od+0.059
bridge+0.056
es+0.055
Neg logit contributions
burn-0.036
coat-0.031
 street-0.030
ety-0.025
 rag-0.023
Token into
Token ID656
Feature activation+3.24e-03

Pos logit contributions
burn+0.023
coat+0.020
 street+0.019
ety+0.017
 raining+0.017
Neg logit contributions
ement-0.022
izards-0.021
od-0.020
bridge-0.020
es-0.019
Token pieces
Token ID5207
Feature activation-1.91e-02

Pos logit contributions
burn+0.007
 street+0.006
coat+0.006
 yard+0.005
 raining+0.005
Neg logit contributions
ement-0.006
izards-0.006
od-0.005
bridge-0.005
hell-0.005
Token.
Token ID13
Feature activation+6.93e-03

Pos logit contributions
ement+0.033
od+0.032
izards+0.031
es+0.030
bridge+0.029
Neg logit contributions
burn-0.040
coat-0.036
 street-0.035
ety-0.030
 yard-0.030
Token Lily
Token ID20037
Feature activation+1.45e-02

Pos logit contributions
burn+0.013
coat+0.011
 street+0.011
ety+0.010
 yard+0.009
Neg logit contributions
ement-0.014
od-0.013
izards-0.013
es-0.013
bridge-0.012
Token started
Token ID2067
Feature activation+1.07e-01

Pos logit contributions
burn+0.028
 street+0.026
coat+0.025
ety+0.022
 yard+0.022
Neg logit contributions
ement-0.027
od-0.026
izards-0.026
bridge-0.025
 pounds-0.023
Token to
Token ID284
Feature activation+1.06e-02

Pos logit contributions
burn+0.185
coat+0.166
 street+0.160
ety+0.132
 yard+0.131
Neg logit contributions
od-0.215
es-0.203
ement-0.199
izards-0.193
hell-0.189
Token weep
Token ID49671
Feature activation-6.59e-03

Pos logit contributions
burn+0.021
coat+0.019
 street+0.018
ety+0.016
ained+0.016
Neg logit contributions
od-0.017
es-0.016
hell-0.016
izards-0.016
ement-0.015
Token because
Token ID780
Feature activation+4.16e-02

Pos logit contributions
ement+0.013
od+0.013
izards+0.013
bridge+0.012
es+0.012
Neg logit contributions
burn-0.012
coat-0.010
 street-0.010
ety-0.009
 yard-0.008
Token she
Token ID673
Feature activation+1.68e-03

Pos logit contributions
burn+0.081
coat+0.073
 street+0.071
ety+0.061
 yard+0.060
Neg logit contributions
ement-0.078
od-0.076
izards-0.074
es-0.072
bridge-0.070
Token really
Token ID1107
Feature activation+9.18e-03

Pos logit contributions
burn+0.003
coat+0.003
 street+0.003
ety+0.003
 yard+0.003
Neg logit contributions
ement-0.003
od-0.003
izards-0.003
bridge-0.003
es-0.003
Token there
Token ID612
Feature activation+8.23e-03

Pos logit contributions
burn+0.047
coat+0.042
 street+0.042
ety+0.035
 yard+0.035
Neg logit contributions
ement-0.048
od-0.047
izards-0.046
es-0.044
bridge-0.044
Token either
Token ID2035
Feature activation-9.64e-03

Pos logit contributions
burn+0.018
coat+0.017
 street+0.017
ety+0.014
 yard+0.014
Neg logit contributions
ement-0.013
od-0.013
izards-0.012
es-0.012
bridge-0.012
Token.
Token ID13
Feature activation+1.11e-02

Pos logit contributions
ement+0.017
od+0.017
izards+0.016
es+0.016
bridge+0.015
Neg logit contributions
burn-0.020
 street-0.018
coat-0.018
ety-0.015
 yard-0.015
Token Tim
Token ID5045
Feature activation+1.75e-02

Pos logit contributions
burn+0.020
 street+0.018
coat+0.018
ety+0.016
 yard+0.016
Neg logit contributions
ement-0.022
od-0.021
izards-0.021
es-0.020
bridge-0.020
Tokenmy
Token ID1820
Feature activation+1.46e-02

Pos logit contributions
burn+0.019
 street+0.017
coat+0.016
 Dog+0.011
 wander+0.010
Neg logit contributions
ement-0.045
od-0.045
es-0.044
izards-0.043
hell-0.042
Token started
Token ID2067
Feature activation+1.07e-01

Pos logit contributions
burn+0.031
coat+0.028
 street+0.028
ety+0.024
 yard+0.023
Neg logit contributions
ement-0.025
od-0.024
izards-0.023
es-0.023
bridge-0.022
Token to
Token ID284
Feature activation+9.38e-03

Pos logit contributions
burn+0.190
coat+0.177
 street+0.169
ety+0.152
 yard+0.142
Neg logit contributions
od-0.193
es-0.193
ement-0.177
izards-0.174
sters-0.164
Token feel
Token ID1254
Feature activation-3.73e-03

Pos logit contributions
burn+0.018
coat+0.017
 street+0.016
ety+0.014
athy+0.014
Neg logit contributions
od-0.015
izards-0.014
es-0.014
hell-0.014
ement-0.014
Token sad
Token ID6507
Feature activation+1.83e-02

Pos logit contributions
ement+0.008
izards+0.008
od+0.008
es+0.008
bridge+0.007
Neg logit contributions
burn-0.006
coat-0.006
 street-0.005
ety-0.004
 yard-0.004
Token.
Token ID13
Feature activation+1.75e-02

Pos logit contributions
burn+0.030
 street+0.026
coat+0.026
 yard+0.021
ety+0.021
Neg logit contributions
ement-0.040
od-0.039
izards-0.038
bridge-0.038
es-0.037
Token
Token ID198
Feature activation+4.73e-03

Pos logit contributions
burn+0.037
coat+0.033
 street+0.032
ety+0.027
 yard+0.027
Neg logit contributions
ement-0.030
od-0.029
izards-0.028
es-0.027
hell-0.026
Token watched
Token ID7342
Feature activation-2.48e-02

Pos logit contributions
ement+0.021
izards+0.020
od+0.020
bridge+0.019
 pounds+0.019
Neg logit contributions
burn-0.018
 street-0.016
coat-0.016
 yard-0.014
ety-0.013
Token the
Token ID262
Feature activation-3.92e-03

Pos logit contributions
izards+0.049
ement+0.049
 pounds+0.048
hell+0.047
sters+0.046
Neg logit contributions
burn-0.040
 street-0.036
coat-0.033
 raining-0.032
 skipping-0.031
Token colorful
Token ID20239
Feature activation-1.55e-02

Pos logit contributions
es+0.008
izards+0.008
ement+0.008
od+0.008
 pounds+0.008
Neg logit contributions
 street-0.006
burn-0.006
coat-0.005
 yard-0.005
 wander-0.005
Token lights
Token ID7588
Feature activation+1.85e-02

Pos logit contributions
izards+0.032
ement+0.032
od+0.031
es+0.031
olo+0.030
Neg logit contributions
burn-0.025
 street-0.025
coat-0.022
 yard-0.020
 wander-0.019
Token in
Token ID287
Feature activation-8.64e-03

Pos logit contributions
burn+0.033
coat+0.030
 street+0.030
ety+0.024
 yard+0.024
Neg logit contributions
ement-0.037
od-0.036
izards-0.036
es-0.034
bridge-0.033
Token amaz
Token ID40642
Feature activation-1.57e-01

Pos logit contributions
ement+0.017
izards+0.017
od+0.017
es+0.016
bridge+0.016
Neg logit contributions
burn-0.015
 street-0.014
coat-0.013
 yard-0.012
 raining-0.011
Tokenement
Token ID972
Feature activation-5.68e-02

Pos logit contributions
izards+0.125
olo+0.101
od+0.099
es+0.097
 kil+0.094
Neg logit contributions
burn-0.418
 street-0.403
coat-0.403
 automobile-0.385
 yard-0.378
Token,
Token ID11
Feature activation-1.94e-02

Pos logit contributions
ement+0.111
izards+0.110
od+0.107
bridge+0.105
es+0.102
Neg logit contributions
burn-0.101
 street-0.090
coat-0.089
ety-0.073
 yard-0.073
Token feeling
Token ID4203
Feature activation-3.57e-02

Pos logit contributions
ement+0.041
izards+0.040
od+0.040
es+0.038
bridge+0.038
Neg logit contributions
burn-0.032
 street-0.029
coat-0.028
 yard-0.023
ety-0.023
Token truly
Token ID4988
Feature activation-3.27e-02

Pos logit contributions
ement+0.072
izards+0.070
od+0.070
es+0.067
 pounds+0.066
Neg logit contributions
burn-0.059
 street-0.055
coat-0.053
 raining-0.045
 yard-0.044
Token lucky
Token ID9670
Feature activation-4.66e-03

Pos logit contributions
ement+0.066
izards+0.065
od+0.065
es+0.062
bridge+0.061
Neg logit contributions
burn-0.055
 street-0.051
coat-0.049
 yard-0.042
 raining-0.041
Token baby
Token ID5156
Feature activation+4.76e-03

Pos logit contributions
burn+0.023
 street+0.021
coat+0.020
 yard+0.017
ety+0.017
Neg logit contributions
ement-0.027
od-0.026
izards-0.026
es-0.025
bridge-0.024
Token le
Token ID443
Feature activation+1.41e-02

Pos logit contributions
burn+0.008
coat+0.007
 street+0.007
ety+0.006
 yard+0.006
Neg logit contributions
ement-0.010
od-0.010
izards-0.010
bridge-0.009
es-0.009
Tokenopard
Token ID15478
Feature activation-1.37e-02

Pos logit contributions
burn+0.024
coat+0.021
 street+0.020
ety+0.018
 yard+0.017
Neg logit contributions
ement-0.030
od-0.029
izards-0.028
bridge-0.027
es-0.027
Token watched
Token ID7342
Feature activation-3.38e-02

Pos logit contributions
ement+0.027
izards+0.026
od+0.026
bridge+0.025
 pounds+0.025
Neg logit contributions
burn-0.024
coat-0.022
 street-0.021
ety-0.018
gy-0.018
Token in
Token ID287
Feature activation-3.77e-03

Pos logit contributions
ement+0.066
izards+0.065
bridge+0.064
od+0.063
ils+0.062
Neg logit contributions
burn-0.058
 street-0.051
coat-0.048
 Dog-0.046
 raining-0.044
Token amaz
Token ID40642
Feature activation-1.54e-01

Pos logit contributions
od+0.006
ement+0.006
izards+0.006
bridge+0.006
es+0.006
Neg logit contributions
burn-0.008
 street-0.007
coat-0.007
 yard-0.006
 wander-0.006
Tokenement
Token ID972
Feature activation-5.31e-02

Pos logit contributions
izards+0.100
od+0.099
 kilograms+0.091
hell+0.089
 kil+0.088
Neg logit contributions
burn-0.394
coat-0.362
 street-0.361
 automobile-0.354
 yard-0.343
Token as
Token ID355
Feature activation+3.00e-02

Pos logit contributions
ement+0.110
bridge+0.108
izards+0.108
od+0.106
hell+0.102
Neg logit contributions
burn-0.086
 street-0.075
coat-0.073
 raining-0.062
ety-0.062
Token the
Token ID262
Feature activation-2.50e-03

Pos logit contributions
burn+0.056
 street+0.052
coat+0.049
 Dog+0.044
 raining+0.043
Neg logit contributions
ement-0.057
od-0.053
izards-0.052
ils-0.052
bridge-0.051
Token lion
Token ID18744
Feature activation-2.78e-02

Pos logit contributions
ement+0.005
od+0.005
izards+0.005
es+0.005
bridge+0.004
Neg logit contributions
burn-0.005
 street-0.004
coat-0.004
 yard-0.003
ety-0.003
Token flex
Token ID7059
Feature activation-1.18e-02

Pos logit contributions
ement+0.058
od+0.056
izards+0.056
bridge+0.053
 pounds+0.053
Neg logit contributions
burn-0.045
coat-0.040
 street-0.040
 wander-0.033
 Dog-0.033
Token stared
Token ID18484
Feature activation+2.38e-03

Pos logit contributions
ement+0.012
od+0.011
izards+0.011
bridge+0.011
es+0.011
Neg logit contributions
burn-0.011
 street-0.010
coat-0.010
ety-0.009
 yard-0.008
Token at
Token ID379
Feature activation-2.64e-02

Pos logit contributions
burn+0.004
coat+0.004
 street+0.003
 raining+0.003
 yard+0.003
Neg logit contributions
izards-0.005
ement-0.004
od-0.004
ils-0.004
es-0.004
Token the
Token ID262
Feature activation-3.56e-03

Pos logit contributions
izards+0.051
od+0.049
ement+0.047
bridge+0.047
sters+0.047
Neg logit contributions
burn-0.044
 street-0.042
 yard-0.037
 tire-0.037
 automobile-0.036
Token pie
Token ID2508
Feature activation-3.20e-02

Pos logit contributions
izards+0.008
es+0.008
od+0.007
ement+0.007
ils+0.007
Neg logit contributions
 street-0.006
burn-0.005
 yard-0.005
coat-0.005
ety-0.004
Token in
Token ID287
Feature activation-9.44e-03

Pos logit contributions
izards+0.060
ement+0.060
od+0.060
bridge+0.056
es+0.056
Neg logit contributions
burn-0.059
 street-0.054
coat-0.053
 yard-0.045
 raining-0.043
Token amaz
Token ID40642
Feature activation-1.54e-01

Pos logit contributions
izards+0.020
ement+0.019
od+0.019
es+0.019
sters+0.018
Neg logit contributions
burn-0.016
 street-0.015
coat-0.013
 yard-0.013
 wander-0.012
Tokenement
Token ID972
Feature activation-4.73e-02

Pos logit contributions
izards+0.126
es+0.107
od+0.101
sters+0.096
olo+0.094
Neg logit contributions
burn-0.399
coat-0.380
 street-0.375
 automobile-0.366
 yard-0.361
Token.
Token ID13
Feature activation-3.68e-03

Pos logit contributions
izards+0.091
ement+0.091
od+0.088
bridge+0.087
ils+0.086
Neg logit contributions
burn-0.083
 street-0.074
coat-0.073
 raining-0.061
ety-0.061
Token He
Token ID679
Feature activation-1.80e-02

Pos logit contributions
ement+0.007
izards+0.007
od+0.007
ils+0.007
es+0.007
Neg logit contributions
burn-0.006
 street-0.006
coat-0.006
 yard-0.005
 Dog-0.005
Token just
Token ID655
Feature activation-2.83e-03

Pos logit contributions
ement+0.038
izards+0.037
od+0.036
bridge+0.036
hell+0.034
Neg logit contributions
burn-0.028
 street-0.026
coat-0.026
ety-0.022
 yard-0.021
Token couldn
Token ID3521
Feature activation-3.16e-02

Pos logit contributions
ement+0.005
od+0.005
izards+0.005
es+0.005
bridge+0.005
Neg logit contributions
burn-0.005
coat-0.005
 street-0.005
ety-0.004
 yard-0.004
Token gazed
Token ID50255
Feature activation+2.69e-03

Pos logit contributions
burn+0.112
coat+0.101
 street+0.100
ety+0.086
 yard+0.085
Neg logit contributions
ement-0.085
od-0.084
izards-0.080
es-0.079
bridge-0.076
Token at
Token ID379
Feature activation-2.89e-02

Pos logit contributions
burn+0.005
 street+0.005
coat+0.005
 raining+0.004
 yard+0.004
Neg logit contributions
ement-0.005
od-0.005
izards-0.005
bridge-0.005
es-0.004
Token the
Token ID262
Feature activation-6.53e-03

Pos logit contributions
od+0.047
ement+0.047
bridge+0.047
izards+0.046
boards+0.044
Neg logit contributions
burn-0.060
 street-0.056
coat-0.052
 yard-0.049
 rag-0.048
Token butterfly
Token ID35113
Feature activation-2.01e-02

Pos logit contributions
ement+0.012
od+0.011
izards+0.011
es+0.011
bridge+0.011
Neg logit contributions
burn-0.013
 street-0.012
coat-0.012
 yard-0.010
ety-0.010
Token in
Token ID287
Feature activation-7.55e-03

Pos logit contributions
ement+0.042
od+0.040
izards+0.040
bridge+0.038
es+0.038
Neg logit contributions
burn-0.035
 street-0.031
coat-0.030
 yard-0.025
ety-0.025
Token amaz
Token ID40642
Feature activation-1.54e-01

Pos logit contributions
ement+0.013
izards+0.013
od+0.013
es+0.012
bridge+0.012
Neg logit contributions
burn-0.015
 street-0.014
coat-0.013
 yard-0.012
 raining-0.012
Tokenement
Token ID972
Feature activation-5.19e-02

Pos logit contributions
izards+0.102
od+0.088
 kilograms+0.084
es+0.082
 kil+0.080
Neg logit contributions
burn-0.428
coat-0.407
 street-0.403
 automobile-0.389
 yard-0.389
Token.
Token ID13
Feature activation-5.77e-03

Pos logit contributions
izards+0.101
ement+0.101
bridge+0.100
od+0.098
hell+0.095
Neg logit contributions
burn-0.090
 street-0.080
coat-0.078
 raining-0.066
ety-0.066
Token
Token ID198
Feature activation-6.43e-03

Pos logit contributions
ement+0.012
od+0.011
izards+0.011
bridge+0.011
es+0.011
Neg logit contributions
burn-0.010
 street-0.009
coat-0.009
ety-0.008
 yard-0.008
Token
Token ID198
Feature activation-9.78e-03

Pos logit contributions
ement+0.013
od+0.012
izards+0.012
es+0.012
bridge+0.011
Neg logit contributions
burn-0.012
coat-0.011
 street-0.011
ety-0.009
 yard-0.009
TokenBut
Token ID1537
Feature activation-1.88e-02

Pos logit contributions
ement+0.018
od+0.018
izards+0.017
es+0.017
bridge+0.017
Neg logit contributions
burn-0.019
coat-0.017
 street-0.017
ety-0.014
 yard-0.014
Token She
Token ID1375
Feature activation-1.67e-02

Pos logit contributions
ement+0.005
od+0.005
izards+0.005
es+0.005
bridge+0.005
Neg logit contributions
burn-0.005
coat-0.005
 street-0.004
ety-0.004
 yard-0.004
Token opened
Token ID4721
Feature activation-1.62e-02

Pos logit contributions
ement+0.033
od+0.032
izards+0.032
es+0.030
bridge+0.030
Neg logit contributions
burn-0.030
 street-0.028
coat-0.027
 yard-0.023
 wander-0.023
Token her
Token ID607
Feature activation-2.47e-02

Pos logit contributions
izards+0.035
ement+0.035
od+0.034
hell+0.034
 pounds+0.034
Neg logit contributions
burn-0.025
 street-0.022
coat-0.021
 yard-0.018
 raining-0.017
Token mouth
Token ID5422
Feature activation-3.31e-02

Pos logit contributions
od+0.032
izards+0.032
ement+0.031
bridge+0.029
es+0.029
Neg logit contributions
burn-0.059
 street-0.058
coat-0.055
 yard-0.052
 wander-0.049
Token in
Token ID287
Feature activation-1.94e-02

Pos logit contributions
ement+0.067
od+0.065
izards+0.063
es+0.062
bridge+0.061
Neg logit contributions
burn-0.059
coat-0.052
 street-0.052
ety-0.043
 yard-0.042
Token amaz
Token ID40642
Feature activation-1.53e-01

Pos logit contributions
ement+0.041
od+0.040
izards+0.040
es+0.039
bridge+0.038
Neg logit contributions
burn-0.033
 street-0.029
coat-0.029
 yard-0.023
ety-0.023
Tokenement
Token ID972
Feature activation-5.17e-02

Pos logit contributions
izards+0.102
od+0.083
es+0.078
 kilograms+0.078
olo+0.077
Neg logit contributions
burn-0.432
coat-0.418
 street-0.405
 automobile-0.389
 yard-0.383
Token.
Token ID13
Feature activation-6.99e-03

Pos logit contributions
ement+0.098
od+0.095
izards+0.095
bridge+0.091
es+0.090
Neg logit contributions
burn-0.097
coat-0.087
 street-0.087
ety-0.073
 yard-0.072
Token She
Token ID1375
Feature activation-2.17e-02

Pos logit contributions
ement+0.012
od+0.011
izards+0.011
es+0.011
bridge+0.010
Neg logit contributions
burn-0.015
coat-0.014
 street-0.013
ety-0.012
 yard-0.011
Token had
Token ID550
Feature activation-1.12e-02

Pos logit contributions
ement+0.043
izards+0.042
od+0.041
bridge+0.040
hell+0.039
Neg logit contributions
burn-0.037
 street-0.035
coat-0.034
 yard-0.029
 wander-0.028
Token never
Token ID1239
Feature activation+1.30e-02

Pos logit contributions
ement+0.025
izards+0.023
od+0.023
es+0.022
 pounds+0.022
Neg logit contributions
burn-0.018
 street-0.016
coat-0.016
 yard-0.013
ety-0.013
Token at
Token ID379
Feature activation-1.58e-02

Pos logit contributions
od+0.017
izards+0.017
ement+0.017
es+0.017
bridge+0.017
Neg logit contributions
burn-0.016
 street-0.015
coat-0.014
 yard-0.013
 raining-0.012
Token the
Token ID262
Feature activation+4.52e-03

Pos logit contributions
ement+0.029
od+0.029
izards+0.028
es+0.027
bridge+0.027
Neg logit contributions
burn-0.031
coat-0.027
 street-0.027
ety-0.023
 yard-0.023
Token red
Token ID2266
Feature activation+9.45e-04

Pos logit contributions
 street+0.006
burn+0.006
coat+0.006
 yard+0.005
 raining+0.005
Neg logit contributions
izards-0.010
ement-0.010
es-0.010
od-0.010
ils-0.010
Token blocks
Token ID7021
Feature activation+1.23e-02

Pos logit contributions
 street+0.001
burn+0.001
coat+0.001
 yard+0.001
 raining+0.001
Neg logit contributions
izards-0.002
ement-0.002
olo-0.002
ils-0.002
ocket-0.002
Token in
Token ID287
Feature activation-7.61e-04

Pos logit contributions
burn+0.018
 street+0.017
coat+0.016
 yard+0.013
ety+0.012
Neg logit contributions
izards-0.027
od-0.027
ement-0.027
es-0.025
bridge-0.025
Token amaz
Token ID40642
Feature activation-1.52e-01

Pos logit contributions
ement+0.002
izards+0.002
od+0.002
es+0.001
bridge+0.001
Neg logit contributions
burn-0.001
 street-0.001
coat-0.001
 yard-0.001
 raining-0.001
Tokenement
Token ID972
Feature activation-5.00e-02

Pos logit contributions
izards+0.113
od+0.091
es+0.088
 kilograms+0.083
keys+0.082
Neg logit contributions
burn-0.406
coat-0.399
 street-0.392
 yard-0.378
 automobile-0.376
Token.
Token ID13
Feature activation-2.45e-03

Pos logit contributions
ement+0.095
izards+0.093
od+0.092
bridge+0.089
es+0.087
Neg logit contributions
burn-0.092
coat-0.082
 street-0.082
ety-0.069
 yard-0.068
Token He
Token ID679
Feature activation-2.54e-02

Pos logit contributions
ement+0.004
od+0.004
izards+0.004
es+0.004
bridge+0.004
Neg logit contributions
burn-0.005
coat-0.005
 street-0.005
ety-0.004
 yard-0.004
Token couldn
Token ID3521
Feature activation-3.33e-02

Pos logit contributions
izards+0.053
ement+0.053
bridge+0.050
od+0.049
hell+0.049
Neg logit contributions
 street-0.037
burn-0.037
coat-0.034
 yard-0.031
ety-0.030
Token't
Token ID470
Feature activation+3.51e-02

Pos logit contributions
ement+0.058
od+0.056
izards+0.055
es+0.053
bridge+0.052
Neg logit contributions
burn-0.068
coat-0.062
 street-0.061
ety-0.052
 yard-0.052
Token watch
Token ID2342
Feature activation-1.90e-02

Pos logit contributions
ement+0.015
od+0.015
izards+0.015
es+0.014
bridge+0.014
Neg logit contributions
burn-0.010
 street-0.009
coat-0.009
ety-0.007
 yard-0.007
Token the
Token ID262
Feature activation-8.43e-03

Pos logit contributions
ement+0.039
izards+0.037
ocket+0.036
bridge+0.035
od+0.035
Neg logit contributions
burn-0.033
 street-0.030
coat-0.027
 Dog-0.026
 raining-0.026
Token big
Token ID1263
Feature activation-8.90e-03

Pos logit contributions
ement+0.017
od+0.016
izards+0.016
es+0.016
bridge+0.015
Neg logit contributions
burn-0.016
 street-0.015
coat-0.014
 yard-0.012
ety-0.012
Token elephant
Token ID20950
Feature activation-1.51e-02

Pos logit contributions
ement+0.019
od+0.019
izards+0.019
es+0.018
bridge+0.018
Neg logit contributions
burn-0.015
 street-0.013
coat-0.013
 yard-0.011
ety-0.010
Token in
Token ID287
Feature activation-4.40e-03

Pos logit contributions
ement+0.031
od+0.030
izards+0.030
bridge+0.028
es+0.028
Neg logit contributions
burn-0.026
 street-0.024
coat-0.023
 wander-0.019
 yard-0.019
Token amaz
Token ID40642
Feature activation-1.52e-01

Pos logit contributions
ement+0.009
od+0.009
izards+0.009
sters+0.009
es+0.009
Neg logit contributions
burn-0.007
 street-0.007
coat-0.006
 yard-0.006
 raining-0.006
Tokenement
Token ID972
Feature activation-4.38e-02

Pos logit contributions
izards+0.090
od+0.081
es+0.080
 ah+0.071
ocket+0.069
Neg logit contributions
burn-0.440
 street-0.413
coat-0.411
 yard-0.395
 automobile-0.390
Token.
Token ID13
Feature activation-3.87e-03

Pos logit contributions
ement+0.084
izards+0.081
od+0.080
bridge+0.078
hell+0.076
Neg logit contributions
burn-0.081
 street-0.072
coat-0.071
ety-0.060
 raining-0.060
Token
Token ID198
Feature activation-4.33e-03

Pos logit contributions
ement+0.008
od+0.007
izards+0.007
es+0.007
bridge+0.007
Neg logit contributions
burn-0.007
 street-0.006
coat-0.006
 yard-0.005
ety-0.005
Token
Token ID198
Feature activation-8.14e-03

Pos logit contributions
ement+0.009
od+0.009
izards+0.009
bridge+0.009
es+0.008
Neg logit contributions
burn-0.007
 street-0.006
coat-0.006
 yard-0.005
ety-0.005
TokenThe
Token ID464
Feature activation+1.25e-02

Pos logit contributions
ement+0.021
od+0.021
izards+0.020
es+0.020
bridge+0.020
Neg logit contributions
burn-0.010
 street-0.008
coat-0.008
ety-0.006
 yard-0.006
Token her
Token ID607
Feature activation-2.23e-02

Pos logit contributions
ement+0.141
od+0.132
izards+0.132
bridge+0.128
es+0.128
Neg logit contributions
burn-0.101
 street-0.092
coat-0.086
 wander-0.074
 yard-0.073
Token doll
Token ID3654
Feature activation-6.15e-03

Pos logit contributions
ement+0.046
od+0.045
izards+0.044
es+0.043
bridge+0.042
Neg logit contributions
burn-0.039
coat-0.035
 street-0.035
ety-0.029
 yard-0.028
Token and
Token ID290
Feature activation-2.88e-02

Pos logit contributions
ement+0.012
od+0.012
izards+0.012
es+0.012
bridge+0.011
Neg logit contributions
burn-0.011
coat-0.010
 street-0.010
ety-0.008
 yard-0.008
Token watched
Token ID7342
Feature activation-3.70e-02

Pos logit contributions
ement+0.057
od+0.055
izards+0.054
es+0.051
bridge+0.051
Neg logit contributions
burn-0.053
coat-0.047
 street-0.047
ety-0.039
 yard-0.039
Token in
Token ID287
Feature activation-4.94e-03

Pos logit contributions
izards+0.069
ement+0.068
sters+0.065
od+0.065
bridge+0.064
Neg logit contributions
burn-0.066
 street-0.058
coat-0.056
 raining-0.051
 visit-0.050
Token amaz
Token ID40642
Feature activation-1.52e-01

Pos logit contributions
od+0.008
izards+0.008
ement+0.008
sters+0.008
es+0.007
Neg logit contributions
burn-0.010
 street-0.010
coat-0.009
 yard-0.009
 wander-0.008
Tokenement
Token ID972
Feature activation-4.74e-02

Pos logit contributions
izards+0.116
 kilograms+0.103
 kil+0.100
od+0.098
hell+0.098
Neg logit contributions
burn-0.386
 automobile-0.355
coat-0.352
 street-0.348
 neighborhood-0.333
Token as
Token ID355
Feature activation+2.76e-02

Pos logit contributions
ement+0.092
izards+0.089
bridge+0.088
od+0.088
hell+0.085
Neg logit contributions
burn-0.084
 street-0.075
coat-0.074
ety-0.062
 raining-0.062
Token it
Token ID340
Feature activation-4.40e-02

Pos logit contributions
burn+0.051
 street+0.048
coat+0.046
 raining+0.040
 yard+0.039
Neg logit contributions
ement-0.052
od-0.048
izards-0.048
bridge-0.046
ils-0.046
Token slowly
Token ID6364
Feature activation-1.68e-03

Pos logit contributions
ement+0.101
od+0.098
izards+0.097
 pounds+0.096
hell+0.094
Neg logit contributions
burn-0.063
coat-0.056
 street-0.056
 wander-0.045
 yard-0.044
Token flew
Token ID13112
Feature activation+2.29e-02

Pos logit contributions
ement+0.003
od+0.003
izards+0.003
es+0.003
bridge+0.003
Neg logit contributions
burn-0.003
coat-0.003
 street-0.003
ety-0.002
 yard-0.002
Token just
Token ID655
Feature activation-1.04e-02

Pos logit contributions
ement+0.053
izards+0.051
od+0.050
bridge+0.050
 pounds+0.048
Neg logit contributions
burn-0.052
coat-0.047
 street-0.046
ety-0.041
 yard-0.039
Token stared
Token ID18484
Feature activation+6.72e-03

Pos logit contributions
ement+0.019
izards+0.019
od+0.019
bridge+0.019
es+0.018
Neg logit contributions
burn-0.019
coat-0.018
 street-0.017
ety-0.015
 raining-0.014
Token at
Token ID379
Feature activation-2.46e-02

Pos logit contributions
burn+0.014
coat+0.012
 street+0.012
ety+0.010
 raining+0.010
Neg logit contributions
ement-0.011
od-0.011
izards-0.011
es-0.011
bridge-0.011
Token him
Token ID683
Feature activation-8.33e-03

Pos logit contributions
ement+0.046
od+0.045
izards+0.045
bridge+0.045
sters+0.043
Neg logit contributions
burn-0.044
 street-0.039
coat-0.039
 Dog-0.033
 yard-0.033
Token in
Token ID287
Feature activation-2.36e-04

Pos logit contributions
ement+0.016
izards+0.016
od+0.016
bridge+0.015
ils+0.014
Neg logit contributions
burn-0.015
coat-0.013
 street-0.013
 raining-0.011
 yard-0.011
Token amaz
Token ID40642
Feature activation-1.52e-01

Pos logit contributions
ement+0.000
od+0.000
izards+0.000
es+0.000
bridge+0.000
Neg logit contributions
burn-0.000
 street-0.000
coat-0.000
 yard-0.000
 raining-0.000
Tokenement
Token ID972
Feature activation-4.84e-02

Pos logit contributions
izards+0.104
es+0.089
od+0.089
 kilograms+0.078
hell+0.077
Neg logit contributions
burn-0.419
coat-0.397
 street-0.385
 automobile-0.374
 yard-0.363
Token.
Token ID13
Feature activation-4.26e-03

Pos logit contributions
ement+0.092
izards+0.091
od+0.089
bridge+0.088
es+0.085
Neg logit contributions
burn-0.087
coat-0.077
 street-0.077
ety-0.065
 raining-0.064
Token So
Token ID1406
Feature activation+2.25e-02

Pos logit contributions
ement+0.008
od+0.008
izards+0.008
es+0.008
bridge+0.008
Neg logit contributions
burn-0.008
coat-0.007
 street-0.007
ety-0.006
 yard-0.006
Token,
Token ID11
Feature activation-2.95e-03

Pos logit contributions
burn+0.035
 street+0.033
coat+0.030
 Dog+0.027
 wander+0.027
Neg logit contributions
ement-0.048
izards-0.047
od-0.046
hell-0.046
bridge-0.045
Token he
Token ID339
Feature activation-1.93e-02

Pos logit contributions
ement+0.006
izards+0.006
od+0.006
hell+0.005
bridge+0.005
Neg logit contributions
burn-0.005
 street-0.005
coat-0.005
 Dog-0.004
 wander-0.004
Token looked
Token ID3114
Feature activation-1.15e-02

Pos logit contributions
burn+0.003
 street+0.003
coat+0.003
 yard+0.003
ety+0.003
Neg logit contributions
ement-0.003
od-0.003
izards-0.003
bridge-0.003
es-0.003
Token at
Token ID379
Feature activation-2.35e-02

Pos logit contributions
ement+0.023
od+0.022
izards+0.022
es+0.022
bridge+0.021
Neg logit contributions
burn-0.020
 street-0.019
coat-0.018
 yard-0.016
 raining-0.015
Token the
Token ID262
Feature activation-4.95e-03

Pos logit contributions
ement+0.049
bridge+0.048
izards+0.048
od+0.048
es+0.045
Neg logit contributions
burn-0.038
 street-0.036
coat-0.032
 yard-0.031
ety-0.029
Token rainbow
Token ID27223
Feature activation+1.60e-04

Pos logit contributions
es+0.011
izards+0.010
ement+0.010
od+0.010
ils+0.010
Neg logit contributions
 street-0.008
burn-0.007
 yard-0.007
coat-0.007
 raining-0.006
Token in
Token ID287
Feature activation-8.38e-03

Pos logit contributions
burn+0.000
 street+0.000
coat+0.000
 yard+0.000
 raining+0.000
Neg logit contributions
ement-0.000
izards-0.000
od-0.000
bridge-0.000
es-0.000
Token amaz
Token ID40642
Feature activation-1.52e-01

Pos logit contributions
ement+0.016
od+0.016
izards+0.016
es+0.015
bridge+0.015
Neg logit contributions
burn-0.015
 street-0.014
coat-0.014
 yard-0.012
ety-0.011
Tokenement
Token ID972
Feature activation-4.93e-02

Pos logit contributions
izards+0.110
od+0.095
es+0.094
 kilograms+0.085
 ah+0.081
Neg logit contributions
burn-0.394
 street-0.391
coat-0.379
 yard-0.378
 automobile-0.368
Token and
Token ID290
Feature activation-7.09e-03

Pos logit contributions
ement+0.097
izards+0.096
od+0.094
bridge+0.093
hell+0.091
Neg logit contributions
burn-0.086
 street-0.077
coat-0.075
 yard-0.064
 raining-0.064
Token laughed
Token ID13818
Feature activation-1.42e-02

Pos logit contributions
ement+0.015
bridge+0.015
izards+0.015
hell+0.014
od+0.014
Neg logit contributions
 street-0.011
burn-0.011
coat-0.010
 yard-0.009
 raining-0.009
Token with
Token ID351
Feature activation-1.88e-02

Pos logit contributions
izards+0.032
ement+0.032
 ounces+0.031
ocket+0.031
 pounds+0.031
Neg logit contributions
burn-0.019
 street-0.016
coat-0.016
 raining-0.016
 sunny-0.014
Token joy
Token ID8716
Feature activation-1.97e-02

Pos logit contributions
boards+0.033
izards+0.032
 pounds+0.032
ement+0.032
sters+0.032
Neg logit contributions
 street-0.035
burn-0.034
 yard-0.032
 Dog-0.030
 play-0.029
Token looked
Token ID3114
Feature activation-1.15e-02

Pos logit contributions
burn+0.003
 street+0.003
coat+0.003
 yard+0.003
ety+0.003
Neg logit contributions
ement-0.003
od-0.003
izards-0.003
bridge-0.003
es-0.003
Token at
Token ID379
Feature activation-2.35e-02

Pos logit contributions
ement+0.023
od+0.022
izards+0.022
es+0.022
bridge+0.021
Neg logit contributions
burn-0.020
 street-0.019
coat-0.018
 yard-0.016
 raining-0.015
Token the
Token ID262
Feature activation-4.95e-03

Pos logit contributions
ement+0.049
bridge+0.048
izards+0.048
od+0.048
es+0.045
Neg logit contributions
burn-0.038
 street-0.036
coat-0.032
 yard-0.031
ety-0.029
Token rainbow
Token ID27223
Feature activation+1.60e-04

Pos logit contributions
es+0.011
izards+0.010
ement+0.010
od+0.010
ils+0.010
Neg logit contributions
 street-0.008
burn-0.007
 yard-0.007
coat-0.007
 raining-0.006
Token in
Token ID287
Feature activation-8.38e-03

Pos logit contributions
burn+0.000
 street+0.000
coat+0.000
 yard+0.000
 raining+0.000
Neg logit contributions
ement-0.000
izards-0.000
od-0.000
bridge-0.000
es-0.000
Token amaz
Token ID40642
Feature activation-1.52e-01

Pos logit contributions
ement+0.016
od+0.016
izards+0.016
es+0.015
bridge+0.015
Neg logit contributions
burn-0.015
 street-0.014
coat-0.014
 yard-0.012
ety-0.011
Tokenement
Token ID972
Feature activation-4.93e-02

Pos logit contributions
izards+0.110
od+0.095
es+0.094
 kilograms+0.085
 ah+0.081
Neg logit contributions
burn-0.394
 street-0.391
coat-0.379
 yard-0.378
 automobile-0.368
Token and
Token ID290
Feature activation-7.09e-03

Pos logit contributions
ement+0.097
izards+0.096
od+0.094
bridge+0.093
hell+0.091
Neg logit contributions
burn-0.086
 street-0.077
coat-0.075
 yard-0.064
 raining-0.064
Token laughed
Token ID13818
Feature activation-1.42e-02

Pos logit contributions
ement+0.015
bridge+0.015
izards+0.015
hell+0.014
od+0.014
Neg logit contributions
 street-0.011
burn-0.011
coat-0.010
 yard-0.009
 raining-0.009
Token with
Token ID351
Feature activation-1.88e-02

Pos logit contributions
izards+0.032
ement+0.032
 ounces+0.031
ocket+0.031
 pounds+0.031
Neg logit contributions
burn-0.019
 street-0.016
coat-0.016
 raining-0.016
 sunny-0.014
Token joy
Token ID8716
Feature activation-1.97e-02

Pos logit contributions
boards+0.033
izards+0.032
 pounds+0.032
ement+0.032
sters+0.032
Neg logit contributions
 street-0.035
burn-0.034
 yard-0.032
 Dog-0.030
 play-0.029
Token line
Token ID1627
Feature activation-4.33e-02

Pos logit contributions
burn+0.016
coat+0.014
 street+0.014
ety+0.012
 yard+0.012
Neg logit contributions
ement-0.016
od-0.015
izards-0.015
es-0.014
bridge-0.014
Token.
Token ID13
Feature activation-5.35e-03

Pos logit contributions
ement+0.073
od+0.071
izards+0.069
es+0.067
bridge+0.065
Neg logit contributions
burn-0.092
coat-0.082
 street-0.082
ety-0.071
 yard-0.070
Token Billy
Token ID15890
Feature activation-4.42e-03

Pos logit contributions
ement+0.009
od+0.009
izards+0.009
es+0.008
bridge+0.008
Neg logit contributions
burn-0.011
coat-0.010
 street-0.010
ety-0.009
 yard-0.008
Token watched
Token ID7342
Feature activation-2.78e-02

Pos logit contributions
ement+0.008
od+0.008
es+0.007
izards+0.007
bridge+0.007
Neg logit contributions
burn-0.009
coat-0.008
 street-0.008
ety-0.007
 yard-0.007
Token in
Token ID287
Feature activation+2.21e-03

Pos logit contributions
ement+0.054
izards+0.054
od+0.052
ocket+0.050
es+0.049
Neg logit contributions
burn-0.050
 street-0.044
coat-0.043
 raining-0.037
 Dog-0.037
Token amaz
Token ID40642
Feature activation-1.51e-01

Pos logit contributions
burn+0.005
 street+0.005
coat+0.005
 yard+0.004
 raining+0.004
Neg logit contributions
od-0.003
izards-0.003
ement-0.003
es-0.003
bridge-0.003
Tokenement
Token ID972
Feature activation-4.53e-02

Pos logit contributions
izards+0.114
ocket+0.105
od+0.097
hell+0.096
es+0.092
Neg logit contributions
burn-0.380
 automobile-0.358
coat-0.356
 street-0.356
 yard-0.336
Token as
Token ID355
Feature activation+3.01e-02

Pos logit contributions
ement+0.089
izards+0.088
od+0.086
bridge+0.086
hell+0.082
Neg logit contributions
burn-0.079
 street-0.070
coat-0.069
ety-0.058
 raining-0.058
Token the
Token ID262
Feature activation+7.02e-03

Pos logit contributions
burn+0.061
 street+0.055
coat+0.054
 yard+0.046
ety+0.046
Neg logit contributions
ement-0.054
od-0.052
izards-0.051
es-0.049
bridge-0.048
Token ro
Token ID686
Feature activation-2.58e-02

Pos logit contributions
burn+0.011
coat+0.010
 street+0.010
ety+0.008
 yard+0.008
Neg logit contributions
ement-0.015
od-0.015
izards-0.015
es-0.014
bridge-0.014
Tokenoster
Token ID6197
Feature activation-1.68e-02

Pos logit contributions
ement+0.039
od+0.039
izards+0.038
es+0.034
ocket+0.034
Neg logit contributions
burn-0.057
coat-0.054
 street-0.052
 yard-0.044
ety-0.044
Token trick
Token ID6908
Feature activation-5.52e-02

Pos logit contributions
ement+0.075
od+0.072
izards+0.070
es+0.068
bridge+0.068
Neg logit contributions
burn-0.069
coat-0.062
 street-0.061
ety-0.053
 yard-0.050
Token.
Token ID13
Feature activation-8.77e-03

Pos logit contributions
ement+0.103
izards+0.100
od+0.100
ocket+0.095
bridge+0.095
Neg logit contributions
burn-0.098
coat-0.089
 street-0.086
 Dog-0.071
 rag-0.071
Token Everyone
Token ID11075
Feature activation+1.10e-02

Pos logit contributions
ement+0.013
od+0.012
es+0.012
izards+0.012
bridge+0.011
Neg logit contributions
burn-0.020
coat-0.019
 street-0.018
ety-0.016
 yard-0.015
Token watched
Token ID7342
Feature activation-2.71e-02

Pos logit contributions
burn+0.019
 street+0.018
coat+0.017
 yard+0.015
 wander+0.014
Neg logit contributions
ement-0.021
izards-0.020
od-0.020
bridge-0.019
 pounds-0.019
Token in
Token ID287
Feature activation+4.80e-03

Pos logit contributions
izards+0.043
ement+0.043
od+0.041
ocket+0.039
bridge+0.039
Neg logit contributions
burn-0.058
 street-0.053
coat-0.052
 Dog-0.046
 raining-0.045
Token amaz
Token ID40642
Feature activation-1.51e-01

Pos logit contributions
burn+0.010
 street+0.010
coat+0.009
 yard+0.008
 raining+0.008
Neg logit contributions
izards-0.008
od-0.008
ement-0.008
es-0.007
sters-0.007
Tokenement
Token ID972
Feature activation-4.93e-02

Pos logit contributions
izards+0.112
ocket+0.100
hell+0.097
od+0.088
 kilograms+0.085
Neg logit contributions
burn-0.392
 street-0.367
 automobile-0.365
coat-0.363
 neighborhood-0.348
Token and
Token ID290
Feature activation+2.23e-03

Pos logit contributions
ement+0.098
izards+0.095
od+0.094
bridge+0.093
hell+0.090
Neg logit contributions
burn-0.087
 street-0.077
coat-0.076
ety-0.063
 yard-0.063
Token applauded
Token ID38911
Feature activation-3.48e-02

Pos logit contributions
burn+0.004
 street+0.004
coat+0.004
 yard+0.003
ety+0.003
Neg logit contributions
ement-0.004
izards-0.004
od-0.004
bridge-0.004
hell-0.004
Token the
Token ID262
Feature activation+2.11e-02

Pos logit contributions
izards+0.070
ement+0.068
ocket+0.065
bridge+0.065
olo+0.063
Neg logit contributions
burn-0.059
 street-0.054
coat-0.049
 Dog-0.047
 automobile-0.045
Token young
Token ID1862
Feature activation+2.73e-02

Pos logit contributions
burn+0.035
coat+0.030
 street+0.030
ety+0.025
 yard+0.024
Neg logit contributions
ement-0.046
od-0.044
izards-0.043
es-0.042
bridge-0.042
Token.
Token ID13
Feature activation-1.17e-02

Pos logit contributions
ement+0.013
od+0.013
izards+0.013
bridge+0.012
es+0.012
Neg logit contributions
burn-0.011
coat-0.010
 street-0.010
 yard-0.009
 raining-0.009
Token The
Token ID383
Feature activation+1.00e-02

Pos logit contributions
ement+0.023
od+0.023
izards+0.022
bridge+0.022
es+0.021
Neg logit contributions
burn-0.021
 street-0.019
coat-0.019
ety-0.016
 yard-0.016
Token sheep
Token ID15900
Feature activation+5.50e-03

Pos logit contributions
burn+0.015
coat+0.013
 street+0.012
ety+0.010
 yard+0.009
Neg logit contributions
ement-0.024
od-0.022
izards-0.022
es-0.021
bridge-0.021
Token watched
Token ID7342
Feature activation-3.03e-02

Pos logit contributions
burn+0.010
coat+0.009
 street+0.009
ety+0.008
 yard+0.008
Neg logit contributions
ement-0.011
od-0.010
izards-0.010
bridge-0.010
es-0.010
Token in
Token ID287
Feature activation-1.53e-03

Pos logit contributions
izards+0.062
ement+0.062
od+0.059
bridge+0.059
 pounds+0.058
Neg logit contributions
burn-0.050
coat-0.042
 street-0.042
 raining-0.037
 Dog-0.036
Token amaz
Token ID40642
Feature activation-1.50e-01

Pos logit contributions
od+0.002
ement+0.002
izards+0.002
es+0.002
bridge+0.002
Neg logit contributions
burn-0.004
 street-0.003
coat-0.003
 yard-0.003
 wander-0.003
Tokenement
Token ID972
Feature activation-4.61e-02

Pos logit contributions
izards+0.116
ocket+0.097
od+0.096
es+0.096
hell+0.096
Neg logit contributions
burn-0.387
coat-0.360
 street-0.357
 automobile-0.343
 raining-0.329
Token and
Token ID290
Feature activation-3.90e-03

Pos logit contributions
ement+0.089
izards+0.087
od+0.086
bridge+0.084
es+0.082
Neg logit contributions
burn-0.084
 street-0.075
coat-0.074
ety-0.062
 yard-0.062
Token admired
Token ID29382
Feature activation-2.83e-02

Pos logit contributions
ement+0.008
izards+0.008
od+0.007
bridge+0.007
hell+0.007
Neg logit contributions
burn-0.007
 street-0.006
coat-0.006
 wander-0.005
ety-0.005
Token the
Token ID262
Feature activation+1.03e-02

Pos logit contributions
ement+0.062
bridge+0.061
boards+0.060
hell+0.060
izards+0.060
Neg logit contributions
burn-0.041
 street-0.034
coat-0.031
 Dog-0.029
 raining-0.029
Token flower
Token ID15061
Feature activation-5.53e-04

Pos logit contributions
burn+0.018
 street+0.016
coat+0.016
 yard+0.013
ety+0.013
Neg logit contributions
ement-0.021
od-0.021
izards-0.021
es-0.021
bridge-0.020
Token that
Token ID326
Feature activation-3.34e-02

Pos logit contributions
ement+0.095
od+0.092
izards+0.090
es+0.089
bridge+0.088
Neg logit contributions
burn-0.075
 street-0.069
coat-0.067
 yard-0.056
ety-0.055
Token made
Token ID925
Feature activation-2.67e-02

Pos logit contributions
ement+0.059
od+0.056
izards+0.055
bridge+0.053
es+0.053
Neg logit contributions
burn-0.066
 street-0.064
coat-0.061
 yard-0.054
ety-0.054
Token it
Token ID340
Feature activation-9.50e-03

Pos logit contributions
ement+0.053
od+0.048
 pounds+0.047
bridge+0.047
izards+0.046
Neg logit contributions
burn-0.047
 street-0.043
 Dog-0.042
 wander-0.040
 raining-0.039
Token pause
Token ID14985
Feature activation-9.14e-03

Pos logit contributions
ement+0.019
od+0.019
izards+0.018
es+0.018
bridge+0.018
Neg logit contributions
burn-0.017
coat-0.015
 street-0.015
ety-0.012
 yard-0.012
Token in
Token ID287
Feature activation+1.41e-02

Pos logit contributions
ement+0.019
od+0.018
izards+0.018
bridge+0.017
es+0.017
Neg logit contributions
burn-0.016
 street-0.014
coat-0.014
ety-0.012
 yard-0.012
Token amaz
Token ID40642
Feature activation-1.50e-01

Pos logit contributions
burn+0.025
 street+0.023
coat+0.022
 yard+0.019
 raining+0.019
Neg logit contributions
ement-0.028
od-0.027
izards-0.027
es-0.026
bridge-0.026
Tokenement
Token ID972
Feature activation-4.61e-02

Pos logit contributions
 ah+0.081
izards+0.080
od+0.077
es+0.073
olo+0.071
Neg logit contributions
burn-0.411
coat-0.395
 street-0.384
 yard-0.365
 automobile-0.364
Token.
Token ID13
Feature activation-3.84e-03

Pos logit contributions
ement+0.090
od+0.085
izards+0.085
bridge+0.083
hell+0.080
Neg logit contributions
burn-0.084
 street-0.075
coat-0.074
 raining-0.062
ety-0.062
Token There
Token ID1318
Feature activation+2.04e-02

Pos logit contributions
ement+0.008
od+0.008
izards+0.008
es+0.007
bridge+0.007
Neg logit contributions
burn-0.006
 street-0.006
coat-0.006
 yard-0.005
ety-0.005
Token,
Token ID11
Feature activation-1.90e-02

Pos logit contributions
burn+0.036
 street+0.034
coat+0.032
 yard+0.030
 Dog+0.030
Neg logit contributions
ement-0.037
izards-0.036
od-0.036
bridge-0.036
hell-0.035
Token spreading
Token ID14342
Feature activation+2.24e-03

Pos logit contributions
ement+0.039
od+0.037
izards+0.035
hell+0.035
ils+0.034
Neg logit contributions
 street-0.033
burn-0.032
coat-0.028
 Dog-0.027
 wander-0.026
Token the
Token ID262
Feature activation-2.23e-02

Pos logit contributions
ement+0.065
od+0.061
izards+0.058
es+0.056
ils+0.056
Neg logit contributions
burn-0.105
coat-0.100
 street-0.090
ety-0.084
 wander-0.080
Token bush
Token ID24484
Feature activation-3.06e-02

Pos logit contributions
ement+0.046
od+0.044
bridge+0.043
izards+0.042
 pounds+0.042
Neg logit contributions
burn-0.040
coat-0.034
 street-0.030
ety-0.028
 Kathy-0.026
Token and
Token ID290
Feature activation-2.14e-02

Pos logit contributions
ement+0.059
od+0.057
izards+0.055
es+0.055
bridge+0.053
Neg logit contributions
burn-0.058
coat-0.051
 street-0.051
ety-0.043
 yard-0.042
Token watched
Token ID7342
Feature activation-3.65e-02

Pos logit contributions
ement+0.042
od+0.040
izards+0.040
bridge+0.038
es+0.037
Neg logit contributions
burn-0.041
 street-0.036
coat-0.036
ety-0.030
 yard-0.030
Token in
Token ID287
Feature activation-1.63e-03

Pos logit contributions
izards+0.063
ement+0.063
bridge+0.060
boards+0.060
od+0.059
Neg logit contributions
burn-0.072
 street-0.063
coat-0.059
 Dog-0.056
 raining-0.056
Token amaz
Token ID40642
Feature activation-1.50e-01

Pos logit contributions
ement+0.003
od+0.003
izards+0.003
es+0.003
bridge+0.003
Neg logit contributions
burn-0.003
 street-0.003
coat-0.003
 yard-0.002
ety-0.002
Tokenement
Token ID972
Feature activation-4.79e-02

Pos logit contributions
izards+0.107
od+0.091
ocket+0.088
sters+0.086
es+0.084
Neg logit contributions
burn-0.410
coat-0.378
 automobile-0.368
 street-0.366
 yard-0.349
Token as
Token ID355
Feature activation+2.63e-02

Pos logit contributions
ement+0.091
izards+0.088
od+0.087
bridge+0.086
hell+0.082
Neg logit contributions
burn-0.090
coat-0.079
 street-0.079
ety-0.066
 raining-0.065
Token it
Token ID340
Feature activation-4.29e-02

Pos logit contributions
burn+0.051
 street+0.046
coat+0.045
 raining+0.038
 yard+0.038
Neg logit contributions
ement-0.049
od-0.047
izards-0.046
bridge-0.044
es-0.044
Token flew
Token ID13112
Feature activation+2.73e-02

Pos logit contributions
ement+0.097
od+0.094
izards+0.093
 pounds+0.090
hell+0.088
Neg logit contributions
burn-0.066
coat-0.058
 street-0.056
 yard-0.046
ety-0.045
Token away
Token ID1497
Feature activation-2.02e-02

Pos logit contributions
burn+0.048
coat+0.042
 street+0.042
ety+0.035
 yard+0.034
Neg logit contributions
ement-0.056
od-0.055
izards-0.054
es-0.052
bridge-0.051
Token and
Token ID290
Feature activation+9.38e-03

Pos logit contributions
izards+0.045
bridge+0.044
ement+0.043
hell+0.043
ocket+0.043
Neg logit contributions
burn-0.026
 street-0.022
coat-0.022
 raining-0.020
gy-0.018
Token pointed
Token ID6235
Feature activation+1.38e-02

Pos logit contributions
burn+0.016
 street+0.015
coat+0.014
 Dog+0.013
ety+0.012
Neg logit contributions
ement-0.019
izards-0.018
od-0.018
bridge-0.018
hell-0.018
Token at
Token ID379
Feature activation-2.46e-02

Pos logit contributions
burn+0.019
 street+0.017
coat+0.017
 Dog+0.014
 yard+0.014
Neg logit contributions
ement-0.031
od-0.031
izards-0.031
bridge-0.031
hell-0.029
Token it
Token ID340
Feature activation-1.86e-02

Pos logit contributions
ement+0.050
bridge+0.050
od+0.050
izards+0.049
hell+0.047
Neg logit contributions
burn-0.042
 street-0.037
coat-0.036
 Dog-0.031
ety-0.031
Token in
Token ID287
Feature activation-3.90e-03

Pos logit contributions
ement+0.037
izards+0.036
od+0.036
bridge+0.035
es+0.033
Neg logit contributions
burn-0.033
coat-0.029
 street-0.029
 yard-0.024
ety-0.024
Token amaz
Token ID40642
Feature activation-1.49e-01

Pos logit contributions
ement+0.007
od+0.007
izards+0.007
es+0.007
bridge+0.007
Neg logit contributions
burn-0.008
 street-0.007
coat-0.007
 yard-0.006
ety-0.006
Tokenement
Token ID972
Feature activation-5.07e-02

Pos logit contributions
izards+0.104
od+0.092
 kilograms+0.090
hell+0.085
sters+0.083
Neg logit contributions
burn-0.393
coat-0.378
 street-0.365
 automobile-0.355
 yard-0.344
Token.
Token ID13
Feature activation-1.04e-02

Pos logit contributions
ement+0.096
izards+0.096
od+0.094
bridge+0.093
hell+0.090
Neg logit contributions
burn-0.091
 street-0.080
coat-0.080
 raining-0.067
ety-0.066
Token The
Token ID383
Feature activation+1.01e-02

Pos logit contributions
ement+0.018
od+0.018
izards+0.017
es+0.017
bridge+0.016
Neg logit contributions
burn-0.022
coat-0.019
 street-0.019
ety-0.017
 yard-0.016
Token bird
Token ID6512
Feature activation-7.17e-03

Pos logit contributions
burn+0.018
 street+0.016
coat+0.016
 yard+0.013
ety+0.013
Neg logit contributions
ement-0.021
od-0.020
izards-0.020
es-0.019
bridge-0.019
Token stopped
Token ID5025
Feature activation+2.04e-02

Pos logit contributions
ement+0.014
izards+0.014
od+0.013
bridge+0.013
 pounds+0.013
Neg logit contributions
burn-0.013
 street-0.012
coat-0.012
ety-0.010
 yard-0.010
Token gazed
Token ID50255
Feature activation-2.09e-03

Pos logit contributions
ement+0.025
izards+0.024
od+0.024
 pounds+0.023
hell+0.023
Neg logit contributions
burn-0.021
 street-0.019
coat-0.018
ety-0.015
 wander-0.015
Token at
Token ID379
Feature activation-2.45e-02

Pos logit contributions
ement+0.004
od+0.004
izards+0.004
hell+0.004
bridge+0.004
Neg logit contributions
burn-0.004
 street-0.003
coat-0.003
 raining-0.003
 yard-0.003
Token Ad
Token ID1215
Feature activation-2.04e-02

Pos logit contributions
ement+0.048
izards+0.048
od+0.047
bridge+0.046
es+0.045
Neg logit contributions
burn-0.044
 street-0.040
coat-0.038
ety-0.033
 yard-0.032
Tokeneline
Token ID4470
Feature activation-2.88e-02

Pos logit contributions
ement+0.053
od+0.052
izards+0.051
es+0.050
bridge+0.049
Neg logit contributions
burn-0.025
coat-0.021
 street-0.021
ety-0.015
 yard-0.015
Token in
Token ID287
Feature activation+6.59e-03

Pos logit contributions
ement+0.057
izards+0.056
bridge+0.055
od+0.054
hell+0.053
Neg logit contributions
burn-0.050
 street-0.045
coat-0.043
 yard-0.037
ety-0.037
Token amaz
Token ID40642
Feature activation-1.49e-01

Pos logit contributions
burn+0.013
 street+0.012
coat+0.011
 yard+0.010
 wander+0.010
Neg logit contributions
ement-0.012
izards-0.012
od-0.012
sters-0.011
es-0.011
Tokenement
Token ID972
Feature activation-4.56e-02

Pos logit contributions
izards+0.113
 kilograms+0.096
 pounds+0.092
od+0.089
es+0.089
Neg logit contributions
burn-0.399
 street-0.374
coat-0.374
 automobile-0.368
 neighborhood-0.350
Token.
Token ID13
Feature activation-8.09e-03

Pos logit contributions
ement+0.084
izards+0.084
od+0.082
bridge+0.081
hell+0.078
Neg logit contributions
burn-0.085
 street-0.076
coat-0.075
ety-0.063
 yard-0.063
Token As
Token ID1081
Feature activation+3.69e-02

Pos logit contributions
ement+0.015
od+0.014
izards+0.013
es+0.013
bridge+0.013
Neg logit contributions
burn-0.016
coat-0.015
 street-0.014
ety-0.012
 yard-0.012
Token she
Token ID673
Feature activation-3.33e-02

Pos logit contributions
burn+0.077
coat+0.071
 street+0.069
ety+0.060
 yard+0.060
Neg logit contributions
ement-0.063
od-0.062
izards-0.059
es-0.058
bridge-0.056
Token sang
Token ID25889
Feature activation-7.30e-03

Pos logit contributions
ement+0.070
od+0.068
izards+0.068
bridge+0.066
 pounds+0.065
Neg logit contributions
burn-0.056
coat-0.049
 street-0.049
ety-0.040
 yard-0.040
Token shaking
Token ID17275
Feature activation+2.01e-02

Pos logit contributions
ement+0.016
od+0.015
bridge+0.014
es+0.014
izards+0.014
Neg logit contributions
burn-0.016
 street-0.014
coat-0.014
ety-0.013
 wander-0.012
Token.
Token ID13
Feature activation-8.81e-04

Pos logit contributions
burn+0.039
coat+0.036
 street+0.035
ety+0.030
 yard+0.030
Neg logit contributions
ement-0.037
od-0.036
izards-0.035
es-0.034
bridge-0.033
Token Mom
Token ID11254
Feature activation+1.68e-02

Pos logit contributions
ement+0.002
od+0.002
izards+0.002
es+0.001
bridge+0.001
Neg logit contributions
burn-0.002
coat-0.002
 street-0.002
ety-0.001
 yard-0.001
Token watched
Token ID7342
Feature activation-2.64e-02

Pos logit contributions
burn+0.033
coat+0.029
 street+0.029
ety+0.025
 yard+0.025
Neg logit contributions
ement-0.031
od-0.030
izards-0.029
es-0.029
bridge-0.028
Token in
Token ID287
Feature activation-5.42e-04

Pos logit contributions
izards+0.055
ement+0.053
od+0.053
bridge+0.052
sters+0.051
Neg logit contributions
burn-0.044
coat-0.039
 street-0.038
 raining-0.032
 wander-0.031
Token amaz
Token ID40642
Feature activation-1.48e-01

Pos logit contributions
od+0.001
ement+0.001
izards+0.001
es+0.001
bridge+0.001
Neg logit contributions
burn-0.001
 street-0.001
coat-0.001
 yard-0.001
 raining-0.001
Tokenement
Token ID972
Feature activation-4.78e-02

Pos logit contributions
izards+0.111
ocket+0.094
hell+0.093
od+0.092
 kil+0.091
Neg logit contributions
burn-0.382
coat-0.359
 street-0.353
 automobile-0.344
 Kathy-0.337
Token from
Token ID422
Feature activation-4.04e-02

Pos logit contributions
ement+0.094
izards+0.092
od+0.092
bridge+0.090
es+0.086
Neg logit contributions
burn-0.085
 street-0.075
coat-0.075
ety-0.062
 yard-0.061
Token a
Token ID257
Feature activation-2.52e-02

Pos logit contributions
ement+0.068
od+0.064
izards+0.063
es+0.060
bridge+0.059
Neg logit contributions
burn-0.087
coat-0.079
 street-0.075
ety-0.068
 yard-0.064
Token distance
Token ID5253
Feature activation+2.22e-02

Pos logit contributions
ement+0.056
od+0.054
izards+0.052
es+0.051
bridge+0.051
Neg logit contributions
burn-0.040
coat-0.035
 street-0.034
ety-0.029
 yard-0.027
Token,
Token ID11
Feature activation-1.92e-02

Pos logit contributions
burn+0.037
 street+0.034
coat+0.033
 yard+0.028
ety+0.027
Neg logit contributions
od-0.045
ement-0.045
izards-0.045
bridge-0.043
es-0.043
Token.
Token ID13
Feature activation-5.33e-03

Pos logit contributions
ement+0.039
izards+0.038
od+0.038
es+0.036
ils+0.035
Neg logit contributions
burn-0.037
coat-0.034
 street-0.033
 yard-0.028
 raining-0.028
Token The
Token ID383
Feature activation+1.36e-02

Pos logit contributions
ement+0.011
od+0.011
izards+0.011
bridge+0.010
es+0.010
Neg logit contributions
burn-0.008
 street-0.008
coat-0.008
 yard-0.007
 Dog-0.007
Token deer
Token ID20096
Feature activation+7.29e-03

Pos logit contributions
burn+0.023
coat+0.020
 street+0.020
ety+0.016
 yard+0.016
Neg logit contributions
ement-0.029
od-0.028
izards-0.028
es-0.027
bridge-0.027
Token stared
Token ID18484
Feature activation+7.91e-03

Pos logit contributions
burn+0.013
 street+0.012
coat+0.012
ety+0.010
 yard+0.010
Neg logit contributions
ement-0.014
izards-0.014
od-0.014
bridge-0.013
 pounds-0.013
Token in
Token ID287
Feature activation+6.11e-04

Pos logit contributions
burn+0.016
coat+0.015
 street+0.014
ety+0.012
 yard+0.012
Neg logit contributions
ement-0.014
od-0.013
izards-0.013
es-0.013
bridge-0.013
Token amaz
Token ID40642
Feature activation-1.48e-01

Pos logit contributions
burn+0.001
 street+0.001
coat+0.001
 yard+0.001
 wander+0.001
Neg logit contributions
od-0.001
izards-0.001
ement-0.001
es-0.001
bridge-0.001
Tokenement
Token ID972
Feature activation-4.76e-02

Pos logit contributions
izards+0.113
od+0.104
es+0.093
 kilograms+0.089
olo+0.087
Neg logit contributions
burn-0.374
coat-0.359
 street-0.352
 automobile-0.346
 yard-0.333
Token.
Token ID13
Feature activation-8.52e-03

Pos logit contributions
ement+0.094
izards+0.094
bridge+0.093
od+0.092
ils+0.089
Neg logit contributions
burn-0.081
 street-0.071
coat-0.070
 raining-0.060
ety-0.060
Token He
Token ID679
Feature activation-2.08e-02

Pos logit contributions
ement+0.017
od+0.016
izards+0.016
ils+0.015
bridge+0.015
Neg logit contributions
burn-0.015
 street-0.014
coat-0.014
 yard-0.012
 Dog-0.012
Token had
Token ID550
Feature activation-4.99e-03

Pos logit contributions
ement+0.046
izards+0.044
bridge+0.043
od+0.043
hell+0.042
Neg logit contributions
burn-0.030
 street-0.029
coat-0.027
ety-0.024
 wander-0.024
Token never
Token ID1239
Feature activation+1.91e-02

Pos logit contributions
ement+0.011
od+0.010
izards+0.010
es+0.010
bridge+0.010
Neg logit contributions
burn-0.008
 street-0.007
coat-0.007
 yard-0.006
ety-0.006
Token.
Token ID13
Feature activation+2.54e-03

Pos logit contributions
ement+0.082
izards+0.081
od+0.081
bridge+0.075
es+0.074
Neg logit contributions
burn-0.081
coat-0.073
 street-0.073
 yard-0.059
ety-0.059
Token<|endoftext|>
Token ID50256
Feature activation-3.67e-02

Pos logit contributions
burn+0.005
coat+0.005
 street+0.004
ety+0.004
 yard+0.004
Neg logit contributions
ement-0.005
od-0.005
izards-0.004
es-0.004
bridge-0.004
TokenM
Token ID44
Feature activation-1.68e-02

Pos logit contributions
ement+0.083
od+0.081
izards+0.080
 pounds+0.078
ils+0.077
Neg logit contributions
burn-0.054
 street-0.049
coat-0.048
 yard-0.042
ety-0.038
Tokenolly
Token ID5098
Feature activation-9.34e-03

Pos logit contributions
od+0.032
izards+0.031
ement+0.031
es+0.031
bridge+0.030
Neg logit contributions
burn-0.031
 street-0.028
coat-0.027
 yard-0.024
ety-0.024
Token was
Token ID373
Feature activation+1.93e-02

Pos logit contributions
ement+0.017
od+0.017
izards+0.016
es+0.016
bridge+0.015
Neg logit contributions
burn-0.018
coat-0.016
 street-0.016
ety-0.014
 yard-0.013
Token a
Token ID257
Feature activation+4.75e-02

Pos logit contributions
burn+0.035
 street+0.032
coat+0.031
ety+0.030
 wander+0.027
Neg logit contributions
ement-0.035
od-0.034
bridge-0.033
izards-0.033
vel-0.031
Token brave
Token ID14802
Feature activation+3.66e-02

Pos logit contributions
burn+0.091
coat+0.080
 street+0.075
ety+0.068
ained+0.065
Neg logit contributions
ement-0.086
od-0.085
ious-0.078
bridge-0.077
izards-0.076
Token girl
Token ID2576
Feature activation+1.76e-02

Pos logit contributions
burn+0.067
coat+0.059
 street+0.058
ety+0.050
 yard+0.048
Neg logit contributions
ement-0.072
od-0.070
izards-0.067
bridge-0.064
es-0.064
Token,
Token ID11
Feature activation+1.09e-02

Pos logit contributions
burn+0.038
coat+0.035
 street+0.034
ety+0.030
 yard+0.028
Neg logit contributions
ement-0.028
od-0.028
es-0.027
izards-0.027
bridge-0.025
Token she
Token ID673
Feature activation+1.60e-02

Pos logit contributions
burn+0.023
 street+0.020
coat+0.020
ety+0.017
 rag+0.016
Neg logit contributions
od-0.018
izards-0.017
es-0.017
ement-0.017
bridge-0.016
Token liked
Token ID8288
Feature activation+2.07e-02

Pos logit contributions
burn+0.031
coat+0.028
 street+0.027
ety+0.024
 yard+0.023
Neg logit contributions
ement-0.030
od-0.029
izards-0.028
es-0.028
bridge-0.027
Token
Token ID198
Feature activation-1.53e-02

Pos logit contributions
ement+0.024
od+0.023
izards+0.023
 pounds+0.022
ils+0.022
Neg logit contributions
burn-0.018
 street-0.016
coat-0.015
 yard-0.013
ety-0.013
TokenThe
Token ID464
Feature activation+1.19e-02

Pos logit contributions
ement+0.033
od+0.032
izards+0.031
es+0.030
 pounds+0.029
Neg logit contributions
burn-0.025
 street-0.022
coat-0.022
ety-0.018
 yard-0.018
Token hunter
Token ID19177
Feature activation-6.40e-03

Pos logit contributions
burn+0.022
 street+0.020
coat+0.020
 yard+0.017
ety+0.016
Neg logit contributions
ement-0.023
od-0.023
izards-0.022
es-0.022
bridge-0.021
Token was
Token ID373
Feature activation+4.22e-03

Pos logit contributions
ement+0.013
izards+0.012
od+0.012
bridge+0.011
 pounds+0.011
Neg logit contributions
burn-0.011
 street-0.011
coat-0.010
 yard-0.009
ety-0.009
Token proud
Token ID6613
Feature activation-1.08e-02

Pos logit contributions
burn+0.009
coat+0.008
 street+0.008
ety+0.007
 yard+0.007
Neg logit contributions
ement-0.007
od-0.007
izards-0.006
es-0.006
bridge-0.006
Token of
Token ID286
Feature activation+5.40e-02

Pos logit contributions
ement+0.019
izards+0.019
od+0.018
bridge+0.018
es+0.018
Neg logit contributions
burn-0.021
 street-0.020
coat-0.019
 yard-0.017
 raining-0.017
Token himself
Token ID2241
Feature activation+2.37e-02

Pos logit contributions
burn+0.100
 street+0.096
coat+0.088
 Dog+0.082
 yard+0.081
Neg logit contributions
ement-0.095
od-0.093
izards-0.091
bridge-0.090
als-0.088
Token and
Token ID290
Feature activation+1.95e-02

Pos logit contributions
burn+0.040
 street+0.036
coat+0.035
 yard+0.030
 wander+0.029
Neg logit contributions
ement-0.048
izards-0.046
od-0.045
bridge-0.045
es-0.042
Token thanked
Token ID26280
Feature activation-2.56e-02

Pos logit contributions
burn+0.037
 street+0.034
coat+0.033
 yard+0.028
ety+0.028
Neg logit contributions
ement-0.037
od-0.036
izards-0.035
bridge-0.033
es-0.033
Token his
Token ID465
Feature activation+1.22e-02

Pos logit contributions
izards+0.057
ement+0.057
od+0.055
bridge+0.055
sters+0.054
Neg logit contributions
burn-0.036
 street-0.034
 Dog-0.030
coat-0.028
 visit-0.028
Token friends
Token ID2460
Feature activation+2.45e-02

Pos logit contributions
burn+0.020
 street+0.018
coat+0.017
 yard+0.014
ety+0.014
Neg logit contributions
ement-0.026
od-0.026
izards-0.025
es-0.024
bridge-0.024
Token,
Token ID11
Feature activation+9.88e-03

Pos logit contributions
ement+0.045
od+0.044
izards+0.043
bridge+0.042
 pounds+0.040
Neg logit contributions
burn-0.032
coat-0.027
 street-0.027
 Dog-0.022
 raining-0.021
Token "
Token ID366
Feature activation+1.73e-02

Pos logit contributions
burn+0.020
coat+0.018
 street+0.018
ety+0.015
 yard+0.015
Neg logit contributions
ement-0.018
od-0.017
izards-0.017
es-0.016
bridge-0.016
TokenWe
Token ID1135
Feature activation+2.84e-02

Pos logit contributions
burn+0.032
coat+0.029
 street+0.029
 yard+0.025
ety+0.024
Neg logit contributions
ement-0.033
od-0.032
izards-0.031
es-0.031
bridge-0.030
Token are
Token ID389
Feature activation-1.04e-02

Pos logit contributions
burn+0.050
coat+0.045
 street+0.042
ety+0.037
 yard+0.037
Neg logit contributions
ement-0.061
od-0.057
izards-0.056
es-0.054
bridge-0.053
Token sorry
Token ID7926
Feature activation+1.71e-02

Pos logit contributions
ement+0.021
od+0.020
izards+0.020
es+0.019
bridge+0.019
Neg logit contributions
burn-0.019
coat-0.017
 street-0.017
 yard-0.014
ety-0.014
Token.
Token ID13
Feature activation+4.74e-02

Pos logit contributions
burn+0.030
 street+0.026
coat+0.026
ety+0.022
 yard+0.022
Neg logit contributions
ement-0.036
od-0.035
izards-0.034
bridge-0.033
es-0.032
Token We
Token ID775
Feature activation+2.09e-02

Pos logit contributions
burn+0.107
coat+0.098
 street+0.097
ety+0.084
 yard+0.083
Neg logit contributions
ement-0.073
od-0.071
izards-0.069
es-0.066
bridge-0.065
Token are
Token ID389
Feature activation-1.67e-02

Pos logit contributions
burn+0.045
coat+0.041
 street+0.040
ety+0.035
 yard+0.034
Neg logit contributions
ement-0.036
od-0.034
izards-0.034
es-0.032
bridge-0.032
Token happy
Token ID3772
Feature activation-1.19e-02

Pos logit contributions
ement+0.031
od+0.031
izards+0.030
es+0.029
bridge+0.028
Neg logit contributions
burn-0.032
coat-0.029
 street-0.029
ety-0.024
 yard-0.024
Token.
Token ID13
Feature activation+4.48e-02

Pos logit contributions
ement+0.023
od+0.022
izards+0.022
bridge+0.022
hell+0.021
Neg logit contributions
burn-0.023
 street-0.020
coat-0.019
 raining-0.017
 yard-0.017
Token We
Token ID775
Feature activation+2.05e-02

Pos logit contributions
burn+0.102
coat+0.095
 street+0.093
ety+0.081
 yard+0.080
Neg logit contributions
ement-0.068
od-0.065
izards-0.063
es-0.061
bridge-0.059
Token girl
Token ID2576
Feature activation+5.26e-03

Pos logit contributions
burn+0.100
coat+0.092
 street+0.087
ained+0.076
ety+0.075
Neg logit contributions
ement-0.088
od-0.087
izards-0.084
es-0.081
ious-0.080
Token named
Token ID3706
Feature activation+2.07e-02

Pos logit contributions
burn+0.010
coat+0.009
 street+0.008
ained+0.007
 tire+0.007
Neg logit contributions
od-0.010
es-0.010
izards-0.009
ils-0.009
ious-0.008
Token Lily
Token ID20037
Feature activation+2.42e-02

Pos logit contributions
burn+0.043
coat+0.038
 street+0.038
 yard+0.032
ety+0.031
Neg logit contributions
od-0.036
ement-0.035
izards-0.034
es-0.033
hell-0.032
Token.
Token ID13
Feature activation+9.14e-03

Pos logit contributions
burn+0.068
coat+0.066
 street+0.061
 Kathy+0.056
rolling+0.055
Neg logit contributions
od-0.023
es-0.021
hell-0.017
izards-0.017
ils-0.015
Token She
Token ID1375
Feature activation+1.57e-02

Pos logit contributions
burn+0.016
coat+0.014
 street+0.014
ety+0.011
 yard+0.011
Neg logit contributions
ement-0.019
od-0.018
izards-0.018
es-0.018
hell-0.017
Token loved
Token ID6151
Feature activation+4.49e-02

Pos logit contributions
burn+0.031
coat+0.027
 street+0.025
ety+0.022
 pasture+0.021
Neg logit contributions
od-0.029
es-0.028
izards-0.028
ement-0.027
hell-0.027
Token to
Token ID284
Feature activation+1.62e-02

Pos logit contributions
burn+0.076
coat+0.072
 street+0.065
ety+0.058
gy+0.057
Neg logit contributions
od-0.088
izards-0.083
ils-0.080
es-0.079
ement-0.078
Token play
Token ID711
Feature activation+5.30e-02

Pos logit contributions
burn+0.025
coat+0.021
 street+0.020
ety+0.020
ained+0.018
Neg logit contributions
od-0.035
bridge-0.032
izards-0.032
hell-0.031
ement-0.031
Token outside
Token ID2354
Feature activation+7.50e-02

Pos logit contributions
burn+0.073
coat+0.065
 street+0.063
 yard+0.050
 rag+0.046
Neg logit contributions
ement-0.130
od-0.125
izards-0.123
 pounds-0.120
hell-0.118
Token and
Token ID290
Feature activation+7.50e-03

Pos logit contributions
burn+0.168
coat+0.153
 street+0.148
ety+0.134
 Dog+0.126
Neg logit contributions
ement-0.117
od-0.115
es-0.111
izards-0.110
bridge-0.103
Token lay
Token ID3830
Feature activation+5.92e-02

Pos logit contributions
burn+0.012
coat+0.011
 street+0.009
ety+0.009
 rag+0.008
Neg logit contributions
od-0.015
izards-0.015
ement-0.014
es-0.014
bridge-0.014
Tokenmy
Token ID1820
Feature activation+2.39e-02

Pos logit contributions
burn+0.037
 street+0.033
coat+0.033
 Kathy+0.024
 rag+0.024
Neg logit contributions
od-0.050
ement-0.050
es-0.050
izards-0.047
hell-0.046
Token.
Token ID13
Feature activation+1.83e-02

Pos logit contributions
burn+0.062
coat+0.060
 street+0.058
 Kathy+0.051
 raining+0.050
Neg logit contributions
es-0.026
od-0.025
ement-0.024
ious-0.020
hell-0.019
Token Tim
Token ID5045
Feature activation+3.34e-02

Pos logit contributions
burn+0.043
coat+0.038
 street+0.037
 wander+0.031
ety+0.031
Neg logit contributions
ement-0.028
od-0.026
izards-0.024
bridge-0.023
es-0.023
Tokenmy
Token ID1820
Feature activation+3.00e-02

Pos logit contributions
burn+0.048
 street+0.041
coat+0.040
 Dog+0.031
 Kathy+0.031
Neg logit contributions
od-0.075
ement-0.074
es-0.072
hell-0.072
izards-0.068
Token loved
Token ID6151
Feature activation+4.73e-02

Pos logit contributions
burn+0.068
coat+0.059
 street+0.056
 Kathy+0.049
 leash+0.049
Neg logit contributions
od-0.047
es-0.045
ement-0.041
hell-0.040
ious-0.039
Token going
Token ID1016
Feature activation+4.57e-02

Pos logit contributions
burn+0.078
coat+0.073
 street+0.066
ety+0.057
 yard+0.053
Neg logit contributions
od-0.098
ement-0.093
izards-0.093
es-0.089
ils-0.088
Token to
Token ID284
Feature activation+9.04e-03

Pos logit contributions
burn+0.091
coat+0.084
 street+0.078
ety+0.072
 rag+0.070
Neg logit contributions
es-0.070
izards-0.069
od-0.068
ement-0.065
boards-0.064
Token the
Token ID262
Feature activation-2.24e-03

Pos logit contributions
burn+0.020
coat+0.019
 street+0.017
ety+0.016
any+0.015
Neg logit contributions
od-0.014
ement-0.013
izards-0.012
es-0.012
bridge-0.011
Token beach
Token ID10481
Feature activation+2.55e-02

Pos logit contributions
od+0.005
ement+0.005
bridge+0.004
izards+0.004
sters+0.004
Neg logit contributions
burn-0.003
coat-0.003
 street-0.003
ety-0.002
any-0.002
Token to
Token ID284
Feature activation-2.52e-02

Pos logit contributions
burn+0.048
coat+0.043
 street+0.042
ety+0.036
 yard+0.035
Neg logit contributions
ement-0.049
od-0.048
izards-0.047
es-0.046
bridge-0.045
Token see
Token ID766
Feature activation-1.58e-02

Pos logit contributions
od+0.051
ement+0.050
izards+0.048
bridge+0.048
es+0.046
Neg logit contributions
burn-0.044
coat-0.039
 street-0.036
ety-0.032
 Kathy-0.029
Token play
Token ID711
Feature activation+4.14e-02

Pos logit contributions
burn+0.007
coat+0.006
 street+0.005
ety+0.005
 rag+0.005
Neg logit contributions
od-0.008
izards-0.007
hell-0.007
es-0.007
ement-0.007
Token in
Token ID287
Feature activation+2.00e-02

Pos logit contributions
burn+0.070
 street+0.064
coat+0.063
 yard+0.053
 raining+0.051
Neg logit contributions
ement-0.087
od-0.084
izards-0.081
bridge-0.078
ocket-0.076
Token here
Token ID994
Feature activation-1.30e-02

Pos logit contributions
burn+0.044
coat+0.041
 street+0.038
ety+0.035
 wander+0.032
Neg logit contributions
ement-0.032
od-0.031
izards-0.031
es-0.030
 pounds-0.028
Token.
Token ID13
Feature activation+2.39e-02

Pos logit contributions
ement+0.022
od+0.022
izards+0.021
es+0.021
bridge+0.020
Neg logit contributions
burn-0.027
coat-0.024
 street-0.024
ety-0.021
 yard-0.020
Token The
Token ID383
Feature activation+8.15e-03

Pos logit contributions
burn+0.059
coat+0.054
 street+0.053
ety+0.046
 yard+0.045
Neg logit contributions
ement-0.032
izards-0.031
od-0.031
es-0.029
bridge-0.028
Token horse
Token ID8223
Feature activation-7.79e-03

Pos logit contributions
burn+0.013
coat+0.012
 street+0.010
ety+0.010
gy+0.009
Neg logit contributions
ement-0.017
izards-0.016
bridge-0.016
od-0.016
 pounds-0.016
Token might
Token ID1244
Feature activation+1.30e-02

Pos logit contributions
ement+0.013
od+0.013
izards+0.012
bridge+0.012
 pounds+0.011
Neg logit contributions
burn-0.016
 street-0.015
coat-0.015
 yard-0.013
ety-0.013
Token get
Token ID651
Feature activation+1.41e-02

Pos logit contributions
burn+0.023
coat+0.021
 street+0.020
ety+0.017
 yard+0.017
Neg logit contributions
izards-0.024
od-0.024
hell-0.024
ement-0.023
es-0.023
Token scared
Token ID12008
Feature activation+2.31e-02

Pos logit contributions
burn+0.023
coat+0.021
 street+0.021
 yard+0.017
ety+0.016
Neg logit contributions
ement-0.029
izards-0.029
od-0.029
es-0.028
bridge-0.027
Token or
Token ID393
Feature activation-1.24e-02

Pos logit contributions
burn+0.048
coat+0.043
 street+0.043
ety+0.037
 yard+0.036
Neg logit contributions
ement-0.041
od-0.039
izards-0.038
es-0.037
bridge-0.036
Token hurt
Token ID5938
Feature activation+3.07e-02

Pos logit contributions
ement+0.026
izards+0.026
od+0.026
es+0.025
bridge+0.024
Neg logit contributions
burn-0.020
coat-0.018
 street-0.017
ety-0.014
 yard-0.014
Token them
Token ID606
Feature activation+1.30e-02

Pos logit contributions
ement+0.026
od+0.025
izards+0.024
bridge+0.023
es+0.022
Neg logit contributions
burn-0.047
coat-0.042
 street-0.041
ety-0.038
 Dog-0.037
Token a
Token ID257
Feature activation-1.60e-02

Pos logit contributions
burn+0.025
 street+0.023
coat+0.023
ety+0.019
 yard+0.019
Neg logit contributions
ement-0.023
od-0.023
izards-0.023
es-0.022
hell-0.021
Token tissue
Token ID10712
Feature activation-4.95e-04

Pos logit contributions
hell+0.028
 lid+0.025
od+0.025
ement+0.024
es+0.024
Neg logit contributions
burn-0.029
 street-0.026
ety-0.025
coat-0.024
gy-0.024
Token to
Token ID284
Feature activation-5.97e-02

Pos logit contributions
ement+0.001
od+0.001
es+0.001
izards+0.001
bridge+0.001
Neg logit contributions
burn-0.001
 street-0.001
coat-0.001
ety-0.001
 yard-0.001
Token wipe
Token ID19916
Feature activation-1.74e-02

Pos logit contributions
ement+0.128
od+0.125
izards+0.123
es+0.120
bridge+0.117
Neg logit contributions
burn-0.097
coat-0.085
 street-0.085
ety-0.070
 yard-0.068
Token their
Token ID511
Feature activation-1.87e-02

Pos logit contributions
ement+0.035
od+0.035
izards+0.035
bridge+0.033
es+0.032
Neg logit contributions
burn-0.031
coat-0.027
 street-0.027
ety-0.022
 yard-0.022
Token eyes
Token ID2951
Feature activation-3.52e-02

Pos logit contributions
od+0.030
ement+0.030
izards+0.028
bridge+0.027
es+0.026
Neg logit contributions
burn-0.042
 street-0.040
coat-0.038
 yard-0.035
 rag-0.034
Token.
Token ID13
Feature activation+3.10e-03

Pos logit contributions
ement+0.062
od+0.060
es+0.058
hell+0.057
izards+0.056
Neg logit contributions
burn-0.071
coat-0.065
 street-0.064
ety-0.055
 yard-0.055
Token
Token ID198
Feature activation-2.03e-03

Pos logit contributions
burn+0.006
coat+0.005
 street+0.005
ety+0.005
gy+0.004
Neg logit contributions
ement-0.006
od-0.006
es-0.005
izards-0.005
bridge-0.005
Token
Token ID198
Feature activation-4.88e-03

Pos logit contributions
od+0.003
ement+0.003
izards+0.003
es+0.003
hell+0.003
Neg logit contributions
burn-0.005
coat-0.004
 street-0.004
ety-0.004
 raining-0.003
Token"
Token ID1
Feature activation-8.57e-03

Pos logit contributions
es+0.007
od+0.006
izards+0.006
ement+0.006
hell+0.006
Neg logit contributions
burn-0.012
coat-0.011
 street-0.010
 raining-0.010
gy-0.009
Token both
Token ID1111
Feature activation+6.62e-02

Pos logit contributions
od+0.017
es+0.016
hell+0.015
ement+0.015
izards+0.015
Neg logit contributions
burn-0.018
coat-0.017
 street-0.016
ety-0.014
 Kathy-0.013
Token be
Token ID307
Feature activation+6.86e-03

Pos logit contributions
burn+0.104
coat+0.091
 street+0.085
ety+0.071
 yard+0.066
Neg logit contributions
od-0.145
ement-0.145
izards-0.141
es-0.138
bridge-0.136
Token more
Token ID517
Feature activation+6.97e-02

Pos logit contributions
burn+0.013
 street+0.013
coat+0.013
 wander+0.011
ety+0.010
Neg logit contributions
es-0.012
od-0.011
ement-0.011
bridge-0.011
izards-0.011
Token careful
Token ID8161
Feature activation+3.89e-03

Pos logit contributions
burn+0.143
coat+0.127
 street+0.120
 wander+0.111
ety+0.110
Neg logit contributions
od-0.117
ement-0.117
es-0.117
 pounds-0.115
izards-0.115
Token with
Token ID351
Feature activation+2.16e-03

Pos logit contributions
burn+0.008
coat+0.007
 street+0.007
ety+0.006
 wander+0.006
Neg logit contributions
ement-0.007
od-0.007
es-0.007
izards-0.007
bridge-0.006
Token our
Token ID674
Feature activation+2.20e-03

Pos logit contributions
burn+0.004
coat+0.004
 street+0.004
ety+0.003
 yard+0.003
Neg logit contributions
ement-0.004
od-0.004
izards-0.004
es-0.004
bridge-0.004
Token toys
Token ID14958
Feature activation+3.81e-02

Pos logit contributions
burn+0.004
coat+0.004
 street+0.003
ety+0.003
 Kathy+0.003
Neg logit contributions
ement-0.004
izards-0.004
od-0.004
es-0.004
 pounds-0.004
Token."
Token ID526
Feature activation-1.08e-02

Pos logit contributions
burn+0.080
coat+0.073
 street+0.072
ety+0.062
 yard+0.061
Neg logit contributions
ement-0.065
od-0.063
izards-0.061
es-0.059
bridge-0.058
Token
Token ID198
Feature activation+1.59e-03

Pos logit contributions
ement+0.022
od+0.021
izards+0.021
bridge+0.020
es+0.020
Neg logit contributions
burn-0.019
 street-0.017
coat-0.017
ety-0.014
 yard-0.014
Token
Token ID198
Feature activation-2.76e-03

Pos logit contributions
burn+0.003
 street+0.002
coat+0.002
 yard+0.002
ety+0.002
Neg logit contributions
ement-0.003
od-0.003
izards-0.003
bridge-0.003
es-0.003
TokenFrom
Token ID4863
Feature activation-1.86e-02

Pos logit contributions
ement+0.005
od+0.005
izards+0.005
es+0.005
bridge+0.005
Neg logit contributions
burn-0.005
coat-0.004
 street-0.004
ety-0.004
 yard-0.003
TokenI
Token ID40
Feature activation+4.12e-02

Pos logit contributions
burn+0.005
coat+0.004
 street+0.004
ety+0.003
 yard+0.003
Neg logit contributions
ement-0.005
od-0.005
izards-0.005
es-0.005
bridge-0.005
Token love
Token ID1842
Feature activation+2.49e-02

Pos logit contributions
burn+0.069
coat+0.061
 street+0.060
ety+0.049
 yard+0.049
Neg logit contributions
ement-0.089
od-0.086
izards-0.085
es-0.082
bridge-0.081
Token you
Token ID345
Feature activation+9.99e-03

Pos logit contributions
burn+0.053
 street+0.047
coat+0.047
 raining+0.041
 yard+0.040
Neg logit contributions
ement-0.044
od-0.041
izards-0.040
bridge-0.039
hell-0.038
Token".
Token ID1911
Feature activation-2.33e-02

Pos logit contributions
burn+0.020
coat+0.018
 street+0.018
 yard+0.015
ety+0.015
Neg logit contributions
ement-0.018
od-0.018
izards-0.018
bridge-0.017
es-0.016
Token
Token ID198
Feature activation-5.22e-04

Pos logit contributions
ement+0.047
izards+0.046
od+0.045
bridge+0.045
ils+0.045
Neg logit contributions
burn-0.040
 street-0.036
coat-0.036
 Dog-0.030
ety-0.030
Token
Token ID198
Feature activation-4.95e-03

Pos logit contributions
ement+0.001
izards+0.001
od+0.001
bridge+0.001
ils+0.001
Neg logit contributions
burn-0.001
 street-0.001
coat-0.001
 yard-0.001
 Dog-0.001
TokenAl
Token ID2348
Feature activation-3.22e-02

Pos logit contributions
ement+0.010
izards+0.010
od+0.010
bridge+0.009
es+0.009
Neg logit contributions
burn-0.009
coat-0.008
 street-0.008
ety-0.006
 yard-0.006
Tokenina
Token ID1437
Feature activation-4.93e-03

Pos logit contributions
ement+0.064
izards+0.062
bridge+0.060
od+0.059
hell+0.058
Neg logit contributions
burn-0.056
coat-0.050
 street-0.047
ety-0.044
any-0.041
Token felt
Token ID2936
Feature activation-7.19e-03

Pos logit contributions
ement+0.009
od+0.009
izards+0.009
bridge+0.008
es+0.008
Neg logit contributions
burn-0.009
coat-0.009
 street-0.008
 yard-0.007
ety-0.007
Token much
Token ID881
Feature activation+4.74e-02

Pos logit contributions
ement+0.014
od+0.014
izards+0.013
es+0.013
bridge+0.013
Neg logit contributions
burn-0.013
coat-0.012
 street-0.012
ety-0.010
 yard-0.010
Token better
Token ID1365
Feature activation+2.21e-02

Pos logit contributions
burn+0.086
coat+0.077
 street+0.076
ety+0.065
 yard+0.063
Neg logit contributions
ement-0.096
od-0.090
izards-0.089
es-0.087
bridge-0.086
Token and
Token ID290
Feature activation+1.17e-04

Pos logit contributions
burn+0.032
coat+0.030
 street+0.029
 yard+0.025
ety+0.023
Neg logit contributions
ement-0.047
od-0.046
bridge-0.045
izards-0.044
olo-0.042
Token exciting
Token ID7895
Feature activation-1.37e-02

Pos logit contributions
burn+0.000
 street+0.000
coat+0.000
ety+0.000
 yard+0.000
Neg logit contributions
ement-0.000
od-0.000
izards-0.000
es-0.000
bridge-0.000
Token.
Token ID13
Feature activation+1.08e-02

Pos logit contributions
ement+0.031
od+0.030
bridge+0.029
izards+0.028
olo+0.028
Neg logit contributions
burn-0.019
 street-0.019
coat-0.018
 wander-0.016
 yard-0.015
Token So
Token ID1406
Feature activation+3.39e-02

Pos logit contributions
burn+0.023
coat+0.021
 street+0.020
ety+0.017
 yard+0.017
Neg logit contributions
ement-0.018
od-0.017
izards-0.017
es-0.017
bridge-0.016
Token he
Token ID339
Feature activation+7.55e-04

Pos logit contributions
burn+0.069
coat+0.063
 street+0.061
ety+0.053
 yard+0.052
Neg logit contributions
ement-0.060
od-0.058
izards-0.056
es-0.055
bridge-0.053
Token decided
Token ID3066
Feature activation+7.54e-03

Pos logit contributions
burn+0.001
coat+0.001
 street+0.001
ety+0.001
 yard+0.001
Neg logit contributions
ement-0.002
od-0.002
izards-0.002
es-0.002
bridge-0.001
Token to
Token ID284
Feature activation+1.53e-02

Pos logit contributions
burn+0.012
coat+0.010
 street+0.010
ety+0.008
 yard+0.008
Neg logit contributions
ement-0.017
od-0.017
izards-0.017
es-0.016
bridge-0.016
Token travel
Token ID3067
Feature activation+2.65e-02

Pos logit contributions
burn+0.025
coat+0.022
 street+0.021
ety+0.018
 raining+0.017
Neg logit contributions
od-0.032
izards-0.032
ement-0.031
es-0.030
bridge-0.030
Token to
Token ID284
Feature activation-2.22e-02

Pos logit contributions
burn+0.035
coat+0.031
 street+0.031
 yard+0.023
ety+0.023
Neg logit contributions
ement-0.067
od-0.065
izards-0.064
es-0.061
bridge-0.061
Token find
Token ID1064
Feature activation-4.27e-07

Pos logit contributions
ement+0.042
od+0.041
izards+0.040
es+0.039
bridge+0.038
Neg logit contributions
burn-0.042
coat-0.038
 street-0.037
ety-0.032
 yard-0.031
Token something
Token ID1223
Feature activation-3.91e-02

Feature not active on prev token;
no predictions were affected.
Token
Token ID198
Feature activation-1.29e-02

Pos logit contributions
ement+0.024
izards+0.023
od+0.023
ils+0.023
sters+0.022
Neg logit contributions
burn-0.013
 street-0.012
coat-0.011
 yard-0.010
 Dog-0.009
TokenJake
Token ID43930
Feature activation-1.86e-02

Pos logit contributions
ement+0.029
izards+0.028
od+0.027
sters+0.027
ocket+0.026
Neg logit contributions
burn-0.019
 street-0.018
coat-0.017
 yard-0.015
 raining-0.014
Token was
Token ID373
Feature activation+4.41e-03

Pos logit contributions
ement+0.034
od+0.033
izards+0.032
es+0.031
bridge+0.031
Neg logit contributions
burn-0.037
coat-0.033
 street-0.033
ety-0.028
 yard-0.028
Token so
Token ID523
Feature activation+3.07e-04

Pos logit contributions
burn+0.010
coat+0.009
 street+0.009
ety+0.008
 yard+0.008
Neg logit contributions
ement-0.007
od-0.007
bridge-0.006
es-0.006
izards-0.006
Token thankful
Token ID25535
Feature activation-2.69e-02

Pos logit contributions
burn+0.001
coat+0.001
 street+0.001
ety+0.000
 yard+0.000
Neg logit contributions
ement-0.001
od-0.001
izards-0.001
es-0.001
bridge-0.001
Token for
Token ID329
Feature activation-3.30e-02

Pos logit contributions
ement+0.057
od+0.057
izards+0.056
bridge+0.055
es+0.053
Neg logit contributions
burn-0.043
 street-0.039
coat-0.038
 yard-0.032
 wander-0.031
Token his
Token ID465
Feature activation+3.74e-02

Pos logit contributions
od+0.072
ement+0.072
izards+0.071
sters+0.070
hell+0.070
Neg logit contributions
burn-0.046
 street-0.043
coat-0.037
 Dog-0.037
 raining-0.036
Token body
Token ID1767
Feature activation+4.26e-02

Pos logit contributions
burn+0.069
coat+0.061
 street+0.060
ety+0.054
 Kathy+0.049
Neg logit contributions
ement-0.072
od-0.067
hell-0.064
 pounds-0.064
izards-0.063
Token's
Token ID338
Feature activation+2.21e-02

Pos logit contributions
burn+0.080
coat+0.071
 street+0.071
ety+0.060
 yard+0.059
Neg logit contributions
ement-0.081
od-0.079
izards-0.077
es-0.076
bridge-0.074
Token power
Token ID1176
Feature activation+3.68e-02

Pos logit contributions
burn+0.043
coat+0.039
 street+0.038
ety+0.035
 Kathy+0.031
Neg logit contributions
ement-0.039
od-0.036
hell-0.035
 pounds-0.035
es-0.035
Token to
Token ID284
Feature activation-2.36e-02

Pos logit contributions
burn+0.071
coat+0.063
 street+0.062
ety+0.054
 yard+0.052
Neg logit contributions
ement-0.069
od-0.067
izards-0.065
es-0.064
bridge-0.062
Token Lily
Token ID20037
Feature activation+4.15e-02

Pos logit contributions
burn+0.052
coat+0.045
 street+0.045
 rag+0.038
 Dog+0.038
Neg logit contributions
ement-0.076
od-0.075
izards-0.072
es-0.070
ils-0.070
Token.
Token ID13
Feature activation+3.94e-02

Pos logit contributions
burn+0.086
coat+0.078
 street+0.077
ety+0.066
 yard+0.065
Neg logit contributions
ement-0.072
od-0.070
izards-0.069
es-0.066
bridge-0.065
Token That
Token ID1320
Feature activation-2.75e-02

Pos logit contributions
burn+0.087
coat+0.079
 street+0.078
ety+0.068
 yard+0.066
Neg logit contributions
ement-0.063
od-0.061
izards-0.060
es-0.058
bridge-0.056
Token sounds
Token ID5238
Feature activation-6.35e-03

Pos logit contributions
ement+0.028
od+0.027
es+0.027
hell+0.025
bridge+0.025
Neg logit contributions
burn-0.071
coat-0.066
 street-0.063
ety-0.062
 Kathy-0.057
Token fun
Token ID1257
Feature activation+3.32e-02

Pos logit contributions
ement+0.015
od+0.014
izards+0.014
es+0.014
bridge+0.013
Neg logit contributions
burn-0.009
 street-0.009
coat-0.008
 yard-0.007
ety-0.007
Token."
Token ID526
Feature activation-3.00e-02

Pos logit contributions
burn+0.062
coat+0.058
 street+0.058
 yard+0.049
ety+0.048
Neg logit contributions
ement-0.063
od-0.061
izards-0.059
bridge-0.058
es-0.055
Token Max
Token ID5436
Feature activation-9.55e-03

Pos logit contributions
od+0.051
ement+0.050
es+0.050
izards+0.049
bridge+0.045
Neg logit contributions
burn-0.061
coat-0.055
 street-0.052
ety-0.045
 pasture-0.043
Token said
Token ID531
Feature activation-2.35e-02

Pos logit contributions
ement+0.017
od+0.017
izards+0.016
bridge+0.016
 pounds+0.015
Neg logit contributions
burn-0.019
coat-0.018
 street-0.017
ety-0.015
 yard-0.015
Token,
Token ID11
Feature activation-6.14e-03

Pos logit contributions
ement+0.040
od+0.039
es+0.039
izards+0.037
hell+0.035
Neg logit contributions
burn-0.049
 street-0.046
coat-0.044
 yard-0.039
ety-0.039
Token as
Token ID355
Feature activation+3.47e-02

Pos logit contributions
ement+0.011
od+0.011
es+0.010
bridge+0.010
rily+0.010
Neg logit contributions
burn-0.011
coat-0.010
 street-0.010
ety-0.010
 yard-0.009
Token they
Token ID484
Feature activation-2.88e-02

Pos logit contributions
burn+0.081
coat+0.075
 street+0.074
ety+0.065
 yard+0.064
Neg logit contributions
ement-0.050
od-0.049
izards-0.048
es-0.046
bridge-0.044
Token the
Token ID262
Feature activation-9.38e-03

Pos logit contributions
burn+0.042
 street+0.038
coat+0.037
ety+0.032
 rag+0.032
Neg logit contributions
ement-0.046
od-0.044
izards-0.044
bridge-0.042
ocket-0.041
Token truck
Token ID7779
Feature activation+4.39e-03

Pos logit contributions
ement+0.020
od+0.019
bridge+0.019
izards+0.019
 pounds+0.018
Neg logit contributions
burn-0.015
coat-0.013
 street-0.013
ety-0.011
 wander-0.010
Token out
Token ID503
Feature activation-1.61e-03

Pos logit contributions
burn+0.008
coat+0.007
 street+0.007
ety+0.006
 yard+0.006
Neg logit contributions
ement-0.008
od-0.008
es-0.008
izards-0.008
hell-0.007
Token of
Token ID286
Feature activation-1.02e-02

Pos logit contributions
ement+0.003
izards+0.003
od+0.003
bridge+0.002
es+0.002
Neg logit contributions
burn-0.003
 street-0.003
coat-0.003
 yard-0.003
 raining-0.003
Token the
Token ID262
Feature activation-1.35e-02

Pos logit contributions
ement+0.016
od+0.015
izards+0.015
es+0.014
bridge+0.014
Neg logit contributions
burn-0.022
coat-0.021
 street-0.019
ety-0.018
 wander-0.017
Token trap
Token ID12840
Feature activation-4.77e-02

Pos logit contributions
ement+0.027
bridge+0.025
 pounds+0.024
od+0.024
hell+0.024
Neg logit contributions
burn-0.024
coat-0.021
ety-0.018
 street-0.018
 Kathy-0.016
Token.
Token ID13
Feature activation-5.71e-03

Pos logit contributions
ement+0.090
od+0.087
izards+0.086
bridge+0.081
es+0.081
Neg logit contributions
burn-0.090
coat-0.083
 street-0.082
 yard-0.069
ety-0.068
Token The
Token ID383
Feature activation+1.15e-02

Pos logit contributions
ement+0.012
od+0.012
izards+0.012
ils+0.012
bridge+0.011
Neg logit contributions
burn-0.009
 street-0.008
coat-0.008
 yard-0.007
ety-0.007
Token truck
Token ID7779
Feature activation+6.41e-03

Pos logit contributions
burn+0.020
coat+0.017
 street+0.017
ety+0.014
 yard+0.013
Neg logit contributions
ement-0.024
od-0.023
izards-0.023
bridge-0.022
es-0.022
Token was
Token ID373
Feature activation-6.72e-03

Pos logit contributions
burn+0.011
 street+0.010
coat+0.010
 yard+0.008
 tire+0.008
Neg logit contributions
izards-0.013
ement-0.013
od-0.013
 pounds-0.012
bridge-0.012
Token free
Token ID1479
Feature activation+5.30e-02

Pos logit contributions
ement+0.012
od+0.012
bridge+0.011
es+0.011
izards+0.011
Neg logit contributions
burn-0.013
coat-0.012
 street-0.012
ety-0.010
 wander-0.010
Token her
Token ID607
Feature activation+1.57e-02

Pos logit contributions
burn+0.020
 street+0.018
coat+0.018
ety+0.015
 yard+0.015
Neg logit contributions
ement-0.017
od-0.017
izards-0.017
es-0.017
hell-0.016
Token reach
Token ID3151
Feature activation+2.82e-04

Pos logit contributions
burn+0.034
coat+0.031
 street+0.030
ety+0.026
 Kathy+0.026
Neg logit contributions
od-0.024
es-0.024
ement-0.023
izards-0.022
hell-0.022
Token her
Token ID607
Feature activation-2.92e-03

Pos logit contributions
burn+0.001
coat+0.001
 street+0.001
ety+0.000
 yard+0.000
Neg logit contributions
ement-0.000
od-0.000
izards-0.000
es-0.000
hell-0.000
Token ball
Token ID2613
Feature activation+1.17e-02

Pos logit contributions
ement+0.006
od+0.005
es+0.005
izards+0.005
hell+0.005
Neg logit contributions
burn-0.005
coat-0.005
 street-0.005
any-0.004
ety-0.004
Token in
Token ID287
Feature activation-7.68e-03

Pos logit contributions
burn+0.026
 street+0.023
coat+0.023
ety+0.020
 Kathy+0.019
Neg logit contributions
ement-0.018
od-0.018
izards-0.017
es-0.017
hell-0.016
Token the
Token ID262
Feature activation-3.51e-02

Pos logit contributions
ement+0.013
od+0.013
izards+0.012
es+0.012
bridge+0.012
Neg logit contributions
burn-0.016
coat-0.015
 street-0.014
ety-0.013
 yard-0.012
Token west
Token ID7421
Feature activation+7.74e-03

Pos logit contributions
ement+0.068
 lid+0.065
bridge+0.064
hell+0.062
boards+0.062
Neg logit contributions
burn-0.061
coat-0.054
ety-0.044
any-0.044
 blowing-0.042
Token.
Token ID13
Feature activation-4.97e-03

Pos logit contributions
burn+0.018
coat+0.016
 street+0.015
ety+0.014
 rag+0.013
Neg logit contributions
ement-0.012
od-0.011
es-0.011
izards-0.011
bridge-0.010
Token
Token ID198
Feature activation-6.09e-03

Pos logit contributions
ement+0.010
od+0.010
izards+0.009
es+0.009
bridge+0.009
Neg logit contributions
burn-0.009
coat-0.008
 street-0.008
ety-0.007
 yard-0.007
Token
Token ID198
Feature activation-9.62e-03

Pos logit contributions
ement+0.012
od+0.012
izards+0.012
es+0.011
bridge+0.011
Neg logit contributions
burn-0.011
coat-0.010
 street-0.009
ety-0.008
 yard-0.008
TokenSpot
Token ID32565
Feature activation+2.08e-03

Pos logit contributions
ement+0.018
od+0.017
es+0.017
izards+0.017
hell+0.017
Neg logit contributions
burn-0.018
 street-0.016
coat-0.016
ety-0.014
 raining-0.014
Token he
Token ID339
Feature activation-2.33e-02

Pos logit contributions
ement+0.017
od+0.016
izards+0.016
bridge+0.015
es+0.015
Neg logit contributions
burn-0.022
 street-0.020
coat-0.020
ety-0.017
 yard-0.017
Token was
Token ID373
Feature activation+1.15e-03

Pos logit contributions
ement+0.039
od+0.038
izards+0.037
bridge+0.035
es+0.035
Neg logit contributions
burn-0.050
coat-0.045
 street-0.045
ety-0.039
 yard-0.039
Token scared
Token ID12008
Feature activation+4.31e-02

Pos logit contributions
burn+0.003
coat+0.002
 street+0.002
 yard+0.002
 rag+0.002
Neg logit contributions
izards-0.002
od-0.002
ement-0.002
es-0.002
bridge-0.002
Token that
Token ID326
Feature activation+1.77e-02

Pos logit contributions
burn+0.096
coat+0.087
 street+0.086
ety+0.074
 yard+0.074
Neg logit contributions
ement-0.070
od-0.067
izards-0.066
es-0.063
bridge-0.061
Token he
Token ID339
Feature activation-5.70e-03

Pos logit contributions
burn+0.040
 street+0.037
coat+0.036
ety+0.032
 yard+0.032
Neg logit contributions
ement-0.028
od-0.026
izards-0.026
bridge-0.024
es-0.024
Token didn
Token ID1422
Feature activation-5.30e-02

Pos logit contributions
ement+0.009
od+0.009
izards+0.009
es+0.009
bridge+0.008
Neg logit contributions
burn-0.012
coat-0.011
 street-0.011
ety-0.010
 yard-0.009
Token't
Token ID470
Feature activation+4.87e-02

Pos logit contributions
od+0.075
ement+0.075
izards+0.071
es+0.070
bridge+0.065
Neg logit contributions
burn-0.124
coat-0.117
 street-0.116
ety-0.104
 yard-0.101
Token belong
Token ID5594
Feature activation+1.41e-02

Pos logit contributions
burn+0.097
 street+0.087
coat+0.087
 yard+0.075
 driveway+0.072
Neg logit contributions
od-0.086
izards-0.084
hell-0.080
es-0.078
ement-0.076
Token.
Token ID13
Feature activation+1.25e-02

Pos logit contributions
burn+0.024
 street+0.021
coat+0.021
 yard+0.017
 rag+0.016
Neg logit contributions
ement-0.029
od-0.029
izards-0.029
es-0.028
hell-0.026
Token
Token ID198
Feature activation+5.98e-03

Pos logit contributions
burn+0.021
 street+0.019
coat+0.019
ety+0.016
 yard+0.016
Neg logit contributions
ement-0.026
od-0.026
izards-0.025
bridge-0.024
es-0.024
Token
Token ID198
Feature activation+1.30e-03

Pos logit contributions
burn+0.009
 street+0.008
coat+0.008
ety+0.007
 yard+0.007
Neg logit contributions
ement-0.013
od-0.013
izards-0.012
bridge-0.012
es-0.012
Token if
Token ID611
Feature activation-5.11e-03

Pos logit contributions
bridge+0.044
ement+0.044
od+0.043
izards+0.043
ocket+0.042
Neg logit contributions
burn-0.030
 street-0.028
coat-0.026
ety-0.024
 raining-0.023
Token he
Token ID339
Feature activation-2.64e-02

Pos logit contributions
ement+0.009
od+0.008
bridge+0.008
izards+0.008
hell+0.008
Neg logit contributions
burn-0.010
 street-0.010
coat-0.009
 Dog-0.008
 wander-0.008
Token told
Token ID1297
Feature activation-3.57e-02

Pos logit contributions
ement+0.051
od+0.048
izards+0.048
bridge+0.047
hell+0.045
Neg logit contributions
burn-0.047
 street-0.044
coat-0.044
 wander-0.037
ety-0.037
Token them
Token ID606
Feature activation+1.38e-02

Pos logit contributions
ement+0.059
bridge+0.057
od+0.056
izards+0.054
sters+0.053
Neg logit contributions
burn-0.069
 street-0.067
 Dog-0.061
 wander-0.059
coat-0.059
Token this
Token ID428
Feature activation-2.41e-02

Pos logit contributions
burn+0.023
 street+0.022
coat+0.020
 wander+0.020
 yard+0.019
Neg logit contributions
ement-0.027
bridge-0.025
od-0.024
izards-0.024
ocket-0.023
Token story
Token ID1621
Feature activation-9.13e-02

Pos logit contributions
od+0.047
ement+0.047
izards+0.046
es+0.044
bridge+0.043
Neg logit contributions
burn-0.041
 street-0.041
coat-0.038
 yard-0.034
 raining-0.032
Token.
Token ID13
Feature activation-1.33e-03

Pos logit contributions
ement+0.168
od+0.163
izards+0.159
bridge+0.150
sters+0.149
Neg logit contributions
burn-0.165
 street-0.159
coat-0.155
 yard-0.131
 raining-0.127
Token From
Token ID3574
Feature activation-1.17e-02

Pos logit contributions
ement+0.003
od+0.003
izards+0.003
ils+0.003
bridge+0.003
Neg logit contributions
burn-0.002
 street-0.002
coat-0.002
 yard-0.002
 Dog-0.002
Token then
Token ID788
Feature activation+5.63e-02

Pos logit contributions
ement+0.018
od+0.018
izards+0.017
es+0.017
bridge+0.016
Neg logit contributions
burn-0.026
coat-0.024
 street-0.024
ety-0.021
 yard-0.021
Token on
Token ID319
Feature activation+1.95e-03

Pos logit contributions
burn+0.110
coat+0.100
 street+0.099
ety+0.084
 yard+0.083
Neg logit contributions
ement-0.104
od-0.101
izards-0.098
es-0.096
bridge-0.093
Token,
Token ID11
Feature activation+8.72e-03

Pos logit contributions
burn+0.003
 street+0.003
coat+0.003
 yard+0.002
 Dog+0.002
Neg logit contributions
od-0.004
ement-0.004
izards-0.004
bridge-0.004
hell-0.004
Token on
Token ID319
Feature activation-1.90e-02

Pos logit contributions
burn+0.021
 street+0.020
coat+0.019
ety+0.018
 yard+0.017
Neg logit contributions
ement-0.016
es-0.016
od-0.015
bridge-0.015
izards-0.015
Token his
Token ID465
Feature activation-1.59e-02

Pos logit contributions
ement+0.035
od+0.033
izards+0.032
es+0.032
bridge+0.030
Neg logit contributions
burn-0.038
coat-0.034
 street-0.033
ety-0.030
 yard-0.028
Token paws
Token ID49193
Feature activation+2.54e-02

Pos logit contributions
ement+0.032
od+0.030
izards+0.030
es+0.029
hell+0.029
Neg logit contributions
burn-0.029
coat-0.025
 street-0.023
ety-0.022
 raining-0.019
Token and
Token ID290
Feature activation-1.31e-02

Pos logit contributions
burn+0.050
 street+0.045
coat+0.043
ety+0.039
 yard+0.037
Neg logit contributions
ement-0.046
od-0.043
es-0.043
izards-0.041
hell-0.040
Token listen
Token ID6004
Feature activation+8.34e-05

Pos logit contributions
ement+0.027
od+0.026
izards+0.025
es+0.025
bridge+0.024
Neg logit contributions
burn-0.023
coat-0.020
 street-0.020
ety-0.017
 yard-0.016
Token int
Token ID493
Feature activation-1.02e-01

Pos logit contributions
burn+0.000
coat+0.000
 street+0.000
 raining+0.000
 yard+0.000
Neg logit contributions
ement-0.000
izards-0.000
od-0.000
bridge-0.000
es-0.000
Tokenently
Token ID1473
Feature activation+4.42e-03

Pos logit contributions
od+0.106
izards+0.103
bridge+0.099
ement+0.097
hell+0.097
Neg logit contributions
burn-0.258
 street-0.230
coat-0.230
 raining-0.205
 blowing-0.204
Token to
Token ID284
Feature activation-2.71e-02

Pos logit contributions
burn+0.009
coat+0.008
 street+0.008
ety+0.007
 yard+0.006
Neg logit contributions
ement-0.008
od-0.008
izards-0.008
es-0.007
bridge-0.007
Token her
Token ID607
Feature activation+9.11e-03

Pos logit contributions
ement+0.049
od+0.048
izards+0.047
es+0.045
bridge+0.044
Neg logit contributions
burn-0.054
coat-0.049
 street-0.048
ety-0.041
 yard-0.040
Token until
Token ID1566
Feature activation-2.32e-02

Pos logit contributions
burn+0.017
 street+0.015
coat+0.015
 yard+0.012
 wander+0.012
Neg logit contributions
ement-0.018
od-0.018
izards-0.017
bridge-0.017
es-0.016
Token she
Token ID673
Feature activation-3.87e-02

Pos logit contributions
ement+0.035
od+0.034
izards+0.033
es+0.032
bridge+0.031
Neg logit contributions
burn-0.053
coat-0.049
 street-0.048
ety-0.042
 yard-0.042
Token."
Token ID526
Feature activation-1.78e-02

Pos logit contributions
burn+0.077
coat+0.069
 street+0.069
ety+0.060
 yard+0.058
Neg logit contributions
ement-0.062
od-0.061
izards-0.059
es-0.059
bridge-0.056
Token Lily
Token ID20037
Feature activation+3.87e-03

Pos logit contributions
ement+0.039
od+0.038
izards+0.037
es+0.036
ils+0.036
Neg logit contributions
burn-0.029
 street-0.026
coat-0.026
ety-0.022
 yard-0.021
Token says
Token ID1139
Feature activation-2.53e-02

Pos logit contributions
burn+0.008
 street+0.008
coat+0.008
 yard+0.007
ety+0.007
Neg logit contributions
ement-0.006
od-0.006
izards-0.006
bridge-0.006
es-0.006
Token,
Token ID11
Feature activation-2.64e-03

Pos logit contributions
ement+0.051
od+0.050
izards+0.049
bridge+0.047
es+0.047
Neg logit contributions
burn-0.045
coat-0.040
 street-0.039
ety-0.033
 yard-0.032
Token "
Token ID366
Feature activation+1.75e-02

Pos logit contributions
ement+0.004
od+0.004
izards+0.004
es+0.004
bridge+0.004
Neg logit contributions
burn-0.006
coat-0.005
 street-0.005
ety-0.004
 yard-0.004
TokenReally
Token ID26392
Feature activation-9.12e-02

Pos logit contributions
burn+0.031
coat+0.027
 street+0.026
 yard+0.022
ety+0.022
Neg logit contributions
ement-0.037
od-0.035
izards-0.034
es-0.034
bridge-0.033
Token?
Token ID30
Feature activation+2.90e-02

Pos logit contributions
ement+0.214
od+0.212
izards+0.211
bridge+0.209
ils+0.200
Neg logit contributions
burn-0.127
coat-0.106
 street-0.101
ety-0.087
 yard-0.082
Token You
Token ID921
Feature activation-4.45e-02

Pos logit contributions
burn+0.068
coat+0.062
 street+0.062
ety+0.054
 yard+0.053
Neg logit contributions
ement-0.043
od-0.041
izards-0.040
es-0.039
bridge-0.037
Token will
Token ID481
Feature activation-1.13e-02

Pos logit contributions
ement+0.063
od+0.060
izards+0.058
es+0.055
bridge+0.054
Neg logit contributions
burn-0.107
coat-0.099
 street-0.098
 yard-0.086
ety-0.086
Token let
Token ID1309
Feature activation-5.80e-03

Pos logit contributions
od+0.021
ement+0.021
izards+0.020
bridge+0.020
hell+0.020
Neg logit contributions
burn-0.021
coat-0.018
 street-0.018
ety-0.016
 yard-0.015
Token me
Token ID502
Feature activation-3.20e-03

Pos logit contributions
ement+0.009
od+0.009
izards+0.009
es+0.009
bridge+0.008
Neg logit contributions
burn-0.013
coat-0.012
 street-0.012
ety-0.010
 yard-0.010
Token been
Token ID587
Feature activation-1.06e-02

Pos logit contributions
burn+0.010
coat+0.009
 street+0.008
ety+0.007
 yard+0.007
Neg logit contributions
ement-0.010
od-0.010
izards-0.009
es-0.009
bridge-0.009
Token big
Token ID1263
Feature activation+2.87e-02

Pos logit contributions
od+0.020
ement+0.020
izards+0.020
es+0.019
 pounds+0.018
Neg logit contributions
burn-0.020
coat-0.018
 street-0.018
ety-0.015
 yard-0.015
Token and
Token ID290
Feature activation+5.03e-03

Pos logit contributions
burn+0.053
coat+0.048
 street+0.048
 yard+0.040
ety+0.040
Neg logit contributions
ement-0.055
od-0.054
izards-0.053
es-0.051
bridge-0.050
Token strong
Token ID1913
Feature activation+1.95e-02

Pos logit contributions
burn+0.008
coat+0.007
 street+0.007
ety+0.006
 yard+0.006
Neg logit contributions
ement-0.011
od-0.011
izards-0.010
es-0.010
bridge-0.010
Token.
Token ID13
Feature activation-3.38e-03

Pos logit contributions
burn+0.039
coat+0.035
 street+0.035
ety+0.029
 yard+0.029
Neg logit contributions
ement-0.035
od-0.034
izards-0.034
es-0.032
bridge-0.032
Token How
Token ID1374
Feature activation-1.07e-01

Pos logit contributions
ement+0.007
izards+0.007
od+0.007
es+0.007
bridge+0.007
Neg logit contributions
burn-0.005
 street-0.005
coat-0.005
 yard-0.004
 raining-0.004
Token could
Token ID714
Feature activation+1.09e-02

Pos logit contributions
ement+0.187
sters+0.157
rily+0.154
izards+0.153
 ounces+0.152
Neg logit contributions
burn-0.204
coat-0.199
 street-0.198
 yard-0.183
 raining-0.182
Token it
Token ID340
Feature activation-2.41e-02

Pos logit contributions
burn+0.022
 street+0.020
coat+0.019
 wander+0.017
 Dog+0.017
Neg logit contributions
ement-0.020
od-0.018
izards-0.018
hell-0.018
bridge-0.017
Token be
Token ID307
Feature activation-1.26e-02

Pos logit contributions
ement+0.054
od+0.051
izards+0.051
es+0.050
bridge+0.049
Neg logit contributions
burn-0.038
 street-0.034
coat-0.033
 wander-0.027
ety-0.027
Token shrinking
Token ID27382
Feature activation-1.42e-02

Pos logit contributions
od+0.024
ement+0.024
izards+0.024
es+0.023
bridge+0.022
Neg logit contributions
burn-0.024
coat-0.021
 street-0.021
ety-0.017
 yard-0.017
Token all
Token ID477
Feature activation+5.26e-02

Pos logit contributions
ement+0.028
od+0.027
izards+0.026
bridge+0.026
es+0.025
Neg logit contributions
burn-0.026
 street-0.023
coat-0.023
 yard-0.019
 raining-0.019
Token a
Token ID257
Feature activation-2.64e-02

Pos logit contributions
izards+0.013
ement+0.013
bridge+0.012
od+0.012
es+0.012
Neg logit contributions
burn-0.009
coat-0.008
 street-0.008
 rag-0.006
 yard-0.006
Token little
Token ID1310
Feature activation+9.80e-03

Pos logit contributions
ement+0.052
od+0.051
izards+0.050
es+0.048
bridge+0.047
Neg logit contributions
burn-0.049
coat-0.044
 street-0.043
 yard-0.036
ety-0.036
Token note
Token ID3465
Feature activation-9.33e-02

Pos logit contributions
burn+0.019
coat+0.017
 street+0.017
ety+0.014
 yard+0.014
Neg logit contributions
ement-0.018
od-0.018
izards-0.017
es-0.017
bridge-0.016
Token on
Token ID319
Feature activation-2.63e-02

Pos logit contributions
ement+0.174
od+0.168
izards+0.168
es+0.156
bridge+0.156
Neg logit contributions
burn-0.180
coat-0.163
 street-0.160
ety-0.133
 yard-0.133
Token her
Token ID607
Feature activation-1.70e-02

Pos logit contributions
ement+0.050
izards+0.050
bridge+0.046
od+0.045
sters+0.044
Neg logit contributions
burn-0.047
 street-0.042
coat-0.041
 rag-0.039
 Dog-0.037
Token slice
Token ID16416
Feature activation-9.47e-02

Pos logit contributions
ement+0.032
izards+0.031
od+0.031
es+0.030
bridge+0.030
Neg logit contributions
burn-0.032
 street-0.029
coat-0.029
 yard-0.025
 rag-0.024
Token.
Token ID13
Feature activation+5.46e-03

Pos logit contributions
ement+0.187
izards+0.186
od+0.183
bridge+0.171
 pounds+0.171
Neg logit contributions
burn-0.164
coat-0.155
 street-0.148
 yard-0.126
ety-0.123
Token The
Token ID383
Feature activation+1.44e-02

Pos logit contributions
burn+0.010
coat+0.009
 street+0.009
ety+0.007
 yard+0.007
Neg logit contributions
ement-0.011
od-0.011
izards-0.010
es-0.010
bridge-0.010
Token note
Token ID3465
Feature activation-8.29e-02

Pos logit contributions
burn+0.026
 street+0.025
coat+0.024
 yard+0.021
 rag+0.020
Neg logit contributions
ement-0.028
izards-0.027
od-0.027
es-0.026
bridge-0.025
Token said
Token ID531
Feature activation-2.89e-02

Pos logit contributions
izards+0.163
od+0.158
ement+0.157
 pounds+0.156
olo+0.152
Neg logit contributions
burn-0.136
 street-0.130
coat-0.121
 rag-0.104
 yard-0.103
Token '
Token ID705
Feature activation+2.15e-02

Pos logit contributions
izards+0.064
ement+0.062
 pounds+0.061
ils+0.059
 kilograms+0.058
Neg logit contributions
burn-0.037
coat-0.034
 Dog-0.031
 street-0.030
 raining-0.027