TOP ACTIVATIONS
MAX = 8.433

her doll and watched in amaz ement as it slowly flew
but they ran back in amaz ement ! The post had
and pointed at it in amaz ement . The bird stopped
just stared at him in amaz ement . So , he
the bush and watched in amaz ement as it flew away
door , and to her amaz ement , she could see
pond and everyone watched in amaz ement as her thread gl
The girl stepped back in amaz ement as the dark started
her mom my watched in amaz ement as the machine flew
hill and everyone watched in amaz ement . The rock was
his mummy , trembling in amaz ement . They had just
THE BE LL WHEN YOU FE EL LIKE IT ".
baby le opard watched in amaz ement as the lion flex
He looked at it in amaz ement and smiled . Now
He looked at it in amaz ement and smiled . Now
. Everyone watched him in amaz ement and cheered .
. Tim my watched in amaz ement as the black board
uddle !" she said in amaz ement .
gazed at the butterfly in amaz ement . But
at the red blocks in amaz ement . He couldn 't

MIN ACTIVATIONS
MIN = -6.464

modest barn . Two mis chie vous kittens lived in the
too close . The ost ric hes might pe ck you
but be careful . Ost ric hes can be gr umpy
ostr ich pen . Ost ric hes are big birds with
you count how many ost ric hes there are ?"
should not tease the ost ric hes . They are not
ostr ich pen . Ost ric hes are big birds with
cried . " The ost ric hes are mean ! They
With a mis chie vous gl int in her
. They were called ost ric hes . Lily and Ben
shouted . " The ost ric hes are so funny !"
and looked at the ost ric hes . They saw one
so that no more mis chie vous mice could come in
One day a mis chie vous monkey saw the bear
. He was a mis chie vous little baby and always
One day , a mis chie vous young boy decided to
. One of the ost ric hes looked different from the
ie . Unlike other ost ric hes , his feathers gl
did not know what ost ric hes were . They looked
and run to the ost ric hes . "

INTERVAL 4.709 - 8.433
CONTAINS 0.018%

went home and had a y ummy dinner . Lily was
€ � � but don â € ™ t touch it
just a big cat . â € Tom was
her nap and had a y ummy sausage adventure . <|endoftext|>
™ s OK , we â € ™ ll mention it

INTERVAL 0.985 - 4.709
CONTAINS 16.472%

looked and said , " Wow , Lily ! Your dress
hears the noise and comes to see what is wrong .
day his dad gave him a weapon . He was really
made her feel cool . But then the fan started to
" yes ." Amy and the cat played all

INTERVAL -2.739 - 0.985
CONTAINS 82.900%

you , Tom !" From that day , Tom
" A and a match !" Mom smiles and
going missing ! The mother said , " What
too . He was restless and the bike had made him
much . Sam and his mom had discovered

INTERVAL -6.464 - -2.739
CONTAINS 0.610%

. The end . <|endoftext|> John was a
. They had a box of shapes that had circles ,
't get better without the band age and said she would
After a while , it started to rain and the infant
at his mom with a smile and she smiled back .
Token her
Token ID607
Feature activation+3.91e-01

Pos logit contributions
 destination+0.015
aman+0.014
 isn+0.014
heit+0.014
ement+0.013
Neg logit contributions
 blown-0.009
 Blood-0.009
 blood-0.009
 bitten-0.009
 spilled-0.008
Token doll
Token ID3654
Feature activation+1.22e+00

Pos logit contributions
aman+0.012
mmm+0.011
hew+0.011
heit+0.011
 isn+0.011
Neg logit contributions
 blood-0.007
 blown-0.007
 bitten-0.006
 Blood-0.006
 cat-0.006
Token and
Token ID290
Feature activation+2.71e-01

Pos logit contributions
heit+0.036
aman+0.034
 isn+0.033
 destination+0.033
hew+0.033
Neg logit contributions
 blown-0.023
 blood-0.022
 Blood-0.021
 bitten-0.021
 spilled-0.020
Token watched
Token ID7342
Feature activation+1.57e+00

Pos logit contributions
 destination+0.008
aman+0.008
 isn+0.007
heit+0.007
ement+0.007
Neg logit contributions
 blown-0.005
 blood-0.005
 Blood-0.005
 bitten-0.005
 spilled-0.005
Token in
Token ID287
Feature activation+2.18e+00

Pos logit contributions
 destination+0.046
heit+0.045
aman+0.045
 isn+0.044
hew+0.043
Neg logit contributions
 blown-0.030
 blood-0.030
 Blood-0.029
 bitten-0.028
 spilled-0.025
Token amaz
Token ID40642
Feature activation+7.26e+00

Pos logit contributions
heit+0.045
aman+0.043
hew+0.043
mmm+0.041
 isn+0.041
Neg logit contributions
 blood-0.064
 blown-0.061
 bitten-0.059
 Blood-0.058
 spilled-0.054
Tokenement
Token ID972
Feature activation+1.44e+00

Pos logit contributions
 destination+0.061
heit+0.058
olog+0.058
bek+0.055
 isn+0.055
Neg logit contributions
 blood-0.283
 Blood-0.267
 blown-0.265
 bitten-0.259
agged-0.258
Token as
Token ID355
Feature activation-1.57e+00

Pos logit contributions
 destination+0.038
aman+0.037
heit+0.037
 isn+0.036
ement+0.034
Neg logit contributions
 blown-0.032
 blood-0.032
 Blood-0.031
 bitten-0.031
 spilled-0.028
Token it
Token ID340
Feature activation-3.96e-01

Pos logit contributions
 blood+0.028
 blown+0.027
 Blood+0.026
 bitten+0.025
 spilled+0.023
Neg logit contributions
 destination-0.048
aman-0.048
heit-0.048
 isn-0.046
hew-0.046
Token slowly
Token ID6364
Feature activation-1.48e+00

Pos logit contributions
 blown+0.007
 blood+0.006
 Blood+0.006
 bitten+0.006
 spilled+0.005
Neg logit contributions
 destination-0.013
aman-0.012
 isn-0.012
heit-0.012
ement-0.012
Token flew
Token ID13112
Feature activation+7.74e-02

Pos logit contributions
 Blood+0.028
 blood+0.027
 blown+0.025
 bitten+0.025
 spilled+0.021
Neg logit contributions
 destination-0.044
 isn-0.042
aman-0.042
heit-0.041
ement-0.041
Token but
Token ID475
Feature activation+1.61e+00

Pos logit contributions
 blood+0.021
 bitten+0.020
 blown+0.020
 spilled+0.019
 Blood+0.017
Neg logit contributions
heit-0.045
aman-0.043
 destination-0.042
bek-0.041
hew-0.040
Token they
Token ID484
Feature activation+8.18e-01

Pos logit contributions
aman+0.051
 destination+0.049
heit+0.049
hew+0.048
ement+0.047
Neg logit contributions
 blown-0.029
 blood-0.029
 Blood-0.027
 bitten-0.027
 spilled-0.025
Token ran
Token ID4966
Feature activation-3.43e-01

Pos logit contributions
 destination+0.022
aman+0.021
heit+0.021
 isn+0.021
ement+0.020
Neg logit contributions
 blown-0.018
 blood-0.018
 Blood-0.017
 bitten-0.017
 spilled-0.016
Token back
Token ID736
Feature activation-3.60e-01

Pos logit contributions
 blown+0.007
 blood+0.007
 bitten+0.007
 Blood+0.006
 spilled+0.006
Neg logit contributions
aman-0.010
heit-0.010
 isn-0.010
 destination-0.010
ement-0.009
Token in
Token ID287
Feature activation+1.82e+00

Pos logit contributions
 blown+0.006
 blood+0.006
 bitten+0.006
 Blood+0.006
 spilled+0.005
Neg logit contributions
heit-0.011
aman-0.011
 destination-0.011
 isn-0.011
ement-0.011
Token amaz
Token ID40642
Feature activation+7.22e+00

Pos logit contributions
heit+0.056
aman+0.055
 destination+0.055
 isn+0.054
hew+0.054
Neg logit contributions
 blood-0.034
 blown-0.033
 bitten-0.032
 Blood-0.031
 spilled-0.027
Tokenement
Token ID972
Feature activation+1.81e+00

Pos logit contributions
 destination+0.053
heit+0.050
 isn+0.048
olog+0.047
aman+0.041
Neg logit contributions
 blood-0.291
 Blood-0.279
 blown-0.279
 bitten-0.273
agged-0.268
Token!
Token ID0
Feature activation+4.60e-01

Pos logit contributions
 destination+0.051
heit+0.050
aman+0.050
 isn+0.049
hew+0.046
Neg logit contributions
 blown-0.037
 blood-0.036
 Blood-0.036
 bitten-0.035
 spilled-0.031
Token The
Token ID383
Feature activation-9.43e-01

Pos logit contributions
 destination+0.015
heit+0.014
aman+0.014
 isn+0.014
ement+0.014
Neg logit contributions
 Blood-0.008
 blown-0.008
 blood-0.007
 bitten-0.007
 spilled-0.006
Token post
Token ID1281
Feature activation-4.44e-01

Pos logit contributions
 blown+0.024
 blood+0.023
 Blood+0.023
 bitten+0.023
 spilled+0.021
Neg logit contributions
 destination-0.022
aman-0.022
 isn-0.021
heit-0.021
ement-0.020
Token had
Token ID550
Feature activation-1.70e+00

Pos logit contributions
 blown+0.011
 blood+0.011
 Blood+0.010
 bitten+0.010
 spilled+0.009
Neg logit contributions
 destination-0.011
heit-0.011
aman-0.011
 isn-0.010
ement-0.010
Token and
Token ID290
Feature activation+1.17e+00

Pos logit contributions
heit+0.020
 destination+0.019
aman+0.019
hew+0.018
 isn+0.018
Neg logit contributions
 blood-0.010
 blown-0.010
 Blood-0.010
 bitten-0.009
 spilled-0.009
Token pointed
Token ID6235
Feature activation+2.80e+00

Pos logit contributions
 destination+0.035
aman+0.034
heit+0.033
 isn+0.033
ement+0.033
Neg logit contributions
 blown-0.023
 blood-0.022
 Blood-0.021
 bitten-0.021
 spilled-0.019
Token at
Token ID379
Feature activation+1.77e+00

Pos logit contributions
heit+0.096
aman+0.096
mmm+0.096
hew+0.095
 destination+0.094
Neg logit contributions
 blood-0.039
 bitten-0.036
 blown-0.036
 Blood-0.032
ked-0.028
Token it
Token ID340
Feature activation+6.94e-01

Pos logit contributions
 destination+0.060
aman+0.059
heit+0.058
 isn+0.057
hew+0.056
Neg logit contributions
 blood-0.026
 blown-0.026
 bitten-0.024
 Blood-0.024
 spilled-0.021
Token in
Token ID287
Feature activation+9.90e-01

Pos logit contributions
heit+0.020
aman+0.020
hew+0.018
 destination+0.018
bek+0.018
Neg logit contributions
 blown-0.014
 blood-0.013
 bitten-0.013
 Blood-0.013
 spilled-0.012
Token amaz
Token ID40642
Feature activation+7.01e+00

Pos logit contributions
 destination+0.026
heit+0.026
aman+0.026
 isn+0.026
hew+0.025
Neg logit contributions
 blood-0.022
 blown-0.022
 bitten-0.021
 Blood-0.021
 spilled-0.018
Tokenement
Token ID972
Feature activation+1.52e+00

Pos logit contributions
 destination+0.056
heit+0.053
olog+0.048
 isn+0.047
hew+0.045
Neg logit contributions
 blood-0.281
 Blood-0.269
 blown-0.269
 bitten-0.263
agged-0.254
Token.
Token ID13
Feature activation-2.04e-01

Pos logit contributions
 destination+0.040
heit+0.040
aman+0.039
 isn+0.039
hew+0.037
Neg logit contributions
 blown-0.033
 blood-0.033
 Blood-0.032
 bitten-0.031
 spilled-0.029
Token The
Token ID383
Feature activation-9.52e-01

Pos logit contributions
 blown+0.004
 blood+0.004
 Blood+0.004
 bitten+0.004
 spilled+0.003
Neg logit contributions
 destination-0.006
aman-0.006
heit-0.006
 isn-0.006
ement-0.005
Token bird
Token ID6512
Feature activation-6.60e-01

Pos logit contributions
 blown+0.017
 Blood+0.017
 bitten+0.016
 blood+0.016
elt+0.013
Neg logit contributions
 destination-0.029
 isn-0.028
aman-0.028
ement-0.027
heit-0.027
Token stopped
Token ID5025
Feature activation-1.85e+00

Pos logit contributions
 blown+0.014
 blood+0.013
 bitten+0.013
 Blood+0.013
 spilled+0.011
Neg logit contributions
 destination-0.019
aman-0.019
heit-0.018
 isn-0.018
ement-0.017
Token just
Token ID655
Feature activation+6.57e-01

Pos logit contributions
 destination+0.024
heit+0.023
aman+0.023
 isn+0.022
ement+0.022
Neg logit contributions
 blown-0.019
 blood-0.019
 bitten-0.018
 Blood-0.018
 spilled-0.018
Token stared
Token ID18484
Feature activation+1.56e+00

Pos logit contributions
 destination+0.019
aman+0.018
heit+0.018
 isn+0.017
ement+0.017
Neg logit contributions
 blown-0.014
 blood-0.013
 Blood-0.013
 bitten-0.013
 spilled-0.012
Token at
Token ID379
Feature activation+2.19e+00

Pos logit contributions
heit+0.044
aman+0.042
 destination+0.041
hew+0.040
 isn+0.040
Neg logit contributions
 blood-0.033
 blown-0.033
 bitten-0.031
 Blood-0.031
elt-0.029
Token him
Token ID683
Feature activation+7.31e-01

Pos logit contributions
 destination+0.067
heit+0.066
aman+0.065
 isn+0.064
hew+0.063
Neg logit contributions
 blood-0.040
 blown-0.038
 Blood-0.036
 bitten-0.036
 spilled-0.032
Token in
Token ID287
Feature activation+1.63e+00

Pos logit contributions
heit+0.024
aman+0.024
hew+0.022
 destination+0.021
bek+0.021
Neg logit contributions
 blood-0.011
 blown-0.011
 bitten-0.010
 spilled-0.010
 Blood-0.010
Token amaz
Token ID40642
Feature activation+6.92e+00

Pos logit contributions
heit+0.037
aman+0.037
 destination+0.037
hew+0.036
 isn+0.036
Neg logit contributions
 blood-0.043
 blown-0.041
 bitten-0.041
 Blood-0.040
 spilled-0.036
Tokenement
Token ID972
Feature activation+1.59e+00

Pos logit contributions
heit+0.061
olog+0.059
 destination+0.057
hew+0.054
 isn+0.053
Neg logit contributions
 blood-0.270
 blown-0.255
 Blood-0.253
 bitten-0.249
agged-0.244
Token.
Token ID13
Feature activation+2.12e-01

Pos logit contributions
 destination+0.043
heit+0.043
aman+0.042
 isn+0.042
hew+0.040
Neg logit contributions
 blood-0.033
 blown-0.033
 Blood-0.032
 bitten-0.031
 spilled-0.028
Token So
Token ID1406
Feature activation+7.10e-01

Pos logit contributions
 destination+0.007
heit+0.007
aman+0.007
 isn+0.007
ement+0.006
Neg logit contributions
 Blood-0.003
 blown-0.003
 blood-0.003
 bitten-0.003
 spilled-0.003
Token,
Token ID11
Feature activation-1.62e-01

Pos logit contributions
heit+0.023
aman+0.023
hew+0.022
 destination+0.022
 isn+0.022
Neg logit contributions
 blown-0.011
 blood-0.010
 Blood-0.010
 bitten-0.010
 spilled-0.009
Token he
Token ID339
Feature activation+5.36e-01

Pos logit contributions
 blown+0.002
 blood+0.002
 Blood+0.002
 bitten+0.002
 spilled+0.002
Neg logit contributions
 destination-0.005
heit-0.005
aman-0.005
 isn-0.005
hew-0.005
Token the
Token ID262
Feature activation+1.24e+00

Pos logit contributions
 destination+0.064
aman+0.062
heit+0.060
 isn+0.058
 exactly+0.057
Neg logit contributions
 Blood-0.046
 blown-0.044
 blood-0.044
 bitten-0.043
elt-0.040
Token bush
Token ID24484
Feature activation+2.21e+00

Pos logit contributions
 destination+0.034
aman+0.033
 isn+0.033
heit+0.032
ement+0.031
Neg logit contributions
 blown-0.026
 Blood-0.026
 blood-0.026
 bitten-0.025
 spilled-0.022
Token and
Token ID290
Feature activation+6.16e-01

Pos logit contributions
heit+0.065
 destination+0.061
 isn+0.061
aman+0.060
ement+0.057
Neg logit contributions
 blown-0.044
 blood-0.042
 Blood-0.041
 bitten-0.041
 spilled-0.038
Token watched
Token ID7342
Feature activation+1.48e+00

Pos logit contributions
 destination+0.017
aman+0.017
 isn+0.017
heit+0.017
ement+0.016
Neg logit contributions
 Blood-0.012
 blown-0.012
 blood-0.012
 bitten-0.012
 spilled-0.010
Token in
Token ID287
Feature activation+2.07e+00

Pos logit contributions
 destination+0.041
aman+0.040
heit+0.040
 isn+0.039
hew+0.038
Neg logit contributions
 blown-0.031
 blood-0.031
 Blood-0.030
 bitten-0.029
 spilled-0.026
Token amaz
Token ID40642
Feature activation+6.86e+00

Pos logit contributions
heit+0.057
 destination+0.057
aman+0.056
 isn+0.056
hew+0.054
Neg logit contributions
 blood-0.044
 blown-0.044
 bitten-0.041
 Blood-0.041
 spilled-0.037
Tokenement
Token ID972
Feature activation+1.22e+00

Pos logit contributions
 destination+0.050
heit+0.046
 isn+0.043
olog+0.039
bek+0.036
Neg logit contributions
 blood-0.280
 blown-0.270
 Blood-0.266
 bitten-0.264
agged-0.251
Token as
Token ID355
Feature activation-1.56e+00

Pos logit contributions
 destination+0.032
aman+0.031
heit+0.031
 isn+0.031
ement+0.029
Neg logit contributions
 blown-0.027
 blood-0.027
 Blood-0.027
 bitten-0.026
 spilled-0.023
Token it
Token ID340
Feature activation-3.90e-01

Pos logit contributions
 blown+0.030
 blood+0.030
 Blood+0.029
 bitten+0.028
 spilled+0.025
Neg logit contributions
 destination-0.046
aman-0.045
heit-0.044
 isn-0.044
ement-0.042
Token flew
Token ID13112
Feature activation+5.20e-04

Pos logit contributions
 Blood+0.007
 blood+0.007
 blown+0.007
 bitten+0.006
elt+0.006
Neg logit contributions
 destination-0.012
 isn-0.011
aman-0.011
heit-0.011
ement-0.011
Token away
Token ID1497
Feature activation-1.22e+00

Pos logit contributions
heit+0.000
 destination+0.000
aman+0.000
 isn+0.000
ement+0.000
Neg logit contributions
 blown-0.000
 blood-0.000
 bitten-0.000
 Blood-0.000
 spilled-0.000
Token door
Token ID3420
Feature activation-2.64e-01

Pos logit contributions
aman+0.024
heit+0.024
mmm+0.024
hew+0.023
idays+0.022
Neg logit contributions
 blood-0.013
 blown-0.012
 bitten-0.011
 Blood-0.011
 spilled-0.010
Token,
Token ID11
Feature activation+4.64e-01

Pos logit contributions
 blown+0.005
 blood+0.004
 Blood+0.004
 bitten+0.004
 spilled+0.004
Neg logit contributions
heit-0.008
 isn-0.008
aman-0.008
hew-0.008
 destination-0.008
Token and
Token ID290
Feature activation+6.00e-01

Pos logit contributions
 destination+0.012
aman+0.012
 isn+0.012
heit+0.012
ement+0.011
Neg logit contributions
 blown-0.010
 blood-0.010
 Blood-0.010
 bitten-0.010
 spilled-0.009
Token to
Token ID284
Feature activation+9.21e-01

Pos logit contributions
 destination+0.018
aman+0.018
heit+0.017
 isn+0.017
ement+0.017
Neg logit contributions
 blown-0.011
 blood-0.011
 Blood-0.011
 bitten-0.011
 spilled-0.009
Token her
Token ID607
Feature activation+9.78e-01

Pos logit contributions
 destination+0.028
aman+0.027
 isn+0.027
heit+0.027
ement+0.026
Neg logit contributions
 blown-0.017
 blood-0.017
 Blood-0.017
 bitten-0.016
 spilled-0.014
Token amaz
Token ID40642
Feature activation+6.80e+00

Pos logit contributions
aman+0.024
mmm+0.023
heit+0.023
hew+0.023
idays+0.021
Neg logit contributions
 blown-0.022
 blood-0.022
 bitten-0.021
 Blood-0.021
 cat-0.020
Tokenement
Token ID972
Feature activation+1.55e+00

Pos logit contributions
heit+0.043
 isn+0.038
 destination+0.037
hew+0.037
aman+0.031
Neg logit contributions
 blood-0.284
 blown-0.278
 Blood-0.273
 bitten-0.270
 spilled-0.254
Token,
Token ID11
Feature activation-1.79e-01

Pos logit contributions
 destination+0.037
heit+0.037
 isn+0.036
aman+0.036
ement+0.034
Neg logit contributions
 blown-0.037
 blood-0.037
 Blood-0.036
 bitten-0.036
 spilled-0.033
Token she
Token ID673
Feature activation+6.20e-01

Pos logit contributions
 blown+0.003
 blood+0.003
 Blood+0.002
 bitten+0.002
 spilled+0.002
Neg logit contributions
 destination-0.006
heit-0.006
aman-0.006
 isn-0.006
ement-0.006
Token could
Token ID714
Feature activation-1.04e+00

Pos logit contributions
aman+0.020
heit+0.019
 destination+0.019
 isn+0.018
ement+0.018
Neg logit contributions
 blown-0.011
 Blood-0.010
 bitten-0.010
 blood-0.010
 spilled-0.009
Token see
Token ID766
Feature activation+4.77e-01

Pos logit contributions
 blown+0.018
 blood+0.017
 Blood+0.017
 bitten+0.017
 spilled+0.014
Neg logit contributions
 destination-0.033
aman-0.032
 isn-0.032
heit-0.032
ement-0.031
Token pond
Token ID16723
Feature activation-8.25e-02

Pos logit contributions
 blown+0.002
 blood+0.002
 Blood+0.002
 bitten+0.002
 spilled+0.002
Neg logit contributions
 destination-0.004
aman-0.004
 isn-0.004
heit-0.004
ement-0.004
Token and
Token ID290
Feature activation+6.35e-01

Pos logit contributions
 blown+0.002
 blood+0.002
 Blood+0.002
 bitten+0.002
 spilled+0.002
Neg logit contributions
heit-0.002
 destination-0.002
aman-0.002
 isn-0.002
hew-0.002
Token everyone
Token ID2506
Feature activation-1.68e+00

Pos logit contributions
 destination+0.018
aman+0.018
heit+0.018
 isn+0.018
ement+0.017
Neg logit contributions
 blown-0.013
 blood-0.012
 Blood-0.012
 bitten-0.012
 spilled-0.011
Token watched
Token ID7342
Feature activation+1.63e+00

Pos logit contributions
 blown+0.037
 blood+0.036
 bitten+0.035
 Blood+0.035
 spilled+0.033
Neg logit contributions
 destination-0.046
aman-0.045
heit-0.044
 isn-0.043
ement-0.041
Token in
Token ID287
Feature activation+2.17e+00

Pos logit contributions
 destination+0.052
heit+0.052
aman+0.051
 isn+0.050
hew+0.049
Neg logit contributions
 blown-0.027
 blood-0.027
 Blood-0.025
 bitten-0.025
 spilled-0.022
Token amaz
Token ID40642
Feature activation+6.75e+00

Pos logit contributions
heit+0.043
hew+0.040
aman+0.039
mmm+0.039
 isn+0.038
Neg logit contributions
 blood-0.067
 blown-0.064
 bitten-0.062
 Blood-0.059
 spilled-0.057
Tokenement
Token ID972
Feature activation+1.09e+00

Pos logit contributions
 destination+0.051
heit+0.051
 isn+0.048
olog+0.047
hew+0.042
Neg logit contributions
 blood-0.269
 blown-0.258
 Blood-0.256
 bitten-0.252
agged-0.244
Token as
Token ID355
Feature activation-1.59e+00

Pos logit contributions
 destination+0.029
heit+0.028
aman+0.028
 isn+0.028
ement+0.026
Neg logit contributions
 blown-0.024
 blood-0.024
 Blood-0.024
 bitten-0.023
 spilled-0.021
Token her
Token ID607
Feature activation-4.81e-01

Pos logit contributions
 blown+0.028
 blood+0.028
 Blood+0.027
 bitten+0.026
 spilled+0.024
Neg logit contributions
 destination-0.049
aman-0.048
heit-0.048
 isn-0.047
hew-0.046
Token thread
Token ID4704
Feature activation-5.92e-01

Pos logit contributions
 blown+0.010
 blood+0.010
 Blood+0.009
 bitten+0.009
 spilled+0.008
Neg logit contributions
 destination-0.014
aman-0.014
heit-0.013
 isn-0.013
ement-0.013
Token gl
Token ID1278
Feature activation+1.29e+00

Pos logit contributions
 Blood+0.011
 blood+0.011
 blown+0.010
 bitten+0.010
elt+0.008
Neg logit contributions
 destination-0.018
 isn-0.017
aman-0.017
heit-0.016
ement-0.016
Token The
Token ID383
Feature activation-1.18e+00

Pos logit contributions
 blown+0.009
 blood+0.009
 bitten+0.009
 Blood+0.008
 spilled+0.008
Neg logit contributions
 destination-0.013
 isn-0.013
aman-0.013
ement-0.012
heit-0.012
Token girl
Token ID2576
Feature activation-1.69e+00

Pos logit contributions
 blown+0.021
 blood+0.021
 Blood+0.020
 bitten+0.020
 spilled+0.017
Neg logit contributions
 destination-0.036
aman-0.036
heit-0.035
 isn-0.035
ement-0.034
Token stepped
Token ID10764
Feature activation+7.83e-01

Pos logit contributions
 blown+0.034
 bitten+0.032
 blood+0.032
 Blood+0.031
 spilled+0.030
Neg logit contributions
aman-0.050
 destination-0.049
heit-0.049
mmm-0.046
 isn-0.046
Token back
Token ID736
Feature activation-8.99e-01

Pos logit contributions
 destination+0.023
aman+0.022
 isn+0.022
heit+0.022
ement+0.021
Neg logit contributions
 blown-0.015
 blood-0.015
 Blood-0.015
 bitten-0.015
 spilled-0.013
Token in
Token ID287
Feature activation+1.52e+00

Pos logit contributions
 blown+0.015
 blood+0.015
 bitten+0.014
 Blood+0.014
 spilled+0.013
Neg logit contributions
heit-0.028
aman-0.028
 isn-0.027
 destination-0.027
hew-0.027
Token amaz
Token ID40642
Feature activation+6.75e+00

Pos logit contributions
 destination+0.045
heit+0.044
aman+0.044
 isn+0.043
hew+0.042
Neg logit contributions
 blood-0.030
 blown-0.029
 Blood-0.028
 bitten-0.028
 spilled-0.025
Tokenement
Token ID972
Feature activation+1.56e+00

Pos logit contributions
 destination+0.039
heit+0.032
 isn+0.032
aman+0.026
hew+0.023
Neg logit contributions
 blood-0.291
 Blood-0.283
 blown-0.281
 bitten-0.276
 spilled-0.261
Token as
Token ID355
Feature activation-1.70e+00

Pos logit contributions
 destination+0.042
heit+0.041
aman+0.041
 isn+0.041
ement+0.038
Neg logit contributions
 blown-0.033
 blood-0.033
 Blood-0.033
 bitten-0.032
 spilled-0.029
Token the
Token ID262
Feature activation-1.41e+00

Pos logit contributions
 blown+0.033
 Blood+0.032
 blood+0.032
 bitten+0.032
 spilled+0.027
Neg logit contributions
 destination-0.049
 isn-0.047
aman-0.047
heit-0.046
ement-0.045
Token dark
Token ID3223
Feature activation-2.51e+00

Pos logit contributions
 blown+0.025
 blood+0.025
 Blood+0.025
 bitten+0.024
 spilled+0.021
Neg logit contributions
 destination-0.043
aman-0.042
heit-0.042
 isn-0.042
ement-0.040
Token started
Token ID2067
Feature activation-3.49e+00

Pos logit contributions
 Blood+0.051
 blown+0.050
 bitten+0.050
 blood+0.049
Tweet+0.041
Neg logit contributions
 destination-0.070
 isn-0.068
aman-0.066
ement-0.064
heit-0.060
Token her
Token ID607
Feature activation-2.27e+00

Pos logit contributions
 blown+0.022
 blood+0.021
 Blood+0.021
 bitten+0.020
 spilled+0.017
Neg logit contributions
 destination-0.039
aman-0.038
 isn-0.038
heit-0.037
ement-0.036
Token mom
Token ID1995
Feature activation-9.36e-01

Pos logit contributions
 blown+0.060
 Blood+0.059
 bitten+0.058
 blood+0.058
elt+0.052
Neg logit contributions
 destination-0.051
 isn-0.047
aman-0.046
heit-0.045
ement-0.045
Tokenmy
Token ID1820
Feature activation+2.39e-01

Pos logit contributions
 blown+0.024
 Blood+0.024
 blood+0.023
 bitten+0.023
 spilled+0.020
Neg logit contributions
 destination-0.022
aman-0.021
 isn-0.021
heit-0.020
hew-0.020
Token watched
Token ID7342
Feature activation+1.37e+00

Pos logit contributions
 destination+0.007
aman+0.007
 isn+0.006
heit+0.006
ement+0.006
Neg logit contributions
 blown-0.005
 blood-0.005
 Blood-0.005
 bitten-0.005
 spilled-0.004
Token in
Token ID287
Feature activation+1.63e+00

Pos logit contributions
 destination+0.041
heit+0.040
aman+0.040
 isn+0.039
hew+0.038
Neg logit contributions
 blown-0.026
 blood-0.026
 Blood-0.025
 bitten-0.024
 spilled-0.022
Token amaz
Token ID40642
Feature activation+6.75e+00

Pos logit contributions
heit+0.031
hew+0.030
aman+0.029
mmm+0.029
 isn+0.028
Neg logit contributions
 blood-0.052
 blown-0.048
 bitten-0.046
 Blood-0.045
 spilled-0.044
Tokenement
Token ID972
Feature activation+1.30e+00

Pos logit contributions
 destination+0.042
heit+0.038
 isn+0.036
aman+0.028
olog+0.028
Neg logit contributions
 blood-0.284
 blown-0.274
 Blood-0.274
 bitten-0.267
 spilled-0.255
Token as
Token ID355
Feature activation-1.80e+00

Pos logit contributions
 destination+0.037
aman+0.036
 isn+0.035
heit+0.035
ement+0.034
Neg logit contributions
 blown-0.027
 blood-0.026
 Blood-0.026
 bitten-0.025
 spilled-0.023
Token the
Token ID262
Feature activation-1.48e+00

Pos logit contributions
 blown+0.038
 blood+0.037
 Blood+0.037
 bitten+0.036
 spilled+0.032
Neg logit contributions
 destination-0.050
aman-0.048
 isn-0.048
heit-0.048
ement-0.045
Token machine
Token ID4572
Feature activation+1.95e-03

Pos logit contributions
 Blood+0.040
 bitten+0.040
 blown+0.040
 blood+0.039
elt+0.038
Neg logit contributions
 destination-0.031
 isn-0.029
aman-0.027
heit-0.027
ement-0.027
Token flew
Token ID13112
Feature activation-3.99e-01

Pos logit contributions
 destination+0.000
aman+0.000
heit+0.000
 isn+0.000
ement+0.000
Neg logit contributions
 blown-0.000
 blood-0.000
 bitten-0.000
 Blood-0.000
 spilled-0.000
Token hill
Token ID12788
Feature activation+7.56e-01

Pos logit contributions
 destination+0.011
aman+0.011
heit+0.011
 isn+0.011
ement+0.010
Neg logit contributions
 blown-0.006
 blood-0.006
 Blood-0.006
 bitten-0.006
 spilled-0.005
Token and
Token ID290
Feature activation+1.88e-01

Pos logit contributions
heit+0.021
 destination+0.021
aman+0.021
 isn+0.020
hew+0.019
Neg logit contributions
 blown-0.016
 blood-0.015
 Blood-0.015
 bitten-0.015
 spilled-0.013
Token everyone
Token ID2506
Feature activation-1.95e+00

Pos logit contributions
 destination+0.005
 isn+0.005
aman+0.005
heit+0.005
ement+0.005
Neg logit contributions
 blood-0.004
 Blood-0.004
 blown-0.004
 bitten-0.004
 spilled-0.003
Token watched
Token ID7342
Feature activation+1.49e+00

Pos logit contributions
 blown+0.046
 blood+0.045
 Blood+0.044
 bitten+0.044
 spilled+0.040
Neg logit contributions
 destination-0.050
aman-0.049
heit-0.048
 isn-0.047
ement-0.045
Token in
Token ID287
Feature activation+2.04e+00

Pos logit contributions
 destination+0.043
aman+0.043
heit+0.042
 isn+0.040
hew+0.039
Neg logit contributions
 blown-0.030
 blood-0.030
 Blood-0.029
 bitten-0.028
 spilled-0.025
Token amaz
Token ID40642
Feature activation+6.68e+00

Pos logit contributions
heit+0.044
aman+0.043
hew+0.041
 isn+0.041
 destination+0.041
Neg logit contributions
 blood-0.058
 blown-0.056
 bitten-0.053
 Blood-0.053
 spilled-0.049
Tokenement
Token ID972
Feature activation+1.09e+00

Pos logit contributions
 destination+0.050
heit+0.045
 isn+0.042
olog+0.040
aman+0.038
Neg logit contributions
 blood-0.272
 blown-0.262
 Blood-0.261
 bitten-0.256
agged-0.247
Token.
Token ID13
Feature activation+8.92e-01

Pos logit contributions
 destination+0.028
aman+0.027
heit+0.027
 isn+0.027
ement+0.025
Neg logit contributions
 blown-0.025
 blood-0.025
 Blood-0.024
 bitten-0.024
 spilled-0.021
Token The
Token ID383
Feature activation-5.47e-01

Pos logit contributions
 destination+0.028
aman+0.027
heit+0.027
 isn+0.026
ement+0.025
Neg logit contributions
 Blood-0.016
 blown-0.016
 blood-0.015
 bitten-0.014
 spilled-0.013
Token rock
Token ID3881
Feature activation-1.43e+00

Pos logit contributions
 blown+0.010
 Blood+0.009
 bitten+0.009
 blood+0.009
 spilled+0.008
Neg logit contributions
 destination-0.017
 isn-0.016
heit-0.016
aman-0.016
ement-0.016
Token was
Token ID373
Feature activation-9.66e-02

Pos logit contributions
 blown+0.032
 blood+0.031
 Blood+0.031
 bitten+0.030
 spilled+0.027
Neg logit contributions
 destination-0.038
aman-0.037
heit-0.037
 isn-0.036
ement-0.035
Token his
Token ID465
Feature activation-6.93e-01

Pos logit contributions
 destination+0.030
aman+0.029
 isn+0.029
heit+0.029
hew+0.028
Neg logit contributions
 blood-0.017
 blown-0.017
 bitten-0.016
 Blood-0.015
 spilled-0.013
Token mummy
Token ID38567
Feature activation+2.25e-01

Pos logit contributions
 blood+0.011
 blown+0.011
 Blood+0.011
 bitten+0.011
 spilled+0.009
Neg logit contributions
aman-0.023
 destination-0.022
heit-0.022
 isn-0.021
hew-0.021
Token,
Token ID11
Feature activation+8.81e-02

Pos logit contributions
heit+0.005
 destination+0.005
 isn+0.005
aman+0.005
ement+0.005
Neg logit contributions
 blown-0.006
 blood-0.005
 bitten-0.005
 spilled-0.005
 Blood-0.005
Token trembling
Token ID39228
Feature activation-4.35e-01

Pos logit contributions
 destination+0.002
aman+0.002
 isn+0.002
heit+0.002
ement+0.002
Neg logit contributions
 blown-0.002
 blood-0.002
 Blood-0.002
 bitten-0.002
 spilled-0.002
Token in
Token ID287
Feature activation+1.42e+00

Pos logit contributions
 blown+0.009
 blood+0.009
 bitten+0.009
 Blood+0.008
 spilled+0.008
Neg logit contributions
 destination-0.012
aman-0.012
heit-0.012
 isn-0.012
hew-0.011
Token amaz
Token ID40642
Feature activation+6.68e+00

Pos logit contributions
 destination+0.037
aman+0.036
heit+0.036
 isn+0.036
hew+0.035
Neg logit contributions
 blown-0.032
 blood-0.032
 bitten-0.031
 Blood-0.031
 spilled-0.027
Tokenement
Token ID972
Feature activation+1.93e+00

Pos logit contributions
 destination+0.050
heit+0.049
 isn+0.044
olog+0.041
hew+0.038
Neg logit contributions
 blood-0.271
 blown-0.258
 Blood-0.258
 bitten-0.253
agged-0.240
Token.
Token ID13
Feature activation-6.55e-02

Pos logit contributions
 destination+0.051
heit+0.050
 isn+0.050
aman+0.050
ement+0.047
Neg logit contributions
 blown-0.042
 blood-0.041
 Blood-0.040
 bitten-0.040
 spilled-0.036
Token They
Token ID1119
Feature activation-1.99e-01

Pos logit contributions
 Blood+0.001
 blown+0.001
 blood+0.001
 bitten+0.001
elt+0.001
Neg logit contributions
 destination-0.002
heit-0.002
aman-0.002
 isn-0.002
ement-0.002
Token had
Token ID550
Feature activation-5.07e-01

Pos logit contributions
 blown+0.004
 blood+0.004
 bitten+0.003
 Blood+0.003
 spilled+0.003
Neg logit contributions
aman-0.006
 destination-0.006
 isn-0.006
heit-0.006
ement-0.006
Token just
Token ID655
Feature activation-8.36e-02

Pos logit contributions
 blown+0.010
 blood+0.010
 bitten+0.010
 Blood+0.009
 spilled+0.008
Neg logit contributions
 destination-0.015
aman-0.014
heit-0.014
 isn-0.014
ement-0.014
Token THE
Token ID3336
Feature activation+1.25e-01

Pos logit contributions
 blown+0.023
 Blood+0.022
 blood+0.022
 bitten+0.022
 spilled+0.020
Neg logit contributions
 destination-0.023
aman-0.022
heit-0.022
ement-0.021
 isn-0.021
Token BE
Token ID9348
Feature activation+2.57e+00

Pos logit contributions
heit+0.003
 destination+0.003
aman+0.003
hew+0.003
 exactly+0.003
Neg logit contributions
 Blood-0.003
 bitten-0.003
 blown-0.003
 blood-0.003
 spilled-0.002
TokenLL
Token ID3069
Feature activation+2.20e+00

Pos logit contributions
aman+0.059
heit+0.058
 destination+0.057
ement+0.055
 isn+0.054
Neg logit contributions
 Blood-0.067
 blown-0.059
Tweet-0.059
 bitten-0.058
 blood-0.056
Token WHEN
Token ID42099
Feature activation+1.87e+00

Pos logit contributions
 destination+0.051
 isn+0.051
aman+0.050
heit+0.049
hew+0.047
Neg logit contributions
 blown-0.055
 blood-0.054
 bitten-0.051
 Blood-0.050
 spilled-0.047
Token YOU
Token ID7013
Feature activation+2.01e+00

Pos logit contributions
 destination+0.030
aman+0.029
 isn+0.028
heit+0.028
ement+0.026
Neg logit contributions
 blown-0.061
 blood-0.060
 Blood-0.059
 bitten-0.059
 spilled-0.055
Token FE
Token ID18630
Feature activation+6.66e+00

Pos logit contributions
aman+0.050
 destination+0.047
ement+0.045
heit+0.043
 destinations+0.041
Neg logit contributions
 Blood-0.049
 blown-0.047
 bitten-0.046
 blood-0.042
 spilled-0.042
TokenEL
Token ID3698
Feature activation+1.84e+00

Pos logit contributions
aman+0.145
 destination+0.144
heit+0.140
 amaz+0.133
 isn+0.132
Neg logit contributions
 Blood-0.170
 bitten-0.146
agged-0.145
 blood-0.145
 blown-0.144
Token LIKE
Token ID34178
Feature activation+3.64e+00

Pos logit contributions
 destination+0.052
aman+0.052
heit+0.049
 isn+0.048
 exactly+0.048
Neg logit contributions
 bitten-0.038
 blown-0.037
 Blood-0.037
 blood-0.036
 spilled-0.032
Token IT
Token ID7283
Feature activation+1.58e+00

Pos logit contributions
aman+0.087
 isn+0.086
rd+0.084
 destination+0.083
hew+0.082
Neg logit contributions
 Blood-0.088
 blood-0.085
 blown-0.081
 bitten-0.076
hes-0.070
Token".
Token ID1911
Feature activation+3.09e-01

Pos logit contributions
aman+0.032
 destination+0.030
ement+0.028
heit+0.028
hew+0.027
Neg logit contributions
 blown-0.045
 Blood-0.044
 bitten-0.043
 blood-0.043
 spilled-0.041
Token
Token ID198
Feature activation+4.94e-01

Pos logit contributions
heit+0.011
 destination+0.011
aman+0.010
 isn+0.010
ement+0.010
Neg logit contributions
 Blood-0.005
 blood-0.005
 bitten-0.004
 blown-0.004
 spilled-0.003
Token baby
Token ID5156
Feature activation-1.77e+00

Pos logit contributions
 blown+0.024
 Blood+0.023
 blood+0.023
 bitten+0.022
 spilled+0.019
Neg logit contributions
 destination-0.042
 isn-0.041
aman-0.040
heit-0.040
ement-0.038
Token le
Token ID443
Feature activation-1.11e+00

Pos logit contributions
 blown+0.026
 blood+0.025
 Blood+0.025
 bitten+0.024
 spilled+0.020
Neg logit contributions
 destination-0.059
 isn-0.058
aman-0.058
heit-0.057
ement-0.056
Tokenopard
Token ID15478
Feature activation+4.26e-02

Pos logit contributions
 blown+0.022
 blood+0.020
 Blood+0.019
 spilled+0.018
 bitten+0.018
Neg logit contributions
aman-0.030
ement-0.030
 isn-0.030
hew-0.030
 destination-0.029
Token watched
Token ID7342
Feature activation+8.40e-01

Pos logit contributions
 destination+0.001
aman+0.001
heit+0.001
 isn+0.001
ement+0.001
Neg logit contributions
 blown-0.001
 blood-0.001
 bitten-0.001
 Blood-0.001
 spilled-0.001
Token in
Token ID287
Feature activation+1.52e+00

Pos logit contributions
 destination+0.023
aman+0.022
 isn+0.022
heit+0.022
ement+0.021
Neg logit contributions
 blown-0.018
 blood-0.017
 Blood-0.017
 bitten-0.017
 spilled-0.015
Token amaz
Token ID40642
Feature activation+6.65e+00

Pos logit contributions
 destination+0.031
aman+0.030
heit+0.030
 isn+0.030
hew+0.028
Neg logit contributions
 blood-0.044
 blown-0.043
 bitten-0.042
 Blood-0.042
 spilled-0.038
Tokenement
Token ID972
Feature activation+1.14e+00

Pos logit contributions
 destination+0.047
 isn+0.039
heit+0.039
olog+0.034
aman+0.033
Neg logit contributions
 blood-0.275
 Blood-0.266
 blown-0.263
 bitten-0.260
agged-0.247
Token as
Token ID355
Feature activation-1.96e+00

Pos logit contributions
 destination+0.029
aman+0.028
 isn+0.028
heit+0.028
ement+0.027
Neg logit contributions
 blown-0.026
 blood-0.026
 Blood-0.025
 bitten-0.025
 spilled-0.022
Token the
Token ID262
Feature activation-1.39e+00

Pos logit contributions
 blown+0.043
 Blood+0.042
 bitten+0.041
 blood+0.041
elt+0.037
Neg logit contributions
 destination-0.050
 isn-0.050
heit-0.048
aman-0.048
ement-0.046
Token lion
Token ID18744
Feature activation-1.25e+00

Pos logit contributions
 blown+0.027
 Blood+0.027
 blood+0.026
 bitten+0.025
elt+0.024
Neg logit contributions
 destination-0.039
 isn-0.038
heit-0.037
aman-0.036
ement-0.035
Token flex
Token ID7059
Feature activation-1.55e+00

Pos logit contributions
 blown+0.021
 blood+0.020
 bitten+0.020
 Blood+0.020
 spilled+0.018
Neg logit contributions
 destination-0.040
aman-0.039
heit-0.039
 isn-0.038
ement-0.037
Token He
Token ID679
Feature activation-6.48e-02

Pos logit contributions
 Blood+0.005
 blood+0.005
 blown+0.005
 bitten+0.005
 spilled+0.004
Neg logit contributions
 destination-0.013
heit-0.013
aman-0.013
 isn-0.012
ement-0.012
Token looked
Token ID3114
Feature activation+1.13e+00

Pos logit contributions
 blown+0.001
 blood+0.001
 Blood+0.001
 bitten+0.001
 spilled+0.001
Neg logit contributions
 destination-0.002
aman-0.002
heit-0.002
 isn-0.002
ement-0.002
Token at
Token ID379
Feature activation+1.53e+00

Pos logit contributions
aman+0.033
 destination+0.033
heit+0.032
hew+0.031
mmm+0.031
Neg logit contributions
 blood-0.022
 blown-0.022
 bitten-0.021
 Blood-0.020
 spilled-0.019
Token it
Token ID340
Feature activation+1.18e-01

Pos logit contributions
 destination+0.041
aman+0.039
heit+0.039
 isn+0.039
ement+0.037
Neg logit contributions
 blood-0.034
 blown-0.034
 Blood-0.033
 bitten-0.033
 spilled-0.029
Token in
Token ID287
Feature activation+1.12e+00

Pos logit contributions
heit+0.004
aman+0.004
 destination+0.003
bek+0.003
rd+0.003
Neg logit contributions
 blown-0.002
 blood-0.002
 Blood-0.002
 bitten-0.002
 spilled-0.002
Token amaz
Token ID40642
Feature activation+6.64e+00

Pos logit contributions
 destination+0.029
aman+0.028
heit+0.028
 isn+0.028
ement+0.027
Neg logit contributions
 blood-0.026
 blown-0.026
 Blood-0.025
 bitten-0.025
 spilled-0.022
Tokenement
Token ID972
Feature activation+1.82e+00

Pos logit contributions
 destination+0.053
heit+0.050
olog+0.045
 isn+0.043
 virtue+0.042
Neg logit contributions
 blood-0.268
 Blood-0.256
 blown-0.250
 bitten-0.248
agged-0.241
Token and
Token ID290
Feature activation+1.11e+00

Pos logit contributions
 destination+0.047
aman+0.045
heit+0.045
 isn+0.045
ement+0.042
Neg logit contributions
 blown-0.042
 blood-0.041
 Blood-0.041
 bitten-0.040
 spilled-0.036
Token smiled
Token ID13541
Feature activation-1.08e+00

Pos logit contributions
 destination+0.035
aman+0.035
heit+0.033
ement+0.032
 isn+0.032
Neg logit contributions
 blood-0.020
 blown-0.019
 Blood-0.019
 bitten-0.019
 spilled-0.017
Token.
Token ID13
Feature activation+1.12e-01

Pos logit contributions
 blood+0.021
 blown+0.021
 Blood+0.021
 bitten+0.020
elt+0.018
Neg logit contributions
aman-0.031
heit-0.031
 destination-0.030
 isn-0.029
hew-0.029
Token Now
Token ID2735
Feature activation+8.42e-01

Pos logit contributions
 destination+0.004
aman+0.003
heit+0.003
ement+0.003
 isn+0.003
Neg logit contributions
 Blood-0.002
 blood-0.002
 blown-0.002
 bitten-0.002
 spilled-0.002
Token He
Token ID679
Feature activation-6.48e-02

Pos logit contributions
 Blood+0.005
 blood+0.005
 blown+0.005
 bitten+0.005
 spilled+0.004
Neg logit contributions
 destination-0.013
heit-0.013
aman-0.013
 isn-0.012
ement-0.012
Token looked
Token ID3114
Feature activation+1.13e+00

Pos logit contributions
 blown+0.001
 blood+0.001
 Blood+0.001
 bitten+0.001
 spilled+0.001
Neg logit contributions
 destination-0.002
aman-0.002
heit-0.002
 isn-0.002
ement-0.002
Token at
Token ID379
Feature activation+1.53e+00

Pos logit contributions
aman+0.033
 destination+0.033
heit+0.032
hew+0.031
mmm+0.031
Neg logit contributions
 blood-0.022
 blown-0.022
 bitten-0.021
 Blood-0.020
 spilled-0.019
Token it
Token ID340
Feature activation+1.18e-01

Pos logit contributions
 destination+0.041
aman+0.039
heit+0.039
 isn+0.039
ement+0.037
Neg logit contributions
 blood-0.034
 blown-0.034
 Blood-0.033
 bitten-0.033
 spilled-0.029
Token in
Token ID287
Feature activation+1.12e+00

Pos logit contributions
heit+0.004
aman+0.004
 destination+0.003
bek+0.003
rd+0.003
Neg logit contributions
 blown-0.002
 blood-0.002
 Blood-0.002
 bitten-0.002
 spilled-0.002
Token amaz
Token ID40642
Feature activation+6.64e+00

Pos logit contributions
 destination+0.029
aman+0.028
heit+0.028
 isn+0.028
ement+0.027
Neg logit contributions
 blood-0.026
 blown-0.026
 Blood-0.025
 bitten-0.025
 spilled-0.022
Tokenement
Token ID972
Feature activation+1.82e+00

Pos logit contributions
 destination+0.053
heit+0.050
olog+0.045
 isn+0.043
 virtue+0.042
Neg logit contributions
 blood-0.268
 Blood-0.256
 blown-0.250
 bitten-0.248
agged-0.241
Token and
Token ID290
Feature activation+1.11e+00

Pos logit contributions
 destination+0.047
aman+0.045
heit+0.045
 isn+0.045
ement+0.042
Neg logit contributions
 blown-0.042
 blood-0.041
 Blood-0.041
 bitten-0.040
 spilled-0.036
Token smiled
Token ID13541
Feature activation-1.08e+00

Pos logit contributions
 destination+0.035
aman+0.035
heit+0.033
ement+0.032
 isn+0.032
Neg logit contributions
 blood-0.020
 blown-0.019
 Blood-0.019
 bitten-0.019
 spilled-0.017
Token.
Token ID13
Feature activation+1.12e-01

Pos logit contributions
 blood+0.021
 blown+0.021
 Blood+0.021
 bitten+0.020
elt+0.018
Neg logit contributions
aman-0.031
heit-0.031
 destination-0.030
 isn-0.029
hew-0.029
Token Now
Token ID2735
Feature activation+8.42e-01

Pos logit contributions
 destination+0.004
aman+0.003
heit+0.003
ement+0.003
 isn+0.003
Neg logit contributions
 Blood-0.002
 blood-0.002
 blown-0.002
 bitten-0.002
 spilled-0.002
Token.
Token ID13
Feature activation-8.48e-01

Pos logit contributions
 blood+0.037
 blown+0.037
 bitten+0.035
 Blood+0.034
 spilled+0.031
Neg logit contributions
aman-0.050
 destination-0.049
heit-0.049
ement-0.046
 isn-0.046
Token Everyone
Token ID11075
Feature activation-2.58e+00

Pos logit contributions
 blown+0.014
 blood+0.013
 bitten+0.013
 Blood+0.013
 spilled+0.011
Neg logit contributions
 destination-0.028
 isn-0.027
aman-0.027
heit-0.026
ement-0.025
Token watched
Token ID7342
Feature activation+8.28e-01

Pos logit contributions
 blown+0.055
 blood+0.054
 bitten+0.053
 Blood+0.052
 spilled+0.050
Neg logit contributions
 destination-0.074
aman-0.073
heit-0.069
ement-0.066
 isn-0.065
Token him
Token ID683
Feature activation+1.38e-01

Pos logit contributions
 destination+0.024
aman+0.024
heit+0.023
 isn+0.022
hew+0.022
Neg logit contributions
 blood-0.017
 blown-0.017
 Blood-0.016
 bitten-0.016
 spilled-0.014
Token in
Token ID287
Feature activation+1.61e+00

Pos logit contributions
aman+0.004
 destination+0.004
heit+0.004
 isn+0.004
ement+0.004
Neg logit contributions
 blown-0.003
 blood-0.003
 Blood-0.002
 bitten-0.002
 spilled-0.002
Token amaz
Token ID40642
Feature activation+6.61e+00

Pos logit contributions
 destination+0.044
aman+0.043
heit+0.043
 isn+0.042
ement+0.041
Neg logit contributions
 blood-0.035
 blown-0.035
 Blood-0.034
 bitten-0.033
 spilled-0.030
Tokenement
Token ID972
Feature activation+1.58e+00

Pos logit contributions
 destination+0.043
heit+0.041
 isn+0.038
olog+0.036
aman+0.032
Neg logit contributions
 blood-0.272
 Blood-0.264
 blown-0.262
 bitten-0.257
agged-0.248
Token and
Token ID290
Feature activation+1.24e+00

Pos logit contributions
 destination+0.040
aman+0.039
 isn+0.038
heit+0.038
ement+0.036
Neg logit contributions
 blown-0.037
 blood-0.036
 Blood-0.036
 bitten-0.035
 spilled-0.032
Token cheered
Token ID34767
Feature activation-3.49e-01

Pos logit contributions
aman+0.037
 destination+0.037
heit+0.036
ement+0.035
 isn+0.035
Neg logit contributions
 blown-0.024
 blood-0.023
 bitten-0.022
 Blood-0.022
 spilled-0.020
Token.
Token ID13
Feature activation+3.31e-01

Pos logit contributions
 Blood+0.005
 blood+0.005
 blown+0.005
 bitten+0.004
 mice+0.004
Neg logit contributions
aman-0.012
heit-0.011
 destination-0.011
hew-0.011
ement-0.010
Token
Token ID220
Feature activation-1.70e+00

Pos logit contributions
 destination+0.012
aman+0.011
heit+0.011
 isn+0.011
ement+0.011
Neg logit contributions
 Blood-0.005
 blood-0.004
 blown-0.004
 bitten-0.004
elt-0.003
Token.
Token ID13
Feature activation+8.61e-01

Pos logit contributions
heit+0.005
aman+0.005
 destination+0.005
 isn+0.004
ement+0.004
Neg logit contributions
 blown-0.004
 blood-0.004
 Blood-0.004
 bitten-0.003
 spilled-0.003
Token Tim
Token ID5045
Feature activation+1.01e+00

Pos logit contributions
 destination+0.026
heit+0.025
aman+0.024
 isn+0.024
ement+0.023
Neg logit contributions
 Blood-0.017
 blood-0.016
 blown-0.016
 bitten-0.015
elt-0.014
Tokenmy
Token ID1820
Feature activation+3.87e-02

Pos logit contributions
 destination+0.028
heit+0.027
aman+0.027
 isn+0.026
ement+0.025
Neg logit contributions
 blood-0.021
 blown-0.021
 Blood-0.021
 bitten-0.021
 spilled-0.019
Token watched
Token ID7342
Feature activation+6.63e-01

Pos logit contributions
 destination+0.001
aman+0.001
heit+0.001
 isn+0.001
ement+0.001
Neg logit contributions
 blown-0.001
 blood-0.001
 Blood-0.001
 bitten-0.001
 spilled-0.001
Token in
Token ID287
Feature activation+1.43e+00

Pos logit contributions
 destination+0.018
aman+0.018
 isn+0.018
heit+0.017
ement+0.017
Neg logit contributions
 blown-0.014
 blood-0.014
 Blood-0.014
 bitten-0.013
 spilled-0.012
Token amaz
Token ID40642
Feature activation+6.58e+00

Pos logit contributions
 destination+0.039
heit+0.039
aman+0.039
 isn+0.038
hew+0.036
Neg logit contributions
 blood-0.031
 blown-0.030
 Blood-0.029
 bitten-0.029
 spilled-0.026
Tokenement
Token ID972
Feature activation+1.09e+00

Pos logit contributions
 destination+0.045
heit+0.040
 isn+0.036
aman+0.032
olog+0.030
Neg logit contributions
 blood-0.275
 Blood-0.265
 blown-0.262
 bitten-0.258
 spilled-0.245
Token as
Token ID355
Feature activation-1.94e+00

Pos logit contributions
 destination+0.030
aman+0.029
 isn+0.028
heit+0.028
ement+0.027
Neg logit contributions
 blown-0.024
 blood-0.023
 Blood-0.023
 bitten-0.023
 spilled-0.020
Token the
Token ID262
Feature activation-1.62e+00

Pos logit contributions
 blown+0.043
 bitten+0.042
 Blood+0.041
 blood+0.039
elt+0.037
Neg logit contributions
 destination-0.049
 isn-0.048
aman-0.048
 exactly-0.047
heit-0.046
Token black
Token ID2042
Feature activation-3.04e+00

Pos logit contributions
 blown+0.033
 Blood+0.030
 bitten+0.029
 blood+0.028
elt+0.026
Neg logit contributions
 destination-0.046
 isn-0.045
aman-0.042
ement-0.042
heit-0.041
Tokenboard
Token ID3526
Feature activation-1.24e+00

Pos logit contributions
 blown+0.099
 bitten+0.089
 Blood+0.084
Tweet+0.083
 blood+0.083
Neg logit contributions
 isn-0.055
 destination-0.051
ement-0.049
aman-0.047
hew-0.042
Tokenuddle
Token ID24500
Feature activation-2.37e-01

Pos logit contributions
 destination+0.022
aman+0.022
heit+0.021
 isn+0.021
ement+0.019
Neg logit contributions
 blood-0.039
 blown-0.039
 Blood-0.039
 bitten-0.038
 spilled-0.035
Token!"
Token ID2474
Feature activation-1.04e+00

Pos logit contributions
 blown+0.007
 blood+0.007
 bitten+0.007
 Blood+0.007
 spilled+0.007
Neg logit contributions
 destination-0.004
aman-0.004
heit-0.004
 isn-0.004
ement-0.004
Token she
Token ID673
Feature activation-1.49e+00

Pos logit contributions
 blown+0.017
 blood+0.017
 Blood+0.017
 bitten+0.016
 spilled+0.014
Neg logit contributions
 destination-0.033
aman-0.032
heit-0.032
 isn-0.031
hew-0.031
Token said
Token ID531
Feature activation-1.21e+00

Pos logit contributions
 blown+0.033
 blood+0.033
 Blood+0.033
 bitten+0.032
 spilled+0.029
Neg logit contributions
 destination-0.040
aman-0.039
heit-0.038
 isn-0.037
ement-0.037
Token in
Token ID287
Feature activation+1.08e-01

Pos logit contributions
 blown+0.026
 blood+0.025
 Blood+0.025
 bitten+0.025
 spilled+0.022
Neg logit contributions
 destination-0.033
heit-0.033
aman-0.033
 isn-0.032
hew-0.031
Token amaz
Token ID40642
Feature activation+6.57e+00

Pos logit contributions
 destination+0.003
aman+0.003
 isn+0.003
heit+0.003
ement+0.003
Neg logit contributions
 blown-0.002
 Blood-0.002
 blood-0.002
 bitten-0.002
 spilled-0.002
Tokenement
Token ID972
Feature activation+1.91e+00

Pos logit contributions
 destination+0.045
heit+0.038
 isn+0.037
hew+0.032
aman+0.031
Neg logit contributions
 blood-0.275
 Blood-0.268
 blown-0.266
 bitten-0.262
agged-0.247
Token.
Token ID13
Feature activation+1.18e-01

Pos logit contributions
 destination+0.049
 isn+0.047
aman+0.047
heit+0.047
ement+0.044
Neg logit contributions
 blown-0.043
 blood-0.043
 Blood-0.043
 bitten-0.042
 spilled-0.038
Token
Token ID220
Feature activation-1.58e+00

Pos logit contributions
 destination+0.003
heit+0.003
aman+0.003
 isn+0.003
ement+0.003
Neg logit contributions
 Blood-0.003
 blown-0.003
 blood-0.002
 bitten-0.002
elt-0.002
Token
Token ID220
Feature activation-1.55e+00

Pos logit contributions
 blown+0.032
 Blood+0.032
 blood+0.032
 bitten+0.031
 spilled+0.027
Neg logit contributions
 destination-0.045
heit-0.043
aman-0.043
 isn-0.042
ement-0.041
Token
Token ID198
Feature activation+7.67e-02

Pos logit contributions
 blown+0.032
 blood+0.032
 Blood+0.032
 bitten+0.031
 spilled+0.027
Neg logit contributions
 destination-0.043
aman-0.042
heit-0.042
 isn-0.041
ement-0.040
Token gazed
Token ID50255
Feature activation+3.17e-02

Pos logit contributions
 Blood+0.029
 blood+0.029
 blown+0.027
 bitten+0.026
elt+0.023
Neg logit contributions
 isn-0.027
heit-0.026
 destination-0.026
aman-0.026
hew-0.025
Token at
Token ID379
Feature activation+1.96e+00

Pos logit contributions
 destination+0.001
aman+0.001
heit+0.001
 isn+0.001
ement+0.001
Neg logit contributions
 blown-0.001
 blood-0.001
 Blood-0.001
 bitten-0.001
 spilled-0.001
Token the
Token ID262
Feature activation+1.86e-01

Pos logit contributions
 destination+0.049
aman+0.048
heit+0.047
 isn+0.047
ement+0.045
Neg logit contributions
 blown-0.046
 blood-0.046
 Blood-0.045
 bitten-0.044
 spilled-0.040
Token butterfly
Token ID35113
Feature activation+8.39e-01

Pos logit contributions
 destination+0.005
 isn+0.005
aman+0.005
heit+0.005
ement+0.005
Neg logit contributions
 Blood-0.004
 bitten-0.004
 blown-0.004
 blood-0.004
elt-0.004
Token in
Token ID287
Feature activation+1.26e+00

Pos logit contributions
heit+0.023
aman+0.023
 destination+0.023
 isn+0.022
ement+0.021
Neg logit contributions
 blown-0.018
 blood-0.017
 bitten-0.016
 Blood-0.016
 spilled-0.015
Token amaz
Token ID40642
Feature activation+6.55e+00

Pos logit contributions
 destination+0.029
aman+0.029
heit+0.029
 isn+0.028
ement+0.027
Neg logit contributions
 blown-0.032
 blood-0.032
 Blood-0.031
 bitten-0.031
 spilled-0.028
Tokenement
Token ID972
Feature activation+1.46e+00

Pos logit contributions
 destination+0.037
heit+0.036
 isn+0.031
aman+0.027
hew+0.024
Neg logit contributions
 blood-0.278
 blown-0.272
 Blood-0.269
 bitten-0.265
 spilled-0.251
Token.
Token ID13
Feature activation+3.80e-01

Pos logit contributions
 destination+0.036
aman+0.035
 isn+0.034
heit+0.034
ement+0.033
Neg logit contributions
 blown-0.035
 blood-0.034
 Blood-0.034
 bitten-0.034
 spilled-0.030
Token
Token ID198
Feature activation+2.95e-02

Pos logit contributions
 destination+0.010
 isn+0.010
aman+0.010
heit+0.010
ement+0.009
Neg logit contributions
 blown-0.008
 blood-0.008
 Blood-0.008
 bitten-0.008
 spilled-0.007
Token
Token ID198
Feature activation-2.89e-01

Pos logit contributions
 destination+0.001
aman+0.001
heit+0.001
 isn+0.001
ement+0.001
Neg logit contributions
 blown-0.001
 blood-0.001
 Blood-0.001
 bitten-0.001
 spilled-0.001
TokenBut
Token ID1537
Feature activation+6.10e-01

Pos logit contributions
 blown+0.007
 blood+0.007
 Blood+0.007
 bitten+0.007
 spilled+0.006
Neg logit contributions
 destination-0.007
aman-0.007
 isn-0.007
heit-0.007
ement-0.006
Token at
Token ID379
Feature activation+1.41e+00

Pos logit contributions
aman+0.027
heit+0.026
 destination+0.026
mmm+0.026
hew+0.026
Neg logit contributions
 blown-0.020
 blood-0.019
 bitten-0.018
 Blood-0.018
 spilled-0.018
Token the
Token ID262
Feature activation-5.52e-01

Pos logit contributions
 destination+0.044
aman+0.043
 isn+0.043
heit+0.043
hew+0.041
Neg logit contributions
 blood-0.024
 blown-0.024
 Blood-0.023
 bitten-0.022
 spilled-0.019
Token red
Token ID2266
Feature activation-2.25e+00

Pos logit contributions
 blown+0.009
 blood+0.009
 Blood+0.009
 bitten+0.009
 spilled+0.007
Neg logit contributions
 destination-0.018
 isn-0.017
aman-0.017
heit-0.017
ement-0.016
Token blocks
Token ID7021
Feature activation-7.92e-02

Pos logit contributions
 blown+0.040
 bitten+0.038
 blood+0.038
 Blood+0.037
 spilled+0.031
Neg logit contributions
 destination-0.071
 isn-0.070
ement-0.066
aman-0.066
heit-0.065
Token in
Token ID287
Feature activation+7.46e-01

Pos logit contributions
 blown+0.002
 blood+0.002
 Blood+0.001
 bitten+0.001
 spilled+0.001
Neg logit contributions
heit-0.002
 destination-0.002
aman-0.002
 isn-0.002
hew-0.002
Token amaz
Token ID40642
Feature activation+6.54e+00

Pos logit contributions
heit+0.024
 destination+0.024
 isn+0.024
aman+0.024
hew+0.024
Neg logit contributions
 blood-0.012
 blown-0.011
 Blood-0.011
 bitten-0.011
 spilled-0.009
Tokenement
Token ID972
Feature activation+1.70e+00

Pos logit contributions
heit+0.050
 destination+0.046
olog+0.041
 isn+0.039
hew+0.037
Neg logit contributions
 blood-0.265
 Blood-0.255
 blown-0.252
 bitten-0.246
agged-0.238
Token.
Token ID13
Feature activation-4.63e-01

Pos logit contributions
 destination+0.044
heit+0.043
aman+0.042
 isn+0.042
hew+0.039
Neg logit contributions
 blown-0.038
 blood-0.038
 Blood-0.037
 bitten-0.036
 spilled-0.033
Token He
Token ID679
Feature activation-2.54e-01

Pos logit contributions
 Blood+0.007
 blood+0.007
 blown+0.007
 bitten+0.007
elt+0.006
Neg logit contributions
 destination-0.015
heit-0.015
aman-0.015
 isn-0.014
hew-0.014
Token couldn
Token ID3521
Feature activation+1.21e-01

Pos logit contributions
 blown+0.004
 Blood+0.004
 blood+0.004
 bitten+0.004
 spilled+0.004
Neg logit contributions
aman-0.008
 destination-0.008
heit-0.007
ement-0.007
 isn-0.007
Token't
Token ID470
Feature activation-1.98e+00

Pos logit contributions
 destination+0.004
 isn+0.003
aman+0.003
heit+0.003
ement+0.003
Neg logit contributions
 blown-0.002
 blood-0.002
 bitten-0.002
 Blood-0.002
 spilled-0.002
Token modest
Token ID12949
Feature activation-1.20e-01

Pos logit contributions
 blown+0.021
 blood+0.020
 bitten+0.020
 Blood+0.019
elt+0.016
Neg logit contributions
 isn-0.029
 destination-0.028
aman-0.028
heit-0.028
ement-0.027
Token barn
Token ID25203
Feature activation+1.33e+00

Pos logit contributions
 blood+0.002
 blown+0.002
 Blood+0.002
 bitten+0.002
 spilled+0.001
Neg logit contributions
 destination-0.004
heit-0.004
aman-0.004
 isn-0.004
hew-0.004
Token.
Token ID13
Feature activation-9.70e-01

Pos logit contributions
 destination+0.032
 isn+0.030
aman+0.030
heit+0.030
ement+0.029
Neg logit contributions
 blown-0.033
 blood-0.032
 Blood-0.032
 bitten-0.032
 spilled-0.028
Token Two
Token ID4930
Feature activation-1.45e+00

Pos logit contributions
 blown+0.019
 blood+0.019
 bitten+0.018
 Blood+0.018
 spilled+0.016
Neg logit contributions
 destination-0.028
 isn-0.028
aman-0.027
heit-0.026
ement-0.026
Token mis
Token ID2984
Feature activation-2.76e+00

Pos logit contributions
 blown+0.022
 blood+0.021
 Blood+0.021
 bitten+0.021
 spilled+0.018
Neg logit contributions
 destination-0.049
aman-0.048
heit-0.047
 isn-0.046
ement-0.045
Tokenchie
Token ID3043
Feature activation-6.46e+00

Pos logit contributions
 blood+0.065
 Blood+0.063
 blown+0.062
 bitten+0.059
 spilled+0.058
Neg logit contributions
 destination-0.068
aman-0.065
heit-0.065
hew-0.064
 isn-0.063
Tokenvous
Token ID31222
Feature activation-1.52e+00

Pos logit contributions
 blown+0.103
 blood+0.102
 Blood+0.099
 bitten+0.096
 spilled+0.082
Neg logit contributions
 destination-0.208
 isn-0.204
aman-0.203
heit-0.202
ement-0.194
Token kittens
Token ID45584
Feature activation+1.58e-01

Pos logit contributions
 blown+0.024
 blood+0.023
 Blood+0.023
 bitten+0.022
 spilled+0.019
Neg logit contributions
 destination-0.050
 isn-0.049
aman-0.048
heit-0.048
ement-0.046
Token lived
Token ID5615
Feature activation-8.23e-01

Pos logit contributions
 destination+0.004
aman+0.004
heit+0.004
 isn+0.004
ement+0.004
Neg logit contributions
 blown-0.003
 blood-0.003
 bitten-0.003
 Blood-0.003
 spilled-0.003
Token in
Token ID287
Feature activation-6.23e-02

Pos logit contributions
 blood+0.018
 Blood+0.017
 blown+0.017
 bitten+0.017
 spilled+0.015
Neg logit contributions
 destination-0.021
aman-0.020
 isn-0.020
 exactly-0.020
heit-0.020
Token the
Token ID262
Feature activation-1.00e+00

Pos logit contributions
 blown+0.001
 blood+0.001
 Blood+0.001
 bitten+0.001
elt+0.001
Neg logit contributions
 destination-0.002
 isn-0.002
aman-0.002
heit-0.002
ement-0.002
Token too
Token ID1165
Feature activation-1.90e+00

Pos logit contributions
aman+0.006
 destination+0.006
heit+0.006
 isn+0.006
ement+0.006
Neg logit contributions
 blown-0.006
 bitten-0.005
 blood-0.005
 Blood-0.005
 spilled-0.005
Token close
Token ID1969
Feature activation-6.99e-02

Pos logit contributions
 blown+0.042
 blood+0.041
 Blood+0.040
 bitten+0.040
 spilled+0.035
Neg logit contributions
 destination-0.051
 isn-0.050
aman-0.050
heit-0.049
ement-0.049
Token.
Token ID13
Feature activation+1.44e+00

Pos logit contributions
 blown+0.001
 blood+0.001
 bitten+0.001
 Blood+0.001
 spilled+0.001
Neg logit contributions
heit-0.002
 destination-0.002
aman-0.002
ement-0.002
 isn-0.002
Token The
Token ID383
Feature activation-1.86e-01

Pos logit contributions
 destination+0.037
aman+0.036
heit+0.036
ement+0.034
 isn+0.034
Neg logit contributions
 Blood-0.033
 blown-0.033
 blood-0.033
 bitten-0.032
 spilled-0.028
Token ost
Token ID23619
Feature activation+1.19e+00

Pos logit contributions
 blown+0.003
 blood+0.003
 bitten+0.003
 Blood+0.003
 spilled+0.003
Neg logit contributions
aman-0.006
heit-0.006
 destination-0.006
ement-0.006
 isn-0.006
Tokenric
Token ID1173
Feature activation-6.28e+00

Pos logit contributions
 destination+0.025
aman+0.024
 isn+0.023
heit+0.023
ement+0.022
Neg logit contributions
 blown-0.033
 blood-0.033
 Blood-0.032
 bitten-0.032
 spilled-0.030
Tokenhes
Token ID956
Feature activation-1.91e+00

Pos logit contributions
 blown+0.058
 blood+0.055
 Blood+0.050
 bitten+0.050
 spilled+0.038
Neg logit contributions
 isn-0.239
heit-0.235
 destination-0.235
aman-0.231
ement-0.229
Token might
Token ID1244
Feature activation-4.29e-01

Pos logit contributions
 blown+0.046
 blood+0.045
 bitten+0.044
 Blood+0.044
 spilled+0.041
Neg logit contributions
 destination-0.046
aman-0.046
heit-0.045
 isn-0.043
ement-0.043
Token pe
Token ID613
Feature activation-8.13e-02

Pos logit contributions
 blown+0.009
 blood+0.009
 Blood+0.008
 bitten+0.008
 spilled+0.007
Neg logit contributions
 destination-0.012
aman-0.012
 isn-0.012
heit-0.012
ement-0.011
Tokenck
Token ID694
Feature activation-9.82e-01

Pos logit contributions
 blown+0.002
 blood+0.002
 Blood+0.002
 bitten+0.002
 spilled+0.002
Neg logit contributions
 destination-0.002
heit-0.002
aman-0.002
 isn-0.002
ement-0.002
Token you
Token ID345
Feature activation-6.84e-02

Pos logit contributions
 blown+0.021
 blood+0.021
 bitten+0.020
 Blood+0.020
 spilled+0.018
Neg logit contributions
 destination-0.027
aman-0.027
heit-0.026
 isn-0.025
ement-0.025
Token but
Token ID475
Feature activation+3.53e+00

Pos logit contributions
 destination+0.015
heit+0.014
aman+0.014
ement+0.014
 destinations+0.013
Neg logit contributions
 blood-0.014
 Blood-0.012
 blown-0.012
 bitten-0.012
 spilled-0.012
Token be
Token ID307
Feature activation-1.88e-01

Pos logit contributions
 destination+0.093
heit+0.091
ement+0.090
aman+0.090
 isn+0.087
Neg logit contributions
 blood-0.080
 blown-0.078
 Blood-0.077
 bitten-0.075
 spilled-0.067
Token careful
Token ID8161
Feature activation+1.65e+00

Pos logit contributions
 blood+0.004
 bitten+0.004
 blown+0.004
 Blood+0.004
hes+0.004
Neg logit contributions
 destination-0.005
aman-0.005
heit-0.005
 isn-0.005
ement-0.005
Token.
Token ID13
Feature activation+1.47e+00

Pos logit contributions
 destination+0.047
aman+0.047
heit+0.046
ement+0.043
 isn+0.042
Neg logit contributions
 blood-0.034
 Blood-0.034
 blown-0.033
 bitten-0.032
 spilled-0.029
Token Ost
Token ID38919
Feature activation+3.16e+00

Pos logit contributions
 destination+0.042
heit+0.040
aman+0.040
 isn+0.039
ement+0.038
Neg logit contributions
 Blood-0.030
 blood-0.030
 blown-0.030
 bitten-0.028
 spilled-0.024
Tokenric
Token ID1173
Feature activation-6.25e+00

Pos logit contributions
 destination+0.070
aman+0.067
 isn+0.066
heit+0.066
ement+0.062
Neg logit contributions
 blown-0.084
 blood-0.083
 Blood-0.082
 bitten-0.081
 spilled-0.074
Tokenhes
Token ID956
Feature activation-1.15e+00

Pos logit contributions
 blown+0.063
 blood+0.057
 Blood+0.054
 bitten+0.054
 spilled+0.043
Neg logit contributions
 isn-0.232
heit-0.228
 destination-0.225
hew-0.223
 exactly-0.222
Token can
Token ID460
Feature activation+6.16e-03

Pos logit contributions
 blown+0.032
 blood+0.032
 Blood+0.031
 bitten+0.031
 spilled+0.028
Neg logit contributions
 destination-0.024
aman-0.024
heit-0.023
ement-0.022
 isn-0.022
Token be
Token ID307
Feature activation-1.89e+00

Pos logit contributions
 destination+0.000
aman+0.000
 isn+0.000
heit+0.000
mmm+0.000
Neg logit contributions
 blown-0.000
 Blood-0.000
 blood-0.000
 bitten-0.000
elt-0.000
Token gr
Token ID1036
Feature activation-1.01e+00

Pos logit contributions
 Blood+0.038
 blood+0.038
 blown+0.038
 bitten+0.035
 spilled+0.032
Neg logit contributions
 destination-0.050
 isn-0.050
heit-0.049
aman-0.049
hew-0.047
Tokenumpy
Token ID32152
Feature activation-6.31e-01

Pos logit contributions
 blown+0.021
 blood+0.021
 Blood+0.021
 bitten+0.020
 spilled+0.019
Neg logit contributions
 destination-0.027
 isn-0.026
aman-0.026
hew-0.026
heit-0.026
Token ostr
Token ID42387
Feature activation-5.18e-02

Pos logit contributions
heit+0.024
ement+0.023
aman+0.023
 isn+0.022
mmm+0.022
Neg logit contributions
 blood-0.016
 blown-0.015
 bitten-0.014
 Blood-0.014
 spilled-0.014
Tokenich
Token ID488
Feature activation+9.10e-02

Pos logit contributions
 blown+0.001
 blood+0.001
 Blood+0.001
 bitten+0.001
 spilled+0.001
Neg logit contributions
 destination-0.002
aman-0.002
 isn-0.002
heit-0.001
ement-0.001
Token pen
Token ID3112
Feature activation+6.20e-01

Pos logit contributions
heit+0.003
aman+0.002
 destination+0.002
 isn+0.002
mmm+0.002
Neg logit contributions
 blood-0.002
 blown-0.002
 bitten-0.002
 Blood-0.002
 spilled-0.002
Token.
Token ID13
Feature activation-8.91e-01

Pos logit contributions
 destination+0.016
heit+0.016
aman+0.016
 isn+0.016
ement+0.015
Neg logit contributions
 blown-0.013
 blood-0.013
 Blood-0.013
 bitten-0.013
 spilled-0.012
Token Ost
Token ID38919
Feature activation+3.05e+00

Pos logit contributions
 Blood+0.012
 blood+0.011
 blown+0.011
 bitten+0.010
elt+0.009
Neg logit contributions
 destination-0.032
heit-0.031
aman-0.031
hew-0.030
ement-0.030
Tokenric
Token ID1173
Feature activation-6.25e+00

Pos logit contributions
 destination+0.066
aman+0.064
 isn+0.062
heit+0.062
ement+0.059
Neg logit contributions
 blown-0.083
 blood-0.082
 Blood-0.081
 bitten-0.080
 spilled-0.074
Tokenhes
Token ID956
Feature activation-1.03e+00

Pos logit contributions
 blown+0.071
 blood+0.065
 bitten+0.060
 Blood+0.058
 spilled+0.049
Neg logit contributions
 isn-0.221
heit-0.215
 exactly-0.213
hew-0.213
ement-0.212
Token are
Token ID389
Feature activation-6.38e-01

Pos logit contributions
 blown+0.027
 blood+0.027
 bitten+0.026
 Blood+0.026
 spilled+0.025
Neg logit contributions
 destination-0.023
aman-0.023
heit-0.022
 isn-0.021
ement-0.021
Token big
Token ID1263
Feature activation+1.14e-01

Pos logit contributions
 blown+0.013
 blood+0.013
 Blood+0.012
 bitten+0.012
 spilled+0.011
Neg logit contributions
 destination-0.018
aman-0.018
heit-0.018
 isn-0.018
ement-0.017
Token birds
Token ID10087
Feature activation-8.90e-01

Pos logit contributions
 destination+0.003
aman+0.003
heit+0.003
 isn+0.003
ement+0.003
Neg logit contributions
 blood-0.002
 blown-0.002
 bitten-0.002
 Blood-0.002
 spilled-0.002
Token with
Token ID351
Feature activation-1.44e-01

Pos logit contributions
 blown+0.018
 blood+0.018
 bitten+0.018
 Blood+0.017
 spilled+0.016
Neg logit contributions
 destination-0.026
heit-0.025
aman-0.025
 isn-0.024
ement-0.023
Token you
Token ID345
Feature activation-1.62e+00

Pos logit contributions
 destination+0.040
aman+0.039
heit+0.039
 isn+0.038
ement+0.036
Neg logit contributions
 blown-0.050
 blood-0.050
 Blood-0.049
 bitten-0.048
 spilled-0.044
Token count
Token ID954
Feature activation+1.92e+00

Pos logit contributions
 blown+0.034
 blood+0.034
 Blood+0.034
 bitten+0.033
 spilled+0.030
Neg logit contributions
 destination-0.044
 isn-0.042
aman-0.042
heit-0.042
ement-0.039
Token how
Token ID703
Feature activation+1.25e+00

Pos logit contributions
aman+0.057
 destination+0.057
heit+0.056
ement+0.054
 isn+0.053
Neg logit contributions
 blood-0.036
 blown-0.035
 Blood-0.035
 bitten-0.033
elt-0.027
Token many
Token ID867
Feature activation-1.28e+00

Pos logit contributions
 destination+0.040
aman+0.039
heit+0.038
 isn+0.037
ement+0.037
Neg logit contributions
 blown-0.022
 Blood-0.021
 blood-0.021
 bitten-0.020
 spilled-0.018
Token ost
Token ID23619
Feature activation+8.69e-01

Pos logit contributions
 blown+0.025
 blood+0.024
 bitten+0.023
 Blood+0.023
 spilled+0.020
Neg logit contributions
 destination-0.039
aman-0.038
heit-0.036
ement-0.036
 isn-0.035
Tokenric
Token ID1173
Feature activation-6.19e+00

Pos logit contributions
 destination+0.018
 isn+0.017
aman+0.017
heit+0.016
hew+0.016
Neg logit contributions
 blood-0.024
 blown-0.024
 Blood-0.024
 bitten-0.024
 spilled-0.022
Tokenhes
Token ID956
Feature activation-2.27e+00

Pos logit contributions
 blood+0.087
 blown+0.087
 Blood+0.079
 bitten+0.078
 spilled+0.069
Neg logit contributions
 isn-0.204
heit-0.199
 destination-0.197
ement-0.193
hew-0.192
Token there
Token ID612
Feature activation-3.26e-01

Pos logit contributions
 blown+0.055
 blood+0.054
 Blood+0.053
 bitten+0.052
 spilled+0.048
Neg logit contributions
 destination-0.055
aman-0.054
heit-0.053
 isn-0.052
ement-0.050
Token are
Token ID389
Feature activation-1.50e+00

Pos logit contributions
 blown+0.009
 blood+0.009
 Blood+0.008
 bitten+0.008
 spilled+0.008
Neg logit contributions
aman-0.007
 destination-0.007
heit-0.007
 isn-0.007
ement-0.007
Token?"
Token ID1701
Feature activation-1.96e-01

Pos logit contributions
 blown+0.033
 blood+0.032
 Blood+0.032
 bitten+0.032
 spilled+0.028
Neg logit contributions
 destination-0.040
aman-0.039
heit-0.038
 isn-0.038
ement-0.037
Token
Token ID198
Feature activation+5.17e-01

Pos logit contributions
 blown+0.005
 blood+0.004
 bitten+0.004
 Blood+0.004
 spilled+0.004
Neg logit contributions
 isn-0.005
 destination-0.005
aman-0.005
heit-0.005
ement-0.005
Token should
Token ID815
Feature activation+1.86e+00

Pos logit contributions
 isn+0.006
 destination+0.006
hew+0.006
heit+0.005
 exactly+0.005
Neg logit contributions
 Blood-0.008
 blood-0.008
 blown-0.008
 bitten-0.007
eh-0.007
Token not
Token ID407
Feature activation-1.25e+00

Pos logit contributions
 destination+0.050
aman+0.049
heit+0.048
 isn+0.048
ement+0.047
Neg logit contributions
 blown-0.040
 blood-0.040
 Blood-0.039
 bitten-0.039
 spilled-0.035
Token tease
Token ID34691
Feature activation-7.08e-02

Pos logit contributions
 blown+0.023
 Blood+0.023
 blood+0.023
 bitten+0.022
 spilled+0.019
Neg logit contributions
 destination-0.037
 isn-0.036
aman-0.036
heit-0.036
hew-0.034
Token the
Token ID262
Feature activation-9.98e-01

Pos logit contributions
 blood+0.002
 blown+0.002
 Blood+0.002
 bitten+0.002
 spilled+0.001
Neg logit contributions
 destination-0.002
aman-0.002
heit-0.002
ement-0.002
 isn-0.002
Token ost
Token ID23619
Feature activation+1.19e+00

Pos logit contributions
 blown+0.024
 blood+0.024
 bitten+0.023
 Blood+0.023
 spilled+0.021
Neg logit contributions
 destination-0.025
heit-0.024
aman-0.024
 isn-0.024
ement-0.023
Tokenric
Token ID1173
Feature activation-6.17e+00

Pos logit contributions
 destination+0.025
aman+0.024
 isn+0.024
heit+0.024
ement+0.023
Neg logit contributions
 blown-0.032
 blood-0.032
 Blood-0.032
 bitten-0.031
 spilled-0.029
Tokenhes
Token ID956
Feature activation-1.93e+00

Pos logit contributions
 blown+0.063
 blood+0.059
 Blood+0.056
 bitten+0.054
 spilled+0.043
Neg logit contributions
 isn-0.227
heit-0.224
 destination-0.222
aman-0.219
hew-0.218
Token.
Token ID13
Feature activation+1.12e+00

Pos logit contributions
 blood+0.041
 blown+0.040
 bitten+0.039
 Blood+0.038
 spilled+0.035
Neg logit contributions
 destination-0.053
aman-0.053
heit-0.052
ement-0.050
 isn-0.049
Token They
Token ID1119
Feature activation-1.06e-01

Pos logit contributions
 destination+0.035
aman+0.033
heit+0.033
 isn+0.032
ement+0.031
Neg logit contributions
 Blood-0.021
 blood-0.020
 blown-0.020
 bitten-0.019
 spilled-0.016
Token are
Token ID389
Feature activation+7.28e-01

Pos logit contributions
 blown+0.003
 blood+0.003
 Blood+0.003
 bitten+0.003
 spilled+0.002
Neg logit contributions
 destination-0.002
 isn-0.002
aman-0.002
heit-0.002
ement-0.002
Token not
Token ID407
Feature activation-1.27e+00

Pos logit contributions
 destination+0.016
 isn+0.016
heit+0.016
aman+0.016
 exactly+0.015
Neg logit contributions
 Blood-0.018
 blown-0.018
 blood-0.018
 bitten-0.017
 spilled-0.016
Token ostr
Token ID42387
Feature activation+1.65e-01

Pos logit contributions
heit+0.023
ement+0.023
aman+0.023
 isn+0.022
mmm+0.022
Neg logit contributions
 blood-0.015
 blown-0.014
 bitten-0.014
 Blood-0.014
 spilled-0.013
Tokenich
Token ID488
Feature activation+5.82e-02

Pos logit contributions
 destination+0.005
aman+0.005
 isn+0.005
heit+0.005
ement+0.005
Neg logit contributions
 blown-0.003
 blood-0.003
 Blood-0.003
 bitten-0.003
 spilled-0.002
Token pen
Token ID3112
Feature activation+5.42e-01

Pos logit contributions
heit+0.002
aman+0.002
 isn+0.002
 destination+0.002
ement+0.001
Neg logit contributions
 blood-0.001
 blown-0.001
 bitten-0.001
 Blood-0.001
 spilled-0.001
Token.
Token ID13
Feature activation-4.54e-01

Pos logit contributions
 destination+0.014
heit+0.014
aman+0.014
 isn+0.014
ement+0.013
Neg logit contributions
 blown-0.012
 blood-0.012
 Blood-0.011
 bitten-0.011
 spilled-0.010
Token Ost
Token ID38919
Feature activation+3.24e+00

Pos logit contributions
 Blood+0.005
 blood+0.005
 blown+0.004
 bitten+0.004
elt+0.003
Neg logit contributions
 destination-0.017
heit-0.017
aman-0.017
ement-0.016
hew-0.016
Tokenric
Token ID1173
Feature activation-6.14e+00

Pos logit contributions
 destination+0.071
aman+0.068
 isn+0.067
heit+0.067
ement+0.063
Neg logit contributions
 blown-0.087
 blood-0.086
 Blood-0.085
 bitten-0.084
 spilled-0.077
Tokenhes
Token ID956
Feature activation-1.03e+00

Pos logit contributions
 blown+0.070
 blood+0.063
 bitten+0.059
 Blood+0.057
 spilled+0.049
Neg logit contributions
 isn-0.219
heit-0.213
hew-0.210
 exactly-0.210
 destination-0.209
Token are
Token ID389
Feature activation-7.37e-01

Pos logit contributions
 blood+0.026
 blown+0.026
 Blood+0.026
 bitten+0.025
 spilled+0.023
Neg logit contributions
 destination-0.024
aman-0.023
heit-0.022
 isn-0.022
ement-0.022
Token big
Token ID1263
Feature activation-2.10e-04

Pos logit contributions
 blown+0.015
 blood+0.014
 Blood+0.014
 bitten+0.014
 spilled+0.012
Neg logit contributions
 destination-0.021
aman-0.020
 isn-0.020
heit-0.020
ement-0.019
Token birds
Token ID10087
Feature activation-9.00e-01

Pos logit contributions
 blood+0.000
 blown+0.000
 bitten+0.000
 Blood+0.000
 spilled+0.000
Neg logit contributions
 destination-0.000
aman-0.000
heit-0.000
 isn-0.000
ement-0.000
Token with
Token ID351
Feature activation-1.97e-01

Pos logit contributions
 blown+0.018
 blood+0.018
 bitten+0.018
 Blood+0.017
 spilled+0.016
Neg logit contributions
 destination-0.026
aman-0.026
heit-0.026
 isn-0.024
ement-0.024
Token cried
Token ID16896
Feature activation-3.40e+00

Pos logit contributions
 blown+0.038
 Blood+0.037
 blood+0.036
 bitten+0.036
 spilled+0.031
Neg logit contributions
 destination-0.048
 isn-0.047
aman-0.046
heit-0.046
hew-0.044
Token.
Token ID13
Feature activation-7.55e-01

Pos logit contributions
 blown+0.118
 Blood+0.111
 bitten+0.111
eh+0.104
 spilled+0.103
Neg logit contributions
 forever-0.041
 destination-0.038
 exactly-0.038
 isn-0.037
ement-0.035
Token "
Token ID366
Feature activation+4.26e-01

Pos logit contributions
 blown+0.019
 bitten+0.018
 blood+0.017
eh+0.016
 Blood+0.016
Neg logit contributions
 isn-0.018
 destination-0.017
aman-0.017
heit-0.016
ement-0.016
TokenThe
Token ID464
Feature activation-3.98e-01

Pos logit contributions
So+0.007
�+0.007
 isn+0.007
hew+0.007
heit+0.006
Neg logit contributions
 blown-0.012
 bitten-0.011
 blood-0.010
 robbers-0.010
ses-0.010
Token ost
Token ID23619
Feature activation+1.58e+00

Pos logit contributions
 Blood+0.008
 blown+0.007
 bitten+0.007
 blood+0.007
elt+0.006
Neg logit contributions
 destination-0.011
 isn-0.011
aman-0.011
heit-0.011
ement-0.010
Tokenric
Token ID1173
Feature activation-6.13e+00

Pos logit contributions
 destination+0.028
aman+0.027
heit+0.027
 isn+0.027
hew+0.025
Neg logit contributions
 blown-0.047
 Blood-0.047
 blood-0.046
 bitten-0.045
 spilled-0.043
Tokenhes
Token ID956
Feature activation-2.31e+00

Pos logit contributions
 blown+0.078
 blood+0.064
 bitten+0.064
 robbers+0.064
 Blood+0.063
Neg logit contributions
 isn-0.208
heit-0.201
 exactly-0.200
hew-0.199
ement-0.195
Token are
Token ID389
Feature activation-3.61e-01

Pos logit contributions
 blown+0.065
 blood+0.064
 Blood+0.064
 bitten+0.063
 spilled+0.057
Neg logit contributions
 destination-0.047
aman-0.045
 isn-0.045
heit-0.045
ement-0.042
Token mean
Token ID1612
Feature activation-1.82e+00

Pos logit contributions
 Blood+0.007
 blown+0.007
 blood+0.007
 bitten+0.007
elt+0.006
Neg logit contributions
 isn-0.009
heit-0.009
 destination-0.009
aman-0.009
 exactly-0.009
Token!
Token ID0
Feature activation+1.66e-02

Pos logit contributions
 blood+0.054
 blown+0.053
 bitten+0.053
 Blood+0.052
 spilled+0.048
Neg logit contributions
 destination-0.036
aman-0.034
heit-0.033
ement-0.032
 isn-0.032
Token They
Token ID1119
Feature activation-2.89e-01

Pos logit contributions
 isn+0.000
 destination+0.000
aman+0.000
heit+0.000
ement+0.000
Neg logit contributions
 blown-0.000
 blood-0.000
 bitten-0.000
 Blood-0.000
 spilled-0.000
Token
Token ID198
Feature activation-6.99e-01

Pos logit contributions
 blown+0.039
 blood+0.039
 Blood+0.039
 bitten+0.038
 spilled+0.033
Neg logit contributions
 destination-0.052
aman-0.050
heit-0.050
 isn-0.049
ement-0.047
Token
Token ID198
Feature activation-1.09e+00

Pos logit contributions
 Blood+0.012
 blood+0.011
 blown+0.011
 bitten+0.011
 spilled+0.009
Neg logit contributions
 destination-0.022
heit-0.022
aman-0.022
 isn-0.021
ement-0.021
TokenWith
Token ID3152
Feature activation+5.08e-01

Pos logit contributions
 Blood+0.025
 blown+0.024
 blood+0.023
 bitten+0.023
 spilled+0.021
Neg logit contributions
 destination-0.029
heit-0.028
aman-0.027
 isn-0.027
ement-0.027
Token a
Token ID257
Feature activation+4.76e-01

Pos logit contributions
 destination+0.017
aman+0.016
 isn+0.016
heit+0.016
ement+0.016
Neg logit contributions
 blown-0.008
 blood-0.008
 Blood-0.008
 bitten-0.007
 spilled-0.006
Token mis
Token ID2984
Feature activation-2.07e+00

Pos logit contributions
 destination+0.014
aman+0.014
 isn+0.014
heit+0.014
ement+0.014
Neg logit contributions
 blood-0.008
 blown-0.008
 Blood-0.008
 bitten-0.008
 spilled-0.007
Tokenchie
Token ID3043
Feature activation-5.94e+00

Pos logit contributions
 blown+0.037
 bitten+0.035
 Blood+0.035
 blood+0.035
 spilled+0.028
Neg logit contributions
 destination-0.065
aman-0.063
 isn-0.063
heit-0.062
ement-0.059
Tokenvous
Token ID31222
Feature activation-1.15e+00

Pos logit contributions
 blown+0.087
 blood+0.085
 Blood+0.084
 bitten+0.081
 spilled+0.068
Neg logit contributions
 destination-0.201
aman-0.196
 isn-0.194
heit-0.194
ement-0.187
Token gl
Token ID1278
Feature activation+4.64e-01

Pos logit contributions
 blood+0.024
 blown+0.024
 Blood+0.023
 bitten+0.023
 spilled+0.021
Neg logit contributions
 destination-0.032
aman-0.031
heit-0.030
 isn-0.030
ement-0.029
Tokenint
Token ID600
Feature activation-2.43e+00

Pos logit contributions
 destination+0.009
aman+0.009
heit+0.009
 isn+0.008
ement+0.008
Neg logit contributions
 blown-0.014
 blood-0.013
 Blood-0.013
 bitten-0.013
 spilled-0.012
Token in
Token ID287
Feature activation+6.13e-01

Pos logit contributions
 blown+0.054
 Blood+0.054
 blood+0.053
 bitten+0.051
 spilled+0.046
Neg logit contributions
 destination-0.063
 isn-0.062
aman-0.061
heit-0.061
ement-0.059
Token her
Token ID607
Feature activation+1.30e-02

Pos logit contributions
 destination+0.021
aman+0.021
heit+0.020
 isn+0.020
hew+0.020
Neg logit contributions
 blood-0.009
 blown-0.009
 Blood-0.009
 bitten-0.009
 spilled-0.007
Token.
Token ID13
Feature activation-2.91e-01

Pos logit contributions
 blown+0.042
 blood+0.041
 Blood+0.041
 bitten+0.040
 spilled+0.036
Neg logit contributions
 destination-0.043
aman-0.041
 isn-0.041
heit-0.040
ement-0.039
Token They
Token ID1119
Feature activation-1.02e+00

Pos logit contributions
 Blood+0.004
 blood+0.003
 blown+0.003
 bitten+0.003
elt+0.003
Neg logit contributions
heit-0.011
 destination-0.011
aman-0.010
ement-0.010
 isn-0.010
Token were
Token ID547
Feature activation-1.27e-01

Pos logit contributions
 blown+0.019
 blood+0.019
 Blood+0.019
 bitten+0.018
 spilled+0.016
Neg logit contributions
 destination-0.030
aman-0.029
 isn-0.029
heit-0.029
ement-0.028
Token called
Token ID1444
Feature activation-1.20e+00

Pos logit contributions
 blown+0.003
 blood+0.003
 Blood+0.003
 bitten+0.003
 spilled+0.002
Neg logit contributions
 destination-0.003
aman-0.003
heit-0.003
 isn-0.003
ement-0.003
Token ost
Token ID23619
Feature activation+1.41e+00

Pos logit contributions
 blown+0.028
 blood+0.028
 Blood+0.027
 bitten+0.027
 spilled+0.024
Neg logit contributions
 destination-0.030
aman-0.029
heit-0.029
 isn-0.029
hew-0.028
Tokenric
Token ID1173
Feature activation-5.91e+00

Pos logit contributions
 destination+0.033
aman+0.032
 isn+0.032
heit+0.032
ement+0.030
Neg logit contributions
 blown-0.035
 blood-0.034
 Blood-0.034
 bitten-0.034
 spilled-0.030
Tokenhes
Token ID956
Feature activation-1.14e+00

Pos logit contributions
 blood+0.062
 blown+0.062
 Blood+0.057
 bitten+0.055
 spilled+0.044
Neg logit contributions
 isn-0.211
heit-0.210
 destination-0.209
ement-0.205
 exactly-0.204
Token.
Token ID13
Feature activation-5.77e-03

Pos logit contributions
 blown+0.025
 blood+0.024
 Blood+0.024
 bitten+0.024
 spilled+0.021
Neg logit contributions
 destination-0.031
aman-0.030
heit-0.030
 isn-0.029
ement-0.028
Token Lily
Token ID20037
Feature activation-3.97e-01

Pos logit contributions
 Blood+0.000
 blood+0.000
 blown+0.000
 bitten+0.000
elt+0.000
Neg logit contributions
 destination-0.000
heit-0.000
aman-0.000
 isn-0.000
ement-0.000
Token and
Token ID290
Feature activation-1.22e+00

Pos logit contributions
 blown+0.007
 bitten+0.006
 Blood+0.006
 spilled+0.006
 blood+0.006
Neg logit contributions
 destination-0.013
heit-0.012
aman-0.012
ement-0.012
mmm-0.012
Token Ben
Token ID3932
Feature activation+2.27e-01

Pos logit contributions
 blown+0.028
 Blood+0.027
 blood+0.027
 bitten+0.026
 spilled+0.023
Neg logit contributions
 destination-0.031
aman-0.031
 isn-0.030
heit-0.030
 exactly-0.027
Token shouted
Token ID17293
Feature activation-3.05e+00

Pos logit contributions
 blown+0.018
 blood+0.018
 Blood+0.018
 bitten+0.017
 spilled+0.015
Neg logit contributions
 destination-0.022
aman-0.021
heit-0.021
 isn-0.021
ement-0.020
Token.
Token ID13
Feature activation-1.43e+00

Pos logit contributions
 blown+0.082
 blood+0.080
 Blood+0.080
 bitten+0.078
 spilled+0.071
Neg logit contributions
 destination-0.066
 isn-0.063
aman-0.062
heit-0.061
ement-0.060
Token "
Token ID366
Feature activation+2.02e-01

Pos logit contributions
 blown+0.044
 bitten+0.041
 blood+0.039
orns+0.039
 spilled+0.037
Neg logit contributions
 isn-0.025
 destination-0.024
aman-0.021
 So-0.021
So-0.021
TokenThe
Token ID464
Feature activation-5.49e-01

Pos logit contributions
 isn+0.004
aman+0.004
 destination+0.004
So+0.004
hew+0.004
Neg logit contributions
 blown-0.005
 blood-0.005
 bitten-0.005
 Blood-0.005
 spilled-0.005
Token ost
Token ID23619
Feature activation+1.69e+00

Pos logit contributions
 blood+0.009
 blown+0.009
 Blood+0.008
 bitten+0.008
 spilled+0.007
Neg logit contributions
 destination-0.018
aman-0.018
heit-0.018
 isn-0.018
ement-0.017
Tokenric
Token ID1173
Feature activation-5.91e+00

Pos logit contributions
 destination+0.034
aman+0.033
 isn+0.032
heit+0.032
ement+0.030
Neg logit contributions
 blown-0.048
 blood-0.048
 Blood-0.047
 bitten-0.047
 spilled-0.043
Tokenhes
Token ID956
Feature activation-2.24e+00

Pos logit contributions
 blown+0.062
 blood+0.056
 bitten+0.052
 Blood+0.050
 spilled+0.042
Neg logit contributions
 isn-0.216
heit-0.213
ement-0.208
 destination-0.208
hew-0.207
Token are
Token ID389
Feature activation-5.03e-01

Pos logit contributions
 blown+0.059
 blood+0.058
 Blood+0.057
 bitten+0.057
 spilled+0.053
Neg logit contributions
 destination-0.049
aman-0.049
heit-0.047
 isn-0.046
ement-0.045
Token so
Token ID523
Feature activation+3.83e-01

Pos logit contributions
 blown+0.011
 blood+0.010
 Blood+0.010
 bitten+0.010
 spilled+0.009
Neg logit contributions
 destination-0.014
aman-0.014
heit-0.013
 isn-0.013
ement-0.013
Token funny
Token ID8258
Feature activation-1.58e-01

Pos logit contributions
 destination+0.012
aman+0.011
heit+0.011
ement+0.011
 isn+0.011
Neg logit contributions
 blown-0.008
 Blood-0.008
 bitten-0.007
 blood-0.007
 spilled-0.006
Token!"
Token ID2474
Feature activation-1.03e+00

Pos logit contributions
 blown+0.004
 blood+0.004
 bitten+0.004
 Blood+0.004
 spilled+0.004
Neg logit contributions
 destination-0.004
aman-0.004
heit-0.003
ement-0.003
bek-0.003
Token and
Token ID290
Feature activation-1.04e-01

Pos logit contributions
 blown+0.033
 Blood+0.033
 bitten+0.031
 blood+0.031
 spilled+0.028
Neg logit contributions
 destination-0.038
aman-0.037
 isn-0.035
heit-0.035
ement-0.034
Token looked
Token ID3114
Feature activation+1.71e+00

Pos logit contributions
 blown+0.002
 blood+0.002
 Blood+0.002
 bitten+0.002
 spilled+0.002
Neg logit contributions
 destination-0.003
aman-0.003
heit-0.003
 isn-0.003
ement-0.003
Token at
Token ID379
Feature activation+1.68e+00

Pos logit contributions
aman+0.050
 destination+0.049
mmm+0.047
heit+0.047
hew+0.045
Neg logit contributions
 blood-0.035
 blown-0.034
 bitten-0.033
 spilled-0.031
 Blood-0.030
Token the
Token ID262
Feature activation-2.10e-01

Pos logit contributions
 destination+0.045
aman+0.044
 isn+0.043
heit+0.043
ement+0.041
Neg logit contributions
 blown-0.037
 Blood-0.036
 bitten-0.035
 blood-0.035
 spilled-0.031
Token ost
Token ID23619
Feature activation+1.53e+00

Pos logit contributions
 blown+0.005
 blood+0.004
 bitten+0.004
 Blood+0.004
 spilled+0.004
Neg logit contributions
 destination-0.006
heit-0.006
aman-0.006
 isn-0.006
ement-0.005
Tokenric
Token ID1173
Feature activation-5.87e+00

Pos logit contributions
 destination+0.034
aman+0.032
 isn+0.032
heit+0.032
ement+0.030
Neg logit contributions
 blown-0.040
 blood-0.040
 Blood-0.040
 bitten-0.039
 spilled-0.036
Tokenhes
Token ID956
Feature activation-1.13e+00

Pos logit contributions
 blown+0.055
 blood+0.052
 bitten+0.048
 Blood+0.047
 spilled+0.036
Neg logit contributions
 isn-0.220
heit-0.218
 destination-0.218
aman-0.214
ement-0.214
Token.
Token ID13
Feature activation-6.14e-01

Pos logit contributions
 blown+0.025
 blood+0.025
 Blood+0.024
 bitten+0.024
 spilled+0.022
Neg logit contributions
 destination-0.030
aman-0.030
heit-0.030
 isn-0.029
ement-0.027
Token They
Token ID1119
Feature activation-4.89e-01

Pos logit contributions
 blown+0.010
 blood+0.010
 Blood+0.010
 bitten+0.009
 spilled+0.008
Neg logit contributions
 destination-0.020
aman-0.020
heit-0.019
 isn-0.019
ement-0.019
Token saw
Token ID2497
Feature activation+1.51e-01

Pos logit contributions
 blown+0.009
 blood+0.009
 Blood+0.009
 bitten+0.009
 spilled+0.008
Neg logit contributions
 destination-0.014
aman-0.014
 isn-0.014
heit-0.014
ement-0.013
Token one
Token ID530
Feature activation+6.32e-01

Pos logit contributions
 destination+0.004
 isn+0.004
aman+0.004
 exactly+0.004
heit+0.004
Neg logit contributions
 Blood-0.003
 blown-0.003
 bitten-0.003
 blood-0.003
 opener-0.002
Token so
Token ID523
Feature activation+8.62e-01

Pos logit contributions
aman+0.018
 destination+0.018
heit+0.017
 isn+0.017
hew+0.016
Neg logit contributions
 blown-0.014
 blood-0.014
 Blood-0.013
 bitten-0.013
 spilled-0.012
Token that
Token ID326
Feature activation+1.28e+00

Pos logit contributions
 destination+0.028
aman+0.027
heit+0.027
 isn+0.027
ement+0.026
Neg logit contributions
 blown-0.014
 blood-0.014
 Blood-0.014
 bitten-0.013
 spilled-0.011
Token no
Token ID645
Feature activation-1.99e-01

Pos logit contributions
ement+0.047
heit+0.047
aman+0.046
 destination+0.045
hew+0.044
Neg logit contributions
 blown-0.014
 blood-0.013
 bitten-0.013
 spilled-0.012
 hurt-0.011
Token more
Token ID517
Feature activation-9.54e-01

Pos logit contributions
 blood+0.004
 blown+0.004
 bitten+0.004
 Blood+0.004
 spilled+0.004
Neg logit contributions
heit-0.006
 destination-0.005
aman-0.005
 isn-0.005
hew-0.005
Token mis
Token ID2984
Feature activation-2.26e+00

Pos logit contributions
 blood+0.021
 blown+0.021
 bitten+0.020
 Blood+0.019
 spilled+0.018
Neg logit contributions
aman-0.026
heit-0.026
 destination-0.026
hew-0.025
 isn-0.024
Tokenchie
Token ID3043
Feature activation-5.87e+00

Pos logit contributions
 Blood+0.055
 blood+0.055
 blown+0.052
 spilled+0.050
 bitten+0.050
Neg logit contributions
 destination-0.053
aman-0.051
heit-0.050
hew-0.050
 isn-0.049
Tokenvous
Token ID31222
Feature activation-6.14e-01

Pos logit contributions
 blown+0.094
 blood+0.092
 Blood+0.091
 bitten+0.088
 spilled+0.075
Neg logit contributions
 destination-0.190
aman-0.185
 isn-0.184
heit-0.183
ement-0.176
Token mice
Token ID10693
Feature activation-4.33e-01

Pos logit contributions
 blood+0.013
 blown+0.013
 bitten+0.013
 Blood+0.012
 spilled+0.011
Neg logit contributions
 destination-0.017
aman-0.016
heit-0.016
 isn-0.016
ement-0.015
Token could
Token ID714
Feature activation-1.44e+00

Pos logit contributions
 blown+0.009
 blood+0.009
 bitten+0.009
 Blood+0.009
 spilled+0.008
Neg logit contributions
 destination-0.012
aman-0.012
heit-0.012
ement-0.011
 isn-0.011
Token come
Token ID1282
Feature activation-1.20e+00

Pos logit contributions
 blown+0.030
 blood+0.029
 Blood+0.029
 bitten+0.028
 spilled+0.025
Neg logit contributions
 destination-0.040
aman-0.039
heit-0.039
 isn-0.039
ement-0.037
Token in
Token ID287
Feature activation+1.84e+00

Pos logit contributions
 blown+0.026
 blood+0.025
 bitten+0.024
 Blood+0.024
 spilled+0.021
Neg logit contributions
heit-0.032
aman-0.032
 destination-0.032
 isn-0.031
ement-0.031
Token
Token ID198
Feature activation-7.72e-01

Pos logit contributions
 Blood+0.008
 blood+0.008
 blown+0.008
 bitten+0.007
 spilled+0.006
Neg logit contributions
 destination-0.013
heit-0.013
aman-0.013
 isn-0.013
ement-0.012
TokenOne
Token ID3198
Feature activation+1.24e+00

Pos logit contributions
 Blood+0.018
 blood+0.017
 blown+0.017
Tweet+0.017
 bitten+0.016
Neg logit contributions
 destination-0.021
aman-0.019
heit-0.019
 isn-0.019
ement-0.018
Token day
Token ID1110
Feature activation-1.63e+00

Pos logit contributions
 destination+0.025
 isn+0.024
aman+0.024
heit+0.023
ement+0.022
Neg logit contributions
 blown-0.035
 blood-0.035
 Blood-0.034
 bitten-0.034
 spilled-0.030
Token a
Token ID257
Feature activation+1.08e+00

Pos logit contributions
 blown+0.048
 blood+0.048
 Blood+0.047
 bitten+0.047
 spilled+0.043
Neg logit contributions
 destination-0.031
aman-0.030
 isn-0.030
heit-0.029
ement-0.027
Token mis
Token ID2984
Feature activation-1.03e+00

Pos logit contributions
 destination+0.031
aman+0.030
 isn+0.030
heit+0.030
ement+0.029
Neg logit contributions
 blown-0.021
 blood-0.021
 Blood-0.020
 bitten-0.020
 spilled-0.018
Tokenchie
Token ID3043
Feature activation-5.84e+00

Pos logit contributions
 blood+0.022
 blown+0.022
 Blood+0.022
 bitten+0.021
 spilled+0.020
Neg logit contributions
 destination-0.027
aman-0.027
heit-0.026
 isn-0.026
hew-0.026
Tokenvous
Token ID31222
Feature activation-2.58e-01

Pos logit contributions
 blood+0.097
 blown+0.096
 Blood+0.092
 bitten+0.088
 spilled+0.077
Neg logit contributions
 isn-0.182
 destination-0.182
aman-0.180
heit-0.178
ement-0.172
Token monkey
Token ID21657
Feature activation-8.88e-01

Pos logit contributions
 blown+0.004
 Blood+0.004
 bitten+0.004
 blood+0.004
 spilled+0.003
Neg logit contributions
 isn-0.009
 destination-0.008
aman-0.008
heit-0.008
ement-0.008
Token saw
Token ID2497
Feature activation-8.03e-02

Pos logit contributions
 Blood+0.016
 blood+0.016
 blown+0.016
 bitten+0.015
 spilled+0.012
Neg logit contributions
 destination-0.026
 isn-0.026
aman-0.025
heit-0.025
hew-0.024
Token the
Token ID262
Feature activation-6.64e-01

Pos logit contributions
 blown+0.002
 Blood+0.002
 blood+0.002
 bitten+0.002
 spilled+0.001
Neg logit contributions
 isn-0.002
 destination-0.002
aman-0.002
heit-0.002
 exactly-0.002
Token bear
Token ID6842
Feature activation-1.16e+00

Pos logit contributions
 blown+0.011
 Blood+0.011
 blood+0.010
 bitten+0.010
 spilled+0.008
Neg logit contributions
 destination-0.022
 isn-0.021
aman-0.020
heit-0.020
ement-0.019
Token.
Token ID13
Feature activation-1.04e+00

Pos logit contributions
 blown+0.001
 Blood+0.001
 blood+0.001
 bitten+0.001
 spilled+0.001
Neg logit contributions
 isn-0.002
 destination-0.002
aman-0.002
ement-0.002
heit-0.002
Token He
Token ID679
Feature activation-1.23e+00

Pos logit contributions
 blown+0.022
 blood+0.021
 bitten+0.020
 Blood+0.019
 spilled+0.018
Neg logit contributions
 isn-0.029
 destination-0.029
aman-0.029
heit-0.027
ement-0.026
Token was
Token ID373
Feature activation-1.20e+00

Pos logit contributions
 blown+0.036
 blood+0.035
 Blood+0.034
 bitten+0.034
elt+0.031
Neg logit contributions
 isn-0.024
 destination-0.021
heit-0.021
aman-0.020
hew-0.019
Token a
Token ID257
Feature activation-5.27e-01

Pos logit contributions
 blood+0.034
 blown+0.034
 Blood+0.033
 bitten+0.033
orns+0.031
Neg logit contributions
 exactly-0.021
 destination-0.020
 isn-0.019
 forever-0.018
 equally-0.017
Token mis
Token ID2984
Feature activation-1.97e+00

Pos logit contributions
 blown+0.011
 blood+0.010
 Blood+0.010
 bitten+0.010
 spilled+0.009
Neg logit contributions
 destination-0.015
aman-0.015
 isn-0.014
heit-0.014
ement-0.014
Tokenchie
Token ID3043
Feature activation-5.80e+00

Pos logit contributions
 blood+0.044
 Blood+0.042
 blown+0.042
 bitten+0.041
 spilled+0.038
Neg logit contributions
 destination-0.052
aman-0.050
heit-0.049
 isn-0.048
hew-0.048
Tokenvous
Token ID31222
Feature activation-1.42e+00

Pos logit contributions
 blood+0.099
 blown+0.098
 Blood+0.093
 bitten+0.091
 spilled+0.078
Neg logit contributions
 isn-0.179
 destination-0.178
aman-0.176
heit-0.173
ement-0.169
Token little
Token ID1310
Feature activation-1.15e+00

Pos logit contributions
 blown+0.022
 blood+0.022
 Blood+0.022
 bitten+0.021
 spilled+0.018
Neg logit contributions
 destination-0.046
aman-0.045
heit-0.045
 isn-0.045
ement-0.043
Token baby
Token ID5156
Feature activation-4.26e-01

Pos logit contributions
 blown+0.022
 Blood+0.022
 blood+0.021
 bitten+0.021
 spilled+0.017
Neg logit contributions
 destination-0.034
 isn-0.033
aman-0.032
heit-0.031
ement-0.031
Token and
Token ID290
Feature activation-2.66e-01

Pos logit contributions
 blood+0.009
 blown+0.009
 bitten+0.009
 Blood+0.009
 spilled+0.008
Neg logit contributions
 destination-0.011
heit-0.011
aman-0.011
 isn-0.011
ement-0.010
Token always
Token ID1464
Feature activation+1.44e-01

Pos logit contributions
 blown+0.006
 blood+0.006
 Blood+0.006
 bitten+0.006
 spilled+0.005
Neg logit contributions
 isn-0.006
 destination-0.006
heit-0.006
aman-0.006
ement-0.006
TokenOne
Token ID3198
Feature activation+7.32e-01

Pos logit contributions
 Blood+0.018
 blown+0.018
 blood+0.017
 bitten+0.017
 spilled+0.016
Neg logit contributions
 destination-0.015
heit-0.014
aman-0.014
 isn-0.013
ement-0.013
Token day
Token ID1110
Feature activation-1.67e+00

Pos logit contributions
 destination+0.016
 isn+0.016
aman+0.016
heit+0.015
ement+0.014
Neg logit contributions
 blown-0.019
 blood-0.019
 Blood-0.019
 bitten-0.019
 spilled-0.017
Token,
Token ID11
Feature activation-2.86e-01

Pos logit contributions
 blown+0.051
 blood+0.050
 Blood+0.050
 bitten+0.049
 spilled+0.045
Neg logit contributions
 destination-0.031
aman-0.029
 isn-0.029
heit-0.029
ement-0.027
Token a
Token ID257
Feature activation+6.59e-01

Pos logit contributions
 blown+0.006
 bitten+0.005
 blood+0.005
 Blood+0.005
 spilled+0.004
Neg logit contributions
 isn-0.008
 destination-0.008
 exactly-0.008
heit-0.008
aman-0.007
Token mis
Token ID2984
Feature activation-1.16e+00

Pos logit contributions
 destination+0.020
aman+0.020
 isn+0.020
heit+0.020
ement+0.019
Neg logit contributions
 blown-0.012
 blood-0.011
 Blood-0.011
 bitten-0.011
 spilled-0.009
Tokenchie
Token ID3043
Feature activation-5.72e+00

Pos logit contributions
 blood+0.023
 blown+0.023
 Blood+0.023
 bitten+0.022
 spilled+0.020
Neg logit contributions
 destination-0.033
aman-0.032
heit-0.032
 isn-0.032
ement-0.030
Tokenvous
Token ID31222
Feature activation-5.68e-01

Pos logit contributions
 blood+0.102
 blown+0.099
 Blood+0.095
 bitten+0.093
 spilled+0.080
Neg logit contributions
 isn-0.172
 destination-0.171
aman-0.169
heit-0.167
ement-0.162
Token young
Token ID1862
Feature activation-1.28e+00

Pos logit contributions
 blown+0.008
 Blood+0.008
 blood+0.007
 bitten+0.007
 spilled+0.006
Neg logit contributions
 isn-0.019
 destination-0.019
aman-0.019
heit-0.019
ement-0.018
Token boy
Token ID2933
Feature activation-7.79e-01

Pos logit contributions
 Blood+0.025
 blown+0.025
 blood+0.024
 bitten+0.024
 spilled+0.021
Neg logit contributions
 destination-0.037
aman-0.036
 isn-0.036
heit-0.034
ement-0.033
Token decided
Token ID3066
Feature activation+1.79e+00

Pos logit contributions
 blood+0.015
 blown+0.015
 Blood+0.015
 bitten+0.014
 spilled+0.012
Neg logit contributions
 isn-0.022
 destination-0.022
aman-0.021
heit-0.021
hew-0.020
Token to
Token ID284
Feature activation+7.69e-01

Pos logit contributions
 destination+0.057
aman+0.055
 isn+0.055
heit+0.055
ement+0.052
Neg logit contributions
 blown-0.030
 blood-0.030
 Blood-0.029
 bitten-0.028
 spilled-0.024
Token.
Token ID13
Feature activation-6.70e-01

Pos logit contributions
 destination+0.055
aman+0.054
heit+0.053
 isn+0.052
ement+0.050
Neg logit contributions
 blown-0.054
 blood-0.054
 Blood-0.053
 bitten-0.052
 spilled-0.047
Token One
Token ID1881
Feature activation+6.91e-02

Pos logit contributions
 blown+0.014
 blood+0.012
 bitten+0.012
 Blood+0.011
 spilled+0.011
Neg logit contributions
 isn-0.019
 destination-0.019
aman-0.019
ement-0.018
heit-0.018
Token of
Token ID286
Feature activation-1.59e+00

Pos logit contributions
 destination+0.002
aman+0.002
 isn+0.002
heit+0.002
ement+0.002
Neg logit contributions
 blown-0.001
 blood-0.001
 Blood-0.001
 bitten-0.001
 spilled-0.001
Token the
Token ID262
Feature activation-3.32e-01

Pos logit contributions
 blown+0.034
 Blood+0.032
 bitten+0.032
 blood+0.032
 spilled+0.029
Neg logit contributions
 destination-0.042
aman-0.042
heit-0.041
 isn-0.041
 exactly-0.040
Token ost
Token ID23619
Feature activation+1.29e+00

Pos logit contributions
 blown+0.007
 blood+0.006
 bitten+0.006
 Blood+0.006
 spilled+0.005
Neg logit contributions
 destination-0.010
heit-0.010
aman-0.010
 isn-0.009
ement-0.009
Tokenric
Token ID1173
Feature activation-5.70e+00

Pos logit contributions
 destination+0.026
aman+0.025
 isn+0.024
heit+0.024
ement+0.023
Neg logit contributions
 blown-0.036
 blood-0.036
 Blood-0.036
 bitten-0.035
 spilled-0.033
Tokenhes
Token ID956
Feature activation-1.93e+00

Pos logit contributions
 blown+0.056
 blood+0.052
 bitten+0.048
 Blood+0.047
 spilled+0.037
Neg logit contributions
 isn-0.210
heit-0.207
 destination-0.207
ement-0.206
aman-0.204
Token looked
Token ID3114
Feature activation+1.06e+00

Pos logit contributions
 blood+0.042
 blown+0.042
 Blood+0.042
 bitten+0.040
elt+0.035
Neg logit contributions
 destination-0.050
 isn-0.049
aman-0.048
heit-0.047
ement-0.047
Token different
Token ID1180
Feature activation-9.20e-01

Pos logit contributions
aman+0.029
 destination+0.029
heit+0.028
hew+0.027
mmm+0.027
Neg logit contributions
 blood-0.024
 blown-0.023
 bitten-0.023
 Blood-0.022
 spilled-0.021
Token from
Token ID422
Feature activation+2.46e-01

Pos logit contributions
 blown+0.016
 blood+0.016
 bitten+0.016
 Blood+0.014
 spilled+0.014
Neg logit contributions
aman-0.028
 destination-0.028
heit-0.028
hew-0.027
olog-0.026
Token the
Token ID262
Feature activation+1.19e-01

Pos logit contributions
 destination+0.007
aman+0.007
 isn+0.007
heit+0.007
ement+0.007
Neg logit contributions
 blown-0.004
 Blood-0.004
 blood-0.004
 bitten-0.004
 spilled-0.004
Tokenie
Token ID494
Feature activation+1.26e-01

Pos logit contributions
 blown+0.004
 blood+0.004
 Blood+0.004
 bitten+0.004
 spilled+0.004
Neg logit contributions
 destination-0.004
aman-0.004
 isn-0.004
heit-0.004
ement-0.003
Token.
Token ID13
Feature activation-8.64e-01

Pos logit contributions
heit+0.004
 destination+0.004
aman+0.004
 isn+0.004
ement+0.004
Neg logit contributions
 blood-0.002
 blown-0.002
 bitten-0.002
 Blood-0.002
 cat-0.002
Token Unlike
Token ID12101
Feature activation+7.43e-01

Pos logit contributions
 Blood+0.016
 blown+0.015
 blood+0.015
 bitten+0.015
 spilled+0.013
Neg logit contributions
 destination-0.027
aman-0.026
heit-0.026
 isn-0.025
ement-0.024
Token other
Token ID584
Feature activation-9.85e-01

Pos logit contributions
 destination+0.019
heit+0.018
 isn+0.018
aman+0.018
ement+0.017
Neg logit contributions
 blown-0.017
 blood-0.017
 Blood-0.017
 bitten-0.017
 spilled-0.015
Token ost
Token ID23619
Feature activation+1.71e+00

Pos logit contributions
 blown+0.015
 bitten+0.015
 blood+0.015
 Blood+0.013
 squirrel+0.011
Neg logit contributions
ement-0.032
heit-0.032
aman-0.032
 destination-0.031
mmm-0.031
Tokenric
Token ID1173
Feature activation-5.69e+00

Pos logit contributions
 destination+0.037
aman+0.036
 isn+0.035
heit+0.035
ement+0.033
Neg logit contributions
 blown-0.046
 blood-0.045
 Blood-0.045
 bitten-0.044
 spilled-0.040
Tokenhes
Token ID956
Feature activation-1.41e+00

Pos logit contributions
 blown+0.060
 blood+0.059
 Blood+0.054
 bitten+0.053
 spilled+0.043
Neg logit contributions
 isn-0.205
heit-0.202
 destination-0.202
 exactly-0.199
ement-0.198
Token,
Token ID11
Feature activation-5.69e-01

Pos logit contributions
 blown+0.032
 blood+0.032
 Blood+0.031
 bitten+0.031
 spilled+0.028
Neg logit contributions
 destination-0.037
aman-0.036
heit-0.035
 isn-0.034
ement-0.034
Token his
Token ID465
Feature activation+1.06e+00

Pos logit contributions
 blown+0.012
 blood+0.012
 Blood+0.012
 bitten+0.011
 spilled+0.010
Neg logit contributions
 destination-0.015
 isn-0.015
aman-0.015
heit-0.015
ement-0.014
Token feathers
Token ID27400
Feature activation-3.00e-01

Pos logit contributions
heit+0.032
ement+0.032
aman+0.032
 isn+0.031
mmm+0.031
Neg logit contributions
 blown-0.019
 blood-0.018
 bitten-0.018
 Blood-0.017
 spilled-0.014
Token gl
Token ID1278
Feature activation+1.76e+00

Pos logit contributions
 Blood+0.008
 blown+0.008
 blood+0.008
 bitten+0.008
 spilled+0.007
Neg logit contributions
 isn-0.006
 destination-0.006
aman-0.006
heit-0.006
ement-0.006
Token did
Token ID750
Feature activation+2.66e-01

Pos logit contributions
aman+0.019
 destination+0.019
heit+0.019
mmm+0.018
ement+0.018
Neg logit contributions
 blown-0.008
 bitten-0.007
 Blood-0.007
 blood-0.007
 spilled-0.007
Token not
Token ID407
Feature activation-9.17e-01

Pos logit contributions
aman+0.010
hew+0.009
ement+0.009
heit+0.009
 destination+0.009
Neg logit contributions
 Blood-0.003
 blown-0.003
 blood-0.003
 bitten-0.003
 hurt-0.003
Token know
Token ID760
Feature activation-2.40e-01

Pos logit contributions
 blown+0.024
 Blood+0.024
 blood+0.024
 bitten+0.023
 spilled+0.021
Neg logit contributions
 destination-0.020
 isn-0.019
aman-0.019
heit-0.019
hew-0.018
Token what
Token ID644
Feature activation+5.30e-02

Pos logit contributions
 blood+0.006
 blown+0.005
 bitten+0.005
 spilled+0.005
 Blood+0.005
Neg logit contributions
 destination-0.007
aman-0.006
heit-0.006
bek-0.006
olog-0.006
Token ost
Token ID23619
Feature activation+1.29e+00

Pos logit contributions
aman+0.002
heit+0.002
 destination+0.002
hew+0.002
ement+0.002
Neg logit contributions
 Blood-0.001
 blood-0.001
 blown-0.001
 bitten-0.001
 spilled-0.001
Tokenric
Token ID1173
Feature activation-5.69e+00

Pos logit contributions
 destination+0.026
aman+0.025
 isn+0.024
heit+0.024
ement+0.023
Neg logit contributions
 blood-0.037
 blown-0.037
 Blood-0.036
 bitten-0.035
 spilled-0.033
Tokenhes
Token ID956
Feature activation-2.36e+00

Pos logit contributions
 blood+0.065
 blown+0.065
 Blood+0.061
 bitten+0.059
 spilled+0.048
Neg logit contributions
 isn-0.203
 destination-0.203
heit-0.201
aman-0.198
ement-0.194
Token were
Token ID547
Feature activation-1.57e+00

Pos logit contributions
 blown+0.047
 blood+0.046
 Blood+0.045
 bitten+0.044
 spilled+0.041
Neg logit contributions
 destination-0.067
aman-0.066
heit-0.065
hew-0.062
ement-0.062
Token.
Token ID13
Feature activation-5.50e-01

Pos logit contributions
 blown+0.035
 blood+0.033
 bitten+0.033
 Blood+0.032
 spilled+0.030
Neg logit contributions
 destination-0.042
aman-0.042
heit-0.041
ement-0.039
 isn-0.039
Token They
Token ID1119
Feature activation-5.57e-01

Pos logit contributions
 Blood+0.007
 blown+0.006
 blood+0.006
 bitten+0.005
elt+0.005
Neg logit contributions
heit-0.020
 destination-0.020
aman-0.020
ement-0.019
hew-0.019
Token looked
Token ID3114
Feature activation+1.61e+00

Pos logit contributions
 blown+0.010
 blood+0.010
 Blood+0.010
 bitten+0.009
 spilled+0.009
Neg logit contributions
 destination-0.017
aman-0.017
 isn-0.016
heit-0.016
ement-0.016
Token and
Token ID290
Feature activation-1.23e-02

Pos logit contributions
heit+0.008
aman+0.008
 destination+0.008
 isn+0.007
hew+0.007
Neg logit contributions
 blood-0.005
 blown-0.005
 Blood-0.005
 bitten-0.005
 spilled-0.004
Token run
Token ID1057
Feature activation-8.20e-01

Pos logit contributions
 blown+0.000
 blood+0.000
 Blood+0.000
 bitten+0.000
 spilled+0.000
Neg logit contributions
 destination-0.000
aman-0.000
 isn-0.000
heit-0.000
ement-0.000
Token to
Token ID284
Feature activation+1.50e+00

Pos logit contributions
 blown+0.014
 bitten+0.014
 blood+0.014
 Blood+0.014
 spilled+0.012
Neg logit contributions
aman-0.026
 destination-0.026
heit-0.025
 isn-0.025
ement-0.024
Token the
Token ID262
Feature activation+3.23e-01

Pos logit contributions
aman+0.049
 destination+0.049
 isn+0.048
heit+0.048
ement+0.048
Neg logit contributions
 blood-0.024
 blown-0.023
 Blood-0.023
 bitten-0.022
 spilled-0.018
Token ost
Token ID23619
Feature activation+1.88e+00

Pos logit contributions
 destination+0.010
aman+0.010
heit+0.010
 isn+0.010
ement+0.009
Neg logit contributions
 blown-0.006
 blood-0.006
 Blood-0.006
 bitten-0.006
 spilled-0.005
Tokenric
Token ID1173
Feature activation-5.60e+00

Pos logit contributions
 destination+0.041
aman+0.039
 isn+0.039
heit+0.039
ement+0.036
Neg logit contributions
 blown-0.051
 blood-0.050
 Blood-0.049
 bitten-0.049
 spilled-0.045
Tokenhes
Token ID956
Feature activation-9.63e-01

Pos logit contributions
 blown+0.055
 blood+0.052
 bitten+0.048
 Blood+0.047
 spilled+0.038
Neg logit contributions
 isn-0.206
 destination-0.205
heit-0.204
aman-0.201
ement-0.200
Token.
Token ID13
Feature activation+9.67e-02

Pos logit contributions
 blown+0.020
 blood+0.020
 Blood+0.020
 bitten+0.019
 spilled+0.017
Neg logit contributions
 destination-0.026
aman-0.026
heit-0.026
 isn-0.025
ement-0.024
Token
Token ID198
Feature activation+4.51e-01

Pos logit contributions
 destination+0.003
heit+0.003
aman+0.003
 isn+0.003
ement+0.003
Neg logit contributions
 Blood-0.002
 blood-0.002
 blown-0.002
 bitten-0.001
 spilled-0.001
Token
Token ID198
Feature activation+1.27e-01

Pos logit contributions
 destination+0.014
aman+0.014
heit+0.014
 isn+0.014
ement+0.013
Neg logit contributions
 Blood-0.008
 blood-0.008
 blown-0.008
 bitten-0.007
 spilled-0.006
Token"
Token ID1
Feature activation-1.28e+00

Pos logit contributions
 destination+0.003
 isn+0.003
ement+0.003
aman+0.003
heit+0.003
Neg logit contributions
 Blood-0.003
 blown-0.003
 blood-0.003
 bitten-0.003
Tweet-0.003
Token went
Token ID1816
Feature activation-7.06e-01

Pos logit contributions
 Blood+0.002
 blood+0.002
 blown+0.002
 bitten+0.002
 spilled+0.002
Neg logit contributions
 destination-0.004
aman-0.004
heit-0.004
 isn-0.004
hew-0.004
Token home
Token ID1363
Feature activation-8.58e-01

Pos logit contributions
 Blood+0.019
 blown+0.018
 blood+0.018
 bitten+0.017
 spilled+0.016
Neg logit contributions
 destination-0.017
aman-0.015
 exactly-0.015
 isn-0.014
 forever-0.014
Token and
Token ID290
Feature activation+4.87e-01

Pos logit contributions
 blown+0.021
 Blood+0.021
 blood+0.021
 bitten+0.020
 spilled+0.018
Neg logit contributions
 destination-0.021
aman-0.020
 isn-0.019
heit-0.018
 exactly-0.018
Token had
Token ID550
Feature activation-5.28e-01

Pos logit contributions
 destination+0.015
aman+0.015
 isn+0.015
heit+0.015
ement+0.014
Neg logit contributions
 blown-0.008
 blood-0.008
 Blood-0.008
 bitten-0.008
 spilled-0.007
Token a
Token ID257
Feature activation+1.31e+00

Pos logit contributions
 blown+0.008
 blood+0.007
 bitten+0.007
 Blood+0.007
 spilled+0.006
Neg logit contributions
heit-0.018
 destination-0.018
aman-0.018
 isn-0.017
ement-0.017
Token y
Token ID331
Feature activation+5.04e+00

Pos logit contributions
heit+0.035
ement+0.033
 isn+0.033
 destination+0.033
aman+0.033
Neg logit contributions
 blood-0.029
 blown-0.029
 Blood-0.028
 bitten-0.028
 spilled-0.028
Tokenummy
Token ID13513
Feature activation-6.87e-01

Pos logit contributions
 isn+0.093
heit+0.093
 destination+0.089
aman+0.086
hew+0.080
Neg logit contributions
 blood-0.146
 blown-0.144
 Blood-0.142
 bitten-0.141
 spilled-0.131
Token dinner
Token ID8073
Feature activation+1.60e+00

Pos logit contributions
 blood+0.014
 blown+0.014
 Blood+0.014
 bitten+0.014
 spilled+0.013
Neg logit contributions
 destination-0.019
heit-0.019
aman-0.018
 isn-0.018
hew-0.017
Token.
Token ID13
Feature activation-1.04e-01

Pos logit contributions
heit+0.048
 destination+0.046
aman+0.045
 isn+0.044
hew+0.043
Neg logit contributions
 blown-0.032
 blood-0.031
 bitten-0.030
 Blood-0.029
 spilled-0.028
Token Lily
Token ID20037
Feature activation-3.53e-01

Pos logit contributions
 Blood+0.001
 blown+0.001
 blood+0.001
 bitten+0.001
 spilled+0.001
Neg logit contributions
 destination-0.004
heit-0.004
aman-0.004
 isn-0.003
ement-0.003
Token was
Token ID373
Feature activation+2.23e-01

Pos logit contributions
 blown+0.007
 blood+0.007
 bitten+0.006
 spilled+0.006
 Blood+0.006
Neg logit contributions
 destination-0.010
heit-0.010
aman-0.010
ement-0.010
 isn-0.010
Token€
Token ID26391
Feature activation+2.23e-01

Pos logit contributions
 destination+0.077
heit+0.075
 exactly+0.072
aman+0.072
 isn+0.068
Neg logit contributions
 Blood-0.083
 blown-0.079
 bitten-0.075
 blood-0.073
elt-0.068
Token�
Token ID129
Feature activation+2.91e+00

Pos logit contributions
heit+0.007
 destination+0.007
aman+0.007
ement+0.006
 exactly+0.006
Neg logit contributions
 Blood-0.004
 blown-0.004
 bitten-0.003
 blood-0.003
 spilled-0.003
Token�
Token ID241
Feature activation+3.38e-01

Pos logit contributions
 destination+0.064
 isn+0.062
 exactly+0.062
heit+0.061
aman+0.059
Neg logit contributions
 Blood-0.077
 blown-0.072
 bitten-0.069
 blood-0.066
Tweet-0.063
Tokenbut
Token ID4360
Feature activation+2.38e+00

Pos logit contributions
 destination+0.010
heit+0.010
aman+0.009
 isn+0.009
ement+0.009
Neg logit contributions
 Blood-0.007
 blown-0.007
 blood-0.007
 bitten-0.006
 spilled-0.006
Token don
Token ID836
Feature activation+5.90e-01

Pos logit contributions
 destination+0.065
aman+0.065
heit+0.064
ement+0.064
hew+0.061
Neg logit contributions
 blood-0.048
 blown-0.048
 bitten-0.044
 Blood-0.044
 spilled-0.041
Tokenâ
Token ID22940
Feature activation+4.72e+00

Pos logit contributions
 destination+0.020
aman+0.020
heit+0.019
 isn+0.019
ement+0.019
Neg logit contributions
 blown-0.009
 Blood-0.008
 blood-0.008
 bitten-0.008
 spilled-0.007
Token€
Token ID26391
Feature activation-1.59e-01

Pos logit contributions
 destination+0.099
heit+0.092
 exactly+0.092
aman+0.090
 isn+0.088
Neg logit contributions
 blown-0.125
 Blood-0.125
 bitten-0.122
 blood-0.119
agged-0.109
Tokenâ„¢
Token ID8151
Feature activation+8.13e-01

Pos logit contributions
 Blood+0.004
 blown+0.003
 bitten+0.003
 blood+0.003
elt+0.003
Neg logit contributions
heit-0.004
 destination-0.004
aman-0.004
ement-0.004
 exactly-0.004
Tokent
Token ID83
Feature activation-8.37e-01

Pos logit contributions
heit+0.027
 destination+0.026
aman+0.025
idays+0.024
 amaz+0.024
Neg logit contributions
 Blood-0.012
 bitten-0.011
 blown-0.011
 blood-0.011
 spilled-0.010
Token touch
Token ID3638
Feature activation+9.46e-01

Pos logit contributions
 blown+0.016
 blood+0.016
 Blood+0.016
 bitten+0.015
 spilled+0.014
Neg logit contributions
 destination-0.024
aman-0.023
ement-0.023
heit-0.023
 exactly-0.021
Token it
Token ID340
Feature activation-5.42e-02

Pos logit contributions
 destination+0.026
aman+0.025
bek+0.025
heit+0.024
olog+0.024
Neg logit contributions
 blood-0.020
 blown-0.019
 bitten-0.018
 Blood-0.017
 spilled-0.016
Token just
Token ID655
Feature activation+1.15e+00

Pos logit contributions
aman+0.045
 destination+0.045
heit+0.043
ement+0.043
 isn+0.039
Neg logit contributions
 blown-0.052
 blood-0.051
 bitten-0.050
 Blood-0.049
 spilled-0.046
Token a
Token ID257
Feature activation+1.62e+00

Pos logit contributions
 destination+0.030
aman+0.030
heit+0.029
ement+0.028
 isn+0.027
Neg logit contributions
 blown-0.026
 blood-0.026
 bitten-0.025
 Blood-0.025
 spilled-0.022
Token big
Token ID1263
Feature activation+7.02e-01

Pos logit contributions
ement+0.050
heit+0.049
aman+0.049
 destination+0.047
hew+0.047
Neg logit contributions
 blown-0.029
 blood-0.028
 bitten-0.028
 Blood-0.026
 spilled-0.026
Token cat
Token ID3797
Feature activation-1.38e-01

Pos logit contributions
aman+0.020
heit+0.020
 destination+0.020
ement+0.020
hew+0.020
Neg logit contributions
 blood-0.013
 blown-0.013
 bitten-0.012
 Blood-0.012
 spilled-0.011
Token.
Token ID13
Feature activation+8.72e-01

Pos logit contributions
 blown+0.003
 bitten+0.003
 blood+0.003
 spilled+0.003
 Blood+0.003
Neg logit contributions
 destination-0.004
heit-0.003
aman-0.003
ement-0.003
hew-0.003
Tokenâ
Token ID22940
Feature activation+4.76e+00

Pos logit contributions
 destination+0.025
heit+0.024
aman+0.023
ement+0.022
 isn+0.022
Neg logit contributions
 Blood-0.018
 blood-0.017
 blown-0.017
 bitten-0.017
elt-0.015
Token€
Token ID26391
Feature activation-2.69e-02

Pos logit contributions
 destination+0.100
aman+0.089
heit+0.089
 exactly+0.087
 isn+0.087
Neg logit contributions
 Blood-0.130
 blown-0.130
 bitten-0.129
 blood-0.128
 spilled-0.115
Token
Token ID198
Feature activation+4.61e-01

Pos logit contributions
 Blood+0.001
 bitten+0.001
 blown+0.001
 blood+0.001
 spilled+0.001
Neg logit contributions
 destination-0.001
aman-0.001
heit-0.001
ement-0.001
 exactly-0.001
Token
Token ID198
Feature activation-3.20e-02

Pos logit contributions
 destination+0.015
heit+0.014
aman+0.014
 isn+0.014
ement+0.013
Neg logit contributions
 Blood-0.008
 blood-0.008
 blown-0.008
 bitten-0.008
Tweet-0.006
TokenTom
Token ID13787
Feature activation+1.04e+00

Pos logit contributions
 Blood+0.001
 blown+0.001
 blood+0.001
 bitten+0.001
Tweet+0.001
Neg logit contributions
 destination-0.001
 isn-0.001
ement-0.001
heit-0.001
aman-0.001
Token was
Token ID373
Feature activation+3.71e-01

Pos logit contributions
 destination+0.030
heit+0.029
aman+0.029
ement+0.029
 isn+0.028
Neg logit contributions
 blown-0.020
 bitten-0.019
 blood-0.019
 Blood-0.019
 spilled-0.018
Token her
Token ID607
Feature activation-9.26e-01

Pos logit contributions
 blown+0.010
 blood+0.010
 bitten+0.010
 Blood+0.010
 spilled+0.008
Neg logit contributions
 destination-0.021
aman-0.020
heit-0.020
 isn-0.020
ement-0.019
Token nap
Token ID25422
Feature activation+9.99e-01

Pos logit contributions
 blown+0.016
 blood+0.016
 bitten+0.016
 Blood+0.015
 spilled+0.014
Neg logit contributions
aman-0.029
heit-0.029
 destination-0.028
 isn-0.028
ement-0.027
Token and
Token ID290
Feature activation+4.01e-01

Pos logit contributions
 destination+0.029
heit+0.029
aman+0.029
 isn+0.028
hew+0.027
Neg logit contributions
 blown-0.019
 blood-0.019
 bitten-0.018
 Blood-0.018
 spilled-0.017
Token had
Token ID550
Feature activation+3.09e-01

Pos logit contributions
 destination+0.012
aman+0.011
heit+0.011
 isn+0.011
ement+0.011
Neg logit contributions
 blown-0.008
 blood-0.008
 Blood-0.007
 bitten-0.007
 spilled-0.007
Token a
Token ID257
Feature activation+1.68e+00

Pos logit contributions
 destination+0.010
heit+0.009
aman+0.009
 isn+0.009
ement+0.009
Neg logit contributions
 blown-0.006
 blood-0.005
 bitten-0.005
 Blood-0.005
 spilled-0.005
Token y
Token ID331
Feature activation+4.98e+00

Pos logit contributions
heit+0.043
ement+0.040
 isn+0.039
aman+0.039
hew+0.038
Neg logit contributions
 blood-0.039
 blown-0.038
 spilled-0.037
 bitten-0.037
 Blood-0.036
Tokenummy
Token ID13513
Feature activation-3.22e-01

Pos logit contributions
heit+0.097
 isn+0.096
 destination+0.091
aman+0.090
hew+0.082
Neg logit contributions
 blood-0.140
 blown-0.139
 bitten-0.136
 Blood-0.135
 spilled-0.126
Token sausage
Token ID31889
Feature activation+1.24e+00

Pos logit contributions
 blood+0.007
 blown+0.006
 bitten+0.006
 Blood+0.006
 spilled+0.006
Neg logit contributions
 destination-0.009
heit-0.009
aman-0.009
 isn-0.009
hew-0.008
Token adventure
Token ID8855
Feature activation+1.51e+00

Pos logit contributions
 destination+0.030
aman+0.029
heit+0.029
 isn+0.028
ement+0.027
Neg logit contributions
 blown-0.030
 blood-0.030
 Blood-0.029
 bitten-0.029
 spilled-0.027
Token.
Token ID13
Feature activation+7.70e-01

Pos logit contributions
heit+0.047
aman+0.043
 destination+0.042
 isn+0.041
hew+0.041
Neg logit contributions
 blown-0.028
 bitten-0.027
 blood-0.026
 Blood-0.024
 spilled-0.023
Token<|endoftext|>
Token ID50256
Feature activation+1.19e+00

Pos logit contributions
 destination+0.020
aman+0.020
heit+0.019
 isn+0.019
ement+0.018
Neg logit contributions
 blown-0.017
 blood-0.017
 Blood-0.017
 bitten-0.016
 spilled-0.015
Tokenâ„¢
Token ID8151
Feature activation+1.47e+00

Pos logit contributions
 destination+0.005
aman+0.004
heit+0.004
ement+0.004
 exactly+0.004
Neg logit contributions
 Blood-0.005
 blown-0.005
 bitten-0.005
 blood-0.005
 spilled-0.005
Tokens
Token ID82
Feature activation+2.41e+00

Pos logit contributions
 destination+0.043
heit+0.042
aman+0.040
 isn+0.038
idays+0.038
Neg logit contributions
 Blood-0.028
 blown-0.027
 blood-0.027
 bitten-0.027
 spilled-0.025
Token OK
Token ID7477
Feature activation+2.67e+00

Pos logit contributions
 destination+0.058
aman+0.057
heit+0.056
ement+0.054
 isn+0.051
Neg logit contributions
 blown-0.059
 blood-0.059
 bitten-0.057
 Blood-0.055
 spilled-0.053
Token,
Token ID11
Feature activation-1.90e-01

Pos logit contributions
heit+0.075
 destination+0.074
aman+0.071
ement+0.071
 destinations+0.067
Neg logit contributions
 blood-0.053
 Blood-0.052
 bitten-0.052
 blown-0.050
elt-0.047
Token we
Token ID356
Feature activation+8.58e-01

Pos logit contributions
 blood+0.003
 blown+0.003
 Blood+0.003
 bitten+0.003
 spilled+0.003
Neg logit contributions
 destination-0.006
heit-0.006
ement-0.006
aman-0.006
hew-0.005
Tokenâ
Token ID22940
Feature activation+5.01e+00

Pos logit contributions
aman+0.021
 destination+0.020
heit+0.020
ement+0.020
mmm+0.019
Neg logit contributions
 blown-0.020
 blood-0.020
 bitten-0.020
 spilled-0.019
 Blood-0.018
Token€
Token ID26391
Feature activation+2.19e-01

Pos logit contributions
 destination+0.108
 exactly+0.100
 isn+0.099
heit+0.098
aman+0.097
Neg logit contributions
 blown-0.133
 bitten-0.131
 Blood-0.128
 blood-0.126
 spilled-0.115
Tokenâ„¢
Token ID8151
Feature activation+1.41e+00

Pos logit contributions
heit+0.005
aman+0.005
 destination+0.005
ement+0.005
 exactly+0.005
Neg logit contributions
 Blood-0.005
 blown-0.005
 bitten-0.005
 spilled-0.005
 blood-0.005
Tokenll
Token ID297
Feature activation+1.66e+00

Pos logit contributions
heit+0.044
 destination+0.043
aman+0.041
 isn+0.040
idays+0.039
Neg logit contributions
 Blood-0.024
 blown-0.023
 blood-0.023
 bitten-0.023
 spilled-0.021
Token mention
Token ID3068
Feature activation+2.82e+00

Pos logit contributions
 destination+0.046
aman+0.046
heit+0.044
 isn+0.044
ement+0.044
Neg logit contributions
 blown-0.034
 blood-0.033
 bitten-0.032
 Blood-0.031
 spilled-0.029
Token it
Token ID340
Feature activation+5.52e-01

Pos logit contributions
 destination+0.089
heit+0.088
aman+0.088
bek+0.085
ement+0.085
Neg logit contributions
 blood-0.050
 blown-0.042
 bitten-0.041
 spilled-0.037
 hurt-0.035
Token looked
Token ID3114
Feature activation+1.43e+00

Pos logit contributions
 destination+0.018
aman+0.018
heit+0.018
 isn+0.017
ement+0.017
Neg logit contributions
 blown-0.014
 Blood-0.014
 blood-0.014
 bitten-0.013
 spilled-0.012
Token and
Token ID290
Feature activation+1.32e+00

Pos logit contributions
aman+0.041
 destination+0.041
heit+0.039
mmm+0.039
hew+0.038
Neg logit contributions
 blood-0.030
 blown-0.029
 bitten-0.028
 Blood-0.028
 spilled-0.027
Token said
Token ID531
Feature activation-6.92e-01

Pos logit contributions
 destination+0.039
aman+0.038
 isn+0.038
heit+0.037
ement+0.036
Neg logit contributions
 blown-0.026
 blood-0.025
 Blood-0.025
 bitten-0.025
 spilled-0.021
Token,
Token ID11
Feature activation+7.57e-02

Pos logit contributions
 Blood+0.018
 blood+0.017
 bitten+0.017
 blown+0.017
 spilled+0.016
Neg logit contributions
 destination-0.017
aman-0.017
heit-0.016
hew-0.015
 destinations-0.015
Token "
Token ID366
Feature activation+7.33e-01

Pos logit contributions
 destination+0.002
 isn+0.002
aman+0.002
heit+0.002
ement+0.002
Neg logit contributions
 blown-0.002
 blood-0.002
 Blood-0.002
 bitten-0.002
 spilled-0.001
TokenWow
Token ID22017
Feature activation+1.28e+00

Pos logit contributions
 destination+0.018
 isn+0.017
aman+0.017
heit+0.017
ement+0.016
Neg logit contributions
 blown-0.018
 blood-0.018
 Blood-0.017
 bitten-0.017
 spilled-0.015
Token,
Token ID11
Feature activation+5.22e-01

Pos logit contributions
aman+0.032
 destination+0.031
 destinations+0.029
heit+0.028
ement+0.028
Neg logit contributions
 Blood-0.031
 blood-0.030
 blown-0.029
 bitten-0.028
 spilled-0.028
Token Lily
Token ID20037
Feature activation+6.28e-01

Pos logit contributions
 destination+0.014
aman+0.014
ement+0.013
heit+0.013
hew+0.013
Neg logit contributions
 blood-0.012
 Blood-0.011
 blown-0.011
 bitten-0.011
 spilled-0.010
Token!
Token ID0
Feature activation+1.27e+00

Pos logit contributions
aman+0.014
 destination+0.014
heit+0.014
ement+0.013
 destinations+0.012
Neg logit contributions
 bitten-0.016
 blood-0.016
 blown-0.016
 Blood-0.016
 spilled-0.015
Token Your
Token ID3406
Feature activation+3.93e-01

Pos logit contributions
 destination+0.031
aman+0.030
heit+0.029
 isn+0.028
ement+0.028
Neg logit contributions
 Blood-0.031
 blown-0.031
 blood-0.031
 bitten-0.030
 spilled-0.027
Token dress
Token ID6576
Feature activation-4.71e-03

Pos logit contributions
aman+0.013
heit+0.012
mmm+0.012
 destination+0.011
hew+0.011
Neg logit contributions
 blood-0.007
 blown-0.007
 Blood-0.007
 bitten-0.006
 spilled-0.006
Token hears
Token ID23180
Feature activation-8.22e-01

Pos logit contributions
 destination+0.035
aman+0.035
heit+0.034
 isn+0.034
ement+0.032
Neg logit contributions
 blood-0.026
 blown-0.026
 Blood-0.025
 bitten-0.025
 spilled-0.022
Token the
Token ID262
Feature activation+3.13e-01

Pos logit contributions
 blown+0.023
 bitten+0.022
 Blood+0.021
 blood+0.020
elt+0.020
Neg logit contributions
aman-0.016
 isn-0.016
 destination-0.016
heit-0.015
ement-0.015
Token noise
Token ID7838
Feature activation-1.03e+00

Pos logit contributions
 isn+0.006
 destination+0.006
 difference+0.005
ement+0.005
heit+0.005
Neg logit contributions
 blown-0.009
 bitten-0.009
 Blood-0.009
elt-0.008
ashed-0.008
Token and
Token ID290
Feature activation+8.43e-01

Pos logit contributions
 blown+0.023
 blood+0.023
 Blood+0.023
 bitten+0.022
 spilled+0.020
Neg logit contributions
 destination-0.027
aman-0.026
 isn-0.026
heit-0.026
ement-0.025
Token comes
Token ID2058
Feature activation-1.23e+00

Pos logit contributions
 isn+0.022
 destination+0.021
heit+0.021
aman+0.020
ement+0.019
Neg logit contributions
 blown-0.019
 Blood-0.019
 bitten-0.018
 blood-0.017
 spilled-0.016
Token to
Token ID284
Feature activation+2.39e+00

Pos logit contributions
 Blood+0.025
 blown+0.025
 blood+0.024
 bitten+0.023
 spilled+0.021
Neg logit contributions
 destination-0.035
 isn-0.032
aman-0.031
heit-0.031
hew-0.030
Token see
Token ID766
Feature activation+1.61e+00

Pos logit contributions
 destination+0.063
aman+0.060
 isn+0.059
heit+0.056
 difference+0.053
Neg logit contributions
 blown-0.053
 Blood-0.050
 bitten-0.048
 blood-0.047
elt-0.044
Token what
Token ID644
Feature activation+8.28e-01

Pos logit contributions
 destination+0.028
 isn+0.027
aman+0.027
heit+0.027
ement+0.025
Neg logit contributions
 blown-0.050
 Blood-0.049
 blood-0.049
 bitten-0.049
 spilled-0.045
Token is
Token ID318
Feature activation+1.16e+00

Pos logit contributions
 destination+0.013
 isn+0.012
aman+0.012
heit+0.012
ement+0.011
Neg logit contributions
 blown-0.027
 blood-0.027
 Blood-0.027
 bitten-0.027
 spilled-0.025
Token wrong
Token ID2642
Feature activation-8.60e-01

Pos logit contributions
 destination+0.024
aman+0.024
heit+0.023
 isn+0.023
ement+0.022
Neg logit contributions
 blown-0.032
 blood-0.032
 Blood-0.032
 bitten-0.031
 spilled-0.029
Token.
Token ID13
Feature activation-2.48e-01

Pos logit contributions
 blood+0.017
 blown+0.016
 Blood+0.016
 bitten+0.015
 spilled+0.014
Neg logit contributions
 destination-0.026
heit-0.026
aman-0.025
 isn-0.024
hew-0.024
Token day
Token ID1110
Feature activation-1.72e+00

Pos logit contributions
 destination+0.023
aman+0.023
heit+0.023
 isn+0.022
ement+0.021
Neg logit contributions
 blood-0.019
 blown-0.019
 Blood-0.019
 bitten-0.019
 spilled-0.017
Token his
Token ID465
Feature activation+5.77e-01

Pos logit contributions
 Blood+0.045
 blown+0.045
 blood+0.045
 bitten+0.045
 spilled+0.042
Neg logit contributions
 destination-0.039
aman-0.037
heit-0.036
 isn-0.035
ement-0.035
Token dad
Token ID9955
Feature activation+2.13e-01

Pos logit contributions
heit+0.015
 destination+0.015
aman+0.015
 isn+0.015
ement+0.014
Neg logit contributions
 blood-0.013
 blown-0.012
 Blood-0.012
 bitten-0.012
 spilled-0.011
Token gave
Token ID2921
Feature activation+9.80e-01

Pos logit contributions
 destination+0.007
heit+0.007
aman+0.006
ement+0.006
 isn+0.006
Neg logit contributions
 blown-0.004
 blood-0.004
 bitten-0.004
 spilled-0.003
 Blood-0.003
Token him
Token ID683
Feature activation+7.95e-01

Pos logit contributions
 destination+0.027
heit+0.026
aman+0.026
ement+0.025
 isn+0.025
Neg logit contributions
 blood-0.021
 blown-0.021
 bitten-0.021
 Blood-0.020
 spilled-0.018
Token a
Token ID257
Feature activation+1.81e+00

Pos logit contributions
 destination+0.027
aman+0.026
 isn+0.026
heit+0.026
ement+0.025
Neg logit contributions
 blown-0.012
 blood-0.011
 Blood-0.011
 bitten-0.011
 spilled-0.009
Token weapon
Token ID4282
Feature activation+3.92e-01

Pos logit contributions
 destination+0.049
heit+0.049
aman+0.049
 isn+0.048
ement+0.047
Neg logit contributions
 blood-0.038
 blown-0.037
 Blood-0.036
 bitten-0.036
 spilled-0.033
Token.
Token ID13
Feature activation-4.88e-01

Pos logit contributions
 destination+0.011
 isn+0.010
aman+0.010
heit+0.010
ement+0.010
Neg logit contributions
 blown-0.008
 Blood-0.008
 blood-0.008
 bitten-0.008
 spilled-0.007
Token He
Token ID679
Feature activation+3.87e-01

Pos logit contributions
 Blood+0.007
 blood+0.007
 blown+0.006
 bitten+0.006
 spilled+0.005
Neg logit contributions
 destination-0.017
heit-0.017
aman-0.017
 isn-0.016
ement-0.016
Token was
Token ID373
Feature activation+5.00e-01

Pos logit contributions
aman+0.012
 destination+0.012
heit+0.011
ement+0.011
 isn+0.011
Neg logit contributions
 blown-0.007
 blood-0.007
 bitten-0.007
 Blood-0.007
 spilled-0.006
Token really
Token ID1107
Feature activation+1.23e+00

Pos logit contributions
 destination+0.011
 isn+0.011
aman+0.011
heit+0.011
ement+0.010
Neg logit contributions
 blown-0.013
 blood-0.013
 Blood-0.013
 bitten-0.012
 spilled-0.011
Token made
Token ID925
Feature activation-2.47e+00

Pos logit contributions
 blown+0.002
 blood+0.002
 Blood+0.002
 bitten+0.002
 spilled+0.002
Neg logit contributions
 destination-0.004
aman-0.004
 isn-0.004
heit-0.004
ement-0.004
Token her
Token ID607
Feature activation-2.47e-01

Pos logit contributions
 blown+0.054
 bitten+0.051
 Blood+0.049
 blood+0.048
 spilled+0.044
Neg logit contributions
 isn-0.063
 destination-0.063
 exactly-0.061
aman-0.060
heit-0.058
Token feel
Token ID1254
Feature activation-5.03e-01

Pos logit contributions
 blown+0.004
 Blood+0.004
 blood+0.004
 bitten+0.004
 spilled+0.004
Neg logit contributions
 destination-0.008
 isn-0.007
aman-0.007
heit-0.007
ement-0.007
Token cool
Token ID3608
Feature activation+1.18e-01

Pos logit contributions
 blown+0.011
 Blood+0.011
 blood+0.011
 bitten+0.011
 spilled+0.010
Neg logit contributions
 destination-0.013
 isn-0.013
aman-0.013
heit-0.013
ement-0.012
Token.
Token ID13
Feature activation-1.87e-02

Pos logit contributions
 destination+0.003
aman+0.003
heit+0.003
 isn+0.003
ement+0.003
Neg logit contributions
 blown-0.003
 blood-0.003
 Blood-0.003
 bitten-0.003
 spilled-0.002
Token But
Token ID887
Feature activation+1.10e+00

Pos logit contributions
 blown+0.000
 blood+0.000
 bitten+0.000
 Blood+0.000
 spilled+0.000
Neg logit contributions
 destination-0.000
 isn-0.000
aman-0.000
heit-0.000
ement-0.000
Token then
Token ID788
Feature activation-9.38e-01

Pos logit contributions
 destination+0.028
aman+0.027
heit+0.027
 isn+0.027
ement+0.025
Neg logit contributions
 blown-0.026
 blood-0.025
 Blood-0.025
 bitten-0.025
 spilled-0.022
Token the
Token ID262
Feature activation-6.28e-01

Pos logit contributions
 blood+0.019
 Blood+0.019
 blown+0.018
 bitten+0.018
 spilled+0.016
Neg logit contributions
 destination-0.027
aman-0.027
heit-0.026
 isn-0.025
ement-0.025
Token fan
Token ID4336
Feature activation-2.08e-01

Pos logit contributions
 Blood+0.015
 bitten+0.015
 blown+0.015
 blood+0.014
ked+0.014
Neg logit contributions
 destination-0.014
 isn-0.014
ement-0.014
aman-0.014
heit-0.013
Token started
Token ID2067
Feature activation-2.92e+00

Pos logit contributions
 Blood+0.004
 blood+0.004
 blown+0.004
 bitten+0.003
 spilled+0.003
Neg logit contributions
 destination-0.006
 isn-0.006
aman-0.006
heit-0.006
ement-0.006
Token to
Token ID284
Feature activation+1.09e+00

Pos logit contributions
 blown+0.052
 Blood+0.052
 blood+0.051
 bitten+0.050
 spilled+0.042
Neg logit contributions
 destination-0.088
aman-0.084
 isn-0.084
heit-0.081
ement-0.079
Token "
Token ID366
Feature activation+7.82e-01

Pos logit contributions
 destination+0.012
heit+0.012
aman+0.012
hew+0.011
ement+0.011
Neg logit contributions
 blood-0.006
 blown-0.006
 bitten-0.005
 Blood-0.005
 spilled-0.005
Tokenyes
Token ID8505
Feature activation+1.89e-01

Pos logit contributions
 destination+0.021
 isn+0.020
aman+0.020
heit+0.019
ement+0.019
Neg logit contributions
 blood-0.017
 blown-0.017
 Blood-0.016
 bitten-0.016
 spilled-0.015
Token."
Token ID526
Feature activation-2.63e-01

Pos logit contributions
 destination+0.004
aman+0.004
heit+0.004
 amaz+0.004
 destinations+0.004
Neg logit contributions
 Blood-0.005
 bitten-0.004
 blown-0.004
 blood-0.004
 spilled-0.004
Token
Token ID198
Feature activation-2.81e-01

Pos logit contributions
 blown+0.006
 blood+0.006
 Blood+0.006
 bitten+0.006
 spilled+0.005
Neg logit contributions
 destination-0.007
aman-0.007
 isn-0.007
heit-0.007
ement-0.006
Token
Token ID198
Feature activation-5.96e-01

Pos logit contributions
 blown+0.006
 blood+0.006
 Blood+0.006
 bitten+0.006
 spilled+0.005
Neg logit contributions
 destination-0.008
aman-0.007
heit-0.007
 isn-0.007
ement-0.007
TokenAmy
Token ID40797
Feature activation+1.06e+00

Pos logit contributions
 blown+0.015
 Blood+0.015
 blood+0.015
 bitten+0.014
 spilled+0.013
Neg logit contributions
 destination-0.014
aman-0.014
 isn-0.013
heit-0.013
ement-0.013
Token and
Token ID290
Feature activation-1.11e+00

Pos logit contributions
 destination+0.032
aman+0.032
heit+0.031
 isn+0.031
ement+0.030
Neg logit contributions
 blown-0.020
 blood-0.019
 bitten-0.019
 Blood-0.019
 spilled-0.017
Token the
Token ID262
Feature activation-2.59e+00

Pos logit contributions
 blown+0.028
 blood+0.027
 Blood+0.026
 bitten+0.026
elt+0.024
Neg logit contributions
 isn-0.024
aman-0.024
 destination-0.024
heit-0.024
ph-0.021
Token cat
Token ID3797
Feature activation-1.08e+00

Pos logit contributions
 blown+0.050
iers+0.044
 bitten+0.043
 Blood+0.041
agged+0.041
Neg logit contributions
 isn-0.070
aman-0.063
 destination-0.063
So-0.062
 promise-0.061
Token played
Token ID2826
Feature activation-4.63e-01

Pos logit contributions
 blown+0.017
 blood+0.017
 Blood+0.017
 bitten+0.016
 spilled+0.013
Neg logit contributions
 destination-0.035
 isn-0.034
aman-0.034
heit-0.034
ement-0.033
Token all
Token ID477
Feature activation-1.29e+00

Pos logit contributions
 blown+0.013
 blood+0.013
 Blood+0.013
 bitten+0.013
 spilled+0.012
Neg logit contributions
 destination-0.009
 isn-0.009
heit-0.009
aman-0.009
ement-0.008
Token you
Token ID345
Feature activation-1.02e+00

Pos logit contributions
 Blood+0.008
 blood+0.008
 blown+0.007
 bitten+0.007
 spilled+0.007
Neg logit contributions
 destination-0.005
aman-0.005
heit-0.005
 isn-0.004
ement-0.004
Token,
Token ID11
Feature activation-1.02e+00

Pos logit contributions
 Blood+0.021
 blood+0.020
 bitten+0.020
 mice+0.019
 blown+0.019
Neg logit contributions
aman-0.028
heit-0.028
 destination-0.026
ement-0.025
 destinations-0.025
Token Tom
Token ID4186
Feature activation+1.40e+00

Pos logit contributions
 blood+0.016
 Blood+0.014
 blown+0.013
 bitten+0.012
 cat+0.011
Neg logit contributions
 destination-0.036
heit-0.035
aman-0.035
ement-0.033
rd-0.033
Token!"
Token ID2474
Feature activation-2.96e-01

Pos logit contributions
 destination+0.034
aman+0.033
heit+0.032
ement+0.031
 destinations+0.029
Neg logit contributions
 bitten-0.034
 blood-0.034
 blown-0.033
 Blood-0.033
 spilled-0.031
Token
Token ID198
Feature activation+1.69e-01

Pos logit contributions
 blood+0.006
 blown+0.006
 Blood+0.006
 bitten+0.005
 spilled+0.005
Neg logit contributions
 destination-0.009
aman-0.008
heit-0.008
 isn-0.008
ement-0.008
Token
Token ID198
Feature activation-1.14e-01

Pos logit contributions
 destination+0.005
heit+0.005
aman+0.005
 isn+0.005
ement+0.005
Neg logit contributions
 Blood-0.003
 blood-0.003
 blown-0.003
 bitten-0.003
 spilled-0.002
TokenFrom
Token ID4863
Feature activation+2.48e+00

Pos logit contributions
 Blood+0.002
 blood+0.002
 blown+0.002
Tweet+0.002
 bitten+0.002
Neg logit contributions
 destination-0.003
ement-0.003
aman-0.003
heit-0.003
 isn-0.003
Token that
Token ID326
Feature activation+1.51e+00

Pos logit contributions
 destination+0.060
aman+0.058
 isn+0.057
heit+0.057
ement+0.054
Neg logit contributions
 blown-0.061
 blood-0.060
 Blood-0.060
 bitten-0.058
 spilled-0.053
Token day
Token ID1110
Feature activation-2.15e+00

Pos logit contributions
 destination+0.045
heit+0.044
aman+0.044
ement+0.043
 isn+0.042
Neg logit contributions
 Blood-0.029
 blown-0.029
 blood-0.028
 bitten-0.027
 spilled-0.025
Token,
Token ID11
Feature activation-7.41e-01

Pos logit contributions
 blown+0.043
 blood+0.043
 bitten+0.040
 Blood+0.040
 spilled+0.035
Neg logit contributions
 destination-0.060
 isn-0.058
heit-0.058
aman-0.056
ement-0.055
Token Tom
Token ID4186
Feature activation+1.47e+00

Pos logit contributions
 blown+0.013
 Blood+0.013
 blood+0.013
 bitten+0.013
 spilled+0.011
Neg logit contributions
 destination-0.023
aman-0.022
heit-0.022
 isn-0.022
ement-0.021
Token "
Token ID366
Feature activation+8.60e-01

Pos logit contributions
 destination+0.030
aman+0.029
heit+0.029
 isn+0.028
hew+0.028
Neg logit contributions
 Blood-0.018
 blood-0.017
 blown-0.017
 bitten-0.016
 spilled-0.014
TokenA
Token ID32
Feature activation+6.46e-01

Pos logit contributions
 destination+0.022
aman+0.021
heit+0.021
 isn+0.021
ement+0.020
Neg logit contributions
 blown-0.020
 blood-0.019
 Blood-0.019
 bitten-0.019
 spilled-0.017
Token and
Token ID290
Feature activation-8.03e-01

Pos logit contributions
 destination+0.020
aman+0.020
heit+0.020
ement+0.019
hew+0.019
Neg logit contributions
 Blood-0.011
 blown-0.011
 blood-0.010
 bitten-0.010
 spilled-0.009
Token a
Token ID257
Feature activation+3.85e-01

Pos logit contributions
 blown+0.018
 blood+0.018
 Blood+0.018
 bitten+0.018
 spilled+0.016
Neg logit contributions
 destination-0.021
aman-0.020
heit-0.020
 isn-0.020
ement-0.019
Token match
Token ID2872
Feature activation+2.74e-01

Pos logit contributions
aman+0.011
heit+0.011
 destination+0.011
hew+0.011
ement+0.010
Neg logit contributions
 blood-0.007
 blown-0.007
 Blood-0.007
 bitten-0.007
 spilled-0.007
Token!"
Token ID2474
Feature activation-6.74e-01

Pos logit contributions
aman+0.006
heit+0.006
 destination+0.006
hew+0.006
ement+0.006
Neg logit contributions
 blown-0.007
 blood-0.007
 bitten-0.007
 Blood-0.006
 spilled-0.006
Token
Token ID198
Feature activation-9.11e-02

Pos logit contributions
 blown+0.018
 bitten+0.016
 blood+0.015
 Blood+0.015
 spilled+0.014
Neg logit contributions
 isn-0.015
 destination-0.015
aman-0.015
ement-0.014
 exactly-0.014
Token
Token ID198
Feature activation-1.86e-01

Pos logit contributions
 blown+0.002
 blood+0.002
 bitten+0.002
 Blood+0.002
 spilled+0.002
Neg logit contributions
 destination-0.002
 isn-0.002
aman-0.002
heit-0.002
ement-0.002
TokenMom
Token ID29252
Feature activation+1.23e+00

Pos logit contributions
 blown+0.004
 blood+0.004
 Blood+0.004
 bitten+0.004
 spilled+0.003
Neg logit contributions
 destination-0.005
aman-0.005
 isn-0.005
heit-0.005
ement-0.005
Token smiles
Token ID21845
Feature activation-1.79e+00

Pos logit contributions
aman+0.031
 destination+0.031
heit+0.031
 isn+0.029
mmm+0.028
Neg logit contributions
 blood-0.029
 blown-0.027
 Blood-0.027
 bitten-0.026
 spilled-0.025
Token and
Token ID290
Feature activation+1.69e-01

Pos logit contributions
 blown+0.044
 Blood+0.043
 blood+0.042
 bitten+0.042
 spilled+0.038
Neg logit contributions
 destination-0.043
 isn-0.041
aman-0.040
ement-0.039
heit-0.039
Token going
Token ID1016
Feature activation+1.75e+00

Pos logit contributions
 blown+0.007
 blood+0.007
 Blood+0.007
 bitten+0.007
 spilled+0.006
Neg logit contributions
 destination-0.011
aman-0.010
heit-0.010
 isn-0.010
ement-0.010
Token missing
Token ID4814
Feature activation+1.49e-01

Pos logit contributions
 destination+0.054
aman+0.052
 isn+0.052
heit+0.052
ement+0.050
Neg logit contributions
 blown-0.031
 blood-0.031
 Blood-0.030
 bitten-0.029
 spilled-0.025
Token!
Token ID0
Feature activation-1.83e-01

Pos logit contributions
heit+0.005
aman+0.005
 destination+0.004
ement+0.004
hew+0.004
Neg logit contributions
 blown-0.003
 blood-0.003
 bitten-0.003
 spilled-0.002
 Blood-0.002
Token
Token ID198
Feature activation-3.71e-01

Pos logit contributions
 Blood+0.003
 blown+0.003
 blood+0.003
 bitten+0.003
 spilled+0.002
Neg logit contributions
 destination-0.006
heit-0.006
aman-0.006
 isn-0.006
ement-0.006
Token
Token ID198
Feature activation-6.61e-01

Pos logit contributions
 Blood+0.006
 blood+0.006
 blown+0.005
 bitten+0.005
 spilled+0.004
Neg logit contributions
 destination-0.013
heit-0.012
aman-0.012
 isn-0.012
ement-0.012
TokenThe
Token ID464
Feature activation-1.22e+00

Pos logit contributions
 Blood+0.014
 blown+0.014
 blood+0.013
 bitten+0.013
 spilled+0.012
Neg logit contributions
 destination-0.019
 isn-0.018
ement-0.018
aman-0.018
heit-0.018
Token mother
Token ID2802
Feature activation-1.12e+00

Pos logit contributions
 blown+0.024
 Blood+0.024
 blood+0.024
 bitten+0.023
elt+0.019
Neg logit contributions
 destination-0.035
 isn-0.033
aman-0.033
heit-0.032
ement-0.031
Token said
Token ID531
Feature activation+4.95e-01

Pos logit contributions
 blown+0.023
 blood+0.023
 Blood+0.023
 bitten+0.022
 spilled+0.020
Neg logit contributions
 destination-0.031
aman-0.030
 isn-0.030
heit-0.030
ement-0.028
Token,
Token ID11
Feature activation+4.11e-01

Pos logit contributions
 destination+0.013
aman+0.012
heit+0.012
 isn+0.012
hew+0.011
Neg logit contributions
 Blood-0.012
 blood-0.012
 blown-0.012
 bitten-0.011
 spilled-0.011
Token "
Token ID366
Feature activation+6.45e-01

Pos logit contributions
 destination+0.013
aman+0.013
heit+0.013
 isn+0.012
ement+0.012
Neg logit contributions
 Blood-0.007
 blood-0.007
 blown-0.007
 bitten-0.006
 spilled-0.006
TokenWhat
Token ID2061
Feature activation-1.18e+00

Pos logit contributions
 destination+0.020
heit+0.019
 isn+0.019
ement+0.019
aman+0.018
Neg logit contributions
 blown-0.012
 blood-0.012
 Blood-0.012
 bitten-0.011
 spilled-0.010
Token too
Token ID1165
Feature activation-5.39e-01

Pos logit contributions
 blood+0.000
 blown+0.000
 Blood+0.000
 bitten+0.000
 spilled+0.000
Neg logit contributions
heit-0.000
 destination-0.000
aman-0.000
 isn-0.000
hew-0.000
Token.
Token ID13
Feature activation-5.90e-01

Pos logit contributions
 blown+0.010
 blood+0.010
 Blood+0.010
 bitten+0.009
 spilled+0.008
Neg logit contributions
heit-0.017
aman-0.016
 destination-0.016
 isn-0.015
hew-0.015
Token He
Token ID679
Feature activation+2.04e-01

Pos logit contributions
 blown+0.007
 blood+0.007
 Blood+0.007
 bitten+0.007
 spilled+0.006
Neg logit contributions
 destination-0.021
aman-0.021
heit-0.021
 isn-0.020
ement-0.020
Token was
Token ID373
Feature activation+5.59e-01

Pos logit contributions
 destination+0.006
aman+0.006
heit+0.006
ement+0.006
 isn+0.006
Neg logit contributions
 blown-0.004
 blood-0.003
 bitten-0.003
 Blood-0.003
 spilled-0.003
Token restless
Token ID42537
Feature activation+3.40e-01

Pos logit contributions
 destination+0.012
 exactly+0.011
 isn+0.011
aman+0.011
heit+0.010
Neg logit contributions
 blood-0.015
 Blood-0.015
 blown-0.014
 bitten-0.014
 spilled-0.013
Token and
Token ID290
Feature activation+6.86e-01

Pos logit contributions
heit+0.010
aman+0.010
 destination+0.010
hew+0.009
mmm+0.009
Neg logit contributions
 blood-0.007
 blown-0.007
 bitten-0.006
 Blood-0.006
 spilled-0.006
Token the
Token ID262
Feature activation-1.65e+00

Pos logit contributions
 destination+0.019
 isn+0.018
aman+0.018
heit+0.018
ement+0.017
Neg logit contributions
 blown-0.014
 blood-0.014
 Blood-0.014
 bitten-0.014
 spilled-0.012
Token bike
Token ID7161
Feature activation-1.08e+00

Pos logit contributions
 blown+0.035
 Blood+0.034
 bitten+0.034
 blood+0.033
 spilled+0.029
Neg logit contributions
 destination-0.046
aman-0.045
 isn-0.044
heit-0.043
ement-0.042
Token had
Token ID550
Feature activation-1.36e+00

Pos logit contributions
 blown+0.024
 blood+0.023
 Blood+0.023
 bitten+0.022
 spilled+0.020
Neg logit contributions
 destination-0.029
aman-0.029
heit-0.029
 isn-0.028
ement-0.027
Token made
Token ID925
Feature activation-2.23e+00

Pos logit contributions
 Blood+0.027
 blown+0.026
 blood+0.026
 bitten+0.025
 spilled+0.022
Neg logit contributions
 destination-0.039
 isn-0.038
aman-0.037
heit-0.036
 exactly-0.035
Token him
Token ID683
Feature activation-4.59e-01

Pos logit contributions
 blood+0.039
 blown+0.039
 Blood+0.038
 bitten+0.037
 spilled+0.032
Neg logit contributions
 destination-0.069
heit-0.068
aman-0.068
 isn-0.066
ement-0.064
Token much
Token ID881
Feature activation-1.43e+00

Pos logit contributions
 destination+0.020
aman+0.019
heit+0.018
 isn+0.016
bek+0.016
Neg logit contributions
 blood-0.013
 Blood-0.013
 blown-0.012
 bitten-0.012
 spilled-0.012
Token.
Token ID13
Feature activation+8.10e-01

Pos logit contributions
 blood+0.024
 blown+0.021
 bitten+0.020
 Blood+0.019
 spilled+0.019
Neg logit contributions
heit-0.049
 destination-0.047
aman-0.046
hew-0.046
bek-0.043
Token
Token ID220
Feature activation-1.35e+00

Pos logit contributions
 destination+0.029
heit+0.029
aman+0.028
ement+0.027
 exactly+0.026
Neg logit contributions
 Blood-0.012
 blood-0.010
 blown-0.010
 bitten-0.009
elt-0.008
Token
Token ID198
Feature activation+5.34e-01

Pos logit contributions
 blown+0.028
 blood+0.028
 Blood+0.028
 bitten+0.027
 spilled+0.024
Neg logit contributions
 destination-0.037
aman-0.036
heit-0.036
 isn-0.035
ement-0.034
Token
Token ID198
Feature activation+2.40e-01

Pos logit contributions
 destination+0.016
aman+0.015
heit+0.015
 isn+0.015
ement+0.014
Neg logit contributions
 Blood-0.011
 blown-0.011
 blood-0.010
 bitten-0.010
 spilled-0.009
TokenSam
Token ID16305
Feature activation+8.14e-01

Pos logit contributions
 destination+0.007
 isn+0.007
ement+0.006
heit+0.006
aman+0.006
Neg logit contributions
 Blood-0.005
 blown-0.005
 blood-0.005
 bitten-0.005
Tweet-0.005
Token and
Token ID290
Feature activation-1.88e+00

Pos logit contributions
 destination+0.025
heit+0.024
ement+0.023
aman+0.023
 isn+0.023
Neg logit contributions
 blown-0.015
 blood-0.014
 bitten-0.014
 spilled-0.014
 Blood-0.014
Token his
Token ID465
Feature activation-1.73e+00

Pos logit contributions
 blown+0.048
 Blood+0.044
 blood+0.043
 bitten+0.043
plets+0.041
Neg logit contributions
 isn-0.041
 destination-0.039
heit-0.038
aman-0.038
 why-0.037
Token mom
Token ID1995
Feature activation-8.19e-01

Pos logit contributions
 blown+0.040
 Blood+0.040
 blood+0.039
 bitten+0.039
 spilled+0.034
Neg logit contributions
 destination-0.044
 isn-0.042
aman-0.042
heit-0.041
ement-0.040
Token had
Token ID550
Feature activation-1.80e-02

Pos logit contributions
 blown+0.013
 blood+0.012
 bitten+0.012
 spilled+0.011
 Blood+0.011
Neg logit contributions
 destination-0.027
heit-0.027
 isn-0.026
aman-0.026
ement-0.026
Token discovered
Token ID5071
Feature activation+6.58e-01

Pos logit contributions
 blown+0.000
 blood+0.000
 bitten+0.000
 Blood+0.000
 spilled+0.000
Neg logit contributions
 destination-0.001
heit-0.001
aman-0.001
 isn-0.001
ement-0.001
Token.
Token ID13
Feature activation+1.23e+00

Pos logit contributions
 destination+0.062
aman+0.062
heit+0.060
ement+0.058
hew+0.057
Neg logit contributions
 blown-0.046
 blood-0.045
 bitten-0.044
 Blood-0.043
 spilled-0.042
Token
Token ID220
Feature activation-1.08e+00

Pos logit contributions
 destination+0.041
heit+0.040
aman+0.039
ement+0.038
 isn+0.036
Neg logit contributions
 Blood-0.021
 blood-0.018
 blown-0.017
 bitten-0.017
elt-0.015
Token
Token ID198
Feature activation+4.29e-01

Pos logit contributions
 Blood+0.022
 blood+0.021
 blown+0.021
 bitten+0.020
 spilled+0.018
Neg logit contributions
 destination-0.031
heit-0.030
aman-0.030
 isn-0.029
ement-0.028
Token
Token ID198
Feature activation+6.36e-02

Pos logit contributions
 destination+0.014
heit+0.013
 isn+0.013
aman+0.013
ement+0.012
Neg logit contributions
 Blood-0.008
 blood-0.007
 blown-0.007
 bitten-0.007
Tweet-0.006
TokenThe
Token ID464
Feature activation-8.21e-01

Pos logit contributions
 destination+0.002
 isn+0.002
heit+0.002
ement+0.002
aman+0.002
Neg logit contributions
 Blood-0.001
Tweet-0.001
 blown-0.001
 blood-0.001
 bitten-0.001
Token end
Token ID886
Feature activation-3.23e+00

Pos logit contributions
 blood+0.016
 blown+0.015
 Blood+0.014
 bitten+0.014
 spilled+0.013
Neg logit contributions
 destination-0.024
aman-0.024
heit-0.024
 isn-0.024
ement-0.023
Token.
Token ID13
Feature activation+4.16e-02

Pos logit contributions
 blood+0.035
 Blood+0.034
 bitten+0.027
 opener+0.027
 cat+0.026
Neg logit contributions
heit-0.128
aman-0.126
 destination-0.124
hew-0.116
 destinations-0.112
Token<|endoftext|>
Token ID50256
Feature activation+1.03e-03

Pos logit contributions
heit+0.001
 destination+0.001
aman+0.001
ement+0.001
 isn+0.001
Neg logit contributions
 Blood-0.001
 blood-0.001
 blown-0.001
 bitten-0.001
elt-0.001
TokenJohn
Token ID7554
Feature activation+2.01e+00

Pos logit contributions
 destination+0.000
aman+0.000
heit+0.000
 isn+0.000
ement+0.000
Neg logit contributions
 blown-0.000
 blood-0.000
 Blood-0.000
 bitten-0.000
 spilled-0.000
Token was
Token ID373
Feature activation+9.92e-02

Pos logit contributions
 destination+0.058
heit+0.056
aman+0.056
 isn+0.055
ement+0.054
Neg logit contributions
 blown-0.039
 blood-0.039
 Blood-0.038
 bitten-0.038
 spilled-0.034
Token a
Token ID257
Feature activation+3.41e-01

Pos logit contributions
 destination+0.003
aman+0.003
 isn+0.002
heit+0.002
 exactly+0.002
Neg logit contributions
 blood-0.002
 blown-0.002
 Blood-0.002
 bitten-0.002
 spilled-0.002
Token.
Token ID13
Feature activation-6.46e-01

Pos logit contributions
 destination+0.001
 isn+0.001
aman+0.001
ement+0.001
heit+0.001
Neg logit contributions
 Blood-0.001
 blown-0.001
 blood-0.001
 bitten-0.001
 spilled-0.001
Token They
Token ID1119
Feature activation-1.06e+00

Pos logit contributions
 blown+0.018
 blood+0.017
 bitten+0.017
 Blood+0.017
 spilled+0.015
Neg logit contributions
 destination-0.014
 isn-0.014
aman-0.014
heit-0.013
ement-0.013
Token had
Token ID550
Feature activation-2.16e+00

Pos logit contributions
 blood+0.024
 blown+0.024
 Blood+0.024
 bitten+0.023
elt+0.020
Neg logit contributions
 destination-0.027
 isn-0.026
heit-0.025
aman-0.025
hew-0.024
Token a
Token ID257
Feature activation+1.75e-01

Pos logit contributions
 blown+0.044
 blood+0.044
 Blood+0.044
 bitten+0.042
elt+0.037
Neg logit contributions
 destination-0.059
 isn-0.057
aman-0.055
heit-0.054
 exactly-0.053
Token box
Token ID3091
Feature activation+9.50e-01

Pos logit contributions
aman+0.006
heit+0.006
 destination+0.006
 isn+0.006
ement+0.006
Neg logit contributions
 blood-0.003
 Blood-0.003
 blown-0.003
 bitten-0.003
 spilled-0.002
Token of
Token ID286
Feature activation-3.13e+00

Pos logit contributions
 destination+0.026
 isn+0.024
aman+0.024
 exactly+0.024
 forever+0.023
Neg logit contributions
 blood-0.020
 Blood-0.020
 blown-0.020
 bitten-0.020
 spilled-0.017
Token shapes
Token ID15268
Feature activation+9.36e-02

Pos logit contributions
 blown+0.061
 Blood+0.059
 blood+0.059
 bitten+0.058
 spilled+0.050
Neg logit contributions
 destination-0.091
 isn-0.088
aman-0.088
heit-0.087
ement-0.083
Token that
Token ID326
Feature activation-3.55e-01

Pos logit contributions
 destination+0.002
 isn+0.002
ement+0.002
aman+0.002
 exactly+0.002
Neg logit contributions
 Blood-0.002
 blown-0.002
 blood-0.002
 bitten-0.002
 spilled-0.002
Token had
Token ID550
Feature activation-2.94e+00

Pos logit contributions
 blown+0.007
 blood+0.007
 Blood+0.007
 bitten+0.007
 spilled+0.006
Neg logit contributions
 destination-0.010
 isn-0.010
aman-0.010
heit-0.010
ement-0.009
Token circles
Token ID13332
Feature activation+3.29e-01

Pos logit contributions
 Blood+0.062
 blood+0.060
 blown+0.058
 bitten+0.057
elt+0.054
Neg logit contributions
 destination-0.079
 isn-0.077
 exactly-0.072
 forever-0.069
aman-0.068
Token,
Token ID11
Feature activation-5.09e-01

Pos logit contributions
 destination+0.008
 isn+0.008
aman+0.008
heit+0.007
ement+0.007
Neg logit contributions
 blown-0.008
 blood-0.008
 Blood-0.008
 bitten-0.008
 spilled-0.007
Token't
Token ID470
Feature activation-1.95e+00

Pos logit contributions
 destination+0.019
 isn+0.019
aman+0.018
heit+0.018
!'+0.017
Neg logit contributions
 blood-0.014
 Blood-0.014
 blown-0.014
 bitten-0.014
elt-0.012
Token get
Token ID651
Feature activation-7.98e-01

Pos logit contributions
 Blood+0.040
 blood+0.039
 blown+0.038
 bitten+0.037
elt+0.034
Neg logit contributions
 destination-0.055
 isn-0.053
aman-0.052
heit-0.051
 forever-0.048
Token better
Token ID1365
Feature activation-8.36e-01

Pos logit contributions
 Blood+0.013
 blood+0.012
 blown+0.012
 bitten+0.011
 spilled+0.010
Neg logit contributions
 destination-0.025
 isn-0.025
aman-0.024
heit-0.024
 exactly-0.023
Token without
Token ID1231
Feature activation-9.06e-01

Pos logit contributions
 blown+0.019
 blood+0.019
 bitten+0.018
 Blood+0.017
 spilled+0.016
Neg logit contributions
heit-0.022
 destination-0.022
aman-0.022
 isn-0.021
ement-0.020
Token the
Token ID262
Feature activation+3.20e-01

Pos logit contributions
 blown+0.018
 blood+0.018
 bitten+0.017
 Blood+0.017
 spilled+0.015
Neg logit contributions
 destination-0.027
 isn-0.026
aman-0.026
heit-0.025
ement-0.025
Token band
Token ID4097
Feature activation-3.54e+00

Pos logit contributions
 destination+0.010
aman+0.010
 isn+0.010
heit+0.010
ement+0.010
Neg logit contributions
 Blood-0.005
 blown-0.005
 blood-0.005
 bitten-0.005
 spilled-0.004
Tokenage
Token ID496
Feature activation-4.22e+00

Pos logit contributions
 Blood+0.080
 blood+0.079
 blown+0.077
 bitten+0.072
 spilled+0.067
Neg logit contributions
 destination-0.089
 isn-0.088
aman-0.086
!'-0.082
hew-0.081
Token and
Token ID290
Feature activation+2.19e-01

Pos logit contributions
 blown+0.095
 blood+0.094
 Blood+0.092
 bitten+0.091
 spilled+0.082
Neg logit contributions
 destination-0.109
aman-0.107
heit-0.106
 isn-0.105
ement-0.100
Token said
Token ID531
Feature activation+4.03e-01

Pos logit contributions
 destination+0.006
aman+0.006
heit+0.006
 isn+0.006
ement+0.006
Neg logit contributions
 blown-0.005
 blood-0.005
 Blood-0.004
 bitten-0.004
 spilled-0.004
Token she
Token ID673
Feature activation+1.84e+00

Pos logit contributions
 destination+0.012
aman+0.011
heit+0.011
hew+0.011
 isn+0.010
Neg logit contributions
 Blood-0.008
 blood-0.008
 blown-0.008
 bitten-0.008
 spilled-0.007
Token would
Token ID561
Feature activation+1.26e+00

Pos logit contributions
 destination+0.045
aman+0.045
heit+0.044
ement+0.041
 isn+0.040
Neg logit contributions
 blown-0.045
 blood-0.044
 bitten-0.044
 Blood-0.043
 spilled-0.042
TokenAfter
Token ID3260
Feature activation-6.41e-01

Pos logit contributions
 Blood+0.005
 blown+0.004
 bitten+0.004
 blood+0.004
Tweet+0.004
Neg logit contributions
 destination-0.008
 isn-0.007
heit-0.007
ement-0.007
aman-0.007
Token a
Token ID257
Feature activation+1.07e+00

Pos logit contributions
 blown+0.011
 blood+0.011
 Blood+0.011
 bitten+0.011
 spilled+0.009
Neg logit contributions
 destination-0.019
aman-0.019
 isn-0.018
heit-0.018
ement-0.018
Token while
Token ID981
Feature activation-1.03e+00

Pos logit contributions
 destination+0.030
aman+0.029
 isn+0.029
heit+0.029
ement+0.028
Neg logit contributions
 blown-0.021
 Blood-0.021
 blood-0.021
 bitten-0.020
 spilled-0.018
Token,
Token ID11
Feature activation-5.42e-01

Pos logit contributions
 blown+0.033
 blood+0.033
 Blood+0.032
 bitten+0.032
 spilled+0.030
Neg logit contributions
 destination-0.017
aman-0.016
 isn-0.015
heit-0.015
ement-0.014
Token it
Token ID340
Feature activation-7.48e-01

Pos logit contributions
 blown+0.010
 blood+0.010
 Blood+0.010
 bitten+0.009
 spilled+0.008
Neg logit contributions
 destination-0.017
aman-0.016
 isn-0.016
heit-0.016
ement-0.015
Token started
Token ID2067
Feature activation-2.86e+00

Pos logit contributions
 blood+0.016
 blown+0.016
 Blood+0.016
 bitten+0.015
 spilled+0.013
Neg logit contributions
 destination-0.020
aman-0.020
 isn-0.019
heit-0.019
ement-0.018
Token to
Token ID284
Feature activation+4.50e-01

Pos logit contributions
 Blood+0.061
 blood+0.058
 blown+0.057
 bitten+0.055
orns+0.051
Neg logit contributions
 destination-0.075
aman-0.071
 exactly-0.067
 isn-0.067
 int-0.064
Token rain
Token ID6290
Feature activation+3.46e-01

Pos logit contributions
 destination+0.014
aman+0.014
heit+0.013
 isn+0.013
ement+0.012
Neg logit contributions
 Blood-0.008
 blown-0.007
 bitten-0.007
 blood-0.007
elt-0.007
Token and
Token ID290
Feature activation+1.73e-01

Pos logit contributions
 destination+0.007
aman+0.007
 isn+0.006
ement+0.006
 forever+0.006
Neg logit contributions
 Blood-0.010
 blood-0.009
 bitten-0.009
 blown-0.009
 robbers-0.008
Token the
Token ID262
Feature activation-1.12e+00

Pos logit contributions
 destination+0.005
 isn+0.005
aman+0.005
heit+0.005
 exactly+0.004
Neg logit contributions
 blown-0.003
 Blood-0.003
 blood-0.003
 bitten-0.003
 spilled-0.003
Token infant
Token ID11212
Feature activation-1.70e+00

Pos logit contributions
 Blood+0.021
 blown+0.019
 blood+0.019
 bitten+0.019
elt+0.016
Neg logit contributions
 destination-0.034
 isn-0.033
aman-0.033
heit-0.032
ement-0.031
Token at
Token ID379
Feature activation+2.08e+00

Pos logit contributions
 destination+0.005
aman+0.004
heit+0.004
 isn+0.004
ement+0.004
Neg logit contributions
 blown-0.005
 blood-0.005
 Blood-0.005
 bitten-0.005
 spilled-0.004
Token his
Token ID465
Feature activation+2.52e-01

Pos logit contributions
 destination+0.064
aman+0.062
heit+0.062
 isn+0.062
ement+0.059
Neg logit contributions
 blood-0.038
 blown-0.036
 Blood-0.035
 bitten-0.034
 spilled-0.030
Token mom
Token ID1995
Feature activation-1.92e-01

Pos logit contributions
aman+0.007
heit+0.007
 destination+0.007
 isn+0.007
hew+0.007
Neg logit contributions
 blood-0.005
 blown-0.005
 Blood-0.005
 bitten-0.005
 spilled-0.004
Token with
Token ID351
Feature activation+1.40e+00

Pos logit contributions
 blown+0.003
 blood+0.003
 bitten+0.003
 spilled+0.003
 Blood+0.003
Neg logit contributions
heit-0.006
 destination-0.006
 isn-0.005
aman-0.005
 virtue-0.005
Token a
Token ID257
Feature activation+1.96e+00

Pos logit contributions
 destination+0.043
aman+0.041
 isn+0.041
heit+0.041
ement+0.040
Neg logit contributions
 Blood-0.024
 blown-0.024
 bitten-0.022
 blood-0.022
 spilled-0.020
Token smile
Token ID8212
Feature activation-3.76e+00

Pos logit contributions
 destination+0.061
aman+0.060
heit+0.059
 isn+0.059
hew+0.059
Neg logit contributions
 blood-0.034
 blown-0.033
 Blood-0.031
 bitten-0.031
 spilled-0.028
Token and
Token ID290
Feature activation+6.45e-03

Pos logit contributions
 blown+0.079
 blood+0.078
 Blood+0.076
 bitten+0.075
 spilled+0.068
Neg logit contributions
 destination-0.104
heit-0.101
aman-0.100
 isn-0.099
hew-0.095
Token she
Token ID673
Feature activation+1.41e-01

Pos logit contributions
 destination+0.000
aman+0.000
 isn+0.000
heit+0.000
ement+0.000
Neg logit contributions
 blown-0.000
 blood-0.000
 Blood-0.000
 bitten-0.000
 spilled-0.000
Token smiled
Token ID13541
Feature activation-1.19e+00

Pos logit contributions
 destination+0.004
aman+0.004
heit+0.004
 isn+0.004
ement+0.004
Neg logit contributions
 blown-0.003
 blood-0.002
 bitten-0.002
 Blood-0.002
 spilled-0.002
Token back
Token ID736
Feature activation-5.59e-01

Pos logit contributions
 blown+0.025
 blood+0.024
 Blood+0.024
 bitten+0.023
elt+0.021
Neg logit contributions
heit-0.033
 destination-0.032
aman-0.032
 isn-0.032
hew-0.031
Token.
Token ID13
Feature activation+6.48e-01

Pos logit contributions
 blown+0.009
 Blood+0.009
 blood+0.009
 bitten+0.009
elt+0.008
Neg logit contributions
 destination-0.017
heit-0.017
aman-0.017
 isn-0.016
hew-0.016