H7.0 top features

Top feature 0 in H7.0: (feature 2697)

TOP ACTIVATIONS
MAX = 2.082

one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.014
major
Token major
Feature activation+0.656
Jude
Token Jude
Feature activation+0.019
an
Tokenan
Feature activation+2.082
rebel
Token rebel
Feature activation+1.003
factions
Token factions
Feature activation+0.332
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
First
Token First
Feature activation+0.000
the
Token the
Feature activation+0.000
four
Token four
Feature activation+0.131
(
Token (
Feature activation+0.506
perhaps
Tokenperhaps
Feature activation+1.297
more
Token more
Feature activation+0.033
)
Token)
Feature activation+1.867
sophisticated
Token sophisticated
Feature activation+1.025
counterfe
Token counterfe
Feature activation+1.080
iting
Tokeniting
Feature activation+1.784
operations
Token operations
Feature activation+1.429
operating
Token operating
Feature activation+0.000
h
Tokenh
Feature activation+0.000
ane
Tokenane
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
red
Token red
Feature activation+1.835
peaks
Token peaks
Feature activation+0.983
on
Token on
Feature activation+0.087
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.128
show
Token show
Feature activation+0.015
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.008
R
Token R
Feature activation+0.206
AG
TokenAG
Feature activation+0.856
G
TokenG
Feature activation+0.707
ED
TokenED
Feature activation+1.815
ED
Token ED
Feature activation+0.000
GE
TokenGE
Feature activation+0.813
tournaments
Token tournaments
Feature activation+0.436
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
perhaps
Tokenperhaps
Feature activation+1.297
more
Token more
Feature activation+0.033
)
Token)
Feature activation+1.867
sophisticated
Token sophisticated
Feature activation+1.025
counterfe
Token counterfe
Feature activation+1.080
iting
Tokeniting
Feature activation+1.784
operations
Token operations
Feature activation+1.429
operating
Token operating
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
Lima
Token Lima
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
Dig
Token Dig
Feature activation+0.180
il
Tokenil
Feature activation+0.202
ent
Tokenent
Feature activation+1.780
PM
Token PM
Feature activation+0.103
OD
TokenOD
Feature activation+0.296
ports
Token ports
Feature activation+0.157
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
yell
Token yell
Feature activation+0.760
ows
Tokenows
Feature activation+1.066
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
back
Token back
Feature activation+0.089
in
Token in
Feature activation+1.767
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
,
Token,
Feature activation+0.000
guard
Token guard
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
offensive
Token offensive
Feature activation+1.712
tackles
Token tackles
Feature activation+0.809
are
Token are
Feature activation+0.000
next
Token next
Feature activation+0.000
to
Token to
Feature activation+0.000
each
Token each
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.294
three
Token three
Feature activation+0.637
investigations
Token investigations
Feature activation+1.653
into
Token into
Feature activation+0.551
the
Token the
Feature activation+0.000
actions
Token actions
Feature activation+0.000
of
Token of
Feature activation+0.000
Salt
Token Salt
Feature activation+0.000
three
Token three
Feature activation+0.000
Gotham
Token Gotham
Feature activation+0.768
City
Token City
Feature activation+1.214
âĢ
TokenâĢ
Feature activation+0.274
Ļ
TokenĻ
Feature activation+0.520
s
Tokens
Feature activation+1.635
high
Token high
Feature activation+0.078
-
Token-
Feature activation+0.000
level
Tokenlevel
Feature activation+0.305
employees
Token employees
Feature activation+0.289
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
oldest
Token oldest
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
nine
Token nine
Feature activation+0.010
Seymour
Token Seymour
Feature activation+1.616
children
Token children
Feature activation+0.352
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000
born
Token born
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
two
Token two
Feature activation+0.367
directors
Token directors
Feature activation+1.611
leading
Token leading
Feature activation+0.000
the
Token the
Feature activation+0.000
G
Token G
Feature activation+0.000
iro
Tokeniro
Feature activation+0.000
team
Token team
Feature activation+0.000
photo
Token photo
Feature activation+0.000
of
Token of
Feature activation+0.000
himself
Token himself
Feature activation+0.000
and
Token and
Feature activation+0.000
two
Token two
Feature activation+0.000
obscured
Token obscured
Feature activation+1.609
inv
Token inv
Feature activation+0.655
id
Tokenid
Feature activation+0.158
ual
Tokenual
Feature activation+0.734
s
Tokens
Feature activation+0.677
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
two
Token two
Feature activation+0.000
forwarded
Token forwarded
Feature activation+1.597
by
Token by
Feature activation+0.661
the
Token the
Feature activation+0.000
Spokane
Token Spokane
Feature activation+0.000
Tribal
Token Tribal
Feature activation+0.000
Business
Token Business
Feature activation+0.000
and
Token and
Feature activation+0.000
11
Token 11
Feature activation+0.000
of
Token of
Feature activation+0.353
the
Token the
Feature activation+0.405
16
Token 16
Feature activation+0.631
contests
Token contests
Feature activation+1.597
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
doing
Token doing
Feature activation+0.000
so
Token so
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
four
Token four
Feature activation+0.000
suspended
Token suspended
Feature activation+1.593
firefighters
Token firefighters
Feature activation+0.468
said
Token said
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
told
Token told
Feature activation+0.000
make
Token make
Feature activation+0.000
illness
Token illness
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.048
"
Token "
Feature activation+1.578
prime
Tokenprime
Feature activation+1.534
themes
Token themes
Feature activation+0.569
"
Token"
Feature activation+0.000
alongside
Token alongside
Feature activation+0.000
"
Token "
Feature activation+0.000
tre
Token tre
Feature activation+0.000
asured
Tokenasured
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
many
Token many
Feature activation+0.000
timeless
Token timeless
Feature activation+1.575
classic
Token classic
Feature activation+0.681
feature
Token feature
Feature activation+0.372
films
Token films
Feature activation+1.018
it
Token it
Feature activation+0.000
has
Token has
Feature activation+0.000
-
Token-
Feature activation+0.000
reaching
Tokenreaching
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.131
two
Token two
Feature activation+0.323
court
Token court
Feature activation+1.566
cases
Token cases
Feature activation+0.986
affected
Token affected
Feature activation+0.000
jurisdictions
Token jurisdictions
Feature activation+0.000
in
Token in
Feature activation+0.000
nine
Token nine
Feature activation+0.000
was
Token was
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
lamb
Token lamb
Feature activation+1.208
ik
Tokenik
Feature activation+1.561
houses
Token houses
Feature activation+0.872
Cant
Token Cant
Feature activation+0.000
illon
Tokenillon
Feature activation+0.000
and
Token and
Feature activation+0.000
Til
Token Til
Feature activation+0.000

Top DFA by src position
MAX = 2.337

leader
Token leader
Feature activation-0.022
Top resid features:
of
Token of
Feature activation-0.009
Top resid features:
one
Token one
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.087
Top resid features:
major
Token major
Feature activation+2.337
Top resid features:
Jude
Token Jude
Feature activation+0.011
Top resid features:
an
Tokenan
Feature activation+0.001
Top resid features:
rebel
Token rebel
Feature activation+0.000
Top resid features:
factions
Token factions
Feature activation+0.000
Top resid features:
during
Token during
Feature activation+0.000
Top resid features:
leader
Token leader
Feature activation-0.031
Top resid features:
of
Token of
Feature activation-0.022
Top resid features:
one
Token one
Feature activation-0.030
Top resid features:
of
Token of
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.262
Top resid features:
four
Token four
Feature activation+1.983
Top resid features:
(
Token (
Feature activation+0.004
Top resid features:
perhaps
Tokenperhaps
Feature activation+0.003
Top resid features:
more
Token more
Feature activation-0.001
Top resid features:
)
Token)
Feature activation+0.006
Top resid features:
sophisticated
Token sophisticated
Feature activation+0.000
Top resid features:
omet
Tokenomet
Feature activation+0.001
Top resid features:
h
Tokenh
Feature activation+0.001
Top resid features:
ane
Tokenane
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
two
Token two
Feature activation+1.984
Top resid features:
red
Token red
Feature activation+0.094
Top resid features:
peaks
Token peaks
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
right
Token right
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.032
Top resid features:
winner
Token winner
Feature activation-0.003
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
one
Token one
Feature activation-0.004
Top resid features:
of
Token of
Feature activation+0.282
Top resid features:
the
Token the
Feature activation+1.802
Top resid features:
R
Token R
Feature activation+0.029
Top resid features:
AG
TokenAG
Feature activation+0.019
Top resid features:
G
TokenG
Feature activation+0.013
Top resid features:
ED
TokenED
Feature activation+0.020
Top resid features:
ED
Token ED
Feature activation+0.000
Top resid features:
four
Token four
Feature activation+0.406
Top resid features:
(
Token (
Feature activation-0.000
Top resid features:
perhaps
Tokenperhaps
Feature activation+0.001
Top resid features:
more
Token more
Feature activation-0.001
Top resid features:
)
Token)
Feature activation+0.111
Top resid features:
sophisticated
Token sophisticated
Feature activation+1.444
Top resid features:
counterfe
Token counterfe
Feature activation+0.016
Top resid features:
iting
Tokeniting
Feature activation+0.001
Top resid features:
operations
Token operations
Feature activation+0.000
Top resid features:
operating
Token operating
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
MI
TokenMI
Feature activation+0.001
Top resid features:
output
Token output
Feature activation+0.003
Top resid features:
port
Token port
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Two
TokenTwo
Feature activation+1.916
Top resid features:
Dig
Token Dig
Feature activation+0.038
Top resid features:
il
Tokenil
Feature activation-0.012
Top resid features:
ent
Tokenent
Feature activation+0.010
Top resid features:
PM
Token PM
Feature activation+0.000
Top resid features:
OD
TokenOD
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.029
Top resid features:
yell
Token yell
Feature activation+0.045
Top resid features:
ows
Tokenows
Feature activation+0.040
Top resid features:
back
Token back
Feature activation+0.019
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
back
Token back
Feature activation+1.952
Top resid features:
in
Token in
Feature activation-0.010
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
few
Token few
Feature activation+0.000
Top resid features:
minutes
Token minutes
Feature activation+0.000
Top resid features:
side
Tokenside
Feature activation+0.005
Top resid features:
guard
Token guard
Feature activation+0.022
Top resid features:
,
Token,
Feature activation-0.028
Top resid features:
while
Token while
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
two
Token two
Feature activation+1.956
Top resid features:
offensive
Token offensive
Feature activation+0.022
Top resid features:
tackles
Token tackles
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.015
Top resid features:
Two
TokenTwo
Feature activation+0.015
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.186
Top resid features:
three
Token three
Feature activation+1.716
Top resid features:
investigations
Token investigations
Feature activation+0.030
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
actions
Token actions
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Art
Token Art
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
com
Tokencom
Feature activation-0.004
Top resid features:
executives
Token executives
Feature activation-0.007
Top resid features:
fired
Token fired
Feature activation+0.033
Top resid features:
three
Token three
Feature activation+1.875
Top resid features:
Gotham
Token Gotham
Feature activation+0.026
Top resid features:
City
Token City
Feature activation+0.011
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation+0.039
Top resid features:
was
Token was
Feature activation+0.003
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
oldest
Token oldest
Feature activation-0.031
Top resid features:
of
Token of
Feature activation-0.028
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
nine
Token nine
Feature activation+1.937
Top resid features:
Seymour
Token Seymour
Feature activation-0.002
Top resid features:
children
Token children
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
He
Token He
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
idi
Tokenidi
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.016
Top resid features:
one
Token one
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.010
Top resid features:
our
Token our
Feature activation+0.179
Top resid features:
two
Token two
Feature activation+1.774
Top resid features:
directors
Token directors
Feature activation+0.028
Top resid features:
leading
Token leading
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
G
Token G
Feature activation+0.000
Top resid features:
iro
Tokeniro
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.008
Top resid features:
photo
Token photo
Feature activation-0.025
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
himself
Token himself
Feature activation-0.022
Top resid features:
and
Token and
Feature activation-0.018
Top resid features:
two
Token two
Feature activation+1.887
Top resid features:
obscured
Token obscured
Feature activation+0.053
Top resid features:
inv
Token inv
Feature activation+0.000
Top resid features:
id
Tokenid
Feature activation+0.000
Top resid features:
ual
Tokenual
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
English
Token English
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
was
Token was
Feature activation-0.010
Top resid features:
one
Token one
Feature activation-0.012
Top resid features:
of
Token of
Feature activation+0.020
Top resid features:
two
Token two
Feature activation+1.879
Top resid features:
forwarded
Token forwarded
Feature activation+0.019
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Spokane
Token Spokane
Feature activation+0.000
Top resid features:
Tribal
Token Tribal
Feature activation+0.000
Top resid features:
delegates
Token delegates
Feature activation-0.000
Top resid features:
and
Token and
Feature activation-0.020
Top resid features:
11
Token 11
Feature activation+0.026
Top resid features:
of
Token of
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.100
Top resid features:
16
Token 16
Feature activation+1.797
Top resid features:
contests
Token contests
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
In
Token In
Feature activation+0.000
Top resid features:
doing
Token doing
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
âĢ
TokenâĢ
Feature activation-0.011
Top resid features:
ľ
Tokenľ
Feature activation-0.003
Top resid features:
The
TokenThe
Feature activation-0.010
Top resid features:
four
Token four
Feature activation+1.898
Top resid features:
suspended
Token suspended
Feature activation+0.032
Top resid features:
firefighters
Token firefighters
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
make
Token make
Feature activation-0.005
Top resid features:
illness
Token illness
Feature activation-0.006
Top resid features:
one
Token one
Feature activation-0.004
Top resid features:
of
Token of
Feature activation+0.111
Top resid features:
its
Token its
Feature activation+1.803
Top resid features:
"
Token "
Feature activation+0.007
Top resid features:
prime
Tokenprime
Feature activation+0.000
Top resid features:
themes
Token themes
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
alongside
Token alongside
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
tre
Token tre
Feature activation-0.000
Top resid features:
asured
Tokenasured
Feature activation-0.002
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
many
Token many
Feature activation+1.875
Top resid features:
timeless
Token timeless
Feature activation+0.021
Top resid features:
classic
Token classic
Feature activation+0.000
Top resid features:
feature
Token feature
Feature activation+0.000
Top resid features:
films
Token films
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
far
Token far
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
reaching
Tokenreaching
Feature activation-0.009
Top resid features:
of
Token of
Feature activation+0.023
Top resid features:
the
Token the
Feature activation+0.104
Top resid features:
two
Token two
Feature activation+1.725
Top resid features:
court
Token court
Feature activation+0.029
Top resid features:
cases
Token cases
Feature activation+0.000
Top resid features:
affected
Token affected
Feature activation+0.000
Top resid features:
jurisdictions
Token jurisdictions
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
this
Token this
Feature activation-0.004
Top resid features:
year
Token year
Feature activation-0.002
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
two
Token two
Feature activation+1.811
Top resid features:
lamb
Token lamb
Feature activation+0.035
Top resid features:
ik
Tokenik
Feature activation+0.007
Top resid features:
houses
Token houses
Feature activation+0.000
Top resid features:
Cant
Token Cant
Feature activation+0.000
Top resid features:
illon
Tokenillon
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.60

Head 1: 0.02

Head 2: 0.04

Head 3: 0.06

Head 4: 0.05

Head 5: 0.05

Head 6: 0.03

Head 7: 0.02

Head 8: 0.05

Head 9: 0.04

Head 10: 0.02

Head 11: 0.02

Positive logits

pillars2.38

variants2.34

equivalents2.34

fronts2.28

constants2.28

versions2.28

varieties2.21

categories2.19

iterations2.16

izations2.16

extensions2.15

cylinders2.14

slots2.13

implementations2.13

clauses2.12

branches2.11

tiers2.10

panels2.10

finalists2.09

segments2.06

Negative logits

hyde-1.86

someone-1.70

Semitism-1.69

Shutterstock-1.69

rency-1.64

��-1.63

dignity-1.52

epad-1.49

ossession-1.49

flix-1.48

keleton-1.48

obia-1.48

understatement-1.47

culosis-1.47

escription-1.45

rower-1.45

hower-1.45

iosis-1.43

Flesh-1.42

enance-1.41

INTERVAL 1.873 - 2.082
CONTAINS 0.000%

one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.014
major
Token major
Feature activation+0.656
Jude
Token Jude
Feature activation+0.019
an
Tokenan
Feature activation+2.082
rebel
Token rebel
Feature activation+1.003
factions
Token factions
Feature activation+0.332
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
First
Token First
Feature activation+0.000

INTERVAL 1.665 - 1.873
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
Dig
Token Dig
Feature activation+0.180
il
Tokenil
Feature activation+0.202
ent
Tokenent
Feature activation+1.780
PM
Token PM
Feature activation+0.103
OD
TokenOD
Feature activation+0.296
ports
Token ports
Feature activation+0.157
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
four
Token four
Feature activation+0.131
(
Token (
Feature activation+0.506
perhaps
Tokenperhaps
Feature activation+1.297
more
Token more
Feature activation+0.033
)
Token)
Feature activation+1.867
sophisticated
Token sophisticated
Feature activation+1.025
counterfe
Token counterfe
Feature activation+1.080
iting
Tokeniting
Feature activation+1.784
operations
Token operations
Feature activation+1.429
operating
Token operating
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.008
R
Token R
Feature activation+0.206
AG
TokenAG
Feature activation+0.856
G
TokenG
Feature activation+0.707
ED
TokenED
Feature activation+1.815
ED
Token ED
Feature activation+0.000
GE
TokenGE
Feature activation+0.813
tournaments
Token tournaments
Feature activation+0.436
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
h
Tokenh
Feature activation+0.000
ane
Tokenane
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
red
Token red
Feature activation+1.835
peaks
Token peaks
Feature activation+0.983
on
Token on
Feature activation+0.087
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.128
show
Token show
Feature activation+0.015
yell
Token yell
Feature activation+0.760
ows
Tokenows
Feature activation+1.066
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
back
Token back
Feature activation+0.089
in
Token in
Feature activation+1.767
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.457 - 1.665
CONTAINS 0.003%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.294
three
Token three
Feature activation+0.637
investigations
Token investigations
Feature activation+1.653
into
Token into
Feature activation+0.551
the
Token the
Feature activation+0.000
actions
Token actions
Feature activation+0.000
of
Token of
Feature activation+0.000
Salt
Token Salt
Feature activation+0.000
was
Token was
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
lamb
Token lamb
Feature activation+1.208
ik
Tokenik
Feature activation+1.561
houses
Token houses
Feature activation+0.872
Cant
Token Cant
Feature activation+0.000
illon
Tokenillon
Feature activation+0.000
and
Token and
Feature activation+0.000
Til
Token Til
Feature activation+0.000
and
Token and
Feature activation+0.000
11
Token 11
Feature activation+0.000
of
Token of
Feature activation+0.353
the
Token the
Feature activation+0.405
16
Token 16
Feature activation+0.631
contests
Token contests
Feature activation+1.597
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
doing
Token doing
Feature activation+0.000
so
Token so
Feature activation+0.000
,
Token,
Feature activation+0.000
prayers
Token prayers
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
various
Token various
Feature activation+0.000
AD
Token AD
Feature activation+0.059
AMS
TokenAMS
Feature activation+1.507
(
Token (
Feature activation+0.018
All
TokenAll
Feature activation+0.591
Dull
Token Dull
Feature activation+0.000
es
Tokenes
Feature activation+0.038
Area
Token Area
Feature activation+0.110
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
two
Token two
Feature activation+0.367
directors
Token directors
Feature activation+1.611
leading
Token leading
Feature activation+0.000
the
Token the
Feature activation+0.000
G
Token G
Feature activation+0.000
iro
Tokeniro
Feature activation+0.000
team
Token team
Feature activation+0.000

INTERVAL 1.249 - 1.457
CONTAINS 0.010%

those
Token those
Feature activation+0.000
[
Token [
Feature activation+1.052
A
TokenA
Feature activation+0.734
ur
Tokenur
Feature activation+0.245
ora
Tokenora
Feature activation+0.664
]
Token]
Feature activation+1.405
attacks
Token attacks
Feature activation+0.498
and
Token and
Feature activation+0.000
this
Token this
Feature activation+0.000
group
Token group
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
THE
TokenTHE
Feature activation+0.000
F
Token F
Feature activation+0.000
OUR
TokenOUR
Feature activation+0.000
LA
Token LA
Feature activation+1.366
WS
TokenWS
Feature activation+1.362
THAT
Token THAT
Feature activation+0.061
H
Token H
Feature activation+0.000
ILL
TokenILL
Feature activation+0.000
ARY
TokenARY
Feature activation+0.000
CL
Token CL
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
one
Tokenone
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
fundamental
Token fundamental
Feature activation+1.320
rights
Token rights
Feature activation+0.534
of
Token of
Feature activation+0.000
English
Token English
Feature activation+0.000
men
Tokenmen
Feature activation+0.000
.
Token.
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
inn
Token inn
Feature activation+0.000
ately
Tokenately
Feature activation+0.761
fraudulent
Token fraudulent
Feature activation+1.250
News
Token News
Feature activation+0.091
peak
Tokenpeak
Feature activation+1.073
mant
Token mant
Feature activation+0.191
ras
Tokenras
Feature activation+0.825
that
Token that
Feature activation+0.000
four
Token four
Feature activation+0.000
or
Token or
Feature activation+0.361
five
Token five
Feature activation+0.036
simple
Token simple
Feature activation+1.014
but
Token but
Feature activation+1.159
compelling
Token compelling
Feature activation+1.283
examples
Token examples
Feature activation+0.903
of
Token of
Feature activation+0.000
where
Token where
Feature activation+0.000
government
Token government
Feature activation+0.000
can
Token can
Feature activation+0.000

INTERVAL 1.041 - 1.249
CONTAINS 0.026%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
unfortunate
Token unfortunate
Feature activation+1.015
and
Token and
Feature activation+1.117
painful
Token painful
Feature activation+1.204
stories
Token stories
Feature activation+0.266
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.000
've
Token've
Feature activation+0.000
come
Token come
Feature activation+0.000
com
Tokencom
Feature activation+0.000
executives
Token executives
Feature activation+0.000
fired
Token fired
Feature activation+0.000
three
Token three
Feature activation+0.000
Gotham
Token Gotham
Feature activation+0.768
City
Token City
Feature activation+1.214
âĢ
TokenâĢ
Feature activation+0.274
Ļ
TokenĻ
Feature activation+0.520
s
Tokens
Feature activation+1.635
high
Token high
Feature activation+0.078
-
Token-
Feature activation+0.000
in
Token in
Feature activation+0.000
Hampshire
Token Hampshire
Feature activation+0.000
ahead
Token ahead
Feature activation+0.000
of
Token of
Feature activation+0.000
two
Token two
Feature activation+0.000
practice
Token practice
Feature activation+1.051
matches
Token matches
Feature activation+1.077
in
Token in
Feature activation+0.000
Somerset
Token Somerset
Feature activation+0.000
and
Token and
Feature activation+0.000
Sussex
Token Sussex
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
founding
Token founding
Feature activation+0.394
tra
Token tra
Feature activation+0.909
um
Tokenum
Feature activation+0.435
as
Tokenas
Feature activation+1.093
of
Token of
Feature activation+0.069
the
Token the
Feature activation+0.000
modern
Token modern
Feature activation+0.000
center
Token center
Feature activation+0.000
-
Token-
Feature activation+0.000
m
Tokenm
Feature activation+0.000
just
Token just
Feature activation+0.000
using
Token using
Feature activation+0.000
my
Token my
Feature activation+0.000
two
Token two
Feature activation+0.000
text
Token text
Feature activation+1.063
columns
Token columns
Feature activation+0.536
name
Token name
Feature activation+0.000
and
Token and
Feature activation+0.000
passage
Token passage
Feature activation+0.000
,
Token ,
Feature activation+0.000

INTERVAL 0.833 - 1.041
CONTAINS 0.066%

telev
Token telev
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
two
Token two
Feature activation+0.000
campaign
Token campaign
Feature activation+0.721
-
Token-
Feature activation+0.456
style
Tokenstyle
Feature activation+0.952
advertisements
Token advertisements
Feature activation+0.479
that
Token that
Feature activation+0.000
emphasize
Token emphasize
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
's
Token's
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
those
Token those
Feature activation+0.000
t
Token t
Feature activation+1.178
ins
Tokenins
Feature activation+0.993
of
Token of
Feature activation+0.000
crust
Token crust
Feature activation+0.000
y
Tokeny
Feature activation+0.000
goodness
Token goodness
Feature activation+0.000
that
Token that
Feature activation+0.000
to
Token to
Feature activation+0.000
agreeing
Token agreeing
Feature activation+0.000
on
Token on
Feature activation+0.000
delaying
Token delaying
Feature activation+0.000
two
Token two
Feature activation+0.000
major
Token major
Feature activation+0.877
taxes
Token taxes
Feature activation+1.215
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
network
Token network
Feature activation+0.000
,
Token,
Feature activation+0.000
despite
Token despite
Feature activation+0.000
the
Token the
Feature activation+0.000
various
Token various
Feature activation+0.000
dec
Token dec
Feature activation+0.857
rying
Tokenrying
Feature activation+1.311
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
that
Token that
Feature activation+0.000
puts
Token puts
Feature activation+0.000
the
Token the
Feature activation+0.000
3
Token 3
Feature activation+0.000
desk
Token desk
Feature activation+0.381
tops
Tokentops
Feature activation+0.937
in
Token in
Feature activation+0.000
hard
Token hard
Feature activation+0.000
competition
Token competition
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.624 - 0.833
CONTAINS 0.126%

.
Token.
Feature activation+0.000
Two
Token Two
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.702
three
Token three
Feature activation+0.668
j
Token j
Feature activation+0.717
agu
Tokenagu
Feature activation+0.446
ars
Tokenars
Feature activation+0.895
are
Token are
Feature activation+0.000
thought
Token thought
Feature activation+0.103
to
Token to
Feature activation+0.000
ored
Tokenored
Feature activation+0.000
methods
Token methods
Feature activation+0.000
?
Token?
Feature activation+0.000
Are
Token Are
Feature activation+0.000
there
Token there
Feature activation+0.191
local
Token local
Feature activation+0.825
variables
Token variables
Feature activation+0.154
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
now
Token now
Feature activation+0.000
lying
Token lying
Feature activation+0.000
artist
Token artist
Feature activation+0.000
on
Token on
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.754
internationally
Token internationally
Feature activation+1.199
published
Token published
Feature activation+1.471
games
Token games
Feature activation+1.126
to
Token to
Feature activation+0.000
come
Token come
Feature activation+0.000
and
Token and
Feature activation+0.000
is
Token is
Feature activation+0.000
linked
Token linked
Feature activation+0.000
to
Token to
Feature activation+0.000
numerous
Token numerous
Feature activation+0.000
international
Token international
Feature activation+0.683
parcel
Token parcel
Feature activation+0.107
shipments
Token shipments
Feature activation+0.076
from
Token from
Feature activation+0.000
China
Token China
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
dozen
Token dozen
Feature activation+0.000
more
Token more
Feature activation+0.818
rules
Token rules
Feature activation+0.201
logging
Token logging
Feature activation+0.000
different
Token different
Feature activation+0.000
things
Token things
Feature activation+0.179
,
Token,
Feature activation+0.000

INTERVAL 0.416 - 0.624
CONTAINS 0.226%

and
Token and
Feature activation+0.000
Avalon
Token Avalon
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
also
Token also
Feature activation+0.560
seven
Token seven
Feature activation+0.164
Dig
Token Dig
Feature activation+0.065
ides
Tokenides
Feature activation+0.310
ign
Tokenign
Feature activation+0.867
Pro
Token Pro
Feature activation+1.195
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
fifteen
Token fifteen
Feature activation+0.000
of
Token of
Feature activation+0.224
the
Token the
Feature activation+0.433
shows
Token shows
Feature activation+0.587
with
Token with
Feature activation+0.000
higher
Token higher
Feature activation+0.000
-
Token-
Feature activation+0.031
than
Tokenthan
Feature activation+0.000
-
Token-
Feature activation+0.000
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
actual
Token actual
Feature activation+0.247
RAM
Token RAM
Feature activation+0.350
bits
Token bits
Feature activation+0.420
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
system
Token system
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
to
Token to
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.035
match
Token match
Feature activation+0.096
making
Tokenmaking
Feature activation+0.439
issues
Token issues
Feature activation+0.062
in
Token in
Feature activation+0.000
Armored
Token Armored
Feature activation+0.000
Warfare
Token Warfare
Feature activation+0.000
.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.092
his
Token his
Feature activation+0.597
races
Token races
Feature activation+0.596
,
Token,
Feature activation+0.000
entering
Token entering
Feature activation+0.000
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000

INTERVAL 0.208 - 0.416
CONTAINS 0.438%

İ
Tokenİ
Feature activation+0.000
ãģ
Tokenãģ
Feature activation+0.000
ij
Tokenij
Feature activation+0.000
ãģ¦
Tokenãģ¦
Feature activation+0.000
10
Token10
Feature activation+0.000
æľ
Tokenæľ
Feature activation+0.292
Ī
TokenĪ
Feature activation+0.378
20
Token20
Feature activation+0.000
æĹ
TokenæĹ
Feature activation+0.214
¥
Token¥
Feature activation+0.182
ãģª
Tokenãģª
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
roughly
Token roughly
Feature activation+0.000
80
Token 80
Feature activation+0.000
,
Token,
Feature activation+0.337
000
Token000
Feature activation+0.371
people
Token people
Feature activation+0.069
who
Token who
Feature activation+0.000
are
Token are
Feature activation+0.000
wounded
Token wounded
Feature activation+0.000
by
Token by
Feature activation+0.000
Some
TokenSome
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.125
kinds
Token kinds
Feature activation+0.259
of
Token of
Feature activation+0.476
tips
Token tips
Feature activation+0.619
that
Token that
Feature activation+0.034
we
Token we
Feature activation+0.000
really
Token really
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
illegal
Token illegal
Feature activation+0.349
drug
Token drug
Feature activation+0.427
samples
Token samples
Feature activation+0.094
containing
Token containing
Feature activation+0.000
fentanyl
Token fentanyl
Feature activation+0.000
has
Token has
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
th
Tokenth
Feature activation+0.000
ousands
Tokenousands
Feature activation+0.000
of
Token of
Feature activation+0.041
fundra
Token fundra
Feature activation+0.177
isers
Tokenisers
Feature activation+0.260
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000

INTERVAL 0.000 - 0.208
CONTAINS 99.105%

least
Token least
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
rated
Token rated
Feature activation+0.000
in
Token in
Feature activation+0.000
poor
Token poor
Feature activation+0.000
condition
Token condition
Feature activation+0.000
by
Token by
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
saw
Token saw
Feature activation+0.000
most
Token most
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
playing
Token playing
Feature activation+0.000
time
Token time
Feature activation+0.000
on
Token on
Feature activation+0.000
special
Token special
Feature activation+0.000
teams
Token teams
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
right
Token right
Feature activation+0.000
to
Token to
Feature activation+0.000
equal
Token equal
Feature activation+0.000
protection
Token protection
Feature activation+0.000
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
law
Token law
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
voice
Token voice
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
always
Token always
Feature activation+0.000
involved
Token involved
Feature activation+0.000
and
Token and
Feature activation+0.000
ALWAYS
Token ALWAYS
Feature activation+0.000
read
Token read
Feature activation+0.000
and
Token and
Feature activation+0.000
approve
Token approve
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Like
TokenLike
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
notes
Token notes
Feature activation+0.000
she
Token she
Feature activation+0.000
had
Token had
Feature activation+0.000
written
Token written
Feature activation+0.000
up
Token up
Feature activation+0.000
about
Token about
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.061
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.061
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 1 in H7.0: (feature 22734)

TOP ACTIVATIONS
MAX = 2.226

ion
Tokenion
Feature activation+0.000
ari
Tokenari
Feature activation+0.000
del
Token del
Feature activation+0.000
l
Token l
Feature activation+1.000
u
Tokenu
Feature activation+0.649
ogo
Tokenogo
Feature activation+2.226
che
Token che
Feature activation+0.000
s
Token s
Feature activation+0.000
ost
Tokenost
Feature activation+0.000
ene
Tokenene
Feature activation+0.000
v
Tokenv
Feature activation+0.000
en
Tokenen
Feature activation+0.000
as
Tokenas
Feature activation+0.000
y
Token y
Feature activation+0.000
del
Token del
Feature activation+0.000
f
Tokenf
Feature activation+0.575
ines
Tokenines
Feature activation+1.930
en
Token en
Feature activation+0.000
nu
Token nu
Feature activation+0.018
est
Tokenest
Feature activation+0.000
ras
Tokenras
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
dim
Token dim
Feature activation+0.000
ost
Tokenost
Feature activation+0.000
raz
Tokenraz
Feature activation+0.000
ione
Tokenione
Feature activation+0.000
del
Token del
Feature activation+0.000
su
Token su
Feature activation+1.851
o
Tokeno
Feature activation+1.157
car
Token car
Feature activation+0.370
att
Tokenatt
Feature activation+0.648
ere
Tokenere
Feature activation+0.000
ind
Token ind
Feature activation+0.000
que
Tokenque
Feature activation+0.000
o
Token o
Feature activation+0.000
val
Token val
Feature activation+0.000
or
Tokenor
Feature activation+0.000
da
Token da
Feature activation+0.000
mo
Token mo
Feature activation+1.228
eda
Tokeneda
Feature activation+0.122
est
Token est
Feature activation+0.000
ava
Tokenava
Feature activation+0.000
ba
Token ba
Feature activation+0.000
ix
Tokenix
Feature activation+0.000
ost
Tokenost
Feature activation+0.000
raz
Tokenraz
Feature activation+0.000
ione
Tokenione
Feature activation+0.000
del
Token del
Feature activation+0.000
su
Token su
Feature activation+1.851
o
Tokeno
Feature activation+1.157
car
Token car
Feature activation+0.370
att
Tokenatt
Feature activation+0.648
ere
Tokenere
Feature activation+0.000
ind
Token ind
Feature activation+0.000
om
Tokenom
Feature activation+0.000
icia
Tokenicia
Feature activation+0.000
!
Token!
Feature activation+0.000
Cont
Token Cont
Feature activation+0.000
igo
Tokenigo
Feature activation+0.000
al
Token al
Feature activation+0.000
f
Token f
Feature activation+1.051
rent
Tokenrent
Feature activation+0.440
e
Tokene
Feature activation+0.615
de
Token de
Feature activation+0.000
Del
Token Del
Feature activation+0.000
phi
Tokenphi
Feature activation+0.000
s
Tokens
Feature activation+0.000
c
Token c
Feature activation+0.000
ela
Tokenela
Feature activation+0.000
,
Token,
Feature activation+0.000
il
Token il
Feature activation+0.000
a
Token a
Feature activation+1.018
l
Token l
Feature activation+0.340
u
Tokenu
Feature activation+0.000
des
Token des
Feature activation+0.055
g
Token g
Feature activation+0.000
ens
Tokenens
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
rea
Tokenrea
Feature activation+0.000
del
Token del
Feature activation+0.000
le
Tokenle
Feature activation+0.044
Fr
Token Fr
Feature activation+1.017
at
Tokenat
Feature activation+0.990
te
Tokente
Feature activation+0.000
in
Token in
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
As
TokenAs
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
uz
Tokenuz
Feature activation+0.000
ion
Tokenion
Feature activation+0.000
ari
Tokenari
Feature activation+0.000
del
Token del
Feature activation+0.000
l
Token l
Feature activation+1.000
u
Tokenu
Feature activation+0.649
ogo
Tokenogo
Feature activation+2.226
che
Token che
Feature activation+0.000
s
Token s
Feature activation+0.000
ost
Tokenost
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
rea
Tokenrea
Feature activation+0.000
del
Token del
Feature activation+0.000
le
Tokenle
Feature activation+0.044
Fr
Token Fr
Feature activation+1.017
at
Tokenat
Feature activation+0.990
te
Tokente
Feature activation+0.000
in
Token in
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
As
TokenAs
Feature activation+0.000
this
Token this
Feature activation+0.000
viol
Token viol
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
ione
Tokenione
Feature activation+0.000
del
Token del
Feature activation+0.000
le
Tokenle
Feature activation+0.214
norm
Token norm
Feature activation+0.955
e
Tokene
Feature activation+1.496
di
Token di
Feature activation+0.000
acc
Token acc
Feature activation+0.000
redit
Tokenredit
Feature activation+0.428
ament
Tokenament
Feature activation+0.186
ini
Tokenini
Feature activation+0.000
ed
Token ed
Feature activation+0.000
un
Token un
Feature activation+0.000
o
Tokeno
Feature activation+0.000
del
Token del
Feature activation+0.000
Senegal
Token Senegal
Feature activation+0.919
(
Token (
Feature activation+0.000
due
Tokendue
Feature activation+0.000
di
Token di
Feature activation+0.000
sed
Token sed
Feature activation+0.000
ici
Tokenici
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
este
Token este
Feature activation+0.000
o
Token o
Feature activation+0.965
farm
Token farm
Feature activation+0.692
ac
Tokenac
Feature activation+0.545
ie
Tokenie
Feature activation+0.887
des
Token des
Feature activation+0.000
ch
Tokench
Feature activation+0.000
is
Tokenis
Feature activation+0.000
Ä
TokenÄ
Feature activation+0.000
ĥ
Tokenĥ
Feature activation+0.000
June
Token June
Feature activation+0.000
,
Token,
Feature activation+0.000
Ess
Token Ess
Feature activation+0.000
am
Tokenam
Feature activation+0.000
el
Token el
Feature activation+0.000
H
Token H
Feature activation+0.862
add
Tokenadd
Feature activation+0.687
ad
Tokenad
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
i
Tokeni
Feature activation+0.000
orno
Tokenorno
Feature activation+0.752
dop
Token dop
Feature activation+0.000
o
Tokeno
Feature activation+0.000
il
Token il
Feature activation+0.000
fol
Token fol
Feature activation+0.775
le
Tokenle
Feature activation+0.086
raid
Token raid
Feature activation+0.000
av
Token av
Feature activation+0.000
ven
Tokenven
Feature activation+0.000
uto
Tokenuto
Feature activation+0.000
n
Token n
Feature activation+0.000
el
Tokenel
Feature activation+0.000
cor
Token cor
Feature activation+0.000
so
Tokenso
Feature activation+0.000
del
Token del
Feature activation+0.000
le
Tokenle
Feature activation+0.774
per
Token per
Feature activation+0.059
qu
Tokenqu
Feature activation+0.541
is
Tokenis
Feature activation+0.732
iz
Tokeniz
Feature activation+0.141
ion
Tokenion
Feature activation+0.326
or
Tokenor
Feature activation+0.000
iza
Tokeniza
Feature activation+0.000
ç
Tokenç
Feature activation+0.000
ão
Tokenão
Feature activation+0.000
da
Token da
Feature activation+0.000
c
Token c
Feature activation+0.772
ript
Tokenript
Feature activation+0.370
omo
Tokenomo
Feature activation+0.000
eda
Tokeneda
Feature activation+0.000
e
Token e
Feature activation+0.000
na
Token na
Feature activation+0.000
arrest
Token arrest
Feature activation+0.000
ati
Tokenati
Feature activation+0.000
il
Token il
Feature activation+0.000
g
Token g
Feature activation+0.605
i
Tokeni
Feature activation+0.000
orno
Tokenorno
Feature activation+0.752
dop
Token dop
Feature activation+0.000
o
Tokeno
Feature activation+0.000
il
Token il
Feature activation+0.000
fol
Token fol
Feature activation+0.775
le
Tokenle
Feature activation+0.086
so
Tokenso
Feature activation+0.000
del
Token del
Feature activation+0.000
le
Tokenle
Feature activation+0.774
per
Token per
Feature activation+0.059
qu
Tokenqu
Feature activation+0.541
is
Tokenis
Feature activation+0.732
iz
Tokeniz
Feature activation+0.141
ion
Tokenion
Feature activation+0.326
i
Tokeni
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
o
Token o
Feature activation+0.000
g
Token g
Feature activation+0.000
erent
Tokenerent
Feature activation+0.000
e
Tokene
Feature activation+0.000
da
Token da
Feature activation+0.000
Nokia
Token Nokia
Feature activation+0.726
.
Token.
Feature activation+0.000
Por
Token Por
Feature activation+0.000
me
Token me
Feature activation+0.000
io
Tokenio
Feature activation+0.000
do
Token do
Feature activation+0.000

Top DFA by src position
MAX = 3.615

iv
Tokeniv
Feature activation-0.010
Top resid features:
ol
Tokenol
Feature activation+0.007
Top resid features:
uz
Tokenuz
Feature activation+0.009
Top resid features:
ion
Tokenion
Feature activation+0.001
Top resid features:
ari
Tokenari
Feature activation+0.014
Top resid features:
del
Token del
Feature activation+3.615
Top resid features:
l
Token l
Feature activation+0.217
Top resid features:
u
Tokenu
Feature activation+0.049
Top resid features:
ogo
Tokenogo
Feature activation+0.121
Top resid features:
che
Token che
Feature activation+0.000
Top resid features:
s
Token s
Feature activation+0.000
Top resid features:
para
Token para
Feature activation+0.006
Top resid features:
ball
Token ball
Feature activation+0.096
Top resid features:
en
Tokenen
Feature activation-0.032
Top resid features:
as
Tokenas
Feature activation+0.024
Top resid features:
y
Token y
Feature activation+0.089
Top resid features:
del
Token del
Feature activation+2.827
Top resid features:
f
Tokenf
Feature activation+0.490
Top resid features:
ines
Tokenines
Feature activation+0.048
Top resid features:
en
Token en
Feature activation+0.000
Top resid features:
nu
Token nu
Feature activation+0.000
Top resid features:
est
Tokenest
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
dim
Token dim
Feature activation-0.012
Top resid features:
ost
Tokenost
Feature activation-0.011
Top resid features:
raz
Tokenraz
Feature activation+0.011
Top resid features:
ione
Tokenione
Feature activation+0.014
Top resid features:
del
Token del
Feature activation+3.021
Top resid features:
su
Token su
Feature activation+0.074
Top resid features:
o
Tokeno
Feature activation+0.000
Top resid features:
car
Token car
Feature activation+0.000
Top resid features:
att
Tokenatt
Feature activation+0.000
Top resid features:
ere
Tokenere
Feature activation+0.000
Top resid features:
por
Token por
Feature activation+0.075
Top resid features:
que
Tokenque
Feature activation+0.004
Top resid features:
o
Token o
Feature activation+0.043
Top resid features:
val
Token val
Feature activation+0.014
Top resid features:
or
Tokenor
Feature activation-0.022
Top resid features:
da
Token da
Feature activation+2.511
Top resid features:
mo
Token mo
Feature activation+0.029
Top resid features:
eda
Tokeneda
Feature activation+0.000
Top resid features:
est
Token est
Feature activation+0.000
Top resid features:
ava
Tokenava
Feature activation+0.000
Top resid features:
ba
Token ba
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.182
Top resid features:
infl
Token infl
Feature activation-0.006
Top resid features:
itt
Tokenitt
Feature activation-0.001
Top resid features:
i
Tokeni
Feature activation-0.000
Top resid features:
da
Token da
Feature activation+0.009
Top resid features:
un
Token un
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.343
Top resid features:
L
Token L
Feature activation-0.005
Top resid features:
ately
Tokenately
Feature activation-0.002
Top resid features:
we
Token we
Feature activation-0.002
Top resid features:
had
Token had
Feature activation-0.001
Top resid features:
have
Token have
Feature activation-0.001
Top resid features:
è
Tokenè
Feature activation-0.089
Top resid features:
s
Tokens
Feature activation-0.028
Top resid features:
c
Token c
Feature activation+0.016
Top resid features:
ela
Tokenela
Feature activation+0.072
Top resid features:
,
Token,
Feature activation-0.063
Top resid features:
il
Token il
Feature activation+2.419
Top resid features:
a
Token a
Feature activation+0.063
Top resid features:
l
Token l
Feature activation+0.000
Top resid features:
u
Tokenu
Feature activation+0.000
Top resid features:
des
Token des
Feature activation+0.000
Top resid features:
g
Token g
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.280
Top resid features:
You
Token You
Feature activation-0.003
Top resid features:
have
Token have
Feature activation-0.000
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
be
Token be
Feature activation-0.000
Top resid features:
focused
Token focused
Feature activation-0.000
Top resid features:
iv
Tokeniv
Feature activation-0.048
Top resid features:
ol
Tokenol
Feature activation+0.028
Top resid features:
uz
Tokenuz
Feature activation+0.011
Top resid features:
ion
Tokenion
Feature activation+0.003
Top resid features:
ari
Tokenari
Feature activation+0.014
Top resid features:
del
Token del
Feature activation+2.354
Top resid features:
l
Token l
Feature activation+0.046
Top resid features:
u
Tokenu
Feature activation+0.000
Top resid features:
ogo
Tokenogo
Feature activation+0.000
Top resid features:
che
Token che
Feature activation+0.000
Top resid features:
s
Token s
Feature activation+0.000
Top resid features:
Sant
Token Sant
Feature activation+0.006
Top resid features:
âĢ
TokenâĢ
Feature activation+0.110
Top resid features:
Ļ
TokenĻ
Feature activation+0.005
Top resid features:
And
TokenAnd
Feature activation+0.006
Top resid features:
rea
Tokenrea
Feature activation+0.026
Top resid features:
del
Token del
Feature activation+2.233
Top resid features:
le
Tokenle
Feature activation+0.328
Top resid features:
Fr
Token Fr
Feature activation+0.056
Top resid features:
at
Tokenat
Feature activation-0.014
Top resid features:
te
Tokente
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.375
Top resid features:
o
Tokeno
Feature activation-0.002
Top resid features:
dec
Token dec
Feature activation-0.002
Top resid features:
ine
Tokenine
Feature activation-0.009
Top resid features:
i
Token i
Feature activation+0.001
Top resid features:
document
Token document
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.978
Top resid features:
ando
Tokenando
Feature activation-0.013
Top resid features:
tut
Token tut
Feature activation+0.010
Top resid features:
to
Tokento
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
E
Token E
Feature activation-0.006
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.916
Top resid features:
este
Token este
Feature activation+1.706
Top resid features:
o
Token o
Feature activation+0.180
Top resid features:
farm
Token farm
Feature activation+0.290
Top resid features:
ac
Tokenac
Feature activation+0.343
Top resid features:
ie
Tokenie
Feature activation+0.049
Top resid features:
th
Tokenth
Feature activation-0.012
Top resid features:
June
Token June
Feature activation-0.027
Top resid features:
,
Token,
Feature activation-0.025
Top resid features:
Ess
Token Ess
Feature activation-0.092
Top resid features:
am
Tokenam
Feature activation+0.024
Top resid features:
el
Token el
Feature activation+2.464
Top resid features:
H
Token H
Feature activation+0.007
Top resid features:
add
Tokenadd
Feature activation+0.000
Top resid features:
ad
Tokenad
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.348
Top resid features:
ando
Tokenando
Feature activation-0.005
Top resid features:
tut
Token tut
Feature activation+0.015
Top resid features:
to
Tokento
Feature activation+0.009
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
E
Token E
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.379
Top resid features:
o
Tokeno
Feature activation-0.008
Top resid features:
dec
Token dec
Feature activation-0.016
Top resid features:
ine
Tokenine
Feature activation+0.011
Top resid features:
i
Token i
Feature activation+0.041
Top resid features:
document
Token document
Feature activation-0.037
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.239
Top resid features:
ou
Tokenou
Feature activation-0.010
Top resid features:
que
Token que
Feature activation-0.008
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
em
Token em
Feature activation-0.008
Top resid features:
p
Tokenp
Feature activation+0.011
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+1.903
Top resid features:
ando
Tokenando
Feature activation+0.000
Top resid features:
tut
Token tut
Feature activation+0.013
Top resid features:
to
Tokento
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
E
Token E
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.012
Top resid features:
o
Tokeno
Feature activation+0.000
Top resid features:
dec
Token dec
Feature activation-0.023
Top resid features:
ine
Tokenine
Feature activation-0.003
Top resid features:
i
Token i
Feature activation+0.018
Top resid features:
document
Token document
Feature activation-0.041
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.101
Top resid features:
a
Token a
Feature activation-0.011
Top resid features:
fam
Token fam
Feature activation-0.007
Top resid features:
ÃŃ
TokenÃŃ
Feature activation-0.005
Top resid features:
lia
Tokenlia
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.017
Top resid features:

Decoder Weights Distribution

Head 0: 0.59

Head 1: 0.03

Head 2: 0.02

Head 3: 0.06

Head 4: 0.04

Head 5: 0.06

Head 6: 0.04

Head 7: 0.02

Head 8: 0.05

Head 9: 0.04

Head 10: 0.03

Head 11: 0.02

Positive logits

ño2.32

ador2.13

ón2.00

icio1.92

apo1.88

itor1.78

izo1.70

itol1.67

oglobin1.66

ć1.61

municipality1.57

oto1.56

icer1.55

ambo1.54

orio1.52

Dominican1.51

umat1.50

ovich1.49

INO1.47

enezuel1.47

Negative logits

nces-2.01

sidel-1.77

ties-1.62

talents-1.61

eatures-1.60

noses-1.59

backgrounds-1.55

isations-1.52

minds-1.52

objections-1.49

instincts-1.48

downs-1.48

fools-1.47

days-1.45

waves-1.45

necks-1.44

selves-1.42

Interstitial-1.41

urations-1.40

spears-1.40

INTERVAL 2.003 - 2.226
CONTAINS 0.000%

ion
Tokenion
Feature activation+0.000
ari
Tokenari
Feature activation+0.000
del
Token del
Feature activation+0.000
l
Token l
Feature activation+1.000
u
Tokenu
Feature activation+0.649
ogo
Tokenogo
Feature activation+2.226
che
Token che
Feature activation+0.000
s
Token s
Feature activation+0.000
ost
Tokenost
Feature activation+0.000
ene
Tokenene
Feature activation+0.000
v
Tokenv
Feature activation+0.000

INTERVAL 1.780 - 2.003
CONTAINS 0.000%

en
Tokenen
Feature activation+0.000
as
Tokenas
Feature activation+0.000
y
Token y
Feature activation+0.000
del
Token del
Feature activation+0.000
f
Tokenf
Feature activation+0.575
ines
Tokenines
Feature activation+1.930
en
Token en
Feature activation+0.000
nu
Token nu
Feature activation+0.018
est
Tokenest
Feature activation+0.000
ras
Tokenras
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
dim
Token dim
Feature activation+0.000
ost
Tokenost
Feature activation+0.000
raz
Tokenraz
Feature activation+0.000
ione
Tokenione
Feature activation+0.000
del
Token del
Feature activation+0.000
su
Token su
Feature activation+1.851
o
Tokeno
Feature activation+1.157
car
Token car
Feature activation+0.370
att
Tokenatt
Feature activation+0.648
ere
Tokenere
Feature activation+0.000
ind
Token ind
Feature activation+0.000

INTERVAL 1.558 - 1.780
CONTAINS 0.000%

INTERVAL 1.335 - 1.558
CONTAINS 0.000%

INTERVAL 1.113 - 1.335
CONTAINS 0.000%

que
Tokenque
Feature activation+0.000
o
Token o
Feature activation+0.000
val
Token val
Feature activation+0.000
or
Tokenor
Feature activation+0.000
da
Token da
Feature activation+0.000
mo
Token mo
Feature activation+1.228
eda
Tokeneda
Feature activation+0.122
est
Token est
Feature activation+0.000
ava
Tokenava
Feature activation+0.000
ba
Token ba
Feature activation+0.000
ix
Tokenix
Feature activation+0.000
ost
Tokenost
Feature activation+0.000
raz
Tokenraz
Feature activation+0.000
ione
Tokenione
Feature activation+0.000
del
Token del
Feature activation+0.000
su
Token su
Feature activation+1.851
o
Tokeno
Feature activation+1.157
car
Token car
Feature activation+0.370
att
Tokenatt
Feature activation+0.648
ere
Tokenere
Feature activation+0.000
ind
Token ind
Feature activation+0.000
om
Tokenom
Feature activation+0.000

INTERVAL 0.890 - 1.113
CONTAINS 0.001%

icia
Tokenicia
Feature activation+0.000
!
Token!
Feature activation+0.000
Cont
Token Cont
Feature activation+0.000
igo
Tokenigo
Feature activation+0.000
al
Token al
Feature activation+0.000
f
Token f
Feature activation+1.051
rent
Tokenrent
Feature activation+0.440
e
Tokene
Feature activation+0.615
de
Token de
Feature activation+0.000
Del
Token Del
Feature activation+0.000
phi
Tokenphi
Feature activation+0.000
viol
Token viol
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
ione
Tokenione
Feature activation+0.000
del
Token del
Feature activation+0.000
le
Tokenle
Feature activation+0.214
norm
Token norm
Feature activation+0.955
e
Tokene
Feature activation+1.496
di
Token di
Feature activation+0.000
acc
Token acc
Feature activation+0.000
redit
Tokenredit
Feature activation+0.428
ament
Tokenament
Feature activation+0.186
ol
Tokenol
Feature activation+0.000
uz
Tokenuz
Feature activation+0.000
ion
Tokenion
Feature activation+0.000
ari
Tokenari
Feature activation+0.000
del
Token del
Feature activation+0.000
l
Token l
Feature activation+1.000
u
Tokenu
Feature activation+0.649
ogo
Tokenogo
Feature activation+2.226
che
Token che
Feature activation+0.000
s
Token s
Feature activation+0.000
ost
Tokenost
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
rea
Tokenrea
Feature activation+0.000
del
Token del
Feature activation+0.000
le
Tokenle
Feature activation+0.044
Fr
Token Fr
Feature activation+1.017
at
Tokenat
Feature activation+0.990
te
Tokente
Feature activation+0.000
in
Token in
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
As
TokenAs
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
rea
Tokenrea
Feature activation+0.000
del
Token del
Feature activation+0.000
le
Tokenle
Feature activation+0.044
Fr
Token Fr
Feature activation+1.017
at
Tokenat
Feature activation+0.990
te
Tokente
Feature activation+0.000
in
Token in
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
As
TokenAs
Feature activation+0.000
this
Token this
Feature activation+0.000

INTERVAL 0.668 - 0.890
CONTAINS 0.001%

arrest
Token arrest
Feature activation+0.000
ati
Tokenati
Feature activation+0.000
il
Token il
Feature activation+0.000
g
Token g
Feature activation+0.605
i
Tokeni
Feature activation+0.000
orno
Tokenorno
Feature activation+0.752
dop
Token dop
Feature activation+0.000
o
Tokeno
Feature activation+0.000
il
Token il
Feature activation+0.000
fol
Token fol
Feature activation+0.775
le
Tokenle
Feature activation+0.086
or
Tokenor
Feature activation+0.000
iza
Tokeniza
Feature activation+0.000
ç
Tokenç
Feature activation+0.000
ão
Tokenão
Feature activation+0.000
da
Token da
Feature activation+0.000
c
Token c
Feature activation+0.772
ript
Tokenript
Feature activation+0.370
omo
Tokenomo
Feature activation+0.000
eda
Tokeneda
Feature activation+0.000
e
Token e
Feature activation+0.000
na
Token na
Feature activation+0.000
o
Token o
Feature activation+0.000
g
Token g
Feature activation+0.000
erent
Tokenerent
Feature activation+0.000
e
Tokene
Feature activation+0.000
da
Token da
Feature activation+0.000
Nokia
Token Nokia
Feature activation+0.726
.
Token.
Feature activation+0.000
Por
Token Por
Feature activation+0.000
me
Token me
Feature activation+0.000
io
Tokenio
Feature activation+0.000
do
Token do
Feature activation+0.000
June
Token June
Feature activation+0.000
,
Token,
Feature activation+0.000
Ess
Token Ess
Feature activation+0.000
am
Tokenam
Feature activation+0.000
el
Token el
Feature activation+0.000
H
Token H
Feature activation+0.862
add
Tokenadd
Feature activation+0.687
ad
Tokenad
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
n
Token n
Feature activation+0.000
el
Tokenel
Feature activation+0.000
cor
Token cor
Feature activation+0.000
so
Tokenso
Feature activation+0.000
del
Token del
Feature activation+0.000
le
Tokenle
Feature activation+0.774
per
Token per
Feature activation+0.059
qu
Tokenqu
Feature activation+0.541
is
Tokenis
Feature activation+0.732
iz
Tokeniz
Feature activation+0.141
ion
Tokenion
Feature activation+0.326

INTERVAL 0.445 - 0.668
CONTAINS 0.002%

de
Token de
Feature activation+0.000
Louis
Token Louis
Feature activation+0.000
iane
Tokeniane
Feature activation+0.000
,
Token,
Feature activation+0.000
il
Token il
Feature activation+0.000
l
Token l
Feature activation+0.653
ance
Tokenance
Feature activation+0.000
le
Token le
Feature activation+0.000
20
Token 20
Feature activation+0.000
ju
Token ju
Feature activation+0.000
in
Tokenin
Feature activation+0.000
ann
Tokenann
Feature activation+0.000
o
Tokeno
Feature activation+0.000
arrest
Token arrest
Feature activation+0.000
ati
Tokenati
Feature activation+0.000
il
Token il
Feature activation+0.000
g
Token g
Feature activation+0.605
i
Tokeni
Feature activation+0.000
orno
Tokenorno
Feature activation+0.752
dop
Token dop
Feature activation+0.000
o
Tokeno
Feature activation+0.000
il
Token il
Feature activation+0.000
ione
Tokenione
Feature activation+0.000
del
Token del
Feature activation+0.000
su
Token su
Feature activation+1.851
o
Tokeno
Feature activation+1.157
car
Token car
Feature activation+0.370
att
Tokenatt
Feature activation+0.648
ere
Tokenere
Feature activation+0.000
ind
Token ind
Feature activation+0.000
om
Tokenom
Feature activation+0.000
ito
Tokenito
Feature activation+0.000
,
Token,
Feature activation+0.000
pert
Tokenpert
Feature activation+0.000
ament
Tokenament
Feature activation+0.000
e
Tokene
Feature activation+0.000
il
Token il
Feature activation+0.000
com
Token com
Feature activation+0.636
un
Tokenun
Feature activation+0.468
ismo
Tokenismo
Feature activation+0.176
liber
Token liber
Feature activation+0.000
t
Tokent
Feature activation+0.000
ario
Tokenario
Feature activation+0.000
e
Token e
Feature activation+0.000
of
Tokenof
Feature activation+0.000
und
Tokenund
Feature activation+0.000
ador
Tokenador
Feature activation+0.000
da
Token da
Feature activation+0.000
bl
Token bl
Feature activation+0.128
ip
Tokenip
Feature activation+0.518
.
Token.
Feature activation+0.000
tv
Tokentv
Feature activation+0.000
,
Token,
Feature activation+0.000
Mike
Token Mike
Feature activation+0.000
abandon
Token abandon
Feature activation+0.000

INTERVAL 0.223 - 0.445
CONTAINS 0.002%

a
Token a
Feature activation+0.000
prime
Token prime
Feature activation+0.000
ira
Tokenira
Feature activation+0.000
const
Token const
Feature activation+0.076
r
Tokenr
Feature activation+0.000
ut
Tokenut
Feature activation+0.247
ora
Tokenora
Feature activation+0.000
list
Token list
Feature activation+0.048
ada
Tokenada
Feature activation+0.000
em
Token em
Feature activation+0.000
b
Token b
Feature activation+0.161
a
Tokena
Feature activation+0.516
ç
Tokenç
Feature activation+0.516
ão
Tokenão
Feature activation+0.266
hom
Token hom
Feature activation+0.000
em
Tokenem
Feature activation+0.031
-
Token-
Feature activation+0.309
m
Tokenm
Feature activation+0.000
á
Tokená
Feature activation+0.000
qu
Tokenqu
Feature activation+0.000
ina
Tokenina
Feature activation+0.000
.
Token.
Feature activation+0.000
le
Tokenle
Feature activation+0.774
per
Token per
Feature activation+0.059
qu
Tokenqu
Feature activation+0.541
is
Tokenis
Feature activation+0.732
iz
Tokeniz
Feature activation+0.141
ion
Tokenion
Feature activation+0.326
i
Tokeni
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
iza
Tokeniza
Feature activation+0.000
ç
Tokenç
Feature activation+0.000
ão
Tokenão
Feature activation+0.000
da
Token da
Feature activation+0.000
c
Token c
Feature activation+0.772
ript
Tokenript
Feature activation+0.370
omo
Tokenomo
Feature activation+0.000
eda
Tokeneda
Feature activation+0.000
e
Token e
Feature activation+0.000
na
Token na
Feature activation+0.000
at
Token at
Feature activation+0.000
infl
Token infl
Feature activation+0.000
itt
Tokenitt
Feature activation+0.000
i
Tokeni
Feature activation+0.000
da
Token da
Feature activation+0.000
un
Token un
Feature activation+0.391
g
Token g
Feature activation+0.432
iov
Tokeniov
Feature activation+0.000
ane
Tokenane
Feature activation+0.089
pad
Token pad
Feature activation+0.000
rone
Tokenrone
Feature activation+0.000
contro
Token contro
Feature activation+0.000

INTERVAL 0.000 - 0.223
CONTAINS 99.993%

IL
TokenIL
Feature activation+0.000
SON
TokenSON
Feature activation+0.000
/
Token/
Feature activation+0.000
ST
TokenST
Feature activation+0.000
UFF
TokenUFF
Feature activation+0.000
Arc
Token Arc
Feature activation+0.000
adia
Tokenadia
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
Bl
Token Bl
Feature activation+0.000
en
Tokenen
Feature activation+0.000
un
Token un
Feature activation+0.000
-
Token-
Feature activation+0.000
partisan
Tokenpartisan
Feature activation+0.000
way
Token way
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
hosting
Token hosting
Feature activation+0.000
goofy
Token goofy
Feature activation+0.000
developer
Token developer
Feature activation+0.000
,
Token,
Feature activation+0.000
more
Token more
Feature activation+0.000
specifically
Token specifically
Feature activation+0.000
a
Token a
Feature activation+0.000
firmware
Token firmware
Feature activation+0.000
developer
Token developer
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
cosmic
Token cosmic
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
entities
Token entities
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
nature
Token nature
Feature activation+0.000
gain
Token gain
Feature activation+0.000
adoption
Token adoption
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
labour
Token labour
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
N
TokenN
Feature activation+0.000
.
Token.
Feature activation+0.000
had
Token had
Feature activation+0.000
not
Token not
Feature activation+0.000
based
Token based
Feature activation+0.000
its
Token its
Feature activation+0.000
report
Token report
Feature activation+0.000
on
Token on
Feature activation+0.000
information
Token information
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 2 in H7.0: (feature 46109)

TOP ACTIVATIONS
MAX = 4.674

this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
US
Token US
Feature activation+4.674
election
Token election
Feature activation+3.408
to
Token to
Feature activation+0.104
help
Token help
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.251
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.019
property
Token property
Feature activation+4.426
tax
Token tax
Feature activation+0.582
bill
Token bill
Feature activation+0.271
by
Token by
Feature activation+0.000
95
Token 95
Feature activation+0.000
percent
Token percent
Feature activation+0.000
someone
Token someone
Feature activation+0.000
else
Token else
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
desk
Token desk
Feature activation+4.038
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.106
.
Token.
Feature activation+0.147
As
Token As
Feature activation+0.000
a
Token a
Feature activation+0.000
is
Token is
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.321
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.480
iPhone
Token iPhone
Feature activation+4.015
.
Token.
Feature activation+0.228
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
(
Token(
Feature activation+0.000
via
Tokenvia
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
first
Token first
Feature activation+4.002
professional
Token professional
Feature activation+0.880
rugby
Token rugby
Feature activation+0.696
league
Token league
Feature activation+0.943
(
Token (
Feature activation+0.040
PRO
TokenPRO
Feature activation+0.000
radio
Token radio
Feature activation+0.000
personality
Token personality
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
former
Token former
Feature activation+3.971
wife
Token wife
Feature activation+2.099
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
control
Tokencontrol
Feature activation+0.000
movement
Token movement
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
other
Token other
Feature activation+3.961
products
Token products
Feature activation+2.279
like
Token like
Feature activation+0.000
they
Token they
Feature activation+0.000
contained
Token contained
Feature activation+0.000
lead
Token lead
Feature activation+0.000
store
Token store
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.276
Ļ
TokenĻ
Feature activation+0.316
s
Tokens
Feature activation+0.000
non
Token non
Feature activation+2.144
fiction
Tokenfiction
Feature activation+3.949
best
Token best
Feature activation+0.635
-
Token-
Feature activation+0.312
seller
Tokenseller
Feature activation+2.728
list
Token list
Feature activation+0.335
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
Assange
Token Assange
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
US
Token US
Feature activation+3.932
legal
Token legal
Feature activation+3.175
representative
Token representative
Feature activation+2.328
,
Token,
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
Mormon
Token Mormon
Feature activation+0.000
community
Token community
Feature activation+0.155
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
all
Token all
Feature activation+3.881
-
Token-
Feature activation+2.305
too
Tokentoo
Feature activation+1.573
-
Token-
Feature activation+0.970
recent
Tokenrecent
Feature activation+2.689
history
Token history
Feature activation+1.172
the
Token the
Feature activation+0.000
DNC
Token DNC
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.422
Ļ
TokenĻ
Feature activation+0.235
s
Tokens
Feature activation+0.165
âĢ
Token âĢ
Feature activation+3.738
ľ
Tokenľ
Feature activation+3.265
V
TokenV
Feature activation+2.733
oter
Tokenoter
Feature activation+1.147
Expansion
Token Expansion
Feature activation+0.532
Data
Token Data
Feature activation+0.078
Vermont
Token Vermont
Feature activation+0.000
senator
Token senator
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
favor
Token favor
Feature activation+3.699
in
Token in
Feature activation+0.148
her
Token her
Feature activation+0.000
home
Token home
Feature activation+0.000
state
Token state
Feature activation+0.000
of
Token of
Feature activation+0.000
band
Token band
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
furiously
Token furiously
Feature activation+2.238
triumphant
Token triumphant
Feature activation+3.670
run
Token run
Feature activation+2.129
of
Token of
Feature activation+0.000
shows
Token shows
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
giant
Token giant
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.512
service
Token service
Feature activation+3.628
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Google
TokenGoogle
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
London
Token London
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
time
Token time
Feature activation+3.460
zone
Token zone
Feature activation+3.580
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
0
Token0
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
Bay
Token Bay
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
city
Token city
Feature activation+3.574
attorney
Token attorney
Feature activation+3.008
,
Token,
Feature activation+0.184
and
Token and
Feature activation+0.019
then
Token then
Feature activation+0.000
-
Token-
Feature activation+0.000
out
Tokenout
Feature activation+0.000
a
Tokena
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
âĢ
Token âĢ
Feature activation+3.473
ľ
Tokenľ
Feature activation+2.518
Central
TokenCentral
Feature activation+1.389
Section
Token Section
Feature activation+0.583
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
be
Token be
Feature activation+0.000
London
Token London
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
time
Token time
Feature activation+3.460
zone
Token zone
Feature activation+3.580
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.027
s
Tokens
Feature activation+0.610
[
Token [
Feature activation+3.063
email
Tokenemail
Feature activation+0.000
provider
Token provider
Feature activation+0.204
]
Token]
Feature activation+3.454
in
Token in
Feature activation+1.669
the
Token the
Feature activation+0.000
course
Token course
Feature activation+0.000
of
Token of
Feature activation+0.000
delivery
Token delivery
Feature activation+0.000
the
Token the
Feature activation+0.000
Administration
Token Administration
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.104
s
Tokens
Feature activation+0.541
Obamacare
Token Obamacare
Feature activation+3.446
talking
Token talking
Feature activation+1.231
points
Token points
Feature activation+2.338
and
Token and
Feature activation+0.000
un
Token un
Feature activation+0.000
confirmed
Tokenconfirmed
Feature activation+0.000

Top DFA by src position
MAX = 4.911

with
Token with
Feature activation+0.002
Top resid features:
this
Token this
Feature activation-0.012
Top resid features:
year
Token year
Feature activation-0.010
Top resid features:
âĢ
TokenâĢ
Feature activation+0.029
Top resid features:
Ļ
TokenĻ
Feature activation+0.067
Top resid features:
s
Tokens
Feature activation+4.911
Top resid features:
US
Token US
Feature activation+0.058
Top resid features:
election
Token election
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
help
Token help
Feature activation+0.000
Top resid features:
Donald
Token Donald
Feature activation+0.000
Top resid features:
cuts
Token cuts
Feature activation+0.008
Top resid features:
this
Token this
Feature activation+0.001
Top resid features:
year
Token year
Feature activation+0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.044
Top resid features:
Ļ
TokenĻ
Feature activation+0.042
Top resid features:
s
Tokens
Feature activation+4.866
Top resid features:
property
Token property
Feature activation+0.013
Top resid features:
tax
Token tax
Feature activation+0.000
Top resid features:
bill
Token bill
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
95
Token 95
Feature activation+0.000
Top resid features:
on
Token on
Feature activation-0.012
Top resid features:
someone
Token someone
Feature activation-0.002
Top resid features:
else
Token else
Feature activation+0.020
Top resid features:
âĢ
TokenâĢ
Feature activation+0.063
Top resid features:
Ļ
TokenĻ
Feature activation+0.074
Top resid features:
s
Tokens
Feature activation+4.354
Top resid features:
desk
Token desk
Feature activation+0.032
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
As
Token As
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.006
Top resid features:
is
Token is
Feature activation-0.007
Top resid features:
Apple
Token Apple
Feature activation+0.024
Top resid features:
âĢ
TokenâĢ
Feature activation+0.073
Top resid features:
Ļ
TokenĻ
Feature activation+0.031
Top resid features:
s
Tokens
Feature activation+4.330
Top resid features:
iPhone
Token iPhone
Feature activation+0.015
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
(
Token(
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.014
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
country
Token country
Feature activation-0.015
Top resid features:
âĢ
TokenâĢ
Feature activation+0.021
Top resid features:
Ļ
TokenĻ
Feature activation+0.069
Top resid features:
s
Tokens
Feature activation+4.329
Top resid features:
first
Token first
Feature activation+0.019
Top resid features:
professional
Token professional
Feature activation+0.000
Top resid features:
rugby
Token rugby
Feature activation+0.000
Top resid features:
league
Token league
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
radio
Token radio
Feature activation+0.015
Top resid features:
personality
Token personality
Feature activation+0.077
Top resid features:
âĢ
TokenâĢ
Feature activation+0.019
Top resid features:
Ļ
TokenĻ
Feature activation+0.061
Top resid features:
s
Tokens
Feature activation+4.268
Top resid features:
former
Token former
Feature activation-0.004
Top resid features:
wife
Token wife
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
control
Tokencontrol
Feature activation-0.034
Top resid features:
movement
Token movement
Feature activation+0.032
Top resid features:
âĢ
TokenâĢ
Feature activation+0.020
Top resid features:
Ļ
TokenĻ
Feature activation+0.052
Top resid features:
s
Tokens
Feature activation+4.401
Top resid features:
other
Token other
Feature activation+0.054
Top resid features:
products
Token products
Feature activation+0.000
Top resid features:
like
Token like
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
contained
Token contained
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.026
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
store
Token store
Feature activation+0.072
Top resid features:
âĢ
TokenâĢ
Feature activation+0.051
Top resid features:
Ļ
TokenĻ
Feature activation+0.011
Top resid features:
s
Tokens
Feature activation+4.234
Top resid features:
non
Token non
Feature activation+0.018
Top resid features:
fiction
Tokenfiction
Feature activation+0.033
Top resid features:
best
Token best
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
seller
Tokenseller
Feature activation+0.000
Top resid features:
ner
Tokenner
Feature activation+0.025
Top resid features:
,
Token,
Feature activation+0.054
Top resid features:
Assange
Token Assange
Feature activation+0.024
Top resid features:
âĢ
TokenâĢ
Feature activation+0.068
Top resid features:
Ļ
TokenĻ
Feature activation+0.061
Top resid features:
s
Tokens
Feature activation+4.201
Top resid features:
US
Token US
Feature activation+0.016
Top resid features:
legal
Token legal
Feature activation+0.000
Top resid features:
representative
Token representative
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
told
Token told
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
Mormon
Token Mormon
Feature activation+0.059
Top resid features:
community
Token community
Feature activation+0.039
Top resid features:
âĢ
TokenâĢ
Feature activation+0.026
Top resid features:
Ļ
TokenĻ
Feature activation+0.017
Top resid features:
s
Tokens
Feature activation+4.116
Top resid features:
all
Token all
Feature activation+0.023
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
too
Tokentoo
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
recent
Tokenrecent
Feature activation+0.000
Top resid features:
was
Token was
Feature activation-0.008
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
DNC
Token DNC
Feature activation+0.035
Top resid features:
âĢ
TokenâĢ
Feature activation+0.023
Top resid features:
Ļ
TokenĻ
Feature activation+0.113
Top resid features:
s
Tokens
Feature activation+3.929
Top resid features:
âĢ
Token âĢ
Feature activation+0.017
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
V
TokenV
Feature activation+0.000
Top resid features:
oter
Tokenoter
Feature activation+0.000
Top resid features:
Expansion
Token Expansion
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
Vermont
Token Vermont
Feature activation+0.007
Top resid features:
senator
Token senator
Feature activation+0.016
Top resid features:
âĢ
TokenâĢ
Feature activation+0.024
Top resid features:
Ļ
TokenĻ
Feature activation+0.120
Top resid features:
s
Tokens
Feature activation+4.044
Top resid features:
favor
Token favor
Feature activation+0.023
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
home
Token home
Feature activation+0.000
Top resid features:
state
Token state
Feature activation+0.000
Top resid features:
for
Token for
Feature activation-0.010
Top resid features:
the
Token the
Feature activation-0.013
Top resid features:
band
Token band
Feature activation+0.026
Top resid features:
âĢ
TokenâĢ
Feature activation+0.033
Top resid features:
Ļ
TokenĻ
Feature activation+0.033
Top resid features:
s
Tokens
Feature activation+4.093
Top resid features:
furiously
Token furiously
Feature activation+0.027
Top resid features:
triumphant
Token triumphant
Feature activation+0.051
Top resid features:
run
Token run
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
shows
Token shows
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
Internet
Token Internet
Feature activation+0.007
Top resid features:
giant
Token giant
Feature activation+0.047
Top resid features:
âĢ
TokenâĢ
Feature activation+0.043
Top resid features:
Ļ
TokenĻ
Feature activation+0.152
Top resid features:
s
Tokens
Feature activation+3.906
Top resid features:
service
Token service
Feature activation+0.047
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Google
TokenGoogle
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.002
Top resid features:
be
Token be
Feature activation-0.025
Top resid features:
London
Token London
Feature activation+0.009
Top resid features:
âĢ
TokenâĢ
Feature activation+0.040
Top resid features:
Ļ
TokenĻ
Feature activation+0.076
Top resid features:
s
Tokens
Feature activation+4.006
Top resid features:
time
Token time
Feature activation+0.029
Top resid features:
zone
Token zone
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
Mor
Token Mor
Feature activation+0.010
Top resid features:
ro
Tokenro
Feature activation-0.011
Top resid features:
Bay
Token Bay
Feature activation+0.012
Top resid features:
âĢ
TokenâĢ
Feature activation+0.041
Top resid features:
Ļ
TokenĻ
Feature activation+0.066
Top resid features:
s
Tokens
Feature activation+3.860
Top resid features:
city
Token city
Feature activation+0.014
Top resid features:
attorney
Token attorney
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
then
Token then
Feature activation+0.000
Top resid features:
Gh
Token Gh
Feature activation-0.007
Top resid features:
out
Tokenout
Feature activation-0.014
Top resid features:
a
Tokena
Feature activation-0.024
Top resid features:
âĢ
TokenâĢ
Feature activation+0.010
Top resid features:
Ļ
TokenĻ
Feature activation+0.090
Top resid features:
s
Tokens
Feature activation+3.714
Top resid features:
âĢ
Token âĢ
Feature activation+0.017
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
Central
TokenCentral
Feature activation+0.000
Top resid features:
Section
Token Section
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
would
Token would
Feature activation-0.009
Top resid features:
be
Token be
Feature activation-0.029
Top resid features:
London
Token London
Feature activation+0.005
Top resid features:
âĢ
TokenâĢ
Feature activation+0.039
Top resid features:
Ļ
TokenĻ
Feature activation+0.064
Top resid features:
s
Tokens
Feature activation+3.980
Top resid features:
time
Token time
Feature activation-0.002
Top resid features:
zone
Token zone
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.041
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
recipient
Token recipient
Feature activation+0.074
Top resid features:
âĢ
TokenâĢ
Feature activation+0.039
Top resid features:
Ļ
TokenĻ
Feature activation+0.023
Top resid features:
s
Tokens
Feature activation+3.679
Top resid features:
[
Token [
Feature activation+0.045
Top resid features:
email
Tokenemail
Feature activation+0.006
Top resid features:
provider
Token provider
Feature activation+0.029
Top resid features:
]
Token]
Feature activation+0.056
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
rot
Tokenrot
Feature activation+0.032
Top resid features:
the
Token the
Feature activation+0.048
Top resid features:
Administration
Token Administration
Feature activation+0.082
Top resid features:
âĢ
TokenâĢ
Feature activation+0.053
Top resid features:
Ļ
TokenĻ
Feature activation+0.040
Top resid features:
s
Tokens
Feature activation+3.494
Top resid features:
Obamacare
Token Obamacare
Feature activation+0.081
Top resid features:
talking
Token talking
Feature activation+0.000
Top resid features:
points
Token points
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
un
Token un
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.58

Head 1: 0.02

Head 2: 0.03

Head 3: 0.07

Head 4: 0.06

Head 5: 0.03

Head 6: 0.02

Head 7: 0.02

Head 8: 0.05

Head 9: 0.06

Head 10: 0.01

Head 11: 0.04

Positive logits

nings2.01

owment1.75

announcement1.70

playbook1.66

acle1.65

declaration1.64

mma1.63

making1.61

lineup1.59

iest1.59

arsenal1.57

portfolio1.56

base1.56

liest1.56

repository1.54

pan1.53

timetable1.53

reservoir1.52

signature1.51

homepage1.51

Negative logits

etheless-1.95

theless-1.84

rarily-1.80

ometimes-1.76

��-1.62

bg-1.48

ocally-1.47

"]=>-1.46

inarily-1.46

anyahu-1.43

ilaterally-1.41

=#-1.39

iably-1.39

mornings-1.39

Leone-1.38

certific-1.38

-1.38

cially-1.38

++)-1.36

itably-1.36

INTERVAL 4.206 - 4.674
CONTAINS 0.000%

this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
US
Token US
Feature activation+4.674
election
Token election
Feature activation+3.408
to
Token to
Feature activation+0.104
help
Token help
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.251
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.019
property
Token property
Feature activation+4.426
tax
Token tax
Feature activation+0.582
bill
Token bill
Feature activation+0.271
by
Token by
Feature activation+0.000
95
Token 95
Feature activation+0.000
percent
Token percent
Feature activation+0.000

INTERVAL 3.739 - 4.206
CONTAINS 0.001%

the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
first
Token first
Feature activation+4.002
professional
Token professional
Feature activation+0.880
rugby
Token rugby
Feature activation+0.696
league
Token league
Feature activation+0.943
(
Token (
Feature activation+0.040
PRO
TokenPRO
Feature activation+0.000
Mormon
Token Mormon
Feature activation+0.000
community
Token community
Feature activation+0.155
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
all
Token all
Feature activation+3.881
-
Token-
Feature activation+2.305
too
Tokentoo
Feature activation+1.573
-
Token-
Feature activation+0.970
recent
Tokenrecent
Feature activation+2.689
history
Token history
Feature activation+1.172
control
Tokencontrol
Feature activation+0.000
movement
Token movement
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
other
Token other
Feature activation+3.961
products
Token products
Feature activation+2.279
like
Token like
Feature activation+0.000
they
Token they
Feature activation+0.000
contained
Token contained
Feature activation+0.000
lead
Token lead
Feature activation+0.000
radio
Token radio
Feature activation+0.000
personality
Token personality
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
former
Token former
Feature activation+3.971
wife
Token wife
Feature activation+2.099
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
,
Token,
Feature activation+0.000
Assange
Token Assange
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
US
Token US
Feature activation+3.932
legal
Token legal
Feature activation+3.175
representative
Token representative
Feature activation+2.328
,
Token,
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 3.272 - 3.739
CONTAINS 0.003%

the
Token the
Feature activation+0.000
Administration
Token Administration
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.104
s
Tokens
Feature activation+0.541
Obamacare
Token Obamacare
Feature activation+3.446
talking
Token talking
Feature activation+1.231
points
Token points
Feature activation+2.338
and
Token and
Feature activation+0.000
un
Token un
Feature activation+0.000
confirmed
Tokenconfirmed
Feature activation+0.000
year
Token year
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
US
Token US
Feature activation+4.674
election
Token election
Feature activation+3.408
to
Token to
Feature activation+0.104
help
Token help
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
secure
Token secure
Feature activation+0.000
OPEC
Token OPEC
Feature activation+0.000
nation
Token nation
Feature activation+0.354
âĢ
TokenâĢ
Feature activation+0.215
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.054
economy
Token economy
Feature activation+3.371
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
most
Token most
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
of
Token of
Feature activation+0.000
Base
Token Base
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
âĢ
Token âĢ
Feature activation+3.329
ľ
Tokenľ
Feature activation+2.555
I
TokenI
Feature activation+1.580
Saw
Token Saw
Feature activation+0.019
the
Token the
Feature activation+0.000
Sign
Token Sign
Feature activation+0.000
ad
Tokenad
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.005
constant
Token constant
Feature activation+3.282
and
Token and
Feature activation+0.098
working
Token working
Feature activation+0.000
out
Token out
Feature activation+0.000
its
Token its
Feature activation+0.000
value
Token value
Feature activation+0.000

INTERVAL 2.804 - 3.272
CONTAINS 0.011%

Mil
Token Mil
Feature activation+0.000
gram
Tokengram
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
study
Token study
Feature activation+3.005
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
conducted
Token conducted
Feature activation+0.000
in
Token in
Feature activation+0.000
Chicago
Token Chicago
Feature activation+0.000
Hank
Token Hank
Feature activation+0.000
Aaron
Token Aaron
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.100
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
all
Token all
Feature activation+2.968
-
Token-
Feature activation+1.429
time
Tokentime
Feature activation+2.663
home
Token home
Feature activation+1.431
run
Token run
Feature activation+1.634
record
Token record
Feature activation+1.462
Bowman
Token Bowman
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
bat
Token bat
Feature activation+1.467
man
Tokenman
Feature activation+2.809
in
Token in
Feature activation+0.115
2016
Token 2016
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
9
Token 9
Feature activation+0.000
rex
Tokenrex
Feature activation+0.000
el
Tokenel
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Center
Token Center
Feature activation+3.106
for
Token for
Feature activation+0.188
Hospital
Token Hospital
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
and
Token and
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
Al
Token Al
Feature activation+0.000
Qaeda
Token Qaeda
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Libyan
Token Libyan
Feature activation+3.169
Islamic
Token Islamic
Feature activation+0.656
Fighting
Token Fighting
Feature activation+0.000
Group
Token Group
Feature activation+2.494
(
Token (
Feature activation+0.069
L
TokenL
Feature activation+0.000

INTERVAL 2.337 - 2.804
CONTAINS 0.028%

No
Token No
Feature activation+0.000
Campaign
Token Campaign
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.060
ridiculous
Token ridiculous
Feature activation+2.457
scare
Token scare
Feature activation+1.049
stories
Token stories
Feature activation+1.004
for
Token for
Feature activation+0.080
fear
Token fear
Feature activation+0.000
of
Token of
Feature activation+0.000
in
Token in
Feature activation+0.000
Indra
Token Indra
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Net
Token Net
Feature activation+2.555
,
Token,
Feature activation+0.521
I
Token I
Feature activation+0.000
should
Token should
Feature activation+0.000
have
Token have
Feature activation+0.000
cited
Token cited
Feature activation+0.000
Egyptian
Token Egyptian
Feature activation+0.000
church
Token church
Feature activation+0.102
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.408
activity
Token activity
Feature activation+2.465
in
Token in
Feature activation+0.831
Africa
Token Africa
Feature activation+0.218
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
region
Token region
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
cities
Token cities
Feature activation+2.420
and
Token and
Feature activation+0.372
ports
Token ports
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
these
Token these
Feature activation+0.000
state
Token state
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
âĢ
Token âĢ
Feature activation+2.508
ľ
Tokenľ
Feature activation+2.370
l
Tokenl
Feature activation+1.281
ax
Tokenax
Feature activation+1.335
gift
Token gift
Feature activation+1.334
laws
Token laws
Feature activation+0.587
.
Token.
Feature activation+0.000

INTERVAL 1.870 - 2.337
CONTAINS 0.055%

in
Token in
Feature activation+0.000
Aleppo
Token Aleppo
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
buzzing
Token buzzing
Feature activation+1.914
Me
Token Me
Feature activation+0.641
idan
Tokenidan
Feature activation+0.905
district
Token district
Feature activation+0.919
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Clinton
TokenClinton
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
campaign
Token campaign
Feature activation+2.324
relied
Token relied
Feature activation+0.000
on
Token on
Feature activation+0.000
small
Token small
Feature activation+0.000
organizing
Token organizing
Feature activation+0.000
,
Token,
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.482
ľ
Tokenľ
Feature activation+1.566
mist
Tokenmist
Feature activation+1.440
ake
Tokenake
Feature activation+2.100
âĢ
TokenâĢ
Feature activation+0.049
Ŀ
TokenĿ
Feature activation+0.102
in
Token in
Feature activation+0.299
leaving
Token leaving
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.203
art
Token art
Feature activation+1.939
editor
Token editor
Feature activation+2.085
informed
Token informed
Feature activation+0.000
him
Token him
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
your
Token your
Feature activation+0.000
child
Token child
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
life
Token life
Feature activation+2.337
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
long
Token long
Feature activation+0.000
term
Token term
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.402 - 1.870
CONTAINS 0.079%

America
Token America
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
heroin
Token heroin
Feature activation+2.138
habit
Token habit
Feature activation+1.570
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
fraught
Token fraught
Feature activation+0.000
ried
Tokenried
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.482
ľ
Tokenľ
Feature activation+1.566
mist
Tokenmist
Feature activation+1.440
ake
Tokenake
Feature activation+2.100
âĢ
TokenâĢ
Feature activation+0.049
Ŀ
TokenĿ
Feature activation+0.102
This
TokenThis
Feature activation+0.000
week
Token week
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Carbon
Token Carbon
Feature activation+1.427
Tracker
Token Tracker
Feature activation+1.657
report
Token report
Feature activation+0.688
comes
Token comes
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
on
Token on
Feature activation+0.000
John
Token John
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
name
Token name
Feature activation+1.619
.
Token.
Feature activation+0.025
If
Token If
Feature activation+0.000
Mark
Token Mark
Feature activation+0.000
had
Token had
Feature activation+0.000
,
Token,
Feature activation+0.000
than
Token than
Feature activation+0.000
Japan
Token Japan
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
$
Token $
Feature activation+1.674
4
Token4
Feature activation+1.548
,
Token,
Feature activation+0.116
157
Token157
Feature activation+1.886
.
Token.
Feature activation+0.000
By
Token By
Feature activation+0.000

INTERVAL 0.935 - 1.402
CONTAINS 0.109%

M
Token M
Feature activation+0.000
addy
Tokenaddy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
other
Token other
Feature activation+1.348
TV
Token TV
Feature activation+0.478
and
Token and
Feature activation+0.239
film
Token film
Feature activation+0.448
credits
Token credits
Feature activation+0.345
including
Token including
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.055
B
Token B
Feature activation+1.979
ior
Tokenior
Feature activation+0.000
ob
Tokenob
Feature activation+0.000
otics
Tokenotics
Feature activation+1.280
Lab
Token Lab
Feature activation+2.493
using
Token using
Feature activation+0.195
Kinect
Token Kinect
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
The
Token The
Feature activation+0.000
area
Token area
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
trails
Token trails
Feature activation+1.153
are
Token are
Feature activation+0.000
used
Token used
Feature activation+0.000
by
Token by
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
share
Token share
Feature activation+0.000
the
Token the
Feature activation+0.046
magazine
Token magazine
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.139
Ļ
TokenĻ
Feature activation+0.889
s
Tokens
Feature activation+0.535
zeal
Token zeal
Feature activation+1.811
for
Token for
Feature activation+0.737
punct
Token punct
Feature activation+0.000
all
Tokenall
Feature activation+0.000
Hor
Token Hor
Feature activation+0.000
an
Tokenan
Feature activation+0.000
'
Token '
Feature activation+0.000
s
Tokens
Feature activation+0.000
tissues
Token tissues
Feature activation+1.084
with
Token with
Feature activation+0.000
Sw
Token Sw
Feature activation+0.000
arov
Tokenarov
Feature activation+0.000
ski
Tokenski
Feature activation+0.000
crystals
Token crystals
Feature activation+0.000

INTERVAL 0.467 - 0.935
CONTAINS 0.167%

O
Token O
Feature activation+0.000
HL
TokenHL
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.188
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
success
Token success
Feature activation+0.752
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
CI
Token CI
Feature activation+0.000
BC
TokenBC
Feature activation+0.000
into
Token into
Feature activation+0.000
Rap
Token Rap
Feature activation+0.000
un
Tokenun
Feature activation+0.000
zel
Tokenzel
Feature activation+0.000
's
Token's
Feature activation+0.000
red
Token red
Feature activation+0.542
eyes
Token eyes
Feature activation+0.000
,
Token,
Feature activation+0.000
puls
Token puls
Feature activation+0.000
ating
Tokenating
Feature activation+0.000
with
Token with
Feature activation+0.000
8
Token 8
Feature activation+0.000
i
Tokeni
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
technology
Token technology
Feature activation+0.585
is
Token is
Feature activation+0.000
being
Token being
Feature activation+0.000
used
Token used
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
Bundes
Token Bundes
Feature activation+0.000
bank
Tokenbank
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
annual
Token annual
Feature activation+0.644
report
Token report
Feature activation+0.249
that
Token that
Feature activation+0.000
killing
Token killing
Feature activation+0.000
off
Token off
Feature activation+0.000
higher
Token higher
Feature activation+0.000
F
Token F
Feature activation+0.000
ET
TokenET
Feature activation+0.000
Ã
TokenÃ
Feature activation+0.000
ĸ
Tokenĸ
Feature activation+0.000
(
Token (
Feature activation+0.000
F
TokenF
Feature activation+0.609
eth
Tokeneth
Feature activation+0.371
ullah
Tokenullah
Feature activation+0.170
ist
Tokenist
Feature activation+0.005
Terror
Token Terror
Feature activation+0.000
Organization
Token Organization
Feature activation+0.000

INTERVAL 0.000 - 0.467
CONTAINS 99.547%

aspect
Token aspect
Feature activation+0.000
till
Token till
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
bit
Tokenbit
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
GNOME
Token GNOME
Feature activation+0.000
dedicated
Token dedicated
Feature activation+0.000
to
Token to
Feature activation+0.000
free
Token free
Feature activation+0.000
expression
Token expression
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
chosen
Token chosen
Feature activation+0.000
to
Token to
Feature activation+0.000
silence
Token silence
Feature activation+0.000
opposition
Token opposition
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
in
Token in
Feature activation+0.000
our
Token our
Feature activation+0.000
democracy
Token democracy
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Many
Token Many
Feature activation+0.000
S
Token S
Feature activation+0.000
outher
Tokenouther
Feature activation+0.000
ners
Tokenners
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
ich
Tokenich
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
His
TokenHis
Feature activation+0.000
executive
Token executive
Feature activation+0.000
experience
Token experience
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
praised
Token praised
Feature activation+0.000
oath
Token oath
Feature activation+0.000
that
Token that
Feature activation+0.000
swear
Token swear
Feature activation+0.000
to
Token to
Feature activation+0.000
protect
Token protect
Feature activation+0.000
,
Token,
Feature activation+0.000
save
Token save
Feature activation+0.000
lives
Token lives
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
the
Token the
Feature activation+0.000
cops
Token cops
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 3 in H7.0: (feature 6223)

TOP ACTIVATIONS
MAX = 4.525

drinking
Token drinking
Feature activation+0.000
water
Token water
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
America
Token America
Feature activation+4.525
's
Token's
Feature activation+1.649
most
Token most
Feature activation+0.167
be
Token be
Feature activation+0.351
league
Tokenleague
Feature activation+0.000
red
Tokenred
Feature activation+1.034
last
Token last
Feature activation+0.000
month
Token month
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
May
Token May
Feature activation+4.397
wood
Tokenwood
Feature activation+4.144
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.079
s
Tokens
Feature activation+3.930
fire
Token fire
Feature activation+0.587
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.968
country
Token country
Feature activation+3.444
âĢ
TokenâĢ
Feature activation+0.742
Ļ
TokenĻ
Feature activation+1.230
s
Tokens
Feature activation+4.294
major
Token major
Feature activation+1.256
clubs
Token clubs
Feature activation+0.676
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.290
tape
Token tape
Feature activation+1.836
âĢ
TokenâĢ
Feature activation+0.262
Ļ
TokenĻ
Feature activation+0.645
s
Tokens
Feature activation+4.280
standout
Token standout
Feature activation+0.181
tracks
Token tracks
Feature activation+0.176
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Berlin
Token Berlin
Feature activation+3.217
âĢ
TokenâĢ
Feature activation+0.150
Ļ
TokenĻ
Feature activation+1.977
s
Tokens
Feature activation+4.251
most
Token most
Feature activation+0.912
culturally
Token culturally
Feature activation+0.000
relevant
Token relevant
Feature activation+0.689
institutions
Token institutions
Feature activation+0.211
âĢĶ
Token âĢĶ
Feature activation+0.000
Ott
Token Ott
Feature activation+0.443
oc
Tokenoc
Feature activation+0.407
at
Tokenat
Feature activation+3.753
âĢ
TokenâĢ
Feature activation+0.215
Ļ
TokenĻ
Feature activation+1.801
s
Tokens
Feature activation+4.167
co
Token co
Feature activation+0.606
-
Token-
Feature activation+0.260
found
Tokenfound
Feature activation+0.174
ers
Tokeners
Feature activation+0.129
,
Token,
Feature activation+0.000
Cro
Token Cro
Feature activation+0.760
ck
Tokenck
Feature activation+0.408
ford
Tokenford
Feature activation+1.473
âĢ
TokenâĢ
Feature activation+0.103
Ļ
TokenĻ
Feature activation+0.750
s
Tokens
Feature activation+4.163
bad
Token bad
Feature activation+0.449
parts
Token parts
Feature activation+0.000
of
Token of
Feature activation+0.000
Javascript
Token Javascript
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
month
Token month
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
May
Token May
Feature activation+4.397
wood
Tokenwood
Feature activation+4.144
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.079
s
Tokens
Feature activation+3.930
fire
Token fire
Feature activation+0.587
houses
Tokenhouses
Feature activation+0.304
the
Token the
Feature activation+0.282
Royal
Token Royal
Feature activation+1.814
Society
Token Society
Feature activation+1.220
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.240
s
Tokens
Feature activation+4.128
most
Token most
Feature activation+0.473
famous
Token famous
Feature activation+0.830
members
Token members
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
Sir
TokenSir
Feature activation+0.000
of
Token of
Feature activation+0.000
Mars
Token Mars
Feature activation+2.249
2020
Token 2020
Feature activation+3.140
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.205
s
Tokens
Feature activation+4.024
main
Token main
Feature activation+0.483
is
Token is
Feature activation+0.000
creating
Token creating
Feature activation+0.000
a
Token a
Feature activation+0.000
cache
Token cache
Feature activation+0.000
of
Token of
Feature activation+0.000
May
Token May
Feature activation+4.397
wood
Tokenwood
Feature activation+4.144
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.079
s
Tokens
Feature activation+3.930
fire
Token fire
Feature activation+0.587
houses
Tokenhouses
Feature activation+0.304
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
new
Token new
Feature activation+0.000
encing
Tokenencing
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Canadian
Token Canadian
Feature activation+3.319
university
Token university
Feature activation+1.964
sport
Token sport
Feature activation+3.888
's
Token's
Feature activation+2.870
longest
Token longest
Feature activation+0.095
-
Token-
Feature activation+0.032
standing
Tokenstanding
Feature activation+0.577
traditions
Token traditions
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
Snyder
Token Snyder
Feature activation+2.286
âĢ
TokenâĢ
Feature activation+0.606
Ļ
TokenĻ
Feature activation+2.020
s
Tokens
Feature activation+3.787
own
Token own
Feature activation+1.702
drawings
Token drawings
Feature activation+0.000
.
Token.
Feature activation+0.000
Or
Token Or
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
of
Token of
Feature activation+0.000
Ott
Token Ott
Feature activation+0.443
oc
Tokenoc
Feature activation+0.407
at
Tokenat
Feature activation+3.753
âĢ
TokenâĢ
Feature activation+0.215
Ļ
TokenĻ
Feature activation+1.801
s
Tokens
Feature activation+4.167
co
Token co
Feature activation+0.606
-
Token-
Feature activation+0.260
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Obama
Token Obama
Feature activation+1.583
âĢ
TokenâĢ
Feature activation+0.372
Ļ
TokenĻ
Feature activation+1.640
s
Tokens
Feature activation+3.718
first
Token first
Feature activation+1.273
acts
Token acts
Feature activation+0.000
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000
launch
Token launch
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.708
world
Token world
Feature activation+3.049
âĢ
TokenâĢ
Feature activation+0.867
Ļ
TokenĻ
Feature activation+1.491
s
Tokens
Feature activation+3.715
biggest
Token biggest
Feature activation+1.003
seed
Token seed
Feature activation+0.000
makers
Token makers
Feature activation+0.444
,
Token,
Feature activation+0.000
Sy
Token Sy
Feature activation+0.000
the
Token the
Feature activation+0.000
rubble
Token rubble
Feature activation+0.000
to
Token to
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Berlin
Token Berlin
Feature activation+3.640
's
Token's
Feature activation+2.253
debris
Token debris
Feature activation+1.236
mountains
Token mountains
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
the
Token the
Feature activation+0.000
help
Token help
Feature activation+0.000
of
Token of
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
Washington
Token Washington
Feature activation+3.532
's
Token's
Feature activation+1.923
most
Token most
Feature activation+0.000
successful
Token successful
Feature activation+0.294
-
Token -
Feature activation+0.073
and
Token and
Feature activation+0.000
modern
Token modern
Feature activation+2.776
courts
Token courts
Feature activation+0.870
hip
Tokenhip
Feature activation+0.774
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+3.466
classic
Token classic
Feature activation+0.351
gamb
Token gamb
Feature activation+0.000
les
Tokenles
Feature activation+0.000
:
Token:
Feature activation+0.000
I
Token I
Feature activation+0.000
incidents
Token incidents
Feature activation+0.000
at
Token at
Feature activation+0.000
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.968
country
Token country
Feature activation+3.444
âĢ
TokenâĢ
Feature activation+0.742
Ļ
TokenĻ
Feature activation+1.230
s
Tokens
Feature activation+4.294
major
Token major
Feature activation+1.256
clubs
Token clubs
Feature activation+0.676

Top DFA by src position
MAX = 5.006

toxic
Token toxic
Feature activation-0.004
Top resid features:
drinking
Token drinking
Feature activation-0.010
Top resid features:
water
Token water
Feature activation-0.015
Top resid features:
in
Token in
Feature activation-0.010
Top resid features:
one
Token one
Feature activation+0.043
Top resid features:
of
Token of
Feature activation+5.006
Top resid features:
America
Token America
Feature activation+0.016
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
league
Tokenleague
Feature activation+0.000
Top resid features:
flag
Token flag
Feature activation+0.002
Top resid features:
last
Token last
Feature activation-0.001
Top resid features:
month
Token month
Feature activation-0.013
Top resid features:
in
Token in
Feature activation-0.004
Top resid features:
one
Token one
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+4.914
Top resid features:
May
Token May
Feature activation-0.002
Top resid features:
wood
Tokenwood
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.004
Top resid features:
recent
Token recent
Feature activation+0.006
Top resid features:
incidents
Token incidents
Feature activation+0.003
Top resid features:
at
Token at
Feature activation+0.005
Top resid features:
two
Token two
Feature activation+0.063
Top resid features:
of
Token of
Feature activation+3.491
Top resid features:
the
Token the
Feature activation+1.135
Top resid features:
country
Token country
Feature activation+0.021
Top resid features:
âĢ
TokenâĢ
Feature activation+0.018
Top resid features:
Ļ
TokenĻ
Feature activation+0.009
Top resid features:
s
Tokens
Feature activation+0.011
Top resid features:
from
Token from
Feature activation-0.001
Top resid features:
W
Token W
Feature activation+0.005
Top resid features:
ale
Tokenale
Feature activation-0.002
Top resid features:
on
Token on
Feature activation-0.004
Top resid features:
one
Token one
Feature activation+0.063
Top resid features:
of
Token of
Feature activation+2.963
Top resid features:
the
Token the
Feature activation+1.636
Top resid features:
tape
Token tape
Feature activation+0.082
Top resid features:
âĢ
TokenâĢ
Feature activation+0.012
Top resid features:
Ļ
TokenĻ
Feature activation-0.005
Top resid features:
s
Tokens
Feature activation+0.013
Top resid features:
occupying
Token occupying
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
theater
Token theater
Feature activation+0.055
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.009
Top resid features:
one
Token one
Feature activation+0.026
Top resid features:
of
Token of
Feature activation+4.450
Top resid features:
Berlin
Token Berlin
Feature activation+0.078
Top resid features:
âĢ
TokenâĢ
Feature activation+0.042
Top resid features:
Ļ
TokenĻ
Feature activation+0.005
Top resid features:
s
Tokens
Feature activation+0.099
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
one
Token one
Feature activation+0.002
Top resid features:
thing
Token thing
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
One
Token One
Feature activation+0.032
Top resid features:
of
Token of
Feature activation+4.555
Top resid features:
Ott
Token Ott
Feature activation+0.006
Top resid features:
oc
Tokenoc
Feature activation-0.000
Top resid features:
at
Tokenat
Feature activation+0.038
Top resid features:
âĢ
TokenâĢ
Feature activation+0.018
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
oid
Tokenoid
Feature activation+0.006
Top resid features:
in
Token in
Feature activation-0.016
Top resid features:
JavaScript
Token JavaScript
Feature activation-0.002
Top resid features:
is
Token is
Feature activation+0.081
Top resid features:
one
Token one
Feature activation+0.048
Top resid features:
of
Token of
Feature activation+4.407
Top resid features:
Cro
Token Cro
Feature activation+0.012
Top resid features:
ck
Tokenck
Feature activation+0.000
Top resid features:
ford
Tokenford
Feature activation+0.024
Top resid features:
âĢ
TokenâĢ
Feature activation+0.057
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
flag
Token flag
Feature activation+0.003
Top resid features:
last
Token last
Feature activation-0.014
Top resid features:
month
Token month
Feature activation-0.013
Top resid features:
in
Token in
Feature activation-0.018
Top resid features:
one
Token one
Feature activation+0.016
Top resid features:
of
Token of
Feature activation+4.658
Top resid features:
May
Token May
Feature activation+0.011
Top resid features:
wood
Tokenwood
Feature activation+0.036
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.023
Top resid features:
motion
Token motion
Feature activation-0.005
Top resid features:
described
Token described
Feature activation-0.007
Top resid features:
by
Token by
Feature activation-0.009
Top resid features:
one
Token one
Feature activation+0.028
Top resid features:
of
Token of
Feature activation+3.521
Top resid features:
the
Token the
Feature activation+1.019
Top resid features:
Royal
Token Royal
Feature activation+0.058
Top resid features:
Society
Token Society
Feature activation+0.022
Top resid features:
âĢ
TokenâĢ
Feature activation+0.014
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
terrain
Token terrain
Feature activation+0.003
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
One
TokenOne
Feature activation+0.016
Top resid features:
of
Token of
Feature activation+4.403
Top resid features:
Mars
Token Mars
Feature activation-0.007
Top resid features:
2020
Token 2020
Feature activation+0.030
Top resid features:
âĢ
TokenâĢ
Feature activation+0.055
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.059
Top resid features:
flag
Token flag
Feature activation-0.000
Top resid features:
last
Token last
Feature activation-0.014
Top resid features:
month
Token month
Feature activation-0.018
Top resid features:
in
Token in
Feature activation-0.037
Top resid features:
one
Token one
Feature activation+0.019
Top resid features:
of
Token of
Feature activation+4.323
Top resid features:
May
Token May
Feature activation-0.023
Top resid features:
wood
Tokenwood
Feature activation+0.061
Top resid features:
âĢ
TokenâĢ
Feature activation+0.043
Top resid features:
Ļ
TokenĻ
Feature activation+0.005
Top resid features:
s
Tokens
Feature activation+0.065
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
is
Token is
Feature activation+0.007
Top resid features:
sil
Token sil
Feature activation-0.008
Top resid features:
encing
Tokenencing
Feature activation-0.053
Top resid features:
one
Token one
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+4.275
Top resid features:
Canadian
Token Canadian
Feature activation+0.071
Top resid features:
university
Token university
Feature activation+0.042
Top resid features:
sport
Token sport
Feature activation+0.013
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
longest
Token longest
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.270
Top resid features:
on
Token on
Feature activation-0.011
Top resid features:
some
Token some
Feature activation+0.033
Top resid features:
of
Token of
Feature activation+4.080
Top resid features:
Snyder
Token Snyder
Feature activation+0.040
Top resid features:
âĢ
TokenâĢ
Feature activation+0.080
Top resid features:
Ļ
TokenĻ
Feature activation+0.021
Top resid features:
s
Tokens
Feature activation+0.008
Top resid features:
own
Token own
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.003
Top resid features:
one
Token one
Feature activation+0.006
Top resid features:
thing
Token thing
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
One
Token One
Feature activation+0.026
Top resid features:
of
Token of
Feature activation+4.249
Top resid features:
Ott
Token Ott
Feature activation-0.010
Top resid features:
oc
Tokenoc
Feature activation+0.007
Top resid features:
at
Tokenat
Feature activation+0.012
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
approach
Token approach
Feature activation+0.042
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Indeed
Token Indeed
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
one
Token one
Feature activation+0.035
Top resid features:
of
Token of
Feature activation+3.929
Top resid features:
Obama
Token Obama
Feature activation+0.053
Top resid features:
âĢ
TokenâĢ
Feature activation+0.025
Top resid features:
Ļ
TokenĻ
Feature activation+0.007
Top resid features:
s
Tokens
Feature activation+0.073
Top resid features:
first
Token first
Feature activation+0.000
Top resid features:
ieg
Tokenieg
Feature activation+0.000
Top resid features:
mann
Tokenmann
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
Two
TokenTwo
Feature activation+0.018
Top resid features:
of
Token of
Feature activation+3.567
Top resid features:
the
Token the
Feature activation+0.519
Top resid features:
world
Token world
Feature activation+0.068
Top resid features:
âĢ
TokenâĢ
Feature activation+0.039
Top resid features:
Ļ
TokenĻ
Feature activation-0.004
Top resid features:
s
Tokens
Feature activation+0.017
Top resid features:
adding
Token adding
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
rubble
Token rubble
Feature activation-0.005
Top resid features:
to
Token to
Feature activation-0.015
Top resid features:
one
Token one
Feature activation+0.007
Top resid features:
of
Token of
Feature activation+4.076
Top resid features:
Berlin
Token Berlin
Feature activation+0.012
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
debris
Token debris
Feature activation+0.000
Top resid features:
mountains
Token mountains
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.005
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
help
Token help
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
some
Token some
Feature activation+0.007
Top resid features:
of
Token of
Feature activation+4.033
Top resid features:
Washington
Token Washington
Feature activation-0.010
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
successful
Token successful
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
correct
Token correct
Feature activation-0.001
Top resid features:
feels
Token feels
Feature activation+0.001
Top resid features:
when
Token when
Feature activation+0.004
Top resid features:
facing
Token facing
Feature activation+0.058
Top resid features:
one
Token one
Feature activation+0.045
Top resid features:
of
Token of
Feature activation+3.704
Top resid features:
modern
Token modern
Feature activation+0.102
Top resid features:
courts
Token courts
Feature activation+0.005
Top resid features:
hip
Tokenhip
Feature activation+0.065
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
Ļ
TokenĻ
Feature activation-0.000
Top resid features:
two
Token two
Feature activation+0.006
Top resid features:
recent
Token recent
Feature activation+0.011
Top resid features:
incidents
Token incidents
Feature activation-0.000
Top resid features:
at
Token at
Feature activation-0.000
Top resid features:
two
Token two
Feature activation+0.058
Top resid features:
of
Token of
Feature activation+2.328
Top resid features:
the
Token the
Feature activation+1.494
Top resid features:
country
Token country
Feature activation+0.005
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.58

Head 1: 0.03

Head 2: 0.03

Head 3: 0.05

Head 4: 0.04

Head 5: 0.04

Head 6: 0.02

Head 7: 0.02

Head 8: 0.09

Head 9: 0.06

Head 10: 0.02

Head 11: 0.02

Positive logits

xes2.10

iest2.01

dest1.95

favourites1.88

pillars1.87

favorites1.80

franchises1.74

avorite1.73

saf1.68

deepest1.68

trademarks1.67

worlds1.63

worst1.61

founders1.60

busiest1.60

darkest1.60

destinations1.57

subsidiaries1.57

len1.55

avenues1.54

Negative logits

keleton-1.74

iggurat-1.62

vation-1.58

olation-1.57

rection-1.57

Presence-1.54

ardless-1.49

eanor-1.47

update-1.46

brawl-1.42

etermination-1.41

Norn-1.40

pointer-1.39

"],"-1.39

epad-1.38

displayText-1.38

outine-1.38

heet-1.37

igation-1.36

united-1.36

INTERVAL 4.072 - 4.525
CONTAINS 0.001%

month
Token month
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
May
Token May
Feature activation+4.397
wood
Tokenwood
Feature activation+4.144
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.079
s
Tokens
Feature activation+3.930
fire
Token fire
Feature activation+0.587
houses
Tokenhouses
Feature activation+0.304
last
Token last
Feature activation+0.000
month
Token month
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
May
Token May
Feature activation+4.397
wood
Tokenwood
Feature activation+4.144
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.079
s
Tokens
Feature activation+3.930
fire
Token fire
Feature activation+0.587
Ott
Token Ott
Feature activation+0.443
oc
Tokenoc
Feature activation+0.407
at
Tokenat
Feature activation+3.753
âĢ
TokenâĢ
Feature activation+0.215
Ļ
TokenĻ
Feature activation+1.801
s
Tokens
Feature activation+4.167
co
Token co
Feature activation+0.606
-
Token-
Feature activation+0.260
found
Tokenfound
Feature activation+0.174
ers
Tokeners
Feature activation+0.129
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.968
country
Token country
Feature activation+3.444
âĢ
TokenâĢ
Feature activation+0.742
Ļ
TokenĻ
Feature activation+1.230
s
Tokens
Feature activation+4.294
major
Token major
Feature activation+1.256
clubs
Token clubs
Feature activation+0.676
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
one
Token one
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Berlin
Token Berlin
Feature activation+3.217
âĢ
TokenâĢ
Feature activation+0.150
Ļ
TokenĻ
Feature activation+1.977
s
Tokens
Feature activation+4.251
most
Token most
Feature activation+0.912
culturally
Token culturally
Feature activation+0.000
relevant
Token relevant
Feature activation+0.689
institutions
Token institutions
Feature activation+0.211
âĢĶ
Token âĢĶ
Feature activation+0.000

INTERVAL 3.620 - 4.072
CONTAINS 0.001%

some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
Snyder
Token Snyder
Feature activation+2.286
âĢ
TokenâĢ
Feature activation+0.606
Ļ
TokenĻ
Feature activation+2.020
s
Tokens
Feature activation+3.787
own
Token own
Feature activation+1.702
drawings
Token drawings
Feature activation+0.000
.
Token.
Feature activation+0.000
Or
Token Or
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
of
Token of
Feature activation+0.000
Ott
Token Ott
Feature activation+0.443
oc
Tokenoc
Feature activation+0.407
at
Tokenat
Feature activation+3.753
âĢ
TokenâĢ
Feature activation+0.215
Ļ
TokenĻ
Feature activation+1.801
s
Tokens
Feature activation+4.167
co
Token co
Feature activation+0.606
-
Token-
Feature activation+0.260
the
Token the
Feature activation+0.000
rubble
Token rubble
Feature activation+0.000
to
Token to
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Berlin
Token Berlin
Feature activation+3.640
's
Token's
Feature activation+2.253
debris
Token debris
Feature activation+1.236
mountains
Token mountains
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
of
Token of
Feature activation+0.000
May
Token May
Feature activation+4.397
wood
Tokenwood
Feature activation+4.144
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.079
s
Tokens
Feature activation+3.930
fire
Token fire
Feature activation+0.587
houses
Tokenhouses
Feature activation+0.304
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
new
Token new
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Obama
Token Obama
Feature activation+1.583
âĢ
TokenâĢ
Feature activation+0.372
Ļ
TokenĻ
Feature activation+1.640
s
Tokens
Feature activation+3.718
first
Token first
Feature activation+1.273
acts
Token acts
Feature activation+0.000
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000
launch
Token launch
Feature activation+0.000

INTERVAL 3.167 - 3.620
CONTAINS 0.002%

BIG
Token BIG
Feature activation+1.088
B
TokenB
Feature activation+0.000
ANG
TokenANG
Feature activation+2.669
âĢ
TokenâĢ
Feature activation+1.420
Ļ
TokenĻ
Feature activation+2.860
s
Tokens
Feature activation+3.286
North
Token North
Feature activation+0.183
American
Token American
Feature activation+0.000
legs
Token legs
Feature activation+0.000
sold
Token sold
Feature activation+0.000
out
Token out
Feature activation+0.000
modern
Token modern
Feature activation+2.776
courts
Token courts
Feature activation+0.870
hip
Tokenhip
Feature activation+0.774
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+3.466
classic
Token classic
Feature activation+0.351
gamb
Token gamb
Feature activation+0.000
les
Tokenles
Feature activation+0.000
:
Token:
Feature activation+0.000
I
Token I
Feature activation+0.000
incidents
Token incidents
Feature activation+0.000
at
Token at
Feature activation+0.000
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.968
country
Token country
Feature activation+3.444
âĢ
TokenâĢ
Feature activation+0.742
Ļ
TokenĻ
Feature activation+1.230
s
Tokens
Feature activation+4.294
major
Token major
Feature activation+1.256
clubs
Token clubs
Feature activation+0.676
of
Token of
Feature activation+0.000
R
Token R
Feature activation+1.731
VA
TokenVA
Feature activation+3.076
Street
Token Street
Feature activation+3.304
Art
Token Art
Feature activation+2.766
Fest
Token Fest
Feature activation+3.300
Organ
Token Organ
Feature activation+0.000
izers
Tokenizers
Feature activation+2.180
)
Token)
Feature activation+0.000
met
Token met
Feature activation+0.000
with
Token with
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.080
Marvel
Token Marvel
Feature activation+2.857
âĢ
TokenâĢ
Feature activation+0.398
Ļ
TokenĻ
Feature activation+1.142
s
Tokens
Feature activation+3.302
most
Token most
Feature activation+0.143
popular
Token popular
Feature activation+0.232
characters
Token characters
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000

INTERVAL 2.715 - 3.167
CONTAINS 0.004%

one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Canadian
Token Canadian
Feature activation+3.319
university
Token university
Feature activation+1.964
sport
Token sport
Feature activation+3.888
's
Token's
Feature activation+2.870
longest
Token longest
Feature activation+0.095
-
Token-
Feature activation+0.032
standing
Tokenstanding
Feature activation+0.577
traditions
Token traditions
Feature activation+0.000
on
Token on
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.708
world
Token world
Feature activation+3.049
âĢ
TokenâĢ
Feature activation+0.867
Ļ
TokenĻ
Feature activation+1.491
s
Tokens
Feature activation+3.715
biggest
Token biggest
Feature activation+1.003
seed
Token seed
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
humanity
Token humanity
Feature activation+2.065
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.168
s
Tokens
Feature activation+2.990
oldest
Token oldest
Feature activation+0.000
,
Token,
Feature activation+0.000
most
Token most
Feature activation+0.000
profound
Token profound
Feature activation+0.165
,
Token,
Feature activation+0.000
V
Token V
Feature activation+0.000
ipers
Tokenipers
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+2.873
string
Token string
Feature activation+0.489
of
Token of
Feature activation+0.073
special
Token special
Feature activation+0.359
versions
Token versions
Feature activation+0.000
designed
Token designed
Feature activation+0.000
the
Token the
Feature activation+0.000
rights
Token rights
Feature activation+0.000
to
Token to
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.080
Marvel
Token Marvel
Feature activation+2.857
âĢ
TokenâĢ
Feature activation+0.398
Ļ
TokenĻ
Feature activation+1.142
s
Tokens
Feature activation+3.302
most
Token most
Feature activation+0.143
popular
Token popular
Feature activation+0.232

INTERVAL 2.262 - 2.715
CONTAINS 0.006%

one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
P
Token P
Feature activation+2.064
ORT
TokenORT
Feature activation+1.970
AL
TokenAL
Feature activation+0.599
's
Token's
Feature activation+2.529
creators
Token creators
Feature activation+1.094
,
Token,
Feature activation+0.439
says
Token says
Feature activation+0.000
they
Token they
Feature activation+0.000
've
Token've
Feature activation+0.000
for
Token for
Feature activation+0.000
each
Token each
Feature activation+0.000
of
Token of
Feature activation+0.000
BIG
Token BIG
Feature activation+1.088
B
TokenB
Feature activation+0.000
ANG
TokenANG
Feature activation+2.669
âĢ
TokenâĢ
Feature activation+1.420
Ļ
TokenĻ
Feature activation+2.860
s
Tokens
Feature activation+3.286
North
Token North
Feature activation+0.183
American
Token American
Feature activation+0.000
of
Token of
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.154
the
Token the
Feature activation+1.749
world
Token world
Feature activation+3.110
's
Token's
Feature activation+2.350
oldest
Token oldest
Feature activation+0.541
maps
Token maps
Feature activation+0.225
has
Token has
Feature activation+0.000
made
Token made
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
steal
Token steal
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
ATM
Token ATM
Feature activation+1.643
Solutions
Token Solutions
Feature activation+2.686
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.026
armored
Token armored
Feature activation+0.596
vans
Token vans
Feature activation+0.000
.
Token.
Feature activation+0.000
Stanley
Token Stanley
Feature activation+0.000
Kay
Token Kay
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
One
TokenOne
Feature activation+0.000
of
Token of
Feature activation+0.000
Spain
Token Spain
Feature activation+2.637
's
Token's
Feature activation+2.466
most
Token most
Feature activation+0.179
high
Token high
Feature activation+0.231
-
Token-
Feature activation+0.000
profile
Tokenprofile
Feature activation+0.558

INTERVAL 1.810 - 2.262
CONTAINS 0.008%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
criticized
Token criticized
Feature activation+0.000
by
Token by
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+1.826
readers
Token readers
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
my
Token my
Feature activation+0.000
we
Token we
Feature activation+0.000
became
Token became
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.420
world
Token world
Feature activation+2.212
âĢ
TokenâĢ
Feature activation+0.459
Ļ
TokenĻ
Feature activation+0.772
s
Tokens
Feature activation+1.919
wealthiest
Token wealthiest
Feature activation+0.469
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Ur
Token Ur
Feature activation+0.944
b
Tokenb
Feature activation+0.201
ana
Tokenana
Feature activation+2.708
's
Token's
Feature activation+1.976
23
Token 23
Feature activation+0.000
precincts
Token precincts
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
all
Token all
Feature activation+0.000
produce
Token produce
Feature activation+0.000
files
Token files
Feature activation+0.000
for
Token for
Feature activation+0.000
eight
Token eight
Feature activation+0.000
of
Token of
Feature activation+0.099
the
Token the
Feature activation+2.160
groups
Token groups
Feature activation+1.014
investigators
Token investigators
Feature activation+0.000
were
Token were
Feature activation+0.000
tracking
Token tracking
Feature activation+0.000
.
Token.
Feature activation+0.000
ale
Tokenale
Feature activation+0.000
on
Token on
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.290
tape
Token tape
Feature activation+1.836
âĢ
TokenâĢ
Feature activation+0.262
Ļ
TokenĻ
Feature activation+0.645
s
Tokens
Feature activation+4.280
standout
Token standout
Feature activation+0.181
tracks
Token tracks
Feature activation+0.176

INTERVAL 1.357 - 1.810
CONTAINS 0.014%

now
Token now
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Library
Token Library
Feature activation+2.225
's
Token's
Feature activation+1.653
most
Token most
Feature activation+0.035
popular
Token popular
Feature activation+0.176
and
Token and
Feature activation+0.000
unique
Token unique
Feature activation+0.000
services
Token services
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
enjoy
Token enjoy
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+1.584
films
Token films
Feature activation+0.430
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
*
Token*
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
region
Token region
Feature activation+1.185
âĢ
TokenâĢ
Feature activation+0.275
Ļ
TokenĻ
Feature activation+0.499
s
Tokens
Feature activation+1.688
national
Token national
Feature activation+0.000
economies
Token economies
Feature activation+0.000
could
Token could
Feature activation+0.000
perform
Token perform
Feature activation+0.000
far
Token far
Feature activation+0.000
same
Token same
Feature activation+0.000
size
Token size
Feature activation+0.000
(
Token (
Feature activation+0.000
one
Tokenone
Feature activation+0.000
of
Token of
Feature activation+0.000
wood
Token wood
Feature activation+1.613
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
lead
Token lead
Feature activation+0.000
).
Token).
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.292
world
Token world
Feature activation+1.700
âĢ
TokenâĢ
Feature activation+0.289
Ļ
TokenĻ
Feature activation+0.528
s
Tokens
Feature activation+1.544
leading
Token leading
Feature activation+0.541
modern
Token modern
Feature activation+0.000
maritime
Token maritime
Feature activation+0.000
technology
Token technology
Feature activation+0.000
manufacturers
Token manufacturers
Feature activation+0.000

INTERVAL 0.905 - 1.357
CONTAINS 0.035%

One
Token One
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.177
wind
Token wind
Feature activation+0.693
sur
Tokensur
Feature activation+0.570
f
Tokenf
Feature activation+0.974
ers
Tokeners
Feature activation+0.000
was
Token was
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
Berlin
Token Berlin
Feature activation+3.217
âĢ
TokenâĢ
Feature activation+0.150
Ļ
TokenĻ
Feature activation+1.977
s
Tokens
Feature activation+4.251
most
Token most
Feature activation+0.912
culturally
Token culturally
Feature activation+0.000
relevant
Token relevant
Feature activation+0.689
institutions
Token institutions
Feature activation+0.211
âĢĶ
Token âĢĶ
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
of
Token of
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.322
worst
Token worst
Feature activation+1.245
shootings
Token shootings
Feature activation+0.406
in
Token in
Feature activation+0.000
American
Token American
Feature activation+0.007
history
Token history
Feature activation+0.164
ford
Tokenford
Feature activation+0.000
became
Token became
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.335
Reg
Token Reg
Feature activation+0.908
ency
Tokenency
Feature activation+1.049
Council
Token Council
Feature activation+1.267
,
Token,
Feature activation+0.365
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.708
world
Token world
Feature activation+3.049
âĢ
TokenâĢ
Feature activation+0.867
Ļ
TokenĻ
Feature activation+1.491
s
Tokens
Feature activation+3.715
biggest
Token biggest
Feature activation+1.003
seed
Token seed
Feature activation+0.000
makers
Token makers
Feature activation+0.444
,
Token,
Feature activation+0.000
Sy
Token Sy
Feature activation+0.000
ng
Tokenng
Feature activation+0.000

INTERVAL 0.452 - 0.905
CONTAINS 0.069%

minutes
Token minutes
Feature activation+0.000
of
Token of
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.336
records
Token records
Feature activation+0.592
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
will
Token will
Feature activation+0.000
probably
Token probably
Feature activation+0.000
spell
Token spell
Feature activation+0.000
northern
Token northern
Feature activation+0.000
Aleppo
Token Aleppo
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.875
border
Token border
Feature activation+1.210
areas
Token areas
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
begun
Token begun
Feature activation+0.000
?
Token?
Feature activation+0.000
Join
Token Join
Feature activation+0.000
three
Token three
Feature activation+0.000
COP
Token COP
Feature activation+0.294
I
TokenI
Feature activation+0.515
OUS
TokenOUS
Feature activation+0.767
engineers
Token engineers
Feature activation+0.144
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
share
Token share
Feature activation+0.000
their
Token their
Feature activation+0.000
said
Token said
Feature activation+0.000
police
Token police
Feature activation+0.000
believed
Token believed
Feature activation+0.000
three
Token three
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.794
four
Token four
Feature activation+0.277
recent
Token recent
Feature activation+0.214
home
Token home
Feature activation+0.000
inv
Token inv
Feature activation+0.000
asions
Tokenasions
Feature activation+0.000
to
Token to
Feature activation+0.000
register
Token register
Feature activation+0.000
at
Token at
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.744
shelters
Token shelters
Feature activation+0.245
so
Token so
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000

INTERVAL 0.000 - 0.452
CONTAINS 99.860%

a
Token a
Feature activation+0.000
platform
Token platform
Feature activation+0.000
to
Token to
Feature activation+0.000
show
Token show
Feature activation+0.000
that
Token that
Feature activation+0.000
far
Token far
Feature activation+0.000
from
Token from
Feature activation+0.000
being
Token being
Feature activation+0.000
a
Token a
Feature activation+0.000
gay
Token gay
Feature activation+0.000
Gordon
Token Gordon
Feature activation+0.000
how
Token how
Feature activation+0.000
long
Token long
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
doing
Token doing
Feature activation+0.000
this
Token this
Feature activation+0.000
parameters
Token parameters
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
enforced
Token enforced
Feature activation+0.000
:
Token:
Feature activation+0.000
-
Token -
Feature activation+0.000
O
TokenO
Feature activation+0.000
bey
Tokenbey
Feature activation+0.000
the
Token the
Feature activation+0.000
instructions
Token instructions
Feature activation+0.000
of
Token of
Feature activation+0.000
Morris
Token Morris
Feature activation+0.000
sey
Tokensey
Feature activation+0.000
is
Token is
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
be
Tokenbe
Feature activation+0.000
yond
Tokenyond
Feature activation+0.000
ecstatic
Token ecstatic
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
with
Token with
Feature activation+0.000
dog
Token dog
Feature activation+0.000
?
Token?
Feature activation+0.000
Try
TokenTry
Feature activation+0.000
to
Token to
Feature activation+0.000
guess
Token guess
Feature activation+0.000
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
child
Token child
Feature activation+0.000
has
Token has
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 4 in H7.0: (feature 47699)

TOP ACTIVATIONS
MAX = 3.758

,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
usually
Token usually
Feature activation+0.000
peac
Token peac
Feature activation+2.371
ocking
Tokenocking
Feature activation+3.758
Wire
Token Wire
Feature activation+0.000
removes
Token removes
Feature activation+0.000
his
Token his
Feature activation+0.000
sunglasses
Token sunglasses
Feature activation+0.000
to
Token to
Feature activation+0.000
Den
Token Den
Feature activation+0.000
z
Tokenz
Feature activation+0.000
's
Token's
Feature activation+0.000
tough
Token tough
Feature activation+0.000
and
Token and
Feature activation+0.000
ten
Token ten
Feature activation+3.610
acious
Tokenacious
Feature activation+0.000
character
Token character
Feature activation+0.000
in
Token in
Feature activation+0.000
"
Token "
Feature activation+0.000
B
TokenB
Feature activation+0.000
funny
Token funny
Feature activation+0.000
but
Token but
Feature activation+0.000
at
Token at
Feature activation+2.346
the
Token the
Feature activation+1.136
same
Token same
Feature activation+0.981
time
Token time
Feature activation+3.550
st
Token st
Feature activation+1.557
inging
Tokeninging
Feature activation+1.072
ev
Token ev
Feature activation+0.000
is
Tokenis
Feature activation+0.000
cer
Tokencer
Feature activation+0.000
control
Token control
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
beautiful
Token beautiful
Feature activation+0.000
,
Token,
Feature activation+0.000
life
Token life
Feature activation+3.510
-
Token-
Feature activation+2.004
like
Tokenlike
Feature activation+0.719
robot
Token robot
Feature activation+0.000
assassin
Token assassin
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
uns
Token uns
Feature activation+0.000
aid
Tokenaid
Feature activation+0.000
,
Token,
Feature activation+0.000
dri
Token dri
Feature activation+0.604
ps
Tokenps
Feature activation+3.497
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
p
Token p
Feature activation+0.000
ours
Tokenours
Feature activation+0.000
out
Token out
Feature activation+0.000
India
Token India
Feature activation+0.000
-
Token-
Feature activation+0.000
born
Tokenborn
Feature activation+0.000
,
Token,
Feature activation+0.000
South
Token South
Feature activation+3.123
Carolina
Token Carolina
Feature activation+3.464
-
Token-
Feature activation+1.528
based
Tokenbased
Feature activation+0.000
gastro
Token gastro
Feature activation+0.000
enter
Tokenenter
Feature activation+0.000
ologist
Tokenologist
Feature activation+0.013
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
compliant
Token compliant
Feature activation+0.000
,
Token,
Feature activation+0.000
fore
Token fore
Feature activation+2.472
lock
Tokenlock
Feature activation+3.421
-
Token-
Feature activation+3.186
t
Tokent
Feature activation+2.249
ug
Tokenug
Feature activation+0.523
ging
Tokenging
Feature activation+0.246
citizen
Token citizen
Feature activation+0.000
Gothic
Token Gothic
Feature activation+1.793
monuments
Token monuments
Feature activation+0.020
among
Token among
Feature activation+0.000
lush
Token lush
Feature activation+0.000
,
Token,
Feature activation+0.000
tree
Token tree
Feature activation+3.361
-
Token-
Feature activation+0.995
lined
Tokenlined
Feature activation+0.000
paths
Token paths
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
chronic
Token chronic
Feature activation+0.000
,
Token,
Feature activation+0.000
active
Token active
Feature activation+0.086
,
Token,
Feature activation+0.000
ul
Token ul
Feature activation+1.207
cer
Tokencer
Feature activation+3.236
ative
Tokenative
Feature activation+1.512
,
Token,
Feature activation+0.000
infectious
Token infectious
Feature activation+0.391
disease
Token disease
Feature activation+0.336
.
Token.
Feature activation+0.000
anarchist
Token anarchist
Feature activation+0.000
organizing
Token organizing
Feature activation+0.000
to
Token to
Feature activation+0.000
authoritative
Token authoritative
Feature activation+0.000
and
Token and
Feature activation+0.000
government
Token government
Feature activation+3.222
controlled
Token controlled
Feature activation+0.761
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
paper
Token paper
Feature activation+0.000
will
Token will
Feature activation+0.000
a
Token a
Feature activation+0.000
compliant
Token compliant
Feature activation+0.000
,
Token,
Feature activation+0.000
fore
Token fore
Feature activation+2.472
lock
Tokenlock
Feature activation+3.421
-
Token-
Feature activation+3.186
t
Tokent
Feature activation+2.249
ug
Tokenug
Feature activation+0.523
ging
Tokenging
Feature activation+0.246
citizen
Token citizen
Feature activation+0.000
ry
Tokenry
Feature activation+0.000
(
Token (
Feature activation+0.000
despite
Tokendespite
Feature activation+0.000
the
Token the
Feature activation+0.000
anticipated
Token anticipated
Feature activation+0.000
,
Token,
Feature activation+0.000
sub
Token sub
Feature activation+3.126
par
Tokenpar
Feature activation+0.176
record
Token record
Feature activation+0.000
).
Token).
Feature activation+0.000
Here
Token Here
Feature activation+0.000
are
Token are
Feature activation+0.000
The
Token The
Feature activation+0.000
India
Token India
Feature activation+0.000
-
Token-
Feature activation+0.000
born
Tokenborn
Feature activation+0.000
,
Token,
Feature activation+0.000
South
Token South
Feature activation+3.123
Carolina
Token Carolina
Feature activation+3.464
-
Token-
Feature activation+1.528
based
Tokenbased
Feature activation+0.000
gastro
Token gastro
Feature activation+0.000
enter
Tokenenter
Feature activation+0.000
added
Token added
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
previously
Token previously
Feature activation+0.000
gluten
Token gluten
Feature activation+2.922
-
Token-
Feature activation+3.001
free
Tokenfree
Feature activation+1.152
diet
Token diet
Feature activation+0.000
,
Token,
Feature activation+0.000
caused
Token caused
Feature activation+0.000
gastrointestinal
Token gastrointestinal
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
nearly
Token nearly
Feature activation+0.026
39
Token 39
Feature activation+0.547
,
Token,
Feature activation+2.998
000
Token000
Feature activation+0.000
applicants
Token applicants
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
University
Token University
Feature activation+0.000
sim
Tokensim
Feature activation+0.058
pl
Tokenpl
Feature activation+0.000
istic
Tokenistic
Feature activation+0.018
and
Token and
Feature activation+0.000
under
Token under
Feature activation+2.354
-
Token-
Feature activation+2.937
developed
Tokendeveloped
Feature activation+0.188
"
Token"
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
added
Token added
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
previously
Token previously
Feature activation+0.000
gluten
Token gluten
Feature activation+2.922
-
Token-
Feature activation+3.001
free
Tokenfree
Feature activation+1.152
diet
Token diet
Feature activation+0.000
,
Token,
Feature activation+0.000
caused
Token caused
Feature activation+0.000
,
Token,
Feature activation+0.000
despite
Token despite
Feature activation+0.000
the
Token the
Feature activation+0.000
by
Token by
Feature activation+0.000
now
Token now
Feature activation+0.000
very
Token very
Feature activation+2.912
-
Token-
Feature activation+1.127
well
Tokenwell
Feature activation+1.886
-
Token-
Feature activation+1.684
known
Tokenknown
Feature activation+2.205
shortcomings
Token shortcomings
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
(
Token (
Feature activation+0.000
increasing
Tokenincreasing
Feature activation+2.287
ly
Tokenly
Feature activation+2.153
trademark
Token trademark
Feature activation+2.906
)
Token)
Feature activation+0.046
cynical
Token cynical
Feature activation+0.000
window
Token window
Feature activation+0.000
dressing
Token dressing
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
equally
Token equally
Feature activation+0.000
organised
Token organised
Feature activation+1.670
,
Token,
Feature activation+1.180
similarly
Token similarly
Feature activation+0.066
technological
Token technological
Feature activation+2.901
Rebellion
Token Rebellion
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000

Top DFA by src position
MAX = 4.055

Walking
Token Walking
Feature activation-0.004
Top resid features:
Abortion
Token Abortion
Feature activation-0.016
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.014
Top resid features:
usually
Token usually
Feature activation+4.055
Top resid features:
peac
Token peac
Feature activation+0.015
Top resid features:
ocking
Tokenocking
Feature activation+0.045
Top resid features:
Wire
Token Wire
Feature activation+0.000
Top resid features:
removes
Token removes
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
shape
Token shape
Feature activation+0.001
Top resid features:
Den
Token Den
Feature activation+0.001
Top resid features:
z
Tokenz
Feature activation-0.003
Top resid features:
's
Token's
Feature activation+0.001
Top resid features:
tough
Token tough
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+3.898
Top resid features:
ten
Token ten
Feature activation+0.006
Top resid features:
acious
Tokenacious
Feature activation+0.000
Top resid features:
character
Token character
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
writes
Token writes
Feature activation-0.020
Top resid features:
an
Token an
Feature activation+0.002
Top resid features:
uproar
Token uproar
Feature activation-0.039
Top resid features:
iously
Tokeniously
Feature activation+0.053
Top resid features:
funny
Token funny
Feature activation-0.031
Top resid features:
but
Token but
Feature activation+4.027
Top resid features:
at
Token at
Feature activation-0.008
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
same
Token same
Feature activation-0.019
Top resid features:
time
Token time
Feature activation-0.037
Top resid features:
st
Token st
Feature activation+0.000
Top resid features:
takes
Token takes
Feature activation-0.004
Top resid features:
control
Token control
Feature activation+0.002
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.015
Top resid features:
beautiful
Token beautiful
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+3.802
Top resid features:
life
Token life
Feature activation+0.006
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
like
Tokenlike
Feature activation+0.000
Top resid features:
robot
Token robot
Feature activation+0.000
Top resid features:
assassin
Token assassin
Feature activation+0.000
Top resid features:
open
Token open
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.022
Top resid features:
The
Token The
Feature activation-0.015
Top resid features:
uns
Token uns
Feature activation+0.015
Top resid features:
aid
Tokenaid
Feature activation+0.036
Top resid features:
,
Token,
Feature activation+3.694
Top resid features:
dri
Token dri
Feature activation+0.197
Top resid features:
ps
Tokenps
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
then
Token then
Feature activation+0.000
Top resid features:
p
Token p
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
The
Token The
Feature activation+0.003
Top resid features:
India
Token India
Feature activation+0.005
Top resid features:
-
Token-
Feature activation-0.014
Top resid features:
born
Tokenborn
Feature activation-0.020
Top resid features:
,
Token,
Feature activation+3.720
Top resid features:
South
Token South
Feature activation+0.014
Top resid features:
Carolina
Token Carolina
Feature activation+0.009
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
based
Tokenbased
Feature activation+0.000
Top resid features:
gastro
Token gastro
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
expect
Token expect
Feature activation-0.000
Top resid features:
from
Token from
Feature activation+0.001
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
compliant
Token compliant
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+3.749
Top resid features:
fore
Token fore
Feature activation+0.033
Top resid features:
lock
Tokenlock
Feature activation+0.031
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
ug
Tokenug
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.061
Top resid features:
Gothic
Token Gothic
Feature activation-0.003
Top resid features:
monuments
Token monuments
Feature activation+0.005
Top resid features:
among
Token among
Feature activation-0.006
Top resid features:
lush
Token lush
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+3.625
Top resid features:
tree
Token tree
Feature activation-0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
lined
Tokenlined
Feature activation+0.000
Top resid features:
paths
Token paths
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
have
Token have
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.016
Top resid features:
chronic
Token chronic
Feature activation+0.030
Top resid features:
,
Token,
Feature activation+0.921
Top resid features:
active
Token active
Feature activation-0.023
Top resid features:
,
Token,
Feature activation+2.609
Top resid features:
ul
Token ul
Feature activation+0.052
Top resid features:
cer
Tokencer
Feature activation+0.004
Top resid features:
ative
Tokenative
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
infectious
Token infectious
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.004
Top resid features:
anarchist
Token anarchist
Feature activation+0.001
Top resid features:
organizing
Token organizing
Feature activation-0.009
Top resid features:
to
Token to
Feature activation-0.022
Top resid features:
authoritative
Token authoritative
Feature activation+0.028
Top resid features:
and
Token and
Feature activation+3.583
Top resid features:
government
Token government
Feature activation+0.012
Top resid features:
controlled
Token controlled
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
This
Token This
Feature activation+0.000
Top resid features:
paper
Token paper
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
expect
Token expect
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.001
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
compliant
Token compliant
Feature activation-0.023
Top resid features:
,
Token,
Feature activation+3.552
Top resid features:
fore
Token fore
Feature activation+0.015
Top resid features:
lock
Tokenlock
Feature activation-0.020
Top resid features:
-
Token-
Feature activation+0.011
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
ug
Tokenug
Feature activation+0.000
Top resid features:
results
Token results
Feature activation-0.007
Top resid features:
(
Token (
Feature activation-0.009
Top resid features:
despite
Tokendespite
Feature activation-0.006
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
anticipated
Token anticipated
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+3.418
Top resid features:
sub
Token sub
Feature activation+0.014
Top resid features:
par
Tokenpar
Feature activation+0.000
Top resid features:
record
Token record
Feature activation+0.000
Top resid features:
).
Token).
Feature activation+0.000
Top resid features:
Here
Token Here
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
Token The
Feature activation-0.001
Top resid features:
India
Token India
Feature activation-0.009
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
born
Tokenborn
Feature activation-0.038
Top resid features:
,
Token,
Feature activation+3.475
Top resid features:
South
Token South
Feature activation+0.005
Top resid features:
Carolina
Token Carolina
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
based
Tokenbased
Feature activation+0.000
Top resid features:
gastro
Token gastro
Feature activation+0.000
Top resid features:
gluten
Token gluten
Feature activation-0.008
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
added
Token added
Feature activation+0.006
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
previously
Token previously
Feature activation+3.241
Top resid features:
gluten
Token gluten
Feature activation+0.084
Top resid features:
-
Token-
Feature activation+0.016
Top resid features:
free
Tokenfree
Feature activation+0.000
Top resid features:
diet
Token diet
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
7
Token7
Feature activation-0.024
Top resid features:
percent
Token percent
Feature activation+0.013
Top resid features:
of
Token of
Feature activation-0.007
Top resid features:
their
Token their
Feature activation-0.012
Top resid features:
nearly
Token nearly
Feature activation+3.401
Top resid features:
39
Token 39
Feature activation-0.015
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
000
Token000
Feature activation+0.000
Top resid features:
applicants
Token applicants
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.007
Top resid features:
"
Token "
Feature activation+0.008
Top resid features:
sim
Tokensim
Feature activation-0.002
Top resid features:
pl
Tokenpl
Feature activation+0.011
Top resid features:
istic
Tokenistic
Feature activation+0.012
Top resid features:
and
Token and
Feature activation+3.224
Top resid features:
under
Token under
Feature activation+0.041
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
developed
Tokendeveloped
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
understanding
Token understanding
Feature activation+0.000
Top resid features:
gluten
Token gluten
Feature activation-0.005
Top resid features:
,
Token,
Feature activation-0.024
Top resid features:
added
Token added
Feature activation+0.017
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
a
Token a
Feature activation+0.010
Top resid features:
previously
Token previously
Feature activation+3.223
Top resid features:
gluten
Token gluten
Feature activation+0.020
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
free
Tokenfree
Feature activation+0.000
Top resid features:
diet
Token diet
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
since
Token since
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
despite
Token despite
Feature activation-0.033
Top resid features:
the
Token the
Feature activation-0.013
Top resid features:
by
Token by
Feature activation+0.023
Top resid features:
now
Token now
Feature activation+3.180
Top resid features:
very
Token very
Feature activation+0.031
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
well
Tokenwell
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
known
Tokenknown
Feature activation+0.000
Top resid features:
instead
Token instead
Feature activation-0.005
Top resid features:
of
Token of
Feature activation+0.021
Top resid features:
his
Token his
Feature activation+0.007
Top resid features:
(
Token (
Feature activation+0.671
Top resid features:
increasing
Tokenincreasing
Feature activation-0.012
Top resid features:
ly
Tokenly
Feature activation+2.519
Top resid features:
trademark
Token trademark
Feature activation+0.025
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
cynical
Token cynical
Feature activation+0.000
Top resid features:
window
Token window
Feature activation+0.000
Top resid features:
dressing
Token dressing
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.017
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
equally
Token equally
Feature activation+0.943
Top resid features:
organised
Token organised
Feature activation+0.039
Top resid features:
,
Token,
Feature activation+0.510
Top resid features:
similarly
Token similarly
Feature activation+1.830
Top resid features:
technological
Token technological
Feature activation+0.023
Top resid features:
Rebellion
Token Rebellion
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.58

Head 1: 0.02

Head 2: 0.03

Head 3: 0.05

Head 4: 0.07

Head 5: 0.05

Head 6: 0.04

Head 7: 0.02

Head 8: 0.07

Head 9: 0.04

Head 10: 0.01

Head 11: 0.02

Positive logits

less2.14

emic2.09

hearted2.07

isable2.06

ishable2.03

iless2.01

izable1.95

oriented1.94

erous1.93

humane1.88

-)1.84

able1.84

porous1.84

-1.84

kish1.83

"-1.82

istic1.80

sounding1.79

FUL1.78

flavored1.78

Negative logits

ynthesis-1.99

stals-1.84

afety-1.62

ramids-1.62

="#-1.60

urus-1.59

aea-1.59

Publishers-1.57

clerosis-1.56

azines-1.55

ptions-1.54

anners-1.50

Taxes-1.50

Registration-1.48

gdala-1.47

ionics-1.46

Calculator-1.46

BILITIES-1.44

eeks-1.43

atism-1.43

INTERVAL 3.382 - 3.758
CONTAINS 0.001%

The
Token The
Feature activation+0.000
uns
Token uns
Feature activation+0.000
aid
Tokenaid
Feature activation+0.000
,
Token,
Feature activation+0.000
dri
Token dri
Feature activation+0.604
ps
Tokenps
Feature activation+3.497
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
p
Token p
Feature activation+0.000
ours
Tokenours
Feature activation+0.000
out
Token out
Feature activation+0.000
funny
Token funny
Feature activation+0.000
but
Token but
Feature activation+0.000
at
Token at
Feature activation+2.346
the
Token the
Feature activation+1.136
same
Token same
Feature activation+0.981
time
Token time
Feature activation+3.550
st
Token st
Feature activation+1.557
inging
Tokeninging
Feature activation+1.072
ev
Token ev
Feature activation+0.000
is
Tokenis
Feature activation+0.000
cer
Tokencer
Feature activation+0.000
Den
Token Den
Feature activation+0.000
z
Tokenz
Feature activation+0.000
's
Token's
Feature activation+0.000
tough
Token tough
Feature activation+0.000
and
Token and
Feature activation+0.000
ten
Token ten
Feature activation+3.610
acious
Tokenacious
Feature activation+0.000
character
Token character
Feature activation+0.000
in
Token in
Feature activation+0.000
"
Token "
Feature activation+0.000
B
TokenB
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
usually
Token usually
Feature activation+0.000
peac
Token peac
Feature activation+2.371
ocking
Tokenocking
Feature activation+3.758
Wire
Token Wire
Feature activation+0.000
removes
Token removes
Feature activation+0.000
his
Token his
Feature activation+0.000
sunglasses
Token sunglasses
Feature activation+0.000
to
Token to
Feature activation+0.000
India
Token India
Feature activation+0.000
-
Token-
Feature activation+0.000
born
Tokenborn
Feature activation+0.000
,
Token,
Feature activation+0.000
South
Token South
Feature activation+3.123
Carolina
Token Carolina
Feature activation+3.464
-
Token-
Feature activation+1.528
based
Tokenbased
Feature activation+0.000
gastro
Token gastro
Feature activation+0.000
enter
Tokenenter
Feature activation+0.000
ologist
Tokenologist
Feature activation+0.013

INTERVAL 3.006 - 3.382
CONTAINS 0.001%

anarchist
Token anarchist
Feature activation+0.000
organizing
Token organizing
Feature activation+0.000
to
Token to
Feature activation+0.000
authoritative
Token authoritative
Feature activation+0.000
and
Token and
Feature activation+0.000
government
Token government
Feature activation+3.222
controlled
Token controlled
Feature activation+0.761
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
paper
Token paper
Feature activation+0.000
will
Token will
Feature activation+0.000
(
Token (
Feature activation+0.000
despite
Tokendespite
Feature activation+0.000
the
Token the
Feature activation+0.000
anticipated
Token anticipated
Feature activation+0.000
,
Token,
Feature activation+0.000
sub
Token sub
Feature activation+3.126
par
Tokenpar
Feature activation+0.176
record
Token record
Feature activation+0.000
).
Token).
Feature activation+0.000
Here
Token Here
Feature activation+0.000
are
Token are
Feature activation+0.000
chronic
Token chronic
Feature activation+0.000
,
Token,
Feature activation+0.000
active
Token active
Feature activation+0.086
,
Token,
Feature activation+0.000
ul
Token ul
Feature activation+1.207
cer
Tokencer
Feature activation+3.236
ative
Tokenative
Feature activation+1.512
,
Token,
Feature activation+0.000
infectious
Token infectious
Feature activation+0.391
disease
Token disease
Feature activation+0.336
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
compliant
Token compliant
Feature activation+0.000
,
Token,
Feature activation+0.000
fore
Token fore
Feature activation+2.472
lock
Tokenlock
Feature activation+3.421
-
Token-
Feature activation+3.186
t
Tokent
Feature activation+2.249
ug
Tokenug
Feature activation+0.523
ging
Tokenging
Feature activation+0.246
citizen
Token citizen
Feature activation+0.000
ry
Tokenry
Feature activation+0.000
Gothic
Token Gothic
Feature activation+1.793
monuments
Token monuments
Feature activation+0.020
among
Token among
Feature activation+0.000
lush
Token lush
Feature activation+0.000
,
Token,
Feature activation+0.000
tree
Token tree
Feature activation+3.361
-
Token-
Feature activation+0.995
lined
Tokenlined
Feature activation+0.000
paths
Token paths
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000

INTERVAL 2.631 - 3.006
CONTAINS 0.002%

engaged
Token engaged
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
serious
Token serious
Feature activation+0.000
,
Token,
Feature activation+0.000
heart
Token heart
Feature activation+2.705
-
Token-
Feature activation+1.164
w
Tokenw
Feature activation+0.532
rench
Tokenrench
Feature activation+1.600
ing
Tokening
Feature activation+0.000
process
Token process
Feature activation+0.000
,
Token,
Feature activation+0.000
added
Token added
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
previously
Token previously
Feature activation+0.000
gluten
Token gluten
Feature activation+2.922
-
Token-
Feature activation+3.001
free
Tokenfree
Feature activation+1.152
diet
Token diet
Feature activation+0.000
,
Token,
Feature activation+0.000
caused
Token caused
Feature activation+0.000
winter
Token winter
Feature activation+0.000
.
Token.
Feature activation+0.000
Bring
Token Bring
Feature activation+0.000
new
Token new
Feature activation+0.000
or
Token or
Feature activation+0.000
gently
Token gently
Feature activation+2.643
used
Token used
Feature activation+0.000
coats
Token coats
Feature activation+0.000
,
Token,
Feature activation+0.000
m
Token m
Feature activation+0.000
ittens
Tokenittens
Feature activation+0.000
added
Token added
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
previously
Token previously
Feature activation+0.000
gluten
Token gluten
Feature activation+2.922
-
Token-
Feature activation+3.001
free
Tokenfree
Feature activation+1.152
diet
Token diet
Feature activation+0.000
,
Token,
Feature activation+0.000
caused
Token caused
Feature activation+0.000
gastrointestinal
Token gastrointestinal
Feature activation+0.000
the
Token the
Feature activation+0.000
slick
Token slick
Feature activation+0.000
-
Token-
Feature activation+0.000
looking
Tokenlooking
Feature activation+0.000
and
Token and
Feature activation+0.000
budget
Token budget
Feature activation+2.636
friendly
Token friendly
Feature activation+0.000
New
Token New
Feature activation+0.000
Nintendo
Token Nintendo
Feature activation+0.000
2
Token 2
Feature activation+0.000
DS
TokenDS
Feature activation+0.000

INTERVAL 2.255 - 2.631
CONTAINS 0.008%

an
Token an
Feature activation+0.000
uproar
Token uproar
Feature activation+0.000
iously
Tokeniously
Feature activation+0.000
funny
Token funny
Feature activation+0.000
but
Token but
Feature activation+0.000
at
Token at
Feature activation+2.346
the
Token the
Feature activation+1.136
same
Token same
Feature activation+0.981
time
Token time
Feature activation+3.550
st
Token st
Feature activation+1.557
inging
Tokeninging
Feature activation+1.072
.
Token.
Feature activation+0.000
Good
Token Good
Feature activation+0.000
old
Token old
Feature activation+0.000
fashioned
Token fashioned
Feature activation+0.000
,
Token,
Feature activation+0.000
shoe
Token shoe
Feature activation+2.470
leather
Token leather
Feature activation+1.677
,
Token,
Feature activation+0.000
hitting
Token hitting
Feature activation+0.000
the
Token the
Feature activation+0.000
phones
Token phones
Feature activation+0.000
He
Token He
Feature activation+0.000
offered
Token offered
Feature activation+0.000
a
Token a
Feature activation+0.000
bold
Token bold
Feature activation+0.000
,
Token,
Feature activation+0.000
Libertarian
Token Libertarian
Feature activation+2.356
agenda
Token agenda
Feature activation+0.000
while
Token while
Feature activation+0.000
exposing
Token exposing
Feature activation+0.000
the
Token the
Feature activation+0.000
Big
Token Big
Feature activation+0.000
someone
Token someone
Feature activation+0.000
caught
Token caught
Feature activation+0.000
a
Token a
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000
,
Token,
Feature activation+0.000
cut
Token cut
Feature activation+2.274
er
Tokener
Feature activation+0.000
blue
Token blue
Feature activation+0.000
dragon
Token dragon
Feature activation+0.000
called
Token called
Feature activation+0.000
a
Token a
Feature activation+0.000
success
Token success
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
largely
Token largely
Feature activation+0.000
Asian
Token Asian
Feature activation+2.708
-
Token-
Feature activation+2.585
American
TokenAmerican
Feature activation+1.220
viewership
Token viewership
Feature activation+0.000
eager
Token eager
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000

INTERVAL 1.879 - 2.255
CONTAINS 0.011%

funny
Token funny
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.208
sometimes
Token sometimes
Feature activation+0.666
heart
Token heart
Feature activation+2.370
-
Token-
Feature activation+2.174
w
Tokenw
Feature activation+0.711
rench
Tokenrench
Feature activation+2.518
ing
Tokening
Feature activation+0.184
pieces
Token pieces
Feature activation+0.000
this
Token this
Feature activation+0.000
reliable
Token reliable
Feature activation+0.000
,
Token,
Feature activation+0.000
ordered
Token ordered
Feature activation+0.000
and
Token and
Feature activation+0.000
error
Token error
Feature activation+2.325
-
Token-
Feature activation+2.077
checked
Tokenchecked
Feature activation+0.000
delivery
Token delivery
Feature activation+0.000
of
Token of
Feature activation+0.000
data
Token data
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
particularly
Token particularly
Feature activation+0.000
f
Token f
Feature activation+2.016
ussy
Tokenussy
Feature activation+0.000
eater
Token eater
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+0.000
bit
Token bit
Feature activation+0.000
of
Token of
Feature activation+0.000
heavily
Token heavily
Feature activation+0.000
means
Token means
Feature activation+2.098
-
Token-
Feature activation+0.658
tested
Tokentested
Feature activation+0.000
welfare
Token welfare
Feature activation+0.000
programs
Token programs
Feature activation+0.000
so
Token so
Feature activation+0.000
orn
Token orn
Feature activation+0.000
ate
Tokenate
Feature activation+0.023
,
Token,
Feature activation+0.074
world
Token world
Feature activation+2.665
-
Token-
Feature activation+2.093
span
Tokenspan
Feature activation+2.244
ning
Tokenning
Feature activation+0.234
ep
Token ep
Feature activation+0.000
ics
Tokenics
Feature activation+0.000
,
Token,
Feature activation+0.000
Grant
Token Grant
Feature activation+0.000

INTERVAL 1.503 - 1.879
CONTAINS 0.021%

rivals
Token rivals
Feature activation+0.000
all
Token all
Feature activation+0.000
proposed
Token proposed
Feature activation+0.000
similarly
Token similarly
Feature activation+0.165
budget
Token budget
Feature activation+1.751
-
Token-
Feature activation+1.566
b
Tokenb
Feature activation+0.804
usting
Tokenusting
Feature activation+0.571
tax
Token tax
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
with
Token with
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
never
Token never
Feature activation+0.000
-
Token-
Feature activation+0.000
before
Tokenbefore
Feature activation+0.000
-
Token-
Feature activation+1.657
heard
Tokenheard
Feature activation+0.000
track
Token track
Feature activation+0.000
,
Token,
Feature activation+0.000
giving
Token giving
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
are
Token are
Feature activation+0.000
small
Token small
Feature activation+0.000
,
Token,
Feature activation+0.000
stock
Token stock
Feature activation+1.673
y
Tokeny
Feature activation+0.043
creatures
Token creatures
Feature activation+0.000
found
Token found
Feature activation+0.000
in
Token in
Feature activation+0.000
most
Token most
Feature activation+0.000
an
Token an
Feature activation+0.000
inter
Token inter
Feature activation+0.000
nec
Tokennec
Feature activation+0.000
ine
Tokenine
Feature activation+0.000
,
Token,
Feature activation+0.000
inter
Token inter
Feature activation+1.509
-
Token-
Feature activation+0.744
re
Tokenre
Feature activation+0.000
bel
Tokenbel
Feature activation+0.000
civil
Token civil
Feature activation+0.000
war
Token war
Feature activation+0.000
church
Token church
Feature activation+0.000
-
Token-
Feature activation+0.000
run
Tokenrun
Feature activation+0.000
,
Token,
Feature activation+0.000
government
Token government
Feature activation+2.140
-
Token-
Feature activation+1.608
funded
Tokenfunded
Feature activation+0.000
residential
Token residential
Feature activation+0.000
schools
Token schools
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.127 - 1.503
CONTAINS 0.033%

my
Token my
Feature activation+0.000
childhood
Token childhood
Feature activation+0.000
with
Token with
Feature activation+0.000
fearless
Token fearless
Feature activation+0.000
and
Token and
Feature activation+0.000
smart
Token smart
Feature activation+1.203
Women
Token Women
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Studies
Token Studies
Feature activation+0.000
us
Token us
Feature activation+0.000
in
Token in
Feature activation+0.000
opposing
Token opposing
Feature activation+0.000
this
Token this
Feature activation+0.000
entirely
Token entirely
Feature activation+0.000
counter
Token counter
Feature activation+1.251
-
Token-
Feature activation+0.832
productive
Tokenproductive
Feature activation+0.026
approach
Token approach
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
some
Token some
Feature activation+0.000
strange
Token strange
Feature activation+0.320
and
Token and
Feature activation+0.000
super
Token super
Feature activation+2.871
-
Token-
Feature activation+2.179
hard
Tokenhard
Feature activation+1.131
core
Tokencore
Feature activation+0.837
grand
Token grand
Feature activation+0.000
-
Token-
Feature activation+0.000
str
Tokenstr
Feature activation+0.000
ategy
Tokenategy
Feature activation+0.000
children
Token children
Feature activation+0.000
,
Token,
Feature activation+0.000
smelling
Token smelling
Feature activation+0.000
freshly
Token freshly
Feature activation+0.000
-
Token-
Feature activation+0.340
sp
Tokensp
Feature activation+1.389
illed
Tokenilled
Feature activation+0.039
blood
Token blood
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
beautiful
Token beautiful
Feature activation+0.104
and
Token and
Feature activation+1.250
rare
Token rare
Feature activation+0.918
guitars
Token guitars
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
planet
Token planet
Feature activation+0.000

INTERVAL 0.752 - 1.127
CONTAINS 0.060%

built
Token built
Feature activation+0.000
off
Token off
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
tried
Token tried
Feature activation+0.000
and
Token and
Feature activation+0.825
true
Token true
Feature activation+0.354
platform
Token platform
Feature activation+0.512
with
Token with
Feature activation+0.000
great
Token great
Feature activation+0.000
upgrade
Token upgrade
Feature activation+0.000
the
Token the
Feature activation+0.000
difference
Token difference
Feature activation+0.000
between
Token between
Feature activation+0.000
public
Token public
Feature activation+0.000
and
Token and
Feature activation+0.000
permission
Token permission
Feature activation+1.044
ed
Tokened
Feature activation+0.603
blockchain
Token blockchain
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
comparison
Token comparison
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
genuine
Token genuine
Feature activation+0.417
,
Token,
Feature activation+0.498
un
Token un
Feature activation+0.636
pret
Tokenpret
Feature activation+1.013
entious
Tokenentious
Feature activation+0.256
candidate
Token candidate
Feature activation+0.000
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.000
ever
Token ever
Feature activation+0.000
ask
Token ask
Feature activation+0.000
yourself
Token yourself
Feature activation+0.000
how
Token how
Feature activation+0.000
a
Token a
Feature activation+0.000
dynamically
Token dynamically
Feature activation+0.000
-
Token-
Feature activation+1.002
driven
Tokendriven
Feature activation+0.121
piece
Token piece
Feature activation+0.141
of
Token of
Feature activation+0.000
UI
Token UI
Feature activation+0.000
will
Token will
Feature activation+0.000
the
Token the
Feature activation+0.000
wild
Token wild
Feature activation+0.000
,
Token,
Feature activation+0.000
P
Token P
Feature activation+2.232
PT
TokenPT
Feature activation+0.872
-
Token-
Feature activation+0.993
manufact
Tokenmanufact
Feature activation+0.618
ured
Tokenured
Feature activation+0.000
700
Token 700
Feature activation+0.000
Dow
Token Dow
Feature activation+0.000
rally
Token rally
Feature activation+0.000

INTERVAL 0.376 - 0.752
CONTAINS 0.116%

group
Token group
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
formerly
Token formerly
Feature activation+0.000
al
Token al
Feature activation+0.317
-
Token-
Feature activation+0.439
Qaeda
TokenQaeda
Feature activation+2.182
-
Token-
Feature activation+1.727
affiliated
Tokenaffiliated
Feature activation+0.000
Fate
Token Fate
Feature activation+0.000
h
Tokenh
Feature activation+0.000
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
pathetic
Token pathetic
Feature activation+0.000
,
Token,
Feature activation+0.314
unworthy
Token unworthy
Feature activation+0.379
prey
Token prey
Feature activation+0.000
possible
Token possible
Feature activation+0.000
because
Token because
Feature activation+0.000
otherwise
Token otherwise
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
a
Token a
Feature activation+0.000
low
Token low
Feature activation+0.000
down
Tokendown
Feature activation+0.000
,
Token,
Feature activation+0.000
mean
Token mean
Feature activation+0.395
,
Token,
Feature activation+0.000
despicable
Token despicable
Feature activation+0.000
,
Token,
Feature activation+0.000
evil
Token evil
Feature activation+0.480
manifestation
Token manifestation
Feature activation+0.000
the
Token the
Feature activation+0.000
intention
Token intention
Feature activation+0.000
of
Token of
Feature activation+0.000
having
Token having
Feature activation+0.000
unim
Token unim
Feature activation+0.000
ped
Tokenped
Feature activation+0.621
ed
Tokened
Feature activation+0.432
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
kids
Token kids
Feature activation+0.000
grit
Token grit
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
very
Token very
Feature activation+0.000
determined
Token determined
Feature activation+0.000
and
Token and
Feature activation+0.000
mentally
Token mentally
Feature activation+0.534
tough
Token tough
Feature activation+0.296
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+0.000

INTERVAL 0.000 - 0.376
CONTAINS 99.747%

no
Token no
Feature activation+0.000
rounds
Token rounds
Feature activation+0.000
will
Token will
Feature activation+0.000
impact
Token impact
Feature activation+0.000
the
Token the
Feature activation+0.000
ground
Token ground
Feature activation+0.000
.
Token.
Feature activation+0.000
Also
Token Also
Feature activation+0.000
,
Token,
Feature activation+0.000
If
Token If
Feature activation+0.000
bottom
Token bottom
Feature activation+0.000
exercise
Token exercise
Feature activation+0.000
that
Token that
Feature activation+0.000
relies
Token relies
Feature activation+0.000
heavily
Token heavily
Feature activation+0.000
on
Token on
Feature activation+0.000
using
Token using
Feature activation+0.000
one
Token one
Feature activation+0.000
set
Token set
Feature activation+0.000
of
Token of
Feature activation+0.000
sources
Token sources
Feature activation+0.000
(
Token (
Feature activation+0.000
illness
Token illness
Feature activation+0.000
,
Token,
Feature activation+0.000
Joy
Token Joy
Feature activation+0.000
responded
Token responded
Feature activation+0.000
on
Token on
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
you
Token you
Feature activation+0.000
or
Token or
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
a
Token a
Feature activation+0.000
totally
Token totally
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
,
Token,
Feature activation+0.000
1971
Token 1971
Feature activation+0.000
-
Token-
Feature activation+0.000
74
Token74
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mr
TokenMr
Feature activation+0.000
.
Token.
Feature activation+0.000
Blue
Token Blue
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 5 in H7.0: (feature 7326)

TOP ACTIVATIONS
MAX = 4.936

,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
represents
Token represents
Feature activation+0.000
former
Token former
Feature activation+0.000
Ole
Token Ole
Feature activation+1.080
Miss
Token Miss
Feature activation+4.936
staffer
Token staffer
Feature activation+0.936
Barney
Token Barney
Feature activation+0.000
F
Token F
Feature activation+0.000
arr
Tokenarr
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
him
Token him
Feature activation+0.000
of
Token of
Feature activation+0.000
former
Token former
Feature activation+0.258
Montreal
Token Montreal
Feature activation+2.406
Canad
Token Canad
Feature activation+1.915
ien
Tokenien
Feature activation+4.553
and
Token and
Feature activation+2.976
Hall
Token Hall
Feature activation+1.373
of
Token of
Feature activation+1.263
fame
Token fame
Feature activation+1.960
defenseman
Token defenseman
Feature activation+0.800
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
former
Token former
Feature activation+0.000
El
Token El
Feature activation+2.520
mont
Tokenmont
Feature activation+4.521
Board
Token Board
Feature activation+2.224
of
Token of
Feature activation+0.061
Education
Token Education
Feature activation+2.777
President
Token President
Feature activation+0.000
Aub
Token Aub
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Goldman
Token Goldman
Feature activation+3.628
Sachs
Token Sachs
Feature activation+4.291
president
Token president
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
when
Token when
Feature activation+0.000
asked
Token asked
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
now
Token now
Feature activation+0.000
join
Token join
Feature activation+0.000
former
Token former
Feature activation+0.000
Warriors
Token Warriors
Feature activation+4.089
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.116
teammate
Token teammate
Feature activation+0.000
Elijah
Token Elijah
Feature activation+0.000
Taylor
Token Taylor
Feature activation+0.000
season
Token season
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Bayern
Token Bayern
Feature activation+2.214
Munich
Token Munich
Feature activation+3.991
man
Token man
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
Some
Token Some
Feature activation+0.000
may
Token may
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Southampton
Token Southampton
Feature activation+3.793
flyer
Token flyer
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
leading
Token leading
Feature activation+0.000
the
Token the
Feature activation+0.000
Airbus
Token Airbus
Feature activation+0.000
.
Token.
Feature activation+0.000
En
Token En
Feature activation+0.000
raged
Tokenraged
Feature activation+0.000
former
Token former
Feature activation+0.000
French
Token French
Feature activation+3.790
President
Token President
Feature activation+0.000
François
Token François
Feature activation+0.000
Hollande
Token Hollande
Feature activation+0.000
retali
Token retali
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Tri
Token Tri
Feature activation+1.823
-
Token-
Feature activation+1.709
City
TokenCity
Feature activation+3.753
Americans
Token Americans
Feature activation+1.936
and
Token and
Feature activation+1.856
Chill
Token Chill
Feature activation+0.421
iw
Tokeniw
Feature activation+0.000
ack
Tokenack
Feature activation+1.704
incident
Token incident
Feature activation+0.000
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
former
Token former
Feature activation+0.000
Temple
Token Temple
Feature activation+2.052
University
Token University
Feature activation+3.713
employee
Token employee
Feature activation+1.158
Andrea
Token Andrea
Feature activation+0.000
Con
Token Con
Feature activation+0.000
stand
Tokenstand
Feature activation+0.000
claims
Token claims
Feature activation+0.000
features
Token features
Feature activation+0.000
a
Token a
Feature activation+0.000
clip
Token clip
Feature activation+0.000
of
Token of
Feature activation+0.000
former
Token former
Feature activation+0.000
Alabama
Token Alabama
Feature activation+3.666
Gov
Token Gov
Feature activation+0.980
.
Token.
Feature activation+0.266
Robert
Token Robert
Feature activation+0.000
Bentley
Token Bentley
Feature activation+0.068
saying
Token saying
Feature activation+0.000
.
Token.
Feature activation+0.000
Thus
Token Thus
Feature activation+0.000
,
Token,
Feature activation+0.000
former
Token former
Feature activation+0.000
Hillary
Token Hillary
Feature activation+2.806
Clinton
Token Clinton
Feature activation+3.665
adviser
Token adviser
Feature activation+0.000
Jesse
Token Jesse
Feature activation+0.000
Ferguson
Token Ferguson
Feature activation+0.000
writes
Token writes
Feature activation+0.000
at
Token at
Feature activation+0.000
and
Token and
Feature activation+0.000
former
Token former
Feature activation+0.000
NASCAR
Token NASCAR
Feature activation+2.654
and
Token and
Feature activation+0.413
Formula
Token Formula
Feature activation+0.000
One
Token One
Feature activation+3.663
competitor
Token competitor
Feature activation+0.331
Scott
Token Scott
Feature activation+0.000
Speed
Token Speed
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Goldman
Token Goldman
Feature activation+3.628
Sachs
Token Sachs
Feature activation+4.291
president
Token president
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
when
Token when
Feature activation+0.000
Jerry
Token Jerry
Feature activation+0.000
Jones
Token Jones
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Razor
Token Razor
Feature activation+3.621
back
Tokenback
Feature activation+3.365
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.000
donated
Token donated
Feature activation+0.000
generously
Token generously
Feature activation+0.000
by
Token by
Feature activation+0.000
former
Token former
Feature activation+0.000
San
Token San
Feature activation+0.869
Francisco
Token Francisco
Feature activation+3.291
49
Token 49
Feature activation+0.123
ers
Tokeners
Feature activation+3.620
quarterback
Token quarterback
Feature activation+0.000
Colin
Token Colin
Feature activation+0.000
Kaepernick
Token Kaepernick
Feature activation+0.000
last
Token last
Feature activation+0.000
season
Token season
Feature activation+0.000
founded
Token founded
Feature activation+0.000
by
Token by
Feature activation+0.000
former
Token former
Feature activation+0.089
Magic
Token Magic
Feature activation+2.901
the
Token the
Feature activation+0.000
Gathering
Token Gathering
Feature activation+3.613
and
Token and
Feature activation+0.405
current
Token current
Feature activation+0.000
Hearthstone
Token Hearthstone
Feature activation+1.645
pro
Token pro
Feature activation+0.401
Y
Token Y
Feature activation+0.000
KY
TokenKY
Feature activation+0.000
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Former
TokenFormer
Feature activation+0.000
British
Token British
Feature activation+3.603
No
Token No
Feature activation+1.674
.
Token.
Feature activation+1.361
1
Token1
Feature activation+2.304
Balt
Token Balt
Feature activation+0.168
acha
Tokenacha
Feature activation+0.216
criminal
Token criminal
Feature activation+0.000
case
Token case
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
police
Token police
Feature activation+3.552
officer
Token officer
Feature activation+0.198
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
report
Token report
Feature activation+0.000
conducted
Token conducted
Feature activation+0.000
by
Token by
Feature activation+0.000
former
Token former
Feature activation+0.000
Supreme
Token Supreme
Feature activation+1.193
Court
Token Court
Feature activation+3.492
judge
Token judge
Feature activation+0.515
Frank
Token Frank
Feature activation+0.000
I
Token I
Feature activation+0.000
ac
Tokenac
Feature activation+0.000
ob
Tokenob
Feature activation+0.000

Top DFA by src position
MAX = 5.760

L
TokenL
Feature activation-0.002
Top resid features:
oyd
Tokenoyd
Feature activation+0.004
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
who
Token who
Feature activation-0.010
Top resid features:
represents
Token represents
Feature activation+0.003
Top resid features:
former
Token former
Feature activation+5.760
Top resid features:
Ole
Token Ole
Feature activation+0.096
Top resid features:
Miss
Token Miss
Feature activation+0.167
Top resid features:
staffer
Token staffer
Feature activation+0.000
Top resid features:
Barney
Token Barney
Feature activation+0.000
Top resid features:
F
Token F
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.024
Top resid features:
play
Token play
Feature activation-0.003
Top resid features:
reminds
Token reminds
Feature activation+0.020
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.096
Top resid features:
former
Token former
Feature activation+5.668
Top resid features:
Montreal
Token Montreal
Feature activation+0.206
Top resid features:
Canad
Token Canad
Feature activation+0.008
Top resid features:
ien
Tokenien
Feature activation+0.081
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Hall
Token Hall
Feature activation+0.000
Top resid features:
filled
Token filled
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ŀ
TokenĿ
Feature activation-0.001
Top resid features:
said
Token said
Feature activation+0.004
Top resid features:
former
Token former
Feature activation+5.304
Top resid features:
El
Token El
Feature activation+0.178
Top resid features:
mont
Tokenmont
Feature activation+0.104
Top resid features:
Board
Token Board
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Education
Token Education
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.008
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
from
Token from
Feature activation-0.014
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
former
Token former
Feature activation+4.943
Top resid features:
Goldman
Token Goldman
Feature activation+0.193
Top resid features:
Sachs
Token Sachs
Feature activation+0.286
Top resid features:
president
Token president
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
But
Token But
Feature activation+0.000
Top resid features:
Warriors
Token Warriors
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
They
Token They
Feature activation+0.003
Top resid features:
now
Token now
Feature activation+0.009
Top resid features:
join
Token join
Feature activation-0.027
Top resid features:
former
Token former
Feature activation+5.018
Top resid features:
Warriors
Token Warriors
Feature activation+0.114
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
teammate
Token teammate
Feature activation+0.000
Top resid features:
Elijah
Token Elijah
Feature activation+0.000
Top resid features:
far
Token far
Feature activation-0.011
Top resid features:
this
Token this
Feature activation-0.031
Top resid features:
season
Token season
Feature activation-0.021
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
former
Token former
Feature activation+4.744
Top resid features:
Bayern
Token Bayern
Feature activation+0.102
Top resid features:
Munich
Token Munich
Feature activation+0.136
Top resid features:
man
Token man
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Some
Token Some
Feature activation-0.015
Top resid features:
may
Token may
Feature activation-0.017
Top resid features:
say
Token say
Feature activation-0.007
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
former
Token former
Feature activation+4.731
Top resid features:
Southampton
Token Southampton
Feature activation+0.129
Top resid features:
flyer
Token flyer
Feature activation+0.000
Top resid features:
should
Token should
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
leading
Token leading
Feature activation+0.000
Top resid features:
based
Tokenbased
Feature activation-0.000
Top resid features:
Airbus
Token Airbus
Feature activation+0.010
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
En
Token En
Feature activation+0.033
Top resid features:
raged
Tokenraged
Feature activation+0.026
Top resid features:
former
Token former
Feature activation+4.416
Top resid features:
French
Token French
Feature activation+0.349
Top resid features:
President
Token President
Feature activation+0.000
Top resid features:
François
Token François
Feature activation+0.000
Top resid features:
Hollande
Token Hollande
Feature activation+0.000
Top resid features:
retali
Token retali
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Hill
Token Hill
Feature activation+0.001
Top resid features:
er
Tokener
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.063
Top resid features:
former
Token former
Feature activation+4.817
Top resid features:
Tri
Token Tri
Feature activation+0.097
Top resid features:
-
Token-
Feature activation-0.142
Top resid features:
City
TokenCity
Feature activation+0.063
Top resid features:
Americans
Token Americans
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
2004
Token 2004
Feature activation+0.022
Top resid features:
incident
Token incident
Feature activation-0.007
Top resid features:
in
Token in
Feature activation-0.014
Top resid features:
which
Token which
Feature activation+0.012
Top resid features:
former
Token former
Feature activation+4.340
Top resid features:
Temple
Token Temple
Feature activation+0.144
Top resid features:
University
Token University
Feature activation+0.171
Top resid features:
employee
Token employee
Feature activation+0.000
Top resid features:
Andrea
Token Andrea
Feature activation+0.000
Top resid features:
Con
Token Con
Feature activation+0.000
Top resid features:
also
Token also
Feature activation-0.001
Top resid features:
features
Token features
Feature activation+0.006
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
clip
Token clip
Feature activation-0.003
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
former
Token former
Feature activation+4.381
Top resid features:
Alabama
Token Alabama
Feature activation+0.151
Top resid features:
Gov
Token Gov
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Robert
Token Robert
Feature activation+0.000
Top resid features:
Bentley
Token Bentley
Feature activation+0.000
Top resid features:
liberal
Token liberal
Feature activation-0.001
Top resid features:
guilt
Token guilt
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Thus
Token Thus
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
former
Token former
Feature activation+4.377
Top resid features:
Hillary
Token Hillary
Feature activation+0.249
Top resid features:
Clinton
Token Clinton
Feature activation+0.077
Top resid features:
adviser
Token adviser
Feature activation+0.000
Top resid features:
Jesse
Token Jesse
Feature activation+0.000
Top resid features:
Ferguson
Token Ferguson
Feature activation+0.000
Top resid features:
host
Token host
Feature activation+0.001
Top resid features:
Tanner
Token Tanner
Feature activation+0.002
Top resid features:
F
Token F
Feature activation-0.002
Top resid features:
oust
Tokenoust
Feature activation+0.009
Top resid features:
and
Token and
Feature activation+0.032
Top resid features:
former
Token former
Feature activation+4.127
Top resid features:
NASCAR
Token NASCAR
Feature activation+0.141
Top resid features:
and
Token and
Feature activation+0.370
Top resid features:
Formula
Token Formula
Feature activation+0.043
Top resid features:
One
Token One
Feature activation+0.054
Top resid features:
competitor
Token competitor
Feature activation+0.000
Top resid features:
?
Token?
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.009
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
from
Token from
Feature activation-0.016
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
former
Token former
Feature activation+4.504
Top resid features:
Goldman
Token Goldman
Feature activation+0.121
Top resid features:
Sachs
Token Sachs
Feature activation+0.000
Top resid features:
president
Token president
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
But
Token But
Feature activation+0.000
Top resid features:
owner
Token owner
Feature activation+0.003
Top resid features:
Jerry
Token Jerry
Feature activation-0.003
Top resid features:
Jones
Token Jones
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
former
Token former
Feature activation+4.355
Top resid features:
Razor
Token Razor
Feature activation+0.061
Top resid features:
back
Tokenback
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
donated
Token donated
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.010
Top resid features:
gesture
Token gesture
Feature activation-0.014
Top resid features:
was
Token was
Feature activation-0.002
Top resid features:
started
Token started
Feature activation+0.003
Top resid features:
by
Token by
Feature activation+0.018
Top resid features:
former
Token former
Feature activation+4.358
Top resid features:
San
Token San
Feature activation+0.097
Top resid features:
Francisco
Token Francisco
Feature activation+0.130
Top resid features:
49
Token 49
Feature activation+0.083
Top resid features:
ers
Tokeners
Feature activation+0.057
Top resid features:
quarterback
Token quarterback
Feature activation+0.000
Top resid features:
po
Tokenpo
Feature activation-0.004
Top resid features:
Storm
Token Storm
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.032
Top resid features:
founded
Token founded
Feature activation+0.008
Top resid features:
by
Token by
Feature activation+0.010
Top resid features:
former
Token former
Feature activation+4.294
Top resid features:
Magic
Token Magic
Feature activation+0.159
Top resid features:
the
Token the
Feature activation+0.092
Top resid features:
Gathering
Token Gathering
Feature activation+0.055
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
current
Token current
Feature activation+0.000
Top resid features:
W
Token W
Feature activation-0.000
Top resid features:
KY
TokenKY
Feature activation+0.004
Top resid features:
C
TokenC
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.006
Top resid features:
Former
TokenFormer
Feature activation+4.188
Top resid features:
British
Token British
Feature activation+0.344
Top resid features:
No
Token No
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
1
Token1
Feature activation+0.000
Top resid features:
Balt
Token Balt
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
criminal
Token criminal
Feature activation+0.004
Top resid features:
case
Token case
Feature activation-0.014
Top resid features:
against
Token against
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
former
Token former
Feature activation+4.345
Top resid features:
police
Token police
Feature activation+0.099
Top resid features:
officer
Token officer
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
independent
Token independent
Feature activation-0.013
Top resid features:
report
Token report
Feature activation-0.006
Top resid features:
conducted
Token conducted
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.000
Top resid features:
former
Token former
Feature activation+4.113
Top resid features:
Supreme
Token Supreme
Feature activation+0.302
Top resid features:
Court
Token Court
Feature activation+0.075
Top resid features:
judge
Token judge
Feature activation+0.000
Top resid features:
Frank
Token Frank
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.57

Head 1: 0.03

Head 2: 0.03

Head 3: 0.05

Head 4: 0.05

Head 5: 0.09

Head 6: 0.05

Head 7: 0.02

Head 8: 0.05

Head 9: 0.04

Head 10: 0.01

Head 11: 0.02

Positive logits

advisor1.89

consultant1.89

lieutenant1.89

contractor1.86

adviser1.85

commander1.84

sergeant1.81

cz1.79

director1.76

champ1.73

strategist1.70

nominee1.69

architect1.68

commissioner1.67

chairman1.67

frontrunner1.66

deputy1.66

treasurer1.66

Adviser1.66

surgeon1.65

Negative logits

-1.70

olkien-1.57

taining-1.49

emis-1.43

ERG-1.42

agame-1.41

morrow-1.41

tomat-1.40

matically-1.40

utations-1.39

ortment-1.38

alot-1.38

allery-1.37

ilst-1.37

beit-1.35

amplification-1.33

pport-1.32

fuss-1.31

multiplication-1.30

iosis-1.30

INTERVAL 4.443 - 4.936
CONTAINS 0.000%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
former
Token former
Feature activation+0.000
El
Token El
Feature activation+2.520
mont
Tokenmont
Feature activation+4.521
Board
Token Board
Feature activation+2.224
of
Token of
Feature activation+0.061
Education
Token Education
Feature activation+2.777
President
Token President
Feature activation+0.000
Aub
Token Aub
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
represents
Token represents
Feature activation+0.000
former
Token former
Feature activation+0.000
Ole
Token Ole
Feature activation+1.080
Miss
Token Miss
Feature activation+4.936
staffer
Token staffer
Feature activation+0.936
Barney
Token Barney
Feature activation+0.000
F
Token F
Feature activation+0.000
arr
Tokenarr
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
him
Token him
Feature activation+0.000
of
Token of
Feature activation+0.000
former
Token former
Feature activation+0.258
Montreal
Token Montreal
Feature activation+2.406
Canad
Token Canad
Feature activation+1.915
ien
Tokenien
Feature activation+4.553
and
Token and
Feature activation+2.976
Hall
Token Hall
Feature activation+1.373
of
Token of
Feature activation+1.263
fame
Token fame
Feature activation+1.960
defenseman
Token defenseman
Feature activation+0.800

INTERVAL 3.949 - 4.443
CONTAINS 0.000%

ľ
Tokenľ
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Goldman
Token Goldman
Feature activation+3.628
Sachs
Token Sachs
Feature activation+4.291
president
Token president
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
when
Token when
Feature activation+0.000
asked
Token asked
Feature activation+0.000
season
Token season
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Bayern
Token Bayern
Feature activation+2.214
Munich
Token Munich
Feature activation+3.991
man
Token man
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
now
Token now
Feature activation+0.000
join
Token join
Feature activation+0.000
former
Token former
Feature activation+0.000
Warriors
Token Warriors
Feature activation+4.089
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.116
teammate
Token teammate
Feature activation+0.000
Elijah
Token Elijah
Feature activation+0.000
Taylor
Token Taylor
Feature activation+0.000

INTERVAL 3.455 - 3.949
CONTAINS 0.001%

âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Goldman
Token Goldman
Feature activation+3.628
Sachs
Token Sachs
Feature activation+4.291
president
Token president
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
when
Token when
Feature activation+0.000
Some
Token Some
Feature activation+0.000
may
Token may
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Southampton
Token Southampton
Feature activation+3.793
flyer
Token flyer
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
leading
Token leading
Feature activation+0.000
the
Token the
Feature activation+0.000
features
Token features
Feature activation+0.000
a
Token a
Feature activation+0.000
clip
Token clip
Feature activation+0.000
of
Token of
Feature activation+0.000
former
Token former
Feature activation+0.000
Alabama
Token Alabama
Feature activation+3.666
Gov
Token Gov
Feature activation+0.980
.
Token.
Feature activation+0.266
Robert
Token Robert
Feature activation+0.000
Bentley
Token Bentley
Feature activation+0.068
saying
Token saying
Feature activation+0.000
Airbus
Token Airbus
Feature activation+0.000
.
Token.
Feature activation+0.000
En
Token En
Feature activation+0.000
raged
Tokenraged
Feature activation+0.000
former
Token former
Feature activation+0.000
French
Token French
Feature activation+3.790
President
Token President
Feature activation+0.000
François
Token François
Feature activation+0.000
Hollande
Token Hollande
Feature activation+0.000
retali
Token retali
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
founded
Token founded
Feature activation+0.000
by
Token by
Feature activation+0.000
former
Token former
Feature activation+0.089
Magic
Token Magic
Feature activation+2.901
the
Token the
Feature activation+0.000
Gathering
Token Gathering
Feature activation+3.613
and
Token and
Feature activation+0.405
current
Token current
Feature activation+0.000
Hearthstone
Token Hearthstone
Feature activation+1.645
pro
Token pro
Feature activation+0.401
Y
Token Y
Feature activation+0.000

INTERVAL 2.962 - 3.455
CONTAINS 0.004%

rib
Tokenrib
Feature activation+0.000
bs
Tokenbs
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Former
TokenFormer
Feature activation+0.000
Vikings
Token Vikings
Feature activation+3.001
return
Token return
Feature activation+1.041
er
Tokener
Feature activation+0.488
)
Token)
Feature activation+0.000
Percy
Token Percy
Feature activation+0.000
Har
Token Har
Feature activation+0.000
rein
Token rein
Feature activation+0.000
st
Tokenst
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Former
TokenFormer
Feature activation+0.000
Supreme
Token Supreme
Feature activation+2.125
Court
Token Court
Feature activation+3.275
Justice
Token Justice
Feature activation+2.372
Sandra
Token Sandra
Feature activation+0.000
Day
Token Day
Feature activation+0.000
O
Token O
Feature activation+0.000
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
former
Token former
Feature activation+0.000
New
Token New
Feature activation+3.132
Mexico
Token Mexico
Feature activation+3.290
governor
Token governor
Feature activation+0.275
arrived
Token arrived
Feature activation+0.000
early
Token early
Feature activation+0.000
,
Token,
Feature activation+0.000
wandering
Token wandering
Feature activation+0.000
on
Token on
Feature activation+0.000
memoir
Token memoir
Feature activation+0.000
:
Token:
Feature activation+0.000
report
Token report
Feature activation+0.000
Former
Token Former
Feature activation+0.000
GOP
Token GOP
Feature activation+3.001
lawmaker
Token lawmaker
Feature activation+1.742
on
Token on
Feature activation+0.000
death
Token death
Feature activation+0.000
of
Token of
Feature activation+0.000
7
Token 7
Feature activation+0.000
pand
Token pand
Feature activation+0.000
ering
Tokenering
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Apprentice
Token Apprentice
Feature activation+3.424
boss
Token boss
Feature activation+0.000
,
Token,
Feature activation+0.000
S
Token S
Feature activation+0.000
.
Token.
Feature activation+0.000
N
TokenN
Feature activation+0.000

INTERVAL 2.468 - 2.962
CONTAINS 0.006%

Fr
Token Fr
Feature activation+0.000
um
Tokenum
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
speech
Token speech
Feature activation+2.559
writer
Token writer
Feature activation+2.721
for
Token for
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
43
Token 43
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Massachusetts
Token Massachusetts
Feature activation+2.685
governor
Token governor
Feature activation+0.256
told
Token told
Feature activation+0.000
reporters
Token reporters
Feature activation+0.000
in
Token in
Feature activation+0.000
Miami
Token Miami
Feature activation+0.000
,
Token,
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Former
TokenFormer
Feature activation+0.000
state
Token state
Feature activation+2.724
Supreme
Token Supreme
Feature activation+1.885
Court
Token Court
Feature activation+2.915
Justice
Token Justice
Feature activation+1.358
Robert
Token Robert
Feature activation+0.000
Young
Token Young
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
former
Tokenformer
Feature activation+0.000
Koch
Token Koch
Feature activation+2.601
employee
Token employee
Feature activation+0.095
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
It
Token It
Feature activation+0.000
Qaeda
Token Qaeda
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
former
Token former
Feature activation+0.000
Syrian
Token Syrian
Feature activation+2.741
affiliate
Token affiliate
Feature activation+2.301
,
Token,
Feature activation+0.431
earlier
Token earlier
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000

INTERVAL 1.975 - 2.468
CONTAINS 0.008%

A
TokenA
Feature activation+0.000
jury
Token jury
Feature activation+0.000
unanimously
Token unanimously
Feature activation+0.000
found
Token found
Feature activation+0.000
former
Token former
Feature activation+0.000
Connecticut
Token Connecticut
Feature activation+1.999
Gov
Token Gov
Feature activation+0.031
.
Token.
Feature activation+0.000
John
Token John
Feature activation+0.000
Row
Token Row
Feature activation+0.000
land
Tokenland
Feature activation+0.000
A
TokenA
Feature activation+0.000
.
Token.
Feature activation+0.000
attorney
Token attorney
Feature activation+0.000
and
Token and
Feature activation+0.000
former
Token former
Feature activation+0.000
church
Token church
Feature activation+1.995
member
Token member
Feature activation+0.000
Vance
Token Vance
Feature activation+0.000
Woodward
Token Woodward
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
said
Token said
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
U
Token U
Feature activation+1.102
.
Token.
Feature activation+0.332
S
TokenS
Feature activation+2.329
.
Token.
Feature activation+2.319
intelligence
Token intelligence
Feature activation+1.505
official
Token official
Feature activation+0.000
with
Token with
Feature activation+0.000
experience
Token experience
Feature activation+0.000
movie
Token movie
Feature activation+0.000
director
Token director
Feature activation+0.000
criticized
Token criticized
Feature activation+0.000
former
Token former
Feature activation+0.000
US
Token US
Feature activation+2.607
State
Token State
Feature activation+2.285
Secretary
Token Secretary
Feature activation+1.194
for
Token for
Feature activation+0.000
contributing
Token contributing
Feature activation+0.000
to
Token to
Feature activation+0.000
almost
Token almost
Feature activation+0.000
is
Token is
Feature activation+0.000
undoubtedly
Token undoubtedly
Feature activation+0.000
led
Token led
Feature activation+0.000
by
Token by
Feature activation+0.000
former
Token former
Feature activation+0.000
star
Token star
Feature activation+2.091
loan
Token loan
Feature activation+0.466
ee
Tokenee
Feature activation+0.130
Tom
Token Tom
Feature activation+0.000
Lawrence
Token Lawrence
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.481 - 1.975
CONTAINS 0.008%

Business
Token Business
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Smith
Token Smith
Feature activation+1.695
s
Tokens
Feature activation+3.346
front
Token front
Feature activation+0.000
-
Token-
Feature activation+0.958
man
Tokenman
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Sab
Token Sab
Feature activation+0.000
ah
Tokenah
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
Netflix
Token Netflix
Feature activation+1.625
data
Token data
Feature activation+0.706
scientist
Token scientist
Feature activation+0.624
who
Token who
Feature activation+0.011
joined
Token joined
Feature activation+0.000
Work
Token Work
Feature activation+0.000
-
Token-
Feature activation+0.000
s
Tokens
Feature activation+3.327
ous
Tokenous
Feature activation+0.507
-
Token-
Feature activation+0.531
tra
Tokentra
Feature activation+1.492
itant
Tokenitant
Feature activation+1.559
de
Token de
Feature activation+0.150
l
Token l
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Ag
TokenAg
Feature activation+0.017
man
Tokenman
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
Hardcore
Token Hardcore
Feature activation+1.348
Champion
Token Champion
Feature activation+1.673
and
Token and
Feature activation+1.496
the
Token the
Feature activation+0.425
guy
Token guy
Feature activation+0.000
that
Token that
Feature activation+0.000
eliminated
Token eliminated
Feature activation+0.000
Bond
Token Bond
Feature activation+0.000
Street
Token Street
Feature activation+0.000
rooms
Token rooms
Feature activation+0.000
of
Token of
Feature activation+0.000
former
Token former
Feature activation+0.000
pri
Token pri
Feature activation+1.485
z
Tokenz
Feature activation+0.366
ef
Tokenef
Feature activation+0.000
ighting
Tokenighting
Feature activation+3.397
champion
Token champion
Feature activation+0.083
âĢ
Token âĢ
Feature activation+0.000

INTERVAL 0.987 - 1.481
CONTAINS 0.013%

Ċ
TokenĊ
Feature activation+0.000
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.000
former
Token former
Feature activation+0.000
rabbi
Token rabbi
Feature activation+1.417
,
Token,
Feature activation+0.000
Na
Token Na
Feature activation+0.000
ft
Tokenft
Feature activation+0.000
ali
Tokenali
Feature activation+0.000
B
Token B
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
includes
Token includes
Feature activation+0.000
14
Token 14
Feature activation+0.000
former
Token former
Feature activation+0.000
stars
Token stars
Feature activation+1.056
who
Token who
Feature activation+0.000
exce
Token exce
Feature activation+0.000
lled
Tokenlled
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
now
Token now
Feature activation+0.000
join
Token join
Feature activation+0.000
former
Token former
Feature activation+0.000
Warriors
Token Warriors
Feature activation+4.089
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.116
teammate
Token teammate
Feature activation+0.000
Elijah
Token Elijah
Feature activation+0.000
Taylor
Token Taylor
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
yesterday
Token yesterday
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
former
Token former
Feature activation+0.000
campaign
Token campaign
Feature activation+2.621
manager
Token manager
Feature activation+1.291
and
Token and
Feature activation+0.000
current
Token current
Feature activation+0.000
CNN
Token CNN
Feature activation+1.517
contributor
Token contributor
Feature activation+0.367
Corey
Token Corey
Feature activation+0.000
threat
Token threat
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
reigning
Token reigning
Feature activation+0.000
Grey
Token Grey
Feature activation+0.759
Cup
Token Cup
Feature activation+1.318
Champions
Token Champions
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
chances
Token chances
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.494 - 0.987
CONTAINS 0.021%

to
Token to
Feature activation+0.000
hear
Token hear
Feature activation+0.000
when
Token when
Feature activation+0.000
a
Token a
Feature activation+0.000
current
Token current
Feature activation+0.000
USC
Token USC
Feature activation+0.984
Trojan
Token Trojan
Feature activation+0.835
decides
Token decides
Feature activation+0.000
that
Token that
Feature activation+0.000
Arizona
Token Arizona
Feature activation+0.000
Football
Token Football
Feature activation+0.000
's
Token's
Feature activation+0.000
grandfather
Token grandfather
Feature activation+0.000
,
Token,
Feature activation+0.000
retired
Token retired
Feature activation+0.000
Army
Token Army
Feature activation+0.443
Col
Token Col
Feature activation+0.903
.
Token.
Feature activation+0.000
Joseph
Token Joseph
Feature activation+0.000
L
Token L
Feature activation+0.000
.
Token.
Feature activation+0.000
G
Token G
Feature activation+0.000
Del
Token Del
Feature activation+0.000
ors
Tokenors
Feature activation+0.000
joined
Token joined
Feature activation+0.000
former
Token former
Feature activation+0.000
EU
Token EU
Feature activation+2.221
commissioners
Token commissioners
Feature activation+0.551
Pascal
Token Pascal
Feature activation+0.000
Lam
Token Lam
Feature activation+0.000
y
Tokeny
Feature activation+0.000
and
Token and
Feature activation+0.000
Antonio
Token Antonio
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
former
Token former
Feature activation+0.000
reality
Token reality
Feature activation+0.804
TV
Token TV
Feature activation+2.684
star
Token star
Feature activation+0.020
's
Token's
Feature activation+0.000
95
Token 95
Feature activation+0.000
percent
Token percent
Feature activation+0.000
U
Token U
Feature activation+1.458
.
Token.
Feature activation+2.226
S
TokenS
Feature activation+2.486
.
Token.
Feature activation+2.732
Navy
Token Navy
Feature activation+2.336
Admiral
Token Admiral
Feature activation+0.706
William
Token William
Feature activation+0.000
Mc
Token Mc
Feature activation+0.000
Raven
TokenRaven
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000

INTERVAL 0.000 - 0.494
CONTAINS 99.939%

Lab
Token Lab
Feature activation+0.000
plans
Token plans
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
more
Token more
Feature activation+0.000
details
Token details
Feature activation+0.000
in
Token in
Feature activation+0.000
April
Token April
Feature activation+0.000
about
Token about
Feature activation+0.000
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
condo
Token condo
Feature activation+0.000
development
Token development
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Several
TokenSeveral
Feature activation+0.000
homes
Token homes
Feature activation+0.000
along
Token along
Feature activation+0.000
Mac
Token Mac
Feature activation+0.000
le
Tokenle
Feature activation+0.000
od
Tokenod
Feature activation+0.000
they
Token they
Feature activation+0.000
could
Token could
Feature activation+0.000
learn
Token learn
Feature activation+0.000
quickly
Token quickly
Feature activation+0.000
and
Token and
Feature activation+0.000
easily
Token easily
Feature activation+0.000
enough
Token enough
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
free
Token free
Feature activation+0.000
time
Token time
Feature activation+0.000
g
Tokeng
Feature activation+0.000
.,
Token.,
Feature activation+0.000
hy
Token hy
Feature activation+0.000
st
Tokenst
Feature activation+0.000
ere
Tokenere
Feature activation+0.000
ct
Tokenct
Feature activation+0.000
omy
Tokenomy
Feature activation+0.000
),
Token),
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
and
Token and
Feature activation+0.000
civilians
Token civilians
Feature activation+0.000
working
Token working
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
military
Token military
Feature activation+0.000
.
Token.
Feature activation+0.000
Defense
Token Defense
Feature activation+0.000
officials
Token officials
Feature activation+0.000
have
Token have
Feature activation+0.000
noted
Token noted
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.665
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Organisation
Token Organisation
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.665
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.665
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.665
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.665
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.665
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.665
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 6 in H7.0: (feature 39330)

TOP ACTIVATIONS
MAX = 1.943

the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
way
Token way
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.888
ľ
Tokenľ
Feature activation+1.943
ach
Tokenach
Feature activation+1.272
ieving
Tokenieving
Feature activation+0.000
our
Token our
Feature activation+0.000
mutual
Token mutual
Feature activation+0.000
interests
Token interests
Feature activation+0.000
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.794
if
Token if
Feature activation+0.000
not
Token not
Feature activation+1.942
doing
Token doing
Feature activation+0.000
something
Token something
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
,
Token,
Feature activation+0.352
at
Token at
Feature activation+0.645
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
children
Token children
Feature activation+0.000
and
Token and
Feature activation+0.000
by
Token by
Feature activation+0.000
her
Token her
Feature activation+1.761
unwillingness
Token unwillingness
Feature activation+0.138
to
Token to
Feature activation+0.000
foster
Token foster
Feature activation+0.000
a
Token a
Feature activation+0.000
strong
Token strong
Feature activation+0.000
will
Token will
Feature activation+0.000
find
Token find
Feature activation+0.000
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
of
Token of
Feature activation+0.047
eventually
Token eventually
Feature activation+1.643
going
Token going
Feature activation+0.539
to
Token to
Feature activation+0.000
Mars
Token Mars
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
,
Token,
Feature activation+0.000
whilst
Token whilst
Feature activation+0.000
simultaneously
Token simultaneously
Feature activation+1.606
delivering
Token delivering
Feature activation+0.336
sustainable
Token sustainable
Feature activation+0.000
services
Token services
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
go
Token go
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
way
Token way
Feature activation+0.000
toward
Token toward
Feature activation+0.000
qu
Token qu
Feature activation+1.571
elling
Tokenelling
Feature activation+0.000
the
Token the
Feature activation+0.000
outrage
Token outrage
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
his
Token his
Feature activation+0.000
the
Token the
Feature activation+0.000
Pacific
Token Pacific
Feature activation+0.000
war
Token war
Feature activation+0.000
,
Token,
Feature activation+0.000
thereby
Token thereby
Feature activation+0.000
invalid
Token invalid
Feature activation+1.514
ating
Tokenating
Feature activation+0.000
any
Token any
Feature activation+0.000
arguments
Token arguments
Feature activation+0.000
favoring
Token favoring
Feature activation+0.000
dropping
Token dropping
Feature activation+0.000
restrained
Token restrained
Feature activation+0.000
from
Token from
Feature activation+0.000
interfering
Token interfering
Feature activation+0.041
with
Token with
Feature activation+0.000
or
Token or
Feature activation+0.000
in
Token in
Feature activation+1.483
any
Token any
Feature activation+0.387
way
Token way
Feature activation+1.473
disturbing
Token disturbing
Feature activation+0.343
the
Token the
Feature activation+0.000
possession
Token possession
Feature activation+0.000
interfering
Token interfering
Feature activation+0.041
with
Token with
Feature activation+0.000
or
Token or
Feature activation+0.000
in
Token in
Feature activation+1.483
any
Token any
Feature activation+0.387
way
Token way
Feature activation+1.473
disturbing
Token disturbing
Feature activation+0.343
the
Token the
Feature activation+0.000
possession
Token possession
Feature activation+0.000
or
Token or
Feature activation+0.000
access
Token access
Feature activation+0.000
can
Tokencan
Feature activation+0.000
accused
Token accused
Feature activation+0.000
Banks
Token Banks
Feature activation+0.000
of
Token of
Feature activation+0.000
def
Token def
Feature activation+0.609
raud
Tokenraud
Feature activation+1.441
ing
Tokening
Feature activation+0.000
him
Token him
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
$
Token $
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
internet
Token internet
Feature activation+0.000
telling
Token telling
Feature activation+0.000
and
Token and
Feature activation+0.000
re
Token re
Feature activation+1.426
-
Token-
Feature activation+1.330
telling
Tokentelling
Feature activation+0.009
stories
Token stories
Feature activation+0.000
about
Token about
Feature activation+0.000
how
Token how
Feature activation+0.000
The
TokenThe
Feature activation+0.000
group
Token group
Feature activation+0.000
is
Token is
Feature activation+0.000
restricted
Token restricted
Feature activation+0.100
from
Token from
Feature activation+0.251
aggressively
Token aggressively
Feature activation+1.424
expanding
Token expanding
Feature activation+0.083
as
Token as
Feature activation+0.000
S
Token S
Feature activation+0.000
unt
Tokenunt
Feature activation+0.000
ory
Tokenory
Feature activation+0.000
For
Token For
Feature activation+0.000
example
Token example
Feature activation+0.000
,
Token,
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
or
Token or
Feature activation+0.000
charging
Token charging
Feature activation+1.421
a
Token a
Feature activation+0.000
battery
Token battery
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
hot
Token hot
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
harder
Token harder
Feature activation+0.000
task
Token task
Feature activation+0.000
of
Token of
Feature activation+0.132
replacement
Token replacement
Feature activation+1.391
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
likely
Token likely
Feature activation+0.000
a
Token a
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
and
Token and
Feature activation+0.000
begin
Token begin
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.645
ľ
Tokenľ
Feature activation+1.389
question
Tokenquestion
Feature activation+1.293
ing
Tokening
Feature activation+0.000
evolution
Token evolution
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
kept
Token kept
Feature activation+0.000
clearing
Token clearing
Feature activation+0.391
out
Token out
Feature activation+0.692
,
Token,
Feature activation+0.000
kept
Token kept
Feature activation+0.000
tackling
Token tackling
Feature activation+1.350
and
Token and
Feature activation+0.803
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
game
Token game
Feature activation+0.000
with
Token with
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
there
Tokenthere
Feature activation+0.000
by
Tokenby
Feature activation+0.357
inspiring
Token inspiring
Feature activation+1.340
generations
Token generations
Feature activation+0.000
of
Token of
Feature activation+0.000
future
Token future
Feature activation+0.000
video
Token video
Feature activation+0.000
artists
Token artists
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
gave
Token gave
Feature activation+0.000
up
Token up
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.335
tyre
Token tyre
Feature activation+0.599
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
the
Token the
Feature activation+0.000
internet
Token internet
Feature activation+0.000
telling
Token telling
Feature activation+0.000
and
Token and
Feature activation+0.000
re
Token re
Feature activation+1.426
-
Token-
Feature activation+1.330
telling
Tokentelling
Feature activation+0.009
stories
Token stories
Feature activation+0.000
about
Token about
Feature activation+0.000
how
Token how
Feature activation+0.000
his
Token his
Feature activation+0.000
communities
Token communities
Feature activation+0.000
from
Token from
Feature activation+0.000
fragment
Token fragment
Feature activation+0.949
ing
Tokening
Feature activation+0.202
and
Token and
Feature activation+0.213
social
Token social
Feature activation+1.326
networks
Token networks
Feature activation+0.478
from
Token from
Feature activation+0.000
diss
Token diss
Feature activation+0.658
olving
Tokenolving
Feature activation+0.352
.
Token.
Feature activation+0.000

Top DFA by src position
MAX = 2.556

to
Token to
Feature activation-0.018
Top resid features:
find
Token find
Feature activation-0.008
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
best
Token best
Feature activation-0.027
Top resid features:
way
Token way
Feature activation+0.007
Top resid features:
of
Token of
Feature activation+2.416
Top resid features:
âĢ
Token âĢ
Feature activation-0.005
Top resid features:
ľ
Tokenľ
Feature activation-0.010
Top resid features:
ach
Tokenach
Feature activation+0.000
Top resid features:
ieving
Tokenieving
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.000
Top resid features:
blog
Token blog
Feature activation-0.000
Top resid features:
osphere
Tokenosphere
Feature activation-0.001
Top resid features:
was
Token was
Feature activation-0.015
Top resid features:
a
Token a
Feature activation-0.044
Top resid features:
way
Token way
Feature activation+0.011
Top resid features:
of
Token of
Feature activation+2.556
Top resid features:
,
Token,
Feature activation-0.066
Top resid features:
if
Token if
Feature activation-0.065
Top resid features:
not
Token not
Feature activation-0.009
Top resid features:
doing
Token doing
Feature activation+0.000
Top resid features:
something
Token something
Feature activation+0.000
Top resid features:
front
Token front
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
children
Token children
Feature activation-0.018
Top resid features:
and
Token and
Feature activation+0.025
Top resid features:
by
Token by
Feature activation+2.084
Top resid features:
her
Token her
Feature activation+0.013
Top resid features:
unwillingness
Token unwillingness
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
foster
Token foster
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
people
Token people
Feature activation-0.003
Top resid features:
will
Token will
Feature activation+0.015
Top resid features:
find
Token find
Feature activation+0.113
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
way
Token way
Feature activation+0.066
Top resid features:
of
Token of
Feature activation+1.898
Top resid features:
eventually
Token eventually
Feature activation+0.054
Top resid features:
going
Token going
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Mars
Token Mars
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
worst
Token worst
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
these
Token these
Feature activation+0.004
Top resid features:
cuts
Token cuts
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
whilst
Token whilst
Feature activation+1.912
Top resid features:
simultaneously
Token simultaneously
Feature activation+0.058
Top resid features:
delivering
Token delivering
Feature activation+0.000
Top resid features:
sustainable
Token sustainable
Feature activation+0.000
Top resid features:
services
Token services
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
should
Token should
Feature activation-0.011
Top resid features:
go
Token go
Feature activation-0.005
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
long
Token long
Feature activation-0.001
Top resid features:
way
Token way
Feature activation+0.009
Top resid features:
toward
Token toward
Feature activation+1.948
Top resid features:
qu
Token qu
Feature activation+0.007
Top resid features:
elling
Tokenelling
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
outrage
Token outrage
Feature activation+0.000
Top resid features:
surrounding
Token surrounding
Feature activation+0.000
Top resid features:
winning
Token winning
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
Pacific
Token Pacific
Feature activation+0.001
Top resid features:
war
Token war
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
thereby
Token thereby
Feature activation+1.864
Top resid features:
invalid
Token invalid
Feature activation+0.008
Top resid features:
ating
Tokenating
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
arguments
Token arguments
Feature activation+0.000
Top resid features:
favoring
Token favoring
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
restrained
Token restrained
Feature activation+0.004
Top resid features:
from
Token from
Feature activation+0.011
Top resid features:
interfering
Token interfering
Feature activation+0.034
Top resid features:
with
Token with
Feature activation+0.015
Top resid features:
or
Token or
Feature activation+1.805
Top resid features:
in
Token in
Feature activation+0.020
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
way
Token way
Feature activation+0.000
Top resid features:
disturbing
Token disturbing
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
restrained
Token restrained
Feature activation-0.002
Top resid features:
from
Token from
Feature activation+0.002
Top resid features:
interfering
Token interfering
Feature activation+0.033
Top resid features:
with
Token with
Feature activation+0.016
Top resid features:
or
Token or
Feature activation+1.856
Top resid features:
in
Token in
Feature activation+0.025
Top resid features:
any
Token any
Feature activation-0.003
Top resid features:
way
Token way
Feature activation-0.000
Top resid features:
disturbing
Token disturbing
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Dun
TokenDun
Feature activation+0.001
Top resid features:
can
Tokencan
Feature activation+0.002
Top resid features:
accused
Token accused
Feature activation-0.001
Top resid features:
Banks
Token Banks
Feature activation+0.010
Top resid features:
of
Token of
Feature activation+1.606
Top resid features:
def
Token def
Feature activation+0.092
Top resid features:
raud
Tokenraud
Feature activation+0.015
Top resid features:
ing
Tokening
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
day
Token day
Feature activation-0.007
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
internet
Token internet
Feature activation-0.002
Top resid features:
telling
Token telling
Feature activation-0.017
Top resid features:
and
Token and
Feature activation+1.846
Top resid features:
re
Token re
Feature activation+0.011
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
telling
Tokentelling
Feature activation+0.000
Top resid features:
stories
Token stories
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation-0.002
Top resid features:
The
TokenThe
Feature activation-0.005
Top resid features:
group
Token group
Feature activation+0.001
Top resid features:
is
Token is
Feature activation+0.009
Top resid features:
restricted
Token restricted
Feature activation+0.028
Top resid features:
from
Token from
Feature activation+1.775
Top resid features:
aggressively
Token aggressively
Feature activation+0.023
Top resid features:
expanding
Token expanding
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
S
Token S
Feature activation+0.000
Top resid features:
unt
Tokenunt
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
For
Token For
Feature activation-0.007
Top resid features:
example
Token example
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
leaving
Token leaving
Feature activation+0.042
Top resid features:
or
Token or
Feature activation+1.711
Top resid features:
charging
Token charging
Feature activation+0.006
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
battery
Token battery
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
worrying
Token worrying
Feature activation+0.006
Top resid features:
about
Token about
Feature activation+0.038
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
harder
Token harder
Feature activation+0.025
Top resid features:
task
Token task
Feature activation+0.227
Top resid features:
of
Token of
Feature activation+1.569
Top resid features:
replacement
Token replacement
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
likely
Token likely
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
years
Token years
Feature activation-0.005
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ŀ
TokenĿ
Feature activation-0.002
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
begin
Token begin
Feature activation+1.757
Top resid features:
âĢ
Token âĢ
Feature activation+0.005
Top resid features:
ľ
Tokenľ
Feature activation+0.002
Top resid features:
question
Tokenquestion
Feature activation+0.000
Top resid features:
ing
Tokening
Feature activation+0.000
Top resid features:
evolution
Token evolution
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
kept
Token kept
Feature activation+0.123
Top resid features:
clearing
Token clearing
Feature activation+0.002
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
kept
Token kept
Feature activation+1.695
Top resid features:
tackling
Token tackling
Feature activation-0.003
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
playing
Token playing
Feature activation+0.023
Top resid features:
with
Token with
Feature activation-0.001
Top resid features:
it
Token it
Feature activation-0.012
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.023
Top resid features:
there
Tokenthere
Feature activation+0.045
Top resid features:
by
Tokenby
Feature activation+1.771
Top resid features:
inspiring
Token inspiring
Feature activation-0.026
Top resid features:
generations
Token generations
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
future
Token future
Feature activation+0.000
Top resid features:
video
Token video
Feature activation+0.000
Top resid features:
Eventually
Token Eventually
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
he
Token he
Feature activation+0.004
Top resid features:
gave
Token gave
Feature activation+0.003
Top resid features:
up
Token up
Feature activation+0.040
Top resid features:
on
Token on
Feature activation+1.681
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
tyre
Token tyre
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
didn
Token didn
Feature activation+0.000
Top resid features:
day
Token day
Feature activation-0.018
Top resid features:
on
Token on
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
internet
Token internet
Feature activation-0.005
Top resid features:
telling
Token telling
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+1.780
Top resid features:
re
Token re
Feature activation+0.010
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
telling
Tokentelling
Feature activation+0.000
Top resid features:
stories
Token stories
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
prevent
Token prevent
Feature activation+0.020
Top resid features:
communities
Token communities
Feature activation+0.014
Top resid features:
from
Token from
Feature activation+0.121
Top resid features:
fragment
Token fragment
Feature activation+0.020
Top resid features:
ing
Tokening
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+1.429
Top resid features:
social
Token social
Feature activation+0.016
Top resid features:
networks
Token networks
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
diss
Token diss
Feature activation+0.000
Top resid features:
olving
Tokenolving
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.57

Head 1: 0.03

Head 2: 0.02

Head 3: 0.05

Head 4: 0.04

Head 5: 0.06

Head 6: 0.04

Head 7: 0.03

Head 8: 0.05

Head 9: 0.06

Head 10: 0.02

Head 11: 0.02

Positive logits

ding2.61

ucing2.54

picking2.48

angering2.46

ping2.45

pleting2.45

igating2.44

ting2.41

ouncing2.41

idding2.38

aching2.38

icating2.36

uling2.35

verting2.35

ribing2.35

lining2.35

asuring2.34

gging2.32

itting2.31

izing2.31

Negative logits

Apostle-1.69

Barrier-1.65

Trainer-1.62

OECD-1.53

apostle-1.49

Klu-1.48

Kad-1.48

Wy-1.48

Deity-1.47

Bagg-1.47

Cree-1.44

USA-1.43

Gy-1.43

Slate-1.42

Compass-1.41

iren-1.40

iggurat-1.39

Collider-1.39

ambulance-1.39

Bureau-1.38

INTERVAL 1.749 - 1.943
CONTAINS 0.000%

a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.794
if
Token if
Feature activation+0.000
not
Token not
Feature activation+1.942
doing
Token doing
Feature activation+0.000
something
Token something
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
,
Token,
Feature activation+0.352
at
Token at
Feature activation+0.645
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
way
Token way
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.888
ľ
Tokenľ
Feature activation+1.943
ach
Tokenach
Feature activation+1.272
ieving
Tokenieving
Feature activation+0.000
our
Token our
Feature activation+0.000
mutual
Token mutual
Feature activation+0.000
interests
Token interests
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
children
Token children
Feature activation+0.000
and
Token and
Feature activation+0.000
by
Token by
Feature activation+0.000
her
Token her
Feature activation+1.761
unwillingness
Token unwillingness
Feature activation+0.138
to
Token to
Feature activation+0.000
foster
Token foster
Feature activation+0.000
a
Token a
Feature activation+0.000
strong
Token strong
Feature activation+0.000

INTERVAL 1.555 - 1.749
CONTAINS 0.000%

go
Token go
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
way
Token way
Feature activation+0.000
toward
Token toward
Feature activation+0.000
qu
Token qu
Feature activation+1.571
elling
Tokenelling
Feature activation+0.000
the
Token the
Feature activation+0.000
outrage
Token outrage
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
his
Token his
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
,
Token,
Feature activation+0.000
whilst
Token whilst
Feature activation+0.000
simultaneously
Token simultaneously
Feature activation+1.606
delivering
Token delivering
Feature activation+0.336
sustainable
Token sustainable
Feature activation+0.000
services
Token services
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
will
Token will
Feature activation+0.000
find
Token find
Feature activation+0.000
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
of
Token of
Feature activation+0.047
eventually
Token eventually
Feature activation+1.643
going
Token going
Feature activation+0.539
to
Token to
Feature activation+0.000
Mars
Token Mars
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000

INTERVAL 1.360 - 1.555
CONTAINS 0.001%

For
Token For
Feature activation+0.000
example
Token example
Feature activation+0.000
,
Token,
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
or
Token or
Feature activation+0.000
charging
Token charging
Feature activation+1.421
a
Token a
Feature activation+0.000
battery
Token battery
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
hot
Token hot
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
and
Token and
Feature activation+0.000
begin
Token begin
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.645
ľ
Tokenľ
Feature activation+1.389
question
Tokenquestion
Feature activation+1.293
ing
Tokening
Feature activation+0.000
evolution
Token evolution
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
harder
Token harder
Feature activation+0.000
task
Token task
Feature activation+0.000
of
Token of
Feature activation+0.132
replacement
Token replacement
Feature activation+1.391
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
likely
Token likely
Feature activation+0.000
a
Token a
Feature activation+0.000
can
Tokencan
Feature activation+0.000
accused
Token accused
Feature activation+0.000
Banks
Token Banks
Feature activation+0.000
of
Token of
Feature activation+0.000
def
Token def
Feature activation+0.609
raud
Tokenraud
Feature activation+1.441
ing
Tokening
Feature activation+0.000
him
Token him
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
$
Token $
Feature activation+0.000
interfering
Token interfering
Feature activation+0.041
with
Token with
Feature activation+0.000
or
Token or
Feature activation+0.000
in
Token in
Feature activation+1.483
any
Token any
Feature activation+0.387
way
Token way
Feature activation+1.473
disturbing
Token disturbing
Feature activation+0.343
the
Token the
Feature activation+0.000
possession
Token possession
Feature activation+0.000
or
Token or
Feature activation+0.000
access
Token access
Feature activation+0.000

INTERVAL 1.166 - 1.360
CONTAINS 0.003%

Ŀ
TokenĿ
Feature activation+0.000
and
Token and
Feature activation+0.000
begin
Token begin
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.645
ľ
Tokenľ
Feature activation+1.389
question
Tokenquestion
Feature activation+1.293
ing
Tokening
Feature activation+0.000
evolution
Token evolution
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
ever
Token ever
Feature activation+0.000
British
Token British
Feature activation+0.000
counterpart
Token counterpart
Feature activation+0.000
by
Token by
Feature activation+0.000
second
Token second
Feature activation+1.145
-
Token-
Feature activation+1.211
round
Tokenround
Feature activation+1.294
knockout
Token knockout
Feature activation+0.298
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
other
Token other
Feature activation+0.000
penetration
Token penetration
Feature activation+0.000
aids
Token aids
Feature activation+0.000
capable
Token capable
Feature activation+0.000
of
Token of
Feature activation+0.000
impair
Token impair
Feature activation+1.173
ing
Tokening
Feature activation+0.000
effectiveness
Token effectiveness
Feature activation+0.000
against
Token against
Feature activation+0.000
missile
Token missile
Feature activation+0.000
defenses
Token defenses
Feature activation+0.000
best
Token best
Feature activation+0.000
way
Token way
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.888
ľ
Tokenľ
Feature activation+1.943
ach
Tokenach
Feature activation+1.272
ieving
Tokenieving
Feature activation+0.000
our
Token our
Feature activation+0.000
mutual
Token mutual
Feature activation+0.000
interests
Token interests
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
hesitation
Token hesitation
Feature activation+0.000
supporting
Token supporting
Feature activation+0.000
and
Token and
Feature activation+0.000
co
Token co
Feature activation+1.123
-
Token-
Feature activation+1.133
spons
Tokenspons
Feature activation+1.177
oring
Tokenoring
Feature activation+0.000
this
Token this
Feature activation+0.000
important
Token important
Feature activation+0.000
legislation
Token legislation
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.972 - 1.166
CONTAINS 0.006%

the
Token the
Feature activation+0.000
real
Token real
Feature activation+0.000
work
Token work
Feature activation+0.000
of
Token of
Feature activation+0.000
self
Token self
Feature activation+1.011
-
Token-
Feature activation+1.101
improve
Tokenimprove
Feature activation+0.867
ment
Tokenment
Feature activation+1.003
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
swamp
Token swamp
Feature activation+0.000
y
Tokeny
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
others
Token others
Feature activation+0.000
cont
Token cont
Feature activation+1.094
ending
Tokenending
Feature activation+0.152
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
rocky
Token rocky
Feature activation+0.000
high
Token high
Feature activation+0.000
tool
Token tool
Feature activation+0.000
which
Token which
Feature activation+0.000
helps
Token helps
Feature activation+0.000
in
Token in
Feature activation+0.000
aud
Token aud
Feature activation+0.941
iting
Tokeniting
Feature activation+0.987
the
Token the
Feature activation+0.000
redirect
Token redirect
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
searching
Token searching
Feature activation+0.114
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
better
Token better
Feature activation+0.000
shot
Token shot
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.021
ED
Token ED
Feature activation+0.000
-
Token-
Feature activation+0.000
209
Token209
Feature activation+0.358
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
students
Token students
Feature activation+0.000
proved
Token proved
Feature activation+0.000
their
Token their
Feature activation+0.000
fandom
Token fandom
Feature activation+0.000
by
Token by
Feature activation+0.000
indul
Token indul
Feature activation+1.106
ging
Tokenging
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
most
Token most
Feature activation+0.000
sacred
Token sacred
Feature activation+0.000

INTERVAL 0.777 - 0.972
CONTAINS 0.011%

find
Token find
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
way
Token way
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.888
ľ
Tokenľ
Feature activation+1.943
ach
Tokenach
Feature activation+1.272
ieving
Tokenieving
Feature activation+0.000
our
Token our
Feature activation+0.000
mutual
Token mutual
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
aiming
Token aiming
Feature activation+0.000
at
Token at
Feature activation+0.000
mobile
Token mobile
Feature activation+0.834
to
Token to
Feature activation+0.000
mobile
Token mobile
Feature activation+0.000
connection
Token connection
Feature activation+0.000
.
Token.
Feature activation+0.000
Vin
Token Vin
Feature activation+0.000
some
Token some
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
option
Token option
Feature activation+0.000
of
Token of
Feature activation+0.000
additional
Token additional
Feature activation+0.784
matched
Token matched
Feature activation+0.000
contributions
Token contributions
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
).
Token).
Feature activation+0.000
This
Token This
Feature activation+0.000
will
Token will
Feature activation+0.000
aid
Token aid
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.778
reliability
Token reliability
Feature activation+0.352
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
drums
Token drums
Feature activation+0.000
feeding
Token feeding
Feature activation+0.000
.
Token.
Feature activation+0.000
Perhaps
Token Perhaps
Feature activation+0.000
she
Token she
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
never
Token never
Feature activation+0.800
signed
Token signed
Feature activation+0.000
the
Token the
Feature activation+0.000
Ma
Token Ma
Feature activation+0.000
ast
Tokenast
Feature activation+0.000
rich
Tokenrich
Feature activation+0.000

INTERVAL 0.583 - 0.777
CONTAINS 0.024%

would
Token would
Feature activation+0.000
go
Token go
Feature activation+0.000
some
Token some
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.157
addressing
Token addressing
Feature activation+0.738
local
Token local
Feature activation+0.000
im
Token im
Feature activation+0.000
bal
Tokenbal
Feature activation+0.000
ances
Tokenances
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
indicted
Token indicted
Feature activation+0.000
for
Token for
Feature activation+0.000
em
Token em
Feature activation+0.192
be
Tokenbe
Feature activation+0.471
zz
Tokenzz
Feature activation+0.734
ling
Tokenling
Feature activation+0.000
some
Token some
Feature activation+0.000
$
Token $
Feature activation+0.000
40
Token40
Feature activation+0.000
million
Token million
Feature activation+0.000
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
tread
Token tread
Feature activation+0.735
ing
Tokening
Feature activation+0.000
that
Token that
Feature activation+0.000
path
Token path
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
before
Token before
Feature activation+0.000
initially
Token initially
Feature activation+0.035
cr
Token cr
Feature activation+0.693
amping
Tokenamping
Feature activation+0.530
up
Token up
Feature activation+0.000
,
Token,
Feature activation+0.000
increasing
Token increasing
Feature activation+0.000
both
Token both
Feature activation+0.000
ul
Tokenul
Feature activation+0.000
ieve
Tokenieve
Feature activation+0.000
will
Token will
Feature activation+0.000
begin
Token begin
Feature activation+0.000
in
Token in
Feature activation+0.156
-
Token-
Feature activation+0.679
store
Tokenstore
Feature activation+0.242
sales
Token sales
Feature activation+0.048
Tuesday
Token Tuesday
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.389 - 0.583
CONTAINS 0.064%

in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
fut
Token fut
Feature activation+0.000
ility
Tokenility
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.468
inevitable
Token inevitable
Feature activation+0.095
attempts
Token attempts
Feature activation+0.000
to
Token to
Feature activation+0.000
assimil
Token assimil
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
of
Token of
Feature activation+0.000
continuing
Token continuing
Feature activation+0.145
to
Token to
Feature activation+0.000
improve
Token improve
Feature activation+0.000
by
Token by
Feature activation+0.000
its
Token its
Feature activation+0.393
own
Token own
Feature activation+0.425
inherent
Token inherent
Feature activation+0.000
activity
Token activity
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
tool
Token tool
Feature activation+0.000
for
Token for
Feature activation+0.000
aqu
Token aqu
Feature activation+0.363
ac
Tokenac
Feature activation+0.407
ulture
Tokenulture
Feature activation+0.393
to
Token to
Feature activation+0.000
gain
Token gain
Feature activation+0.000
better
Token better
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
currently
Token currently
Feature activation+0.000
lim
Token lim
Feature activation+0.577
ping
Tokenping
Feature activation+0.000
along
Token along
Feature activation+0.000
in
Token in
Feature activation+0.000
C
Token C
Feature activation+0.000
++
Token++
Feature activation+0.000
'm
Token'm
Feature activation+0.000
happy
Token happy
Feature activation+0.000
to
Token to
Feature activation+0.000
insist
Token insist
Feature activation+0.000
on
Token on
Feature activation+0.000
my
Token my
Feature activation+0.538
red
Token red
Feature activation+0.001
lines
Token lines
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000

INTERVAL 0.194 - 0.389
CONTAINS 0.163%

Death
Token Death
Feature activation+0.000
Star
Token Star
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.092
in
Token in
Feature activation+0.000
turn
Token turn
Feature activation+0.197
,
Token,
Feature activation+0.422
the
Token the
Feature activation+0.386
Empire
Token Empire
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
sold
Tokensold
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
instead
Token instead
Feature activation+0.000
favoring
Token favoring
Feature activation+0.232
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.013
dr
Tokendr
Feature activation+0.000
ill
Tokenill
Feature activation+0.000
holes
Token holes
Feature activation+0.000
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
middle
Token middle
Feature activation+0.000
of
Token of
Feature activation+0.000
any
Token any
Feature activation+0.303
sane
Token sane
Feature activation+0.000
political
Token political
Feature activation+0.000
spectrum
Token spectrum
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
because
Token because
Feature activation+0.000
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
capable
Token capable
Feature activation+0.000
of
Token of
Feature activation+0.000
being
Token being
Feature activation+0.298
just
Token just
Feature activation+0.000
as
Token as
Feature activation+0.000
sorry
Token sorry
Feature activation+0.000
as
Token as
Feature activation+0.000
you
Token you
Feature activation+0.000
blamed
Token blamed
Feature activation+0.000
the
Token the
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+0.000
for
Token for
Feature activation+0.000
pedd
Token pedd
Feature activation+0.378
ling
Tokenling
Feature activation+0.000
it
Token it
Feature activation+0.000
and
Token and
Feature activation+0.000
mishand
Token mishand
Feature activation+0.000
ling
Tokenling
Feature activation+0.000

INTERVAL 0.000 - 0.194
CONTAINS 99.727%

Rats
Token Rats
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
taken
Token taken
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
been
Token been
Feature activation+0.000
done
Token done
Feature activation+0.000
already
Token already
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Q
TokenQ
Feature activation+0.000
:
Token:
Feature activation+0.000
Will
Token Will
Feature activation+0.000
airplanes
Token airplanes
Feature activation+0.000
carried
Token carried
Feature activation+0.000
twenty
Token twenty
Feature activation+0.000
-
Token-
Feature activation+0.000
pound
Tokenpound
Feature activation+0.000
bombs
Token bombs
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
one
Token one
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
were
Token were
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
perceived
Token perceived
Feature activation+0.000
as
Token as
Feature activation+0.000
of
Token of
Feature activation+0.000
color
Token color
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
That
TokenThat
Feature activation+0.000
argument
Token argument
Feature activation+0.000
turned
Token turned
Feature activation+0.000
especially
Token especially
Feature activation+0.000
bitter
Token bitter
Feature activation+0.000
last
Token last
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 7 in H7.0: (feature 27049)

TOP ACTIVATIONS
MAX = 2.437

was
Token was
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
serious
Token serious
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+2.437
the
Token the
Feature activation+2.104
scale
Token scale
Feature activation+0.273
(
Token (
Feature activation+0.643
h
Tokenh
Feature activation+0.000
onest
Tokenonest
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
serious
Token serious
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+2.437
the
Token the
Feature activation+2.104
scale
Token scale
Feature activation+0.273
(
Token (
Feature activation+0.643
h
Tokenh
Feature activation+0.000
onest
Tokenonest
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
8
Token8
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
.
Token.
Feature activation+0.682
4
Token4
Feature activation+0.000
.
Token.
Feature activation+1.999
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
Google
Token Google
Feature activation+0.000
DNS
Token DNS
Feature activation+0.000
all
Tokenall
Feature activation+0.000
,
Token,
Feature activation+0.000
be
Token be
Feature activation+0.000
-
Token-
Feature activation+0.000
all
Tokenall
Feature activation+0.000
no
Token no
Feature activation+1.839
matter
Token matter
Feature activation+1.027
what
Token what
Feature activation+0.000
in
Token in
Feature activation+0.051
any
Token any
Feature activation+0.000
situation
Token situation
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
man
Token man
Feature activation+0.000
standing
Token standing
Feature activation+0.000
in
Token in
Feature activation+1.835
that
Token that
Feature activation+0.000
locker
Token locker
Feature activation+0.000
room
Token room
Feature activation+0.000
.
Token.
Feature activation+0.000
Everyone
Token Everyone
Feature activation+0.000
174
Token 174
Feature activation+0.000
S
Token S
Feature activation+0.000
.
Token.
Feature activation+0.000
Howard
Token Howard
Feature activation+0.000
St
Token St
Feature activation+0.628
.,
Token.,
Feature activation+1.826
Spokane
Token Spokane
Feature activation+0.406
,
Token,
Feature activation+0.000
WA
Token WA
Feature activation+0.000
from
Token from
Feature activation+0.000
6
Token 6
Feature activation+0.000
'm
Token'm
Feature activation+0.000
going
Token going
Feature activation+0.000
mean
Token mean
Feature activation+0.000
and
Token and
Feature activation+0.000
large
Token large
Feature activation+0.171
and
Token and
Feature activation+1.803
referencing
Token referencing
Feature activation+0.000
probably
Token probably
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
gov
Tokengov
Feature activation+0.000
and
Token and
Feature activation+0.000
army
Token army
Feature activation+0.000
.
Token.
Feature activation+0.000
mil
Tokenmil
Feature activation+0.000
.
Token.
Feature activation+1.780
The
Token The
Feature activation+0.000
information
Token information
Feature activation+0.000
also
Token also
Feature activation+0.000
includes
Token includes
Feature activation+0.000
work
Token work
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
often
Tokenoften
Feature activation+0.000
unpredictable
Token unpredictable
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
process
Tokenprocess
Feature activation+0.000
and
Token and
Feature activation+1.744
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
consequence
Token consequence
Feature activation+0.000
,
Token,
Feature activation+0.198
the
Token the
Feature activation+0.000
investment
Token investment
Feature activation+0.000
bankers
Token bankers
Feature activation+0.000
came
Token came
Feature activation+0.000
knocking
Token knocking
Feature activation+0.355
on
Token on
Feature activation+1.688
the
Token the
Feature activation+0.862
door
Token door
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Me
Token Me
Feature activation+0.000
H
Token H
Feature activation+0.000
anging
Tokenanging
Feature activation+0.000
Like
Token Like
Feature activation+0.000
That
Token That
Feature activation+0.000
Bru
Token Bru
Feature activation+1.572
h
Tokenh
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
R
Token R
Feature activation+0.000
ICH
TokenICH
Feature activation+0.000
gang
Token gang
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
what
Token what
Feature activation+0.000
's
Token's
Feature activation+1.550
more
Token more
Feature activation+0.000
obnoxious
Token obnoxious
Feature activation+0.691
that
Token that
Feature activation+0.000
14
Token 14
Feature activation+0.000
year
Token year
Feature activation+0.000
rich
Tokenrich
Feature activation+0.000
had
Token had
Feature activation+0.000
it
Token it
Feature activation+0.000
so
Token so
Feature activation+0.000
good
Token good
Feature activation+0.047
and
Token and
Feature activation+1.539
,
Token,
Feature activation+0.000
until
Token until
Feature activation+0.000
recently
Token recently
Feature activation+0.000
,
Token,
Feature activation+0.452
it
Token it
Feature activation+0.000
condos
Token condos
Feature activation+0.000
,
Token,
Feature activation+0.000
restaurants
Token restaurants
Feature activation+0.000
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.000
focused
Token focused
Feature activation+1.516
on
Token on
Feature activation+0.059
the
Token the
Feature activation+0.000
Latino
Token Latino
Feature activation+0.000
community
Token community
Feature activation+0.000
.
Token.
Feature activation+0.000
below
Token below
Feature activation+0.000
the
Token the
Feature activation+0.000
free
Token free
Feature activation+0.000
throw
Token throw
Feature activation+0.000
line
Token line
Feature activation+0.000
extended
Token extended
Feature activation+1.509
for
Token for
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
five
Token five
Feature activation+0.000
seconds
Token seconds
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Story
TokenStory
Feature activation+0.000
continues
Token continues
Feature activation+0.000
below
Token below
Feature activation+0.000
advertisement
Token advertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.490
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
was
Token was
Feature activation+0.000
answering
Token answering
Feature activation+0.000
a
Token a
Feature activation+0.000
be
Token be
Feature activation+0.000
continued
Token continued
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
format
Token format
Feature activation+0.000
and
Token and
Feature activation+1.490
will
Token will
Feature activation+0.000
evolve
Token evolve
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
reader
Token reader
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
,
Token,
Feature activation+0.000
hold
Token hold
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+1.476
sec
Token sec
Feature activation+0.026
.
Token.
Feature activation+1.307
Not
Token Not
Feature activation+0.304
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.042
Ċ
TokenĊ
Feature activation+0.000
Story
TokenStory
Feature activation+0.000
continues
Token continues
Feature activation+0.000
below
Token below
Feature activation+0.000
advertisement
Token advertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.464
Ċ
TokenĊ
Feature activation+0.120
Act
TokenAct
Feature activation+0.000
ing
Tokening
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
popular
Token popular
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
them
Token them
Feature activation+0.000
illicit
Token illicit
Feature activation+1.459
ly
Tokenly
Feature activation+0.295
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Introdu
TokenIntrodu
Feature activation+0.000

Top DFA by src position
MAX = 2.983

crime
Token crime
Feature activation-0.033
Top resid features:
was
Token was
Feature activation-0.004
Top resid features:
on
Token on
Feature activation-0.009
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
serious
Token serious
Feature activation-0.002
Top resid features:
end
Token end
Feature activation+2.983
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
scale
Token scale
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
h
Tokenh
Feature activation+0.000
Top resid features:
crime
Token crime
Feature activation-0.016
Top resid features:
was
Token was
Feature activation+0.004
Top resid features:
on
Token on
Feature activation-0.012
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
serious
Token serious
Feature activation+0.004
Top resid features:
end
Token end
Feature activation+2.527
Top resid features:
of
Token of
Feature activation+0.073
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
scale
Token scale
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
h
Tokenh
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
8
Token8
Feature activation-0.016
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
4
Token4
Feature activation+0.394
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
4
Token4
Feature activation+2.201
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
While
TokenWhile
Feature activation+0.000
Top resid features:
Google
Token Google
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
all
Tokenall
Feature activation-0.012
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
be
Token be
Feature activation-0.007
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
all
Tokenall
Feature activation+2.340
Top resid features:
no
Token no
Feature activation+0.004
Top resid features:
matter
Token matter
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
Lang
Token Lang
Feature activation+0.001
Top resid features:
was
Token was
Feature activation-0.009
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
last
Token last
Feature activation+0.005
Top resid features:
man
Token man
Feature activation-0.020
Top resid features:
standing
Token standing
Feature activation+2.354
Top resid features:
in
Token in
Feature activation-0.009
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
locker
Token locker
Feature activation+0.000
Top resid features:
room
Token room
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.028
Top resid features:
174
Token 174
Feature activation-0.005
Top resid features:
S
Token S
Feature activation-0.004
Top resid features:
.
Token.
Feature activation-0.015
Top resid features:
Howard
Token Howard
Feature activation+0.003
Top resid features:
St
Token St
Feature activation+2.328
Top resid features:
.,
Token.,
Feature activation+0.059
Top resid features:
Spokane
Token Spokane
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
WA
Token WA
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.010
Top resid features:
'm
Token'm
Feature activation+0.033
Top resid features:
going
Token going
Feature activation-0.013
Top resid features:
mean
Token mean
Feature activation-0.009
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
large
Token large
Feature activation+2.121
Top resid features:
and
Token and
Feature activation+0.115
Top resid features:
referencing
Token referencing
Feature activation+0.000
Top resid features:
probably
Token probably
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
gov
Tokengov
Feature activation+0.073
Top resid features:
and
Token and
Feature activation-0.011
Top resid features:
army
Token army
Feature activation-0.015
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
mil
Tokenmil
Feature activation+2.180
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
information
Token information
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.000
Top resid features:
includes
Token includes
Feature activation+0.000
Top resid features:
difficult
Token difficult
Feature activation-0.036
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation-0.008
Top resid features:
often
Tokenoften
Feature activation-0.005
Top resid features:
unpredictable
Token unpredictable
Feature activation-0.006
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation-0.003
Top resid features:
process
Tokenprocess
Feature activation+2.379
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
consequence
Token consequence
Feature activation+0.000
Top resid features:
before
Token before
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
investment
Token investment
Feature activation-0.004
Top resid features:
bankers
Token bankers
Feature activation-0.023
Top resid features:
came
Token came
Feature activation+0.017
Top resid features:
knocking
Token knocking
Feature activation+2.120
Top resid features:
on
Token on
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
door
Token door
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Leave
Token Leave
Feature activation-0.007
Top resid features:
Me
Token Me
Feature activation+0.001
Top resid features:
H
Token H
Feature activation-0.003
Top resid features:
anging
Tokenanging
Feature activation+0.001
Top resid features:
Like
Token Like
Feature activation-0.012
Top resid features:
That
Token That
Feature activation+1.986
Top resid features:
Bru
Token Bru
Feature activation-0.004
Top resid features:
h
Tokenh
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
R
Token R
Feature activation+0.000
Top resid features:
ICH
TokenICH
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
But
TokenBut
Feature activation-0.021
Top resid features:
you
Token you
Feature activation-0.003
Top resid features:
know
Token know
Feature activation+0.010
Top resid features:
what
Token what
Feature activation+2.049
Top resid features:
's
Token's
Feature activation-0.004
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
obnoxious
Token obnoxious
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
14
Token 14
Feature activation+0.000
Top resid features:
super
Token super
Feature activation+0.007
Top resid features:
rich
Tokenrich
Feature activation+0.022
Top resid features:
had
Token had
Feature activation+0.005
Top resid features:
it
Token it
Feature activation+0.056
Top resid features:
so
Token so
Feature activation+0.090
Top resid features:
good
Token good
Feature activation+1.742
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
until
Token until
Feature activation+0.000
Top resid features:
recently
Token recently
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.014
Top resid features:
condos
Token condos
Feature activation-0.005
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
restaurants
Token restaurants
Feature activation-0.014
Top resid features:
and
Token and
Feature activation-0.021
Top resid features:
more
Token more
Feature activation+2.112
Top resid features:
focused
Token focused
Feature activation-0.003
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Latino
Token Latino
Feature activation+0.000
Top resid features:
community
Token community
Feature activation+0.000
Top resid features:
basket
Token basket
Feature activation+0.131
Top resid features:
below
Token below
Feature activation-0.005
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
free
Token free
Feature activation-0.001
Top resid features:
throw
Token throw
Feature activation+0.129
Top resid features:
line
Token line
Feature activation+1.668
Top resid features:
extended
Token extended
Feature activation+0.022
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
five
Token five
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.026
Top resid features:
Story
TokenStory
Feature activation+0.018
Top resid features:
continues
Token continues
Feature activation-0.005
Top resid features:
below
Token below
Feature activation+0.004
Top resid features:
advertisement
Token advertisement
Feature activation+1.958
Top resid features:
Ċ
TokenĊ
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
He
TokenHe
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
answering
Token answering
Feature activation+0.000
Top resid features:
to
Tokento
Feature activation-0.001
Top resid features:
be
Token be
Feature activation+0.010
Top resid features:
continued
Token continued
Feature activation+0.007
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ŀ
TokenĿ
Feature activation+0.014
Top resid features:
format
Token format
Feature activation+2.021
Top resid features:
and
Token and
Feature activation+0.014
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
evolve
Token evolve
Feature activation+0.000
Top resid features:
based
Token based
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Now
TokenNow
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
hold
Token hold
Feature activation-0.033
Top resid features:
on
Token on
Feature activation+1.916
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
sec
Token sec
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Not
Token Not
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.020
Top resid features:
Story
TokenStory
Feature activation+0.036
Top resid features:
continues
Token continues
Feature activation-0.004
Top resid features:
below
Token below
Feature activation+0.006
Top resid features:
advertisement
Token advertisement
Feature activation+1.858
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Act
TokenAct
Feature activation+0.000
Top resid features:
ing
Tokening
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
most
Token most
Feature activation-0.015
Top resid features:
popular
Token popular
Feature activation+0.001
Top resid features:
way
Token way
Feature activation+0.031
Top resid features:
to
Token to
Feature activation+0.027
Top resid features:
use
Token use
Feature activation+0.038
Top resid features:
them
Token them
Feature activation+1.744
Top resid features:
illicit
Token illicit
Feature activation+0.026
Top resid features:
ly
Tokenly
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.57

Head 1: 0.02

Head 2: 0.03

Head 3: 0.06

Head 4: 0.06

Head 5: 0.03

Head 6: 0.03

Head 7: 0.03

Head 8: 0.07

Head 9: 0.05

Head 10: 0.02

Head 11: 0.02

Positive logits

etheless3.26

withstanding2.27

cause2.21

ometimes1.99

respective1.95

agree1.94

nonetheless1.91

theless1.89

.}1.85

fortunately1.84

nevertheless1.83

ilaterally1.83

.<1.79

hence1.76

itionally1.75

anwhile1.75

ocally1.72

thereby1.71

ortunately1.71

because1.70

Negative logits

logger-1.70

porary-1.57

fist-1.51

essor-1.49

Grain-1.46

psons-1.46

fir-1.42

paddle-1.42

Parm-1.41

rets-1.40

oret-1.38

gged-1.38

companion-1.37

lockout-1.36

DVD-1.36

kt-1.35

Movies-1.35

Fund-1.35

annels-1.34

sequel-1.34

INTERVAL 2.193 - 2.437
CONTAINS 0.000%

was
Token was
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
serious
Token serious
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+2.437
the
Token the
Feature activation+2.104
scale
Token scale
Feature activation+0.273
(
Token (
Feature activation+0.643
h
Tokenh
Feature activation+0.000
onest
Tokenonest
Feature activation+0.000

INTERVAL 1.950 - 2.193
CONTAINS 0.000%

8
Token8
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
.
Token.
Feature activation+0.682
4
Token4
Feature activation+0.000
.
Token.
Feature activation+1.999
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
Google
Token Google
Feature activation+0.000
DNS
Token DNS
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
serious
Token serious
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+2.437
the
Token the
Feature activation+2.104
scale
Token scale
Feature activation+0.273
(
Token (
Feature activation+0.643
h
Tokenh
Feature activation+0.000
onest
Tokenonest
Feature activation+0.000
ly
Tokenly
Feature activation+0.000

INTERVAL 1.706 - 1.950
CONTAINS 0.001%

âĢĶ
TokenâĢĶ
Feature activation+0.000
often
Tokenoften
Feature activation+0.000
unpredictable
Token unpredictable
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
process
Tokenprocess
Feature activation+0.000
and
Token and
Feature activation+1.744
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
consequence
Token consequence
Feature activation+0.000
,
Token,
Feature activation+0.198
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
man
Token man
Feature activation+0.000
standing
Token standing
Feature activation+0.000
in
Token in
Feature activation+1.835
that
Token that
Feature activation+0.000
locker
Token locker
Feature activation+0.000
room
Token room
Feature activation+0.000
.
Token.
Feature activation+0.000
Everyone
Token Everyone
Feature activation+0.000
'm
Token'm
Feature activation+0.000
going
Token going
Feature activation+0.000
mean
Token mean
Feature activation+0.000
and
Token and
Feature activation+0.000
large
Token large
Feature activation+0.171
and
Token and
Feature activation+1.803
referencing
Token referencing
Feature activation+0.000
probably
Token probably
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
gov
Tokengov
Feature activation+0.000
and
Token and
Feature activation+0.000
army
Token army
Feature activation+0.000
.
Token.
Feature activation+0.000
mil
Tokenmil
Feature activation+0.000
.
Token.
Feature activation+1.780
The
Token The
Feature activation+0.000
information
Token information
Feature activation+0.000
also
Token also
Feature activation+0.000
includes
Token includes
Feature activation+0.000
work
Token work
Feature activation+0.000
174
Token 174
Feature activation+0.000
S
Token S
Feature activation+0.000
.
Token.
Feature activation+0.000
Howard
Token Howard
Feature activation+0.000
St
Token St
Feature activation+0.628
.,
Token.,
Feature activation+1.826
Spokane
Token Spokane
Feature activation+0.406
,
Token,
Feature activation+0.000
WA
Token WA
Feature activation+0.000
from
Token from
Feature activation+0.000
6
Token 6
Feature activation+0.000

INTERVAL 1.462 - 1.706
CONTAINS 0.001%

be
Token be
Feature activation+0.000
continued
Token continued
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
format
Token format
Feature activation+0.000
and
Token and
Feature activation+1.490
will
Token will
Feature activation+0.000
evolve
Token evolve
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
reader
Token reader
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Story
TokenStory
Feature activation+0.000
continues
Token continues
Feature activation+0.000
below
Token below
Feature activation+0.000
advertisement
Token advertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.464
Ċ
TokenĊ
Feature activation+0.120
Act
TokenAct
Feature activation+0.000
ing
Tokening
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
Me
Token Me
Feature activation+0.000
H
Token H
Feature activation+0.000
anging
Tokenanging
Feature activation+0.000
Like
Token Like
Feature activation+0.000
That
Token That
Feature activation+0.000
Bru
Token Bru
Feature activation+1.572
h
Tokenh
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
R
Token R
Feature activation+0.000
ICH
TokenICH
Feature activation+0.000
gang
Token gang
Feature activation+0.000
the
Token the
Feature activation+0.000
investment
Token investment
Feature activation+0.000
bankers
Token bankers
Feature activation+0.000
came
Token came
Feature activation+0.000
knocking
Token knocking
Feature activation+0.355
on
Token on
Feature activation+1.688
the
Token the
Feature activation+0.862
door
Token door
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
what
Token what
Feature activation+0.000
's
Token's
Feature activation+1.550
more
Token more
Feature activation+0.000
obnoxious
Token obnoxious
Feature activation+0.691
that
Token that
Feature activation+0.000
14
Token 14
Feature activation+0.000
year
Token year
Feature activation+0.000

INTERVAL 1.218 - 1.462
CONTAINS 0.006%

Ċ
TokenĊ
Feature activation+0.000
Story
TokenStory
Feature activation+0.000
continues
Token continues
Feature activation+0.000
below
Token below
Feature activation+0.000
advertisement
Token advertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.323
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
College
Token College
Feature activation+0.000
of
Token of
Feature activation+0.000
Tr
Token Tr
Feature activation+0.000
People
Token People
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Republic
Token Republic
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.248
Ļ
TokenĻ
Feature activation+1.346
s
Tokens
Feature activation+0.000
(
Token (
Feature activation+0.000
D
TokenD
Feature activation+0.000
PR
TokenPR
Feature activation+0.000
MO
TokenMO
Feature activation+0.000
timing
Token timing
Feature activation+0.153
(
Token (
Feature activation+0.000
left
Tokenleft
Feature activation+0.000
)
Token)
Feature activation+0.387
and
Token and
Feature activation+1.244
1
Token 1
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
small
Token small
Feature activation+0.000
phase
Token phase
Feature activation+0.000
very
Token very
Feature activation+0.000
big
Token big
Feature activation+0.000
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
a
Token a
Feature activation+1.232
change
Token change
Feature activation+0.000
like
Token like
Feature activation+0.000
this
Token this
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
actually
Token actually
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
war
Token war
Feature activation+0.000
zone
Token zone
Feature activation+0.000
out
Token out
Feature activation+1.402
there
Token there
Feature activation+0.677
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
99
Token 99
Feature activation+0.000
out
Token out
Feature activation+0.000

INTERVAL 0.975 - 1.218
CONTAINS 0.016%

that
Token that
Feature activation+0.000
Bitcoin
Token Bitcoin
Feature activation+0.000
was
Token was
Feature activation+0.000
worth
Token worth
Feature activation+0.000
money
Token money
Feature activation+0.000
he
Token he
Feature activation+0.975
pulled
Token pulled
Feature activation+0.000
his
Token his
Feature activation+0.000
coins
Token coins
Feature activation+0.000
into
Token into
Feature activation+0.000
an
Token an
Feature activation+0.000
the
Token the
Feature activation+0.000
Leeds
Token Leeds
Feature activation+0.000
badge
Token badge
Feature activation+0.000
of
Token of
Feature activation+0.935
honour
Token honour
Feature activation+0.335
and
Token and
Feature activation+1.021
to
Token to
Feature activation+0.000
don
Token don
Feature activation+0.000
the
Token the
Feature activation+0.000
famous
Token famous
Feature activation+0.000
white
Token white
Feature activation+0.000
failed
Token failed
Feature activation+0.000
,
Token,
Feature activation+0.012
52
Token 52
Feature activation+0.011
to
Token to
Feature activation+0.000
48
Token 48
Feature activation+0.000
.
Token.
Feature activation+1.092
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
To
Token To
Feature activation+0.000
ome
Tokenome
Feature activation+0.000
:
Token:
Feature activation+0.050
Repeat
Token Repeat
Feature activation+0.000
R
Token R
Feature activation+0.000
nd
Tokennd
Feature activation+0.000
1
Token 1
Feature activation+0.000
Fast
Token Fast
Feature activation+1.029
en
Tokenen
Feature activation+0.313
off
Token off
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
the
Token the
Feature activation+0.000
band
Token band
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
and
Token and
Feature activation+1.176
has
Token has
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
credibility
Token credibility
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.731 - 0.975
CONTAINS 0.045%

some
Token some
Feature activation+0.000
form
Token form
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+0.019
other
Token other
Feature activation+0.000
even
Token even
Feature activation+0.923
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
passing
Token passing
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
full
Token full
Feature activation+0.000
wedding
Token wedding
Feature activation+0.000
breakfast
Token breakfast
Feature activation+0.000
to
Token to
Feature activation+0.000
follow
Token follow
Feature activation+0.000
the
Token the
Feature activation+0.818
ceremony
Token ceremony
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sea
TokenSea
Feature activation+0.000
Julius
Token Julius
Feature activation+0.000
Max
Token Max
Feature activation+0.000
imil
Tokenimil
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
University
Token University
Feature activation+0.000
W
Token W
Feature activation+0.756
ür
Tokenür
Feature activation+0.000
z
Tokenz
Feature activation+0.000
burg
Tokenburg
Feature activation+0.143
made
Token made
Feature activation+0.000
the
Token the
Feature activation+0.000
should
Token should
Feature activation+0.000
take
Token take
Feature activation+0.000
advantage
Token advantage
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.713
week
Token week
Feature activation+0.790
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
five
Token five
Feature activation+0.000
hitting
Token hitting
Feature activation+0.000
matchups
Token matchups
Feature activation+0.000
of
Token of
Feature activation+0.000
where
Token where
Feature activation+0.000
our
Token our
Feature activation+0.000
identity
Token identity
Feature activation+0.000
resides
Token resides
Feature activation+0.000
and
Token and
Feature activation+0.816
what
Token what
Feature activation+0.000
are
Token are
Feature activation+0.000
its
Token its
Feature activation+0.000
ir
Token ir
Feature activation+0.000
red
Tokenred
Feature activation+0.000

INTERVAL 0.487 - 0.731
CONTAINS 0.141%

booted
Token booted
Feature activation+0.000
in
Token in
Feature activation+0.000
about
Token about
Feature activation+0.000
6
Token 6
Feature activation+0.000
months
Token months
Feature activation+0.000
of
Token of
Feature activation+0.608
kernel
Token kernel
Feature activation+0.000
releases
Token releases
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
did
Token did
Feature activation+0.000
sentenced
Token sentenced
Feature activation+0.000
on
Token on
Feature activation+0.000
September
Token September
Feature activation+0.000
25
Token 25
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.545
The
TokenThe
Feature activation+0.000
court
Token court
Feature activation+0.000
heard
Token heard
Feature activation+0.000
Woodward
Token Woodward
Feature activation+0.000
had
Token had
Feature activation+0.000
?).
Token?).
Feature activation+0.000
All
Token All
Feature activation+0.000
you
Token you
Feature activation+0.000
need
Token need
Feature activation+0.000
now
Token now
Feature activation+1.158
is
Token is
Feature activation+0.519
to
Token to
Feature activation+0.000
write
Token write
Feature activation+0.000
some
Token some
Feature activation+0.000
simple
Token simple
Feature activation+0.000
script
Token script
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Be
TokenBe
Feature activation+0.000
a
Token a
Feature activation+0.000
hero
Token hero
Feature activation+0.000
,
Token,
Feature activation+0.604
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
zero
Token zero
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
or
Token or
Feature activation+0.103
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
disorderly
Token disorderly
Feature activation+0.000
one
Token one
Feature activation+0.000
,
Token,
Feature activation+0.629
for
Token for
Feature activation+0.000
that
Token that
Feature activation+0.000
matter
Token matter
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.114
some
Token some
Feature activation+0.000

INTERVAL 0.244 - 0.487
CONTAINS 0.494%

goods
Token goods
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
grocery
Token grocery
Feature activation+0.000
staples
Token staples
Feature activation+0.000
(
Token (
Feature activation+0.456
mil
Tokenmil
Feature activation+0.000
k
Tokenk
Feature activation+0.000
,
Token,
Feature activation+0.000
eggs
Token eggs
Feature activation+0.000
,
Token,
Feature activation+0.000
BR
Token BR
Feature activation+0.000
D
TokenD
Feature activation+0.000
principal
Token principal
Feature activation+0.000
Raj
Token Raj
Feature activation+0.094
ee
Tokenee
Feature activation+0.000
v
Tokenv
Feature activation+0.402
Mish
Token Mish
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
,
Token,
Feature activation+0.000
chief
Token chief
Feature activation+0.000
ana
Token ana
Feature activation+0.000
Room
Token Room
Feature activation+0.000
at
Token at
Feature activation+0.000
211
Token 211
Feature activation+0.000
Peters
Token Peters
Feature activation+0.000
St
Token St
Feature activation+0.181
.
Token.
Feature activation+0.352
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.000
driving
Token driving
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
truth
Tokentruth
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.309
Ŀ
TokenĿ
Feature activation+0.259
may
Token may
Feature activation+0.031
be
Token be
Feature activation+0.170
,
Token,
Feature activation+0.000
Kanye
Token Kanye
Feature activation+0.000
is
Token is
Feature activation+0.000
middle
Token middle
Feature activation+0.000
ware
Tokenware
Feature activation+0.000
business
Token business
Feature activation+0.000
picked
Token picked
Feature activation+0.000
up
Token up
Feature activation+0.000
too
Token too
Feature activation+0.452
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
closed
Token closed
Feature activation+0.000

INTERVAL 0.000 - 0.244
CONTAINS 99.297%

exclusion
Token exclusion
Feature activation+0.000
of
Token of
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
continued
Token continued
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
did
Token did
Feature activation+0.000
the
Token the
Feature activation+0.000
mobil
Token mobil
Feature activation+0.000
izations
Tokenizations
Feature activation+0.000
.
Token.
Feature activation+0.000
af
Tokenaf
Feature activation+0.000
rost
Tokenrost
Feature activation+0.000
once
Token once
Feature activation+0.000
existed
Token existed
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
study
Token study
Feature activation+0.000
,
Token,
Feature activation+0.000
led
Token led
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
'
Token '
Feature activation+0.000
Muslim
TokenMuslim
Feature activation+0.000
Patrol
Token Patrol
Feature activation+0.000
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
must
Token must
Feature activation+0.000
read
Token read
Feature activation+0.000
the
Token the
Feature activation+0.000
precautions
Token precautions
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
drugs
Token drugs
Feature activation+0.000
outlined
Token outlined
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
manufacturer
Token manufacturer
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
more
Token more
Feature activation+0.000
discreet
Token discreet
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.115
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.115
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.115
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 8 in H7.0: (feature 26913)

TOP ACTIVATIONS
MAX = 3.763

has
Token has
Feature activation+0.000
evolved
Token evolved
Feature activation+0.000
greatly
Token greatly
Feature activation+0.000
since
Token since
Feature activation+0.000
those
Token those
Feature activation+0.000
early
Token early
Feature activation+3.763
days
Token days
Feature activation+0.730
and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.000
seen
Token seen
Feature activation+0.000
four
Token four
Feature activation+0.000
note
Token note
Feature activation+0.000
,
Token,
Feature activation+0.000
hopefully
Token hopefully
Feature activation+0.000
those
Token those
Feature activation+0.000
magn
Token magn
Feature activation+2.035
animous
Tokenanimous
Feature activation+3.711
souls
Token souls
Feature activation+2.071
who
Token who
Feature activation+0.000
were
Token were
Feature activation+0.025
eager
Token eager
Feature activation+0.258
to
Token to
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
.
Token.
Feature activation+0.000
Those
Token Those
Feature activation+0.000
ward
Token ward
Feature activation+3.679
leaders
Token leaders
Feature activation+2.600
head
Token head
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+0.000
need
Token need
Feature activation+0.000
a
Token a
Feature activation+0.000
gym
Token gym
Feature activation+0.000
for
Token for
Feature activation+0.000
those
Token those
Feature activation+0.000
rainy
Token rainy
Feature activation+3.557
days
Token days
Feature activation+2.858
âĢĵ
Token âĢĵ
Feature activation+0.000
check
Token check
Feature activation+0.000
The
Token The
Feature activation+0.000
Gym
Token Gym
Feature activation+0.000
Without
Token Without
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
those
Token those
Feature activation+0.000
spell
Token spell
Feature activation+2.526
binding
Tokenbinding
Feature activation+3.554
battle
Token battle
Feature activation+1.030
scenes
Token scenes
Feature activation+0.184
would
Token would
Feature activation+0.000
not
Token not
Feature activation+0.000
have
Token have
Feature activation+0.000
among
Token among
Feature activation+0.000
those
Token those
Feature activation+0.000
same
Token same
Feature activation+2.327
Scottish
Token Scottish
Feature activation+3.231
-
Token-
Feature activation+1.681
based
Tokenbased
Feature activation+3.501
major
Token major
Feature activation+1.611
financial
Token financial
Feature activation+0.000
institutions
Token institutions
Feature activation+2.462
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
g
Tokeng
Feature activation+0.000
ates
Tokenates
Feature activation+0.000
open
Token open
Feature activation+0.000
and
Token and
Feature activation+0.000
those
Token those
Feature activation+0.000
middle
Token middle
Feature activation+3.469
men
Tokenmen
Feature activation+1.653
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
politically
Token politically
Feature activation+0.000
charged
Token charged
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
accuracy
Token accuracy
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
sources
Token sources
Feature activation+3.452
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
material
Token material
Feature activation+0.000
has
Token has
Feature activation+0.000
here
Token here
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Let
TokenLet
Feature activation+0.000
those
Token those
Feature activation+0.000
creative
Token creative
Feature activation+3.406
juices
Token juices
Feature activation+2.141
flow
Token flow
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
clearly
Token clearly
Feature activation+0.000
,
Token,
Feature activation+0.000
especially
Token especially
Feature activation+0.000
for
Token for
Feature activation+0.000
those
Token those
Feature activation+0.000
authors
Token authors
Feature activation+3.313
who
Token who
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
do
Token do
Feature activation+0.000
values
Token values
Feature activation+0.000
."
Token."
Feature activation+0.000
Rel
TokenRel
Feature activation+0.000
ating
Tokenating
Feature activation+0.000
those
Token those
Feature activation+0.000
undeniable
Token undeniable
Feature activation+3.261
rights
Token rights
Feature activation+0.743
to
Token to
Feature activation+0.000
tech
Token tech
Feature activation+0.000
,
Token,
Feature activation+0.000
Cook
Token Cook
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
when
Token when
Feature activation+0.000
those
Token those
Feature activation+0.000
grinding
Token grinding
Feature activation+3.258
stomach
Token stomach
Feature activation+0.000
noises
Token noises
Feature activation+1.844
rise
Token rise
Feature activation+0.000
up
Token up
Feature activation+0.000
from
Token from
Feature activation+0.000
of
Token of
Feature activation+0.000
relief
Token relief
Feature activation+0.000
among
Token among
Feature activation+0.000
those
Token those
Feature activation+0.000
same
Token same
Feature activation+2.327
Scottish
Token Scottish
Feature activation+3.231
-
Token-
Feature activation+1.681
based
Tokenbased
Feature activation+3.501
major
Token major
Feature activation+1.611
financial
Token financial
Feature activation+0.000
institutions
Token institutions
Feature activation+2.462
dinner
Token dinner
Feature activation+0.000
party
Token party
Feature activation+0.000
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000
same
Token same
Feature activation+3.111
elite
Token elite
Feature activation+3.230
neighborhoods
Token neighborhoods
Feature activation+0.997
consists
Token consists
Feature activation+0.000
almost
Token almost
Feature activation+0.000
wholly
Token wholly
Feature activation+0.000
of
Token of
Feature activation+0.000
and
Token and
Feature activation+0.000
making
Token making
Feature activation+0.000
those
Token those
Feature activation+0.000
game
Token game
Feature activation+1.844
-
Token-
Feature activation+0.705
time
Tokentime
Feature activation+3.221
decisions
Token decisions
Feature activation+0.332
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
gate
Token gate
Feature activation+0.000
keepers
Tokenkeepers
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
v
Token v
Feature activation+2.921
aults
Tokenaults
Feature activation+3.164
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
understandably
Token understandably
Feature activation+0.000
keep
Token keep
Feature activation+0.000
their
Token their
Feature activation+0.000
hardest
Token hardest
Feature activation+0.000
part
Token part
Feature activation+0.000
is
Token is
Feature activation+0.000
getting
Token getting
Feature activation+0.000
those
Token those
Feature activation+0.000
first
Token first
Feature activation+3.156
few
Token few
Feature activation+0.645
believers
Token believers
Feature activation+1.732
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
you
Token you
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
faces
Token faces
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
outsiders
Token outsiders
Feature activation+3.119
hoping
Token hoping
Feature activation+0.000
the
Token the
Feature activation+0.000
empire
Token empire
Feature activation+0.000
will
Token will
Feature activation+0.000
completely
Token completely
Feature activation+0.000
a
Token a
Feature activation+0.000
dinner
Token dinner
Feature activation+0.000
party
Token party
Feature activation+0.000
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000
same
Token same
Feature activation+3.111
elite
Token elite
Feature activation+3.230
neighborhoods
Token neighborhoods
Feature activation+0.997
consists
Token consists
Feature activation+0.000
almost
Token almost
Feature activation+0.000
wholly
Token wholly
Feature activation+0.000
should
Token should
Feature activation+0.000
push
Token push
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
those
Token those
Feature activation+0.000
other
Token other
Feature activation+3.096
unions
Token unions
Feature activation+0.717
neutral
Token neutral
Feature activation+0.000
.
Token.
Feature activation+0.000
Any
Token Any
Feature activation+0.000
word
Token word
Feature activation+0.000

Top DFA by src position
MAX = 4.913

game
Token game
Feature activation-0.093
Top resid features:
has
Token has
Feature activation-0.020
Top resid features:
evolved
Token evolved
Feature activation-0.039
Top resid features:
greatly
Token greatly
Feature activation-0.023
Top resid features:
since
Token since
Feature activation+0.001
Top resid features:
those
Token those
Feature activation+4.913
Top resid features:
early
Token early
Feature activation+0.046
Top resid features:
days
Token days
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
seen
Token seen
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
side
Token side
Feature activation-0.015
Top resid features:
note
Token note
Feature activation-0.028
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
hopefully
Token hopefully
Feature activation+0.021
Top resid features:
those
Token those
Feature activation+4.652
Top resid features:
magn
Token magn
Feature activation+0.005
Top resid features:
animous
Tokenanimous
Feature activation+0.049
Top resid features:
souls
Token souls
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
leaders
Token leaders
Feature activation+0.012
Top resid features:
across
Token across
Feature activation-0.015
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
city
Token city
Feature activation-0.015
Top resid features:
.
Token.
Feature activation+0.033
Top resid features:
Those
Token Those
Feature activation+4.673
Top resid features:
ward
Token ward
Feature activation-0.006
Top resid features:
leaders
Token leaders
Feature activation+0.000
Top resid features:
head
Token head
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
absolutely
Token absolutely
Feature activation-0.002
Top resid features:
need
Token need
Feature activation-0.002
Top resid features:
a
Token a
Feature activation-0.011
Top resid features:
gym
Token gym
Feature activation-0.038
Top resid features:
for
Token for
Feature activation-0.009
Top resid features:
those
Token those
Feature activation+4.571
Top resid features:
rainy
Token rainy
Feature activation+0.041
Top resid features:
days
Token days
Feature activation+0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
check
Token check
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
money
Token money
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Without
Token Without
Feature activation+0.012
Top resid features:
it
Token it
Feature activation+0.007
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
those
Token those
Feature activation+4.760
Top resid features:
spell
Token spell
Feature activation+0.023
Top resid features:
binding
Tokenbinding
Feature activation+0.009
Top resid features:
battle
Token battle
Feature activation+0.000
Top resid features:
scenes
Token scenes
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
sigh
Token sigh
Feature activation-0.004
Top resid features:
of
Token of
Feature activation-0.009
Top resid features:
relief
Token relief
Feature activation-0.006
Top resid features:
among
Token among
Feature activation+0.010
Top resid features:
those
Token those
Feature activation+1.991
Top resid features:
same
Token same
Feature activation+2.633
Top resid features:
Scottish
Token Scottish
Feature activation-0.004
Top resid features:
-
Token-
Feature activation-0.005
Top resid features:
based
Tokenbased
Feature activation+0.024
Top resid features:
major
Token major
Feature activation+0.000
Top resid features:
financial
Token financial
Feature activation+0.000
Top resid features:
flood
Token flood
Feature activation-0.009
Top resid features:
g
Tokeng
Feature activation-0.010
Top resid features:
ates
Tokenates
Feature activation-0.007
Top resid features:
open
Token open
Feature activation-0.017
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+4.474
Top resid features:
middle
Token middle
Feature activation+0.034
Top resid features:
men
Tokenmen
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
politically
Token politically
Feature activation+0.000
Top resid features:
ouch
Tokenouch
Feature activation+0.016
Top resid features:
for
Token for
Feature activation+0.048
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
accuracy
Token accuracy
Feature activation-0.033
Top resid features:
of
Token of
Feature activation-0.057
Top resid features:
those
Token those
Feature activation+4.217
Top resid features:
sources
Token sources
Feature activation+0.080
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
material
Token material
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
here
Token here
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Let
TokenLet
Feature activation+0.012
Top resid features:
those
Token those
Feature activation+4.379
Top resid features:
creative
Token creative
Feature activation+0.044
Top resid features:
juices
Token juices
Feature activation+0.000
Top resid features:
flow
Token flow
Feature activation+0.000
Top resid features:
!
Token!
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
pretty
Token pretty
Feature activation-0.016
Top resid features:
clearly
Token clearly
Feature activation-0.033
Top resid features:
,
Token,
Feature activation-0.017
Top resid features:
especially
Token especially
Feature activation-0.018
Top resid features:
for
Token for
Feature activation+0.010
Top resid features:
those
Token those
Feature activation+4.310
Top resid features:
authors
Token authors
Feature activation+0.074
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
maybe
Token maybe
Feature activation+0.000
Top resid features:
didn
Token didn
Feature activation+0.000
Top resid features:
't
Token't
Feature activation+0.000
Top resid features:
have
Token have
Feature activation-0.000
Top resid features:
values
Token values
Feature activation-0.014
Top resid features:
."
Token."
Feature activation+0.084
Top resid features:
Rel
TokenRel
Feature activation-0.009
Top resid features:
ating
Tokenating
Feature activation+0.001
Top resid features:
those
Token those
Feature activation+4.141
Top resid features:
undeniable
Token undeniable
Feature activation+0.112
Top resid features:
rights
Token rights
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
tech
Token tech
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
be
Token be
Feature activation-0.001
Top resid features:
eventually
Token eventually
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
And
Token And
Feature activation+0.008
Top resid features:
when
Token when
Feature activation+0.027
Top resid features:
those
Token those
Feature activation+4.123
Top resid features:
grinding
Token grinding
Feature activation+0.015
Top resid features:
stomach
Token stomach
Feature activation+0.000
Top resid features:
noises
Token noises
Feature activation+0.000
Top resid features:
rise
Token rise
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
sigh
Token sigh
Feature activation-0.004
Top resid features:
of
Token of
Feature activation-0.013
Top resid features:
relief
Token relief
Feature activation-0.004
Top resid features:
among
Token among
Feature activation+0.024
Top resid features:
those
Token those
Feature activation+1.657
Top resid features:
same
Token same
Feature activation+2.646
Top resid features:
Scottish
Token Scottish
Feature activation-0.014
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
based
Tokenbased
Feature activation+0.000
Top resid features:
major
Token major
Feature activation+0.000
Top resid features:
financial
Token financial
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
a
Token a
Feature activation-0.013
Top resid features:
dinner
Token dinner
Feature activation-0.040
Top resid features:
party
Token party
Feature activation-0.103
Top resid features:
in
Token in
Feature activation-0.077
Top resid features:
those
Token those
Feature activation+3.878
Top resid features:
same
Token same
Feature activation+0.840
Top resid features:
elite
Token elite
Feature activation+0.008
Top resid features:
neighborhoods
Token neighborhoods
Feature activation+0.000
Top resid features:
consists
Token consists
Feature activation+0.000
Top resid features:
almost
Token almost
Feature activation+0.000
Top resid features:
reading
Token reading
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.016
Top resid features:
defence
Token defence
Feature activation-0.019
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
making
Token making
Feature activation-0.008
Top resid features:
those
Token those
Feature activation+4.333
Top resid features:
game
Token game
Feature activation-0.004
Top resid features:
-
Token-
Feature activation-0.012
Top resid features:
time
Tokentime
Feature activation+0.012
Top resid features:
decisions
Token decisions
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
annoying
Token annoying
Feature activation+0.060
Top resid features:
the
Token the
Feature activation+0.083
Top resid features:
gate
Token gate
Feature activation-0.019
Top resid features:
keepers
Tokenkeepers
Feature activation+0.019
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
those
Token those
Feature activation+4.130
Top resid features:
v
Token v
Feature activation-0.070
Top resid features:
aults
Tokenaults
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
understandably
Token understandably
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation-0.006
Top resid features:
hardest
Token hardest
Feature activation-0.020
Top resid features:
part
Token part
Feature activation-0.032
Top resid features:
is
Token is
Feature activation+0.031
Top resid features:
getting
Token getting
Feature activation-0.028
Top resid features:
those
Token those
Feature activation+4.296
Top resid features:
first
Token first
Feature activation+0.071
Top resid features:
few
Token few
Feature activation+0.000
Top resid features:
believers
Token believers
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
After
Token After
Feature activation+0.000
Top resid features:
back
Token back
Feature activation+0.001
Top resid features:
in
Token in
Feature activation-0.031
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
faces
Token faces
Feature activation+0.053
Top resid features:
of
Token of
Feature activation+0.094
Top resid features:
those
Token those
Feature activation+3.733
Top resid features:
outsiders
Token outsiders
Feature activation+0.083
Top resid features:
hoping
Token hoping
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
empire
Token empire
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
a
Token a
Feature activation-0.032
Top resid features:
dinner
Token dinner
Feature activation-0.112
Top resid features:
party
Token party
Feature activation-0.141
Top resid features:
in
Token in
Feature activation-0.076
Top resid features:
those
Token those
Feature activation+4.581
Top resid features:
same
Token same
Feature activation+0.088
Top resid features:
elite
Token elite
Feature activation+0.000
Top resid features:
neighborhoods
Token neighborhoods
Feature activation+0.000
Top resid features:
consists
Token consists
Feature activation+0.000
Top resid features:
almost
Token almost
Feature activation+0.000
Top resid features:
we
Token we
Feature activation-0.007
Top resid features:
should
Token should
Feature activation+0.006
Top resid features:
push
Token push
Feature activation-0.029
Top resid features:
to
Token to
Feature activation-0.038
Top resid features:
keep
Token keep
Feature activation-0.012
Top resid features:
those
Token those
Feature activation+4.213
Top resid features:
other
Token other
Feature activation+0.074
Top resid features:
unions
Token unions
Feature activation+0.000
Top resid features:
neutral
Token neutral
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Any
Token Any
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.56

Head 1: 0.04

Head 2: 0.01

Head 3: 0.07

Head 4: 0.06

Head 5: 0.04

Head 6: 0.03

Head 7: 0.02

Head 8: 0.07

Head 9: 0.05

Head 10: 0.02

Head 11: 0.02

Positive logits

agements2.07

raints1.81

itives1.77

caveats1.69

threads1.68

iations1.65

eers1.65

clicks1.64

scenes1.64

inconven1.62

beans1.62

uffs1.62

exceptions1.60

deviations1.60

ptions1.60

irements1.60

timers1.58

pages1.58

juices1.57

drops1.57

Negative logits

oire-1.68

organisation-1.58

isine-1.55

illation-1.47

ocity-1.43

obook-1.41

��-1.38

orthodoxy-1.37

prise-1.37

®,-1.36

parity-1.34

ifter-1.30

outine-1.29

mology-1.29

ocide-1.29

composition-1.29

ofer-1.28

ography-1.28

oshop-1.28

estine-1.27

INTERVAL 3.387 - 3.763
CONTAINS 0.001%

Without
Token Without
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
those
Token those
Feature activation+0.000
spell
Token spell
Feature activation+2.526
binding
Tokenbinding
Feature activation+3.554
battle
Token battle
Feature activation+1.030
scenes
Token scenes
Feature activation+0.184
would
Token would
Feature activation+0.000
not
Token not
Feature activation+0.000
have
Token have
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
.
Token.
Feature activation+0.000
Those
Token Those
Feature activation+0.000
ward
Token ward
Feature activation+3.679
leaders
Token leaders
Feature activation+2.600
head
Token head
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
accuracy
Token accuracy
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
sources
Token sources
Feature activation+3.452
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
material
Token material
Feature activation+0.000
has
Token has
Feature activation+0.000
here
Token here
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Let
TokenLet
Feature activation+0.000
those
Token those
Feature activation+0.000
creative
Token creative
Feature activation+3.406
juices
Token juices
Feature activation+2.141
flow
Token flow
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
need
Token need
Feature activation+0.000
a
Token a
Feature activation+0.000
gym
Token gym
Feature activation+0.000
for
Token for
Feature activation+0.000
those
Token those
Feature activation+0.000
rainy
Token rainy
Feature activation+3.557
days
Token days
Feature activation+2.858
âĢĵ
Token âĢĵ
Feature activation+0.000
check
Token check
Feature activation+0.000
The
Token The
Feature activation+0.000
Gym
Token Gym
Feature activation+0.000

INTERVAL 3.011 - 3.387
CONTAINS 0.001%

of
Token of
Feature activation+0.000
relief
Token relief
Feature activation+0.000
among
Token among
Feature activation+0.000
those
Token those
Feature activation+0.000
same
Token same
Feature activation+2.327
Scottish
Token Scottish
Feature activation+3.231
-
Token-
Feature activation+1.681
based
Tokenbased
Feature activation+3.501
major
Token major
Feature activation+1.611
financial
Token financial
Feature activation+0.000
institutions
Token institutions
Feature activation+2.462
dinner
Token dinner
Feature activation+0.000
party
Token party
Feature activation+0.000
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000
same
Token same
Feature activation+3.111
elite
Token elite
Feature activation+3.230
neighborhoods
Token neighborhoods
Feature activation+0.997
consists
Token consists
Feature activation+0.000
almost
Token almost
Feature activation+0.000
wholly
Token wholly
Feature activation+0.000
of
Token of
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
faces
Token faces
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
outsiders
Token outsiders
Feature activation+3.119
hoping
Token hoping
Feature activation+0.000
the
Token the
Feature activation+0.000
empire
Token empire
Feature activation+0.000
will
Token will
Feature activation+0.000
completely
Token completely
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
when
Token when
Feature activation+0.000
those
Token those
Feature activation+0.000
grinding
Token grinding
Feature activation+3.258
stomach
Token stomach
Feature activation+0.000
noises
Token noises
Feature activation+1.844
rise
Token rise
Feature activation+0.000
up
Token up
Feature activation+0.000
from
Token from
Feature activation+0.000
gate
Token gate
Feature activation+0.000
keepers
Tokenkeepers
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
v
Token v
Feature activation+2.921
aults
Tokenaults
Feature activation+3.164
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
understandably
Token understandably
Feature activation+0.000
keep
Token keep
Feature activation+0.000
their
Token their
Feature activation+0.000

INTERVAL 2.634 - 3.011
CONTAINS 0.004%

.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
those
Token those
Feature activation+0.000
early
Token early
Feature activation+2.635
days
Token days
Feature activation+0.133
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
probably
Token probably
Feature activation+0.000
composing
Token composing
Feature activation+0.000
those
Token those
Feature activation+0.000
animate
Token animate
Feature activation+2.722
and
Token and
Feature activation+0.796
marvelous
Token marvelous
Feature activation+2.883
organizations
Token organizations
Feature activation+2.700
called
Token called
Feature activation+0.000
human
Token human
Feature activation+0.000
societies
Token societies
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
well
Token well
Feature activation+0.000
before
Token before
Feature activation+0.000
those
Token those
Feature activation+0.000
nasty
Token nasty
Feature activation+2.809
'
Token '
Feature activation+0.252
70
Token70
Feature activation+0.308
s
Tokens
Feature activation+1.197
feminists
Token feminists
Feature activation+0.439
stopped
Token stopped
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
smart
Token smart
Feature activation+0.000
!
Token!
Feature activation+0.000
Those
Token Those
Feature activation+0.000
Trump
Token Trump
Feature activation+2.719
people
Token people
Feature activation+0.820
just
Token just
Feature activation+0.043
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
em
Tokenem
Feature activation+0.000
ingly
Tokeningly
Feature activation+0.000
,
Token,
Feature activation+0.000
only
Token only
Feature activation+0.000
those
Token those
Feature activation+0.000
subjects
Token subjects
Feature activation+2.872
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
no
Token no
Feature activation+0.000
aggressive
Token aggressive
Feature activation+0.000
feelings
Token feelings
Feature activation+0.000

INTERVAL 2.258 - 2.634
CONTAINS 0.002%

drugs
Token drugs
Feature activation+0.000
being
Token being
Feature activation+0.000
tested
Token tested
Feature activation+0.000
against
Token against
Feature activation+0.000
those
Token those
Feature activation+0.000
mutations
Token mutations
Feature activation+2.494
.
Token.
Feature activation+0.000
Step
Token Step
Feature activation+0.000
4
Token 4
Feature activation+0.000
:
Token:
Feature activation+0.000
test
Token test
Feature activation+0.000
sigh
Token sigh
Feature activation+0.000
of
Token of
Feature activation+0.000
relief
Token relief
Feature activation+0.000
among
Token among
Feature activation+0.000
those
Token those
Feature activation+0.000
same
Token same
Feature activation+2.327
Scottish
Token Scottish
Feature activation+3.231
-
Token-
Feature activation+1.681
based
Tokenbased
Feature activation+3.501
major
Token major
Feature activation+1.611
financial
Token financial
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
those
Token those
Feature activation+0.000
tent
Token tent
Feature activation+0.561
acle
Tokenacle
Feature activation+2.360
hallucinations
Token hallucinations
Feature activation+1.366
may
Token may
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
prompted
Token prompted
Feature activation+0.000
study
Token study
Feature activation+0.000
measures
Token measures
Feature activation+0.000
satisfaction
Token satisfaction
Feature activation+0.000
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000
same
Token same
Feature activation+2.311
five
Token five
Feature activation+1.680
factors
Token factors
Feature activation+0.323
plus
Token plus
Feature activation+0.000
a
Token a
Feature activation+0.000
sixth
Token sixth
Feature activation+0.000
Scottish
Token Scottish
Feature activation+3.231
-
Token-
Feature activation+1.681
based
Tokenbased
Feature activation+3.501
major
Token major
Feature activation+1.611
financial
Token financial
Feature activation+0.000
institutions
Token institutions
Feature activation+2.462
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
talking
Token talking
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 1.882 - 2.258
CONTAINS 0.004%

obtained
Token obtained
Feature activation+0.000
from
Token from
Feature activation+0.000
bosses
Token bosses
Feature activation+0.000
within
Token within
Feature activation+0.000
those
Token those
Feature activation+0.000
raids
Token raids
Feature activation+2.170
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
7
Token7
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
understood
Token understood
Feature activation+0.000
those
Token those
Feature activation+0.000
investigations
Token investigations
Feature activation+2.168
are
Token are
Feature activation+0.000
at
Token at
Feature activation+0.000
an
Token an
Feature activation+0.000
advanced
Token advanced
Feature activation+0.000
stage
Token stage
Feature activation+0.000
repr
Token repr
Feature activation+0.000
ised
Tokenised
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
comments
Token comments
Feature activation+2.058
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
its
Token its
Feature activation+0.000
not
Token not
Feature activation+0.000
surprising
Token surprising
Feature activation+0.000
consensus
Token consensus
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
among
Token among
Feature activation+0.000
those
Token those
Feature activation+0.000
hostile
Token hostile
Feature activation+2.147
to
Token to
Feature activation+0.000
each
Token each
Feature activation+0.000
other
Token other
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+0.000
?
Token?
Feature activation+0.000
Not
Token Not
Feature activation+0.000
to
Token to
Feature activation+0.000
those
Token those
Feature activation+0.000
fan
Token fan
Feature activation+1.133
bases
Token bases
Feature activation+2.088
,
Token,
Feature activation+0.687
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
endured
Token endured
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000

INTERVAL 1.505 - 1.882
CONTAINS 0.007%

ates
Tokenates
Feature activation+0.000
open
Token open
Feature activation+0.000
and
Token and
Feature activation+0.000
those
Token those
Feature activation+0.000
middle
Token middle
Feature activation+3.469
men
Tokenmen
Feature activation+1.653
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
politically
Token politically
Feature activation+0.000
charged
Token charged
Feature activation+0.000
with
Token with
Feature activation+0.000
eliminate
Token eliminate
Feature activation+0.000
jail
Token jail
Feature activation+0.000
time
Token time
Feature activation+0.000
under
Token under
Feature activation+0.000
those
Token those
Feature activation+0.000
circumstances
Token circumstances
Feature activation+1.611
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
6
Token 6
Feature activation+0.000
:
Token:
Feature activation+0.000
24
Token24
Feature activation+0.000
ing
Tokening
Feature activation+0.000
and
Token and
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
through
Token through
Feature activation+0.000
those
Token those
Feature activation+0.000
energy
Token energy
Feature activation+1.601
policies
Token policies
Feature activation+1.532
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
the
Token the
Feature activation+0.000
Toronto
Token Toronto
Feature activation+0.000
past
Token past
Feature activation+0.000
3
Token 3
Feature activation+0.000
days
Token days
Feature activation+0.000
fixing
Token fixing
Feature activation+0.000
those
Token those
Feature activation+0.000
bugs
Token bugs
Feature activation+1.583
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
now
Token now
Feature activation+0.000
the
Token the
Feature activation+0.000
Unity
Token Unity
Feature activation+0.000
Season
Token Season
Feature activation+0.000
and
Token and
Feature activation+0.000
handing
Token handing
Feature activation+0.000
out
Token out
Feature activation+0.000
those
Token those
Feature activation+0.000
glorious
Token glorious
Feature activation+1.694
Reward
Token Reward
Feature activation+0.252
Weapon
Token Weapon
Feature activation+0.000
Sk
Token Sk
Feature activation+0.000
ins
Tokenins
Feature activation+0.207
for
Token for
Feature activation+0.000

INTERVAL 1.129 - 1.505
CONTAINS 0.006%

government
Token government
Feature activation+0.000
except
Token except
Feature activation+0.000
for
Token for
Feature activation+0.000
all
Token all
Feature activation+0.000
those
Token those
Feature activation+0.000
others
Token others
Feature activation+1.371
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
tried
Token tried
Feature activation+0.000
.
Token.
Feature activation+0.000
with
Token with
Feature activation+0.000
not
Token not
Feature activation+0.000
winning
Token winning
Feature activation+0.000
with
Token with
Feature activation+0.000
those
Token those
Feature activation+0.000
awesome
Token awesome
Feature activation+1.260
ly
Tokenly
Feature activation+0.940
dumb
Token dumb
Feature activation+0.908
cards
Token cards
Feature activation+0.313
and
Token and
Feature activation+0.000
just
Token just
Feature activation+0.000
cade
Tokencade
Feature activation+0.000
,
Token,
Feature activation+0.000
during
Token during
Feature activation+0.000
which
Token which
Feature activation+0.000
those
Token those
Feature activation+0.000
in
Token in
Feature activation+1.329
the
Token the
Feature activation+0.000
parade
Token parade
Feature activation+0.000
wear
Token wear
Feature activation+0.000
rain
Token rain
Feature activation+0.000
coats
Token coats
Feature activation+0.000
NATO
Token NATO
Feature activation+0.000
standards
Token standards
Feature activation+0.000
and
Token and
Feature activation+0.000
only
Token only
Feature activation+0.000
those
Token those
Feature activation+0.000
responsible
Token responsible
Feature activation+1.388
in
Token in
Feature activation+0.000
each
Token each
Feature activation+0.000
case
Token case
Feature activation+0.000
have
Token have
Feature activation+0.000
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
advantage
Token advantage
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
fronts
Token fronts
Feature activation+1.181
.
Token.
Feature activation+0.000
Mid
Token Mid
Feature activation+0.000
line
Tokenline
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.753 - 1.129
CONTAINS 0.012%

assessments
Token assessments
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Those
TokenThose
Feature activation+0.000
reports
Token reports
Feature activation+1.077
are
Token are
Feature activation+0.000
due
Token due
Feature activation+0.000
Feb
Token Feb
Feature activation+0.000
.
Token.
Feature activation+0.000
23
Token 23
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
those
Token those
Feature activation+0.000
spell
Token spell
Feature activation+2.526
binding
Tokenbinding
Feature activation+3.554
battle
Token battle
Feature activation+1.030
scenes
Token scenes
Feature activation+0.184
would
Token would
Feature activation+0.000
not
Token not
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
then
Token then
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
take
Token take
Feature activation+0.000
those
Token those
Feature activation+0.000
numbers
Token numbers
Feature activation+0.850
and
Token and
Feature activation+0.107
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
put
Token put
Feature activation+0.000
context
Token context
Feature activation+0.000
from
Token from
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
those
Token those
Feature activation+0.000
three
Token three
Feature activation+0.851
-
Token-
Feature activation+0.981
pointers
Tokenpointers
Feature activation+0.419
were
Token were
Feature activation+0.000
timely
Token timely
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
Those
Token Those
Feature activation+0.000
people
Token people
Feature activation+0.969
briefly
Token briefly
Feature activation+1.050
enter
Token enter
Feature activation+0.000
Scout
Token Scout
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 0.376 - 0.753
CONTAINS 0.021%

My
Token My
Feature activation+0.000
bill
Token bill
Feature activation+0.000
would
Token would
Feature activation+0.000
ensure
Token ensure
Feature activation+0.000
those
Token those
Feature activation+0.000
rights
Token rights
Feature activation+0.576
are
Token are
Feature activation+0.000
protected
Token protected
Feature activation+0.000
by
Token by
Feature activation+0.000
Maine
Token Maine
Feature activation+0.000
law
Token law
Feature activation+0.000
Wow
TokenWow
Feature activation+0.000
,
Token,
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
them
Token them
Feature activation+0.000
fire
Token fire
Feature activation+0.434
up
Token up
Feature activation+0.175
that
Token that
Feature activation+0.000
Gold
Token Gold
Feature activation+0.000
il
Tokenil
Feature activation+0.000
ocks
Tokenocks
Feature activation+0.000
time
Token time
Feature activation+0.000
of
Token of
Feature activation+0.000
day
Token day
Feature activation+0.000
,
Token,
Feature activation+0.000
say
Token say
Feature activation+0.000
at
Token at
Feature activation+0.402
2
Token 2
Feature activation+0.000
:
Token:
Feature activation+0.000
30
Token30
Feature activation+0.000
pm
Token pm
Feature activation+0.000
every
Token every
Feature activation+0.000
detachment
Token detachment
Feature activation+0.000
will
Token will
Feature activation+0.000
now
Token now
Feature activation+0.000
revive
Token revive
Feature activation+0.000
these
Token these
Feature activation+0.000
historic
Token historic
Feature activation+0.406
forces
Token forces
Feature activation+0.000
.
Token.
Feature activation+0.000
Sett
Token Sett
Feature activation+0.000
ler
Tokenler
Feature activation+0.000
leader
Token leader
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
kinds
Token kinds
Feature activation+0.000
of
Token of
Feature activation+0.000
computer
Token computer
Feature activation+0.467
viruses
Token viruses
Feature activation+0.000
that
Token that
Feature activation+0.000
can
Token can
Feature activation+0.000
help
Token help
Feature activation+0.000
criminals
Token criminals
Feature activation+0.000

INTERVAL 0.000 - 0.376
CONTAINS 99.942%

ich
Tokenich
Feature activation+0.000
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
interview
Token interview
Feature activation+0.000
with
Token with
Feature activation+0.000
Cru
Token Cru
Feature activation+0.000
x
Tokenx
Feature activation+0.000
this
Token this
Feature activation+0.000
week
Token week
Feature activation+0.000
that
Token that
Feature activation+0.000
That
Token That
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
courtesy
Token courtesy
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
4
Token 4
Feature activation+0.000
.
Token.
Feature activation+0.000
6
Token6
Feature activation+0.000
L
Token L
Feature activation+0.000
infring
Token infring
Feature activation+0.000
e
Tokene
Feature activation+0.000
on
Token on
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
most
Token most
Feature activation+0.000
celebrated
Token celebrated
Feature activation+0.000
features
Token features
Feature activation+0.000
and
Token and
Feature activation+0.000
what
Token what
Feature activation+0.000
manager
Token manager
Feature activation+0.000
Andy
Token Andy
Feature activation+0.000
Thorn
Token Thorn
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
We
TokenWe
Feature activation+0.000
are
Token are
Feature activation+0.000
really
Token really
Feature activation+0.000
pleased
Token pleased
Feature activation+0.000
s
Tokens
Feature activation+0.000
Touch
Token Touch
Feature activation+0.000
ing
Tokening
Feature activation+0.000
Note
Token Note
Feature activation+0.000
Her
Token Her
Feature activation+0.000
Mom
Token Mom
Feature activation+0.000
W
Token W
Feature activation+0.000
rote
Tokenrote
Feature activation+0.000
After
Token After
Feature activation+0.000
Ad
Token Ad
Feature activation+0.000
op
Tokenop
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 9 in H7.0: (feature 33419)

TOP ACTIVATIONS
MAX = 2.827

.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
satire
Token satire
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
biting
Token biting
Feature activation+2.827
as
Token as
Feature activation+0.000
ever
Token ever
Feature activation+0.000
today
Token today
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
The
Token The
Feature activation+0.000
voyage
Token voyage
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
as
Token as
Feature activation+0.000
rough
Token rough
Feature activation+2.743
as
Token as
Feature activation+0.000
any
Token any
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
remember
Token remember
Feature activation+0.000
great
Token great
Feature activation+0.000
instincts
Token instincts
Feature activation+0.000
.
Token.
Feature activation+0.000
Being
Token Being
Feature activation+0.000
as
Token as
Feature activation+0.000
smart
Token smart
Feature activation+2.696
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
as
Token as
Feature activation+0.000
ins
Token ins
Feature activation+0.274
cr
Tokencr
Feature activation+0.624
utable
Tokenutable
Feature activation+2.608
and
Token and
Feature activation+0.796
fascinating
Token fascinating
Feature activation+2.507
as
Token as
Feature activation+0.000
possible
Token possible
Feature activation+0.000
.
Token.
Feature activation+0.000
brew
Token brew
Feature activation+0.000
at
Token at
Feature activation+0.000
home
Token home
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
delicious
Token delicious
Feature activation+2.547
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
summer
Token summer
Feature activation+0.000
day
Token day
Feature activation+0.000
is
Token is
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+2.123
ľ
Tokenľ
Feature activation+2.538
ch
Tokench
Feature activation+1.408
arming
Tokenarming
Feature activation+1.644
âĢ
TokenâĢ
Feature activation+0.467
Ŀ
TokenĿ
Feature activation+0.133
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
as
Token as
Feature activation+0.000
stubborn
Token stubborn
Feature activation+2.520
and
Token and
Feature activation+0.660
as
Token as
Feature activation+0.000
set
Token set
Feature activation+1.225
in
Token in
Feature activation+0.049
your
Token your
Feature activation+0.000
as
Token as
Feature activation+0.000
ins
Token ins
Feature activation+0.274
cr
Tokencr
Feature activation+0.624
utable
Tokenutable
Feature activation+2.608
and
Token and
Feature activation+0.796
fascinating
Token fascinating
Feature activation+2.507
as
Token as
Feature activation+0.000
possible
Token possible
Feature activation+0.000
.
Token.
Feature activation+0.000
Nobody
Token Nobody
Feature activation+0.000
will
Token will
Feature activation+0.000
answer
Token answer
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
dark
Token dark
Feature activation+2.293
and
Token and
Feature activation+1.746
troubling
Token troubling
Feature activation+2.392
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
infamous
Token infamous
Feature activation+0.000
Penn
Token Penn
Feature activation+0.000
Cove
Token Cove
Feature activation+0.000
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
answer
Token answer
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
dark
Token dark
Feature activation+2.293
and
Token and
Feature activation+1.746
troubling
Token troubling
Feature activation+2.392
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
infamous
Token infamous
Feature activation+0.000
sourced
Token sourced
Feature activation+0.000
from
Token from
Feature activation+0.000
regions
Token regions
Feature activation+0.000
as
Token as
Feature activation+0.000
far
Token far
Feature activation+1.278
flung
Token flung
Feature activation+2.192
as
Token as
Feature activation+0.000
Russia
Token Russia
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
present
Token present
Feature activation+0.000
ab
Token ab
Feature activation+0.000
at
Tokenat
Feature activation+0.000
ements
Tokenements
Feature activation+0.000
for
Token for
Feature activation+0.000
as
Token as
Feature activation+0.000
long
Token long
Feature activation+2.175
as
Token as
Feature activation+0.000
25
Token 25
Feature activation+0.000
years
Token years
Feature activation+0.000
to
Token to
Feature activation+0.000
encourage
Token encourage
Feature activation+0.000
His
TokenHis
Feature activation+0.000
crime
Token crime
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
baff
Token baff
Feature activation+1.753
ling
Tokenling
Feature activation+2.162
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
gruesome
Token gruesome
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+2.123
ľ
Tokenľ
Feature activation+2.538
ch
Tokench
Feature activation+1.408
arming
Tokenarming
Feature activation+1.644
âĢ
TokenâĢ
Feature activation+0.467
Ŀ
TokenĿ
Feature activation+0.133
the
Token the
Feature activation+0.000
character
Token character
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
as
Token as
Feature activation+0.000
dark
Token dark
Feature activation+2.101
as
Token as
Feature activation+0.000
Superman
Token Superman
Feature activation+0.000
and
Token and
Feature activation+0.000
Batman
Token Batman
Feature activation+0.000
seem
Token seem
Feature activation+0.000
tried
Token tried
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
this
Token this
Feature activation+0.000
as
Token as
Feature activation+0.000
balanced
Token balanced
Feature activation+2.086
and
Token and
Feature activation+0.356
as
Token as
Feature activation+0.000
fun
Token fun
Feature activation+1.520
as
Token as
Feature activation+0.000
possible
Token possible
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
created
Token created
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
easy
Token easy
Feature activation+1.951
as
Token as
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
a
Token a
Feature activation+0.000
URL
Token URL
Feature activation+0.000
.
Token.
Feature activation+0.000
sure
Token sure
Feature activation+0.000
.
Token.
Feature activation+0.000
Chelsea
Token Chelsea
Feature activation+0.000
are
Token are
Feature activation+0.000
as
Token as
Feature activation+0.000
good
Token good
Feature activation+1.949
as
Token as
Feature activation+0.000
set
Token set
Feature activation+0.000
in
Token in
Feature activation+0.000
terms
Token terms
Feature activation+0.000
of
Token of
Feature activation+0.000
wanna
Token wanna
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
deck
Token deck
Feature activation+0.000
as
Token as
Feature activation+0.000
disgusting
Token disgusting
Feature activation+1.929
as
Token as
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
so
Token so
Feature activation+0.000
I
Token I
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
as
Token as
Feature activation+0.000
dismal
Token dismal
Feature activation+1.919
a
Token a
Feature activation+0.000
vision
Token vision
Feature activation+0.000
of
Token of
Feature activation+0.000
permanent
Token permanent
Feature activation+0.000
trans
Token trans
Feature activation+0.000

Top DFA by src position
MAX = 4.029

death
Token death
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
The
Token The
Feature activation-0.002
Top resid features:
satire
Token satire
Feature activation-0.011
Top resid features:
is
Token is
Feature activation+0.145
Top resid features:
as
Token as
Feature activation+3.887
Top resid features:
biting
Token biting
Feature activation+0.061
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
ever
Token ever
Feature activation+0.000
Top resid features:
today
Token today
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
The
Token The
Feature activation+0.036
Top resid features:
voyage
Token voyage
Feature activation+0.045
Top resid features:
had
Token had
Feature activation-0.024
Top resid features:
been
Token been
Feature activation-0.014
Top resid features:
as
Token as
Feature activation+4.029
Top resid features:
rough
Token rough
Feature activation+0.090
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.011
Top resid features:
great
Token great
Feature activation-0.004
Top resid features:
instincts
Token instincts
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.074
Top resid features:
Being
Token Being
Feature activation+0.041
Top resid features:
as
Token as
Feature activation+3.536
Top resid features:
smart
Token smart
Feature activation+0.120
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
their
Token their
Feature activation-0.047
Top resid features:
way
Token way
Feature activation+0.016
Top resid features:
to
Token to
Feature activation+0.047
Top resid features:
be
Token be
Feature activation+0.013
Top resid features:
as
Token as
Feature activation+3.772
Top resid features:
ins
Token ins
Feature activation+0.081
Top resid features:
cr
Tokencr
Feature activation+0.023
Top resid features:
utable
Tokenutable
Feature activation+0.151
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
fascinating
Token fascinating
Feature activation+0.000
Top resid features:
cold
Token cold
Feature activation-0.022
Top resid features:
brew
Token brew
Feature activation-0.096
Top resid features:
at
Token at
Feature activation+0.018
Top resid features:
home
Token home
Feature activation-0.021
Top resid features:
is
Token is
Feature activation+0.244
Top resid features:
as
Token as
Feature activation+3.481
Top resid features:
delicious
Token delicious
Feature activation+0.174
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
summer
Token summer
Feature activation+0.000
Top resid features:
day
Token day
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.005
Top resid features:
âĢ
TokenâĢ
Feature activation-0.109
Top resid features:
Ļ
TokenĻ
Feature activation-0.009
Top resid features:
t
Tokent
Feature activation-0.042
Top resid features:
be
Token be
Feature activation-0.029
Top resid features:
as
Token as
Feature activation+4.015
Top resid features:
âĢ
Token âĢ
Feature activation-0.044
Top resid features:
ľ
Tokenľ
Feature activation-0.003
Top resid features:
ch
Tokench
Feature activation+0.000
Top resid features:
arming
Tokenarming
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
However
Token However
Feature activation-0.007
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
when
Token when
Feature activation+0.005
Top resid features:
you
Token you
Feature activation+0.004
Top resid features:
are
Token are
Feature activation+0.047
Top resid features:
as
Token as
Feature activation+3.664
Top resid features:
stubborn
Token stubborn
Feature activation+0.076
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
set
Token set
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
their
Token their
Feature activation-0.038
Top resid features:
way
Token way
Feature activation+0.020
Top resid features:
to
Token to
Feature activation+0.054
Top resid features:
be
Token be
Feature activation+0.057
Top resid features:
as
Token as
Feature activation+3.487
Top resid features:
ins
Token ins
Feature activation+0.039
Top resid features:
cr
Tokencr
Feature activation+0.008
Top resid features:
utable
Tokenutable
Feature activation+0.161
Top resid features:
and
Token and
Feature activation+0.124
Top resid features:
fascinating
Token fascinating
Feature activation+0.066
Top resid features:
turns
Token turns
Feature activation-0.001
Top resid features:
out
Token out
Feature activation-0.133
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
answer
Token answer
Feature activation+0.046
Top resid features:
is
Token is
Feature activation+0.084
Top resid features:
as
Token as
Feature activation+3.228
Top resid features:
dark
Token dark
Feature activation+0.113
Top resid features:
and
Token and
Feature activation+0.190
Top resid features:
troubling
Token troubling
Feature activation+0.061
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
turns
Token turns
Feature activation-0.014
Top resid features:
out
Token out
Feature activation-0.129
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
answer
Token answer
Feature activation+0.040
Top resid features:
is
Token is
Feature activation+0.069
Top resid features:
as
Token as
Feature activation+3.365
Top resid features:
dark
Token dark
Feature activation+0.132
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
troubling
Token troubling
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.006
Top resid features:
coal
Token coal
Feature activation-0.005
Top resid features:
sourced
Token sourced
Feature activation-0.006
Top resid features:
from
Token from
Feature activation+0.090
Top resid features:
regions
Token regions
Feature activation-0.005
Top resid features:
as
Token as
Feature activation+2.977
Top resid features:
far
Token far
Feature activation+0.338
Top resid features:
flung
Token flung
Feature activation+0.074
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Russia
Token Russia
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
tax
Token tax
Feature activation-0.005
Top resid features:
ab
Token ab
Feature activation+0.009
Top resid features:
at
Tokenat
Feature activation-0.015
Top resid features:
ements
Tokenements
Feature activation-0.011
Top resid features:
for
Token for
Feature activation+0.158
Top resid features:
as
Token as
Feature activation+3.197
Top resid features:
long
Token long
Feature activation+0.217
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
25
Token 25
Feature activation+0.000
Top resid features:
years
Token years
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
His
TokenHis
Feature activation-0.097
Top resid features:
crime
Token crime
Feature activation+0.027
Top resid features:
is
Token is
Feature activation+0.190
Top resid features:
as
Token as
Feature activation+3.386
Top resid features:
baff
Token baff
Feature activation+0.120
Top resid features:
ling
Tokenling
Feature activation+0.064
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.003
Top resid features:
âĢ
TokenâĢ
Feature activation-0.015
Top resid features:
Ļ
TokenĻ
Feature activation-0.399
Top resid features:
t
Tokent
Feature activation-0.031
Top resid features:
be
Token be
Feature activation-0.012
Top resid features:
as
Token as
Feature activation+3.826
Top resid features:
âĢ
Token âĢ
Feature activation-0.001
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
ch
Tokench
Feature activation+0.000
Top resid features:
arming
Tokenarming
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
whether
Token whether
Feature activation-0.098
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
character
Token character
Feature activation-0.021
Top resid features:
will
Token will
Feature activation-0.007
Top resid features:
be
Token be
Feature activation-0.004
Top resid features:
as
Token as
Feature activation+3.695
Top resid features:
dark
Token dark
Feature activation+0.041
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Superman
Token Superman
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Batman
Token Batman
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.006
Top resid features:
tried
Token tried
Feature activation-0.034
Top resid features:
to
Token to
Feature activation+0.120
Top resid features:
make
Token make
Feature activation+0.089
Top resid features:
this
Token this
Feature activation+0.134
Top resid features:
as
Token as
Feature activation+2.928
Top resid features:
balanced
Token balanced
Feature activation+0.187
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
fun
Token fun
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
world
Token world
Feature activation-0.003
Top resid features:
you
Token you
Feature activation+0.028
Top resid features:
have
Token have
Feature activation+0.031
Top resid features:
created
Token created
Feature activation-0.047
Top resid features:
is
Token is
Feature activation+0.136
Top resid features:
as
Token as
Feature activation+2.891
Top resid features:
easy
Token easy
Feature activation+0.112
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
sharing
Token sharing
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
URL
Token URL
Feature activation+0.000
Top resid features:
m
Tokenm
Feature activation+0.011
Top resid features:
sure
Token sure
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Chelsea
Token Chelsea
Feature activation+0.077
Top resid features:
are
Token are
Feature activation+0.271
Top resid features:
as
Token as
Feature activation+2.830
Top resid features:
good
Token good
Feature activation+0.099
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
set
Token set
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
terms
Token terms
Feature activation+0.000
Top resid features:
just
Token just
Feature activation-0.012
Top resid features:
wanna
Token wanna
Feature activation+0.016
Top resid features:
make
Token make
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
deck
Token deck
Feature activation+0.025
Top resid features:
as
Token as
Feature activation+2.902
Top resid features:
disgusting
Token disgusting
Feature activation+0.091
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.033
Top resid features:
it
Token it
Feature activation+0.028
Top resid features:
âĢ
TokenâĢ
Feature activation+0.010
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation-0.011
Top resid features:
as
Token as
Feature activation+3.176
Top resid features:
dismal
Token dismal
Feature activation+0.084
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
vision
Token vision
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
permanent
Token permanent
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.56

Head 1: 0.03

Head 2: 0.02

Head 3: 0.05

Head 4: 0.07

Head 5: 0.05

Head 6: 0.03

Head 7: 0.02

Head 8: 0.07

Head 9: 0.05

Head 10: 0.03

Head 11: 0.02

Positive logits

Zup1.70

hene1.68

ready1.58

imal1.57

ippy1.56

Afgh1.53

Scand1.52

clusive1.51

sed1.50

architect1.49

ange1.48

imaginable1.47

endar1.45

fy1.45

lp1.44

kw1.44

hesive1.44

lite1.44

nat1.43

kl1.43

Negative logits

cation-1.58

Donation-1.51

docking-1.50

Cause-1.48

loophole-1.45

contributions-1.45

uctions-1.43

roying-1.43

rosso-1.41

ECTION-1.41

clerosis-1.41

grading-1.41

tesy-1.40

sighting-1.39

ecause-1.38

CHAT-1.38

chats-1.38

exchanges-1.37

etermination-1.36

loopholes-1.36

INTERVAL 2.544 - 2.827
CONTAINS 0.001%

great
Token great
Feature activation+0.000
instincts
Token instincts
Feature activation+0.000
.
Token.
Feature activation+0.000
Being
Token Being
Feature activation+0.000
as
Token as
Feature activation+0.000
smart
Token smart
Feature activation+2.696
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
The
Token The
Feature activation+0.000
voyage
Token voyage
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
as
Token as
Feature activation+0.000
rough
Token rough
Feature activation+2.743
as
Token as
Feature activation+0.000
any
Token any
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
remember
Token remember
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
as
Token as
Feature activation+0.000
ins
Token ins
Feature activation+0.274
cr
Tokencr
Feature activation+0.624
utable
Tokenutable
Feature activation+2.608
and
Token and
Feature activation+0.796
fascinating
Token fascinating
Feature activation+2.507
as
Token as
Feature activation+0.000
possible
Token possible
Feature activation+0.000
.
Token.
Feature activation+0.000
brew
Token brew
Feature activation+0.000
at
Token at
Feature activation+0.000
home
Token home
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
delicious
Token delicious
Feature activation+2.547
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
summer
Token summer
Feature activation+0.000
day
Token day
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
satire
Token satire
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
biting
Token biting
Feature activation+2.827
as
Token as
Feature activation+0.000
ever
Token ever
Feature activation+0.000
today
Token today
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 2.262 - 2.544
CONTAINS 0.001%

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+2.123
ľ
Tokenľ
Feature activation+2.538
ch
Tokench
Feature activation+1.408
arming
Tokenarming
Feature activation+1.644
âĢ
TokenâĢ
Feature activation+0.467
Ŀ
TokenĿ
Feature activation+0.133
in
Token in
Feature activation+0.000
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
answer
Token answer
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
dark
Token dark
Feature activation+2.293
and
Token and
Feature activation+1.746
troubling
Token troubling
Feature activation+2.392
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
infamous
Token infamous
Feature activation+0.000
answer
Token answer
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
dark
Token dark
Feature activation+2.293
and
Token and
Feature activation+1.746
troubling
Token troubling
Feature activation+2.392
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
infamous
Token infamous
Feature activation+0.000
Penn
Token Penn
Feature activation+0.000
Cove
Token Cove
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
as
Token as
Feature activation+0.000
stubborn
Token stubborn
Feature activation+2.520
and
Token and
Feature activation+0.660
as
Token as
Feature activation+0.000
set
Token set
Feature activation+1.225
in
Token in
Feature activation+0.049
your
Token your
Feature activation+0.000
as
Token as
Feature activation+0.000
ins
Token ins
Feature activation+0.274
cr
Tokencr
Feature activation+0.624
utable
Tokenutable
Feature activation+2.608
and
Token and
Feature activation+0.796
fascinating
Token fascinating
Feature activation+2.507
as
Token as
Feature activation+0.000
possible
Token possible
Feature activation+0.000
.
Token.
Feature activation+0.000
Nobody
Token Nobody
Feature activation+0.000
will
Token will
Feature activation+0.000

INTERVAL 1.979 - 2.262
CONTAINS 0.001%

sourced
Token sourced
Feature activation+0.000
from
Token from
Feature activation+0.000
regions
Token regions
Feature activation+0.000
as
Token as
Feature activation+0.000
far
Token far
Feature activation+1.278
flung
Token flung
Feature activation+2.192
as
Token as
Feature activation+0.000
Russia
Token Russia
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
present
Token present
Feature activation+0.000
ab
Token ab
Feature activation+0.000
at
Tokenat
Feature activation+0.000
ements
Tokenements
Feature activation+0.000
for
Token for
Feature activation+0.000
as
Token as
Feature activation+0.000
long
Token long
Feature activation+2.175
as
Token as
Feature activation+0.000
25
Token 25
Feature activation+0.000
years
Token years
Feature activation+0.000
to
Token to
Feature activation+0.000
encourage
Token encourage
Feature activation+0.000
His
TokenHis
Feature activation+0.000
crime
Token crime
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
baff
Token baff
Feature activation+1.753
ling
Tokenling
Feature activation+2.162
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
gruesome
Token gruesome
Feature activation+0.000
.
Token.
Feature activation+0.000
tried
Token tried
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
this
Token this
Feature activation+0.000
as
Token as
Feature activation+0.000
balanced
Token balanced
Feature activation+2.086
and
Token and
Feature activation+0.356
as
Token as
Feature activation+0.000
fun
Token fun
Feature activation+1.520
as
Token as
Feature activation+0.000
possible
Token possible
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+2.123
ľ
Tokenľ
Feature activation+2.538
ch
Tokench
Feature activation+1.408
arming
Tokenarming
Feature activation+1.644
âĢ
TokenâĢ
Feature activation+0.467
Ŀ
TokenĿ
Feature activation+0.133

INTERVAL 1.696 - 1.979
CONTAINS 0.001%

It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
as
Token as
Feature activation+0.000
Bad
Token Bad
Feature activation+1.802
as
Token as
Feature activation+0.000
Swim
Token Swim
Feature activation+0.000
Th
Token Th
Feature activation+0.000
inks
Tokeninks
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
sure
Token sure
Feature activation+0.000
.
Token.
Feature activation+0.000
Chelsea
Token Chelsea
Feature activation+0.000
are
Token are
Feature activation+0.000
as
Token as
Feature activation+0.000
good
Token good
Feature activation+1.949
as
Token as
Feature activation+0.000
set
Token set
Feature activation+0.000
in
Token in
Feature activation+0.000
terms
Token terms
Feature activation+0.000
of
Token of
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Com
TokenCom
Feature activation+0.000
puters
Tokenputers
Feature activation+0.000
became
Token became
Feature activation+0.000
as
Token as
Feature activation+0.000
good
Token good
Feature activation+1.845
as
Token as
Feature activation+0.000
or
Token or
Feature activation+0.000
better
Token better
Feature activation+0.000
than
Token than
Feature activation+0.000
humans
Token humans
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
created
Token created
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
easy
Token easy
Feature activation+1.951
as
Token as
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
a
Token a
Feature activation+0.000
URL
Token URL
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
answer
Token answer
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
dark
Token dark
Feature activation+2.293
and
Token and
Feature activation+1.746
troubling
Token troubling
Feature activation+2.392
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
infamous
Token infamous
Feature activation+0.000
Penn
Token Penn
Feature activation+0.000

INTERVAL 1.413 - 1.696
CONTAINS 0.002%

's
Token's
Feature activation+0.000
decision
Token decision
Feature activation+0.000
about
Token about
Feature activation+0.000
something
Token something
Feature activation+0.000
as
Token as
Feature activation+0.000
important
Token important
Feature activation+1.483
as
Token as
Feature activation+0.000
whether
Token whether
Feature activation+0.000
to
Token to
Feature activation+0.000
become
Token become
Feature activation+0.000
a
Token a
Feature activation+0.000
we
Token we
Feature activation+0.000
try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000
play
Token play
Feature activation+0.000
as
Token as
Feature activation+0.000
high
Token high
Feature activation+1.546
as
Token as
Feature activation+0.000
possible
Token possible
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
pitch
Token pitch
Feature activation+0.000
not
Token not
Feature activation+0.000
everything
Token everything
Feature activation+0.000
was
Token was
Feature activation+0.000
as
Token as
Feature activation+0.000
ro
Token ro
Feature activation+0.934
sy
Tokensy
Feature activation+1.440
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
seemed
Token seemed
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
''
Token''
Feature activation+0.000
It
TokenIt
Feature activation+0.000
was
Token was
Feature activation+0.000
as
Token as
Feature activation+0.000
birth
Token birth
Feature activation+1.286
days
Tokendays
Feature activation+1.551
came
Token came
Feature activation+0.000
and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
't
Token't
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
as
Token as
Feature activation+0.000
good
Token good
Feature activation+1.685
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.131 - 1.413
CONTAINS 0.002%

World
Token World
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
as
Token as
Feature activation+0.000
far
Token far
Feature activation+1.019
West
Token West
Feature activation+1.220
as
Token as
Feature activation+0.000
Mali
Token Mali
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
as
Token as
Feature activation+0.000
's
Token's
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
as
Token as
Feature activation+0.000
bad
Token bad
Feature activation+1.366
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
us
Token us
Feature activation+0.000
,
Token,
Feature activation+0.000
battling
Token battling
Feature activation+0.000
dangers
Token dangers
Feature activation+0.000
as
Token as
Feature activation+0.000
real
Token real
Feature activation+1.402
as
Token as
Feature activation+0.000
Sent
Token Sent
Feature activation+0.000
ry
Tokenry
Feature activation+0.000
robots
Token robots
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
rarely
Token rarely
Feature activation+0.000
as
Token as
Feature activation+0.000
ex
Token ex
Feature activation+0.640
uber
Tokenuber
Feature activation+1.195
ant
Tokenant
Feature activation+0.824
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
populated
Token populated
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
as
Token as
Feature activation+0.000
stubborn
Token stubborn
Feature activation+2.520
and
Token and
Feature activation+0.660
as
Token as
Feature activation+0.000
set
Token set
Feature activation+1.225
in
Token in
Feature activation+0.049
your
Token your
Feature activation+0.000
ways
Token ways
Feature activation+0.000
as
Token as
Feature activation+0.000
I
Token I
Feature activation+0.000

INTERVAL 0.848 - 1.131
CONTAINS 0.002%

foll
Token foll
Feature activation+0.000
icle
Tokenicle
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.000
as
Token as
Feature activation+0.000
human
Token human
Feature activation+1.083
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
z
Token z
Feature activation+0.000
yg
Tokenyg
Feature activation+0.000
ote
Tokenote
Feature activation+0.000
functions
Token functions
Feature activation+0.000
that
Token that
Feature activation+0.000
make
Token make
Feature activation+0.000
it
Token it
Feature activation+0.000
as
Token as
Feature activation+0.000
useful
Token useful
Feature activation+1.065
as
Token as
Feature activation+0.000
other
Token other
Feature activation+0.000
computing
Token computing
Feature activation+0.000
devices
Token devices
Feature activation+0.000
.
Token.
Feature activation+0.000
interactive
Token interactive
Feature activation+0.000
features
Token features
Feature activation+0.000
for
Token for
Feature activation+0.000
fans
Token fans
Feature activation+0.000
as
Token as
Feature activation+0.000
videos
Token videos
Feature activation+0.889
of
Token of
Feature activation+0.000
post
Token post
Feature activation+0.000
-
Token-
Feature activation+0.000
game
Tokengame
Feature activation+0.000
interviews
Token interviews
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+1.586
target
Token target
Feature activation+0.849
the
Token the
Feature activation+0.000
present
Token present
Feature activation+0.000
demand
Token demand
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
rite
Token rite
Feature activation+0.000
of
Token of
Feature activation+0.000
passage
Token passage
Feature activation+0.000
lasting
Token lasting
Feature activation+0.000
as
Token as
Feature activation+0.000
long
Token long
Feature activation+0.894
as
Token as
Feature activation+0.000
three
Token three
Feature activation+0.000
months
Token months
Feature activation+0.000
,
Token,
Feature activation+0.000
something
Token something
Feature activation+0.000

INTERVAL 0.565 - 0.848
CONTAINS 0.003%

we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
never
Token never
Feature activation+0.000
been
Token been
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.575
don
Tokendon
Feature activation+0.000
istic
Tokenistic
Feature activation+1.523
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
Romans
Token Romans
Feature activation+0.000
phones
Token phones
Feature activation+0.000
purchased
Token purchased
Feature activation+0.000
from
Token from
Feature activation+0.000
as
Token as
Feature activation+0.000
far
Token far
Feature activation+0.796
back
Token back
Feature activation+0.706
as
Token as
Feature activation+0.000
December
Token December
Feature activation+0.000
are
Token are
Feature activation+0.000
reportedly
Token reportedly
Feature activation+0.000
being
Token being
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
dive
Token dive
Feature activation+0.000
as
Token as
Feature activation+0.000
deep
Token deep
Feature activation+0.706
as
Token as
Feature activation+0.000
100
Token 100
Feature activation+0.000
m
Token m
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
after
Token after
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
deep
Token deep
Feature activation+0.587
-
Token-
Feature activation+0.000
pocket
Tokenpocket
Feature activation+0.000
ed
Tokened
Feature activation+0.481
clubs
Token clubs
Feature activation+0.000
developed
Token developed
Feature activation+0.000
drone
Token drone
Feature activation+0.000
rock
Token rock
Feature activation+0.000
as
Token as
Feature activation+0.000
thick
Token thick
Feature activation+1.120
and
Token and
Feature activation+0.312
murky
Token murky
Feature activation+0.736
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
lyrics
Token lyrics
Feature activation+0.000
are
Token are
Feature activation+0.000
clear
Token clear
Feature activation+0.000

INTERVAL 0.283 - 0.565
CONTAINS 0.006%

-
Token-
Feature activation+0.000
sym
Tokensym
Feature activation+0.000
?
Token?
Feature activation+0.000
accepts
Token accepts
Feature activation+0.000
as
Token as
Feature activation+0.000
arguments
Token arguments
Feature activation+0.338
an
Token an
Feature activation+0.000
S
Token S
Feature activation+0.000
-
Token-
Feature activation+0.000
expression
Tokenexpression
Feature activation+0.000
(
Token (
Feature activation+0.000
of
Token of
Feature activation+0.000
drone
Token drone
Feature activation+0.000
rock
Token rock
Feature activation+0.000
as
Token as
Feature activation+0.000
thick
Token thick
Feature activation+1.120
and
Token and
Feature activation+0.312
murky
Token murky
Feature activation+0.736
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
lyrics
Token lyrics
Feature activation+0.000
are
Token are
Feature activation+0.000
these
Token these
Feature activation+0.000
rapists
Token rapists
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.000
as
Token as
Feature activation+0.000
vile
Token vile
Feature activation+0.446
and
Token and
Feature activation+0.452
depl
Token depl
Feature activation+0.000
orable
Tokenorable
Feature activation+1.045
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
Ji
Token Ji
Feature activation+0.000
Won
Token Won
Feature activation+0.000
and
Token and
Feature activation+0.000
Y
Token Y
Feature activation+0.000
oon
Tokenoon
Feature activation+0.000
Ky
Token Ky
Feature activation+0.435
un
Tokenun
Feature activation+0.000
Sang
Token Sang
Feature activation+0.000
wore
Token wore
Feature activation+0.000
black
Token black
Feature activation+0.000
while
Token while
Feature activation+0.000
help
Token help
Feature activation+0.000
recreate
Token recreate
Feature activation+0.000
in
Token in
Feature activation+0.000
monkeys
Token monkeys
Feature activation+0.000
such
Token such
Feature activation+0.000
diseases
Token diseases
Feature activation+0.310
as
Token as
Feature activation+0.000
Parkinson
Token Parkinson
Feature activation+0.000
's
Token's
Feature activation+0.000
and
Token and
Feature activation+0.000
Alzheimer
Token Alzheimer
Feature activation+0.000

INTERVAL 0.000 - 0.283
CONTAINS 99.983%

entered
Token entered
Feature activation+0.000
the
Token the
Feature activation+0.000
intersection
Token intersection
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
circular
Token circular
Feature activation+0.000
green
Token green
Feature activation+0.000
traffic
Token traffic
Feature activation+0.000
signal
Token signal
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
random
Tokenrandom
Feature activation+0.000
=
Token =
Feature activation+0.000
yes
Token yes
Feature activation+0.000
/
Token/
Feature activation+0.000
no
Tokenno
Feature activation+0.000
].
Token].
Feature activation+0.000
Blocks
Token Blocks
Feature activation+0.000
the
Token the
Feature activation+0.000
culture
Token culture
Feature activation+0.000
from
Token from
Feature activation+0.000
being
Token being
Feature activation+0.000
game
Token game
Feature activation+0.000
off
Token off
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
fool
Token fool
Feature activation+0.000
hard
Tokenhard
Feature activation+0.000
y
Tokeny
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.000
return
Token return
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
couple
Token couple
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
given
Token given
Feature activation+0.000
until
Token until
Feature activation+0.000
May
Token May
Feature activation+0.000
2
Token 2
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
_
Token_
Feature activation+0.000
ts
Tokents
Feature activation+0.000
vector
Tokenvector
Feature activation+0.000
(
Token (
Feature activation+0.000
coales
Token coales
Feature activation+0.000
ce
Tokence
Feature activation+0.000
(
Token (
Feature activation+0.000
name
Token name
Feature activation+0.000
,
Token ,
Feature activation+0.000
''
Token ''
Feature activation+0.000
)
Token )
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000