H8.7 top features

Top feature 0 in H8.7: (feature 14042)

TOP ACTIVATIONS
MAX = 2.427

Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
was
Token was
Feature activation+0.000
during
Token during
Feature activation+0.000
these
Token these
Feature activation+0.000
form
Token form
Feature activation+2.427
ative
Tokenative
Feature activation+0.366
years
Token years
Feature activation+0.369
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
budding
Token budding
Feature activation+0.000
chemical
Token chemical
Feature activation+0.000
serotonin
Token serotonin
Feature activation+0.000
--
Token --
Feature activation+0.000
as
Token as
Feature activation+0.000
do
Token do
Feature activation+0.969
some
Token some
Feature activation+2.340
antidepressants
Token antidepressants
Feature activation+1.047
--
Token --
Feature activation+0.000
and
Token and
Feature activation+0.056
also
Token also
Feature activation+0.000
boosts
Token boosts
Feature activation+0.000
these
Token these
Feature activation+0.287
âĢ
Token âĢ
Feature activation+0.880
ľ
Tokenľ
Feature activation+1.449
thought
Tokenthought
Feature activation+2.047
âĢ
TokenâĢ
Feature activation+0.840
Ŀ
TokenĿ
Feature activation+2.264
verbs
Token verbs
Feature activation+0.821
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
beginning
Token beginning
Feature activation+0.000
of
Token of
Feature activation+0.000
certain
Token certain
Feature activation+0.000
size
Token size
Feature activation+0.000
,
Token,
Feature activation+0.000
these
Token these
Feature activation+0.000
value
Token value
Feature activation+1.729
added
Token added
Feature activation+2.261
services
Token services
Feature activation+0.261
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
wrap
Token wrap
Feature activation+0.000
around
Token around
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
more
Token more
Feature activation+0.000
about
Token about
Feature activation+0.000
these
Token these
Feature activation+0.000
morph
Token morph
Feature activation+2.217
isms
Tokenisms
Feature activation+0.714
,
Token,
Feature activation+0.000
see
Token see
Feature activation+0.000
Simpl
Token Simpl
Feature activation+0.000
ifying
Tokenifying
Feature activation+0.000
and
Token and
Feature activation+0.000
frustrating
Token frustrating
Feature activation+0.000
these
Token these
Feature activation+0.000
m
Token m
Feature activation+1.413
add
Tokenadd
Feature activation+0.386
ening
Tokenening
Feature activation+2.213
attacks
Token attacks
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.114
.
Token.
Feature activation+0.000
Good
Token Good
Feature activation+0.000
and
Token and
Feature activation+0.000
communication
Token communication
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
interpret
Token interpret
Feature activation+1.493
ive
Tokenive
Feature activation+2.130
frameworks
Token frameworks
Feature activation+0.000
are
Token are
Feature activation+0.000
powerful
Token powerful
Feature activation+0.007
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
two
Token two
Feature activation+0.000
upcoming
Token upcoming
Feature activation+0.375
Avengers
Token Avengers
Feature activation+1.282
:
Token:
Feature activation+0.126
Infinity
Token Infinity
Feature activation+0.004
War
Token War
Feature activation+2.096
films
Token films
Feature activation+0.639
once
Token once
Feature activation+0.000
more
Token more
Feature activation+0.000
.
Token.
Feature activation+0.000
Check
Token Check
Feature activation+0.000
writers
Token writers
Feature activation+0.000
use
Token use
Feature activation+0.000
these
Token these
Feature activation+0.287
âĢ
Token âĢ
Feature activation+0.880
ľ
Tokenľ
Feature activation+1.449
thought
Tokenthought
Feature activation+2.047
âĢ
TokenâĢ
Feature activation+0.840
Ŀ
TokenĿ
Feature activation+2.264
verbs
Token verbs
Feature activation+0.821
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
4
Token4
Feature activation+0.000
]
Token]
Feature activation+0.000
includes
Token includes
Feature activation+0.000
these
Token these
Feature activation+0.000
autobi
Token autobi
Feature activation+1.300
ographical
Tokenographical
Feature activation+1.997
notes
Token notes
Feature activation+0.449
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
t
Tokent
Feature activation+0.000
wearing
Token wearing
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
red
Token red
Feature activation+1.991
hats
Token hats
Feature activation+0.800
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
he
Token he
Feature activation+0.000
?
Token?
Feature activation+0.000
the
Token the
Feature activation+0.000
rare
Token rare
Feature activation+0.000
st
Tokenst
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.192
rare
Token rare
Feature activation+1.982
case
Token case
Feature activation+1.245
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
.
Token.
Feature activation+0.000
MORE
TokenMORE
Feature activation+0.000
:
Token:
Feature activation+0.000
7
Token 7
Feature activation+0.000
Weird
Token Weird
Feature activation+0.547
Head
Token Head
Feature activation+0.926
ache
Tokenache
Feature activation+1.965
Tr
Token Tr
Feature activation+1.091
ig
Tokenig
Feature activation+0.731
gers
Tokengers
Feature activation+1.370
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
are
Token are
Feature activation+0.000
no
Token no
Feature activation+0.946
more
Token more
Feature activation+1.305
shared
Token shared
Feature activation+1.670
_
Token_
Feature activation+0.880
ptr
Tokenptr
Feature activation+1.941
instances
Token instances
Feature activation+0.388
pointing
Token pointing
Feature activation+0.000
to
Token to
Feature activation+0.000
this
Token this
Feature activation+0.000
object
Token object
Feature activation+0.000
canopy
Token canopy
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
"
Token "
Feature activation+1.086
high
Tokenhigh
Feature activation+1.376
altitude
Token altitude
Feature activation+1.889
"
Token"
Feature activation+1.832
pitchers
Token pitchers
Feature activation+0.204
are
Token are
Feature activation+0.000
considerably
Token considerably
Feature activation+0.000
narrower
Token narrower
Feature activation+0.000
opened
Token opened
Feature activation+0.000
a
Token a
Feature activation+0.000
couple
Token couple
Feature activation+0.000
of
Token of
Feature activation+0.000
Titan
Token Titan
Feature activation+0.926
Pad
TokenPad
Feature activation+1.884
pages
Token pages
Feature activation+0.374
to
Token to
Feature activation+0.000
crowd
Token crowd
Feature activation+0.000
-
Token-
Feature activation+0.000
source
Tokensource
Feature activation+0.000
s
Tokens
Feature activation+0.000
add
Token add
Feature activation+0.000
a
Token a
Feature activation+0.000
couple
Token couple
Feature activation+0.000
more
Token more
Feature activation+0.345
gro
Token gro
Feature activation+1.883
ats
Tokenats
Feature activation+0.821
to
Token to
Feature activation+0.000
their
Token their
Feature activation+0.000
food
Token food
Feature activation+0.000
stamps
Token stamps
Feature activation+0.056
described
Token described
Feature activation+0.000
the
Token the
Feature activation+0.000
agreement
Token agreement
Feature activation+0.000
covering
Token covering
Feature activation+0.000
these
Token these
Feature activation+0.000
so
Token so
Feature activation+1.859
-
Token-
Feature activation+0.414
called
Tokencalled
Feature activation+1.042
He
Token He
Feature activation+0.776
La
TokenLa
Feature activation+1.349
cells
Token cells
Feature activation+0.341
These
Token These
Feature activation+0.000
are
Token are
Feature activation+0.401
not
Token not
Feature activation+1.191
Metro
Token Metro
Feature activation+1.067
lin
Tokenlin
Feature activation+0.471
x
Tokenx
Feature activation+1.854
projects
Token projects
Feature activation+0.559
per
Token per
Feature activation+0.000
se
Token se
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
part
Token part
Feature activation+0.000
are
Token are
Feature activation+0.496
the
Token the
Feature activation+1.603
owner
Token owner
Feature activation+1.844
..
Token ..
Feature activation+0.000
super
Token super
Feature activation+0.000
friendly
Token friendly
Feature activation+0.000
people
Token people
Feature activation+0.000
and
Token and
Feature activation+0.000

Top DFA by src position
MAX = 2.775

Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
It
TokenIt
Feature activation-0.006
Top resid features:
was
Token was
Feature activation-0.000
Top resid features:
during
Token during
Feature activation-0.002
Top resid features:
these
Token these
Feature activation+2.775
Top resid features:
form
Token form
Feature activation+0.027
Top resid features:
ative
Tokenative
Feature activation+0.000
Top resid features:
years
Token years
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:
brain
Token brain
Feature activation+0.021
Top resid features:
chemical
Token chemical
Feature activation+0.014
Top resid features:
serotonin
Token serotonin
Feature activation+0.014
Top resid features:
--
Token --
Feature activation+0.003
Top resid features:
as
Token as
Feature activation-0.003
Top resid features:
do
Token do
Feature activation+2.587
Top resid features:
some
Token some
Feature activation+0.004
Top resid features:
antidepressants
Token antidepressants
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:
also
Token also
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Typically
TokenTypically
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
writers
Token writers
Feature activation-0.013
Top resid features:
use
Token use
Feature activation+0.071
Top resid features:
these
Token these
Feature activation+2.451
Top resid features:
âĢ
Token âĢ
Feature activation+0.044
Top resid features:
ľ
Tokenľ
Feature activation+0.009
Top resid features:
thought
Tokenthought
Feature activation+0.044
Top resid features:
âĢ
TokenâĢ
Feature activation-0.003
Top resid features:
Ŀ
TokenĿ
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
certain
Token certain
Feature activation+0.006
Top resid features:
size
Token size
Feature activation-0.014
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
these
Token these
Feature activation+2.468
Top resid features:
value
Token value
Feature activation+0.076
Top resid features:
added
Token added
Feature activation+0.043
Top resid features:
services
Token services
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
you
Token you
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:
For
TokenFor
Feature activation+0.004
Top resid features:
more
Token more
Feature activation+0.009
Top resid features:
about
Token about
Feature activation-0.016
Top resid features:
these
Token these
Feature activation+2.392
Top resid features:
morph
Token morph
Feature activation+0.060
Top resid features:
isms
Tokenisms
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
see
Token see
Feature activation+0.000
Top resid features:
Simpl
Token Simpl
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.001
Top resid features:
how
Token how
Feature activation-0.014
Top resid features:
painful
Token painful
Feature activation+0.005
Top resid features:
and
Token and
Feature activation-0.016
Top resid features:
frustrating
Token frustrating
Feature activation+0.000
Top resid features:
these
Token these
Feature activation+2.404
Top resid features:
m
Token m
Feature activation+0.017
Top resid features:
add
Tokenadd
Feature activation-0.001
Top resid features:
ening
Tokenening
Feature activation+0.060
Top resid features:
attacks
Token attacks
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
interpret
Token interpret
Feature activation+0.011
Top resid features:
information
Token information
Feature activation+0.013
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
communication
Token communication
Feature activation+0.014
Top resid features:
.
Token.
Feature activation-0.020
Top resid features:
These
Token These
Feature activation+2.255
Top resid features:
interpret
Token interpret
Feature activation+0.045
Top resid features:
ive
Tokenive
Feature activation+0.054
Top resid features:
frameworks
Token frameworks
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
powerful
Token powerful
Feature activation+0.000
Top resid features:
crossover
Token crossover
Feature activation-0.001
Top resid features:
happening
Token happening
Feature activation-0.007
Top resid features:
in
Token in
Feature activation+0.011
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
two
Token two
Feature activation+0.319
Top resid features:
upcoming
Token upcoming
Feature activation+2.119
Top resid features:
Avengers
Token Avengers
Feature activation+0.038
Top resid features:
:
Token:
Feature activation-0.051
Top resid features:
Infinity
Token Infinity
Feature activation-0.013
Top resid features:
War
Token War
Feature activation+0.006
Top resid features:
films
Token films
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Typically
TokenTypically
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
writers
Token writers
Feature activation-0.008
Top resid features:
use
Token use
Feature activation+0.042
Top resid features:
these
Token these
Feature activation+2.116
Top resid features:
âĢ
Token âĢ
Feature activation+0.121
Top resid features:
ľ
Tokenľ
Feature activation+0.102
Top resid features:
thought
Tokenthought
Feature activation+0.026
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
fusion
Token fusion
Feature activation-0.010
Top resid features:
[
Token[
Feature activation+0.005
Top resid features:
4
Token4
Feature activation-0.001
Top resid features:
]
Token]
Feature activation-0.001
Top resid features:
includes
Token includes
Feature activation+0.063
Top resid features:
these
Token these
Feature activation+2.190
Top resid features:
autobi
Token autobi
Feature activation+0.050
Top resid features:
ographical
Tokenographical
Feature activation+0.047
Top resid features:
notes
Token notes
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.001
Top resid features:
t
Tokent
Feature activation-0.004
Top resid features:
wearing
Token wearing
Feature activation-0.041
Top resid features:
one
Token one
Feature activation-0.016
Top resid features:
of
Token of
Feature activation+0.258
Top resid features:
those
Token those
Feature activation+2.034
Top resid features:
red
Token red
Feature activation+0.038
Top resid features:
hats
Token hats
Feature activation+0.000
Top resid features:
,
Token,
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:
's
Token's
Feature activation-0.026
Top resid features:
the
Token the
Feature activation-0.015
Top resid features:
rare
Token rare
Feature activation+0.017
Top resid features:
st
Tokenst
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.777
Top resid features:
the
Token the
Feature activation+1.492
Top resid features:
rare
Token rare
Feature activation+0.068
Top resid features:
case
Token case
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:
says
Token says
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
MORE
TokenMORE
Feature activation-0.025
Top resid features:
:
Token:
Feature activation-0.021
Top resid features:
7
Token 7
Feature activation+0.379
Top resid features:
Weird
Token Weird
Feature activation+1.851
Top resid features:
Head
Token Head
Feature activation+0.027
Top resid features:
ache
Tokenache
Feature activation+0.015
Top resid features:
Tr
Token Tr
Feature activation+0.000
Top resid features:
ig
Tokenig
Feature activation+0.000
Top resid features:
gers
Tokengers
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
there
Token there
Feature activation-0.009
Top resid features:
are
Token are
Feature activation+0.082
Top resid features:
no
Token no
Feature activation+0.453
Top resid features:
more
Token more
Feature activation+1.523
Top resid features:
shared
Token shared
Feature activation+0.038
Top resid features:
_
Token_
Feature activation+0.005
Top resid features:
ptr
Tokenptr
Feature activation+0.007
Top resid features:
instances
Token instances
Feature activation+0.000
Top resid features:
pointing
Token pointing
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.009
Top resid features:
canopy
Token canopy
Feature activation+0.040
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
These
Token These
Feature activation+1.843
Top resid features:
"
Token "
Feature activation+0.321
Top resid features:
high
Tokenhigh
Feature activation+0.007
Top resid features:
altitude
Token altitude
Feature activation+0.018
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
pitchers
Token pitchers
Feature activation+0.000
Top resid features:
her
Tokenher
Feature activation+0.003
Top resid features:
also
Token also
Feature activation-0.000
Top resid features:
opened
Token opened
Feature activation-0.043
Top resid features:
a
Token a
Feature activation-0.031
Top resid features:
couple
Token couple
Feature activation+0.468
Top resid features:
of
Token of
Feature activation+1.570
Top resid features:
Titan
Token Titan
Feature activation+0.108
Top resid features:
Pad
TokenPad
Feature activation+0.092
Top resid features:
pages
Token pages
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
crowd
Token crowd
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation-0.001
Top resid features:
add
Token add
Feature activation+0.010
Top resid features:
a
Token a
Feature activation-0.016
Top resid features:
couple
Token couple
Feature activation+0.657
Top resid features:
more
Token more
Feature activation+1.509
Top resid features:
gro
Token gro
Feature activation+0.031
Top resid features:
ats
Tokenats
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
food
Token food
Feature activation+0.000
Top resid features:
Collins
Token Collins
Feature activation-0.001
Top resid features:
described
Token described
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
agreement
Token agreement
Feature activation+0.004
Top resid features:
covering
Token covering
Feature activation+0.005
Top resid features:
these
Token these
Feature activation+2.154
Top resid features:
so
Token so
Feature activation+0.006
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
called
Tokencalled
Feature activation+0.000
Top resid features:
He
Token He
Feature activation+0.000
Top resid features:
La
TokenLa
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
corridor
Token corridor
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
These
Token These
Feature activation+0.050
Top resid features:
are
Token are
Feature activation+0.283
Top resid features:
not
Token not
Feature activation+1.819
Top resid features:
Metro
Token Metro
Feature activation-0.001
Top resid features:
lin
Tokenlin
Feature activation-0.001
Top resid features:
x
Tokenx
Feature activation+0.003
Top resid features:
projects
Token projects
Feature activation+0.000
Top resid features:
per
Token per
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.008
Top resid features:
but
Token but
Feature activation-0.004
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
best
Token best
Feature activation-0.009
Top resid features:
part
Token part
Feature activation+0.001
Top resid features:
are
Token are
Feature activation+1.408
Top resid features:
the
Token the
Feature activation+0.736
Top resid features:
owner
Token owner
Feature activation-0.018
Top resid features:
..
Token ..
Feature activation+0.000
Top resid features:
super
Token super
Feature activation+0.000
Top resid features:
friendly
Token friendly
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.01

Head 2: 0.03

Head 3: 0.04

Head 4: 0.06

Head 5: 0.07

Head 6: 0.02

Head 7: 0.58

Head 8: 0.04

Head 9: 0.03

Head 10: 0.07

Head 11: 0.02

Positive logits

equivalents2.94

instances2.93

replacements2.89

entries2.87

examples2.85

scenarios2.84

pairs2.80

pieces2.79

fronts2.75

segments2.73

constants2.72

stones2.72

isms2.72

ones2.70

spots2.69

izations2.69

targets2.69

configurations2.68

markers2.67

locations2.66

Negative logits

fecture-1.92

rower-1.79

ixir-1.71

��-1.70

hyde-1.67

oyer-1.66

itamin-1.64

erva-1.61

uana-1.58

awan-1.58

hirt-1.55

ategory-1.54

estate-1.53

rium-1.52

ENCE-1.52

isma-1.49

uria-1.49

ropolis-1.49

outine-1.48

examination-1.47

INTERVAL 2.184 - 2.427
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
was
Token was
Feature activation+0.000
during
Token during
Feature activation+0.000
these
Token these
Feature activation+0.000
form
Token form
Feature activation+2.427
ative
Tokenative
Feature activation+0.366
years
Token years
Feature activation+0.369
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
budding
Token budding
Feature activation+0.000
certain
Token certain
Feature activation+0.000
size
Token size
Feature activation+0.000
,
Token,
Feature activation+0.000
these
Token these
Feature activation+0.000
value
Token value
Feature activation+1.729
added
Token added
Feature activation+2.261
services
Token services
Feature activation+0.261
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
wrap
Token wrap
Feature activation+0.000
around
Token around
Feature activation+0.000
and
Token and
Feature activation+0.000
frustrating
Token frustrating
Feature activation+0.000
these
Token these
Feature activation+0.000
m
Token m
Feature activation+1.413
add
Tokenadd
Feature activation+0.386
ening
Tokenening
Feature activation+2.213
attacks
Token attacks
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.114
.
Token.
Feature activation+0.000
Good
Token Good
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
more
Token more
Feature activation+0.000
about
Token about
Feature activation+0.000
these
Token these
Feature activation+0.000
morph
Token morph
Feature activation+2.217
isms
Tokenisms
Feature activation+0.714
,
Token,
Feature activation+0.000
see
Token see
Feature activation+0.000
Simpl
Token Simpl
Feature activation+0.000
ifying
Tokenifying
Feature activation+0.000
chemical
Token chemical
Feature activation+0.000
serotonin
Token serotonin
Feature activation+0.000
--
Token --
Feature activation+0.000
as
Token as
Feature activation+0.000
do
Token do
Feature activation+0.969
some
Token some
Feature activation+2.340
antidepressants
Token antidepressants
Feature activation+1.047
--
Token --
Feature activation+0.000
and
Token and
Feature activation+0.056
also
Token also
Feature activation+0.000
boosts
Token boosts
Feature activation+0.000

INTERVAL 1.941 - 2.184
CONTAINS 0.001%

writers
Token writers
Feature activation+0.000
use
Token use
Feature activation+0.000
these
Token these
Feature activation+0.287
âĢ
Token âĢ
Feature activation+0.880
ľ
Tokenľ
Feature activation+1.449
thought
Tokenthought
Feature activation+2.047
âĢ
TokenâĢ
Feature activation+0.840
Ŀ
TokenĿ
Feature activation+2.264
verbs
Token verbs
Feature activation+0.821
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
4
Token4
Feature activation+0.000
]
Token]
Feature activation+0.000
includes
Token includes
Feature activation+0.000
these
Token these
Feature activation+0.000
autobi
Token autobi
Feature activation+1.300
ographical
Tokenographical
Feature activation+1.997
notes
Token notes
Feature activation+0.449
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
t
Tokent
Feature activation+0.000
wearing
Token wearing
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
red
Token red
Feature activation+1.991
hats
Token hats
Feature activation+0.800
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
he
Token he
Feature activation+0.000
?
Token?
Feature activation+0.000
the
Token the
Feature activation+0.000
rare
Token rare
Feature activation+0.000
st
Tokenst
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.192
rare
Token rare
Feature activation+1.982
case
Token case
Feature activation+1.245
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
.
Token.
Feature activation+0.000
two
Token two
Feature activation+0.000
upcoming
Token upcoming
Feature activation+0.375
Avengers
Token Avengers
Feature activation+1.282
:
Token:
Feature activation+0.126
Infinity
Token Infinity
Feature activation+0.004
War
Token War
Feature activation+2.096
films
Token films
Feature activation+0.639
once
Token once
Feature activation+0.000
more
Token more
Feature activation+0.000
.
Token.
Feature activation+0.000
Check
Token Check
Feature activation+0.000

INTERVAL 1.699 - 1.941
CONTAINS 0.004%

Kom
Token Kom
Feature activation+0.000
ired
Tokenired
Feature activation+0.000
di
Tokendi
Feature activation+0.000
in
Token in
Feature activation+0.000
these
Token these
Feature activation+0.000
very
Token very
Feature activation+1.809
pages
Token pages
Feature activation+0.345
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
demise
Token demise
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
Sydney
Token Sydney
Feature activation+1.415
âĢ
TokenâĢ
Feature activation+0.073
Ļ
TokenĻ
Feature activation+0.238
s
Tokens
Feature activation+1.821
A
Token A
Feature activation+0.131
-
Token-
Feature activation+0.024
League
TokenLeague
Feature activation+0.515
attend
Token attend
Feature activation+0.094
ances
Tokenances
Feature activation+0.010
These
Token These
Feature activation+0.000
were
Token were
Feature activation+1.379
the
Token the
Feature activation+1.341
station
Token station
Feature activation+1.547
's
Token's
Feature activation+1.764
regular
Token regular
Feature activation+1.843
new
Token new
Feature activation+1.232
sc
Tokensc
Feature activation+0.126
asters
Tokenasters
Feature activation+1.264
,
Token,
Feature activation+0.000
reputable
Token reputable
Feature activation+0.055
Ċ
TokenĊ
Feature activation+0.000
Here
TokenHere
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.470
new
Token new
Feature activation+1.729
11
Token 11
Feature activation+1.776
(
Token (
Feature activation+0.131
and
Tokenand
Feature activation+0.969
their
Token their
Feature activation+1.158
jersey
Token jersey
Feature activation+1.024
numbers
Token numbers
Feature activation+0.702
are
Token are
Feature activation+0.000
no
Token no
Feature activation+0.946
more
Token more
Feature activation+1.305
shared
Token shared
Feature activation+1.670
_
Token_
Feature activation+0.880
ptr
Tokenptr
Feature activation+1.941
instances
Token instances
Feature activation+0.388
pointing
Token pointing
Feature activation+0.000
to
Token to
Feature activation+0.000
this
Token this
Feature activation+0.000
object
Token object
Feature activation+0.000

INTERVAL 1.456 - 1.699
CONTAINS 0.013%

able
Tokenable
Feature activation+0.000
View
TokenView
Feature activation+0.000
,
Token,
Feature activation+0.000
number
Token number
Feature activation+0.000
Of
TokenOf
Feature activation+0.000
R
TokenR
Feature activation+1.615
ows
Tokenows
Feature activation+0.635
In
TokenIn
Feature activation+0.024
Section
TokenSection
Feature activation+0.000
section
Token section
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
effect
Token effect
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.108
11
Token 11
Feature activation+0.962
false
Token false
Feature activation+1.496
starts
Token starts
Feature activation+1.665
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Seahawks
Token Seahawks
Feature activation+0.000
surely
Token surely
Feature activation+0.000
,
Token,
Feature activation+0.135
Web
Token Web
Feature activation+0.250
design
Token design
Feature activation+1.180
or
Token or
Feature activation+0.272
information
Token information
Feature activation+0.812
technology
Token technology
Feature activation+1.515
people
Token people
Feature activation+0.181
missed
Token missed
Feature activation+0.000
northern
Token northern
Feature activation+0.000
Michigan
Token Michigan
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
admin
Token admin
Feature activation+0.000
isters
Tokenisters
Feature activation+0.000
several
Token several
Feature activation+0.000
inqu
Token inqu
Feature activation+0.772
is
Tokenis
Feature activation+0.637
itive
Tokenitive
Feature activation+1.458
pe
Token pe
Feature activation+0.389
cks
Tokencks
Feature activation+0.575
before
Token before
Feature activation+0.000
finally
Token finally
Feature activation+0.000
pe
Token pe
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
aren
Token aren
Feature activation+0.000
't
Token't
Feature activation+0.069
any
Token any
Feature activation+0.158
hand
Token hand
Feature activation+1.465
ra
Tokenra
Feature activation+0.630
ils
Tokenils
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+0.000
sections
Token sections
Feature activation+0.000

INTERVAL 1.213 - 1.456
CONTAINS 0.027%

views
Token views
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2
Token2
Feature activation+0.000
major
Token major
Feature activation+0.273
street
Token street
Feature activation+1.386
projects
Token projects
Feature activation+0.084
slated
Token slated
Feature activation+0.000
for
Token for
Feature activation+0.000
Manchester
Token Manchester
Feature activation+0.000
in
Token in
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Are
TokenAre
Feature activation+0.000
any
Token any
Feature activation+0.863
of
Token of
Feature activation+1.283
these
Token these
Feature activation+0.428
a
Token a
Feature activation+0.434
part
Token part
Feature activation+0.321
of
Token of
Feature activation+0.000
your
Token your
Feature activation+0.000
Sydney
Token Sydney
Feature activation+0.000
derby
Token derby
Feature activation+0.000
game
Token game
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
Sydney
Token Sydney
Feature activation+1.415
âĢ
TokenâĢ
Feature activation+0.073
Ļ
TokenĻ
Feature activation+0.238
s
Tokens
Feature activation+1.821
A
Token A
Feature activation+0.131
-
Token-
Feature activation+0.024
different
Token different
Feature activation+0.000
enemy
Token enemy
Feature activation+0.000
with
Token with
Feature activation+0.000
each
Token each
Feature activation+0.000
of
Token of
Feature activation+0.000
it
Token it
Feature activation+1.289
âĢ
TokenâĢ
Feature activation+0.406
Ļ
TokenĻ
Feature activation+0.846
s
Tokens
Feature activation+0.273
weapons
Token weapons
Feature activation+0.256
,
Token,
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
three
Token three
Feature activation+0.000
main
Token main
Feature activation+0.237
credit
Token credit
Feature activation+1.329
rating
Token rating
Feature activation+1.243
agencies
Token agencies
Feature activation+0.178
âĢĵ
Token âĢĵ
Feature activation+0.000
Moody
Token Moody
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 0.971 - 1.213
CONTAINS 0.059%

2
Token2
Feature activation+0.000
User
Token User
Feature activation+0.000
Guide
Token Guide
Feature activation+0.000
uses
Token uses
Feature activation+0.000
these
Token these
Feature activation+0.000
typ
Token typ
Feature activation+1.202
ographic
Tokenographic
Feature activation+1.833
conventions
Token conventions
Feature activation+0.148
:
Token:
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+1.027
some
Token some
Feature activation+0.497
studies
Token studies
Feature activation+0.025
investigating
Token investigating
Feature activation+0.000
its
Token its
Feature activation+0.000
potential
Token potential
Feature activation+0.000
top
Token top
Feature activation+0.000
10
Token 10
Feature activation+0.292
Worst
Token Worst
Feature activation+0.491
Fast
Token Fast
Feature activation+0.540
-
Token-
Feature activation+0.000
Food
TokenFood
Feature activation+1.017
Me
Token Me
Feature activation+0.594
als
Tokenals
Feature activation+1.240
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
many
Token many
Feature activation+0.000
scripts
Token scripts
Feature activation+0.094
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
were
Token were
Feature activation+0.000
so
Token so
Feature activation+1.068
many
Token many
Feature activation+0.368
board
Token board
Feature activation+0.571
meetings
Token meetings
Feature activation+0.136
.
Token.
Feature activation+0.000
Em
Token Em
Feature activation+0.000
they
Token they
Feature activation+0.000
conf
Token conf
Feature activation+0.000
lated
Tokenlated
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
diss
Token diss
Feature activation+0.981
ociated
Tokenociated
Feature activation+0.369
issues
Token issues
Feature activation+0.019
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
if
Token if
Feature activation+0.000

INTERVAL 0.728 - 0.971
CONTAINS 0.113%

in
Token in
Feature activation+0.000
these
Token these
Feature activation+0.000
dead
Token dead
Feature activation+0.668
,
Token,
Feature activation+0.840
hollow
Token hollow
Feature activation+0.883
ed
Tokened
Feature activation+0.790
-
Token-
Feature activation+0.295
out
Tokenout
Feature activation+1.244
states
Token states
Feature activation+0.681
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
spring
Token spring
Feature activation+0.000
,
Token,
Feature activation+0.000
were
Token were
Feature activation+0.000
both
Token both
Feature activation+0.150
three
Token three
Feature activation+0.967
-
Token-
Feature activation+0.928
star
Tokenstar
Feature activation+0.887
recruits
Token recruits
Feature activation+0.282
.
Token.
Feature activation+0.000
Dalton
Token Dalton
Feature activation+0.000
was
Token was
Feature activation+0.000
on
Token on
Feature activation+0.000
with
Token with
Feature activation+0.000
hundreds
Token hundreds
Feature activation+0.000
of
Token of
Feature activation+0.000
$
Token $
Feature activation+0.363
3
Token3
Feature activation+0.958
-$
Token-$
Feature activation+0.000
50
Token50
Feature activation+1.197
cards
Token cards
Feature activation+0.097
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
long
Token long
Feature activation+0.000
list
Token list
Feature activation+0.000
of
Token of
Feature activation+0.126
non
Token non
Feature activation+0.733
-
Token-
Feature activation+0.656
general
Tokengeneral
Feature activation+0.848
spells
Token spells
Feature activation+0.473
with
Token with
Feature activation+0.000
their
Token their
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.160
way
Token way
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
despite
Token despite
Feature activation+0.000
those
Token those
Feature activation+0.000
changes
Token changes
Feature activation+0.938
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
economy
Token economy
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000

INTERVAL 0.485 - 0.728
CONTAINS 0.215%

Lin
Token Lin
Feature activation+0.148
ze
Tokenze
Feature activation+0.443
y
Tokeny
Feature activation+0.817
's
Token's
Feature activation+0.500
2005
Token 2005
Feature activation+0.794
radio
Token radio
Feature activation+0.703
appearances
Token appearances
Feature activation+0.318
,
Token,
Feature activation+0.000
Chip
Token Chip
Feature activation+0.000
Ber
Token Ber
Feature activation+0.000
let
Tokenlet
Feature activation+0.000
addition
Token addition
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
eight
Token eight
Feature activation+0.008
to
Token to
Feature activation+0.000
12
Token 12
Feature activation+0.576
cat
Token cat
Feature activation+1.597
whisk
Token whisk
Feature activation+1.684
ers
Tokeners
Feature activation+0.740
your
Token your
Feature activation+0.000
cat
Token cat
Feature activation+0.000
betting
Token betting
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
raft
Token raft
Feature activation+0.000
of
Token of
Feature activation+0.071
economic
Token economic
Feature activation+0.577
data
Token data
Feature activation+0.151
this
Token this
Feature activation+0.000
week
Token week
Feature activation+0.000
won
Token won
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
destroy
Tokendestroy
Feature activation+0.000
3
Token 3
Feature activation+0.000
and
Token and
Feature activation+0.000
10
Token 10
Feature activation+0.000
enemy
Token enemy
Feature activation+0.434
aircraft
Token aircraft
Feature activation+0.657
in
Token in
Feature activation+0.000
Arcade
Token Arcade
Feature activation+0.000
Battles
Token Battles
Feature activation+0.011
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
buy
Token buy
Feature activation+0.000
10
Token 10
Feature activation+0.000
Martin
Token Martin
Feature activation+0.000
's
Token's
Feature activation+0.494
Food
Token Food
Feature activation+0.175
Markets
Token Markets
Feature activation+0.363
store
Token store
Feature activation+0.211
locations
Token locations
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.243 - 0.485
CONTAINS 0.439%

TRUMP
Token TRUMP
Feature activation+0.000
!
Token!
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
TOP
TokenTOP
Feature activation+0.000
5
Token 5
Feature activation+0.000
SP
Token SP
Feature activation+0.341
END
TokenEND
Feature activation+0.715
ING
TokenING
Feature activation+0.737
TOP
Token TOP
Feature activation+0.651
5
Token 5
Feature activation+0.463
SP
Token SP
Feature activation+0.627
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
push
Token push
Feature activation+0.000
all
Token all
Feature activation+0.000
sync
Token sync
Feature activation+0.375
locked
Token locked
Feature activation+0.430
tracks
Token tracks
Feature activation+0.506
down
Token down
Feature activation+0.000
the
Token the
Feature activation+0.000
Timeline
Token Timeline
Feature activation+0.000
after
Token after
Feature activation+0.000
and
Token and
Feature activation+0.000
added
Token added
Feature activation+0.000
a
Token a
Feature activation+0.000
selection
Token selection
Feature activation+0.000
of
Token of
Feature activation+0.000
meat
Token meat
Feature activation+0.326
alternatives
Token alternatives
Feature activation+0.000
:
Token:
Feature activation+0.000
Field
Token Field
Feature activation+0.000
Ro
Token Ro
Feature activation+0.000
ast
Tokenast
Feature activation+0.000
final
Token final
Feature activation+0.000
trophy
Token trophy
Feature activation+0.000
improved
Token improved
Feature activation+0.000
from
Token from
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.310
05
Token05
Feature activation+0.025
%
Token%
Feature activation+0.000
to
Token to
Feature activation+0.000
5
Token 5
Feature activation+0.000
.
Token.
Feature activation+0.000
large
Token large
Feature activation+0.000
and
Token and
Feature activation+0.000
diverse
Token diverse
Feature activation+0.000
genus
Token genus
Feature activation+0.000
of
Token of
Feature activation+0.000
flowering
Token flowering
Feature activation+0.256
plants
Token plants
Feature activation+0.000
,
Token,
Feature activation+0.000
commonly
Token commonly
Feature activation+0.000
called
Token called
Feature activation+0.000
spur
Token spur
Feature activation+0.000

INTERVAL 0.000 - 0.243
CONTAINS 99.128%

and
Token and
Feature activation+0.000
climate
Token climate
Feature activation+0.000
change
Token change
Feature activation+0.000
,
Token,
Feature activation+0.000
Merkel
Token Merkel
Feature activation+0.000
must
Token must
Feature activation+0.000
lead
Token lead
Feature activation+0.000
discussions
Token discussions
Feature activation+0.000
on
Token on
Feature activation+0.000
migration
Token migration
Feature activation+0.000
on
Token on
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
sure
Token sure
Feature activation+0.000
that
Token that
Feature activation+0.000
our
Token our
Feature activation+0.000
research
Token research
Feature activation+0.000
helps
Token helps
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000
better
Token better
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Photo
TokenPhoto
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
addition
Token addition
Feature activation+0.000
,
Token,
Feature activation+0.000
local
Token local
Feature activation+0.000
commanders
Token commanders
Feature activation+0.000
bypass
Token bypass
Feature activation+0.000
ed
Tokened
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Research
TokenResearch
Feature activation+0.000
shows
Token shows
Feature activation+0.000
a
Token a
Feature activation+0.000
child
Token child
Feature activation+0.000
convicted
Token convicted
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
sex
Token sex
Feature activation+0.000
ap
Tokenap
Feature activation+0.000
uz
Tokenuz
Feature activation+0.000
in
Tokenin
Feature activation+0.000
erc
Tokenerc
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
ree
Tokenree
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
then
Token then
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 1 in H8.7: (feature 22406)

TOP ACTIVATIONS
MAX = 3.750

a
Token a
Feature activation+0.334
quarter
Token quarter
Feature activation+2.124
-
Token-
Feature activation+3.357
by
Tokenby
Feature activation+0.258
-
Token-
Feature activation+0.000
quarter
Tokenquarter
Feature activation+3.750
basis
Token basis
Feature activation+0.552
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.862
a
Token a
Feature activation+0.339
global
Token global
Feature activation+2.390
and
Token and
Feature activation+2.789
local
Token local
Feature activation+3.427
scale
Token scale
Feature activation+1.897
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ban
Token Ban
Feature activation+0.000
motive
Token motive
Feature activation+0.000
for
Token for
Feature activation+0.000
struggle
Token struggle
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.425
ideological
Token ideological
Feature activation+3.358
front
Token front
Feature activation+1.127
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
serve
Token serve
Feature activation+0.000
to
Token to
Feature activation+0.000
evaluate
Token evaluate
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.334
quarter
Token quarter
Feature activation+2.124
-
Token-
Feature activation+3.357
by
Tokenby
Feature activation+0.258
-
Token-
Feature activation+0.000
quarter
Tokenquarter
Feature activation+3.750
basis
Token basis
Feature activation+0.552
,
Token,
Feature activation+0.000
cause
Token cause
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
support
Token support
Feature activation+0.000
on
Token on
Feature activation+0.159
its
Token its
Feature activation+1.793
own
Token own
Feature activation+3.040
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
it
Token it
Feature activation+0.000
creates
Token creates
Feature activation+0.000
a
Token a
Feature activation+0.000
place
Token place
Feature activation+0.000
on
Token on
Feature activation+0.110
the
Token the
Feature activation+0.958
Id
Token Id
Feature activation+0.495
itar
Tokenitar
Feature activation+0.034
od
Tokenod
Feature activation+3.030
trail
Token trail
Feature activation+1.940
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000
local
Token local
Feature activation+0.000
climate
Token climate
Feature activation+0.000
.
Token.
Feature activation+0.000
On
Token On
Feature activation+0.000
a
Token a
Feature activation+0.131
global
Token global
Feature activation+2.947
scale
Token scale
Feature activation+0.025
,
Token,
Feature activation+0.000
many
Token many
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
believe
Token believe
Feature activation+0.000
(
Token (
Feature activation+2.082
Form
TokenForm
Feature activation+0.000
ula
Tokenula
Feature activation+0.000
One
Token One
Feature activation+1.317
racing
Token racing
Feature activation+2.492
)
Token)
Feature activation+2.912
track
Token track
Feature activation+1.341
has
Token has
Feature activation+0.000
led
Token led
Feature activation+0.000
to
Token to
Feature activation+0.000
misunderstand
Token misunderstand
Feature activation+0.000
battles
Token battles
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+1.553
case
Token case
Feature activation+2.092
by
Token by
Feature activation+0.979
case
Token case
Feature activation+2.896
basis
Token basis
Feature activation+0.571
with
Token with
Feature activation+0.000
more
Token more
Feature activation+0.000
research
Token research
Feature activation+0.000
and
Token and
Feature activation+0.000
On
TokenOn
Feature activation+0.000
a
Token a
Feature activation+0.637
more
Token more
Feature activation+0.946
meta
Token meta
Feature activation+2.622
-
Token-
Feature activation+2.227
physical
Tokenphysical
Feature activation+2.863
level
Token level
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
become
Token become
Feature activation+0.000
attached
Token attached
Feature activation+0.000
Additionally
TokenAdditionally
Feature activation+0.000
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
[
Token [
Feature activation+1.413
her
Tokenher
Feature activation+0.840
]
Token]
Feature activation+2.844
website
Token website
Feature activation+0.037
âĢ¦
Token âĢ¦
Feature activation+0.000
defendant
Token defendant
Feature activation+0.000
Valerie
Token Valerie
Feature activation+0.000
Sax
Token Sax
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
a
Token a
Feature activation+0.505
side
Token side
Feature activation+2.830
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+0.000
communities
Token communities
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.862
a
Token a
Feature activation+0.339
global
Token global
Feature activation+2.390
and
Token and
Feature activation+2.789
local
Token local
Feature activation+3.427
scale
Token scale
Feature activation+1.897
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
the
Token the
Feature activation+1.710
verbal
Token verbal
Feature activation+2.780
front
Token front
Feature activation+0.310
,
Token,
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
assessment
Token assessment
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.796
NBN
Token NBN
Feature activation+1.137
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.087
s
Tokens
Feature activation+2.716
fibre
Token fibre
Feature activation+2.223
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+0.000
-
Token-
Feature activation+0.000
handed
Tokenhanded
Feature activation+0.000
justice
Token justice
Feature activation+0.000
on
Token on
Feature activation+0.049
his
Token his
Feature activation+2.595
real
Token real
Feature activation+2.703
worth
Token worth
Feature activation+2.208
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
.
Token.
Feature activation+0.000
On
TokenOn
Feature activation+0.000
the
Token the
Feature activation+1.452
10
Token 10
Feature activation+2.620
-
Token-
Feature activation+2.279
kil
Tokenkil
Feature activation+0.697
ometer
Tokenometer
Feature activation+2.694
hike
Token hike
Feature activation+0.493
two
Token two
Feature activation+0.000
men
Token men
Feature activation+0.000
and
Token and
Feature activation+0.000
two
Token two
Feature activation+0.000
bad
Token bad
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
on
Token on
Feature activation+0.078
the
Token the
Feature activation+2.142
manufacturing
Token manufacturing
Feature activation+2.690
line
Token line
Feature activation+0.664
,
Token,
Feature activation+0.000
ther
Token ther
Feature activation+0.000
mos
Tokenmos
Feature activation+0.000
ets
Tokenets
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
a
Token a
Feature activation+0.637
more
Token more
Feature activation+0.946
meta
Token meta
Feature activation+2.622
-
Token-
Feature activation+2.227
physical
Tokenphysical
Feature activation+2.863
level
Token level
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
the
Token the
Feature activation+1.452
10
Token 10
Feature activation+2.620
-
Token-
Feature activation+2.279
kil
Tokenkil
Feature activation+0.697
ometer
Tokenometer
Feature activation+2.694
hike
Token hike
Feature activation+0.493
two
Token two
Feature activation+0.000

Top DFA by src position
MAX = 4.012

and
Token and
Feature activation+0.020
Top resid features:
difficult
Token difficult
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
evaluate
Token evaluate
Feature activation+0.052
Top resid features:
on
Token on
Feature activation+0.368
Top resid features:
a
Token a
Feature activation+4.012
Top resid features:
quarter
Token quarter
Feature activation+0.078
Top resid features:
-
Token-
Feature activation+0.010
Top resid features:
by
Tokenby
Feature activation-0.026
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
quarter
Tokenquarter
Feature activation+0.031
Top resid features:
that
Token that
Feature activation+0.017
Top resid features:
benefits
Token benefits
Feature activation-0.005
Top resid features:
communities
Token communities
Feature activation+0.001
Top resid features:
on
Token on
Feature activation+0.396
Top resid features:
both
Token both
Feature activation+0.284
Top resid features:
a
Token a
Feature activation+3.145
Top resid features:
global
Token global
Feature activation+0.303
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
local
Token local
Feature activation+0.015
Top resid features:
scale
Token scale
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
The
Token The
Feature activation+0.010
Top resid features:
motive
Token motive
Feature activation+0.018
Top resid features:
for
Token for
Feature activation-0.009
Top resid features:
struggle
Token struggle
Feature activation+0.028
Top resid features:
on
Token on
Feature activation+2.586
Top resid features:
the
Token the
Feature activation+1.401
Top resid features:
ideological
Token ideological
Feature activation+0.044
Top resid features:
front
Token front
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
difficult
Token difficult
Feature activation-0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
evaluate
Token evaluate
Feature activation+0.003
Top resid features:
on
Token on
Feature activation+0.793
Top resid features:
a
Token a
Feature activation+3.196
Top resid features:
quarter
Token quarter
Feature activation+0.147
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
by
Tokenby
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
quarter
Tokenquarter
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.010
Top resid features:
cause
Token cause
Feature activation-0.036
Top resid features:
Trump
Token Trump
Feature activation+0.016
Top resid features:
support
Token support
Feature activation+0.019
Top resid features:
on
Token on
Feature activation+0.333
Top resid features:
its
Token its
Feature activation+3.148
Top resid features:
own
Token own
Feature activation+0.281
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
But
Token But
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
creates
Token creates
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
cold
Token cold
Feature activation+0.043
Top resid features:
est
Tokenest
Feature activation+0.034
Top resid features:
place
Token place
Feature activation+0.001
Top resid features:
on
Token on
Feature activation+1.762
Top resid features:
the
Token the
Feature activation+1.837
Top resid features:
Id
Token Id
Feature activation+0.023
Top resid features:
itar
Tokenitar
Feature activation-0.004
Top resid features:
od
Tokenod
Feature activation+0.017
Top resid features:
trail
Token trail
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
local
Token local
Feature activation-0.002
Top resid features:
climate
Token climate
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
On
Token On
Feature activation+0.884
Top resid features:
a
Token a
Feature activation+2.676
Top resid features:
global
Token global
Feature activation+0.110
Top resid features:
scale
Token scale
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
many
Token many
Feature activation+0.000
Top resid features:
scientists
Token scientists
Feature activation+0.000
Top resid features:
achieve
Token achieve
Feature activation+0.005
Top resid features:
its
Token its
Feature activation-0.011
Top resid features:
true
Token true
Feature activation+0.035
Top resid features:
potential
Token potential
Feature activation+0.019
Top resid features:
on
Token on
Feature activation+1.615
Top resid features:
the
Token the
Feature activation+1.897
Top resid features:
(
Token (
Feature activation+0.011
Top resid features:
Form
TokenForm
Feature activation-0.011
Top resid features:
ula
Tokenula
Feature activation-0.025
Top resid features:
One
Token One
Feature activation+0.034
Top resid features:
racing
Token racing
Feature activation+0.016
Top resid features:
Ass
Token Ass
Feature activation+0.001
Top resid features:
essing
Tokenessing
Feature activation+0.028
Top resid features:
custody
Token custody
Feature activation-0.005
Top resid features:
battles
Token battles
Feature activation-0.026
Top resid features:
on
Token on
Feature activation+0.115
Top resid features:
a
Token a
Feature activation+3.605
Top resid features:
case
Token case
Feature activation+0.006
Top resid features:
by
Token by
Feature activation-0.033
Top resid features:
case
Token case
Feature activation+0.005
Top resid features:
basis
Token basis
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
attachments
Token attachments
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.023
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
On
TokenOn
Feature activation+1.323
Top resid features:
a
Token a
Feature activation+1.536
Top resid features:
more
Token more
Feature activation+0.546
Top resid features:
meta
Token meta
Feature activation+0.191
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
physical
Tokenphysical
Feature activation+0.055
Top resid features:
level
Token level
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
âĢ
TokenâĢ
Feature activation+0.003
Top resid features:
ľ
Tokenľ
Feature activation-0.005
Top resid features:
Additionally
TokenAdditionally
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
on
Token on
Feature activation+3.530
Top resid features:
[
Token [
Feature activation+0.019
Top resid features:
her
Tokenher
Feature activation+0.091
Top resid features:
]
Token]
Feature activation+0.002
Top resid features:
website
Token website
Feature activation+0.000
Top resid features:
âĢ¦
Token âĢ¦
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.148
Top resid features:
Ċ
TokenĊ
Feature activation-0.018
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
On
TokenOn
Feature activation+0.252
Top resid features:
a
Token a
Feature activation+3.298
Top resid features:
side
Token side
Feature activation+0.043
Top resid features:
note
Token note
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
hopefully
Token hopefully
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.008
Top resid features:
benefits
Token benefits
Feature activation+0.009
Top resid features:
communities
Token communities
Feature activation-0.009
Top resid features:
on
Token on
Feature activation+0.236
Top resid features:
both
Token both
Feature activation+0.208
Top resid features:
a
Token a
Feature activation+2.898
Top resid features:
global
Token global
Feature activation+0.105
Top resid features:
and
Token and
Feature activation+0.030
Top resid features:
local
Token local
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:
job
Token job
Feature activation-0.006
Top resid features:
interview
Token interview
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
On
TokenOn
Feature activation+1.748
Top resid features:
the
Token the
Feature activation+1.680
Top resid features:
verbal
Token verbal
Feature activation+0.061
Top resid features:
front
Token front
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
switching
Token switching
Feature activation+0.003
Top resid features:
between
Token between
Feature activation+0.012
Top resid features:
competing
Token competing
Feature activation-0.007
Top resid features:
ISPs
Token ISPs
Feature activation+0.027
Top resid features:
on
Token on
Feature activation+0.969
Top resid features:
the
Token the
Feature activation+1.985
Top resid features:
NBN
Token NBN
Feature activation+0.258
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.020
Top resid features:
s
Tokens
Feature activation+0.113
Top resid features:
fibre
Token fibre
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.013
Top resid features:
even
Token even
Feature activation-0.003
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
handed
Tokenhanded
Feature activation-0.008
Top resid features:
justice
Token justice
Feature activation-0.005
Top resid features:
on
Token on
Feature activation+2.372
Top resid features:
his
Token his
Feature activation+1.094
Top resid features:
real
Token real
Feature activation+0.035
Top resid features:
worth
Token worth
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:
women
Token women
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
On
TokenOn
Feature activation+1.144
Top resid features:
the
Token the
Feature activation+1.984
Top resid features:
10
Token 10
Feature activation+0.090
Top resid features:
-
Token-
Feature activation+0.016
Top resid features:
kil
Tokenkil
Feature activation+0.020
Top resid features:
ometer
Tokenometer
Feature activation+0.138
Top resid features:
hike
Token hike
Feature activation+0.000
Top resid features:
't
Token't
Feature activation-0.001
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
bad
Token bad
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
But
Token But
Feature activation+0.013
Top resid features:
on
Token on
Feature activation+2.024
Top resid features:
the
Token the
Feature activation+1.357
Top resid features:
manufacturing
Token manufacturing
Feature activation+0.013
Top resid features:
line
Token line
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
ther
Token ther
Feature activation+0.000
Top resid features:
these
Token these
Feature activation+0.003
Top resid features:
attachments
Token attachments
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.035
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.019
Top resid features:
On
TokenOn
Feature activation+1.635
Top resid features:
a
Token a
Feature activation+1.179
Top resid features:
more
Token more
Feature activation+0.491
Top resid features:
meta
Token meta
Feature activation+0.092
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
physical
Tokenphysical
Feature activation+0.000
Top resid features:
women
Token women
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
On
TokenOn
Feature activation+1.233
Top resid features:
the
Token the
Feature activation+1.960
Top resid features:
10
Token 10
Feature activation+0.065
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
kil
Tokenkil
Feature activation+0.000
Top resid features:
ometer
Tokenometer
Feature activation+0.000
Top resid features:
hike
Token hike
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.02

Head 2: 0.02

Head 3: 0.03

Head 4: 0.09

Head 5: 0.06

Head 6: 0.02

Head 7: 0.55

Head 8: 0.05

Head 9: 0.04

Head 10: 0.07

Head 11: 0.02

Positive logits

basis2.86

occasions2.65

shores2.50

occasion2.34

horizon2.33

shelves2.27

sidelines2.25

roads2.25

grounds2.22

imeo2.22

road2.20

dime2.18

platform2.17

highways2.16

doorstep2.16

eday2.16

runway2.13

shelf2.13

side2.10

weekends2.09

Negative logits

eful-1.39

ibraries-1.35

lords-1.35

Vaughan-1.33

holders-1.33

utter-1.32

orically-1.32

nomine-1.28

incumbent-1.26

ropri-1.25

fits-1.23

Emanuel-1.22

Pierce-1.21

Watts-1.20

ocate-1.20

ults-1.19

baptized-1.19

isch-1.18

terness-1.18

ritch-1.18

INTERVAL 3.375 - 3.750
CONTAINS 0.000%

on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.862
a
Token a
Feature activation+0.339
global
Token global
Feature activation+2.390
and
Token and
Feature activation+2.789
local
Token local
Feature activation+3.427
scale
Token scale
Feature activation+1.897
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ban
Token Ban
Feature activation+0.000
a
Token a
Feature activation+0.334
quarter
Token quarter
Feature activation+2.124
-
Token-
Feature activation+3.357
by
Tokenby
Feature activation+0.258
-
Token-
Feature activation+0.000
quarter
Tokenquarter
Feature activation+3.750
basis
Token basis
Feature activation+0.552
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000

INTERVAL 3.000 - 3.375
CONTAINS 0.001%

place
Token place
Feature activation+0.000
on
Token on
Feature activation+0.110
the
Token the
Feature activation+0.958
Id
Token Id
Feature activation+0.495
itar
Tokenitar
Feature activation+0.034
od
Tokenod
Feature activation+3.030
trail
Token trail
Feature activation+1.940
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000
motive
Token motive
Feature activation+0.000
for
Token for
Feature activation+0.000
struggle
Token struggle
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.425
ideological
Token ideological
Feature activation+3.358
front
Token front
Feature activation+1.127
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
serve
Token serve
Feature activation+0.000
to
Token to
Feature activation+0.000
evaluate
Token evaluate
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.334
quarter
Token quarter
Feature activation+2.124
-
Token-
Feature activation+3.357
by
Tokenby
Feature activation+0.258
-
Token-
Feature activation+0.000
quarter
Tokenquarter
Feature activation+3.750
basis
Token basis
Feature activation+0.552
,
Token,
Feature activation+0.000
cause
Token cause
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
support
Token support
Feature activation+0.000
on
Token on
Feature activation+0.159
its
Token its
Feature activation+1.793
own
Token own
Feature activation+3.040
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
it
Token it
Feature activation+0.000
creates
Token creates
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 2.625 - 3.000
CONTAINS 0.001%

communities
Token communities
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.862
a
Token a
Feature activation+0.339
global
Token global
Feature activation+2.390
and
Token and
Feature activation+2.789
local
Token local
Feature activation+3.427
scale
Token scale
Feature activation+1.897
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Additionally
TokenAdditionally
Feature activation+0.000
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
[
Token [
Feature activation+1.413
her
Tokenher
Feature activation+0.840
]
Token]
Feature activation+2.844
website
Token website
Feature activation+0.037
âĢ¦
Token âĢ¦
Feature activation+0.000
defendant
Token defendant
Feature activation+0.000
Valerie
Token Valerie
Feature activation+0.000
Sax
Token Sax
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.796
NBN
Token NBN
Feature activation+1.137
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.087
s
Tokens
Feature activation+2.716
fibre
Token fibre
Feature activation+2.223
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+0.000
On
TokenOn
Feature activation+0.000
a
Token a
Feature activation+0.637
more
Token more
Feature activation+0.946
meta
Token meta
Feature activation+2.622
-
Token-
Feature activation+2.227
physical
Tokenphysical
Feature activation+2.863
level
Token level
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
become
Token become
Feature activation+0.000
attached
Token attached
Feature activation+0.000
On
TokenOn
Feature activation+0.000
the
Token the
Feature activation+1.452
10
Token 10
Feature activation+2.620
-
Token-
Feature activation+2.279
kil
Tokenkil
Feature activation+0.697
ometer
Tokenometer
Feature activation+2.694
hike
Token hike
Feature activation+0.493
two
Token two
Feature activation+0.000
men
Token men
Feature activation+0.000
and
Token and
Feature activation+0.000
two
Token two
Feature activation+0.000

INTERVAL 2.250 - 2.625
CONTAINS 0.006%

local
Token local
Feature activation+2.453
,
Token,
Feature activation+2.035
state
Token state
Feature activation+1.636
,
Token,
Feature activation+0.769
or
Token or
Feature activation+0.483
federal
Token federal
Feature activation+2.306
level
Token level
Feature activation+0.357
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.000
Rasmussen
Token Rasmussen
Feature activation+0.000
poll
Token poll
Feature activation+0.000
my
Token my
Feature activation+0.000
tactics
Token tactics
Feature activation+0.000
were
Token were
Feature activation+0.000
wrong
Token wrong
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+2.385
night
Token night
Feature activation+0.962
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
should
Token should
Feature activation+0.000
have
Token have
Feature activation+0.000
here
Token here
Feature activation+0.000
.
Token.
Feature activation+0.000
On
Token On
Feature activation+0.000
a
Token a
Feature activation+0.726
bitterly
Token bitterly
Feature activation+1.492
cold
Token cold
Feature activation+2.320
night
Token night
Feature activation+1.090
at
Token at
Feature activation+0.000
Bl
Token Bl
Feature activation+0.000
und
Tokenund
Feature activation+0.000
ell
Tokenell
Feature activation+0.000
âĢĭ
TokenâĢĭ
Feature activation+0.000
"
Token"
Feature activation+0.000
On
TokenOn
Feature activation+0.000
the
Token the
Feature activation+1.134
couple
Token couple
Feature activation+2.365
of
Token of
Feature activation+2.255
nights
Token nights
Feature activation+0.184
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
actually
Token actually
Feature activation+0.000
did
Token did
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢĭ
TokenâĢĭ
Feature activation+0.000
"
Token"
Feature activation+0.000
On
TokenOn
Feature activation+0.000
the
Token the
Feature activation+1.134
couple
Token couple
Feature activation+2.365
of
Token of
Feature activation+2.255
nights
Token nights
Feature activation+0.184
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
actually
Token actually
Feature activation+0.000

INTERVAL 1.875 - 2.250
CONTAINS 0.017%

,
Token,
Feature activation+0.000
only
Token only
Feature activation+0.000
opening
Token opening
Feature activation+0.000
on
Token on
Feature activation+0.123
the
Token the
Feature activation+1.411
outside
Token outside
Feature activation+1.895
world
Token world
Feature activation+1.630
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
H
TokenH
Feature activation+0.000
Sega
Token Sega
Feature activation+0.000
some
Token some
Feature activation+0.000
issues
Token issues
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.106
legal
Token legal
Feature activation+2.152
.
Token.
Feature activation+0.000
Recently
TokenRecently
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
After
Token After
Feature activation+0.000
nobody
Token nobody
Feature activation+0.000
commits
Token commits
Feature activation+0.000
suicide
Token suicide
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+2.116
day
Token day
Feature activation+0.379
,
Token,
Feature activation+0.000
each
Token each
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Duke
Token Duke
Feature activation+0.000
and
Token and
Feature activation+0.000
Kentucky
Token Kentucky
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.242
same
Token same
Feature activation+2.025
day
Token day
Feature activation+0.119
this
Token this
Feature activation+0.000
spring
Token spring
Feature activation+0.000
.
Token.
Feature activation+0.000
Waters
Token Waters
Feature activation+0.000
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.000
think
Token think
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.490
Coalition
Token Coalition
Feature activation+2.060
side
Token side
Feature activation+0.216
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
already
Token already
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000

INTERVAL 1.500 - 1.875
CONTAINS 0.040%

area
Token area
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
just
Token just
Feature activation+1.552
the
Token the
Feature activation+1.154
main
Token main
Feature activation+1.334
lag
Token lag
Feature activation+0.891
oon
Tokenoon
Feature activation+1.680
area
Token area
Feature activation+1.176
missile
Token missile
Feature activation+0.000
is
Token is
Feature activation+0.000
flown
Token flown
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+1.420
standard
Token standard
Feature activation+1.793
flight
Token flight
Feature activation+1.665
path
Token path
Feature activation+1.063
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
example
Token example
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
version
Token version
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.531
grounds
Token grounds
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
take
Token take
Feature activation+0.000
players
Token players
Feature activation+0.000
have
Token have
Feature activation+0.000
faced
Token faced
Feature activation+0.000
on
Token on
Feature activation+0.218
the
Token the
Feature activation+1.903
Nintendo
Token Nintendo
Feature activation+1.650
Switch
Token Switch
Feature activation+1.437
version
Token version
Feature activation+1.077
of
Token of
Feature activation+0.000
Over
Token Over
Feature activation+0.000
cooked
Tokencooked
Feature activation+0.000
also
Token also
Feature activation+0.000
field
Token field
Feature activation+0.000
decent
Token decent
Feature activation+0.000
units
Token units
Feature activation+0.000
on
Token on
Feature activation+0.152
that
Token that
Feature activation+1.681
side
Token side
Feature activation+1.163
of
Token of
Feature activation+0.847
the
Token the
Feature activation+0.531
ball
Token ball
Feature activation+0.784
.
Token.
Feature activation+0.000

INTERVAL 1.125 - 1.500
CONTAINS 0.083%

private
Token private
Feature activation+0.000
lands
Token lands
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.851
small
Token small
Feature activation+2.209
corridor
Token corridor
Feature activation+1.333
of
Token of
Feature activation+1.135
trail
Token trail
Feature activation+0.172
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
in
Token in
Feature activation+0.000
Bu
TokenBu
Feature activation+0.000
ying
Tokenying
Feature activation+0.000
and
Token and
Feature activation+0.000
Selling
Token Selling
Feature activation+0.000
on
Token on
Feature activation+0.300
the
Token the
Feature activation+1.468
Net
Token Net
Feature activation+0.610
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
internet
Token internet
Feature activation+0.000
passes
Token passes
Feature activation+0.000
for
Token for
Feature activation+0.000
analysis
Token analysis
Feature activation+0.000
on
Token on
Feature activation+0.187
the
Token the
Feature activation+1.263
Irish
Token Irish
Feature activation+1.379
Left
Token Left
Feature activation+1.531
âĢ¦
TokenâĢ¦
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
to
Token to
Feature activation+0.000
maintain
Token maintain
Feature activation+0.000
consistency
Token consistency
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.945
site
Token site
Feature activation+1.479
as
Token as
Feature activation+0.345
sprawling
Token sprawling
Feature activation+0.000
as
Token as
Feature activation+0.433
ours
Token ours
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
hit
Token hit
Feature activation+0.000
60
Token 60
Feature activation+0.000
stone
Token stone
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.281
scales
Token scales
Feature activation+0.938
?
Token?
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Researchers
TokenResearchers
Feature activation+0.000
at
Token at
Feature activation+0.000

INTERVAL 0.750 - 1.125
CONTAINS 0.146%

to
Token to
Feature activation+0.000
research
Token research
Feature activation+0.000
Bout
Token Bout
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.652
Internet
Token Internet
Feature activation+0.757
or
Token or
Feature activation+0.000
other
Token other
Feature activation+0.000
media
Token media
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
most
Token most
Feature activation+0.000
impressive
Token impressive
Feature activation+0.000
stat
Token stat
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.623
Scorpion
Token Scorpion
Feature activation+0.851
Pistol
Token Pistol
Feature activation+1.228
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
price
Token price
Feature activation+0.000
tag
Token tag
Feature activation+0.000
compounds
Token compounds
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
deposited
Token deposited
Feature activation+0.000
on
Token on
Feature activation+0.161
the
Token the
Feature activation+0.765
paper
Token paper
Feature activation+1.165
are
Token are
Feature activation+0.000
transported
Token transported
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
ester
Tokenester
Feature activation+0.000
ing
Tokening
Feature activation+0.000
on
Token on
Feature activation+0.000
France
Token France
Feature activation+0.821
's
Token's
Feature activation+0.832
notorious
Token notorious
Feature activation+0.956
suburban
Token suburban
Feature activation+0.713
high
Token high
Feature activation+0.402
-
Token-
Feature activation+0.255
rise
Tokenrise
Feature activation+0.473
estates
Token estates
Feature activation+0.232
living
Token living
Feature activation+0.000
room
Token room
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.036
table
Token table
Feature activation+0.901
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000

INTERVAL 0.375 - 0.750
CONTAINS 0.200%

that
Token that
Feature activation+0.000
girl
Token girl
Feature activation+0.000
spinning
Token spinning
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.710
mountains
Token mountains
Feature activation+0.692
ide
Tokenide
Feature activation+0.403
grew
Token grew
Feature activation+0.000
older
Token older
Feature activation+0.000
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
sharp
Token sharp
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
on
Token on
Feature activation+0.000
Romney
Token Romney
Feature activation+0.000
on
Token on
Feature activation+0.000
matters
Token matters
Feature activation+0.543
of
Token of
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
policy
Token policy
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
get
Token get
Feature activation+0.000
your
Token your
Feature activation+0.000
taxes
Token taxes
Feature activation+0.000
in
Token in
Feature activation+0.000
on
Token on
Feature activation+0.025
time
Token time
Feature activation+0.627
,
Token,
Feature activation+0.000
there
Token there
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
The
Token The
Feature activation+0.000
setting
Token setting
Feature activation+0.000
sun
Token sun
Feature activation+0.000
on
Token on
Feature activation+0.000
Cascade
Token Cascade
Feature activation+0.434
Mountain
Token Mountain
Feature activation+0.762
creates
Token creates
Feature activation+0.000
an
Token an
Feature activation+0.000
Al
Token Al
Feature activation+0.000
p
Tokenp
Feature activation+0.000
l
Tokenl
Feature activation+0.000
ı
Tokenı
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
fa
Tokenfa
Feature activation+0.000
on
Token on
Feature activation+0.000
Turkish
Token Turkish
Feature activation+0.686
Syrian
Token Syrian
Feature activation+0.916
border
Token border
Feature activation+0.604
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 0.000 - 0.375
CONTAINS 99.507%

man
Token man
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Lang
Token Lang
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
He
TokenHe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
strong
Token strong
Feature activation+0.000
ugly
Token ugly
Feature activation+0.000
sou
Token sou
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
ess
Tokeness
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
of
Token of
Feature activation+0.000
unarmed
Token unarmed
Feature activation+0.000
helpless
Token helpless
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
find
Token find
Feature activation+0.000
a
Token a
Feature activation+0.000
skirt
Token skirt
Feature activation+0.000
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
not
Token not
Feature activation+0.000
short
Token short
Feature activation+0.000
on
Token on
Feature activation+0.000
her
Token her
Feature activation+1.444
helps
Token helps
Feature activation+0.000
to
Token to
Feature activation+0.000
straight
Token straight
Feature activation+0.000
en
Tokenen
Feature activation+0.000
it
Token it
Feature activation+0.000
between
Token between
Feature activation+0.000
shar
Token shar
Feature activation+0.324
pen
Tokenpen
Feature activation+0.377
ings
Tokenings
Feature activation+0.389
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
forward
Token forward
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
years
Token years
Feature activation+0.000
of
Token of
Feature activation+0.000
heavy
Token heavy
Feature activation+0.000
job
Token job
Feature activation+0.000
losses
Token losses
Feature activation+0.000
and
Token and
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 H8.7: (feature 20206)

TOP ACTIVATIONS
MAX = 2.276

that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.098
done
Token done
Feature activation+0.000
that
Token that
Feature activation+2.276
way
Token way
Feature activation+0.256
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
your
Token your
Feature activation+0.000
head
Token head
Feature activation+0.000
and
Token and
Feature activation+0.000
spine
Token spine
Feature activation+0.509
right
Token right
Feature activation+0.015
the
Token the
Feature activation+2.014
fuck
Token fuck
Feature activation+1.572
out
Token out
Feature activation+0.777
of
Token of
Feature activation+0.741
your
Token your
Feature activation+0.000
body
Token body
Feature activation+0.000
been
Token been
Feature activation+0.000
located
Token located
Feature activation+0.000
an
Token an
Feature activation+1.154
inch
Token inch
Feature activation+0.744
or
Token or
Feature activation+0.000
two
Token two
Feature activation+1.923
forward
Token forward
Feature activation+0.582
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
fish
Token fish
Feature activation+0.000
would
Token would
Feature activation+0.000
trial
Token trial
Feature activation+0.000
we
Token we
Feature activation+0.000
wanted
Token wanted
Feature activation+0.015
to
Token to
Feature activation+0.204
have
Token have
Feature activation+0.370
six
Token six
Feature activation+1.904
years
Token years
Feature activation+1.026
ago
Token ago
Feature activation+0.550
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
VD
TokenVD
Feature activation+0.000
and
Token and
Feature activation+0.000
reb
Token reb
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
ied
Tokenied
Feature activation+0.000
several
Token several
Feature activation+1.896
times
Token times
Feature activation+0.687
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.811
following
Token following
Feature activation+0.140
decades
Token decades
Feature activation+0.512
had
Token had
Feature activation+0.000
also
Token also
Feature activation+0.000
been
Token been
Feature activation+0.000
broken
Token broken
Feature activation+0.000
into
Token into
Feature activation+0.000
three
Token three
Feature activation+1.797
or
Token or
Feature activation+0.000
four
Token four
Feature activation+1.867
months
Token months
Feature activation+1.073
ago
Token ago
Feature activation+0.913
,
Token,
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
that
Token that
Feature activation+0.000
happens
Token happens
Feature activation+0.000
so
Token so
Feature activation+1.783
naturally
Token naturally
Feature activation+0.998
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
same
Token same
Feature activation+0.000
is
Token is
Feature activation+0.039
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
shot
Token shot
Feature activation+0.000
7
Token 7
Feature activation+0.000
times
Token times
Feature activation+0.000
execution
Token execution
Feature activation+1.774
style
Token style
Feature activation+1.258
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
home
Token home
Feature activation+0.000
,
Token,
Feature activation+0.000
keep
Token keep
Feature activation+0.000
doing
Token doing
Feature activation+0.000
what
Token what
Feature activation+0.000
they
Token they
Feature activation+0.000
love
Token love
Feature activation+0.000
the
Token the
Feature activation+1.743
most
Token most
Feature activation+1.458
âĢĵ
Token âĢĵ
Feature activation+0.001
saving
Token saving
Feature activation+0.000
dogs
Token dogs
Feature activation+0.000
and
Token and
Feature activation+0.000
t
Tokent
Feature activation+0.000
go
Token go
Feature activation+0.000
things
Token things
Feature activation+0.000
like
Token like
Feature activation+0.191
this
Token this
Feature activation+0.225
public
Token public
Feature activation+1.733
punishment
Token punishment
Feature activation+0.521
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
we
Token we
Feature activation+0.000
don
Token don
Feature activation+0.000
had
Token had
Feature activation+0.000
gamb
Token gamb
Feature activation+0.000
led
Tokenled
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
fragmentation
Token fragmentation
Feature activation+1.728
notwithstanding
Token notwithstanding
Feature activation+0.000
,
Token,
Feature activation+0.000
her
Token her
Feature activation+0.000
candidacy
Token candidacy
Feature activation+0.000
in
Token in
Feature activation+0.000
will
Token will
Feature activation+0.000
likely
Token likely
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
block
Token block
Feature activation+0.000
progressive
Token progressive
Feature activation+1.684
action
Token action
Feature activation+0.268
on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
ranks
Token ranks
Feature activation+0.000
We
Token We
Feature activation+0.000
must
Token must
Feature activation+0.000
go
Token go
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000
very
Token very
Feature activation+1.661
consciously
Token consciously
Feature activation+0.451
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Det
TokenDet
Feature activation+0.000
to
Token to
Feature activation+0.000
accomplish
Token accomplish
Feature activation+0.000
what
Token what
Feature activation+0.000
was
Token was
Feature activation+0.000
accomplished
Token accomplished
Feature activation+0.000
this
Token this
Feature activation+1.655
year
Token year
Feature activation+0.907
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
have
Token have
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
to
Token to
Feature activation+0.000
apologize
Token apologize
Feature activation+0.000
for
Token for
Feature activation+0.000
'
Token'
Feature activation+1.652
Steve
Token Steve
Feature activation+0.000
King
Token King
Feature activation+0.000
spins
Token spins
Feature activation+0.000
GOP
Token GOP
Feature activation+0.000
punishment
Token punishment
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
say
Token say
Feature activation+0.000
it
Token it
Feature activation+0.000
one
Token one
Feature activation+0.311
more
Token more
Feature activation+1.628
time
Token time
Feature activation+0.193
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
people
Token people
Feature activation+0.000
in
Token in
Feature activation+0.000
and
Token and
Feature activation+0.000
are
Token are
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
you
Token you
Feature activation+0.000
even
Token even
Feature activation+0.857
now
Token now
Feature activation+1.620
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
FOR
TokenFOR
Feature activation+0.000
MORE
Token MORE
Feature activation+0.000
fuels
Token fuels
Feature activation+0.000
more
Token more
Feature activation+0.086
clean
Token clean
Feature activation+1.085
ly
Tokenly
Feature activation+0.854
and
Token and
Feature activation+0.171
efficiently
Token efficiently
Feature activation+1.602
âĢ
TokenâĢ
Feature activation+0.020
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.000
experts
Token experts
Feature activation+0.000
more
Token more
Feature activation+0.000
tightly
Token tightly
Feature activation+0.487
and
Token and
Feature activation+0.000
release
Token release
Feature activation+0.000
it
Token it
Feature activation+0.000
more
Token more
Feature activation+1.600
slowly
Token slowly
Feature activation+1.287
[
Token [
Feature activation+0.000
_
Token_
Feature activation+0.000
2
Token2
Feature activation+0.000
_
Token_
Feature activation+0.000
died
Token died
Feature activation+0.000
for
Token for
Feature activation+0.000
,
Token,
Feature activation+0.000
worked
Token worked
Feature activation+0.000
for
Token for
Feature activation+0.000
(
Token (
Feature activation+1.588
and
Tokenand
Feature activation+0.000
)
Token)
Feature activation+0.000
fought
Token fought
Feature activation+0.000
for
Token for
Feature activation+0.148
."
Token."
Feature activation+0.000

Top DFA by src position
MAX = 2.848

directed
Token directed
Feature activation+0.007
Top resid features:
that
Token that
Feature activation+0.021
Top resid features:
it
Token it
Feature activation+0.016
Top resid features:
not
Token not
Feature activation+0.015
Top resid features:
be
Token be
Feature activation-0.032
Top resid features:
done
Token done
Feature activation+2.848
Top resid features:
that
Token that
Feature activation+0.075
Top resid features:
way
Token way
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:
Zero
TokenZero
Feature activation+0.008
Top resid features:
your
Token your
Feature activation+0.008
Top resid features:
head
Token head
Feature activation+0.035
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
spine
Token spine
Feature activation+0.087
Top resid features:
right
Token right
Feature activation+2.388
Top resid features:
the
Token the
Feature activation+0.104
Top resid features:
fuck
Token fuck
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
your
Token your
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
If
Token If
Feature activation-0.026
Top resid features:
it
Token it
Feature activation+0.009
Top resid features:
had
Token had
Feature activation-0.019
Top resid features:
been
Token been
Feature activation+0.026
Top resid features:
located
Token located
Feature activation+2.213
Top resid features:
an
Token an
Feature activation+0.077
Top resid features:
inch
Token inch
Feature activation+0.203
Top resid features:
or
Token or
Feature activation-0.001
Top resid features:
two
Token two
Feature activation+0.063
Top resid features:
forward
Token forward
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
trial
Token trial
Feature activation+0.171
Top resid features:
we
Token we
Feature activation+0.012
Top resid features:
wanted
Token wanted
Feature activation+0.427
Top resid features:
to
Token to
Feature activation+0.047
Top resid features:
have
Token have
Feature activation+1.881
Top resid features:
six
Token six
Feature activation+0.034
Top resid features:
years
Token years
Feature activation+0.000
Top resid features:
ago
Token ago
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
NK
Token NK
Feature activation-0.001
Top resid features:
VD
TokenVD
Feature activation+0.011
Top resid features:
and
Token and
Feature activation+0.014
Top resid features:
reb
Token reb
Feature activation+0.008
Top resid features:
ur
Tokenur
Feature activation+0.031
Top resid features:
ied
Tokenied
Feature activation+2.440
Top resid features:
several
Token several
Feature activation+0.030
Top resid features:
times
Token times
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
following
Token following
Feature activation+0.000
Top resid features:
It
Token It
Feature activation-0.009
Top resid features:
had
Token had
Feature activation+0.013
Top resid features:
also
Token also
Feature activation+0.009
Top resid features:
been
Token been
Feature activation+0.024
Top resid features:
broken
Token broken
Feature activation+0.095
Top resid features:
into
Token into
Feature activation+2.306
Top resid features:
three
Token three
Feature activation+0.011
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
four
Token four
Feature activation+0.000
Top resid features:
months
Token months
Feature activation+0.000
Top resid features:
ago
Token ago
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
me
Token me
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
because
Token because
Feature activation+0.025
Top resid features:
that
Token that
Feature activation+0.016
Top resid features:
happens
Token happens
Feature activation+2.275
Top resid features:
so
Token so
Feature activation+0.053
Top resid features:
naturally
Token naturally
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:
same
Token same
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
who
Token who
Feature activation-0.007
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
shot
Token shot
Feature activation+0.068
Top resid features:
7
Token 7
Feature activation+0.169
Top resid features:
times
Token times
Feature activation+2.265
Top resid features:
execution
Token execution
Feature activation+0.017
Top resid features:
style
Token style
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
home
Token home
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
keep
Token keep
Feature activation+0.003
Top resid features:
doing
Token doing
Feature activation+0.002
Top resid features:
what
Token what
Feature activation+0.037
Top resid features:
they
Token they
Feature activation-0.003
Top resid features:
love
Token love
Feature activation+2.388
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
saving
Token saving
Feature activation+0.000
Top resid features:
dogs
Token dogs
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
t
Tokent
Feature activation+0.004
Top resid features:
go
Token go
Feature activation+0.055
Top resid features:
things
Token things
Feature activation+0.079
Top resid features:
like
Token like
Feature activation+0.045
Top resid features:
this
Token this
Feature activation+2.240
Top resid features:
public
Token public
Feature activation+0.010
Top resid features:
punishment
Token punishment
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:
we
Token we
Feature activation+0.000
Top resid features:
ner
Tokenner
Feature activation-0.003
Top resid features:
had
Token had
Feature activation-0.007
Top resid features:
gamb
Token gamb
Feature activation+0.013
Top resid features:
led
Tokenled
Feature activation+0.007
Top resid features:
that
Token that
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+2.393
Top resid features:
fragmentation
Token fragmentation
Feature activation+0.028
Top resid features:
notwithstanding
Token notwithstanding
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
candidacy
Token candidacy
Feature activation+0.000
Top resid features:
they
Token they
Feature activation-0.002
Top resid features:
will
Token will
Feature activation-0.006
Top resid features:
likely
Token likely
Feature activation-0.010
Top resid features:
continue
Token continue
Feature activation+0.077
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
block
Token block
Feature activation+2.280
Top resid features:
progressive
Token progressive
Feature activation+0.050
Top resid features:
action
Token action
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
We
Token We
Feature activation-0.004
Top resid features:
must
Token must
Feature activation+0.006
Top resid features:
go
Token go
Feature activation+0.004
Top resid features:
about
Token about
Feature activation+0.148
Top resid features:
it
Token it
Feature activation+2.017
Top resid features:
very
Token very
Feature activation+0.100
Top resid features:
consciously
Token consciously
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:
got
Token got
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
accomplish
Token accomplish
Feature activation+0.002
Top resid features:
what
Token what
Feature activation+0.087
Top resid features:
was
Token was
Feature activation+0.009
Top resid features:
accomplished
Token accomplished
Feature activation+2.167
Top resid features:
this
Token this
Feature activation+0.114
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
I
TokenI
Feature activation-0.010
Top resid features:
have
Token have
Feature activation-0.006
Top resid features:
nothing
Token nothing
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
apologize
Token apologize
Feature activation+0.060
Top resid features:
for
Token for
Feature activation+2.515
Top resid features:
'
Token'
Feature activation-0.030
Top resid features:
Steve
Token Steve
Feature activation+0.000
Top resid features:
King
Token King
Feature activation+0.000
Top resid features:
spins
Token spins
Feature activation+0.000
Top resid features:
GOP
Token GOP
Feature activation+0.000
Top resid features:
let
Token let
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
s
Tokens
Feature activation+0.006
Top resid features:
say
Token say
Feature activation+0.007
Top resid features:
it
Token it
Feature activation+2.211
Top resid features:
one
Token one
Feature activation+0.112
Top resid features:
more
Token more
Feature activation+0.012
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
spirit
Token spirit
Feature activation+0.021
Top resid features:
and
Token and
Feature activation+0.027
Top resid features:
are
Token are
Feature activation+0.011
Top resid features:
surrounding
Token surrounding
Feature activation+0.024
Top resid features:
you
Token you
Feature activation+1.209
Top resid features:
even
Token even
Feature activation+0.906
Top resid features:
now
Token now
Feature activation+0.057
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:
of
Token of
Feature activation-0.005
Top resid features:
fossil
Token fossil
Feature activation-0.015
Top resid features:
fuels
Token fuels
Feature activation+0.119
Top resid features:
more
Token more
Feature activation+0.599
Top resid features:
clean
Token clean
Feature activation+0.453
Top resid features:
ly
Tokenly
Feature activation+1.071
Top resid features:
and
Token and
Feature activation+0.044
Top resid features:
efficiently
Token efficiently
Feature activation+0.119
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:
ball
Token ball
Feature activation+0.030
Top resid features:
more
Token more
Feature activation+0.013
Top resid features:
tightly
Token tightly
Feature activation-0.017
Top resid features:
and
Token and
Feature activation+0.063
Top resid features:
release
Token release
Feature activation-0.046
Top resid features:
it
Token it
Feature activation+2.180
Top resid features:
more
Token more
Feature activation+0.090
Top resid features:
slowly
Token slowly
Feature activation+0.000
Top resid features:
[
Token [
Feature activation+0.000
Top resid features:
_
Token_
Feature activation+0.000
Top resid features:
2
Token2
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.016
Top resid features:
died
Token died
Feature activation+0.013
Top resid features:
for
Token for
Feature activation+0.548
Top resid features:
,
Token,
Feature activation+0.050
Top resid features:
worked
Token worked
Feature activation+0.053
Top resid features:
for
Token for
Feature activation+1.669
Top resid features:
(
Token (
Feature activation+0.014
Top resid features:
and
Tokenand
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
fought
Token fought
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.02

Head 2: 0.03

Head 3: 0.04

Head 4: 0.08

Head 5: 0.07

Head 6: 0.02

Head 7: 0.53

Head 8: 0.04

Head 9: 0.04

Head 10: 0.08

Head 11: 0.02

Positive logits

ilaterally2.74

etheless2.65

edly2.49

evenings2.47

terday2.42

aneously2.39

til2.35

mornings2.32

itially2.26

nesday2.24

gently2.21

ocally2.21

thereafter2.21

afterward2.19

rarily2.15

inally2.13

withstanding2.13

orously2.10

uly2.10

mediately2.10

Negative logits

nings-1.82

Debt-1.66

MSN-1.62

QUEST-1.58

asive-1.58

val-1.52

qa-1.49

Assets-1.49

eries-1.49

OA-1.49

Wealth-1.48

ulla-1.48

personality-1.47

Encyclopedia-1.46

SELECT-1.44

Dictionary-1.44

debt-1.43

rious-1.42

Companion-1.40

History-1.38

INTERVAL 2.048 - 2.276
CONTAINS 0.000%

that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.098
done
Token done
Feature activation+0.000
that
Token that
Feature activation+2.276
way
Token way
Feature activation+0.256
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000

INTERVAL 1.821 - 2.048
CONTAINS 0.001%

trial
Token trial
Feature activation+0.000
we
Token we
Feature activation+0.000
wanted
Token wanted
Feature activation+0.015
to
Token to
Feature activation+0.204
have
Token have
Feature activation+0.370
six
Token six
Feature activation+1.904
years
Token years
Feature activation+1.026
ago
Token ago
Feature activation+0.550
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
been
Token been
Feature activation+0.000
located
Token located
Feature activation+0.000
an
Token an
Feature activation+1.154
inch
Token inch
Feature activation+0.744
or
Token or
Feature activation+0.000
two
Token two
Feature activation+1.923
forward
Token forward
Feature activation+0.582
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
fish
Token fish
Feature activation+0.000
would
Token would
Feature activation+0.000
your
Token your
Feature activation+0.000
head
Token head
Feature activation+0.000
and
Token and
Feature activation+0.000
spine
Token spine
Feature activation+0.509
right
Token right
Feature activation+0.015
the
Token the
Feature activation+2.014
fuck
Token fuck
Feature activation+1.572
out
Token out
Feature activation+0.777
of
Token of
Feature activation+0.741
your
Token your
Feature activation+0.000
body
Token body
Feature activation+0.000
VD
TokenVD
Feature activation+0.000
and
Token and
Feature activation+0.000
reb
Token reb
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
ied
Tokenied
Feature activation+0.000
several
Token several
Feature activation+1.896
times
Token times
Feature activation+0.687
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.811
following
Token following
Feature activation+0.140
decades
Token decades
Feature activation+0.512

INTERVAL 1.593 - 1.821
CONTAINS 0.001%

and
Token and
Feature activation+0.000
are
Token are
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
you
Token you
Feature activation+0.000
even
Token even
Feature activation+0.857
now
Token now
Feature activation+1.620
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
FOR
TokenFOR
Feature activation+0.000
MORE
Token MORE
Feature activation+0.000
We
Token We
Feature activation+0.000
must
Token must
Feature activation+0.000
go
Token go
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000
very
Token very
Feature activation+1.661
consciously
Token consciously
Feature activation+0.451
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Det
TokenDet
Feature activation+0.000
had
Token had
Feature activation+0.000
also
Token also
Feature activation+0.000
been
Token been
Feature activation+0.000
broken
Token broken
Feature activation+0.000
into
Token into
Feature activation+0.000
three
Token three
Feature activation+1.797
or
Token or
Feature activation+0.000
four
Token four
Feature activation+1.867
months
Token months
Feature activation+1.073
ago
Token ago
Feature activation+0.913
,
Token,
Feature activation+0.000
had
Token had
Feature activation+0.000
gamb
Token gamb
Feature activation+0.000
led
Tokenled
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
fragmentation
Token fragmentation
Feature activation+1.728
notwithstanding
Token notwithstanding
Feature activation+0.000
,
Token,
Feature activation+0.000
her
Token her
Feature activation+0.000
candidacy
Token candidacy
Feature activation+0.000
in
Token in
Feature activation+0.000
have
Token have
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
to
Token to
Feature activation+0.000
apologize
Token apologize
Feature activation+0.000
for
Token for
Feature activation+0.000
'
Token'
Feature activation+1.652
Steve
Token Steve
Feature activation+0.000
King
Token King
Feature activation+0.000
spins
Token spins
Feature activation+0.000
GOP
Token GOP
Feature activation+0.000
punishment
Token punishment
Feature activation+0.000

INTERVAL 1.365 - 1.593
CONTAINS 0.003%

,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
do
Token do
Feature activation+0.000
it
Token it
Feature activation+0.000
all
Token all
Feature activation+0.078
the
Token the
Feature activation+1.434
time
Token time
Feature activation+0.000
you
Token you
Feature activation+0.061
bitch
Token bitch
Feature activation+0.000
!
Token!
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.065
length
Token length
Feature activation+0.197
if
Token if
Feature activation+0.000
necessary
Token necessary
Feature activation+0.417
,
Token,
Feature activation+1.504
if
Token if
Feature activation+0.013
you
Token you
Feature activation+0.401
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.122
heavy
Token heavy
Feature activation+0.000
weights
Tokenweights
Feature activation+0.000
making
Token making
Feature activation+0.000
contributions
Token contributions
Feature activation+0.000
just
Token just
Feature activation+0.590
ÂŃ
Token ÂŃ
Feature activation+1.545
before
Tokenbefore
Feature activation+0.208
or
Token or
Feature activation+0.000
after
Token after
Feature activation+0.000
their
Token their
Feature activation+0.000
appearances
Token appearances
Feature activation+0.000
do
Token do
Feature activation+0.000
these
Token these
Feature activation+0.000
things
Token things
Feature activation+0.000
a
Token a
Feature activation+0.974
little
Token little
Feature activation+1.560
more
Token more
Feature activation+1.568
often
Token often
Feature activation+0.646
?
Token?
Feature activation+0.000
Maybe
Token Maybe
Feature activation+0.000
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
his
Token his
Feature activation+0.000
age
Token age
Feature activation+0.000
try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000
recover
Token recover
Feature activation+0.000
the
Token the
Feature activation+1.445
fitness
Token fitness
Feature activation+0.784
and
Token and
Feature activation+0.771
form
Token form
Feature activation+0.452
that
Token that
Feature activation+0.867
would
Token would
Feature activation+0.000

INTERVAL 1.138 - 1.365
CONTAINS 0.007%

unanimously
Token unanimously
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.283
and
Token and
Feature activation+0.000
passed
Token passed
Feature activation+0.000
the
Token the
Feature activation+1.170
House
Token House
Feature activation+0.378
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
vote
Token vote
Feature activation+0.000
of
Token of
Feature activation+0.000
tightly
Token tightly
Feature activation+0.487
and
Token and
Feature activation+0.000
release
Token release
Feature activation+0.000
it
Token it
Feature activation+0.000
more
Token more
Feature activation+1.600
slowly
Token slowly
Feature activation+1.287
[
Token [
Feature activation+0.000
_
Token_
Feature activation+0.000
2
Token2
Feature activation+0.000
_
Token_
Feature activation+0.000
]
Token]
Feature activation+0.166
she
Token she
Feature activation+0.000
-
Token-
Feature activation+0.000
oak
Tokenoak
Feature activation+0.000
is
Token is
Feature activation+0.000
found
Token found
Feature activation+0.000
only
Token only
Feature activation+1.205
within
Token within
Feature activation+0.000
metropolitan
Token metropolitan
Feature activation+0.000
Sydney
Token Sydney
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
others
Token others
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
more
Token more
Feature activation+0.754
broadly
Token broadly
Feature activation+1.175
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Assange
Token Assange
Feature activation+0.000
said
Token said
Feature activation+0.000
Michigan
Token Michigan
Feature activation+0.000
who
Token who
Feature activation+0.000
risked
Token risked
Feature activation+0.000
his
Token his
Feature activation+0.000
life
Token life
Feature activation+0.000
multiple
Token multiple
Feature activation+1.198
times
Token times
Feature activation+0.798
to
Token to
Feature activation+0.000
rescue
Token rescue
Feature activation+0.000
Vietnam
Token Vietnam
Feature activation+0.000
War
Token War
Feature activation+0.000

INTERVAL 0.910 - 1.138
CONTAINS 0.018%

out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.114
memory
Token memory
Feature activation+0.000
more
Token more
Feature activation+0.308
or
Token or
Feature activation+0.000
less
Token less
Feature activation+0.953
in
Token in
Feature activation+0.451
the
Token the
Feature activation+0.380
same
Token same
Feature activation+0.089
wall
Token wall
Feature activation+0.000
-
Token-
Feature activation+0.004
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.911
P
Token P
Feature activation+0.000
ab
Tokenab
Feature activation+0.000
st
Tokenst
Feature activation+0.000
,
Token,
Feature activation+0.000
Schl
Token Schl
Feature activation+0.000
which
Token which
Feature activation+0.000
I
Token I
Feature activation+0.000
still
Token still
Feature activation+0.000
pack
Token pack
Feature activation+0.000
1
Token 1
Feature activation+1.221
of
Token of
Feature activation+0.953
,
Token,
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
job
Token job
Feature activation+0.000
soon
Token soon
Feature activation+0.000
!
Token!
Feature activation+0.000
Keep
Token Keep
Feature activation+0.000
on
Token on
Feature activation+0.000
digging
Token digging
Feature activation+0.000
my
Token my
Feature activation+1.109
Foss
Token Foss
Feature activation+0.000
il
Tokenil
Feature activation+0.105
Fun
Token Fun
Feature activation+0.000
atics
Tokenatics
Feature activation+0.000
,
Token,
Feature activation+0.000
s
Tokens
Feature activation+0.000
made
Token made
Feature activation+0.000
excellent
Token excellent
Feature activation+0.000
progress
Token progress
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.334
night
Token night
Feature activation+0.945
and
Token and
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.072
morning
Token morning
Feature activation+0.916
,
Token,
Feature activation+0.000
setting
Token setting
Feature activation+0.000

INTERVAL 0.683 - 0.910
CONTAINS 0.048%

and
Token and
Feature activation+0.000
established
Token established
Feature activation+0.000
Samsung
Token Samsung
Feature activation+0.000
Construction
Token Construction
Feature activation+0.000
,
Token,
Feature activation+0.000
Samsung
Token Samsung
Feature activation+0.733
Fine
Token Fine
Feature activation+0.000
Chem
Token Chem
Feature activation+0.000
icals
Tokenicals
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
down
Token down
Feature activation+0.000
from
Token from
Feature activation+0.000
15
Token 15
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
police
Token police
Feature activation+0.741
officers
Token officers
Feature activation+0.000
per
Token per
Feature activation+0.000
10
Token 10
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
the
Token the
Feature activation+0.764
same
Token same
Feature activation+0.474
day
Token day
Feature activation+0.000
the
Token the
Feature activation+0.000
report
Token report
Feature activation+0.000
was
Token was
Feature activation+0.000
will
Token will
Feature activation+0.000
also
Token also
Feature activation+0.000
know
Token know
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
far
Token far
Feature activation+0.776
from
Token from
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
-
Token-
Feature activation+0.000
's
Token's
Feature activation+0.000
characterization
Token characterization
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
apologized
Token apologized
Feature activation+0.000
the
Token the
Feature activation+0.708
next
Token next
Feature activation+0.039
day
Token day
Feature activation+0.000
but
Token but
Feature activation+0.000
lost
Token lost
Feature activation+0.000
her
Token her
Feature activation+0.000

INTERVAL 0.455 - 0.683
CONTAINS 0.113%

into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
force
Token force
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.085
today
Token today
Feature activation+0.615
after
Token after
Feature activation+0.000
American
Token American
Feature activation+0.000
troops
Token troops
Feature activation+0.000
left
Token left
Feature activation+0.000
--
Token --
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Most
TokenMost
Feature activation+0.000
fatalities
Token fatalities
Feature activation+0.000
reportedly
Token reportedly
Feature activation+0.098
occur
Token occur
Feature activation+0.000
just
Token just
Feature activation+0.619
before
Token before
Feature activation+0.000
dawn
Token dawn
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
which
Token which
Feature activation+0.000
first
Tokenfirst
Feature activation+0.000
player
Token player
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
used
Token used
Feature activation+0.000
almost
Token almost
Feature activation+0.528
exclusively
Token exclusively
Feature activation+0.822
in
Token in
Feature activation+0.000
ninth
Token ninth
Feature activation+0.000
-
Token-
Feature activation+0.000
inning
Tokeninning
Feature activation+0.000
at
Tokenat
Feature activation+0.000
least
Token least
Feature activation+0.000
they
Token they
Feature activation+0.000
haven
Token haven
Feature activation+0.000
't
Token't
Feature activation+0.254
--
Token--
Feature activation+0.482
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
unlikely
Token unlikely
Feature activation+0.000
to
Token to
Feature activation+0.000
view
Token view
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
changed
Token changed
Feature activation+0.000
it
Token it
Feature activation+0.000
so
Token so
Feature activation+0.519
as
Token as
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
offend
Token offend
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.228 - 0.455
CONTAINS 0.289%

-
Token-
Feature activation+0.037
wide
Tokenwide
Feature activation+0.712
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
this
Token this
Feature activation+0.164
year
Token year
Feature activation+0.289
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
the
Token the
Feature activation+0.000
this
Token this
Feature activation+0.000
list
Token list
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
places
Token places
Feature activation+0.388
to
Token to
Feature activation+0.211
find
Token find
Feature activation+0.000
work
Token work
Feature activation+0.000
in
Token in
Feature activation+0.021
Canada
Token Canada
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
lay
Token lay
Feature activation+0.000
awake
Token awake
Feature activation+0.000
at
Token at
Feature activation+0.288
night
Token night
Feature activation+0.246
creating
Token creating
Feature activation+0.000
mental
Token mental
Feature activation+0.000
imagery
Token imagery
Feature activation+0.000
of
Token of
Feature activation+0.000
how
Token how
Feature activation+0.000
defense
Token defense
Feature activation+0.000
got
Token got
Feature activation+0.000
the
Token the
Feature activation+0.000
ball
Token ball
Feature activation+0.000
right
Token right
Feature activation+0.273
back
Token back
Feature activation+0.320
in
Token in
Feature activation+0.349
each
Token each
Feature activation+0.000
game
Token game
Feature activation+0.000
.
Token.
Feature activation+0.000
R
Token R
Feature activation+0.000
practice
Token practice
Feature activation+0.000
has
Token has
Feature activation+0.388
been
Token been
Feature activation+0.194
dubbed
Token dubbed
Feature activation+0.884
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.337
anch
Tokenanch
Feature activation+0.000
or
Tokenor
Feature activation+0.000
babies
Token babies
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000

INTERVAL 0.000 - 0.228
CONTAINS 99.520%

charity
Token charity
Feature activation+0.000
Shelter
Token Shelter
Feature activation+0.541
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
hopes
Token hopes
Feature activation+0.000
of
Token of
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
of
Token of
Feature activation+0.000
festive
Token festive
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Five
TokenFive
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
of
Token of
Feature activation+0.000
fame
Token fame
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
borough
Token borough
Feature activation+0.000
at
Token at
Feature activation+0.000
£
Token £
Feature activation+0.000
371
Token371
Feature activation+0.000
,
Token,
Feature activation+0.000
139
Token139
Feature activation+0.000
,
Token,
Feature activation+0.000
up
Token up
Feature activation+0.000
by
Token by
Feature activation+0.000
£
Token £
Feature activation+0.000
that
Token that
Feature activation+0.000
presents
Token presents
Feature activation+0.000
for
Token for
Feature activation+0.000
filmmakers
Token filmmakers
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
the
Token the
Feature activation+0.000
recent
Token recent
Feature activation+0.000
Virtual
Token Virtual
Feature activation+0.000
Reality
Token Reality
Feature activation+0.000
Film
Token Film
Feature activation+0.000
neighborhood
Token neighborhood
Feature activation+0.000
on
Token on
Feature activation+0.000
suspicion
Token suspicion
Feature activation+0.000
of
Token of
Feature activation+0.000
resisting
Token resisting
Feature activation+0.000
arrest
Token arrest
Feature activation+0.000
and
Token and
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
violations
Token violations
Feature activation+0.000
charges
Token charges
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

Top feature 3 in H8.7: (feature 12113)

TOP ACTIVATIONS
MAX = 3.512

.
Token.
Feature activation+0.000
Each
Token Each
Feature activation+0.000
of
Token of
Feature activation+0.000
Met
Token Met
Feature activation+0.614
el
Tokenel
Feature activation+0.999
ka
Tokenka
Feature activation+3.512
âĢ
TokenâĢ
Feature activation+0.153
Ļ
TokenĻ
Feature activation+2.676
s
Tokens
Feature activation+2.962
legs
Token legs
Feature activation+0.000
arrives
Token arrives
Feature activation+0.000
health
Token health
Feature activation+0.000
systems
Token systems
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
Africa
Token Africa
Feature activation+3.489
's
Token's
Feature activation+0.110
poorest
Token poorest
Feature activation+0.603
countries
Token countries
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
something
Token something
Feature activation+0.000
else
Token else
Feature activation+0.000
:
Token:
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
Manafort
Token Manafort
Feature activation+3.317
âĢ
TokenâĢ
Feature activation+0.214
Ļ
TokenĻ
Feature activation+1.123
s
Tokens
Feature activation+2.354
associates
Token associates
Feature activation+0.000
in
Token in
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+3.296
's
Token's
Feature activation+0.000
most
Token most
Feature activation+0.000
successful
Token successful
Feature activation+0.000
-
Token -
Feature activation+0.000
and
Token and
Feature activation+0.000
sure
Token sure
Feature activation+0.000
each
Token each
Feature activation+0.000
of
Token of
Feature activation+0.000
Met
Token Met
Feature activation+0.000
Life
TokenLife
Feature activation+0.697
Stadium
Token Stadium
Feature activation+3.283
âĢ
TokenâĢ
Feature activation+0.627
Ļ
TokenĻ
Feature activation+2.696
s
Tokens
Feature activation+2.052
1
Token 1
Feature activation+1.005
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.514
study
Token study
Feature activation+3.175
's
Token's
Feature activation+1.091
co
Token co
Feature activation+0.131
-
Token-
Feature activation+0.380
authors
Tokenauthors
Feature activation+0.000
,
Token,
Feature activation+0.000
followed
Token followed
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
Liga
Token Liga
Feature activation+0.064
MX
Token MX
Feature activation+3.066
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.440
s
Tokens
Feature activation+1.641
usual
Token usual
Feature activation+0.000
suspects
Token suspects
Feature activation+0.000
oath
Token oath
Feature activation+0.000
,
Token,
Feature activation+0.000
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
Wil
Token Wil
Feature activation+0.001
ley
Tokenley
Feature activation+3.030
's
Token's
Feature activation+0.000
closest
Token closest
Feature activation+0.404
friends
Token friends
Feature activation+0.000
directly
Token directly
Feature activation+0.000
contradicted
Token contradicted
Feature activation+0.000
on
Token on
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
Snyder
Token Snyder
Feature activation+1.112
âĢ
TokenâĢ
Feature activation+0.839
Ļ
TokenĻ
Feature activation+3.007
s
Tokens
Feature activation+2.354
own
Token own
Feature activation+1.315
drawings
Token drawings
Feature activation+0.000
.
Token.
Feature activation+0.000
Or
Token Or
Feature activation+0.000
.
Token.
Feature activation+0.000
Furthermore
Token Furthermore
Feature activation+0.000
,
Token,
Feature activation+0.000
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
Amazon
Token Amazon
Feature activation+2.968
's
Token's
Feature activation+0.477
e
Token e
Feature activation+0.000
-
Token-
Feature activation+0.000
books
Tokenbooks
Feature activation+0.000
are
Token are
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
Australia
Token Australia
Feature activation+2.714
âĢ
TokenâĢ
Feature activation+0.172
Ļ
TokenĻ
Feature activation+1.365
s
Tokens
Feature activation+2.965
most
Token most
Feature activation+0.000
multicultural
Token multicultural
Feature activation+0.000
elector
Token elector
Feature activation+0.000
ates
Tokenates
Feature activation+0.000
,
Token,
Feature activation+0.000
Met
Token Met
Feature activation+0.614
el
Tokenel
Feature activation+0.999
ka
Tokenka
Feature activation+3.512
âĢ
TokenâĢ
Feature activation+0.153
Ļ
TokenĻ
Feature activation+2.676
s
Tokens
Feature activation+2.962
legs
Token legs
Feature activation+0.000
arrives
Token arrives
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
particular
Token particular
Feature activation+0.000
to
Token to
Feature activation+0.000
reassure
Token reassure
Feature activation+0.000
every
Token every
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+2.944
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
will
Token will
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
short
Token short
Feature activation+0.000
saga
Token saga
Feature activation+0.000
than
Token than
Feature activation+0.000
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
Daredevil
Token Daredevil
Feature activation+2.899
or
Token or
Feature activation+0.000
Pun
Token Pun
Feature activation+0.000
isher
Tokenisher
Feature activation+1.749
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.131
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+0.712
Solutions
Token Solutions
Feature activation+2.892
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.606
armored
Token armored
Feature activation+0.000
vans
Token vans
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
8
Token 8
Feature activation+0.291
i
Tokeni
Feature activation+1.713
âĢ
TokenâĢ
Feature activation+0.602
Ļ
TokenĻ
Feature activation+2.116
s
Tokens
Feature activation+2.876
first
Token first
Feature activation+1.175
partners
Token partners
Feature activation+0.000
thought
Token thought
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
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+0.366
oc
Tokenoc
Feature activation+0.964
at
Tokenat
Feature activation+2.784
âĢ
TokenâĢ
Feature activation+0.464
Ļ
TokenĻ
Feature activation+2.597
s
Tokens
Feature activation+0.429
co
Token co
Feature activation+0.582
-
Token-
Feature activation+0.065
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
Michele
Token Michele
Feature activation+0.000
Alb
Token Alb
Feature activation+0.000
ore
Tokenore
Feature activation+0.000
to
Tokento
Feature activation+2.721
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.755
s
Tokens
Feature activation+2.506
F
Token F
Feature activation+0.000
1
Token1
Feature activation+0.000
conveniently
Token conveniently
Feature activation+0.000
ignored
Token ignored
Feature activation+0.000
that
Token that
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
Australia
Token Australia
Feature activation+2.714
âĢ
TokenâĢ
Feature activation+0.172
Ļ
TokenĻ
Feature activation+1.365
s
Tokens
Feature activation+2.965
most
Token most
Feature activation+0.000
multicultural
Token multicultural
Feature activation+0.000
of
Token of
Feature activation+0.000
Met
Token Met
Feature activation+0.000
Life
TokenLife
Feature activation+0.697
Stadium
Token Stadium
Feature activation+3.283
âĢ
TokenâĢ
Feature activation+0.627
Ļ
TokenĻ
Feature activation+2.696
s
Tokens
Feature activation+2.052
1
Token 1
Feature activation+1.005
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
billion
Token billion
Feature activation+0.000

Top DFA by src position
MAX = 3.988

goals
Token goals
Feature activation+0.015
Top resid features:
in
Token in
Feature activation-0.011
Top resid features:
mind
Token mind
Feature activation-0.014
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
Each
Token Each
Feature activation+0.046
Top resid features:
of
Token of
Feature activation+3.988
Top resid features:
Met
Token Met
Feature activation+0.014
Top resid features:
el
Tokenel
Feature activation+0.010
Top resid features:
ka
Tokenka
Feature activation+0.073
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
health
Token health
Feature activation-0.008
Top resid features:
systems
Token systems
Feature activation-0.011
Top resid features:
of
Token of
Feature activation+0.021
Top resid features:
some
Token some
Feature activation+0.082
Top resid features:
of
Token of
Feature activation+3.753
Top resid features:
Africa
Token Africa
Feature activation+0.146
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
poorest
Token poorest
Feature activation+0.000
Top resid features:
countries
Token countries
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.013
Top resid features:
something
Token something
Feature activation+0.002
Top resid features:
else
Token else
Feature activation-0.012
Top resid features:
:
Token:
Feature activation+0.019
Top resid features:
some
Token some
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+3.814
Top resid features:
Manafort
Token Manafort
Feature activation+0.147
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:
associates
Token associates
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
help
Token help
Feature activation+0.016
Top resid features:
of
Token of
Feature activation+0.038
Top resid features:
some
Token some
Feature activation+0.072
Top resid features:
of
Token of
Feature activation+3.586
Top resid features:
Washington
Token Washington
Feature activation+0.109
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:
crew
Token crew
Feature activation+0.001
Top resid features:
must
Token must
Feature activation+0.018
Top resid features:
make
Token make
Feature activation-0.005
Top resid features:
sure
Token sure
Feature activation+0.008
Top resid features:
each
Token each
Feature activation+0.064
Top resid features:
of
Token of
Feature activation+3.524
Top resid features:
Met
Token Met
Feature activation+0.006
Top resid features:
Life
TokenLife
Feature activation-0.041
Top resid features:
Stadium
Token Stadium
Feature activation+0.121
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
several
Token several
Feature activation+0.001
Top resid features:
weeks
Token weeks
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
said
Token said
Feature activation-0.088
Top resid features:
two
Token two
Feature activation+0.094
Top resid features:
of
Token of
Feature activation+3.120
Top resid features:
the
Token the
Feature activation+0.605
Top resid features:
study
Token study
Feature activation-0.019
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
co
Token co
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
list
Token list
Feature activation-0.071
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
followed
Token followed
Feature activation-0.020
Top resid features:
by
Token by
Feature activation+0.007
Top resid features:
some
Token some
Feature activation+0.059
Top resid features:
of
Token of
Feature activation+3.566
Top resid features:
Liga
Token Liga
Feature activation+0.052
Top resid features:
MX
Token MX
Feature activation+0.070
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:
.
Token.
Feature activation+0.003
Top resid features:
Under
Token Under
Feature activation-0.009
Top resid features:
oath
Token oath
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
two
Token two
Feature activation+0.033
Top resid features:
of
Token of
Feature activation+3.553
Top resid features:
Wil
Token Wil
Feature activation+0.057
Top resid features:
ley
Tokenley
Feature activation+0.021
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
closest
Token closest
Feature activation+0.000
Top resid features:
friends
Token friends
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.522
Top resid features:
on
Token on
Feature activation-0.050
Top resid features:
some
Token some
Feature activation-0.039
Top resid features:
of
Token of
Feature activation+3.187
Top resid features:
Snyder
Token Snyder
Feature activation+0.036
Top resid features:
âĢ
TokenâĢ
Feature activation+0.206
Top resid features:
Ļ
TokenĻ
Feature activation+0.114
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
own
Token own
Feature activation+0.000
Top resid features:
competition
Token competition
Feature activation-0.014
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Furthermore
Token Furthermore
Feature activation-0.022
Top resid features:
,
Token,
Feature activation-0.041
Top resid features:
many
Token many
Feature activation-0.035
Top resid features:
of
Token of
Feature activation+3.514
Top resid features:
Amazon
Token Amazon
Feature activation+0.070
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
e
Token e
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
books
Tokenbooks
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.029
Top resid features:
conveniently
Token conveniently
Feature activation-0.016
Top resid features:
ignored
Token ignored
Feature activation-0.021
Top resid features:
that
Token that
Feature activation+0.005
Top resid features:
some
Token some
Feature activation-0.003
Top resid features:
of
Token of
Feature activation+3.509
Top resid features:
Australia
Token Australia
Feature activation+0.286
Top resid features:
âĢ
TokenâĢ
Feature activation+0.071
Top resid features:
Ļ
TokenĻ
Feature activation+0.016
Top resid features:
s
Tokens
Feature activation+0.017
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
goals
Token goals
Feature activation-0.007
Top resid features:
in
Token in
Feature activation-0.014
Top resid features:
mind
Token mind
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.022
Top resid features:
Each
Token Each
Feature activation-0.116
Top resid features:
of
Token of
Feature activation+3.489
Top resid features:
Met
Token Met
Feature activation+0.025
Top resid features:
el
Tokenel
Feature activation+0.011
Top resid features:
ka
Tokenka
Feature activation+0.111
Top resid features:
âĢ
TokenâĢ
Feature activation+0.084
Top resid features:
Ļ
TokenĻ
Feature activation+0.052
Top resid features:
want
Token want
Feature activation-0.041
Top resid features:
to
Token to
Feature activation-0.038
Top resid features:
reassure
Token reassure
Feature activation-0.096
Top resid features:
every
Token every
Feature activation+0.008
Top resid features:
one
Token one
Feature activation+0.103
Top resid features:
of
Token of
Feature activation+3.713
Top resid features:
that
Token that
Feature activation+0.058
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
We
Token We
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
continue
Token continue
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.018
Top resid features:
short
Token short
Feature activation-0.004
Top resid features:
saga
Token saga
Feature activation+0.007
Top resid features:
than
Token than
Feature activation-0.015
Top resid features:
many
Token many
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+3.165
Top resid features:
Daredevil
Token Daredevil
Feature activation+0.251
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
Pun
Token Pun
Feature activation+0.000
Top resid features:
isher
Tokenisher
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
d
Tokend
Feature activation-0.007
Top resid features:
have
Token have
Feature activation+0.023
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
steal
Token steal
Feature activation-0.085
Top resid features:
one
Token one
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+3.408
Top resid features:
ATM
Token ATM
Feature activation-0.018
Top resid features:
Solutions
Token Solutions
Feature activation+0.068
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
armored
Token armored
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation-0.009
Top resid features:
apparently
Token apparently
Feature activation-0.028
Top resid features:
also
Token also
Feature activation-0.031
Top resid features:
what
Token what
Feature activation-0.260
Top resid features:
some
Token some
Feature activation+0.052
Top resid features:
of
Token of
Feature activation+3.289
Top resid features:
8
Token 8
Feature activation+0.007
Top resid features:
i
Tokeni
Feature activation+0.117
Top resid features:
âĢ
TokenâĢ
Feature activation+0.106
Top resid features:
Ļ
TokenĻ
Feature activation+0.057
Top resid features:
s
Tokens
Feature activation+0.103
Top resid features:
for
Token for
Feature activation-0.010
Top resid features:
one
Token one
Feature activation-0.002
Top resid features:
thing
Token thing
Feature activation-0.031
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
One
Token One
Feature activation-0.073
Top resid features:
of
Token of
Feature activation+3.680
Top resid features:
Ott
Token Ott
Feature activation-0.016
Top resid features:
oc
Tokenoc
Feature activation-0.010
Top resid features:
at
Tokenat
Feature activation+0.027
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
any
Token any
Feature activation-0.019
Top resid features:
Ferr
Token Ferr
Feature activation+0.037
Top resid features:
aris
Tokenaris
Feature activation+0.037
Top resid features:
but
Token but
Feature activation+0.033
Top resid features:
two
Token two
Feature activation+0.138
Top resid features:
of
Token of
Feature activation+3.316
Top resid features:
Michele
Token Michele
Feature activation-0.028
Top resid features:
Alb
Token Alb
Feature activation+0.020
Top resid features:
ore
Tokenore
Feature activation+0.001
Top resid features:
to
Tokento
Feature activation-0.012
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.021
Top resid features:
conveniently
Token conveniently
Feature activation-0.010
Top resid features:
ignored
Token ignored
Feature activation-0.014
Top resid features:
that
Token that
Feature activation-0.032
Top resid features:
some
Token some
Feature activation-0.058
Top resid features:
of
Token of
Feature activation+3.270
Top resid features:
Australia
Token Australia
Feature activation+0.191
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:
most
Token most
Feature activation+0.000
Top resid features:
crew
Token crew
Feature activation+0.003
Top resid features:
must
Token must
Feature activation+0.004
Top resid features:
make
Token make
Feature activation+0.001
Top resid features:
sure
Token sure
Feature activation+0.004
Top resid features:
each
Token each
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+2.789
Top resid features:
Met
Token Met
Feature activation+0.012
Top resid features:
Life
TokenLife
Feature activation-0.006
Top resid features:
Stadium
Token Stadium
Feature activation+0.126
Top resid features:
âĢ
TokenâĢ
Feature activation+0.048
Top resid features:
Ļ
TokenĻ
Feature activation+0.032
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.01

Head 2: 0.05

Head 3: 0.04

Head 4: 0.09

Head 5: 0.05

Head 6: 0.02

Head 7: 0.53

Head 8: 0.05

Head 9: 0.04

Head 10: 0.06

Head 11: 0.03

Positive logits

´1.93

redients1.92

aliases1.84

units1.84

's1.82

1.78

ten1.74

peers1.73

natureconservancy1.73

properties1.73

vals1.69

tenets1.69

finalists1.68

additions1.67

ingred1.67

iterations1.66

talents1.66

pects1.65

found1.65

redund1.65

Negative logits

rift-1.79

plunge-1.64

jumper-1.61

selfie-1.54

cause-1.53

imeter-1.53

indication-1.51

purse-1.51

outing-1.51

cradle-1.51

Coffin-1.50

pointer-1.48

tracker-1.47

urance-1.46

amen-1.46

fitting-1.45

ocard-1.45

impression-1.45

umption-1.45

Flag-1.44

INTERVAL 3.161 - 3.512
CONTAINS 0.001%

health
Token health
Feature activation+0.000
systems
Token systems
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
Africa
Token Africa
Feature activation+3.489
's
Token's
Feature activation+0.110
poorest
Token poorest
Feature activation+0.603
countries
Token countries
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
Each
Token Each
Feature activation+0.000
of
Token of
Feature activation+0.000
Met
Token Met
Feature activation+0.614
el
Tokenel
Feature activation+0.999
ka
Tokenka
Feature activation+3.512
âĢ
TokenâĢ
Feature activation+0.153
Ļ
TokenĻ
Feature activation+2.676
s
Tokens
Feature activation+2.962
legs
Token legs
Feature activation+0.000
arrives
Token arrives
Feature activation+0.000
something
Token something
Feature activation+0.000
else
Token else
Feature activation+0.000
:
Token:
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
Manafort
Token Manafort
Feature activation+3.317
âĢ
TokenâĢ
Feature activation+0.214
Ļ
TokenĻ
Feature activation+1.123
s
Tokens
Feature activation+2.354
associates
Token associates
Feature activation+0.000
in
Token in
Feature activation+0.000
sure
Token sure
Feature activation+0.000
each
Token each
Feature activation+0.000
of
Token of
Feature activation+0.000
Met
Token Met
Feature activation+0.000
Life
TokenLife
Feature activation+0.697
Stadium
Token Stadium
Feature activation+3.283
âĢ
TokenâĢ
Feature activation+0.627
Ļ
TokenĻ
Feature activation+2.696
s
Tokens
Feature activation+2.052
1
Token 1
Feature activation+1.005
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.514
study
Token study
Feature activation+3.175
's
Token's
Feature activation+1.091
co
Token co
Feature activation+0.131
-
Token-
Feature activation+0.380
authors
Tokenauthors
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.810 - 3.161
CONTAINS 0.001%

.
Token.
Feature activation+0.000
Furthermore
Token Furthermore
Feature activation+0.000
,
Token,
Feature activation+0.000
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
Amazon
Token Amazon
Feature activation+2.968
's
Token's
Feature activation+0.477
e
Token e
Feature activation+0.000
-
Token-
Feature activation+0.000
books
Tokenbooks
Feature activation+0.000
are
Token are
Feature activation+0.000
oath
Token oath
Feature activation+0.000
,
Token,
Feature activation+0.000
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
Wil
Token Wil
Feature activation+0.001
ley
Tokenley
Feature activation+3.030
's
Token's
Feature activation+0.000
closest
Token closest
Feature activation+0.404
friends
Token friends
Feature activation+0.000
directly
Token directly
Feature activation+0.000
contradicted
Token contradicted
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+0.712
Solutions
Token Solutions
Feature activation+2.892
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.606
armored
Token armored
Feature activation+0.000
vans
Token vans
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
reassure
Token reassure
Feature activation+0.000
every
Token every
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+2.944
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
will
Token will
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
Met
Token Met
Feature activation+0.614
el
Tokenel
Feature activation+0.999
ka
Tokenka
Feature activation+3.512
âĢ
TokenâĢ
Feature activation+0.153
Ļ
TokenĻ
Feature activation+2.676
s
Tokens
Feature activation+2.962
legs
Token legs
Feature activation+0.000
arrives
Token arrives
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
particular
Token particular
Feature activation+0.000

INTERVAL 2.458 - 2.810
CONTAINS 0.002%

John
Token John
Feature activation+0.000
Hammond
Token Hammond
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Indiana
Token Indiana
Feature activation+2.532
âĢ
TokenâĢ
Feature activation+0.656
Ļ
TokenĻ
Feature activation+2.041
s
Tokens
Feature activation+1.243
two
Token two
Feature activation+0.500
members
Token members
Feature activation+0.000
occupied
Token occupied
Feature activation+0.000
by
Token by
Feature activation+0.000
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+2.484
's
Token's
Feature activation+0.000
power
Token power
Feature activation+0.000
brokers
Token brokers
Feature activation+0.000
.
Token.
Feature activation+0.000
Or
Token Or
Feature activation+0.000
Alb
Token Alb
Feature activation+0.000
ore
Tokenore
Feature activation+0.000
to
Tokento
Feature activation+2.721
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.755
s
Tokens
Feature activation+2.506
F
Token F
Feature activation+0.000
1
Token1
Feature activation+0.000
cars
Token cars
Feature activation+0.000
!
Token!
Feature activation+0.000
And
Token And
Feature activation+0.000
of
Token of
Feature activation+0.000
Met
Token Met
Feature activation+0.614
el
Tokenel
Feature activation+0.999
ka
Tokenka
Feature activation+3.512
âĢ
TokenâĢ
Feature activation+0.153
Ļ
TokenĻ
Feature activation+2.676
s
Tokens
Feature activation+2.962
legs
Token legs
Feature activation+0.000
arrives
Token arrives
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
conveniently
Token conveniently
Feature activation+0.000
ignored
Token ignored
Feature activation+0.000
that
Token that
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
Australia
Token Australia
Feature activation+2.714
âĢ
TokenâĢ
Feature activation+0.172
Ļ
TokenĻ
Feature activation+1.365
s
Tokens
Feature activation+2.965
most
Token most
Feature activation+0.000
multicultural
Token multicultural
Feature activation+0.000

INTERVAL 2.107 - 2.458
CONTAINS 0.002%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
One
TokenOne
Feature activation+0.000
of
Token of
Feature activation+0.000
Mars
Token Mars
Feature activation+0.180
2020
Token 2020
Feature activation+2.355
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.487
s
Tokens
Feature activation+1.013
main
Token main
Feature activation+1.113
is
Token is
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
PHOTOS
TokenPHOTOS
Feature activation+0.000
:
Token:
Feature activation+0.000
35
Token 35
Feature activation+0.000
of
Token of
Feature activation+0.000
2014
Token 2014
Feature activation+2.222
's
Token's
Feature activation+0.000
Most
Token Most
Feature activation+0.000
Ant
Token Ant
Feature activation+0.000
icipated
Tokenicipated
Feature activation+0.000
Movies
Token Movies
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
Manafort
Token Manafort
Feature activation+3.317
âĢ
TokenâĢ
Feature activation+0.214
Ļ
TokenĻ
Feature activation+1.123
s
Tokens
Feature activation+2.354
associates
Token associates
Feature activation+0.000
in
Token in
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
home
Token home
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+0.000
area
Token area
Feature activation+2.234
's
Token's
Feature activation+0.000
wealthiest
Token wealthiest
Feature activation+0.000
auto
Token auto
Feature activation+0.000
bar
Token bar
Feature activation+0.000
ons
Tokenons
Feature activation+0.000
linking
Token linking
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
Adobe
Token Adobe
Feature activation+1.215
âĢ
TokenâĢ
Feature activation+0.850
Ļ
TokenĻ
Feature activation+2.157
s
Tokens
Feature activation+0.748
apps
Token apps
Feature activation+0.000
(
Token (
Feature activation+0.000
third
Tokenthird
Feature activation+0.000
party
Token party
Feature activation+0.000

INTERVAL 1.756 - 2.107
CONTAINS 0.002%

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+1.880
's
Token's
Feature activation+0.000
debris
Token debris
Feature activation+0.000
mountains
Token mountains
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
state
Token state
Feature activation+0.000
will
Token will
Feature activation+0.000
create
Token create
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Obamacare
Token Obamacare
Feature activation+1.815
âĢ
TokenâĢ
Feature activation+0.008
Ļ
TokenĻ
Feature activation+0.967
s
Tokens
Feature activation+0.486
health
Token health
Feature activation+0.000
-
Token-
Feature activation+0.000
Met
Token Met
Feature activation+0.000
Life
TokenLife
Feature activation+0.697
Stadium
Token Stadium
Feature activation+3.283
âĢ
TokenâĢ
Feature activation+0.627
Ļ
TokenĻ
Feature activation+2.696
s
Tokens
Feature activation+2.052
1
Token 1
Feature activation+1.005
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
billion
Token billion
Feature activation+0.000
blades
Token blades
Feature activation+0.000
So
Token So
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
dad
Token dad
Feature activation+1.179
âĢ
TokenâĢ
Feature activation+0.037
Ļ
TokenĻ
Feature activation+1.899
s
Tokens
Feature activation+2.556
hard
Token hard
Feature activation+0.000
earned
Token earned
Feature activation+0.000
coin
Token coin
Feature activation+0.000
goes
Token goes
Feature activation+0.000
of
Token of
Feature activation+0.000
Thrones
Token Thrones
Feature activation+1.817
âĢ
TokenâĢ
Feature activation+0.011
Ļ
TokenĻ
Feature activation+0.555
season
Token season
Feature activation+1.044
5
Token 5
Feature activation+1.868
cast
Token cast
Feature activation+0.525
additions
Token additions
Feature activation+0.431
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
HBO
Token HBO
Feature activation+0.000

INTERVAL 1.405 - 1.756
CONTAINS 0.003%

facing
Token facing
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
modern
Token modern
Feature activation+0.994
courts
Token courts
Feature activation+0.115
hip
Tokenhip
Feature activation+1.591
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.308
classic
Token classic
Feature activation+1.441
gamb
Token gamb
Feature activation+0.000
of
Token of
Feature activation+0.000
several
Token several
Feature activation+0.000
of
Token of
Feature activation+0.000
James
Token James
Feature activation+0.330
Lin
Token Lin
Feature activation+0.781
ze
Tokenze
Feature activation+1.502
y
Tokeny
Feature activation+2.651
's
Token's
Feature activation+0.521
2005
Token 2005
Feature activation+0.885
radio
Token radio
Feature activation+0.000
appearances
Token appearances
Feature activation+0.000
of
Token of
Feature activation+0.000
Liga
Token Liga
Feature activation+0.064
MX
Token MX
Feature activation+3.066
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.440
s
Tokens
Feature activation+1.641
usual
Token usual
Feature activation+0.000
suspects
Token suspects
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
humane
Tokenhumane
Feature activation+0.000
as
Token as
Feature activation+0.000
any
Token any
Feature activation+0.000
of
Token of
Feature activation+0.000
history
Token history
Feature activation+1.549
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.264
human
Token human
Feature activation+0.000
monsters
Token monsters
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
GOP
Token GOP
Feature activation+2.046
âĢ
TokenâĢ
Feature activation+0.228
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.453
past
Token past
Feature activation+0.038
,
Token,
Feature activation+0.000
current
Token current
Feature activation+0.000
and
Token and
Feature activation+0.000
future
Token future
Feature activation+0.000

INTERVAL 1.054 - 1.405
CONTAINS 0.004%

run
Token run
Feature activation+0.000
:
Token:
Feature activation+0.000
each
Token each
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
youngster
Token youngster
Feature activation+1.076
's
Token's
Feature activation+0.000
seven
Token seven
Feature activation+0.000
assists
Token assists
Feature activation+0.000
in
Token in
Feature activation+0.000
all
Token all
Feature activation+0.000
.
Token.
Feature activation+0.000
Indeed
Token Indeed
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Obama
Token Obama
Feature activation+1.233
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.264
s
Tokens
Feature activation+0.000
first
Token first
Feature activation+0.473
acts
Token acts
Feature activation+0.000
modern
Token modern
Feature activation+0.994
courts
Token courts
Feature activation+0.115
hip
Tokenhip
Feature activation+1.591
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.308
classic
Token classic
Feature activation+1.441
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
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+1.691
âĢ
TokenâĢ
Feature activation+0.263
Ļ
TokenĻ
Feature activation+1.205
s
Tokens
Feature activation+0.134
major
Token major
Feature activation+0.000
clubs
Token clubs
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
conced
Token conced
Feature activation+0.000
ing
Tokening
Feature activation+0.000
four
Token four
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+1.106
five
Token five
Feature activation+0.000
penalties
Token penalties
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.702 - 1.054
CONTAINS 0.008%

million
Token million
Feature activation+0.000
from
Token from
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.780
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
data
Token data
Feature activation+0.000
from
Token from
Feature activation+0.000
mind
Token mind
Feature activation+0.000
.
Token.
Feature activation+0.000
Each
Token Each
Feature activation+0.000
of
Token of
Feature activation+0.000
Met
Token Met
Feature activation+0.614
el
Tokenel
Feature activation+0.999
ka
Tokenka
Feature activation+3.512
âĢ
TokenâĢ
Feature activation+0.153
Ļ
TokenĻ
Feature activation+2.676
s
Tokens
Feature activation+2.962
legs
Token legs
Feature activation+0.000
fluctuations
Token fluctuations
Feature activation+0.000
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
much
Token much
Feature activation+0.000
of
Token of
Feature activation+0.000
C
Token C
Feature activation+0.751
MB
TokenMB
Feature activation+0.532
polarization
Token polarization
Feature activation+0.000
is
Token is
Feature activation+0.000
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
Thrones
Token Thrones
Feature activation+1.817
âĢ
TokenâĢ
Feature activation+0.011
Ļ
TokenĻ
Feature activation+0.555
season
Token season
Feature activation+1.044
5
Token 5
Feature activation+1.868
cast
Token cast
Feature activation+0.525
additions
Token additions
Feature activation+0.431
,
Token,
Feature activation+0.000
with
Token with
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+0.799
's
Token's
Feature activation+0.000
most
Token most
Feature activation+0.000
high
Token high
Feature activation+0.000
-
Token-
Feature activation+0.000
profile
Tokenprofile
Feature activation+0.000

INTERVAL 0.351 - 0.702
CONTAINS 0.021%

Thrones
Token Thrones
Feature activation+1.817
âĢ
TokenâĢ
Feature activation+0.011
Ļ
TokenĻ
Feature activation+0.555
season
Token season
Feature activation+1.044
5
Token 5
Feature activation+1.868
cast
Token cast
Feature activation+0.525
additions
Token additions
Feature activation+0.431
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
HBO
Token HBO
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
N
Token N
Feature activation+0.000
evin
Tokenevin
Feature activation+0.000
,
Token,
Feature activation+0.000
Mohammed
Token Mohammed
Feature activation+0.501
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.372
s
Tokens
Feature activation+0.476
defence
Token defence
Feature activation+0.000
attorney
Token attorney
Feature activation+0.000
,
Token,
Feature activation+0.000
told
Token told
Feature activation+0.000
that
Token that
Feature activation+0.000
houses
Token houses
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Grand
Token Grand
Feature activation+0.571
Theft
Token Theft
Feature activation+0.374
Auto
Token Auto
Feature activation+1.451
settings
Token settings
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
and
Token and
Feature activation+0.000
having
Token having
Feature activation+0.000
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.220
top
Token top
Feature activation+0.489
11
Token 11
Feature activation+0.000
picks
Token picks
Feature activation+0.000
in
Token in
Feature activation+0.000
next
Token next
Feature activation+0.000
year
Token year
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.011
Ļ
TokenĻ
Feature activation+0.555
season
Token season
Feature activation+1.044
5
Token 5
Feature activation+1.868
cast
Token cast
Feature activation+0.525
additions
Token additions
Feature activation+0.431
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
HBO
Token HBO
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 0.000 - 0.351
CONTAINS 99.956%

the
Token the
Feature activation+0.000
roster
Token roster
Feature activation+0.000
and
Token and
Feature activation+0.000
lack
Token lack
Feature activation+0.000
of
Token of
Feature activation+0.000
international
Token international
Feature activation+0.000
spots
Token spots
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
around
Token around
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
gov
Tokengov
Feature activation+0.000
Together
TokenTogether
Feature activation+0.000
Feedback
Token Feedback
Feature activation+0.000
Language
Token Language
Feature activation+0.000
:
Token:
Feature activation+0.000
×
Token ×
Feature activation+0.000
¢
Token¢
Feature activation+0.000
×ij
Token×ij
Feature activation+0.000
ר
Tokenר
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
college
Token college
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
been
Token been
Feature activation+0.000
ment
Token ment
Feature activation+0.000
British
Token British
Feature activation+0.000
gentleman
Token gentleman
Feature activation+0.000
living
Token living
Feature activation+0.000
in
Token in
Feature activation+0.000
solitude
Token solitude
Feature activation+0.000
.
Token.
Feature activation+0.000
Despite
Token Despite
Feature activation+0.000
his
Token his
Feature activation+0.000
wealth
Token wealth
Feature activation+0.000
,
Token,
Feature activation+0.000
F
Token F
Feature activation+0.000
,
Token,
Feature activation+0.000
154
Token 154
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
169
Token 169
Feature activation+0.000
were
Token were
Feature activation+0.000
released
Token released
Feature activation+0.000
pursuant
Token pursuant
Feature activation+0.000
to
Token to
Feature activation+0.000
court
Token court
Feature activation+0.000
order
Token order
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 H8.7: (feature 797)

TOP ACTIVATIONS
MAX = 5.276

members
Token members
Feature activation+0.000
of
Token of
Feature activation+1.107
the
Token the
Feature activation+2.666
Queen
Token Queen
Feature activation+1.356
's
Token's
Feature activation+4.096
University
Token University
Feature activation+5.276
B
Token B
Feature activation+0.447
ands
Tokenands
Feature activation+3.695
are
Token are
Feature activation+0.000
being
Token being
Feature activation+0.000
silent
Token silent
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Members
TokenMembers
Feature activation+0.000
of
Token of
Feature activation+0.304
Fury
Token Fury
Feature activation+3.730
's
Token's
Feature activation+5.139
ent
Token ent
Feature activation+2.557
ourage
Tokenourage
Feature activation+0.242
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Members
TokenMembers
Feature activation+0.000
of
Token of
Feature activation+0.467
Sar
Token Sar
Feature activation+1.073
neck
Tokenneck
Feature activation+1.354
i
Tokeni
Feature activation+4.998
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.791
s
Tokens
Feature activation+4.835
family
Token family
Feature activation+3.741
testified
Token testified
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.677
drag
Token drag
Feature activation+3.469
and
Token and
Feature activation+1.254
L
Token L
Feature activation+0.284
GB
TokenGB
Feature activation+4.960
communities
Token communities
Feature activation+0.149
to
Token to
Feature activation+0.000
stop
Token stop
Feature activation+0.000
using
Token using
Feature activation+0.000
words
Token words
Feature activation+0.000
Sar
Token Sar
Feature activation+1.073
neck
Tokenneck
Feature activation+1.354
i
Tokeni
Feature activation+4.998
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.791
s
Tokens
Feature activation+4.835
family
Token family
Feature activation+3.741
testified
Token testified
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
judge
Token judge
Feature activation+0.000
all
Token all
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.000
Euph
Token Euph
Feature activation+2.064
or
Tokenor
Feature activation+3.267
bi
Tokenbi
Feature activation+4.688
aceae
Tokenaceae
Feature activation+3.154
(
Token (
Feature activation+0.000
in
Tokenin
Feature activation+0.000
def
Token def
Feature activation+0.000
erence
Tokenerence
Feature activation+0.000
iliated
Tokeniliated
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.000
T
Token T
Feature activation+1.487
US
TokenUS
Feature activation+2.028
C
TokenC
Feature activation+4.634
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
latter
Token latter
Feature activation+0.000
are
Token are
Feature activation+0.000
an
Token an
Feature activation+0.000
sixth
Token sixth
Feature activation+0.000
member
Token member
Feature activation+0.000
of
Token of
Feature activation+0.195
the
Token the
Feature activation+0.876
3
Token 3
Feature activation+1.036
DS
TokenDS
Feature activation+4.600
family
Token family
Feature activation+1.113
released
Token released
Feature activation+0.000
in
Token in
Feature activation+0.000
as
Token as
Feature activation+0.000
many
Token many
Feature activation+0.000
or
Token or
Feature activation+0.000
other
Token other
Feature activation+0.000
member
Token member
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.063
cat
Token cat
Feature activation+4.489
family
Token family
Feature activation+1.774
known
Token known
Feature activation+0.378
as
Token as
Feature activation+0.278
"
Token "
Feature activation+0.449
App
TokenApp
Feature activation+0.218
of
Token of
Feature activation+0.000
President
Token President
Feature activation+0.000
Obama
Token Obama
Feature activation+3.702
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.052
s
Tokens
Feature activation+4.347
protective
Token protective
Feature activation+1.605
detail
Token detail
Feature activation+0.667
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
restrooms
Token restrooms
Feature activation+0.000
to
Token to
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+2.749
given
Token given
Feature activation+4.310
"
Token "
Feature activation+3.595
bi
Tokenbi
Feature activation+0.883
ological
Tokenological
Feature activation+2.542
sex
Token sex
Feature activation+1.298
,"
Token,"
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.118
the
Token the
Feature activation+1.008
marriage
Token marriage
Feature activation+4.281
party
Token party
Feature activation+1.865
tried
Token tried
Feature activation+0.000
to
Token to
Feature activation+0.000
convince
Token convince
Feature activation+0.000
the
Token the
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.116
state
Token state
Feature activation+2.623
âĢ
TokenâĢ
Feature activation+0.439
Ļ
TokenĻ
Feature activation+1.653
s
Tokens
Feature activation+4.187
Medical
Token Medical
Feature activation+1.387
Marijuana
Token Marijuana
Feature activation+1.368
Program
Token Program
Feature activation+1.556
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
80
Token 80
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+1.107
the
Token the
Feature activation+2.666
Queen
Token Queen
Feature activation+1.356
's
Token's
Feature activation+4.096
University
Token University
Feature activation+5.276
B
Token B
Feature activation+0.447
ands
Tokenands
Feature activation+3.695
are
Token are
Feature activation+0.000
being
Token being
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.328
the
Token the
Feature activation+1.352
Republican
Token Republican
Feature activation+3.798
National
Token National
Feature activation+2.627
Committee
Token Committee
Feature activation+4.027
,
Token,
Feature activation+1.362
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
interview
Token interview
Feature activation+0.000
a
Token a
Feature activation+0.000
as
Token as
Feature activation+0.000
six
Token six
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.984
a
Token a
Feature activation+3.510
terrorist
Token terrorist
Feature activation+3.979
cell
Token cell
Feature activation+1.373
involved
Token involved
Feature activation+0.634
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Paris
Token Paris
Feature activation+0.000
for
Token for
Feature activation+0.000
all
Token all
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.528
the
Token the
Feature activation+1.542
campus
Token campus
Feature activation+3.971
community
Token community
Feature activation+0.572
,
Token,
Feature activation+0.000
University
Token University
Feature activation+0.017
of
Token of
Feature activation+0.000
Illinois
Token Illinois
Feature activation+0.000
Independent
Token Independent
Feature activation+1.755
School
Token School
Feature activation+1.145
District
Token District
Feature activation+2.267
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.640
s
Tokens
Feature activation+3.960
Board
Token Board
Feature activation+1.786
of
Token of
Feature activation+0.000
Trust
Token Trust
Feature activation+0.055
ees
Tokenees
Feature activation+1.818
resigned
Token resigned
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.442
ľ
Tokenľ
Feature activation+3.313
M
TokenM
Feature activation+1.399
ong
Tokenong
Feature activation+0.252
ol
Tokenol
Feature activation+2.288
ian
Tokenian
Feature activation+3.957
âĢ
TokenâĢ
Feature activation+1.630
Ŀ
TokenĿ
Feature activation+3.551
race
Token race
Feature activation+0.857
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
lose
Token lose
Feature activation+0.000
two
Token two
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+1.951
Republican
Token Republican
Feature activation+3.946
caucus
Token caucus
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
no
Token no
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000

Top DFA by src position
MAX = 6.058

that
Token that
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
some
Token some
Feature activation-0.010
Top resid features:
80
Token 80
Feature activation+0.020
Top resid features:
members
Token members
Feature activation+0.369
Top resid features:
of
Token of
Feature activation+4.023
Top resid features:
the
Token the
Feature activation+1.671
Top resid features:
Queen
Token Queen
Feature activation+0.045
Top resid features:
's
Token's
Feature activation+0.016
Top resid features:
University
Token University
Feature activation+0.038
Top resid features:
B
Token B
Feature activation+0.000
Top resid features:
hee
Tokenhee
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Members
TokenMembers
Feature activation+0.314
Top resid features:
of
Token of
Feature activation+5.890
Top resid features:
Fury
Token Fury
Feature activation-0.079
Top resid features:
's
Token's
Feature activation+0.070
Top resid features:
ent
Token ent
Feature activation+0.000
Top resid features:
ourage
Tokenourage
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.502
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Members
TokenMembers
Feature activation+0.213
Top resid features:
of
Token of
Feature activation+5.838
Top resid features:
Sar
Token Sar
Feature activation-0.019
Top resid features:
neck
Tokenneck
Feature activation-0.029
Top resid features:
i
Tokeni
Feature activation-0.096
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
who
Token who
Feature activation-0.018
Top resid features:
continue
Token continue
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
ask
Token ask
Feature activation+0.008
Top resid features:
members
Token members
Feature activation+0.196
Top resid features:
of
Token of
Feature activation+3.483
Top resid features:
the
Token the
Feature activation+2.276
Top resid features:
drag
Token drag
Feature activation-0.036
Top resid features:
and
Token and
Feature activation+0.188
Top resid features:
L
Token L
Feature activation-0.008
Top resid features:
GB
TokenGB
Feature activation-0.099
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.442
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Members
TokenMembers
Feature activation+0.172
Top resid features:
of
Token of
Feature activation+6.058
Top resid features:
Sar
Token Sar
Feature activation-0.018
Top resid features:
neck
Tokenneck
Feature activation-0.058
Top resid features:
i
Tokeni
Feature activation-0.254
Top resid features:
âĢ
TokenâĢ
Feature activation-0.013
Top resid features:
Ļ
TokenĻ
Feature activation-0.018
Top resid features:
collectively
Token collectively
Feature activation+0.004
Top resid features:
refer
Token refer
Feature activation-0.020
Top resid features:
to
Token to
Feature activation-0.008
Top resid features:
all
Token all
Feature activation+0.015
Top resid features:
members
Token members
Feature activation+0.385
Top resid features:
of
Token of
Feature activation+5.199
Top resid features:
Euph
Token Euph
Feature activation-0.016
Top resid features:
or
Tokenor
Feature activation+0.001
Top resid features:
bi
Tokenbi
Feature activation+0.020
Top resid features:
aceae
Tokenaceae
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
representing
Token representing
Feature activation+0.120
Top resid features:
unaff
Token unaff
Feature activation+0.004
Top resid features:
iliated
Tokeniliated
Feature activation+0.022
Top resid features:
members
Token members
Feature activation+0.214
Top resid features:
of
Token of
Feature activation+5.557
Top resid features:
T
Token T
Feature activation+0.008
Top resid features:
US
TokenUS
Feature activation+0.006
Top resid features:
C
TokenC
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
These
Token These
Feature activation+0.000
Top resid features:
this
Token this
Feature activation-0.021
Top resid features:
is
Token is
Feature activation-0.029
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
sixth
Token sixth
Feature activation+0.198
Top resid features:
member
Token member
Feature activation+0.278
Top resid features:
of
Token of
Feature activation+3.544
Top resid features:
the
Token the
Feature activation+1.847
Top resid features:
3
Token 3
Feature activation-0.003
Top resid features:
DS
TokenDS
Feature activation+0.001
Top resid features:
family
Token family
Feature activation+0.000
Top resid features:
released
Token released
Feature activation+0.000
Top resid features:
lyn
Token lyn
Feature activation-0.020
Top resid features:
x
Tokenx
Feature activation-0.021
Top resid features:
or
Token or
Feature activation-0.055
Top resid features:
other
Token other
Feature activation+0.009
Top resid features:
member
Token member
Feature activation+0.140
Top resid features:
of
Token of
Feature activation+3.527
Top resid features:
the
Token the
Feature activation+1.906
Top resid features:
cat
Token cat
Feature activation+0.049
Top resid features:
family
Token family
Feature activation+0.000
Top resid features:
known
Token known
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
including
Token including
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
top
Token top
Feature activation-0.022
Top resid features:
member
Token member
Feature activation+0.036
Top resid features:
of
Token of
Feature activation+5.433
Top resid features:
President
Token President
Feature activation+0.023
Top resid features:
Obama
Token Obama
Feature activation-0.168
Top resid features:
âĢ
TokenâĢ
Feature activation+0.012
Top resid features:
Ļ
TokenĻ
Feature activation-0.016
Top resid features:
s
Tokens
Feature activation+0.110
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
public
Token public
Feature activation+0.005
Top resid features:
restrooms
Token restrooms
Feature activation+0.195
Top resid features:
to
Token to
Feature activation+0.019
Top resid features:
members
Token members
Feature activation+0.362
Top resid features:
of
Token of
Feature activation+4.260
Top resid features:
a
Token a
Feature activation+0.483
Top resid features:
given
Token given
Feature activation+0.010
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
bi
Tokenbi
Feature activation+0.000
Top resid features:
ological
Tokenological
Feature activation+0.000
Top resid features:
ndra
Tokenndra
Feature activation-0.000
Top resid features:
Bind
Token Bind
Feature activation-0.004
Top resid features:
and
Token and
Feature activation+0.041
Top resid features:
other
Token other
Feature activation-0.016
Top resid features:
members
Token members
Feature activation+0.270
Top resid features:
of
Token of
Feature activation+3.524
Top resid features:
the
Token the
Feature activation+1.287
Top resid features:
marriage
Token marriage
Feature activation+0.103
Top resid features:
party
Token party
Feature activation+0.000
Top resid features:
tried
Token tried
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
A
Token A
Feature activation-0.003
Top resid features:
newly
Token newly
Feature activation+0.012
Top resid features:
registered
Token registered
Feature activation-0.014
Top resid features:
member
Token member
Feature activation+0.283
Top resid features:
of
Token of
Feature activation+3.916
Top resid features:
the
Token the
Feature activation+1.036
Top resid features:
state
Token state
Feature activation-0.070
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.065
Top resid features:
that
Token that
Feature activation-0.006
Top resid features:
the
Token the
Feature activation-0.027
Top resid features:
some
Token some
Feature activation-0.033
Top resid features:
80
Token 80
Feature activation+0.002
Top resid features:
members
Token members
Feature activation+0.141
Top resid features:
of
Token of
Feature activation+3.224
Top resid features:
the
Token the
Feature activation+1.708
Top resid features:
Queen
Token Queen
Feature activation+0.073
Top resid features:
's
Token's
Feature activation+0.006
Top resid features:
University
Token University
Feature activation+0.000
Top resid features:
B
Token B
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.076
Top resid features:
Ļ
TokenĻ
Feature activation+0.029
Top resid features:
s
Tokens
Feature activation-0.047
Top resid features:
two
Token two
Feature activation-0.014
Top resid features:
members
Token members
Feature activation+0.458
Top resid features:
of
Token of
Feature activation+3.059
Top resid features:
the
Token the
Feature activation+1.295
Top resid features:
Republican
Token Republican
Feature activation-0.039
Top resid features:
National
Token National
Feature activation-0.013
Top resid features:
Committee
Token Committee
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
As
TokenAs
Feature activation-0.001
Top resid features:
many
Token many
Feature activation-0.002
Top resid features:
as
Token as
Feature activation+0.008
Top resid features:
six
Token six
Feature activation+0.007
Top resid features:
members
Token members
Feature activation+0.201
Top resid features:
of
Token of
Feature activation+3.347
Top resid features:
a
Token a
Feature activation+1.460
Top resid features:
terrorist
Token terrorist
Feature activation-0.077
Top resid features:
cell
Token cell
Feature activation+0.000
Top resid features:
involved
Token involved
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.517
Top resid features:
appreciation
Token appreciation
Feature activation-0.025
Top resid features:
for
Token for
Feature activation-0.030
Top resid features:
all
Token all
Feature activation+0.030
Top resid features:
members
Token members
Feature activation+0.304
Top resid features:
of
Token of
Feature activation+3.045
Top resid features:
the
Token the
Feature activation+1.445
Top resid features:
campus
Token campus
Feature activation+0.080
Top resid features:
community
Token community
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
University
Token University
Feature activation+0.000
Top resid features:
TON
TokenTON
Feature activation-0.002
Top resid features:
IO
TokenIO
Feature activation-0.009
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.035
Top resid features:
A
Token A
Feature activation+0.118
Top resid features:
member
Token member
Feature activation+0.236
Top resid features:
of
Token of
Feature activation+3.595
Top resid features:
the
Token the
Feature activation+1.360
Top resid features:
Nat
Token Nat
Feature activation-0.012
Top resid features:
alia
Tokenalia
Feature activation-0.025
Top resid features:
Independent
Token Independent
Feature activation+0.013
Top resid features:
School
Token School
Feature activation-0.020
Top resid features:
against
Token against
Feature activation-0.014
Top resid features:
all
Token all
Feature activation+0.005
Top resid features:
Asians
Token Asians
Feature activation+0.016
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
members
Token members
Feature activation+0.100
Top resid features:
of
Token of
Feature activation+2.908
Top resid features:
the
Token the
Feature activation+2.078
Top resid features:
âĢ
Token âĢ
Feature activation-0.004
Top resid features:
ľ
Tokenľ
Feature activation-0.007
Top resid features:
M
TokenM
Feature activation+0.008
Top resid features:
ong
Tokenong
Feature activation-0.016
Top resid features:
can
Token can
Feature activation-0.003
Top resid features:
only
Token only
Feature activation-0.013
Top resid features:
lose
Token lose
Feature activation-0.010
Top resid features:
two
Token two
Feature activation-0.009
Top resid features:
members
Token members
Feature activation+0.064
Top resid features:
of
Token of
Feature activation+3.916
Top resid features:
his
Token his
Feature activation+1.139
Top resid features:
Republican
Token Republican
Feature activation+0.068
Top resid features:
caucus
Token caucus
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:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.01

Head 2: 0.03

Head 3: 0.03

Head 4: 0.10

Head 5: 0.07

Head 6: 0.02

Head 7: 0.52

Head 8: 0.04

Head 9: 0.04

Head 10: 0.08

Head 11: 0.03

Positive logits

mble2.32

crew2.23

ariat2.20

group2.14

group2.11

knit2.08

tribe2.03

crew2.02

amily1.98

chorus1.95

delegation1.94

congregation1.94

family1.91

gang1.90

Advisory1.90

umat1.89

consortium1.88

roup1.88

Team1.87

Group1.87

Negative logits

opportunities-2.10

assurances-2.05

discoveries-2.03

installments-2.00

revelations-1.98

contributions-1.94

disclosures-1.89

moments-1.88

appearances-1.88

visits-1.87

setbacks-1.86

gigs-1.86

mistakes-1.85

reminders-1.84

usions-1.84

peanuts-1.84

insults-1.82

experiences-1.80

endorsements-1.80

volumes-1.79

INTERVAL 4.748 - 5.276
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Members
TokenMembers
Feature activation+0.000
of
Token of
Feature activation+0.467
Sar
Token Sar
Feature activation+1.073
neck
Tokenneck
Feature activation+1.354
i
Tokeni
Feature activation+4.998
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.791
s
Tokens
Feature activation+4.835
family
Token family
Feature activation+3.741
testified
Token testified
Feature activation+0.000
Sar
Token Sar
Feature activation+1.073
neck
Tokenneck
Feature activation+1.354
i
Tokeni
Feature activation+4.998
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.791
s
Tokens
Feature activation+4.835
family
Token family
Feature activation+3.741
testified
Token testified
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
judge
Token judge
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.677
drag
Token drag
Feature activation+3.469
and
Token and
Feature activation+1.254
L
Token L
Feature activation+0.284
GB
TokenGB
Feature activation+4.960
communities
Token communities
Feature activation+0.149
to
Token to
Feature activation+0.000
stop
Token stop
Feature activation+0.000
using
Token using
Feature activation+0.000
words
Token words
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Members
TokenMembers
Feature activation+0.000
of
Token of
Feature activation+0.304
Fury
Token Fury
Feature activation+3.730
's
Token's
Feature activation+5.139
ent
Token ent
Feature activation+2.557
ourage
Tokenourage
Feature activation+0.242
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
the
Token the
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+1.107
the
Token the
Feature activation+2.666
Queen
Token Queen
Feature activation+1.356
's
Token's
Feature activation+4.096
University
Token University
Feature activation+5.276
B
Token B
Feature activation+0.447
ands
Tokenands
Feature activation+3.695
are
Token are
Feature activation+0.000
being
Token being
Feature activation+0.000
silent
Token silent
Feature activation+0.000

INTERVAL 4.221 - 4.748
CONTAINS 0.001%

sixth
Token sixth
Feature activation+0.000
member
Token member
Feature activation+0.000
of
Token of
Feature activation+0.195
the
Token the
Feature activation+0.876
3
Token 3
Feature activation+1.036
DS
TokenDS
Feature activation+4.600
family
Token family
Feature activation+1.113
released
Token released
Feature activation+0.000
in
Token in
Feature activation+0.000
as
Token as
Feature activation+0.000
many
Token many
Feature activation+0.000
or
Token or
Feature activation+0.000
other
Token other
Feature activation+0.000
member
Token member
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.063
cat
Token cat
Feature activation+4.489
family
Token family
Feature activation+1.774
known
Token known
Feature activation+0.378
as
Token as
Feature activation+0.278
"
Token "
Feature activation+0.449
App
TokenApp
Feature activation+0.218
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.118
the
Token the
Feature activation+1.008
marriage
Token marriage
Feature activation+4.281
party
Token party
Feature activation+1.865
tried
Token tried
Feature activation+0.000
to
Token to
Feature activation+0.000
convince
Token convince
Feature activation+0.000
the
Token the
Feature activation+0.000
all
Token all
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.000
Euph
Token Euph
Feature activation+2.064
or
Tokenor
Feature activation+3.267
bi
Tokenbi
Feature activation+4.688
aceae
Tokenaceae
Feature activation+3.154
(
Token (
Feature activation+0.000
in
Tokenin
Feature activation+0.000
def
Token def
Feature activation+0.000
erence
Tokenerence
Feature activation+0.000
restrooms
Token restrooms
Feature activation+0.000
to
Token to
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+2.749
given
Token given
Feature activation+4.310
"
Token "
Feature activation+3.595
bi
Tokenbi
Feature activation+0.883
ological
Tokenological
Feature activation+2.542
sex
Token sex
Feature activation+1.298
,"
Token,"
Feature activation+0.000

INTERVAL 3.693 - 4.221
CONTAINS 0.002%

the
Token the
Feature activation+2.666
Queen
Token Queen
Feature activation+1.356
's
Token's
Feature activation+4.096
University
Token University
Feature activation+5.276
B
Token B
Feature activation+0.447
ands
Tokenands
Feature activation+3.695
are
Token are
Feature activation+0.000
being
Token being
Feature activation+0.000
silent
Token silent
Feature activation+0.000
about
Token about
Feature activation+0.000
being
Token being
Feature activation+0.000
s
Tokens
Feature activation+0.000
two
Token two
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.328
the
Token the
Feature activation+1.352
Republican
Token Republican
Feature activation+3.798
National
Token National
Feature activation+2.627
Committee
Token Committee
Feature activation+4.027
,
Token,
Feature activation+1.362
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.328
the
Token the
Feature activation+1.352
Republican
Token Republican
Feature activation+3.798
National
Token National
Feature activation+2.627
Committee
Token Committee
Feature activation+4.027
,
Token,
Feature activation+1.362
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
interview
Token interview
Feature activation+0.000
a
Token a
Feature activation+0.000
of
Token of
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.595
the
Token the
Feature activation+1.199
art
Token art
Feature activation+3.545
commission
Token commission
Feature activation+3.875
and
Token and
Feature activation+0.000
identifies
Token identifies
Feature activation+0.000
them
Token them
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
neck
Tokenneck
Feature activation+1.354
i
Tokeni
Feature activation+4.998
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.791
s
Tokens
Feature activation+4.835
family
Token family
Feature activation+3.741
testified
Token testified
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
judge
Token judge
Feature activation+0.000
read
Token read
Feature activation+0.000

INTERVAL 3.165 - 3.693
CONTAINS 0.002%

an
Token an
Feature activation+0.000
alleged
Token alleged
Feature activation+0.000
member
Token member
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.834
hacker
Token hacker
Feature activation+3.175
group
Token group
Feature activation+0.326
expressed
Token expressed
Feature activation+0.000
his
Token his
Feature activation+0.000
dissent
Token dissent
Feature activation+0.000
on
Token on
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Members
TokenMembers
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+3.507
latest
Token latest
Feature activation+3.925
generation
Token generation
Feature activation+0.669
of
Token of
Feature activation+0.581
veterans
Token veterans
Feature activation+0.995
are
Token are
Feature activation+0.000
and
Token and
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.888
âĢ
Token âĢ
Feature activation+0.442
ľ
Tokenľ
Feature activation+3.313
M
TokenM
Feature activation+1.399
ong
Tokenong
Feature activation+0.252
ol
Tokenol
Feature activation+2.288
ian
Tokenian
Feature activation+3.957
âĢ
TokenâĢ
Feature activation+1.630
many
Token many
Feature activation+0.000
as
Token as
Feature activation+0.000
six
Token six
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.984
a
Token a
Feature activation+3.510
terrorist
Token terrorist
Feature activation+3.979
cell
Token cell
Feature activation+1.373
involved
Token involved
Feature activation+0.634
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
ographies
Tokenographies
Feature activation+0.000
of
Token of
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.595
the
Token the
Feature activation+1.199
art
Token art
Feature activation+3.545
commission
Token commission
Feature activation+3.875
and
Token and
Feature activation+0.000
identifies
Token identifies
Feature activation+0.000
them
Token them
Feature activation+0.000
as
Token as
Feature activation+0.000

INTERVAL 2.638 - 3.165
CONTAINS 0.004%

mom
Token mom
Feature activation+0.000
and
Token and
Feature activation+0.000
member
Token member
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.736
libertarian
Token libertarian
Feature activation+2.768
-
Token-
Feature activation+0.407
minded
Tokenminded
Feature activation+2.505
Project
Token Project
Feature activation+0.531
21
Token 21
Feature activation+1.318
âĢ
TokenâĢ
Feature activation+0.000
induct
Token induct
Feature activation+0.000
ed
Tokened
Feature activation+0.000
as
Token as
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.670
a
Token a
Feature activation+2.802
team
Token team
Feature activation+3.207
,
Token,
Feature activation+0.267
no
Token no
Feature activation+0.000
matter
Token matter
Feature activation+0.000
how
Token how
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Members
TokenMembers
Feature activation+0.000
of
Token of
Feature activation+0.437
the
Token the
Feature activation+2.013
Connecticut
Token Connecticut
Feature activation+2.724
team
Token team
Feature activation+0.938
contacted
Token contacted
Feature activation+0.092
Con
Token Con
Feature activation+0.000
yers
Tokenyers
Feature activation+0.000
when
Token when
Feature activation+0.000
of
Token of
Feature activation+0.008
the
Token the
Feature activation+2.573
Department
Token Department
Feature activation+3.546
of
Token of
Feature activation+0.000
Public
Token Public
Feature activation+0.000
Safety
Token Safety
Feature activation+3.121
(
Token (
Feature activation+0.000
D
TokenD
Feature activation+0.000
PS
TokenPS
Feature activation+1.921
),
Token),
Feature activation+0.000
all
Token all
Feature activation+0.000
losing
Token losing
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.646
original
Token original
Feature activation+3.292
100
Token 100
Feature activation+2.985
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
having
Token having
Feature activation+0.000
to
Token to
Feature activation+0.000
decide
Token decide
Feature activation+0.000

INTERVAL 2.110 - 2.638
CONTAINS 0.005%

and
Token and
Feature activation+0.000
senior
Token senior
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+1.869
national
Token national
Feature activation+2.419
security
Token security
Feature activation+3.143
team
Token team
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
Defense
Token Defense
Feature activation+0.000
A
Token A
Feature activation+0.000
member
Token member
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.001
Nat
Token Nat
Feature activation+0.000
alia
Tokenalia
Feature activation+2.346
Independent
Token Independent
Feature activation+1.755
School
Token School
Feature activation+1.145
District
Token District
Feature activation+2.267
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.640
two
Token two
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.328
the
Token the
Feature activation+1.352
Republican
Token Republican
Feature activation+3.798
National
Token National
Feature activation+2.627
Committee
Token Committee
Feature activation+4.027
,
Token,
Feature activation+1.362
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
interview
Token interview
Feature activation+0.000
are
Token are
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.099
the
Token the
Feature activation+0.874
Harriet
Token Harriet
Feature activation+0.542
Street
Token Street
Feature activation+2.238
gang
Token gang
Feature activation+0.922
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
H
Token H
Feature activation+0.425
-
Token-
Feature activation+0.601
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+0.368
the
Token the
Feature activation+1.787
'
Token '
Feature activation+2.267
Muslim
TokenMuslim
Feature activation+1.376
Patrol
Token Patrol
Feature activation+2.061
'
Token'
Feature activation+2.693
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.583 - 2.110
CONTAINS 0.008%

said
Token said
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+0.368
the
Token the
Feature activation+1.787
'
Token '
Feature activation+2.267
Muslim
TokenMuslim
Feature activation+1.376
Patrol
Token Patrol
Feature activation+2.061
'
Token'
Feature activation+2.693
Ċ
TokenĊ
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.049
the
Token the
Feature activation+0.878
House
Token House
Feature activation+1.598
and
Token and
Feature activation+0.000
Senate
Token Senate
Feature activation+1.673
Armed
Token Armed
Feature activation+0.000
Services
Token Services
Feature activation+0.199
Committees
Token Committees
Feature activation+0.250
.
Token.
Feature activation+0.000
Despite
Token Despite
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Members
TokenMembers
Feature activation+0.000
of
Token of
Feature activation+0.437
the
Token the
Feature activation+2.013
Connecticut
Token Connecticut
Feature activation+2.724
team
Token team
Feature activation+0.938
contacted
Token contacted
Feature activation+0.092
Con
Token Con
Feature activation+0.000
yers
Tokenyers
Feature activation+0.000
School
Token School
Feature activation+1.145
District
Token District
Feature activation+2.267
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.640
s
Tokens
Feature activation+3.960
Board
Token Board
Feature activation+1.786
of
Token of
Feature activation+0.000
Trust
Token Trust
Feature activation+0.055
ees
Tokenees
Feature activation+1.818
resigned
Token resigned
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
ľ
Tokenľ
Feature activation+3.313
M
TokenM
Feature activation+1.399
ong
Tokenong
Feature activation+0.252
ol
Tokenol
Feature activation+2.288
ian
Tokenian
Feature activation+3.957
âĢ
TokenâĢ
Feature activation+1.630
Ŀ
TokenĿ
Feature activation+3.551
race
Token race
Feature activation+0.857
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.055 - 1.583
CONTAINS 0.012%

a
Token a
Feature activation+0.000
member
Token member
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.693
Lisp
Token Lisp
Feature activation+1.492
cult
Token cult
Feature activation+1.129
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
felt
Token felt
Feature activation+0.000
something
Token something
Feature activation+0.000
a
Token a
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.813
Love
Token Love
Feature activation+0.000
My
Token My
Feature activation+0.000
Oz
Token Oz
Feature activation+0.701
arks
Tokenarks
Feature activation+1.192
Facebook
Token Facebook
Feature activation+0.823
group
Token group
Feature activation+0.522
for
Token for
Feature activation+0.000
providing
Token providing
Feature activation+0.000
so
Token so
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
member
Token member
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.885
Federal
Token Federal
Feature activation+1.342
ist
Tokenist
Feature activation+1.579
Society
Token Society
Feature activation+1.928
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
of
Token of
Feature activation+0.268
the
Token the
Feature activation+2.017
mult
Token mult
Feature activation+1.073
idis
Tokenidis
Feature activation+0.883
ciplinary
Tokenciplinary
Feature activation+2.825
clinical
Token clinical
Feature activation+1.381
trial
Token trial
Feature activation+1.819
team
Token team
Feature activation+0.499
were
Token were
Feature activation+0.000
present
Token present
Feature activation+0.000
.
Token.
Feature activation+0.000
substantial
Token substantial
Feature activation+0.000
elements
Token elements
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.209
âĢ
Token âĢ
Feature activation+0.639
ĺ
Tokenĺ
Feature activation+1.381
old
Tokenold
Feature activation+0.866
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.291
system
Token system
Feature activation+0.482
through
Token through
Feature activation+0.000

INTERVAL 0.528 - 1.055
CONTAINS 0.023%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
composed
Token composed
Feature activation+0.000
of
Token of
Feature activation+0.000
representatives
Token representatives
Feature activation+0.000
of
Token of
Feature activation+0.319
the
Token the
Feature activation+0.598
deal
Token deal
Feature activation+0.449
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.046
s
Tokens
Feature activation+0.373
six
Token six
Feature activation+0.025
group
Token group
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.049
Kurdistan
Token Kurdistan
Feature activation+0.000
Workers
Token Workers
Feature activation+0.111
âĢ
TokenâĢ
Feature activation+0.824
Ļ
TokenĻ
Feature activation+0.185
Party
Token Party
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
P
Token P
Feature activation+0.000
dynamically
Token dynamically
Feature activation+0.000
-
Token-
Feature activation+0.000
driven
Tokendriven
Feature activation+0.000
piece
Token piece
Feature activation+0.000
of
Token of
Feature activation+0.000
UI
Token UI
Feature activation+0.621
will
Token will
Feature activation+0.000
behave
Token behave
Feature activation+0.000
when
Token when
Feature activation+0.000
there
Token there
Feature activation+0.000
aren
Token aren
Feature activation+0.000
most
Token most
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.268
the
Token the
Feature activation+2.017
mult
Token mult
Feature activation+1.073
idis
Tokenidis
Feature activation+0.883
ciplinary
Tokenciplinary
Feature activation+2.825
clinical
Token clinical
Feature activation+1.381
trial
Token trial
Feature activation+1.819
team
Token team
Feature activation+0.499
were
Token were
Feature activation+0.000
Obama
Token Obama
Feature activation+3.702
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.052
s
Tokens
Feature activation+4.347
protective
Token protective
Feature activation+1.605
detail
Token detail
Feature activation+0.667
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Law
TokenLaw
Feature activation+0.000
makers
Tokenmakers
Feature activation+0.000

INTERVAL 0.000 - 0.528
CONTAINS 99.943%

t
Tokent
Feature activation+0.000
I
TokenI
Feature activation+0.000
h
Tokenh
Feature activation+0.000
0
Token0
Feature activation+0.000
k
Tokenk
Feature activation+0.000
3
Token3
Feature activation+0.000
T
TokenT
Feature activation+0.000
ft
Tokenft
Feature activation+0.000
Q
TokenQ
Feature activation+0.000
j
Tokenj
Feature activation+0.000
1
Token1
Feature activation+0.000
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
strain
Token strain
Feature activation+0.000
on
Token on
Feature activation+0.000
our
Token our
Feature activation+0.000
society
Token society
Feature activation+0.000
Frank
Token Frank
Feature activation+0.000
-
Token-
Feature activation+0.000
J
TokenJ
Feature activation+0.000
ür
Tokenür
Feature activation+0.000
gen
Tokengen
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
perfect
Token perfect
Feature activation+0.000
:
Token:
Feature activation+0.000
a
Token a
Feature activation+0.000
wild
Token wild
Feature activation+0.000
pitch
Token pitch
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
strike
Token strike
Feature activation+0.000
out
Tokenout
Feature activation+0.000
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
role
Token role
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
anomal
Token anomal
Feature activation+0.000
ous
Tokenous
Feature activation+0.000
in
Token in
Feature activation+0.000
human
Token human
Feature activation+0.000
life
Token life
Feature activation+0.000
.
Token.
Feature activation+0.000
is
Token is
Feature activation+0.000
paved
Token paved
Feature activation+0.000
with
Token with
Feature activation+0.000
good
Token good
Feature activation+0.000
intentions
Token intentions
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
massive
Token massive
Feature activation+0.000
methane
Token methane
Feature activation+0.000
emissions
Token emissions
Feature activation+0.000
discovered
Token discovered
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 H8.7: (feature 10705)

TOP ACTIVATIONS
MAX = 3.044

on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.363
Germany
Token Germany
Feature activation+2.096
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.346
s
Tokens
Feature activation+3.044
most
Token most
Feature activation+2.941
wanted
Token wanted
Feature activation+2.730
list
Token list
Feature activation+0.392
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
222
Token 222
Feature activation+0.000
inmates
Token inmates
Feature activation+0.000
currently
Token currently
Feature activation+0.000
on
Token on
Feature activation+0.716
Texas
Token Texas
Feature activation+2.839
'
Token'
Feature activation+3.005
death
Token death
Feature activation+2.171
row
Token row
Feature activation+1.837
.
Token.
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+1.363
Germany
Token Germany
Feature activation+2.096
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.346
s
Tokens
Feature activation+3.044
most
Token most
Feature activation+2.941
wanted
Token wanted
Feature activation+2.730
list
Token list
Feature activation+0.392
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
on
Token on
Feature activation+0.000
R
Token R
Feature activation+0.336
SL
TokenSL
Feature activation+2.517
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.137
s
Tokens
Feature activation+2.913
squad
Token squad
Feature activation+1.420
,
Token,
Feature activation+0.000
signed
Token signed
Feature activation+0.000
with
Token with
Feature activation+0.000
Real
Token Real
Feature activation+0.000
the
Token the
Feature activation+0.000
222
Token 222
Feature activation+0.000
inmates
Token inmates
Feature activation+0.000
currently
Token currently
Feature activation+0.000
on
Token on
Feature activation+0.716
Texas
Token Texas
Feature activation+2.839
'
Token'
Feature activation+3.005
death
Token death
Feature activation+2.171
row
Token row
Feature activation+1.837
.
Token.
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
Squirrel
Token Squirrel
Feature activation+0.000
Girl
Token Girl
Feature activation+0.000
was
Token was
Feature activation+0.000
never
Token never
Feature activation+0.000
on
Token on
Feature activation+0.201
either
Token either
Feature activation+2.822
team
Token team
Feature activation+2.525
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
expected
Token expected
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.550
team
Token team
Feature activation+2.751
this
Token this
Feature activation+0.159
season
Token season
Feature activation+0.430
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
considered
Token considered
Feature activation+0.000
Germany
Token Germany
Feature activation+2.096
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.346
s
Tokens
Feature activation+3.044
most
Token most
Feature activation+2.941
wanted
Token wanted
Feature activation+2.730
list
Token list
Feature activation+0.392
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
speculation
Token speculation
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.302
finishing
Token finishing
Feature activation+2.592
end
Token end
Feature activation+0.333
twice
Token twice
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
gotten
Token gotten
Feature activation+0.000
onto
Token onto
Feature activation+0.000
the
Token the
Feature activation+1.456
cash
Token cash
Feature activation+2.586
train
Token train
Feature activation+1.408
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.256
Apple
Token Apple
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
who
Token who
Feature activation+0.000
find
Token find
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
on
Token on
Feature activation+0.337
the
Token the
Feature activation+2.039
wrong
Token wrong
Feature activation+2.566
side
Token side
Feature activation+2.001
of
Token of
Feature activation+0.748
either
Token either
Feature activation+0.000
the
Token the
Feature activation+0.000
law
Token law
Feature activation+0.000
Girl
Token Girl
Feature activation+0.000
was
Token was
Feature activation+0.000
never
Token never
Feature activation+0.000
on
Token on
Feature activation+0.201
either
Token either
Feature activation+2.822
team
Token team
Feature activation+2.525
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
love
Token love
Feature activation+0.000
eight
Token eight
Feature activation+0.000
homegrown
Token homegrown
Feature activation+0.000
players
Token players
Feature activation+0.000
on
Token on
Feature activation+0.000
R
Token R
Feature activation+0.336
SL
TokenSL
Feature activation+2.517
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.137
s
Tokens
Feature activation+2.913
squad
Token squad
Feature activation+1.420
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.181
think
Token think
Feature activation+1.873
tank
Tokentank
Feature activation+2.193
's
Token's
Feature activation+2.508
staff
Token staff
Feature activation+2.038
from
Token from
Feature activation+0.000
1981
Token 1981
Feature activation+0.000
-
Token-
Feature activation+0.000
83
Token83
Feature activation+0.000
place
Token place
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.505
Id
Token Id
Feature activation+0.217
itar
Tokenitar
Feature activation+0.000
od
Tokenod
Feature activation+2.460
trail
Token trail
Feature activation+1.341
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000
been
Token been
Feature activation+0.000
on
Token on
Feature activation+0.000
Rowling
Token Rowling
Feature activation+1.949
âĢ
TokenâĢ
Feature activation+0.230
Ļ
TokenĻ
Feature activation+2.447
s
Tokens
Feature activation+2.452
mind
Token mind
Feature activation+0.514
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
lately
Token lately
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
on
Token on
Feature activation+0.000
Rowling
Token Rowling
Feature activation+1.949
âĢ
TokenâĢ
Feature activation+0.230
Ļ
TokenĻ
Feature activation+2.447
s
Tokens
Feature activation+2.452
mind
Token mind
Feature activation+0.514
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
lately
Token lately
Feature activation+0.000
-
Token-
Feature activation+0.000
05
Token05
Feature activation+0.000
stint
Token stint
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.755
CFL
Token CFL
Feature activation+2.408
landscape
Token landscape
Feature activation+0.880
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
7
Token 7
Feature activation+0.000
months
Token months
Feature activation+0.000
on
Token on
Feature activation+0.209
death
Token death
Feature activation+2.380
row
Token row
Feature activation+1.496
.
Token.
Feature activation+0.000
Though
Token Though
Feature activation+0.000
12
Token 12
Feature activation+0.000
percent
Token percent
Feature activation+0.000
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.000
represented
Token represented
Feature activation+0.000
people
Token people
Feature activation+0.000
on
Token on
Feature activation+0.563
both
Token both
Feature activation+2.378
sides
Token sides
Feature activation+1.346
of
Token of
Feature activation+0.738
the
Token the
Feature activation+0.224
issue
Token issue
Feature activation+0.018
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 3.551

entered
Token entered
Feature activation+0.024
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
country
Token country
Feature activation+0.006
Top resid features:
are
Token are
Feature activation-0.001
Top resid features:
now
Token now
Feature activation+0.038
Top resid features:
on
Token on
Feature activation+2.404
Top resid features:
the
Token the
Feature activation+1.276
Top resid features:
Germany
Token Germany
Feature activation+0.036
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
s
Tokens
Feature activation+0.021
Top resid features:
at
Token at
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
222
Token 222
Feature activation-0.034
Top resid features:
inmates
Token inmates
Feature activation+0.158
Top resid features:
currently
Token currently
Feature activation+0.129
Top resid features:
on
Token on
Feature activation+3.287
Top resid features:
Texas
Token Texas
Feature activation+0.073
Top resid features:
'
Token'
Feature activation+0.138
Top resid features:
death
Token death
Feature activation+0.000
Top resid features:
row
Token row
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
entered
Token entered
Feature activation-0.015
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
country
Token country
Feature activation+0.006
Top resid features:
are
Token are
Feature activation+0.005
Top resid features:
now
Token now
Feature activation+0.047
Top resid features:
on
Token on
Feature activation+2.717
Top resid features:
the
Token the
Feature activation+0.862
Top resid features:
Germany
Token Germany
Feature activation+0.022
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.015
Top resid features:
s
Tokens
Feature activation+0.090
Top resid features:
one
Token one
Feature activation+0.001
Top resid features:
of
Token of
Feature activation-0.007
Top resid features:
eight
Token eight
Feature activation-0.011
Top resid features:
homegrown
Token homegrown
Feature activation+0.021
Top resid features:
players
Token players
Feature activation+0.043
Top resid features:
on
Token on
Feature activation+3.551
Top resid features:
R
Token R
Feature activation+0.025
Top resid features:
SL
TokenSL
Feature activation+0.053
Top resid features:
âĢ
TokenâĢ
Feature activation+0.009
Top resid features:
Ļ
TokenĻ
Feature activation+0.011
Top resid features:
s
Tokens
Feature activation+0.057
Top resid features:
at
Token at
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
222
Token 222
Feature activation-0.022
Top resid features:
inmates
Token inmates
Feature activation+0.092
Top resid features:
currently
Token currently
Feature activation+0.152
Top resid features:
on
Token on
Feature activation+3.299
Top resid features:
Texas
Token Texas
Feature activation+0.040
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
death
Token death
Feature activation+0.000
Top resid features:
row
Token row
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
Squirrel
Token Squirrel
Feature activation+0.015
Top resid features:
Girl
Token Girl
Feature activation+0.046
Top resid features:
was
Token was
Feature activation+0.023
Top resid features:
never
Token never
Feature activation+0.030
Top resid features:
on
Token on
Feature activation+3.090
Top resid features:
either
Token either
Feature activation+0.057
Top resid features:
team
Token team
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:
not
Token not
Feature activation-0.010
Top resid features:
expected
Token expected
Feature activation-0.025
Top resid features:
to
Token to
Feature activation+0.019
Top resid features:
be
Token be
Feature activation-0.009
Top resid features:
on
Token on
Feature activation+1.498
Top resid features:
the
Token the
Feature activation+1.846
Top resid features:
team
Token team
Feature activation+0.095
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
season
Token season
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
country
Token country
Feature activation-0.007
Top resid features:
are
Token are
Feature activation+0.002
Top resid features:
now
Token now
Feature activation+0.017
Top resid features:
on
Token on
Feature activation+1.551
Top resid features:
the
Token the
Feature activation+1.730
Top resid features:
Germany
Token Germany
Feature activation+0.010
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.006
Top resid features:
s
Tokens
Feature activation+0.214
Top resid features:
most
Token most
Feature activation+0.033
Top resid features:
ank
Tokenank
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
has
Token has
Feature activation+0.003
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
on
Token on
Feature activation+1.075
Top resid features:
the
Token the
Feature activation+2.218
Top resid features:
finishing
Token finishing
Feature activation-0.004
Top resid features:
end
Token end
Feature activation+0.000
Top resid features:
twice
Token twice
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.007
Top resid features:
pleased
Token pleased
Feature activation-0.016
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
have
Token have
Feature activation+0.006
Top resid features:
gotten
Token gotten
Feature activation-0.008
Top resid features:
onto
Token onto
Feature activation+1.961
Top resid features:
the
Token the
Feature activation+1.420
Top resid features:
cash
Token cash
Feature activation-0.021
Top resid features:
train
Token train
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
football
Token football
Feature activation+0.003
Top resid features:
ers
Tokeners
Feature activation+0.019
Top resid features:
who
Token who
Feature activation+0.029
Top resid features:
find
Token find
Feature activation+0.026
Top resid features:
themselves
Token themselves
Feature activation+0.036
Top resid features:
on
Token on
Feature activation+2.105
Top resid features:
the
Token the
Feature activation+1.010
Top resid features:
wrong
Token wrong
Feature activation+0.057
Top resid features:
side
Token side
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
either
Token either
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.020
Top resid features:
Squirrel
Token Squirrel
Feature activation+0.004
Top resid features:
Girl
Token Girl
Feature activation+0.015
Top resid features:
was
Token was
Feature activation+0.011
Top resid features:
never
Token never
Feature activation+0.033
Top resid features:
on
Token on
Feature activation+2.356
Top resid features:
either
Token either
Feature activation+0.570
Top resid features:
team
Token team
Feature activation+0.075
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:
one
Token one
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
eight
Token eight
Feature activation-0.018
Top resid features:
homegrown
Token homegrown
Feature activation+0.010
Top resid features:
players
Token players
Feature activation+0.029
Top resid features:
on
Token on
Feature activation+3.234
Top resid features:
R
Token R
Feature activation+0.027
Top resid features:
SL
TokenSL
Feature activation+0.009
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:
Gordon
Token Gordon
Feature activation-0.004
Top resid features:
Wasserman
Token Wasserman
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
who
Token who
Feature activation-0.001
Top resid features:
was
Token was
Feature activation-0.017
Top resid features:
on
Token on
Feature activation+2.105
Top resid features:
the
Token the
Feature activation+1.180
Top resid features:
think
Token think
Feature activation+0.018
Top resid features:
tank
Tokentank
Feature activation+0.047
Top resid features:
's
Token's
Feature activation+0.027
Top resid features:
staff
Token staff
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
the
Token the
Feature activation+0.048
Top resid features:
cold
Token cold
Feature activation+0.014
Top resid features:
est
Tokenest
Feature activation-0.009
Top resid features:
place
Token place
Feature activation+0.058
Top resid features:
on
Token on
Feature activation+1.585
Top resid features:
the
Token the
Feature activation+1.498
Top resid features:
Id
Token Id
Feature activation-0.005
Top resid features:
itar
Tokenitar
Feature activation+0.003
Top resid features:
od
Tokenod
Feature activation-0.000
Top resid features:
trail
Token trail
Feature activation+0.000
Top resid features:
ter
Tokenter
Feature activation+0.011
Top resid features:
âĢ
TokenâĢ
Feature activation+0.013
Top resid features:
Ļ
TokenĻ
Feature activation+0.006
Top resid features:
has
Token has
Feature activation+0.008
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
on
Token on
Feature activation+3.202
Top resid features:
Rowling
Token Rowling
Feature activation+0.040
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.019
Top resid features:
s
Tokens
Feature activation+0.002
Top resid features:
mind
Token mind
Feature activation+0.000
Top resid features:
ter
Tokenter
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.014
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
has
Token has
Feature activation+0.023
Top resid features:
been
Token been
Feature activation+0.018
Top resid features:
on
Token on
Feature activation+3.173
Top resid features:
Rowling
Token Rowling
Feature activation+0.070
Top resid features:
âĢ
TokenâĢ
Feature activation+0.015
Top resid features:
Ļ
TokenĻ
Feature activation-0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
mind
Token mind
Feature activation+0.000
Top resid features:
their
Token their
Feature activation-0.024
Top resid features:
2002
Token 2002
Feature activation-0.014
Top resid features:
-
Token-
Feature activation-0.005
Top resid features:
05
Token05
Feature activation-0.006
Top resid features:
stint
Token stint
Feature activation+0.088
Top resid features:
on
Token on
Feature activation+1.644
Top resid features:
the
Token the
Feature activation+1.466
Top resid features:
CFL
Token CFL
Feature activation+0.052
Top resid features:
landscape
Token landscape
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
15
Token 15
Feature activation-0.001
Top resid features:
years
Token years
Feature activation+0.038
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
7
Token 7
Feature activation+0.003
Top resid features:
months
Token months
Feature activation+0.043
Top resid features:
on
Token on
Feature activation+3.060
Top resid features:
death
Token death
Feature activation+0.012
Top resid features:
row
Token row
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Though
Token Though
Feature activation+0.000
Top resid features:
12
Token 12
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
who
Token who
Feature activation-0.006
Top resid features:
has
Token has
Feature activation+0.002
Top resid features:
represented
Token represented
Feature activation-0.010
Top resid features:
people
Token people
Feature activation+0.061
Top resid features:
on
Token on
Feature activation+2.949
Top resid features:
both
Token both
Feature activation+0.091
Top resid features:
sides
Token sides
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
issue
Token issue
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.01

Head 2: 0.03

Head 3: 0.03

Head 4: 0.08

Head 5: 0.06

Head 6: 0.02

Head 7: 0.51

Head 8: 0.08

Head 9: 0.04

Head 10: 0.08

Head 11: 0.03

Positive logits

roster2.59

blacklist2.39

list2.38

bandwagon2.30

pedest2.30

rosters2.29

Wanted2.28

boards2.24

benches2.17

board2.17

leash2.13

ladder2.12

List2.11

List2.05

deck2.03

throne2.02

igslist2.00

roadmap1.98

list1.97

lists1.97

Negative logits

simplicity-2.10

manner-1.95

characteristic-1.94

teness-1.79

terness-1.78

coincidence-1.76

earnest-1.74

lessness-1.72

ingenuity-1.66

dialect-1.66

sophistication-1.64

fulness-1.63

subdued-1.62

acity-1.62

lapse-1.59

languages-1.58

iosity-1.58

uracy-1.55

inacc-1.55

humility-1.53

INTERVAL 2.739 - 3.044
CONTAINS 0.001%

the
Token the
Feature activation+1.363
Germany
Token Germany
Feature activation+2.096
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.346
s
Tokens
Feature activation+3.044
most
Token most
Feature activation+2.941
wanted
Token wanted
Feature activation+2.730
list
Token list
Feature activation+0.392
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
222
Token 222
Feature activation+0.000
inmates
Token inmates
Feature activation+0.000
currently
Token currently
Feature activation+0.000
on
Token on
Feature activation+0.716
Texas
Token Texas
Feature activation+2.839
'
Token'
Feature activation+3.005
death
Token death
Feature activation+2.171
row
Token row
Feature activation+1.837
.
Token.
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
on
Token on
Feature activation+0.000
R
Token R
Feature activation+0.336
SL
TokenSL
Feature activation+2.517
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.137
s
Tokens
Feature activation+2.913
squad
Token squad
Feature activation+1.420
,
Token,
Feature activation+0.000
signed
Token signed
Feature activation+0.000
with
Token with
Feature activation+0.000
Real
Token Real
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.363
Germany
Token Germany
Feature activation+2.096
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.346
s
Tokens
Feature activation+3.044
most
Token most
Feature activation+2.941
wanted
Token wanted
Feature activation+2.730
list
Token list
Feature activation+0.392
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
222
Token 222
Feature activation+0.000
inmates
Token inmates
Feature activation+0.000
currently
Token currently
Feature activation+0.000
on
Token on
Feature activation+0.716
Texas
Token Texas
Feature activation+2.839
'
Token'
Feature activation+3.005
death
Token death
Feature activation+2.171
row
Token row
Feature activation+1.837
.
Token.
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.435 - 2.739
CONTAINS 0.001%

eight
Token eight
Feature activation+0.000
homegrown
Token homegrown
Feature activation+0.000
players
Token players
Feature activation+0.000
on
Token on
Feature activation+0.000
R
Token R
Feature activation+0.336
SL
TokenSL
Feature activation+2.517
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.137
s
Tokens
Feature activation+2.913
squad
Token squad
Feature activation+1.420
,
Token,
Feature activation+0.000
Germany
Token Germany
Feature activation+2.096
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.346
s
Tokens
Feature activation+3.044
most
Token most
Feature activation+2.941
wanted
Token wanted
Feature activation+2.730
list
Token list
Feature activation+0.392
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
speculation
Token speculation
Feature activation+0.000
place
Token place
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.505
Id
Token Id
Feature activation+0.217
itar
Tokenitar
Feature activation+0.000
od
Tokenod
Feature activation+2.460
trail
Token trail
Feature activation+1.341
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000
who
Token who
Feature activation+0.000
find
Token find
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
on
Token on
Feature activation+0.337
the
Token the
Feature activation+2.039
wrong
Token wrong
Feature activation+2.566
side
Token side
Feature activation+2.001
of
Token of
Feature activation+0.748
either
Token either
Feature activation+0.000
the
Token the
Feature activation+0.000
law
Token law
Feature activation+0.000
been
Token been
Feature activation+0.000
on
Token on
Feature activation+0.000
Rowling
Token Rowling
Feature activation+1.949
âĢ
TokenâĢ
Feature activation+0.230
Ļ
TokenĻ
Feature activation+2.447
s
Tokens
Feature activation+2.452
mind
Token mind
Feature activation+0.514
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
lately
Token lately
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.131 - 2.435
CONTAINS 0.002%

though
Token though
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
on
Token on
Feature activation+0.239
school
Token school
Feature activation+2.173
grounds
Token grounds
Feature activation+0.175
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
those
Token those
Feature activation+0.000
kind
Token kind
Feature activation+0.000
now
Token now
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.363
Germany
Token Germany
Feature activation+2.096
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.346
s
Tokens
Feature activation+3.044
most
Token most
Feature activation+2.941
wanted
Token wanted
Feature activation+2.730
list
Token list
Feature activation+0.392
.
Token.
Feature activation+0.000
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.000
represented
Token represented
Feature activation+0.000
people
Token people
Feature activation+0.000
on
Token on
Feature activation+0.563
both
Token both
Feature activation+2.378
sides
Token sides
Feature activation+1.346
of
Token of
Feature activation+0.738
the
Token the
Feature activation+0.224
issue
Token issue
Feature activation+0.018
,
Token,
Feature activation+0.000
put
Token put
Feature activation+0.000
one
Token one
Feature activation+0.000
woman
Token woman
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+1.670
bike
Token bike
Feature activation+2.171
for
Token for
Feature activation+0.000
every
Token every
Feature activation+0.000
two
Token two
Feature activation+0.000
men
Token men
Feature activation+0.000
in
Token in
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.932
first
Token first
Feature activation+2.031
team
Token team
Feature activation+2.177
of
Token of
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.000
NBA
Token NBA
Feature activation+0.000
D
Token D
Feature activation+0.000

INTERVAL 1.826 - 2.131
CONTAINS 0.003%

most
Token most
Feature activation+0.000
aggressively
Token aggressively
Feature activation+0.000
promoted
Token promoted
Feature activation+0.000
drug
Token drug
Feature activation+0.000
on
Token on
Feature activation+0.238
their
Token their
Feature activation+2.049
list
Token list
Feature activation+0.040
,
Token,
Feature activation+0.000
Type
Token Type
Feature activation+0.000
-
Token-
Feature activation+0.000
2
Token2
Feature activation+0.000
Indian
TokenIndian
Feature activation+0.000
independence
Token independence
Feature activation+0.000
.
Token.
Feature activation+0.000
Once
Token Once
Feature activation+0.000
on
Token on
Feature activation+0.000
Indian
Token Indian
Feature activation+2.013
soil
Token soil
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
she
Token she
Feature activation+0.000
lived
Token lived
Feature activation+0.000
find
Token find
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
on
Token on
Feature activation+0.337
the
Token the
Feature activation+2.039
wrong
Token wrong
Feature activation+2.566
side
Token side
Feature activation+2.001
of
Token of
Feature activation+0.748
either
Token either
Feature activation+0.000
the
Token the
Feature activation+0.000
law
Token law
Feature activation+0.000
or
Token or
Feature activation+0.000
no
Token no
Feature activation+0.000
more
Token more
Feature activation+0.000
visible
Token visible
Feature activation+0.000
player
Token player
Feature activation+0.000
on
Token on
Feature activation+0.311
a
Token a
Feature activation+1.996
football
Token football
Feature activation+1.625
team
Token team
Feature activation+1.788
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
starting
Token starting
Feature activation+0.000
acknowledged
Token acknowledged
Feature activation+0.000
that
Token that
Feature activation+0.000
not
Token not
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
on
Token on
Feature activation+0.017
his
Token his
Feature activation+1.871
team
Token team
Feature activation+0.209
was
Token was
Feature activation+0.000
pleased
Token pleased
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000

INTERVAL 1.522 - 1.826
CONTAINS 0.008%

away
Token away
Feature activation+0.000
,
Token,
Feature activation+0.000
ending
Token ending
Feature activation+0.000
up
Token up
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+1.754
ship
Token ship
Feature activation+0.774
to
Token to
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.000
party
Token party
Feature activation+0.000
"
Token"
Feature activation+0.000
on
Token on
Feature activation+0.341
the
Token the
Feature activation+1.314
town
Token town
Feature activation+1.650
's
Token's
Feature activation+1.566
police
Token police
Feature activation+1.678
log
Token log
Feature activation+0.466
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
McCarthy
Token McCarthy
Feature activation+0.000
providing
Token providing
Feature activation+0.000
shelter
Token shelter
Feature activation+0.000
to
Token to
Feature activation+0.000
those
Token those
Feature activation+0.000
on
Token on
Feature activation+0.054
the
Token the
Feature activation+1.582
run
Token run
Feature activation+0.732
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
have
Token have
Feature activation+0.000
reason
Token reason
Feature activation+0.000
his
Token his
Feature activation+0.000
blind
Token blind
Feature activation+0.000
colleague
Token colleague
Feature activation+0.000
off
Token off
Feature activation+0.000
the
Token the
Feature activation+0.876
Navy
Token Navy
Feature activation+1.522
Yard
Token Yard
Feature activation+1.259
base
Token base
Feature activation+0.933
when
Token when
Feature activation+0.000
they
Token they
Feature activation+0.000
heard
Token heard
Feature activation+0.000
train
Token train
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.978
Beta
Token Beta
Feature activation+1.575
channel
Token channel
Feature activation+0.855
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
will
Token will
Feature activation+0.000
get
Token get
Feature activation+0.000

INTERVAL 1.217 - 1.522
CONTAINS 0.013%

on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.701
seventh
Token seventh
Feature activation+1.015
and
Token and
Feature activation+0.000
final
Token final
Feature activation+1.368
season
Token season
Feature activation+1.364
of
Token of
Feature activation+0.592
FX
Token FX
Feature activation+0.308
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.414
s
Tokens
Feature activation+0.709
and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.178
drawing
Token drawing
Feature activation+1.366
board
Token board
Feature activation+1.046
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
incarnation
Token incarnation
Feature activation+0.000
since
Token since
Feature activation+0.000
an
Token an
Feature activation+0.000
eventual
Token eventual
Feature activation+0.000
audition
Token audition
Feature activation+0.000
on
Token on
Feature activation+0.154
the
Token the
Feature activation+0.747
Leafs
Token Leafs
Feature activation+1.372
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.293
blue
Token blue
Feature activation+1.177
-
Token-
Feature activation+0.549
line
Tokenline
Feature activation+1.385
his
Token his
Feature activation+0.000
seats
Token seats
Feature activation+0.000
on
Token on
Feature activation+0.100
the
Token the
Feature activation+0.814
Communist
Token Communist
Feature activation+0.455
Party
Token Party
Feature activation+1.435
's
Token's
Feature activation+1.530
Central
Token Central
Feature activation+1.399
Committee
Token Committee
Feature activation+1.555
and
Token and
Feature activation+0.000
Polit
Token Polit
Feature activation+0.106
for
Token for
Feature activation+0.000
him
Token him
Feature activation+0.000
was
Token was
Feature activation+0.000
listed
Token listed
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.259
document
Token document
Feature activation+0.374
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

INTERVAL 0.913 - 1.217
CONTAINS 0.019%

70
Token 70
Feature activation+0.000
seats
Token seats
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.176
Legislative
Token Legislative
Feature activation+0.751
Council
Token Council
Feature activation+1.016
,
Token,
Feature activation+0.000
known
Token known
Feature activation+0.000
as
Token as
Feature activation+0.074
Leg
Token Leg
Feature activation+0.000
Co
TokenCo
Feature activation+0.000
the
Token the
Feature activation+0.000
train
Token train
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.978
Beta
Token Beta
Feature activation+1.575
channel
Token channel
Feature activation+0.855
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
will
Token will
Feature activation+0.000
properties
Token properties
Feature activation+0.000
on
Token on
Feature activation+0.020
the
Token the
Feature activation+0.503
Navy
Token Navy
Feature activation+1.127
âĢ
TokenâĢ
Feature activation+0.193
Ļ
TokenĻ
Feature activation+1.139
s
Tokens
Feature activation+1.336
list
Token list
Feature activation+0.529
of
Token of
Feature activation+0.013
training
Token training
Feature activation+0.000
sites
Token sites
Feature activation+0.000
on
Token on
Feature activation+0.000
Rolling
Token Rolling
Feature activation+0.281
Stone
Token Stone
Feature activation+0.812
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.051
s
Tokens
Feature activation+0.995
500
Token 500
Feature activation+0.572
greatest
Token greatest
Feature activation+0.000
albums
Token albums
Feature activation+0.389
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
those
Token those
Feature activation+0.000
shown
Token shown
Feature activation+0.000
on
Token on
Feature activation+0.000
H
Token H
Feature activation+0.092
N
TokenN
Feature activation+0.389
IC
TokenIC
Feature activation+1.100
.
Token.
Feature activation+0.000
Media
Token Media
Feature activation+0.000
representatives
Token representatives
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.609 - 0.913
CONTAINS 0.035%

-
Token -
Feature activation+0.000
was
Token was
Feature activation+0.000
still
Token still
Feature activation+0.000
on
Token on
Feature activation+0.000
cloud
Token cloud
Feature activation+0.383
nine
Token nine
Feature activation+0.618
with
Token with
Feature activation+0.000
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
national
Token national
Feature activation+0.000
team
Token team
Feature activation+0.000
on
Token on
Feature activation+0.000
Marine
Token Marine
Feature activation+0.000
Corps
Token Corps
Feature activation+0.639
Rec
Token Rec
Feature activation+0.000
ru
Tokenru
Feature activation+0.000
iting
Tokeniting
Feature activation+0.650
Command
Token Command
Feature activation+0.881
's
Token's
Feature activation+0.271
social
Token social
Feature activation+0.582
and
Token and
Feature activation+0.285
web
Token web
Feature activation+0.283
personality
Token personality
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
required
Token required
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.907
return
Token return
Feature activation+0.145
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.218
.
Token.
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
best
Token best
Feature activation+0.000
to
Token to
Feature activation+0.000
ever
Token ever
Feature activation+0.629
play
Token play
Feature activation+0.400
the
Token the
Feature activation+0.409
position
Token position
Feature activation+0.188
.
Token.
Feature activation+0.000
Also
Token Also
Feature activation+0.000
affected
Tokenaffected
Feature activation+0.000
Taliban
Token Taliban
Feature activation+0.000
militants
Token militants
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.334
sides
Token sides
Feature activation+0.739
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
border
Token border
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.304 - 0.609
CONTAINS 0.074%

We
Token We
Feature activation+0.000
were
Token were
Feature activation+0.000
even
Token even
Feature activation+0.000
featured
Token featured
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.480
evening
Token evening
Feature activation+0.419
news
Token news
Feature activation+0.844
for
Token for
Feature activation+0.000
our
Token our
Feature activation+0.000
Comic
Token Comic
Feature activation+0.000
Justice
Token Justice
Feature activation+0.330
's
Token's
Feature activation+0.289
laws
Token laws
Feature activation+0.478
-
Token-
Feature activation+0.340
lo
Tokenlo
Feature activation+0.016
is
Tokenis
Feature activation+0.428
.
Token.
Feature activation+0.045
justice
Tokenjustice
Feature activation+0.476
.
Token.
Feature activation+0.000
gc
Tokengc
Feature activation+0.000
.
Token.
Feature activation+0.000
my
Token my
Feature activation+0.000
name
Token name
Feature activation+0.000
on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.459
clip
Token clip
Feature activation+0.591
boards
Tokenboards
Feature activation+0.423
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Too
TokenToo
Feature activation+0.000
small
Token small
Feature activation+0.000
on
Token on
Feature activation+0.000
ble
Token ble
Feature activation+0.053
achers
Tokenachers
Feature activation+0.000
off
Token off
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.408
side
Token side
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
rest
Token rest
Feature activation+0.000
of
Token of
Feature activation+0.000
city
Token city
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
bid
Token bid
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.533
games
Token games
Feature activation+0.569
three
Token three
Feature activation+0.000
years
Token years
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.304
CONTAINS 99.846%

news
Token news
Feature activation+0.000
sites
Token sites
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
listing
Token listing
Feature activation+0.000
of
Token of
Feature activation+0.000
local
Token local
Feature activation+0.000
news
Token news
Feature activation+0.000
affiliates
Token affiliates
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
Cricket
Token Cricket
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
my
Token my
Feature activation+0.000
history
Token history
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
divided
Token divided
Feature activation+0.000
into
Token into
Feature activation+0.000
project
Token project
Feature activation+0.000
files
Token files
Feature activation+0.000
have
Token have
Feature activation+0.000
all
Token all
Feature activation+0.000
been
Token been
Feature activation+0.000
open
Token open
Feature activation+0.000
sourced
Token sourced
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
greatly
Token greatly
Feature activation+0.000
team
Token team
Feature activation+0.000
works
Token works
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
product
Token product
Feature activation+0.000
owner
Token owner
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mic
TokenMic
Feature activation+0.000
roman
Tokenroman
Feature activation+0.000
school
Token school
Feature activation+0.000
at
Token at
Feature activation+0.000
age
Token age
Feature activation+0.000
10
Token 10
Feature activation+0.000
,
Token,
Feature activation+0.000
having
Token having
Feature activation+0.000
learned
Token learned
Feature activation+0.000
neither
Token neither
Feature activation+0.000
how
Token how
Feature activation+0.000
to
Token to
Feature activation+0.000
read
Token read
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 6 in H8.7: (feature 5051)

TOP ACTIVATIONS
MAX = 3.114

gain
Token gain
Feature activation+0.000
influence
Token influence
Feature activation+0.000
at
Token at
Feature activation+0.522
W
Token W
Feature activation+1.505
3
Token3
Feature activation+1.332
C
TokenC
Feature activation+3.114
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
your
Token your
Feature activation+0.000
need
Token need
Feature activation+0.000
determined
Token determined
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
at
Token at
Feature activation+0.085
the
Token the
Feature activation+1.814
national
Token national
Feature activation+3.044
level
Token level
Feature activation+0.178
to
Token to
Feature activation+0.000
move
Token move
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
involved
Token involved
Feature activation+0.000
in
Token in
Feature activation+0.000
participation
Token participation
Feature activation+0.000
at
Token at
Feature activation+0.474
a
Token a
Feature activation+2.008
national
Token national
Feature activation+2.786
level
Token level
Feature activation+1.484
event
Token event
Feature activation+1.443
and
Token and
Feature activation+0.000
for
Token for
Feature activation+0.000
most
Token most
Feature activation+0.000
authoritarian
Token authoritarian
Feature activation+0.000
impulses
Token impulses
Feature activation+0.000
exhibited
Token exhibited
Feature activation+0.000
at
Token at
Feature activation+0.025
the
Token the
Feature activation+2.200
company
Token company
Feature activation+2.771
appear
Token appear
Feature activation+0.000
to
Token to
Feature activation+0.000
eman
Token eman
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
from
Token from
Feature activation+0.000
M
Token M
Feature activation+0.502
á
Tokená
Feature activation+0.000
º
Tokenº
Feature activation+0.000
¹
Token¹
Feature activation+1.392
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.710
s
Tokens
Feature activation+1.688
burial
Token burial
Feature activation+1.065
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token "
Feature activation+0.000
evil
Tokenevil
Feature activation+0.000
"
Token"
Feature activation+0.000
ways
Token ways
Feature activation+0.000
at
Token at
Feature activation+0.086
his
Token his
Feature activation+2.705
unprecedented
Token unprecedented
Feature activation+1.818
war
Token war
Feature activation+1.711
crimes
Token crimes
Feature activation+1.138
trial
Token trial
Feature activation+0.528
.
Token.
Feature activation+0.000
at
Token at
Feature activation+0.000
Mazda
Token Mazda
Feature activation+1.739
,
Token,
Feature activation+0.000
GM
Token GM
Feature activation+0.747
or
Token or
Feature activation+0.355
VW
Token VW
Feature activation+2.677
so
Token so
Feature activation+0.000
I
Token I
Feature activation+0.000
took
Token took
Feature activation+0.000
the
Token the
Feature activation+0.000
plunge
Token plunge
Feature activation+0.000
interested
Token interested
Feature activation+0.000
in
Token in
Feature activation+0.000
A
Token A
Feature activation+0.000
du
Tokendu
Feature activation+0.000
at
Token at
Feature activation+0.682
this
Token this
Feature activation+2.560
point
Token point
Feature activation+0.449
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
Cosmos
Token Cosmos
Feature activation+0.000
used
Token used
Feature activation+0.000
paper
Token paper
Feature activation+0.000
at
Token at
Feature activation+0.094
Charles
Token Charles
Feature activation+1.181
De
Token De
Feature activation+0.000
Gaul
Token Gaul
Feature activation+0.000
le
Tokenle
Feature activation+2.550
in
Token in
Feature activation+0.000
Paris
Token Paris
Feature activation+0.000
and
Token and
Feature activation+0.000
lived
Token lived
Feature activation+0.000
at
Token at
Feature activation+0.000
free
Token free
Feature activation+0.000
ride
Token ride
Feature activation+0.000
at
Token at
Feature activation+0.027
other
Token other
Feature activation+2.114
people
Token people
Feature activation+2.326
's
Token's
Feature activation+2.525
expense
Token expense
Feature activation+0.257
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
most
Token most
Feature activation+0.000
of
Token of
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
personal
Token personal
Feature activation+0.000
profit
Token profit
Feature activation+0.000
at
Token at
Feature activation+0.333
your
Token your
Feature activation+2.523
expense
Token expense
Feature activation+0.385
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
position
Token position
Feature activation+0.000
of
Token of
Feature activation+0.000
advantage
Token advantage
Feature activation+0.000
at
Token at
Feature activation+0.351
or
Token or
Feature activation+0.000
near
Token near
Feature activation+2.486
your
Token your
Feature activation+1.710
six
Token six
Feature activation+1.113
o
Token o
Feature activation+0.041
âĢ
TokenâĢ
Feature activation+0.388
Ļ
TokenĻ
Feature activation+1.087
time
Token time
Feature activation+0.000
being
Token being
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.802
very
Token very
Feature activation+2.469
least
Token least
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
episode
Token episode
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
proper
Token proper
Feature activation+0.000
debate
Token debate
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.380
environment
Token environment
Feature activation+2.454
committee
Token committee
Feature activation+1.881
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
from
Token from
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
strong
Token strong
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.450
back
Token back
Feature activation+2.443
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
mean
Token mean
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
wrong
Token wrong
Feature activation+0.000
decision
Token decision
Feature activation+0.000
at
Token at
Feature activation+0.000
this
Token this
Feature activation+2.433
stage
Token stage
Feature activation+0.000
could
Token could
Feature activation+0.000
prove
Token prove
Feature activation+0.000
disastrous
Token disastrous
Feature activation+0.000
for
Token for
Feature activation+0.000
adopt
Token adopt
Feature activation+0.000
at
Token at
Feature activation+0.000
an
Token an
Feature activation+0.987
S
Token S
Feature activation+1.760
&
Token&
Feature activation+0.422
M
TokenM
Feature activation+2.400
club
Token club
Feature activation+2.029
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Close
TokenClose
Feature activation+0.000
at
Token at
Feature activation+0.373
the
Token the
Feature activation+1.620
Al
Token Al
Feature activation+1.310
H
Token H
Feature activation+0.000
irsch
Tokenirsch
Feature activation+1.750
feld
Tokenfeld
Feature activation+2.384
Theatre
Token Theatre
Feature activation+1.390
before
Token before
Feature activation+0.000
each
Token each
Feature activation+0.000
show
Token show
Feature activation+0.146
to
Token to
Feature activation+0.000
Man
Token Man
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
gamble
Token gamble
Feature activation+0.000
at
Token at
Feature activation+0.000
that
Token that
Feature activation+2.381
point
Token point
Feature activation+0.326
but
Token but
Feature activation+0.000
even
Token even
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
'
Token'
Feature activation+0.000
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
champion
Token champion
Feature activation+0.000
at
Token at
Feature activation+0.218
DOS
Token DOS
Feature activation+2.367
?"
Token?"
Feature activation+0.000
Perkins
Token Perkins
Feature activation+0.000
added
Token added
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 3.671

the
Token the
Feature activation-0.008
Top resid features:
money
Token money
Feature activation-0.008
Top resid features:
to
Token to
Feature activation+0.027
Top resid features:
gain
Token gain
Feature activation-0.003
Top resid features:
influence
Token influence
Feature activation+0.068
Top resid features:
at
Token at
Feature activation+3.671
Top resid features:
W
Token W
Feature activation+0.015
Top resid features:
3
Token3
Feature activation+0.010
Top resid features:
C
TokenC
Feature activation+0.050
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
We
Token We
Feature activation+0.002
Top resid features:
need
Token need
Feature activation+0.008
Top resid features:
determined
Token determined
Feature activation+0.002
Top resid features:
leadership
Token leadership
Feature activation+0.036
Top resid features:
at
Token at
Feature activation+1.447
Top resid features:
the
Token the
Feature activation+2.338
Top resid features:
national
Token national
Feature activation+0.023
Top resid features:
level
Token level
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
move
Token move
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
some
Token some
Feature activation-0.003
Top resid features:
prestige
Token prestige
Feature activation-0.005
Top resid features:
involved
Token involved
Feature activation+0.017
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
participation
Token participation
Feature activation-0.001
Top resid features:
at
Token at
Feature activation+1.733
Top resid features:
a
Token a
Feature activation+1.705
Top resid features:
national
Token national
Feature activation+0.072
Top resid features:
level
Token level
Feature activation+0.000
Top resid features:
event
Token event
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.036
Top resid features:
worst
Token worst
Feature activation-0.002
Top resid features:
authoritarian
Token authoritarian
Feature activation-0.006
Top resid features:
impulses
Token impulses
Feature activation+0.108
Top resid features:
exhibited
Token exhibited
Feature activation+0.048
Top resid features:
at
Token at
Feature activation+2.696
Top resid features:
the
Token the
Feature activation+0.753
Top resid features:
company
Token company
Feature activation+0.003
Top resid features:
appear
Token appear
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
eman
Token eman
Feature activation+0.000
Top resid features:
anyone
Token anyone
Feature activation+0.013
Top resid features:
else
Token else
Feature activation+0.005
Top resid features:
would
Token would
Feature activation+0.007
Top resid features:
see
Token see
Feature activation-0.016
Top resid features:
me
Token me
Feature activation+0.004
Top resid features:
at
Token at
Feature activation+3.253
Top resid features:
M
Token M
Feature activation+0.121
Top resid features:
á
Tokená
Feature activation+0.018
Top resid features:
º
Tokenº
Feature activation+0.004
Top resid features:
¹
Token¹
Feature activation+0.013
Top resid features:
âĢ
TokenâĢ
Feature activation+0.023
Top resid features:
such
Token such
Feature activation-0.006
Top resid features:
"
Token "
Feature activation-0.002
Top resid features:
evil
Tokenevil
Feature activation+0.001
Top resid features:
"
Token"
Feature activation+0.006
Top resid features:
ways
Token ways
Feature activation+0.021
Top resid features:
at
Token at
Feature activation+3.427
Top resid features:
his
Token his
Feature activation+0.024
Top resid features:
unprecedented
Token unprecedented
Feature activation+0.000
Top resid features:
war
Token war
Feature activation+0.000
Top resid features:
crimes
Token crimes
Feature activation+0.000
Top resid features:
trial
Token trial
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.012
Top resid features:
able
Token able
Feature activation+0.028
Top resid features:
to
Token to
Feature activation+0.013
Top resid features:
achieve
Token achieve
Feature activation+0.002
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
at
Token at
Feature activation+3.270
Top resid features:
Mazda
Token Mazda
Feature activation+0.044
Top resid features:
,
Token,
Feature activation+0.062
Top resid features:
GM
Token GM
Feature activation+0.002
Top resid features:
or
Token or
Feature activation+0.119
Top resid features:
VW
Token VW
Feature activation+0.012
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
interested
Token interested
Feature activation-0.027
Top resid features:
in
Token in
Feature activation-0.028
Top resid features:
A
Token A
Feature activation+0.007
Top resid features:
du
Tokendu
Feature activation+0.022
Top resid features:
at
Token at
Feature activation+3.253
Top resid features:
this
Token this
Feature activation+0.064
Top resid features:
point
Token point
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:
Cosmos
Token Cosmos
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
who
Token who
Feature activation+0.043
Top resid features:
lost
Token lost
Feature activation+0.020
Top resid features:
his
Token his
Feature activation+0.009
Top resid features:
paper
Token paper
Feature activation+0.048
Top resid features:
at
Token at
Feature activation+3.137
Top resid features:
Charles
Token Charles
Feature activation+0.027
Top resid features:
De
Token De
Feature activation+0.005
Top resid features:
Gaul
Token Gaul
Feature activation-0.003
Top resid features:
le
Tokenle
Feature activation+0.038
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.003
Top resid features:
wanting
Token wanting
Feature activation-0.006
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
free
Token free
Feature activation+0.001
Top resid features:
ride
Token ride
Feature activation+0.048
Top resid features:
at
Token at
Feature activation+3.216
Top resid features:
other
Token other
Feature activation+0.073
Top resid features:
people
Token people
Feature activation+0.015
Top resid features:
's
Token's
Feature activation+0.015
Top resid features:
expense
Token expense
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.005
Top resid features:
s
Tokens
Feature activation-0.004
Top resid features:
personal
Token personal
Feature activation+0.004
Top resid features:
profit
Token profit
Feature activation+0.060
Top resid features:
at
Token at
Feature activation+3.029
Top resid features:
your
Token your
Feature activation+0.115
Top resid features:
expense
Token expense
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:
obtained
Token obtained
Feature activation+0.020
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
position
Token position
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
advantage
Token advantage
Feature activation+0.019
Top resid features:
at
Token at
Feature activation+3.092
Top resid features:
or
Token or
Feature activation+0.028
Top resid features:
near
Token near
Feature activation+0.036
Top resid features:
your
Token your
Feature activation+0.000
Top resid features:
six
Token six
Feature activation+0.000
Top resid features:
o
Token o
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
time
Token time
Feature activation+0.010
Top resid features:
being
Token being
Feature activation+0.020
Top resid features:
,
Token,
Feature activation+0.078
Top resid features:
at
Token at
Feature activation+1.428
Top resid features:
the
Token the
Feature activation+1.482
Top resid features:
very
Token very
Feature activation+0.296
Top resid features:
least
Token least
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:
episode
Token episode
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.014
Top resid features:
proper
Token proper
Feature activation+0.001
Top resid features:
debate
Token debate
Feature activation+0.038
Top resid features:
at
Token at
Feature activation+1.275
Top resid features:
the
Token the
Feature activation+1.875
Top resid features:
environment
Token environment
Feature activation+0.000
Top resid features:
committee
Token committee
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:
hearing
Token hearing
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.058
Top resid features:
to
Token to
Feature activation+0.051
Top resid features:
be
Token be
Feature activation+0.066
Top resid features:
strong
Token strong
Feature activation-0.001
Top resid features:
at
Token at
Feature activation+0.623
Top resid features:
the
Token the
Feature activation+2.276
Top resid features:
back
Token back
Feature activation+0.068
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
does
Token does
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
conscious
Token conscious
Feature activation+0.001
Top resid features:
that
Token that
Feature activation+0.058
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
wrong
Token wrong
Feature activation+0.005
Top resid features:
decision
Token decision
Feature activation-0.008
Top resid features:
at
Token at
Feature activation+3.075
Top resid features:
this
Token this
Feature activation+0.196
Top resid features:
stage
Token stage
Feature activation+0.000
Top resid features:
could
Token could
Feature activation+0.000
Top resid features:
prove
Token prove
Feature activation+0.000
Top resid features:
disastrous
Token disastrous
Feature activation+0.000
Top resid features:
adventurous
Token adventurous
Feature activation+0.012
Top resid features:
type
Token type
Feature activation+0.011
Top resid features:
might
Token might
Feature activation+0.005
Top resid features:
adopt
Token adopt
Feature activation+0.007
Top resid features:
at
Token at
Feature activation+1.406
Top resid features:
an
Token an
Feature activation+1.587
Top resid features:
S
Token S
Feature activation+0.050
Top resid features:
&
Token&
Feature activation-0.008
Top resid features:
M
TokenM
Feature activation+0.067
Top resid features:
club
Token club
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
physical
Token physical
Feature activation+0.004
Top resid features:
therapy
Token therapy
Feature activation+0.024
Top resid features:
room
Token room
Feature activation-0.023
Top resid features:
backstage
Token backstage
Feature activation+0.060
Top resid features:
at
Token at
Feature activation+1.917
Top resid features:
the
Token the
Feature activation+1.089
Top resid features:
Al
Token Al
Feature activation+0.054
Top resid features:
H
Token H
Feature activation+0.006
Top resid features:
irsch
Tokenirsch
Feature activation+0.008
Top resid features:
feld
Tokenfeld
Feature activation+0.024
Top resid features:
Iron
Token Iron
Feature activation-0.000
Top resid features:
Man
Token Man
Feature activation+0.012
Top resid features:
was
Token was
Feature activation+0.041
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
gamble
Token gamble
Feature activation+0.054
Top resid features:
at
Token at
Feature activation+3.022
Top resid features:
that
Token that
Feature activation+0.059
Top resid features:
point
Token point
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
acy
Tokenacy
Feature activation+0.015
Top resid features:
'
Token'
Feature activation+0.019
Top resid features:
he
Token he
Feature activation-0.001
Top resid features:
would
Token would
Feature activation+0.006
Top resid features:
champion
Token champion
Feature activation+0.004
Top resid features:
at
Token at
Feature activation+2.951
Top resid features:
DOS
Token DOS
Feature activation+0.097
Top resid features:
?"
Token?"
Feature activation+0.000
Top resid features:
Perkins
Token Perkins
Feature activation+0.000
Top resid features:
added
Token added
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.02

Head 2: 0.02

Head 3: 0.04

Head 4: 0.09

Head 5: 0.07

Head 6: 0.02

Head 7: 0.50

Head 8: 0.06

Head 9: 0.05

Head 10: 0.09

Head 11: 0.02

Positive logits

behest2.11

expense2.04

intersections1.99

chwitz1.96

level1.95

conferences1.93

jun1.83

intervals1.82

festivals1.81

meetings1.77

studios1.76

College1.74

outset1.74

checkpoint1.73

amusement1.70

university1.69

pring1.69

School1.68

college1.68

summit1.68

Negative logits

ordes-1.68

pour-1.62

campaigner-1.59

narrator-1.58

jargon-1.58

yrus-1.52

routed-1.47

messenger-1.47

essage-1.44

acted-1.43

vocabulary-1.43

sylv-1.42

propag-1.42

caller-1.41

smuggled-1.41

heroine-1.41

passengers-1.39

dossier-1.37

coded-1.34

treated-1.34

INTERVAL 2.803 - 3.114
CONTAINS 0.000%

gain
Token gain
Feature activation+0.000
influence
Token influence
Feature activation+0.000
at
Token at
Feature activation+0.522
W
Token W
Feature activation+1.505
3
Token3
Feature activation+1.332
C
TokenC
Feature activation+3.114
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
your
Token your
Feature activation+0.000
need
Token need
Feature activation+0.000
determined
Token determined
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
at
Token at
Feature activation+0.085
the
Token the
Feature activation+1.814
national
Token national
Feature activation+3.044
level
Token level
Feature activation+0.178
to
Token to
Feature activation+0.000
move
Token move
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000

INTERVAL 2.491 - 2.803
CONTAINS 0.001%

authoritarian
Token authoritarian
Feature activation+0.000
impulses
Token impulses
Feature activation+0.000
exhibited
Token exhibited
Feature activation+0.000
at
Token at
Feature activation+0.025
the
Token the
Feature activation+2.200
company
Token company
Feature activation+2.771
appear
Token appear
Feature activation+0.000
to
Token to
Feature activation+0.000
eman
Token eman
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
from
Token from
Feature activation+0.000
M
Token M
Feature activation+0.502
á
Tokená
Feature activation+0.000
º
Tokenº
Feature activation+0.000
¹
Token¹
Feature activation+1.392
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.710
s
Tokens
Feature activation+1.688
burial
Token burial
Feature activation+1.065
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token "
Feature activation+0.000
evil
Tokenevil
Feature activation+0.000
"
Token"
Feature activation+0.000
ways
Token ways
Feature activation+0.000
at
Token at
Feature activation+0.086
his
Token his
Feature activation+2.705
unprecedented
Token unprecedented
Feature activation+1.818
war
Token war
Feature activation+1.711
crimes
Token crimes
Feature activation+1.138
trial
Token trial
Feature activation+0.528
.
Token.
Feature activation+0.000
interested
Token interested
Feature activation+0.000
in
Token in
Feature activation+0.000
A
Token A
Feature activation+0.000
du
Tokendu
Feature activation+0.000
at
Token at
Feature activation+0.682
this
Token this
Feature activation+2.560
point
Token point
Feature activation+0.449
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
Cosmos
Token Cosmos
Feature activation+0.000
used
Token used
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
personal
Token personal
Feature activation+0.000
profit
Token profit
Feature activation+0.000
at
Token at
Feature activation+0.333
your
Token your
Feature activation+2.523
expense
Token expense
Feature activation+0.385
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000

INTERVAL 2.180 - 2.491
CONTAINS 0.004%

protection
Token protection
Feature activation+0.000
and
Token and
Feature activation+0.000
social
Token social
Feature activation+0.000
progress
Token progress
Feature activation+0.000
at
Token at
Feature activation+0.793
the
Token the
Feature activation+2.236
same
Token same
Feature activation+1.779
time
Token time
Feature activation+0.691
,"
Token,"
Feature activation+0.000
Christine
Token Christine
Feature activation+0.000
Lag
Token Lag
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.390
mad
Token mad
Feature activation+1.268
r
Tokenr
Feature activation+1.607
ass
Tokenass
Feature activation+1.221
a
Tokena
Feature activation+2.203
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
difficulty
Token difficulty
Feature activation+0.000
recruiting
Token recruiting
Feature activation+0.000
volunteers
Token volunteers
Feature activation+0.000
at
Token at
Feature activation+0.309
the
Token the
Feature activation+1.547
riding
Token riding
Feature activation+2.210
level
Token level
Feature activation+1.024
.
Token.
Feature activation+0.000
Even
Token Even
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
stal
Token stal
Feature activation+0.000
a
Token a
Feature activation+0.000
proper
Token proper
Feature activation+0.000
debate
Token debate
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.380
environment
Token environment
Feature activation+2.454
committee
Token committee
Feature activation+1.881
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
from
Token from
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
brain
Token brain
Feature activation+0.000
trust
Token trust
Feature activation+0.000
at
Token at
Feature activation+0.325
the
Token the
Feature activation+2.289
mid
Token mid
Feature activation+2.302
point
Tokenpoint
Feature activation+1.746
of
Token of
Feature activation+1.027
this
Token this
Feature activation+0.000
long
Token long
Feature activation+0.000
election
Token election
Feature activation+0.000

INTERVAL 1.869 - 2.180
CONTAINS 0.009%

million
Token million
Feature activation+0.000
fraud
Token fraud
Feature activation+0.000
at
Token at
Feature activation+0.751
Tri
Token Tri
Feature activation+0.750
o
Tokeno
Feature activation+1.938
Capital
Token Capital
Feature activation+1.873
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Consider
TokenConsider
Feature activation+0.000
last
Token last
Feature activation+0.000
weekend
Token weekend
Feature activation+0.000
a
Token a
Feature activation+0.000
comes
Token comes
Feature activation+0.000
into
Token into
Feature activation+0.000
his
Token his
Feature activation+0.000
head
Token head
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+2.104
moment
Token moment
Feature activation+0.311
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
really
Token really
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
of
Token of
Feature activation+0.000
fun
Token fun
Feature activation+0.000
at
Token at
Feature activation+0.000
your
Token your
Feature activation+2.037
expense
Token expense
Feature activation+0.000
.
Token.
Feature activation+0.000
Dress
Token Dress
Feature activation+0.000
up
Token up
Feature activation+0.000
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
replacement
Token replacement
Feature activation+0.000
is
Token is
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+2.039
same
Token same
Feature activation+2.148
time
Token time
Feature activation+0.000
repeal
Token repeal
Feature activation+0.000
passes
Token passes
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
good
Token good
Feature activation+0.000
co
Token co
Feature activation+0.000
-
Token-
Feature activation+0.000
workers
Tokenworkers
Feature activation+0.000
at
Token at
Feature activation+0.015
my
Token my
Feature activation+1.959
past
Token past
Feature activation+2.175
jobs
Token jobs
Feature activation+1.243
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
may
Token may
Feature activation+0.000

INTERVAL 1.557 - 1.869
CONTAINS 0.025%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
who
Token who
Feature activation+0.000
performed
Token performed
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.771
Hillary
Token Hillary
Feature activation+1.211
rally
Token rally
Feature activation+1.131
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
three
Token three
Feature activation+0.000
at
Token at
Feature activation+0.114
an
Token an
Feature activation+1.315
Italian
Token Italian
Feature activation+1.730
Grand
Token Grand
Feature activation+0.989
Prix
Token Prix
Feature activation+1.283
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.099
first
Token first
Feature activation+0.103
expertise
Token expertise
Feature activation+0.000
in
Token in
Feature activation+0.000
covert
Token covert
Feature activation+0.000
operations
Token operations
Feature activation+0.000
at
Token at
Feature activation+0.510
the
Token the
Feature activation+1.789
young
Token young
Feature activation+1.959
age
Token age
Feature activation+0.238
of
Token of
Feature activation+0.181
12
Token 12
Feature activation+0.398
,
Token,
Feature activation+0.000
infants
Token infants
Feature activation+0.000
died
Token died
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.702
BR
Token BR
Feature activation+0.161
D
TokenD
Feature activation+1.742
hospital
Token hospital
Feature activation+0.716
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
killer
Token killer
Feature activation+0.000
night
Token night
Feature activation+0.000
backstage
Token backstage
Feature activation+0.000
at
Token at
Feature activation+0.373
the
Token the
Feature activation+1.620
Al
Token Al
Feature activation+1.310
H
Token H
Feature activation+0.000
irsch
Tokenirsch
Feature activation+1.750
feld
Tokenfeld
Feature activation+2.384
Theatre
Token Theatre
Feature activation+1.390
before
Token before
Feature activation+0.000
each
Token each
Feature activation+0.000
show
Token show
Feature activation+0.146

INTERVAL 1.246 - 1.557
CONTAINS 0.041%

a
Token a
Feature activation+0.000
regular
Token regular
Feature activation+0.000
occurrence
Token occurrence
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.018
immigration
Token immigration
Feature activation+1.406
centre
Token centre
Feature activation+0.832
in
Token in
Feature activation+0.000
Tap
Token Tap
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
ula
Tokenula
Feature activation+0.000
Fund
Token Fund
Feature activation+0.000
a
Token a
Feature activation+0.000
lif
Token lif
Feature activation+0.000
eline
Tokeneline
Feature activation+0.000
at
Token at
Feature activation+0.090
a
Token a
Feature activation+1.345
time
Token time
Feature activation+0.752
when
Token when
Feature activation+0.000
donor
Token donor
Feature activation+0.000
support
Token support
Feature activation+0.000
is
Token is
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
I
Token I
Feature activation+0.000
hope
Token hope
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.364
end
Token end
Feature activation+0.531
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
day
Token day
Feature activation+0.000
is
Token is
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
good
Token good
Feature activation+0.000
behaviour
Token behaviour
Feature activation+0.000
while
Token while
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.434
Euro
Token Euro
Feature activation+0.537
2016
Token 2016
Feature activation+1.470
tournament
Token tournament
Feature activation+0.634
in
Token in
Feature activation+0.000
France
Token France
Feature activation+0.000
offering
Token offering
Feature activation+0.000
the
Token the
Feature activation+0.000
card
Token card
Feature activation+0.000
at
Token at
Feature activation+0.139
their
Token their
Feature activation+1.325
Dallas
Token Dallas
Feature activation+1.410
locations
Token locations
Feature activation+0.858
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Un
TokenUn
Feature activation+0.000

INTERVAL 0.934 - 1.246
CONTAINS 0.069%

of
Token of
Feature activation+0.000
shenanigans
Token shenanigans
Feature activation+0.000
off
Token off
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.233
pass
Token pass
Feature activation+0.964
by
Token by
Feature activation+0.000
putting
Token putting
Feature activation+0.000
together
Token together
Feature activation+0.000
something
Token something
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+1.474
Anti
Token Anti
Feature activation+0.484
-
Token-
Feature activation+0.000
Def
TokenDef
Feature activation+0.000
amation
Tokenamation
Feature activation+0.000
League
Token League
Feature activation+1.180
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
Semitic
TokenSemitic
Feature activation+0.000
him
Token him
Feature activation+0.000
,
Token,
Feature activation+0.000
expecting
Token expecting
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.700
very
Token very
Feature activation+0.955
least
Token least
Feature activation+0.000
an
Token an
Feature activation+0.000
uncon
Token uncon
Feature activation+0.000
v
Tokenv
Feature activation+0.000
inc
Tokeninc
Feature activation+0.000
best
Token best
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
business
Token business
Feature activation+0.000
at
Token at
Feature activation+0.000
what
Token what
Feature activation+1.047
he
Token he
Feature activation+0.362
does
Token does
Feature activation+0.333
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
moving
Token moving
Feature activation+0.000
abroad
Token abroad
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+1.025
time
Token time
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 0.623 - 0.934
CONTAINS 0.110%

rooms
Token rooms
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.068
our
Token our
Feature activation+0.316
kitchen
Token kitchen
Feature activation+0.632
tables
Token tables
Feature activation+0.625
,
Token,
Feature activation+0.000
over
Token over
Feature activation+0.000
coffee
Token coffee
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
flight
Token flight
Feature activation+0.000
at
Token at
Feature activation+0.000
John
Token John
Feature activation+0.501
F
Token F
Feature activation+0.098
.
Token.
Feature activation+0.176
Kennedy
Token Kennedy
Feature activation+0.703
International
Token International
Feature activation+0.274
Airport
Token Airport
Feature activation+0.093
but
Token but
Feature activation+0.000
later
Token later
Feature activation+0.000
said
Token said
Feature activation+0.000
barric
Token barric
Feature activation+0.000
ades
Tokenades
Feature activation+0.000
at
Token at
Feature activation+0.000
Occupy
Token Occupy
Feature activation+0.525
Wall
Token Wall
Feature activation+0.000
Street
Token Street
Feature activation+0.873
protests
Token protests
Feature activation+0.313
.
Token.
Feature activation+0.000
Rather
Token Rather
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
and
Token and
Feature activation+0.000
dining
Token dining
Feature activation+0.000
area
Token area
Feature activation+0.000
at
Token at
Feature activation+0.203
Gil
Token Gil
Feature activation+0.854
lette
Tokenlette
Feature activation+0.853
Stadium
Token Stadium
Feature activation+1.317
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
club
Token club
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.196
small
Token small
Feature activation+0.856
,
Token,
Feature activation+0.831
liberal
Token liberal
Feature activation+0.429
arts
Token arts
Feature activation+0.449
college
Token college
Feature activation+0.473
in
Token in
Feature activation+0.000
California
Token California
Feature activation+0.000

INTERVAL 0.311 - 0.623
CONTAINS 0.158%

spending
Token spending
Feature activation+0.000
has
Token has
Feature activation+0.000
increased
Token increased
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.303
much
Token much
Feature activation+0.584
faster
Token faster
Feature activation+0.000
rate
Token rate
Feature activation+0.000
than
Token than
Feature activation+0.000
government
Token government
Feature activation+0.000
spending
Token spending
Feature activation+0.000
resolve
Token resolve
Feature activation+0.000
any
Token any
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.579
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
after
Token after
Feature activation+0.000
reading
Token reading
Feature activation+0.000
their
Token their
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.107
Mar
Token Mar
Feature activation+0.000
riot
Tokenriot
Feature activation+0.000
Ward
Token Ward
Feature activation+0.536
man
Tokenman
Feature activation+0.491
Park
Token Park
Feature activation+0.000
in
Token in
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
,
Token,
Feature activation+0.000
quite
Token quite
Feature activation+0.225
a
Token a
Feature activation+0.659
high
Token high
Feature activation+0.489
price
Token price
Feature activation+0.286
-
Token-
Feature activation+0.000
range
Tokenrange
Feature activation+0.391
for
Token for
Feature activation+0.000
mice
Token mice
Feature activation+0.000
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
cheering
Token cheering
Feature activation+0.000
crowd
Token crowd
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.612
restaurant
Token restaurant
Feature activation+0.686
,
Token,
Feature activation+0.000
Hamb
Token Hamb
Feature activation+0.000
urger
Tokenurger
Feature activation+0.000
Mary
Token Mary
Feature activation+0.000

INTERVAL 0.000 - 0.311
CONTAINS 99.582%

information
Token information
Feature activation+0.000
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
been
Token been
Feature activation+0.000
provided
Token provided
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
50
Token 50
Feature activation+0.000
-
Token-
Feature activation+0.000
is
Token is
Feature activation+0.000
something
Token something
Feature activation+0.000
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
covered
Token covered
Feature activation+0.000
in
Token in
Feature activation+0.000
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
my
Token my
Feature activation+0.000
columns
Token columns
Feature activation+0.000
being
Tokenbeing
Feature activation+0.000
discussed
Token discussed
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
separate
Token separate
Feature activation+0.000
track
Token track
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
one
Token one
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Sw
TokenSw
Feature activation+0.000
ede
Tokenede
Feature activation+0.000
told
Token told
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
cancer
Token cancer
Feature activation+0.000
and
Token and
Feature activation+0.000
forced
Token forced
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
parties
Token parties
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
to
Token to
Feature activation+0.000
speak
Token speak
Feature activation+0.000
truth
Token truth
Feature activation+0.000
to
Token to
Feature activation+0.000
whichever
Token whichever
Feature activation+0.000
POWER
Token POWER
Feature activation+0.000
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.000
hear
Token hear
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 H8.7: (feature 23353)

TOP ACTIVATIONS
MAX = 3.717

,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
woman
Token woman
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.642
early
Token early
Feature activation+3.429
30
Token 30
Feature activation+3.717
s
Tokens
Feature activation+0.000
reported
Token reported
Feature activation+0.000
the
Token the
Feature activation+0.000
crime
Token crime
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
60
Token 60
Feature activation+3.342
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
killings
Token killings
Feature activation+0.000
are
Token are
Feature activation+0.000
now
Token now
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.311
70
Token 70
Feature activation+3.320
s
Tokens
Feature activation+0.335
and
Token and
Feature activation+0.073
80
Token 80
Feature activation+1.922
s
Tokens
Feature activation+0.672
Ċ
TokenĊ
Feature activation+0.000
her
Token her
Feature activation+0.516
late
Token late
Feature activation+2.492
70
Token 70
Feature activation+2.842
s
Tokens
Feature activation+0.380
or
Token or
Feature activation+0.814
80
Token 80
Feature activation+3.295
s
Tokens
Feature activation+0.032
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
fr
Token fr
Feature activation+0.000
at
Tokenat
Feature activation+0.000
boys
Token boys
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+1.269
th
Token th
Feature activation+3.210
irt
Tokenirt
Feature activation+2.906
ies
Tokenies
Feature activation+0.448
wearing
Token wearing
Feature activation+0.000
pol
Token pol
Feature activation+0.201
os
Tokenos
Feature activation+0.000
W
TokenW
Feature activation+0.000
att
Tokenatt
Feature activation+0.000
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.304
60
Token 60
Feature activation+3.112
s
Tokens
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
at
Tokenat
Feature activation+0.000
boys
Token boys
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+1.269
th
Token th
Feature activation+3.210
irt
Tokenirt
Feature activation+2.906
ies
Tokenies
Feature activation+0.448
wearing
Token wearing
Feature activation+0.000
pol
Token pol
Feature activation+0.201
os
Tokenos
Feature activation+0.000
with
Token with
Feature activation+0.000
sitting
Token sitting
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
Ram
Token Ram
Feature activation+0.479
at
Tokenat
Feature activation+0.000
Aviv
Token Aviv
Feature activation+2.896
apartment
Token apartment
Feature activation+0.426
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
recent
Token recent
Feature activation+0.000
weekday
Token weekday
Feature activation+0.000
Asian
Token Asian
Feature activation+0.000
woman
Token woman
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.516
late
Token late
Feature activation+2.492
70
Token 70
Feature activation+2.842
s
Tokens
Feature activation+0.380
or
Token or
Feature activation+0.814
80
Token 80
Feature activation+3.295
s
Tokens
Feature activation+0.032
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
white
Token white
Feature activation+0.000
men
Token men
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.730
mid
Token mid
Feature activation+2.825
20
Token 20
Feature activation+1.776
s
Tokens
Feature activation+0.403
from
Token from
Feature activation+0.000
various
Token various
Feature activation+0.000
backgrounds
Token backgrounds
Feature activation+0.000
studies
Token studies
Feature activation+0.000
,
Token,
Feature activation+0.000
now
Token now
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
15
Token 15
Feature activation+2.785
th
Tokenth
Feature activation+1.070
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
evaluate
Token evaluate
Feature activation+0.000
residential
Token residential
Feature activation+0.000
was
Token was
Feature activation+0.000
standing
Token standing
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.458
p
Token p
Feature activation+2.770
aj
Tokenaj
Feature activation+0.655
amas
Tokenamas
Feature activation+1.737
,
Token,
Feature activation+0.000
talking
Token talking
Feature activation+0.000
to
Token to
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
still
Token still
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
20
Token 20
Feature activation+2.688
s
Tokens
Feature activation+0.201
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
we
Token we
Feature activation+0.000
picked
Token picked
Feature activation+0.000
an
Token an
Feature activation+0.000
Asian
Token Asian
Feature activation+0.000
woman
Token woman
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.516
late
Token late
Feature activation+2.492
70
Token 70
Feature activation+2.842
s
Tokens
Feature activation+0.380
or
Token or
Feature activation+0.814
80
Token 80
Feature activation+3.295
s
Tokens
Feature activation+0.032
black
Token black
Feature activation+0.000
woman
Token woman
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
early
Token early
Feature activation+2.297
20
Token 20
Feature activation+2.402
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
worried
Token worried
Feature activation+0.000
live
Token live
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
Dr
Token Dr
Feature activation+0.591
Evil
Token Evil
Feature activation+2.224
Volcano
Token Volcano
Feature activation+2.379
with
Token with
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
amenities
Token amenities
Feature activation+0.000
We
TokenWe
Feature activation+0.000
step
Token step
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+1.198
solar
Token solar
Feature activation+2.355
system
Token system
Feature activation+1.435
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
universe
Token universe
Feature activation+0.092
seeking
Token seeking
Feature activation+0.000
a
Token a
Feature activation+0.000
black
Token black
Feature activation+0.000
woman
Token woman
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
early
Token early
Feature activation+2.297
20
Token 20
Feature activation+2.402
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.259
mid
Token mid
Feature activation+1.581
-
Token-
Feature activation+2.266
20
Token20
Feature activation+1.757
s
Tokens
Feature activation+0.545
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
are
Token are
Feature activation+0.000
I
Token I
Feature activation+0.000
live
Token live
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
Dr
Token Dr
Feature activation+0.591
Evil
Token Evil
Feature activation+2.224
Volcano
Token Volcano
Feature activation+2.379
with
Token with
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000

Top DFA by src position
MAX = 4.037

Tuesday
Token Tuesday
Feature activation-0.017
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
woman
Token woman
Feature activation+0.027
Top resid features:
in
Token in
Feature activation+0.147
Top resid features:
her
Token her
Feature activation+3.955
Top resid features:
early
Token early
Feature activation+0.230
Top resid features:
30
Token 30
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
reported
Token reported
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
I
Token I
Feature activation-0.020
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.007
Top resid features:
m
Tokenm
Feature activation-0.008
Top resid features:
in
Token in
Feature activation+0.125
Top resid features:
my
Token my
Feature activation+4.019
Top resid features:
60
Token 60
Feature activation+0.006
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
killings
Token killings
Feature activation+0.003
Top resid features:
are
Token are
Feature activation+0.079
Top resid features:
now
Token now
Feature activation+0.053
Top resid features:
in
Token in
Feature activation+0.211
Top resid features:
their
Token their
Feature activation+3.674
Top resid features:
70
Token 70
Feature activation+0.023
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
80
Token 80
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.023
Top resid features:
an
Token an
Feature activation+0.012
Top resid features:
Asian
Token Asian
Feature activation+0.016
Top resid features:
woman
Token woman
Feature activation+0.030
Top resid features:
in
Token in
Feature activation+0.131
Top resid features:
her
Token her
Feature activation+2.799
Top resid features:
late
Token late
Feature activation+0.571
Top resid features:
70
Token 70
Feature activation+0.009
Top resid features:
s
Tokens
Feature activation+0.415
Top resid features:
or
Token or
Feature activation+0.148
Top resid features:
80
Token 80
Feature activation-0.015
Top resid features:
former
Token former
Feature activation+0.000
Top resid features:
fr
Token fr
Feature activation+0.010
Top resid features:
at
Tokenat
Feature activation+0.000
Top resid features:
boys
Token boys
Feature activation+0.031
Top resid features:
in
Token in
Feature activation+0.296
Top resid features:
their
Token their
Feature activation+3.716
Top resid features:
th
Token th
Feature activation+0.023
Top resid features:
irt
Tokenirt
Feature activation+0.000
Top resid features:
ies
Tokenies
Feature activation+0.000
Top resid features:
wearing
Token wearing
Feature activation+0.000
Top resid features:
pol
Token pol
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.009
Top resid features:
W
TokenW
Feature activation-0.002
Top resid features:
att
Tokenatt
Feature activation+0.009
Top resid features:
was
Token was
Feature activation+0.036
Top resid features:
in
Token in
Feature activation+0.157
Top resid features:
his
Token his
Feature activation+3.749
Top resid features:
60
Token 60
Feature activation+0.015
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
former
Token former
Feature activation+0.003
Top resid features:
fr
Token fr
Feature activation+0.008
Top resid features:
at
Tokenat
Feature activation+0.007
Top resid features:
boys
Token boys
Feature activation+0.018
Top resid features:
in
Token in
Feature activation+0.136
Top resid features:
their
Token their
Feature activation+3.315
Top resid features:
th
Token th
Feature activation+0.122
Top resid features:
irt
Tokenirt
Feature activation+0.040
Top resid features:
ies
Tokenies
Feature activation+0.000
Top resid features:
wearing
Token wearing
Feature activation+0.000
Top resid features:
pol
Token pol
Feature activation+0.000
Top resid features:
ed
Tokened
Feature activation-0.003
Top resid features:
aka
Tokenaka
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
sitting
Token sitting
Feature activation+0.015
Top resid features:
in
Token in
Feature activation+0.176
Top resid features:
her
Token her
Feature activation+3.535
Top resid features:
Ram
Token Ram
Feature activation+0.013
Top resid features:
at
Tokenat
Feature activation-0.008
Top resid features:
Aviv
Token Aviv
Feature activation-0.093
Top resid features:
apartment
Token apartment
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.037
Top resid features:
an
Token an
Feature activation+0.014
Top resid features:
Asian
Token Asian
Feature activation+0.003
Top resid features:
woman
Token woman
Feature activation+0.006
Top resid features:
in
Token in
Feature activation+0.145
Top resid features:
her
Token her
Feature activation+2.255
Top resid features:
late
Token late
Feature activation+1.193
Top resid features:
70
Token 70
Feature activation+0.060
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
80
Token 80
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.540
Top resid features:
white
Token white
Feature activation-0.005
Top resid features:
men
Token men
Feature activation-0.055
Top resid features:
in
Token in
Feature activation+0.079
Top resid features:
their
Token their
Feature activation+3.321
Top resid features:
mid
Token mid
Feature activation+0.136
Top resid features:
20
Token 20
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
various
Token various
Feature activation+0.000
Top resid features:
line
Tokenline
Feature activation+0.005
Top resid features:
studies
Token studies
Feature activation-0.081
Top resid features:
,
Token,
Feature activation-0.028
Top resid features:
now
Token now
Feature activation-0.088
Top resid features:
in
Token in
Feature activation-0.059
Top resid features:
their
Token their
Feature activation+4.037
Top resid features:
15
Token 15
Feature activation-0.023
Top resid features:
th
Tokenth
Feature activation+0.000
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
evaluate
Token evaluate
Feature activation+0.000
Top resid features:
ond
Tokenond
Feature activation+0.015
Top resid features:
was
Token was
Feature activation+0.011
Top resid features:
standing
Token standing
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
in
Token in
Feature activation+0.116
Top resid features:
her
Token her
Feature activation+3.325
Top resid features:
p
Token p
Feature activation+0.024
Top resid features:
aj
Tokenaj
Feature activation+0.000
Top resid features:
amas
Tokenamas
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
talking
Token talking
Feature activation+0.000
Top resid features:
when
Token when
Feature activation-0.012
Top resid features:
he
Token he
Feature activation+0.062
Top resid features:
was
Token was
Feature activation-0.014
Top resid features:
still
Token still
Feature activation+0.015
Top resid features:
in
Token in
Feature activation+0.265
Top resid features:
his
Token his
Feature activation+3.136
Top resid features:
20
Token 20
Feature activation-0.001
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.063
Top resid features:
an
Token an
Feature activation+0.031
Top resid features:
Asian
Token Asian
Feature activation+0.010
Top resid features:
woman
Token woman
Feature activation+0.038
Top resid features:
in
Token in
Feature activation+0.155
Top resid features:
her
Token her
Feature activation+2.797
Top resid features:
late
Token late
Feature activation+0.176
Top resid features:
70
Token 70
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
80
Token 80
Feature activation+0.000
Top resid features:
as
Token as
Feature activation-0.010
Top resid features:
a
Token a
Feature activation-0.012
Top resid features:
black
Token black
Feature activation+0.008
Top resid features:
woman
Token woman
Feature activation-0.020
Top resid features:
in
Token in
Feature activation+0.033
Top resid features:
her
Token her
Feature activation+1.698
Top resid features:
early
Token early
Feature activation+1.468
Top resid features:
20
Token 20
Feature activation+0.050
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
she
Token she
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.017
Top resid features:
't
Token't
Feature activation+0.026
Top resid features:
I
Token I
Feature activation+0.006
Top resid features:
live
Token live
Feature activation-0.014
Top resid features:
in
Token in
Feature activation+0.108
Top resid features:
my
Token my
Feature activation+3.056
Top resid features:
Dr
Token Dr
Feature activation+0.004
Top resid features:
Evil
Token Evil
Feature activation+0.072
Top resid features:
Volcano
Token Volcano
Feature activation+0.004
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.037
Top resid features:
We
TokenWe
Feature activation+0.001
Top resid features:
step
Token step
Feature activation+0.040
Top resid features:
out
Token out
Feature activation+0.057
Top resid features:
of
Token of
Feature activation+0.428
Top resid features:
our
Token our
Feature activation+2.518
Top resid features:
solar
Token solar
Feature activation-0.000
Top resid features:
system
Token system
Feature activation+0.000
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
universe
Token universe
Feature activation+0.000
Top resid features:
as
Token as
Feature activation-0.011
Top resid features:
a
Token a
Feature activation-0.004
Top resid features:
black
Token black
Feature activation+0.018
Top resid features:
woman
Token woman
Feature activation-0.063
Top resid features:
in
Token in
Feature activation+0.086
Top resid features:
her
Token her
Feature activation+2.866
Top resid features:
early
Token early
Feature activation+0.180
Top resid features:
20
Token 20
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
she
Token she
Feature activation+0.000
Top resid features:
exist
Token exist
Feature activation-0.004
Top resid features:
when
Token when
Feature activation+0.053
Top resid features:
you
Token you
Feature activation-0.006
Top resid features:
're
Token're
Feature activation+0.025
Top resid features:
in
Token in
Feature activation+0.146
Top resid features:
your
Token your
Feature activation+1.820
Top resid features:
mid
Token mid
Feature activation+0.851
Top resid features:
-
Token-
Feature activation+0.097
Top resid features:
20
Token20
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.036
Top resid features:
't
Token't
Feature activation+0.024
Top resid features:
I
Token I
Feature activation+0.006
Top resid features:
live
Token live
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.110
Top resid features:
my
Token my
Feature activation+2.979
Top resid features:
Dr
Token Dr
Feature activation+0.025
Top resid features:
Evil
Token Evil
Feature activation-0.002
Top resid features:
Volcano
Token Volcano
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.01

Head 2: 0.04

Head 3: 0.03

Head 4: 0.06

Head 5: 0.11

Head 6: 0.03

Head 7: 0.50

Head 8: 0.05

Head 9: 0.03

Head 10: 0.08

Head 11: 0.03

Positive logits

attire2.57

ixties2.34

twenties2.32

guise2.32

robes2.27

adolescence2.22

incarnation2.19

upbringing2.15

role2.14

robe2.12

era2.11

age2.09

bedroom2.09

adulthood2.05

afterlife2.01

lair2.00

stint1.98

autobiography1.97

infancy1.95

gown1.92

Negative logits

osate-2.22

taxpayers-1.91

atoes-1.90

facts-1.68

population-1.65

izont-1.65

Consumers-1.64

-1.62

estones-1.61

enos-1.61

payers-1.61

Investors-1.61

DERR-1.58

Hash-1.55

consumers-1.55

changes-1.54

ONEY-1.53

voters-1.51

Revenue-1.51

Iss-1.51

INTERVAL 3.345 - 3.717
CONTAINS 0.000%

,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
woman
Token woman
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.642
early
Token early
Feature activation+3.429
30
Token 30
Feature activation+3.717
s
Tokens
Feature activation+0.000
reported
Token reported
Feature activation+0.000
the
Token the
Feature activation+0.000
crime
Token crime
Feature activation+0.000

INTERVAL 2.973 - 3.345
CONTAINS 0.001%

W
TokenW
Feature activation+0.000
att
Tokenatt
Feature activation+0.000
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.304
60
Token 60
Feature activation+3.112
s
Tokens
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
fr
Token fr
Feature activation+0.000
at
Tokenat
Feature activation+0.000
boys
Token boys
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+1.269
th
Token th
Feature activation+3.210
irt
Tokenirt
Feature activation+2.906
ies
Tokenies
Feature activation+0.448
wearing
Token wearing
Feature activation+0.000
pol
Token pol
Feature activation+0.201
os
Tokenos
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
60
Token 60
Feature activation+3.342
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
her
Token her
Feature activation+0.516
late
Token late
Feature activation+2.492
70
Token 70
Feature activation+2.842
s
Tokens
Feature activation+0.380
or
Token or
Feature activation+0.814
80
Token 80
Feature activation+3.295
s
Tokens
Feature activation+0.032
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
killings
Token killings
Feature activation+0.000
are
Token are
Feature activation+0.000
now
Token now
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.311
70
Token 70
Feature activation+3.320
s
Tokens
Feature activation+0.335
and
Token and
Feature activation+0.073
80
Token 80
Feature activation+1.922
s
Tokens
Feature activation+0.672
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.602 - 2.973
CONTAINS 0.001%

he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
still
Token still
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
20
Token 20
Feature activation+2.688
s
Tokens
Feature activation+0.201
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
we
Token we
Feature activation+0.000
picked
Token picked
Feature activation+0.000
was
Token was
Feature activation+0.000
standing
Token standing
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.458
p
Token p
Feature activation+2.770
aj
Tokenaj
Feature activation+0.655
amas
Tokenamas
Feature activation+1.737
,
Token,
Feature activation+0.000
talking
Token talking
Feature activation+0.000
to
Token to
Feature activation+0.000
studies
Token studies
Feature activation+0.000
,
Token,
Feature activation+0.000
now
Token now
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
15
Token 15
Feature activation+2.785
th
Tokenth
Feature activation+1.070
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
evaluate
Token evaluate
Feature activation+0.000
residential
Token residential
Feature activation+0.000
at
Tokenat
Feature activation+0.000
boys
Token boys
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+1.269
th
Token th
Feature activation+3.210
irt
Tokenirt
Feature activation+2.906
ies
Tokenies
Feature activation+0.448
wearing
Token wearing
Feature activation+0.000
pol
Token pol
Feature activation+0.201
os
Tokenos
Feature activation+0.000
with
Token with
Feature activation+0.000
sitting
Token sitting
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
Ram
Token Ram
Feature activation+0.479
at
Tokenat
Feature activation+0.000
Aviv
Token Aviv
Feature activation+2.896
apartment
Token apartment
Feature activation+0.426
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
recent
Token recent
Feature activation+0.000
weekday
Token weekday
Feature activation+0.000

INTERVAL 2.230 - 2.602
CONTAINS 0.001%

a
Token a
Feature activation+0.000
black
Token black
Feature activation+0.000
woman
Token woman
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
early
Token early
Feature activation+2.297
20
Token 20
Feature activation+2.402
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
live
Token live
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
Dr
Token Dr
Feature activation+0.591
Evil
Token Evil
Feature activation+2.224
Volcano
Token Volcano
Feature activation+2.379
with
Token with
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
amenities
Token amenities
Feature activation+0.000
black
Token black
Feature activation+0.000
woman
Token woman
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
early
Token early
Feature activation+2.297
20
Token 20
Feature activation+2.402
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
worried
Token worried
Feature activation+0.000
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.259
mid
Token mid
Feature activation+1.581
-
Token-
Feature activation+2.266
20
Token20
Feature activation+1.757
s
Tokens
Feature activation+0.545
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
are
Token are
Feature activation+0.000
an
Token an
Feature activation+0.000
Asian
Token Asian
Feature activation+0.000
woman
Token woman
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.516
late
Token late
Feature activation+2.492
70
Token 70
Feature activation+2.842
s
Tokens
Feature activation+0.380
or
Token or
Feature activation+0.814
80
Token 80
Feature activation+3.295
s
Tokens
Feature activation+0.032

INTERVAL 1.858 - 2.230
CONTAINS 0.001%

in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
theater
Token theater
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.002
early
Token early
Feature activation+2.204
career
Token career
Feature activation+0.911
,
Token,
Feature activation+0.000
performing
Token performing
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
I
Token I
Feature activation+0.000
live
Token live
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
Dr
Token Dr
Feature activation+0.591
Evil
Token Evil
Feature activation+2.224
Volcano
Token Volcano
Feature activation+2.379
with
Token with
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.311
70
Token 70
Feature activation+3.320
s
Tokens
Feature activation+0.335
and
Token and
Feature activation+0.073
80
Token 80
Feature activation+1.922
s
Tokens
Feature activation+0.672
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
President
TokenPresident
Feature activation+0.000
J
Token J
Feature activation+0.000
late
Token late
Feature activation+2.049
20
Token 20
Feature activation+1.973
s
Tokens
Feature activation+0.000
and
Token and
Feature activation+0.645
early
Token early
Feature activation+0.581
30
Token 30
Feature activation+2.019
s
Tokens
Feature activation+0.000
were
Token were
Feature activation+0.000
staying
Token staying
Feature activation+0.000
put
Token put
Feature activation+0.000
after
Token after
Feature activation+0.000
showed
Token showed
Feature activation+0.000
more
Token more
Feature activation+0.000
people
Token people
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
late
Token late
Feature activation+2.049
20
Token 20
Feature activation+1.973
s
Tokens
Feature activation+0.000
and
Token and
Feature activation+0.645
early
Token early
Feature activation+0.581
30
Token 30
Feature activation+2.019

INTERVAL 1.487 - 1.858
CONTAINS 0.002%

from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.398
80
Token 80
Feature activation+1.517
s
Tokens
Feature activation+0.000
following
Token following
Feature activation+0.000
a
Token a
Feature activation+0.000
routine
Token routine
Feature activation+0.000
call
Token call
Feature activation+0.000
and
Token and
Feature activation+0.000
only
Token only
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
late
Token late
Feature activation+2.068
20
Token 20
Feature activation+1.835
s
Tokens
Feature activation+0.000
fell
Token fell
Feature activation+0.000
in
Token in
Feature activation+0.000
love
Token love
Feature activation+0.000
with
Token with
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.458
p
Token p
Feature activation+2.770
aj
Tokenaj
Feature activation+0.655
amas
Tokenamas
Feature activation+1.737
,
Token,
Feature activation+0.000
talking
Token talking
Feature activation+0.000
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
officer
Token officer
Feature activation+0.000
,
Token,
Feature activation+0.000
also
Token also
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.579
bathing
Token bathing
Feature activation+1.582
suits
Token suits
Feature activation+1.587
,
Token,
Feature activation+0.000
wrapped
Token wrapped
Feature activation+0.000
in
Token in
Feature activation+0.000
towels
Token towels
Feature activation+0.000
and
Token and
Feature activation+0.000
when
Token when
Feature activation+0.000
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.259
mid
Token mid
Feature activation+1.581
-
Token-
Feature activation+2.266
20
Token20
Feature activation+1.757
s
Tokens
Feature activation+0.545
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.115 - 1.487
CONTAINS 0.003%

too
Token too
Feature activation+0.000
per
Token per
Feature activation+0.000
missive
Tokenmissive
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.390
parenting
Token parenting
Feature activation+1.411
?
Token?
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
think
Token think
Feature activation+0.000
and
Token and
Feature activation+0.000
solves
Token solves
Feature activation+0.000
crimes
Token crimes
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
spare
Token spare
Feature activation+1.128
time
Token time
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
#
Token#
Feature activation+0.000
16
Token16
Feature activation+0.000
in
Token in
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
his
Token his
Feature activation+0.000
CFL
Token CFL
Feature activation+1.291
debut
Token debut
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
five
Token five
Feature activation+0.000
-
Token-
Feature activation+0.000
stops
Token stops
Feature activation+0.000
when
Token when
Feature activation+0.000
you
Token you
Feature activation+0.000
enter
Token enter
Feature activation+0.000
its
Token its
Feature activation+0.000
working
Token working
Feature activation+1.116
radius
Token radius
Feature activation+0.589
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
in
Token in
Feature activation+0.000
former
Token former
Feature activation+0.000
fr
Token fr
Feature activation+0.000
at
Tokenat
Feature activation+0.000
boys
Token boys
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+1.269
th
Token th
Feature activation+3.210
irt
Tokenirt
Feature activation+2.906
ies
Tokenies
Feature activation+0.448
wearing
Token wearing
Feature activation+0.000
pol
Token pol
Feature activation+0.201

INTERVAL 0.743 - 1.115
CONTAINS 0.008%

particular
Token particular
Feature activation+0.000
found
Token found
Feature activation+0.000
success
Token success
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
limited
Token limited
Feature activation+0.906
body
Token body
Feature activation+0.709
of
Token of
Feature activation+0.000
work
Token work
Feature activation+0.000
,
Token,
Feature activation+0.000
posting
Token posting
Feature activation+0.000
hunting
Token hunting
Feature activation+0.000
wild
Token wild
Feature activation+0.000
game
Token game
Feature activation+0.000
during
Token during
Feature activation+0.000
her
Token her
Feature activation+0.424
childhood
Token childhood
Feature activation+0.755
in
Token in
Feature activation+0.000
Ohio
Token Ohio
Feature activation+0.000
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
marrying
Token marrying
Feature activation+0.000
doing
Token doing
Feature activation+0.000
a
Token a
Feature activation+0.000
dance
Token dance
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
living
Token living
Feature activation+1.029
room
Token room
Feature activation+0.000
when
Token when
Feature activation+0.000
I
Token I
Feature activation+0.000
saw
Token saw
Feature activation+0.000
the
Token the
Feature activation+0.000
P
TokenP
Feature activation+0.000
upp
Tokenupp
Feature activation+0.000
y
Tokeny
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.199
future
Token future
Feature activation+1.081
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
procedure
Token procedure
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
semi
Token semi
Feature activation+0.668
-
Token-
Feature activation+0.501
med
Tokenmed
Feature activation+0.000
icated
Tokenicated
Feature activation+1.000
state
Token state
Feature activation+0.820
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
do
Token do
Feature activation+0.000
recall
Token recall
Feature activation+0.000

INTERVAL 0.372 - 0.743
CONTAINS 0.021%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
0
Token0
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
opening
Token opening
Feature activation+1.110
match
Token match
Feature activation+0.536
at
Token at
Feature activation+0.000
Women
Token Women
Feature activation+0.000
's
Token's
Feature activation+0.000
Euro
Token Euro
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
than
Token than
Feature activation+0.000
just
Token just
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
time
Token time
Feature activation+0.467
.
Token.
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
earlier
Token earlier
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
n
Token n
Feature activation+0.639
es
Tokenes
Feature activation+0.067
&
Token &
Feature activation+0.270
s
Token s
Feature activation+0.698
nes
Tokennes
Feature activation+0.547
era
Token era
Feature activation+0.109
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
them
Token them
Feature activation+0.000
emerge
Token emerge
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
two
Token two
Feature activation+0.900
-
Token-
Feature activation+0.517
hour
Tokenhour
Feature activation+1.112
discussion
Token discussion
Feature activation+0.451
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
emphasized
Token emphasized
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
his
Token his
Feature activation+0.000
Paris
Token Paris
Feature activation+0.695
Review
Token Review
Feature activation+1.235
interview
Token interview
Feature activation+0.000
,
Token,
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.372
CONTAINS 99.963%

aking
Tokenaking
Feature activation+0.000
away
Token away
Feature activation+0.000
outside
Token outside
Feature activation+0.000
Fen
Token Fen
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
place
Token place
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
if
Token if
Feature activation+0.000
ird
Tokenird
Feature activation+0.000
in
Token in
Feature activation+0.000
44
Token 44
Feature activation+0.000
B
Token B
Feature activation+0.000
ü
Tokenü
Feature activation+0.000
cher
Tokencher
Feature activation+0.000
n
Tokenn
Feature activation+0.000
von
Token von
Feature activation+0.000
18
Token 18
Feature activation+0.000
28
Token28
Feature activation+0.000
bis
Token bis
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
sung
Token sung
Feature activation+0.000
by
Token by
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
"
Token "
Feature activation+0.000
America
TokenAmerica
Feature activation+0.000
's
Token's
Feature activation+0.000
Got
Token Got
Feature activation+0.000
Talent
Token Talent
Feature activation+0.000
"
Token"
Feature activation+0.000
oc
Tokenoc
Feature activation+0.000
chini
Tokenchini
Feature activation+0.000
saw
Token saw
Feature activation+0.000
that
Token that
Feature activation+0.000
her
Token her
Feature activation+0.000
wax
Token wax
Feature activation+0.000
worms
Tokenworms
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
from
Tokenfrom
Feature activation+0.000
a
Token a
Feature activation+0.000
different
Token different
Feature activation+0.000
Chris
TokenChris
Feature activation+0.000
Dixon
Token Dixon
Feature activation+0.000
said
Token said
Feature activation+0.000
10
Token 10
Feature activation+0.000
million
Token million
Feature activation+0.000
users
Token users
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
1
Token 1
Feature activation+0.000
million
Token million
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 8 in H8.7: (feature 22746)

TOP ACTIVATIONS
MAX = 2.807

her
Token her
Feature activation+1.152
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
University
Token University
Feature activation+0.000
failed
Token failed
Feature activation+0.000
her
Token her
Feature activation+2.807
.
Token.
Feature activation+0.000
D
Token D
Feature activation+0.000
CH
TokenCH
Feature activation+0.000
Regional
Token Regional
Feature activation+0.000
Medical
Token Medical
Feature activation+0.000
it
Token it
Feature activation+0.000
ever
Token ever
Feature activation+0.000
occurs
Token occurs
Feature activation+0.000
to
Token to
Feature activation+0.000
any
Token any
Feature activation+1.942
of
Token of
Feature activation+2.237
their
Token their
Feature activation+1.482
more
Token more
Feature activation+1.184
rebellious
Token rebellious
Feature activation+0.048
members
Token members
Feature activation+0.722
.
Token.
Feature activation+0.000
always
Token always
Feature activation+0.000
come
Token come
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
haunt
Token haunt
Feature activation+0.501
draft
Token draft
Feature activation+2.115
grad
Token grad
Feature activation+0.430
ers
Tokeners
Feature activation+1.911
like
Token like
Feature activation+0.295
myself
Token myself
Feature activation+0.516
.
Token.
Feature activation+0.000
easy
Token easy
Feature activation+0.000
on
Token on
Feature activation+0.000
y
Token y
Feature activation+1.135
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.545
all
Tokenall
Feature activation+2.094
with
Token with
Feature activation+0.000
Stub
Token Stub
Feature activation+0.000
bies
Tokenbies
Feature activation+0.000
,
Token,
Feature activation+0.000
grow
Token grow
Feature activation+0.000
federal
Token federal
Feature activation+0.000
level
Token level
Feature activation+0.000
and
Token and
Feature activation+0.000
forced
Token forced
Feature activation+0.000
on
Token on
Feature activation+0.000
every
Token every
Feature activation+1.943
American
Token American
Feature activation+1.053
community
Token community
Feature activation+0.129
,
Token,
Feature activation+0.000
whether
Token whether
Feature activation+0.000
by
Token by
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.000
ever
Token ever
Feature activation+0.000
occurs
Token occurs
Feature activation+0.000
to
Token to
Feature activation+0.000
any
Token any
Feature activation+1.942
of
Token of
Feature activation+2.237
their
Token their
Feature activation+1.482
more
Token more
Feature activation+1.184
rebellious
Token rebellious
Feature activation+0.048
members
Token members
Feature activation+0.722
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
haunt
Token haunt
Feature activation+0.501
draft
Token draft
Feature activation+2.115
grad
Token grad
Feature activation+0.430
ers
Tokeners
Feature activation+1.911
like
Token like
Feature activation+0.295
myself
Token myself
Feature activation+0.516
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
fail
Token fail
Feature activation+0.000
the
Token the
Feature activation+1.910
workers
Token workers
Feature activation+1.626
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
's
Token's
Feature activation+0.843
critics
Token critics
Feature activation+0.000
of
Token of
Feature activation+0.000
picking
Token picking
Feature activation+0.000
on
Token on
Feature activation+0.007
members
Token members
Feature activation+1.845
of
Token of
Feature activation+1.048
staff
Token staff
Feature activation+0.682
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
same
Token same
Feature activation+0.000
attributes
Token attributes
Feature activation+0.000
are
Token are
Feature activation+0.000
turned
Token turned
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+1.809
ret
Token ret
Feature activation+0.378
aking
Tokenaking
Feature activation+1.148
CT
Token CT
Feature activation+0.000
s
Tokens
Feature activation+0.325
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
Rin
Token Rin
Feature activation+0.149
ique
Tokenique
Feature activation+0.571
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.235
s
Tokens
Feature activation+1.783
daughter
Token daughter
Feature activation+1.045
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
bir
Token bir
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
worst
Token worst
Feature activation+0.000
in
Token in
Feature activation+0.238
both
Token both
Feature activation+1.707
.
Token.
Feature activation+0.000
Did
Token Did
Feature activation+0.000
Kanye
Token Kanye
Feature activation+0.196
blatantly
Token blatantly
Feature activation+0.000
ignore
Token ignore
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
work
Token work
Feature activation+0.000
ahead
Token ahead
Feature activation+0.000
of
Token of
Feature activation+1.101
them
Token them
Feature activation+1.695
tonight
Token tonight
Feature activation+0.025
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
she
Token she
Feature activation+0.000
Pro
Token Pro
Feature activation+0.000
Bowl
Token Bowl
Feature activation+0.000
spot
Token spot
Feature activation+0.000
away
Token away
Feature activation+0.000
from
Token from
Feature activation+0.310
a
Token a
Feature activation+1.691
Josh
Token Josh
Feature activation+0.000
C
Token C
Feature activation+0.000
rib
Tokenrib
Feature activation+0.000
bs
Tokenbs
Feature activation+0.259
.
Token.
Feature activation+0.000
moment
Token moment
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.000
cheated
Token cheated
Feature activation+0.000
on
Token on
Feature activation+0.154
the
Token the
Feature activation+1.661
woman
Token woman
Feature activation+1.331
and
Token and
Feature activation+0.000
disappeared
Token disappeared
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
system
Token system
Feature activation+0.000
failed
Token failed
Feature activation+0.000
the
Token the
Feature activation+1.656
workers
Token workers
Feature activation+1.420
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
to
Token to
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
fail
Token fail
Feature activation+0.000
the
Token the
Feature activation+1.910
workers
Token workers
Feature activation+1.626
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
UFC
Token UFC
Feature activation+0.000
courts
Token courts
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
collect
Token collect
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+1.609
regime
Token regime
Feature activation+0.000
that
Token that
Feature activation+0.000
uses
Token uses
Feature activation+0.000
front
Token front
Feature activation+0.000
companies
Token companies
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
it
Token it
Feature activation+0.000
easier
Token easier
Feature activation+0.000
on
Token on
Feature activation+0.070
you
Token you
Feature activation+1.573
--
Token --
Feature activation+0.000
a
Token a
Feature activation+0.000
recent
Token recent
Feature activation+0.000
email
Token email
Feature activation+0.000
copied
Token copied
Feature activation+0.000
to
Token to
Feature activation+0.000
Ms
Token Ms
Feature activation+0.812
Mal
Token Mal
Feature activation+0.464
hot
Tokenhot
Feature activation+0.000
ra
Tokenra
Feature activation+1.222
's
Token's
Feature activation+1.550
team
Token team
Feature activation+0.104
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000

Top DFA by src position
MAX = 3.289

failed
Token failed
Feature activation+0.275
Top resid features:
her
Token her
Feature activation+0.010
Top resid features:
.
Token.
Feature activation-0.057
Top resid features:
The
Token The
Feature activation+0.008
Top resid features:
University
Token University
Feature activation+0.029
Top resid features:
failed
Token failed
Feature activation+3.289
Top resid features:
her
Token her
Feature activation+0.059
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
D
Token D
Feature activation+0.000
Top resid features:
CH
TokenCH
Feature activation+0.000
Top resid features:
Regional
Token Regional
Feature activation+0.000
Top resid features:
idea
Token idea
Feature activation+0.004
Top resid features:
if
Token if
Feature activation+0.028
Top resid features:
it
Token it
Feature activation+0.013
Top resid features:
ever
Token ever
Feature activation+0.103
Top resid features:
occurs
Token occurs
Feature activation+0.064
Top resid features:
to
Token to
Feature activation+2.212
Top resid features:
any
Token any
Feature activation+0.390
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
rebellious
Token rebellious
Feature activation+0.000
Top resid features:
Those
TokenThose
Feature activation+0.005
Top resid features:
always
Token always
Feature activation+0.003
Top resid features:
come
Token come
Feature activation+0.007
Top resid features:
back
Token back
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.092
Top resid features:
haunt
Token haunt
Feature activation+2.679
Top resid features:
draft
Token draft
Feature activation+0.012
Top resid features:
grad
Token grad
Feature activation+0.000
Top resid features:
ers
Tokeners
Feature activation+0.000
Top resid features:
like
Token like
Feature activation+0.000
Top resid features:
myself
Token myself
Feature activation+0.000
Top resid features:
try
Token try
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
make
Token make
Feature activation+0.001
Top resid features:
it
Token it
Feature activation+0.005
Top resid features:
easy
Token easy
Feature activation+0.041
Top resid features:
on
Token on
Feature activation+2.661
Top resid features:
y
Token y
Feature activation+0.034
Top resid features:
âĢ
TokenâĢ
Feature activation+0.024
Top resid features:
Ļ
TokenĻ
Feature activation+0.026
Top resid features:
all
Tokenall
Feature activation+0.022
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
federal
Token federal
Feature activation+0.034
Top resid features:
level
Token level
Feature activation+0.024
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
forced
Token forced
Feature activation+0.004
Top resid features:
on
Token on
Feature activation+2.408
Top resid features:
every
Token every
Feature activation+0.071
Top resid features:
American
Token American
Feature activation+0.000
Top resid features:
community
Token community
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
whether
Token whether
Feature activation+0.000
Top resid features:
idea
Token idea
Feature activation+0.007
Top resid features:
if
Token if
Feature activation+0.039
Top resid features:
it
Token it
Feature activation+0.006
Top resid features:
ever
Token ever
Feature activation+0.047
Top resid features:
occurs
Token occurs
Feature activation+0.147
Top resid features:
to
Token to
Feature activation+2.234
Top resid features:
any
Token any
Feature activation+0.068
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
rebellious
Token rebellious
Feature activation+0.000
Top resid features:
Those
TokenThose
Feature activation-0.001
Top resid features:
always
Token always
Feature activation+0.013
Top resid features:
come
Token come
Feature activation+0.015
Top resid features:
back
Token back
Feature activation+0.021
Top resid features:
to
Token to
Feature activation+0.202
Top resid features:
haunt
Token haunt
Feature activation+2.329
Top resid features:
draft
Token draft
Feature activation+0.047
Top resid features:
grad
Token grad
Feature activation+0.025
Top resid features:
ers
Tokeners
Feature activation+0.009
Top resid features:
like
Token like
Feature activation+0.000
Top resid features:
myself
Token myself
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.002
Top resid features:
going
Token going
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.036
Top resid features:
continue
Token continue
Feature activation-0.029
Top resid features:
to
Token to
Feature activation-0.015
Top resid features:
fail
Token fail
Feature activation+2.449
Top resid features:
the
Token the
Feature activation+0.067
Top resid features:
workers
Token workers
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
Corbyn
Token Corbyn
Feature activation+0.020
Top resid features:
's
Token's
Feature activation+0.001
Top resid features:
critics
Token critics
Feature activation+0.010
Top resid features:
of
Token of
Feature activation+0.022
Top resid features:
picking
Token picking
Feature activation+0.022
Top resid features:
on
Token on
Feature activation+2.478
Top resid features:
members
Token members
Feature activation+0.015
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
staff
Token staff
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
same
Token same
Feature activation+0.011
Top resid features:
attributes
Token attributes
Feature activation+0.034
Top resid features:
are
Token are
Feature activation+0.014
Top resid features:
turned
Token turned
Feature activation+0.011
Top resid features:
against
Token against
Feature activation+2.250
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
ret
Token ret
Feature activation+0.000
Top resid features:
aking
Tokenaking
Feature activation+0.000
Top resid features:
CT
Token CT
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
wasn
Token wasn
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.012
Top resid features:
Ļ
TokenĻ
Feature activation+0.006
Top resid features:
t
Tokent
Feature activation+0.002
Top resid features:
lost
Token lost
Feature activation-0.008
Top resid features:
on
Token on
Feature activation+2.476
Top resid features:
Rin
Token Rin
Feature activation+0.038
Top resid features:
ique
Tokenique
Feature activation+0.024
Top resid features:
âĢ
TokenâĢ
Feature activation+0.010
Top resid features:
Ļ
TokenĻ
Feature activation+0.014
Top resid features:
s
Tokens
Feature activation-0.000
Top resid features:
and
Token and
Feature activation+0.024
Top resid features:
bringing
Token bringing
Feature activation-0.004
Top resid features:
out
Token out
Feature activation-0.004
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
worst
Token worst
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+2.464
Top resid features:
both
Token both
Feature activation+0.014
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Did
Token Did
Feature activation+0.000
Top resid features:
Kanye
Token Kanye
Feature activation+0.000
Top resid features:
blatantly
Token blatantly
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.007
Top resid features:
lot
Token lot
Feature activation-0.003
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
work
Token work
Feature activation+0.053
Top resid features:
ahead
Token ahead
Feature activation+0.462
Top resid features:
of
Token of
Feature activation+1.893
Top resid features:
them
Token them
Feature activation+0.038
Top resid features:
tonight
Token tonight
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
Pro
Token Pro
Feature activation+0.016
Top resid features:
Bowl
Token Bowl
Feature activation+0.047
Top resid features:
spot
Token spot
Feature activation+0.052
Top resid features:
away
Token away
Feature activation+0.029
Top resid features:
from
Token from
Feature activation+2.281
Top resid features:
a
Token a
Feature activation+0.038
Top resid features:
Josh
Token Josh
Feature activation+0.000
Top resid features:
C
Token C
Feature activation+0.000
Top resid features:
rib
Tokenrib
Feature activation+0.000
Top resid features:
bs
Tokenbs
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.003
Top resid features:
moment
Token moment
Feature activation+0.014
Top resid features:
his
Token his
Feature activation-0.009
Top resid features:
father
Token father
Feature activation+0.123
Top resid features:
cheated
Token cheated
Feature activation+0.111
Top resid features:
on
Token on
Feature activation+2.218
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
woman
Token woman
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
disappeared
Token disappeared
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
ľ
Tokenľ
Feature activation-0.001
Top resid features:
The
TokenThe
Feature activation+0.003
Top resid features:
system
Token system
Feature activation+0.075
Top resid features:
failed
Token failed
Feature activation+2.199
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
workers
Token workers
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:
it
Token it
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
going
Token going
Feature activation+0.013
Top resid features:
to
Token to
Feature activation+0.022
Top resid features:
continue
Token continue
Feature activation-0.027
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
fail
Token fail
Feature activation+1.983
Top resid features:
the
Token the
Feature activation+0.484
Top resid features:
workers
Token workers
Feature activation+0.042
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
Canadian
Token Canadian
Feature activation+0.015
Top resid features:
courts
Token courts
Feature activation+0.008
Top resid features:
trying
Token trying
Feature activation+0.012
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
collect
Token collect
Feature activation+0.003
Top resid features:
from
Token from
Feature activation+2.199
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
regime
Token regime
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
uses
Token uses
Feature activation+0.000
Top resid features:
front
Token front
Feature activation+0.000
Top resid features:
filing
Token filing
Feature activation-0.002
Top resid features:
to
Token to
Feature activation+0.016
Top resid features:
make
Token make
Feature activation+0.005
Top resid features:
it
Token it
Feature activation+0.002
Top resid features:
easier
Token easier
Feature activation+0.047
Top resid features:
on
Token on
Feature activation+2.142
Top resid features:
you
Token you
Feature activation+0.021
Top resid features:
--
Token --
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
recent
Token recent
Feature activation+0.000
Top resid features:
email
Token email
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.005
Top resid features:
job
Token job
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
had
Token had
Feature activation+0.008
Top resid features:
apologised
Token apologised
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+2.179
Top resid features:
Ms
Token Ms
Feature activation+0.004
Top resid features:
Mal
Token Mal
Feature activation-0.002
Top resid features:
hot
Tokenhot
Feature activation+0.018
Top resid features:
ra
Tokenra
Feature activation-0.008
Top resid features:
's
Token's
Feature activation+0.019
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.02

Head 2: 0.04

Head 3: 0.04

Head 4: 0.08

Head 5: 0.10

Head 6: 0.02

Head 7: 0.50

Head 8: 0.05

Head 9: 0.03

Head 10: 0.07

Head 11: 0.02

Positive logits

passers2.28

gans2.27

occupants2.27

guys2.24

guy2.23

him2.21

devs2.20

unsuspecting2.18

players2.17

players2.17

teammates2.16

subordinates2.12

fellow2.10

omever2.08

drinkers2.07

wearer2.06

owners2.05

attackers2.04

practitioners2.04

erers2.03

Negative logits

autical-1.62

cess-1.61

codes-1.61

ailability-1.58

omial-1.56

ramid-1.55

ruction-1.54

idelines-1.54

annual-1.52

Minimum-1.52

irtual-1.51

urgical-1.50

resize-1.46

cription-1.46

punishments-1.46

accessible-1.45

estic-1.45

flu-1.45

ê-1.44

LCS-1.43

INTERVAL 2.526 - 2.807
CONTAINS 0.000%

her
Token her
Feature activation+1.152
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
University
Token University
Feature activation+0.000
failed
Token failed
Feature activation+0.000
her
Token her
Feature activation+2.807
.
Token.
Feature activation+0.000
D
Token D
Feature activation+0.000
CH
TokenCH
Feature activation+0.000
Regional
Token Regional
Feature activation+0.000
Medical
Token Medical
Feature activation+0.000

INTERVAL 2.246 - 2.526
CONTAINS 0.000%

INTERVAL 1.965 - 2.246
CONTAINS 0.000%

it
Token it
Feature activation+0.000
ever
Token ever
Feature activation+0.000
occurs
Token occurs
Feature activation+0.000
to
Token to
Feature activation+0.000
any
Token any
Feature activation+1.942
of
Token of
Feature activation+2.237
their
Token their
Feature activation+1.482
more
Token more
Feature activation+1.184
rebellious
Token rebellious
Feature activation+0.048
members
Token members
Feature activation+0.722
.
Token.
Feature activation+0.000
easy
Token easy
Feature activation+0.000
on
Token on
Feature activation+0.000
y
Token y
Feature activation+1.135
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.545
all
Tokenall
Feature activation+2.094
with
Token with
Feature activation+0.000
Stub
Token Stub
Feature activation+0.000
bies
Tokenbies
Feature activation+0.000
,
Token,
Feature activation+0.000
grow
Token grow
Feature activation+0.000
always
Token always
Feature activation+0.000
come
Token come
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
haunt
Token haunt
Feature activation+0.501
draft
Token draft
Feature activation+2.115
grad
Token grad
Feature activation+0.430
ers
Tokeners
Feature activation+1.911
like
Token like
Feature activation+0.295
myself
Token myself
Feature activation+0.516
.
Token.
Feature activation+0.000

INTERVAL 1.684 - 1.965
CONTAINS 0.001%

going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
fail
Token fail
Feature activation+0.000
the
Token the
Feature activation+1.910
workers
Token workers
Feature activation+1.626
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
federal
Token federal
Feature activation+0.000
level
Token level
Feature activation+0.000
and
Token and
Feature activation+0.000
forced
Token forced
Feature activation+0.000
on
Token on
Feature activation+0.000
every
Token every
Feature activation+1.943
American
Token American
Feature activation+1.053
community
Token community
Feature activation+0.129
,
Token,
Feature activation+0.000
whether
Token whether
Feature activation+0.000
by
Token by
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
work
Token work
Feature activation+0.000
ahead
Token ahead
Feature activation+0.000
of
Token of
Feature activation+1.101
them
Token them
Feature activation+1.695
tonight
Token tonight
Feature activation+0.025
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
she
Token she
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.000
ever
Token ever
Feature activation+0.000
occurs
Token occurs
Feature activation+0.000
to
Token to
Feature activation+0.000
any
Token any
Feature activation+1.942
of
Token of
Feature activation+2.237
their
Token their
Feature activation+1.482
more
Token more
Feature activation+1.184
rebellious
Token rebellious
Feature activation+0.048
members
Token members
Feature activation+0.722
on
Token on
Feature activation+0.000
Rin
Token Rin
Feature activation+0.149
ique
Tokenique
Feature activation+0.571
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.235
s
Tokens
Feature activation+1.783
daughter
Token daughter
Feature activation+1.045
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
bir
Token bir
Feature activation+0.000

INTERVAL 1.404 - 1.684
CONTAINS 0.002%

it
Token it
Feature activation+0.000
easy
Token easy
Feature activation+0.000
on
Token on
Feature activation+0.000
y
Token y
Feature activation+1.135
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.545
all
Tokenall
Feature activation+2.094
with
Token with
Feature activation+0.000
Stub
Token Stub
Feature activation+0.000
bies
Tokenbies
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
fail
Token fail
Feature activation+0.000
the
Token the
Feature activation+1.910
workers
Token workers
Feature activation+1.626
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
UFC
Token UFC
Feature activation+0.000
altar
Token altar
Feature activation+0.000
of
Token of
Feature activation+0.000
deficit
Token deficit
Feature activation+0.000
reduction
Token reduction
Feature activation+0.000
than
Token than
Feature activation+0.000
our
Token our
Feature activation+1.447
federal
Token federal
Feature activation+0.785
workers
Token workers
Feature activation+0.235
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
ever
Token ever
Feature activation+0.000
occurs
Token occurs
Feature activation+0.000
to
Token to
Feature activation+0.000
any
Token any
Feature activation+1.942
of
Token of
Feature activation+2.237
their
Token their
Feature activation+1.482
more
Token more
Feature activation+1.184
rebellious
Token rebellious
Feature activation+0.048
members
Token members
Feature activation+0.722
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
courts
Token courts
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
collect
Token collect
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+1.609
regime
Token regime
Feature activation+0.000
that
Token that
Feature activation+0.000
uses
Token uses
Feature activation+0.000
front
Token front
Feature activation+0.000
companies
Token companies
Feature activation+0.000

INTERVAL 1.123 - 1.404
CONTAINS 0.008%

and
Token and
Feature activation+0.000
foster
Token foster
Feature activation+0.000
it
Token it
Feature activation+0.000
in
Token in
Feature activation+0.000
places
Token places
Feature activation+0.652
like
Token like
Feature activation+1.191
Venezuela
Token Venezuela
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.000
not
Token not
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
blame
Token blame
Feature activation+0.000
them
Token them
Feature activation+1.196
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
what
Token what
Feature activation+0.000
Jennings
Token Jennings
Feature activation+0.000
see
Token see
Feature activation+0.000
in
Token in
Feature activation+0.113
P
Token P
Feature activation+0.554
onder
Tokenonder
Feature activation+1.147
after
Token after
Feature activation+0.000
his
Token his
Feature activation+0.000
years
Token years
Feature activation+0.000
catching
Token catching
Feature activation+0.000
passes
Token passes
Feature activation+0.000
are
Token are
Feature activation+0.000
turned
Token turned
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+1.809
ret
Token ret
Feature activation+0.378
aking
Tokenaking
Feature activation+1.148
CT
Token CT
Feature activation+0.000
s
Tokens
Feature activation+0.325
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
responsibilities
Token responsibilities
Feature activation+0.000
.
Token.
Feature activation+0.000
Good
Token Good
Feature activation+0.000
luck
Token luck
Feature activation+0.000
to
Token to
Feature activation+0.000
all
Token all
Feature activation+1.131
the
Token the
Feature activation+0.881
men
Token men
Feature activation+0.380
in
Token in
Feature activation+0.000
question
Token question
Feature activation+0.000
!
Token!
Feature activation+0.000

INTERVAL 0.842 - 1.123
CONTAINS 0.026%

that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
or
Token or
Feature activation+0.000
anyone
Token anyone
Feature activation+0.303
else
Token else
Feature activation+0.928
âĢĵ
Token âĢĵ
Feature activation+0.000
have
Token have
Feature activation+0.000
available
Token available
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
federal
Token federal
Feature activation+0.000
courts
Token courts
Feature activation+0.000
have
Token have
Feature activation+0.000
ruled
Token ruled
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.877
victims
Token victims
Feature activation+0.533
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
Iran
Token Iran
Feature activation+0.000
has
Token has
Feature activation+0.000
who
Token who
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
with
Token with
Feature activation+0.000
Frances
Token Frances
Feature activation+0.184
co
Tokenco
Feature activation+1.043
since
Token since
Feature activation+0.000
he
Token he
Feature activation+0.000
began
Token began
Feature activation+0.000
his
Token his
Feature activation+0.000
collection
Token collection
Feature activation+0.000
level
Token level
Feature activation+0.000
and
Token and
Feature activation+0.000
forced
Token forced
Feature activation+0.000
on
Token on
Feature activation+0.000
every
Token every
Feature activation+1.943
American
Token American
Feature activation+1.053
community
Token community
Feature activation+0.129
,
Token,
Feature activation+0.000
whether
Token whether
Feature activation+0.000
by
Token by
Feature activation+0.000
activist
Token activist
Feature activation+0.000
airport
Token airport
Feature activation+0.000
but
Token but
Feature activation+0.000
have
Token have
Feature activation+0.000
released
Token released
Feature activation+0.000
few
Token few
Feature activation+0.458
other
Token other
Feature activation+0.863
details
Token details
Feature activation+0.000
.
Token.
Feature activation+0.000
An
Token An
Feature activation+0.000
11
Token 11
Feature activation+0.000
th
Tokenth
Feature activation+0.000

INTERVAL 0.561 - 0.842
CONTAINS 0.087%

Kara
Token Kara
Feature activation+0.685
is
Token is
Feature activation+0.000
happy
Token happy
Feature activation+0.000
,
Token,
Feature activation+0.000
except
Token except
Feature activation+0.000
her
Token her
Feature activation+0.717
as
Token as
Feature activation+0.000
she
Token she
Feature activation+0.000
is
Token is
Feature activation+0.000
left
Token left
Feature activation+0.000
with
Token with
Feature activation+0.000
-
Token-
Feature activation+0.000
0
Token0
Feature activation+0.000
vote
Token vote
Feature activation+0.000
to
Token to
Feature activation+0.000
expel
Token expel
Feature activation+0.113
Singapore
Token Singapore
Feature activation+0.652
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
bounce
Token bounce
Feature activation+0.000
interactions
Token interactions
Feature activation+0.000
off
Token off
Feature activation+0.610
of
Token of
Feature activation+1.036
each
Token each
Feature activation+0.676
other
Token other
Feature activation+0.301
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Use
TokenUse
Feature activation+0.000
and
Token and
Feature activation+0.000
"
Token "
Feature activation+0.000
you
Tokenyou
Feature activation+0.000
always
Token always
Feature activation+0.000
hurt
Token hurt
Feature activation+0.000
the
Token the
Feature activation+0.582
ones
Token ones
Feature activation+0.000
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.000
closest
Token closest
Feature activation+0.000
to
Token to
Feature activation+0.000
not
Token not
Feature activation+0.000
seem
Token seem
Feature activation+0.000
like
Token like
Feature activation+0.000
much
Token much
Feature activation+0.000
to
Token to
Feature activation+0.000
one
Token one
Feature activation+0.709
person
Token person
Feature activation+0.509
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
every
Token every
Feature activation+0.000
little
Token little
Feature activation+0.000

INTERVAL 0.281 - 0.561
CONTAINS 0.288%

coverage
Token coverage
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.756
New
Token New
Feature activation+0.408
York
Token York
Feature activation+0.302
businessman
Token businessman
Feature activation+0.306
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
He
TokenHe
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
sought
Token sought
Feature activation+0.000
permission
Token permission
Feature activation+0.000
to
Token to
Feature activation+0.000
interview
Token interview
Feature activation+0.000
an
Token an
Feature activation+0.517
FBI
Token FBI
Feature activation+0.000
informant
Token informant
Feature activation+0.000
who
Token who
Feature activation+0.000
helped
Token helped
Feature activation+0.000
agents
Token agents
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
whole
Token whole
Feature activation+0.000
thing
Token thing
Feature activation+0.000
is
Token is
Feature activation+0.078
the
Token the
Feature activation+0.430
person
Token person
Feature activation+0.000
selling
Token selling
Feature activation+0.000
the
Token the
Feature activation+0.000
drugs
Token drugs
Feature activation+0.000
,
Token,
Feature activation+0.000
have
Token have
Feature activation+0.000
we
Token we
Feature activation+0.000
lost
Token lost
Feature activation+0.000
faith
Token faith
Feature activation+0.000
in
Token in
Feature activation+0.000
Luis
Token Luis
Feature activation+0.461
Enrique
Token Enrique
Feature activation+0.554
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
worked
Token worked
Feature activation+0.000
out
Token out
Feature activation+0.000
with
Token with
Feature activation+0.000
Gl
Token Gl
Feature activation+0.399
end
Tokenend
Feature activation+0.145
ening
Tokenening
Feature activation+0.453
at
Token at
Feature activation+0.000
Bar
Token Bar
Feature activation+0.000
w
Tokenw
Feature activation+0.000

INTERVAL 0.000 - 0.281
CONTAINS 99.587%

better
Token better
Feature activation+0.000
cricket
Token cricket
Feature activation+0.000
than
Token than
Feature activation+0.000
them
Token them
Feature activation+0.147
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
A
Token A
Feature activation+0.000
person
Token person
Feature activation+0.000
writing
Token writing
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
report
Token report
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
police
Token police
Feature activation+0.000
station
Token station
Feature activation+0.000
was
Token was
Feature activation+0.000
being
Token being
Feature activation+0.000
the
Token the
Feature activation+0.000
substantive
Token substantive
Feature activation+0.000
-
Token -
Feature activation+0.000
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+0.000
rhetorical
Token rhetorical
Feature activation+0.000
-
Token -
Feature activation+0.000
differences
Token differences
Feature activation+0.000
as
Token as
Feature activation+0.000
slight
Token slight
Feature activation+0.000
.
Token.
Feature activation+0.000
s
Tokens
Feature activation+0.000
super
Token super
Feature activation+0.000
charged
Tokencharged
Feature activation+0.000
politics
Token politics
Feature activation+0.000
,
Token,
Feature activation+0.000
mean
Token mean
Feature activation+0.000
that
Token that
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
chosen
Token chosen
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
one
Token one
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.097
New
Token New
Feature activation+0.254
Democrats
Token Democrats
Feature activation+0.022
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+0.000
provincial
Token provincial
Feature activation+0.000
cousins
Token cousins
Feature activation+0.000
lost
Token lost
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 H8.7: (feature 8081)

TOP ACTIVATIONS
MAX = 4.371

R
TokenR
Feature activation+0.000
iding
Tokeniding
Feature activation+3.789
H
TokenH
Feature activation+0.000
ood
Tokenood
Feature activation+2.903
y
Tokeny
Feature activation+2.449
's
Token's
Feature activation+4.371
own
Token own
Feature activation+3.753
creation
Token creation
Feature activation+2.399
haha
Token haha
Feature activation+0.000
Inside
Token Inside
Feature activation+0.000
was
Token was
Feature activation+0.000
p
Tokenp
Feature activation+0.000
aul
Tokenaul
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
of
Token of
Feature activation+0.000
my
Token my
Feature activation+4.315
generation
Token generation
Feature activation+1.545
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
of
Token of
Feature activation+1.014
my
Token my
Feature activation+2.116
was
Token was
Feature activation+0.000
of
Token of
Feature activation+0.885
Little
Token Little
Feature activation+1.285
Red
TokenRed
Feature activation+0.277
R
TokenR
Feature activation+0.000
iding
Tokeniding
Feature activation+3.789
H
TokenH
Feature activation+0.000
ood
Tokenood
Feature activation+2.903
y
Tokeny
Feature activation+2.449
's
Token's
Feature activation+4.371
own
Token own
Feature activation+3.753
iding
Tokeniding
Feature activation+3.789
H
TokenH
Feature activation+0.000
ood
Tokenood
Feature activation+2.903
y
Tokeny
Feature activation+2.449
's
Token's
Feature activation+4.371
own
Token own
Feature activation+3.753
creation
Token creation
Feature activation+2.399
haha
Token haha
Feature activation+0.000
Inside
Token Inside
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
rock
Token rock
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
of
Token of
Feature activation+0.156
the
Token the
Feature activation+3.147
same
Token same
Feature activation+3.689
composition
Token composition
Feature activation+2.098
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
's
Token's
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
not
Token not
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+3.640
opinion
Token opinion
Feature activation+2.607
that
Token that
Feature activation+0.000
Comey
Token Comey
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
their
Token their
Feature activation+0.000
partners
Token partners
Feature activation+0.000
than
Token than
Feature activation+0.000
people
Token people
Feature activation+0.000
of
Token of
Feature activation+0.000
other
Token other
Feature activation+3.629
sexual
Token sexual
Feature activation+2.864
orient
Token orient
Feature activation+1.131
ations
Tokenations
Feature activation+0.932
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Im
Token Im
Feature activation+0.000
gur
Tokengur
Feature activation+0.000
or
Token or
Feature activation+0.000
something
Token something
Feature activation+0.000
of
Token of
Feature activation+0.203
that
Token that
Feature activation+3.596
nature
Token nature
Feature activation+1.969
.,
Token.,
Feature activation+0.000
this
Token this
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
ircraft
Tokenircraft
Feature activation+0.000
of
Token of
Feature activation+0.000
comparable
Token comparable
Feature activation+0.104
role
Token role
Feature activation+1.593
,
Token,
Feature activation+0.218
configuration
Token configuration
Feature activation+3.565
and
Token and
Feature activation+2.119
era
Token era
Feature activation+2.420
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Related
TokenRelated
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.247
very
Token very
Feature activation+3.384
different
Token different
Feature activation+3.513
kind
Token kind
Feature activation+0.222
.
Token.
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.000
goes
Token goes
Feature activation+0.000
wrong
Token wrong
Feature activation+0.000
were
Token were
Feature activation+0.000
white
Token white
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
of
Token of
Feature activation+0.135
draft
Token draft
Feature activation+3.385
age
Token age
Feature activation+2.644
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Christian
Token Christian
Feature activation+0.000
,
Token,
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
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.247
very
Token very
Feature activation+3.384
different
Token different
Feature activation+3.513
kind
Token kind
Feature activation+0.222
.
Token.
Feature activation+0.000
Whatever
Token Whatever
Feature activation+0.000
goes
Token goes
Feature activation+0.000
to
Token to
Feature activation+0.000
persons
Token persons
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+2.261
same
Token same
Feature activation+3.247
biological
Token biological
Feature activation+3.289
sex
Token sex
Feature activation+1.049
,
Token,
Feature activation+0.000
regardless
Token regardless
Feature activation+0.000
of
Token of
Feature activation+0.000
gender
Token gender
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
do
Token do
Feature activation+0.000
others
Token others
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+3.274
same
Token same
Feature activation+2.869
model
Token model
Feature activation+2.722
in
Token in
Feature activation+0.000
Newark
Token Newark
Feature activation+0.000
,
Token,
Feature activation+0.000
assigned
Token assigned
Feature activation+0.000
to
Token to
Feature activation+0.000
persons
Token persons
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+2.261
same
Token same
Feature activation+3.247
biological
Token biological
Feature activation+3.289
sex
Token sex
Feature activation+1.049
,
Token,
Feature activation+0.000
regardless
Token regardless
Feature activation+0.000
of
Token of
Feature activation+0.000
res
Token res
Feature activation+0.000
sc
Tokensc
Feature activation+0.000
ue
Tokenue
Feature activation+0.000
people
Token people
Feature activation+0.000
of
Token of
Feature activation+0.217
world
Token world
Feature activation+3.172
before
Token before
Feature activation+0.000
all
Token all
Feature activation+0.000
things
Token things
Feature activation+0.000
s
Tokens
Feature activation+0.000
end
Token end
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
of
Token of
Feature activation+0.314
a
Token a
Feature activation+1.247
green
Token green
Feature activation+1.903
apple
Token apple
Feature activation+3.154
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.068
became
Token became
Feature activation+0.000
the
Token the
Feature activation+0.000
basis
Token basis
Feature activation+0.000
lunar
Token lunar
Feature activation+0.000
rock
Token rock
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
of
Token of
Feature activation+0.156
the
Token the
Feature activation+3.147
same
Token same
Feature activation+3.689
composition
Token composition
Feature activation+2.098
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
humans
Token humans
Feature activation+0.000
dropping
Token dropping
Feature activation+0.000
balls
Token balls
Feature activation+0.000
of
Token of
Feature activation+0.572
markedly
Token markedly
Feature activation+2.794
different
Token different
Feature activation+3.120
weights
Token weights
Feature activation+1.374
show
Token show
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
had
Token had
Feature activation+0.000
ever
Token ever
Feature activation+0.000
said
Token said
Feature activation+0.000
anything
Token anything
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+2.946
sort
Token sort
Feature activation+0.000
involving
Token involving
Feature activation+0.000
race
Token race
Feature activation+0.000
.
Token.
Feature activation+0.000
Nonetheless
Token Nonetheless
Feature activation+0.000

Top DFA by src position
MAX = 5.185

which
Token which
Feature activation+0.012
Top resid features:
I
Token I
Feature activation+0.008
Top resid features:
'm
Token'm
Feature activation+0.008
Top resid features:
assuming
Token assuming
Feature activation+0.023
Top resid features:
was
Token was
Feature activation-0.020
Top resid features:
of
Token of
Feature activation+5.185
Top resid features:
Little
Token Little
Feature activation+0.004
Top resid features:
Red
TokenRed
Feature activation+0.027
Top resid features:
R
TokenR
Feature activation+0.009
Top resid features:
iding
Tokeniding
Feature activation+0.024
Top resid features:
H
TokenH
Feature activation-0.000
Top resid features:
ander
Tokenander
Feature activation-0.003
Top resid features:
p
Tokenp
Feature activation+0.005
Top resid features:
aul
Tokenaul
Feature activation+0.002
Top resid features:
was
Token was
Feature activation-0.016
Top resid features:
not
Token not
Feature activation-0.018
Top resid features:
of
Token of
Feature activation+5.183
Top resid features:
my
Token my
Feature activation+0.311
Top resid features:
generation
Token generation
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:
of
Token of
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.011
Top resid features:
I
Token I
Feature activation+0.009
Top resid features:
'm
Token'm
Feature activation+0.018
Top resid features:
assuming
Token assuming
Feature activation+0.022
Top resid features:
was
Token was
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+4.755
Top resid features:
Little
Token Little
Feature activation+0.011
Top resid features:
Red
TokenRed
Feature activation-0.003
Top resid features:
R
TokenR
Feature activation+0.006
Top resid features:
iding
Tokeniding
Feature activation+0.011
Top resid features:
H
TokenH
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.002
Top resid features:
I
Token I
Feature activation+0.008
Top resid features:
'm
Token'm
Feature activation+0.011
Top resid features:
assuming
Token assuming
Feature activation+0.015
Top resid features:
was
Token was
Feature activation-0.022
Top resid features:
of
Token of
Feature activation+4.463
Top resid features:
Little
Token Little
Feature activation+0.002
Top resid features:
Red
TokenRed
Feature activation+0.016
Top resid features:
R
TokenR
Feature activation+0.005
Top resid features:
iding
Tokeniding
Feature activation+0.027
Top resid features:
H
TokenH
Feature activation+0.002
Top resid features:
)
Token)
Feature activation+0.005
Top resid features:
lunar
Token lunar
Feature activation-0.020
Top resid features:
rock
Token rock
Feature activation+0.037
Top resid features:
is
Token is
Feature activation+0.024
Top resid features:
not
Token not
Feature activation+0.064
Top resid features:
of
Token of
Feature activation+3.738
Top resid features:
the
Token the
Feature activation+0.764
Top resid features:
same
Token same
Feature activation+0.244
Top resid features:
composition
Token composition
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:
he
Token he
Feature activation+0.019
Top resid features:
âĢ
TokenâĢ
Feature activation+0.007
Top resid features:
Ļ
TokenĻ
Feature activation-0.031
Top resid features:
s
Tokens
Feature activation+0.039
Top resid features:
not
Token not
Feature activation-0.082
Top resid features:
of
Token of
Feature activation+4.607
Top resid features:
the
Token the
Feature activation+0.236
Top resid features:
opinion
Token opinion
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
Comey
Token Comey
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.002
Top resid features:
their
Token their
Feature activation-0.002
Top resid features:
partners
Token partners
Feature activation+0.005
Top resid features:
than
Token than
Feature activation+0.101
Top resid features:
people
Token people
Feature activation+0.182
Top resid features:
of
Token of
Feature activation+3.759
Top resid features:
other
Token other
Feature activation+0.520
Top resid features:
sexual
Token sexual
Feature activation+0.000
Top resid features:
orient
Token orient
Feature activation+0.000
Top resid features:
ations
Tokenations
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.043
Top resid features:
Im
Token Im
Feature activation+0.027
Top resid features:
gur
Tokengur
Feature activation+0.048
Top resid features:
or
Token or
Feature activation+0.092
Top resid features:
something
Token something
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+4.174
Top resid features:
that
Token that
Feature activation+0.215
Top resid features:
nature
Token nature
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:
will
Token will
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
A
TokenA
Feature activation+0.003
Top resid features:
ircraft
Tokenircraft
Feature activation+0.039
Top resid features:
of
Token of
Feature activation+0.254
Top resid features:
comparable
Token comparable
Feature activation+3.825
Top resid features:
role
Token role
Feature activation+0.157
Top resid features:
,
Token,
Feature activation+0.312
Top resid features:
configuration
Token configuration
Feature activation+0.098
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
era
Token era
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.007
Top resid features:
going
Token going
Feature activation-0.003
Top resid features:
to
Token to
Feature activation+0.017
Top resid features:
be
Token be
Feature activation+0.018
Top resid features:
of
Token of
Feature activation+1.285
Top resid features:
a
Token a
Feature activation+2.616
Top resid features:
very
Token very
Feature activation+0.598
Top resid features:
different
Token different
Feature activation+0.120
Top resid features:
kind
Token kind
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Whatever
Token Whatever
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.009
Top resid features:
were
Token were
Feature activation+0.007
Top resid features:
white
Token white
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
not
Token not
Feature activation+0.079
Top resid features:
of
Token of
Feature activation+4.266
Top resid features:
draft
Token draft
Feature activation+0.013
Top resid features:
age
Token age
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:
Christian
Token Christian
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.022
Top resid features:
going
Token going
Feature activation-0.005
Top resid features:
to
Token to
Feature activation+0.048
Top resid features:
be
Token be
Feature activation+0.038
Top resid features:
of
Token of
Feature activation+1.058
Top resid features:
a
Token a
Feature activation+3.206
Top resid features:
very
Token very
Feature activation+0.168
Top resid features:
different
Token different
Feature activation+0.000
Top resid features:
kind
Token kind
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Whatever
Token Whatever
Feature activation+0.000
Top resid features:
assigned
Token assigned
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
persons
Token persons
Feature activation+0.092
Top resid features:
of
Token of
Feature activation+0.724
Top resid features:
their
Token their
Feature activation+0.595
Top resid features:
same
Token same
Feature activation+2.908
Top resid features:
biological
Token biological
Feature activation+0.099
Top resid features:
sex
Token sex
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
regardless
Token regardless
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
once
Token once
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
as
Token as
Feature activation+0.007
Top resid features:
do
Token do
Feature activation+0.025
Top resid features:
others
Token others
Feature activation+0.044
Top resid features:
of
Token of
Feature activation+4.252
Top resid features:
the
Token the
Feature activation+0.133
Top resid features:
same
Token same
Feature activation+0.000
Top resid features:
model
Token model
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Newark
Token Newark
Feature activation+0.000
Top resid features:
changing
Token changing
Feature activation-0.009
Top resid features:
facilities
Token facilities
Feature activation-0.019
Top resid features:
assigned
Token assigned
Feature activation-0.013
Top resid features:
to
Token to
Feature activation+0.019
Top resid features:
persons
Token persons
Feature activation+0.164
Top resid features:
of
Token of
Feature activation+2.304
Top resid features:
their
Token their
Feature activation+1.548
Top resid features:
same
Token same
Feature activation+0.354
Top resid features:
biological
Token biological
Feature activation+0.000
Top resid features:
sex
Token sex
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.063
Top resid features:
res
Token res
Feature activation-0.002
Top resid features:
sc
Tokensc
Feature activation+0.009
Top resid features:
ue
Tokenue
Feature activation+0.138
Top resid features:
people
Token people
Feature activation+0.084
Top resid features:
of
Token of
Feature activation+3.626
Top resid features:
world
Token world
Feature activation+0.126
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
things
Token things
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
rit
Tokenrit
Feature activation+0.003
Top resid features:
te
Tokente
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.141
Top resid features:
It
Token It
Feature activation+0.026
Top resid features:
was
Token was
Feature activation+0.034
Top resid features:
of
Token of
Feature activation+2.183
Top resid features:
a
Token a
Feature activation+1.435
Top resid features:
green
Token green
Feature activation+0.291
Top resid features:
apple
Token apple
Feature activation+0.119
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
That
Token That
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.010
Top resid features:
lunar
Token lunar
Feature activation-0.028
Top resid features:
rock
Token rock
Feature activation+0.065
Top resid features:
is
Token is
Feature activation+0.072
Top resid features:
not
Token not
Feature activation+0.149
Top resid features:
of
Token of
Feature activation+3.817
Top resid features:
the
Token the
Feature activation+0.257
Top resid features:
same
Token same
Feature activation+0.000
Top resid features:
composition
Token composition
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:
experiments
Token experiments
Feature activation+0.042
Top resid features:
with
Token with
Feature activation+0.045
Top resid features:
humans
Token humans
Feature activation+0.054
Top resid features:
dropping
Token dropping
Feature activation+0.053
Top resid features:
balls
Token balls
Feature activation+0.163
Top resid features:
of
Token of
Feature activation+3.356
Top resid features:
markedly
Token markedly
Feature activation+0.123
Top resid features:
different
Token different
Feature activation+0.343
Top resid features:
weights
Token weights
Feature activation+0.000
Top resid features:
show
Token show
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
Trump
Token Trump
Feature activation+0.048
Top resid features:
had
Token had
Feature activation+0.009
Top resid features:
ever
Token ever
Feature activation-0.012
Top resid features:
said
Token said
Feature activation-0.002
Top resid features:
anything
Token anything
Feature activation+0.104
Top resid features:
of
Token of
Feature activation+3.667
Top resid features:
the
Token the
Feature activation+0.179
Top resid features:
sort
Token sort
Feature activation+0.000
Top resid features:
involving
Token involving
Feature activation+0.000
Top resid features:
race
Token race
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.01

Head 2: 0.03

Head 3: 0.03

Head 4: 0.09

Head 5: 0.08

Head 6: 0.03

Head 7: 0.49

Head 8: 0.04

Head 9: 0.05

Head 10: 0.09

Head 11: 0.03

Positive logits

calib3.16

caliber2.99

stature2.84

il2.51

fame2.41

proportions2.35

significance2.35

dimensions2.34

relevance2.33

persuasion2.31

magnitude2.28

size2.27

seriousness2.27

sophistication2.27

thickness2.23

importance2.21

origin2.20

nobility2.19

renown2.18

variety2.18

Negative logits

pointers-1.76

apses-1.74

withdrawals-1.69

tests-1.63

okes-1.63

cknow-1.57

Interview-1.55

ombs-1.52

Poll-1.48

COMMUN-1.46

Helper-1.45

Shut-1.44

loopholes-1.43

Walk-1.42

deductions-1.42

treats-1.41

refunds-1.40

surgeries-1.39

mails-1.39

videos-1.39

INTERVAL 3.934 - 4.371
CONTAINS 0.000%

p
Tokenp
Feature activation+0.000
aul
Tokenaul
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
of
Token of
Feature activation+0.000
my
Token my
Feature activation+4.315
generation
Token generation
Feature activation+1.545
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
of
Token of
Feature activation+1.014
my
Token my
Feature activation+2.116
R
TokenR
Feature activation+0.000
iding
Tokeniding
Feature activation+3.789
H
TokenH
Feature activation+0.000
ood
Tokenood
Feature activation+2.903
y
Tokeny
Feature activation+2.449
's
Token's
Feature activation+4.371
own
Token own
Feature activation+3.753
creation
Token creation
Feature activation+2.399
haha
Token haha
Feature activation+0.000
Inside
Token Inside
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 3.497 - 3.934
CONTAINS 0.001%

ircraft
Tokenircraft
Feature activation+0.000
of
Token of
Feature activation+0.000
comparable
Token comparable
Feature activation+0.104
role
Token role
Feature activation+1.593
,
Token,
Feature activation+0.218
configuration
Token configuration
Feature activation+3.565
and
Token and
Feature activation+2.119
era
Token era
Feature activation+2.420
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Related
TokenRelated
Feature activation+0.000
Im
Token Im
Feature activation+0.000
gur
Tokengur
Feature activation+0.000
or
Token or
Feature activation+0.000
something
Token something
Feature activation+0.000
of
Token of
Feature activation+0.203
that
Token that
Feature activation+3.596
nature
Token nature
Feature activation+1.969
.,
Token.,
Feature activation+0.000
this
Token this
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
iding
Tokeniding
Feature activation+3.789
H
TokenH
Feature activation+0.000
ood
Tokenood
Feature activation+2.903
y
Tokeny
Feature activation+2.449
's
Token's
Feature activation+4.371
own
Token own
Feature activation+3.753
creation
Token creation
Feature activation+2.399
haha
Token haha
Feature activation+0.000
Inside
Token Inside
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
was
Token was
Feature activation+0.000
of
Token of
Feature activation+0.885
Little
Token Little
Feature activation+1.285
Red
TokenRed
Feature activation+0.277
R
TokenR
Feature activation+0.000
iding
Tokeniding
Feature activation+3.789
H
TokenH
Feature activation+0.000
ood
Tokenood
Feature activation+2.903
y
Tokeny
Feature activation+2.449
's
Token's
Feature activation+4.371
own
Token own
Feature activation+3.753
their
Token their
Feature activation+0.000
partners
Token partners
Feature activation+0.000
than
Token than
Feature activation+0.000
people
Token people
Feature activation+0.000
of
Token of
Feature activation+0.000
other
Token other
Feature activation+3.629
sexual
Token sexual
Feature activation+2.864
orient
Token orient
Feature activation+1.131
ations
Tokenations
Feature activation+0.932
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.060 - 3.497
CONTAINS 0.001%

to
Token to
Feature activation+0.000
persons
Token persons
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+2.261
same
Token same
Feature activation+3.247
biological
Token biological
Feature activation+3.289
sex
Token sex
Feature activation+1.049
,
Token,
Feature activation+0.000
regardless
Token regardless
Feature activation+0.000
of
Token of
Feature activation+0.000
gender
Token gender
Feature activation+0.000
assigned
Token assigned
Feature activation+0.000
to
Token to
Feature activation+0.000
persons
Token persons
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+2.261
same
Token same
Feature activation+3.247
biological
Token biological
Feature activation+3.289
sex
Token sex
Feature activation+1.049
,
Token,
Feature activation+0.000
regardless
Token regardless
Feature activation+0.000
of
Token of
Feature activation+0.000
res
Token res
Feature activation+0.000
sc
Tokensc
Feature activation+0.000
ue
Tokenue
Feature activation+0.000
people
Token people
Feature activation+0.000
of
Token of
Feature activation+0.217
world
Token world
Feature activation+3.172
before
Token before
Feature activation+0.000
all
Token all
Feature activation+0.000
things
Token things
Feature activation+0.000
s
Tokens
Feature activation+0.000
end
Token end
Feature activation+0.000
were
Token were
Feature activation+0.000
white
Token white
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
of
Token of
Feature activation+0.135
draft
Token draft
Feature activation+3.385
age
Token age
Feature activation+2.644
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Christian
Token Christian
Feature activation+0.000
,
Token,
Feature activation+0.000
lunar
Token lunar
Feature activation+0.000
rock
Token rock
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
of
Token of
Feature activation+0.156
the
Token the
Feature activation+3.147
same
Token same
Feature activation+3.689
composition
Token composition
Feature activation+2.098
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000

INTERVAL 2.623 - 3.060
CONTAINS 0.002%

top
Token top
Feature activation+0.000
32
Token 32
Feature activation+0.000
or
Token or
Feature activation+0.000
something
Token something
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+2.861
nature
Token nature
Feature activation+1.280
.
Token.
Feature activation+0.000
Because
Token Because
Feature activation+0.000
when
Token when
Feature activation+0.000
you
Token you
Feature activation+0.000
hunger
Token hunger
Feature activation+0.000
is
Token is
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
hang
Token hang
Feature activation+1.002
over
Tokenover
Feature activation+2.739
variety
Token variety
Feature activation+1.097
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
brunch
Token brunch
Feature activation+0.000
here
Token here
Feature activation+0.000
with
Token with
Feature activation+0.000
humans
Token humans
Feature activation+0.000
dropping
Token dropping
Feature activation+0.000
balls
Token balls
Feature activation+0.000
of
Token of
Feature activation+0.572
markedly
Token markedly
Feature activation+2.794
different
Token different
Feature activation+3.120
weights
Token weights
Feature activation+1.374
show
Token show
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
do
Token do
Feature activation+0.000
others
Token others
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+3.274
same
Token same
Feature activation+2.869
model
Token model
Feature activation+2.722
in
Token in
Feature activation+0.000
Newark
Token Newark
Feature activation+0.000
,
Token,
Feature activation+0.000
Philadelphia
Token Philadelphia
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
do
Token do
Feature activation+0.000
others
Token others
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+3.274
same
Token same
Feature activation+2.869
model
Token model
Feature activation+2.722
in
Token in
Feature activation+0.000
Newark
Token Newark
Feature activation+0.000
,
Token,
Feature activation+0.000
Philadelphia
Token Philadelphia
Feature activation+0.000

INTERVAL 2.186 - 2.623
CONTAINS 0.002%

list
Token list
Feature activation+0.000
.
Token.
Feature activation+0.000
An
Token An
Feature activation+0.000
artist
Token artist
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+2.310
people
Token people
Feature activation+2.643
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
!
Token!
Feature activation+0.000
model
Token model
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+2.392
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
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
not
Token not
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+3.640
opinion
Token opinion
Feature activation+2.607
that
Token that
Feature activation+0.000
Comey
Token Comey
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
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
girl
Token girl
Feature activation+0.000
of
Token of
Feature activation+0.340
Turkish
Token Turkish
Feature activation+2.259
origin
Token origin
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Turkey
TokenTurkey
Feature activation+0.000
were
Token were
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
of
Tokenof
Feature activation+0.000
a
Token a
Feature activation+0.950
new
Token new
Feature activation+2.373
quality
Token quality
Feature activation+2.113
âĢ¦
Token âĢ¦
Feature activation+0.000
What
Token What
Feature activation+0.000
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 1.748 - 2.186
CONTAINS 0.005%

my
Token my
Feature activation+4.315
generation
Token generation
Feature activation+1.545
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
of
Token of
Feature activation+1.014
my
Token my
Feature activation+2.116
generation
Token generation
Feature activation+0.232
's
Token's
Feature activation+1.040
preceding
Token preceding
Feature activation+0.936
generation
Token generation
Feature activation+0.088
.
Token.
Feature activation+0.000
Indiana
Token Indiana
Feature activation+0.000
-
Token-
Feature activation+0.000
born
Tokenborn
Feature activation+0.000
judge
Token judge
Feature activation+0.000
of
Token of
Feature activation+0.431
Mexican
Token Mexican
Feature activation+1.890
ethnic
Token ethnic
Feature activation+2.049
heritage
Token heritage
Feature activation+0.300
âĢĶ
TokenâĢĶ
Feature activation+0.000
but
Tokenbut
Feature activation+0.000
money
Token money
Feature activation+0.000
pointers
Token pointers
Feature activation+0.000
for
Token for
Feature activation+0.000
people
Token people
Feature activation+0.000
of
Token of
Feature activation+0.000
like
Token like
Feature activation+0.402
mind
Token mind
Feature activation+2.172
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
in
Token in
Feature activation+0.000
touch
Token touch
Feature activation+0.000
via
Token via
Feature activation+0.000
an
Token an
Feature activation+0.000
object
Token object
Feature activation+0.000
of
Token of
Feature activation+0.000
Wall
Token Wall
Feature activation+0.461
Street
Token Street
Feature activation+2.006
's
Token's
Feature activation+1.749
attention
Token attention
Feature activation+0.000
.
Token.
Feature activation+0.000
C
Token C
Feature activation+0.000
ME
TokenME
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
considered
Token considered
Feature activation+0.000
of
Token of
Feature activation+0.000
great
Token great
Feature activation+0.783
commercial
Token commercial
Feature activation+2.014
,
Token,
Feature activation+0.070
communication
Token communication
Feature activation+1.440
,
Token,
Feature activation+0.045
and
Token and
Feature activation+0.043
military
Token military
Feature activation+1.498

INTERVAL 1.311 - 1.748
CONTAINS 0.007%

use
Token use
Feature activation+0.000
coal
Token coal
Feature activation+0.000
of
Token of
Feature activation+0.000
less
Token less
Feature activation+0.807
than
Token than
Feature activation+2.236
10
Token 10
Feature activation+1.562
percent
Token percent
Feature activation+1.654
volatility
Token volatility
Feature activation+1.079
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
the
Token the
Feature activation+0.000
over
Token over
Feature activation+0.000
instrument
Token instrument
Feature activation+0.000
als
Tokenals
Feature activation+0.000
of
Token of
Feature activation+0.000
one
Token one
Feature activation+1.479
of
Token of
Feature activation+1.337
my
Token my
Feature activation+1.459
favorite
Token favorite
Feature activation+1.308
groups
Token groups
Feature activation+0.000
of
Token of
Feature activation+0.098
all
Token all
Feature activation+0.087
of
Token of
Feature activation+0.785
J
Token J
Feature activation+1.804
ammu
Tokenammu
Feature activation+1.937
and
Token and
Feature activation+0.000
Kashmir
Token Kashmir
Feature activation+2.424
cad
Token cad
Feature activation+1.483
re
Tokenre
Feature activation+1.173
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
appointed
Token appointed
Feature activation+0.000
as
Token as
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
need
Token need
Feature activation+0.000
dough
Token dough
Feature activation+0.000
of
Token of
Feature activation+0.454
contrasting
Token contrasting
Feature activation+1.392
colors
Token colors
Feature activation+1.446
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
use
Token use
Feature activation+0.000
food
Token food
Feature activation+0.000
web
Token web
Feature activation+0.000
developers
Token developers
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.445
ages
Token ages
Feature activation+0.000
and
Token and
Feature activation+1.439
skill
Token skill
Feature activation+1.618
levels
Token levels
Feature activation+0.331
,"
Token,"
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.874 - 1.311
CONTAINS 0.014%

t
Tokent
Feature activation+0.000
ort
Tokenort
Feature activation+0.000
ure
Tokenure
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.014
Palestinian
Token Palestinian
Feature activation+0.916
man
Token man
Feature activation+0.000
'.
Token'.
Feature activation+0.000
G
Token G
Feature activation+0.000
igg
Tokenigg
Feature activation+0.000
led
Tokenled
Feature activation+0.000
32
Token 32
Feature activation+0.000
or
Token or
Feature activation+0.000
something
Token something
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+2.861
nature
Token nature
Feature activation+1.280
.
Token.
Feature activation+0.000
Because
Token Because
Feature activation+0.000
when
Token when
Feature activation+0.000
you
Token you
Feature activation+0.000
weed
Token weed
Feature activation+0.000
of
Token of
Feature activation+0.000
less
Token less
Feature activation+0.807
than
Token than
Feature activation+2.236
10
Token 10
Feature activation+1.562
percent
Token percent
Feature activation+1.654
volatility
Token volatility
Feature activation+1.079
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
the
Token the
Feature activation+0.000
power
Token power
Feature activation+0.000
station
Token station
Feature activation+0.000
major
Token major
Feature activation+0.000
international
Token international
Feature activation+0.000
banks
Token banks
Feature activation+0.000
of
Token of
Feature activation+0.000
Wall
Token Wall
Feature activation+0.591
Street
Token Street
Feature activation+0.999
,
Token,
Feature activation+0.000
drafted
Token drafted
Feature activation+0.000
what
Token what
Feature activation+0.000
many
Token many
Feature activation+0.000
mistakenly
Token mistakenly
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
none
Token none
Feature activation+0.000
of
Token of
Feature activation+0.000
your
Token your
Feature activation+1.045
damn
Token damn
Feature activation+1.669
business
Token business
Feature activation+0.951
why
Token why
Feature activation+0.000
I
Token I
Feature activation+0.000
did
Token did
Feature activation+0.000

INTERVAL 0.437 - 0.874
CONTAINS 0.035%

of
Token of
Feature activation+0.000
which
Token which
Feature activation+0.000
the
Token the
Feature activation+0.000
people
Token people
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.643
area
Token area
Feature activation+0.000
had
Token had
Feature activation+0.000
had
Token had
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
mantle
Token mantle
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
spot
Token spot
Feature activation+0.000
of
Token of
Feature activation+0.000
expression
Token expression
Feature activation+0.698
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
diff
Token diff
Feature activation+0.000
uses
Tokenuses
Feature activation+0.000
to
Token to
Feature activation+0.000
E
TokenE
Feature activation+0.557
level
Token level
Feature activation+0.052
of
Token of
Feature activation+0.000
quality
Token quality
Feature activation+0.177
and
Token and
Feature activation+0.018
durability
Token durability
Feature activation+0.465
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
you
Token you
Feature activation+0.000
first
Token first
Feature activation+0.000
citation
Token citation
Feature activation+0.000
of
Token of
Feature activation+0.000
M
Token M
Feature activation+0.504
x
Tokenx
Feature activation+0.742
.
Token.
Feature activation+0.650
found
Token found
Feature activation+0.000
by
Token by
Feature activation+0.000
Ms
Token Ms
Feature activation+0.000
.
Token.
Feature activation+0.000
Martin
Token Martin
Feature activation+0.000
...
Token...
Feature activation+0.000
thru
Token thru
Feature activation+0.000
no
Token no
Feature activation+0.000
fault
Token fault
Feature activation+0.000
of
Token of
Feature activation+0.000
your
Token your
Feature activation+0.473
own
Token own
Feature activation+0.286
.
Token.
Feature activation+0.000
Bad
Token Bad
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.000 - 0.437
CONTAINS 99.933%

Friends
Token Friends
Feature activation+0.000
,
Token,
Feature activation+0.000
Angry
Token Angry
Feature activation+0.000
Birds
Token Birds
Feature activation+0.000
,
Token,
Feature activation+0.000
Angry
Token Angry
Feature activation+0.000
Birds
Token Birds
Feature activation+0.000
Star
Token Star
Feature activation+0.000
Wars
Token Wars
Feature activation+0.000
,
Token,
Feature activation+0.000
Bad
Token Bad
Feature activation+0.000
mary
Tokenmary
Feature activation+0.000
was
Token was
Feature activation+0.000
dra
Token dra
Feature activation+0.000
f
Tokenf
Feature activation+0.000
ÂŃ
TokenÂŃ
Feature activation+0.000
ted
Tokented
Feature activation+0.000
by
Token by
Feature activation+0.000
H
Token H
Feature activation+0.000
Branch
Token Branch
Feature activation+0.000
,
Token,
Feature activation+0.000
signed
Token signed
Feature activation+0.000
Seattle
Token Seattle
Feature activation+0.000
and
Token and
Feature activation+0.000
Tacoma
Token Tacoma
Feature activation+0.000
.[
Token.[
Feature activation+0.000
15
Token15
Feature activation+0.000
][
Token][
Feature activation+0.000
5
Token5
Feature activation+0.000
]
Token]
Feature activation+0.000
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
month
Token month
Feature activation+0.000
really
Token really
Feature activation+0.000
in
Token in
Feature activation+0.000
charge
Token charge
Feature activation+0.000
of
Token of
Feature activation+0.000
policing
Token policing
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
its
Token its
Feature activation+0.000
third
Token third
Feature activation+0.000
the
Token the
Feature activation+0.000
dinner
Token dinner
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
got
Token got
Feature activation+0.000
there
Token there
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
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