H10.9 top features

Top feature 0 in H10.9: (feature 19011)

TOP ACTIVATIONS
MAX = 7.407

were
Token were
Feature activation+0.000
also
Token also
Feature activation+0.000
seen
Token seen
Feature activation+0.027
by
Token by
Feature activation+0.000
zoo
Token zoo
Feature activation+0.000
staff
Token staff
Feature activation+7.407
taking
Token taking
Feature activation+0.000
selfies
Token selfies
Feature activation+0.037
beside
Token beside
Feature activation+0.000
lions
Token lions
Feature activation+0.107
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
while
Token while
Feature activation+1.075
after
Token after
Feature activation+0.711
the
Token the
Feature activation+0.000
session
Token session
Feature activation+7.220
getting
Token getting
Feature activation+0.000
sand
Token sand
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
the
Token the
Feature activation+0.000
idea
Token idea
Feature activation+0.000
of
Token of
Feature activation+0.000
men
Token men
Feature activation+0.477
"
Token "
Feature activation+4.587
pret
Tokenpret
Feature activation+6.889
ending
Tokenending
Feature activation+1.429
"
Token"
Feature activation+0.000
to
Token to
Feature activation+0.227
be
Token be
Feature activation+0.000
women
Token women
Feature activation+0.182
âĢĵ
Token âĢĵ
Feature activation+0.000
while
Token while
Feature activation+0.000
at
Token at
Feature activation+0.500
the
Token the
Feature activation+0.000
same
Token same
Feature activation+1.356
time
Token time
Feature activation+6.877
promoting
Token promoting
Feature activation+0.000
key
Token key
Feature activation+0.000
values
Token values
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
go
Token go
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.165
way
Token way
Feature activation+0.000
toward
Token toward
Feature activation+0.758
qu
Token qu
Feature activation+6.414
elling
Tokenelling
Feature activation+0.000
the
Token the
Feature activation+0.000
outrage
Token outrage
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.115
his
Token his
Feature activation+0.000
no
Token no
Feature activation+0.000
business
Token business
Feature activation+1.661
,
Token,
Feature activation+2.968
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.525
,
Token,
Feature activation+6.232
decree
Token decree
Feature activation+2.934
ing
Tokening
Feature activation+0.000
who
Token who
Feature activation+0.000
may
Token may
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+0.000
Pacific
Token Pacific
Feature activation+0.000
war
Token war
Feature activation+0.000
,
Token,
Feature activation+0.000
thereby
Token thereby
Feature activation+0.197
invalid
Token invalid
Feature activation+5.721
ating
Tokenating
Feature activation+0.264
any
Token any
Feature activation+0.000
arguments
Token arguments
Feature activation+0.084
favoring
Token favoring
Feature activation+0.264
dropping
Token dropping
Feature activation+0.000
the
Token the
Feature activation+0.000
specific
Token specific
Feature activation+0.000
aims
Token aims
Feature activation+0.000
of
Token of
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.817
ľ
Tokenľ
Feature activation+5.605
creat
Tokencreat
Feature activation+4.412
ing
Tokening
Feature activation+0.000
public
Token public
Feature activation+0.337
acceptance
Token acceptance
Feature activation+0.000
and
Token and
Feature activation+1.828
itive
Tokenitive
Feature activation+0.000
pe
Token pe
Feature activation+0.000
cks
Tokencks
Feature activation+0.000
before
Token before
Feature activation+0.000
finally
Token finally
Feature activation+4.572
pe
Token pe
Feature activation+5.494
ering
Tokenering
Feature activation+0.137
down
Token down
Feature activation+0.000
the
Token the
Feature activation+0.000
barrel
Token barrel
Feature activation+0.000
of
Token of
Feature activation+1.889
of
Token of
Feature activation+0.000
some
Token some
Feature activation+0.000
weaker
Token weaker
Feature activation+0.000
Christians
Token Christians
Feature activation+0.000
and
Token and
Feature activation+0.176
stun
Token stun
Feature activation+5.492
ting
Tokenting
Feature activation+0.000
their
Token their
Feature activation+0.000
growth
Token growth
Feature activation+0.000
?
Token?
Feature activation+0.000
Isn
Token Isn
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.289
--
Token--
Feature activation+5.487
Run
TokenRun
Feature activation+2.519
stories
Token stories
Feature activation+0.000
past
Token past
Feature activation+0.755
Clinton
Token Clinton
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
and
Token and
Feature activation+0.000
is
Token is
Feature activation+0.000
widely
Token widely
Feature activation+0.000
credited
Token credited
Feature activation+0.000
for
Token for
Feature activation+0.000
popular
Token popular
Feature activation+5.387
ising
Tokenising
Feature activation+0.000
Japanese
Token Japanese
Feature activation+0.000
comic
Token comic
Feature activation+0.000
books
Token books
Feature activation+0.000
internationally
Token internationally
Feature activation+0.000
were
Token were
Feature activation+0.000
prohibited
Token prohibited
Feature activation+0.000
from
Token from
Feature activation+0.029
:
Token:
Feature activation+3.692
Ċ
TokenĊ
Feature activation+0.382
Ċ
TokenĊ
Feature activation+5.349
Calling
TokenCalling
Feature activation+0.000
their
Token their
Feature activation+0.000
places
Token places
Feature activation+0.000
of
Token of
Feature activation+0.401
worship
Token worship
Feature activation+0.000
but
Token but
Feature activation+0.000
he
Token he
Feature activation+0.000
wasted
Token wasted
Feature activation+0.000
no
Token no
Feature activation+0.000
time
Token time
Feature activation+0.000
yesterday
Token yesterday
Feature activation+5.296
in
Token in
Feature activation+0.893
sounding
Token sounding
Feature activation+0.000
out
Token out
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
senators
Token senators
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
before
Token before
Feature activation+0.440
quickly
Token quickly
Feature activation+3.484
back
Token back
Feature activation+4.157
ped
Tokenped
Feature activation+5.263
aling
Tokenaling
Feature activation+0.446
in
Token in
Feature activation+0.430
the
Token the
Feature activation+0.000
face
Token face
Feature activation+0.000
of
Token of
Feature activation+0.000
huge
Token huge
Feature activation+0.000
success
Token success
Feature activation+0.078
between
Token between
Feature activation+0.061
2007
Token 2007
Feature activation+0.000
and
Token and
Feature activation+0.000
2014
Token 2014
Feature activation+5.255
but
Token but
Feature activation+0.318
came
Token came
Feature activation+0.000
crashing
Token crashing
Feature activation+0.000
down
Token down
Feature activation+0.000
when
Token when
Feature activation+0.000
a
Token a
Feature activation+0.000
strong
Token strong
Feature activation+0.000
possibility
Token possibility
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.680
overt
Token overt
Feature activation+5.222
aking
Tokenaking
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
two
Token two
Feature activation+0.000
states
Token states
Feature activation+0.000
takes
Token takes
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
credit
Token credit
Feature activation+0.000
for
Token for
Feature activation+0.000
initially
Token initially
Feature activation+3.042
enact
Token enact
Feature activation+5.193
ing
Tokening
Feature activation+0.874
and
Token and
Feature activation+0.441
seeing
Token seeing
Feature activation+0.167
through
Token through
Feature activation+0.149
those
Token those
Feature activation+0.000
all
Token all
Feature activation+0.000
spent
Token spent
Feature activation+0.000
years
Token years
Feature activation+0.599
psych
Token psych
Feature activation+2.947
oan
Tokenoan
Feature activation+2.789
aly
Tokenaly
Feature activation+5.107
zing
Tokenzing
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
and
Token and
Feature activation+0.042
his
Token his
Feature activation+0.000
o
Token o
Feature activation+0.000
,
Token,
Feature activation+0.000
despite
Token despite
Feature activation+0.000
his
Token his
Feature activation+0.000
lawyer
Token lawyer
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+5.092
s
Tokens
Feature activation+0.064
efforts
Token efforts
Feature activation+0.351
to
Token to
Feature activation+0.034
shut
Token shut
Feature activation+0.499
him
Token him
Feature activation+0.000

Top DFA by src position
MAX = 7.797

animals
Token animals
Feature activation-0.010
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
They
Token They
Feature activation-0.007
Top resid features:
were
Token were
Feature activation-0.004
Top resid features:
also
Token also
Feature activation-0.008
Top resid features:
seen
Token seen
Feature activation+7.797
Top resid features:
by
Token by
Feature activation-0.023
Top resid features:
zoo
Token zoo
Feature activation-0.005
Top resid features:
staff
Token staff
Feature activation+0.115
Top resid features:
taking
Token taking
Feature activation+0.000
Top resid features:
selfies
Token selfies
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.019
Top resid features:
undoubtedly
Token undoubtedly
Feature activation+0.010
Top resid features:
spent
Token spent
Feature activation+0.025
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
good
Token good
Feature activation-0.012
Top resid features:
while
Token while
Feature activation+7.429
Top resid features:
after
Token after
Feature activation+0.051
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
session
Token session
Feature activation+0.132
Top resid features:
getting
Token getting
Feature activation+0.000
Top resid features:
sand
Token sand
Feature activation+0.000
Top resid features:
dismissed
Token dismissed
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
idea
Token idea
Feature activation-0.004
Top resid features:
of
Token of
Feature activation+0.142
Top resid features:
men
Token men
Feature activation+1.881
Top resid features:
"
Token "
Feature activation+5.269
Top resid features:
pret
Tokenpret
Feature activation+0.013
Top resid features:
ending
Tokenending
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
women
Token women
Feature activation+0.002
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
football
Token football
Feature activation+0.000
Top resid features:
clubs
Token clubs
Feature activation+0.001
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.011
Top resid features:
while
Token while
Feature activation+7.093
Top resid features:
at
Token at
Feature activation+0.008
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
same
Token same
Feature activation+0.002
Top resid features:
time
Token time
Feature activation+0.144
Top resid features:
promoting
Token promoting
Feature activation+0.000
Top resid features:
should
Token should
Feature activation-0.000
Top resid features:
go
Token go
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
long
Token long
Feature activation+0.001
Top resid features:
way
Token way
Feature activation+0.018
Top resid features:
toward
Token toward
Feature activation+6.804
Top resid features:
qu
Token qu
Feature activation+0.004
Top resid features:
elling
Tokenelling
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
outrage
Token outrage
Feature activation+0.000
Top resid features:
surrounding
Token surrounding
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
government
Token government
Feature activation-0.009
Top resid features:
has
Token has
Feature activation-0.013
Top resid features:
no
Token no
Feature activation-0.002
Top resid features:
business
Token business
Feature activation+6.756
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
general
Token general
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
decree
Token decree
Feature activation+0.000
Top resid features:
winning
Token winning
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
Pacific
Token Pacific
Feature activation-0.002
Top resid features:
war
Token war
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.159
Top resid features:
thereby
Token thereby
Feature activation+5.578
Top resid features:
invalid
Token invalid
Feature activation+0.012
Top resid features:
ating
Tokenating
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
arguments
Token arguments
Feature activation+0.000
Top resid features:
favoring
Token favoring
Feature activation+0.000
Top resid features:
Jay
Token Jay
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.017
Top resid features:
the
Token the
Feature activation-0.017
Top resid features:
specific
Token specific
Feature activation-0.005
Top resid features:
aims
Token aims
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+6.069
Top resid features:
âĢ
Token âĢ
Feature activation+0.045
Top resid features:
ľ
Tokenľ
Feature activation+0.066
Top resid features:
creat
Tokencreat
Feature activation+0.000
Top resid features:
ing
Tokening
Feature activation+0.000
Top resid features:
public
Token public
Feature activation+0.000
Top resid features:
inqu
Token inqu
Feature activation+0.002
Top resid features:
is
Tokenis
Feature activation-0.001
Top resid features:
itive
Tokenitive
Feature activation+0.002
Top resid features:
pe
Token pe
Feature activation-0.000
Top resid features:
cks
Tokencks
Feature activation+0.001
Top resid features:
before
Token before
Feature activation+3.816
Top resid features:
finally
Token finally
Feature activation+2.151
Top resid features:
pe
Token pe
Feature activation+0.017
Top resid features:
ering
Tokenering
Feature activation+0.000
Top resid features:
down
Token down
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
faith
Token faith
Feature activation-0.009
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
some
Token some
Feature activation-0.007
Top resid features:
weaker
Token weaker
Feature activation-0.002
Top resid features:
Christians
Token Christians
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+6.020
Top resid features:
stun
Token stun
Feature activation+0.002
Top resid features:
ting
Tokenting
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
growth
Token growth
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.001
Top resid features:
more
Token more
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
following
Token following
Feature activation+0.002
Top resid features:
:
Token:
Feature activation+3.096
Top resid features:
Ċ
TokenĊ
Feature activation+0.080
Top resid features:
Ċ
TokenĊ
Feature activation+2.562
Top resid features:
--
Token--
Feature activation+0.325
Top resid features:
Run
TokenRun
Feature activation+0.000
Top resid features:
stories
Token stories
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
is
Token is
Feature activation-0.018
Top resid features:
widely
Token widely
Feature activation-0.003
Top resid features:
credited
Token credited
Feature activation-0.010
Top resid features:
for
Token for
Feature activation+5.919
Top resid features:
popular
Token popular
Feature activation+0.023
Top resid features:
ising
Tokenising
Feature activation+0.000
Top resid features:
Japanese
Token Japanese
Feature activation+0.000
Top resid features:
comic
Token comic
Feature activation+0.000
Top resid features:
books
Token books
Feature activation+0.000
Top resid features:
community
Token community
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
who
Token who
Feature activation-0.011
Top resid features:
were
Token were
Feature activation-0.003
Top resid features:
prohibited
Token prohibited
Feature activation+0.013
Top resid features:
from
Token from
Feature activation+5.315
Top resid features:
:
Token:
Feature activation+0.371
Top resid features:
Ċ
TokenĊ
Feature activation+0.073
Top resid features:
Ċ
TokenĊ
Feature activation+0.129
Top resid features:
Calling
TokenCalling
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
Asia
Token Asia
Feature activation-0.010
Top resid features:
but
Token but
Feature activation-0.005
Top resid features:
he
Token he
Feature activation-0.003
Top resid features:
wasted
Token wasted
Feature activation-0.022
Top resid features:
no
Token no
Feature activation-0.003
Top resid features:
time
Token time
Feature activation+5.775
Top resid features:
yesterday
Token yesterday
Feature activation+0.048
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
sounding
Token sounding
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
Democratic
Token Democratic
Feature activation+0.000
Top resid features:
be
Token be
Feature activation-0.000
Top resid features:
armed
Token armed
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:
before
Token before
Feature activation+0.239
Top resid features:
quickly
Token quickly
Feature activation+5.429
Top resid features:
back
Token back
Feature activation+0.133
Top resid features:
ped
Tokenped
Feature activation+0.001
Top resid features:
aling
Tokenaling
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
he
Tokenhe
Feature activation-0.001
Top resid features:
conom
Tokenconom
Feature activation-0.002
Top resid features:
bank
Tokenbank
Feature activation-0.002
Top resid features:
had
Token had
Feature activation-0.029
Top resid features:
huge
Token huge
Feature activation-0.014
Top resid features:
success
Token success
Feature activation+5.829
Top resid features:
between
Token between
Feature activation+0.003
Top resid features:
2007
Token 2007
Feature activation-0.007
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
2014
Token 2014
Feature activation+0.014
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
be
Token be
Feature activation-0.023
Top resid features:
a
Token a
Feature activation-0.004
Top resid features:
strong
Token strong
Feature activation+0.000
Top resid features:
possibility
Token possibility
Feature activation-0.059
Top resid features:
of
Token of
Feature activation+0.150
Top resid features:
them
Token them
Feature activation+5.665
Top resid features:
overt
Token overt
Feature activation+0.031
Top resid features:
aking
Tokenaking
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
himself
Token himself
Feature activation-0.007
Top resid features:
takes
Token takes
Feature activation-0.005
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.031
Top resid features:
credit
Token credit
Feature activation+0.002
Top resid features:
for
Token for
Feature activation+1.542
Top resid features:
initially
Token initially
Feature activation+4.178
Top resid features:
enact
Token enact
Feature activation+0.006
Top resid features:
ing
Tokening
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
seeing
Token seeing
Feature activation+0.000
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.003
Top resid features:
ve
Tokenve
Feature activation+0.001
Top resid features:
all
Token all
Feature activation-0.004
Top resid features:
spent
Token spent
Feature activation+0.010
Top resid features:
years
Token years
Feature activation+5.110
Top resid features:
psych
Token psych
Feature activation+0.405
Top resid features:
oan
Tokenoan
Feature activation+0.093
Top resid features:
aly
Tokenaly
Feature activation+0.025
Top resid features:
zing
Tokenzing
Feature activation+0.000
Top resid features:
Bush
Token Bush
Feature activation+0.000
Top resid features:
his
Token his
Feature activation-0.001
Top resid features:
case
Token case
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.018
Top resid features:
despite
Token despite
Feature activation+0.074
Top resid features:
his
Token his
Feature activation+0.018
Top resid features:
lawyer
Token lawyer
Feature activation+5.529
Top resid features:
âĢ
TokenâĢ
Feature activation+0.040
Top resid features:
Ļ
TokenĻ
Feature activation+0.032
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
efforts
Token efforts
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.02

Head 3: 0.02

Head 4: 0.02

Head 5: 0.04

Head 6: 0.02

Head 7: 0.03

Head 8: 0.02

Head 9: 0.73

Head 10: 0.02

Head 11: 0.03

Positive logits

angering5.24

playing4.69

gling4.69

roying4.66

ying4.65

joining4.65

acting4.64

lining4.63

izing4.63

TING4.60

forming4.60

ocating4.59

slapping4.58

getting4.58

iating4.56

doing4.54

cutting4.53

porting4.51

ulating4.50

uing4.49

Negative logits

rued-2.11

aceae-2.09

Played-2.03

izons-2.00

Args-1.91

elist-1.89

verages-1.88

tasted-1.87

abus-1.85

actionDate-1.81

Depths-1.80

ursed-1.79

Appearance-1.76

ウス-1.74

},{"-1.74

tec-1.73

OTOS-1.72

=-=-=-=-=-=-=-=--1.71

Topics-1.71

Became-1.70

INTERVAL 6.666 - 7.407
CONTAINS 0.000%

the
Token the
Feature activation+0.000
idea
Token idea
Feature activation+0.000
of
Token of
Feature activation+0.000
men
Token men
Feature activation+0.477
"
Token "
Feature activation+4.587
pret
Tokenpret
Feature activation+6.889
ending
Tokenending
Feature activation+1.429
"
Token"
Feature activation+0.000
to
Token to
Feature activation+0.227
be
Token be
Feature activation+0.000
women
Token women
Feature activation+0.182
âĢĵ
Token âĢĵ
Feature activation+0.000
while
Token while
Feature activation+0.000
at
Token at
Feature activation+0.500
the
Token the
Feature activation+0.000
same
Token same
Feature activation+1.356
time
Token time
Feature activation+6.877
promoting
Token promoting
Feature activation+0.000
key
Token key
Feature activation+0.000
values
Token values
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
while
Token while
Feature activation+1.075
after
Token after
Feature activation+0.711
the
Token the
Feature activation+0.000
session
Token session
Feature activation+7.220
getting
Token getting
Feature activation+0.000
sand
Token sand
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
were
Token were
Feature activation+0.000
also
Token also
Feature activation+0.000
seen
Token seen
Feature activation+0.027
by
Token by
Feature activation+0.000
zoo
Token zoo
Feature activation+0.000
staff
Token staff
Feature activation+7.407
taking
Token taking
Feature activation+0.000
selfies
Token selfies
Feature activation+0.037
beside
Token beside
Feature activation+0.000
lions
Token lions
Feature activation+0.107
,
Token,
Feature activation+0.000

INTERVAL 5.925 - 6.666
CONTAINS 0.000%

go
Token go
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.165
way
Token way
Feature activation+0.000
toward
Token toward
Feature activation+0.758
qu
Token qu
Feature activation+6.414
elling
Tokenelling
Feature activation+0.000
the
Token the
Feature activation+0.000
outrage
Token outrage
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.115
his
Token his
Feature activation+0.000
no
Token no
Feature activation+0.000
business
Token business
Feature activation+1.661
,
Token,
Feature activation+2.968
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.525
,
Token,
Feature activation+6.232
decree
Token decree
Feature activation+2.934
ing
Tokening
Feature activation+0.000
who
Token who
Feature activation+0.000
may
Token may
Feature activation+0.000
or
Token or
Feature activation+0.000

INTERVAL 5.185 - 5.925
CONTAINS 0.001%

were
Token were
Feature activation+0.000
prohibited
Token prohibited
Feature activation+0.000
from
Token from
Feature activation+0.029
:
Token:
Feature activation+3.692
Ċ
TokenĊ
Feature activation+0.382
Ċ
TokenĊ
Feature activation+5.349
Calling
TokenCalling
Feature activation+0.000
their
Token their
Feature activation+0.000
places
Token places
Feature activation+0.000
of
Token of
Feature activation+0.401
worship
Token worship
Feature activation+0.000
itive
Tokenitive
Feature activation+0.000
pe
Token pe
Feature activation+0.000
cks
Tokencks
Feature activation+0.000
before
Token before
Feature activation+0.000
finally
Token finally
Feature activation+4.572
pe
Token pe
Feature activation+5.494
ering
Tokenering
Feature activation+0.137
down
Token down
Feature activation+0.000
the
Token the
Feature activation+0.000
barrel
Token barrel
Feature activation+0.000
of
Token of
Feature activation+1.889
a
Token a
Feature activation+0.000
strong
Token strong
Feature activation+0.000
possibility
Token possibility
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.680
overt
Token overt
Feature activation+5.222
aking
Tokenaking
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
two
Token two
Feature activation+0.000
states
Token states
Feature activation+0.000
takes
Token takes
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
credit
Token credit
Feature activation+0.000
for
Token for
Feature activation+0.000
initially
Token initially
Feature activation+3.042
enact
Token enact
Feature activation+5.193
ing
Tokening
Feature activation+0.874
and
Token and
Feature activation+0.441
seeing
Token seeing
Feature activation+0.167
through
Token through
Feature activation+0.149
those
Token those
Feature activation+0.000
and
Token and
Feature activation+0.000
is
Token is
Feature activation+0.000
widely
Token widely
Feature activation+0.000
credited
Token credited
Feature activation+0.000
for
Token for
Feature activation+0.000
popular
Token popular
Feature activation+5.387
ising
Tokenising
Feature activation+0.000
Japanese
Token Japanese
Feature activation+0.000
comic
Token comic
Feature activation+0.000
books
Token books
Feature activation+0.000
internationally
Token internationally
Feature activation+0.000

INTERVAL 4.444 - 5.185
CONTAINS 0.003%

talk
Token talk
Feature activation+0.000
about
Token about
Feature activation+0.000
him
Token him
Feature activation+0.000
was
Token was
Feature activation+0.000
like
Token like
Feature activation+1.063
"
Token "
Feature activation+4.523
watching
Tokenwatching
Feature activation+0.665
your
Token your
Feature activation+0.000
own
Token own
Feature activation+0.000
funeral
Token funeral
Feature activation+0.000
."
Token."
Feature activation+0.000
a
Token a
Feature activation+0.000
video
Token video
Feature activation+0.055
of
Token of
Feature activation+0.155
him
Token him
Feature activation+0.230
from
Token from
Feature activation+0.000
2005
Token 2005
Feature activation+4.680
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.041
,
Token,
Feature activation+0.215
,
Token,
Feature activation+0.000
despite
Token despite
Feature activation+0.000
his
Token his
Feature activation+0.000
lawyer
Token lawyer
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+5.092
s
Tokens
Feature activation+0.064
efforts
Token efforts
Feature activation+0.351
to
Token to
Feature activation+0.034
shut
Token shut
Feature activation+0.499
him
Token him
Feature activation+0.000
from
Token from
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.100
ĺ
Tokenĺ
Feature activation+3.737
re
Tokenre
Feature activation+2.289
-
Token-
Feature activation+3.726
laun
Tokenlaun
Feature activation+4.734
ching
Tokenching
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
proposals
Token proposals
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+1.555
not
Token not
Feature activation+4.451
doing
Token doing
Feature activation+0.301
something
Token something
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
,
Token,
Feature activation+1.798
at
Token at
Feature activation+1.416

INTERVAL 3.703 - 4.444
CONTAINS 0.008%

hundred
Token hundred
Feature activation+2.467
-
Token-
Feature activation+0.079
fold
Tokenfold
Feature activation+4.639
during
Token during
Feature activation+0.374
this
Token this
Feature activation+0.000
period
Token period
Feature activation+4.064
.
Token.
Feature activation+0.017
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
very
Token very
Feature activation+0.000
proud
Token proud
Feature activation+0.000
of
Token of
Feature activation+0.033
sh
Token sh
Feature activation+0.949
unning
Tokenunning
Feature activation+0.000
controversy
Token controversy
Feature activation+0.000
by
Token by
Feature activation+0.149
utter
Token utter
Feature activation+3.746
ing
Tokening
Feature activation+0.636
plat
Token plat
Feature activation+0.000
itudes
Tokenitudes
Feature activation+0.000
.
Token.
Feature activation+0.000
Instead
Token Instead
Feature activation+0.000
the
Token the
Feature activation+0.000
hours
Token hours
Feature activation+0.000
I
Token I
Feature activation+0.000
spend
Token spend
Feature activation+0.000
each
Token each
Feature activation+0.702
week
Token week
Feature activation+4.223
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
gym
Token gym
Feature activation+4.104
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
armed
Token armed
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
before
Token before
Feature activation+0.440
quickly
Token quickly
Feature activation+3.484
back
Token back
Feature activation+4.157
ped
Tokenped
Feature activation+5.263
aling
Tokenaling
Feature activation+0.446
in
Token in
Feature activation+0.430
the
Token the
Feature activation+0.000
face
Token face
Feature activation+0.000
t
Tokent
Feature activation+0.000
want
Token want
Feature activation+0.000
any
Token any
Feature activation+0.000
company
Token company
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.880
s
Tokens
Feature activation+0.000
product
Token product
Feature activation+0.202
forcing
Token forcing
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 2.963 - 3.703
CONTAINS 0.018%

of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
avoided
Token avoided
Feature activation+0.000
openly
Token openly
Feature activation+3.607
cred
Token cred
Feature activation+3.226
iting
Tokeniting
Feature activation+0.000
Obamacare
Token Obamacare
Feature activation+0.000
with
Token with
Feature activation+0.000
achieving
Token achieving
Feature activation+0.000
the
Token the
Feature activation+0.000
progress
Token progress
Feature activation+0.266
Tuesday
Token Tuesday
Feature activation+3.558
night
Token night
Feature activation+3.596
and
Token and
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+3.172
morning
Token morning
Feature activation+3.367
,
Token,
Feature activation+0.500
setting
Token setting
Feature activation+0.000
off
Token off
Feature activation+0.000
controlled
Token controlled
Feature activation+0.000
burns
Token burns
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
has
Token has
Feature activation+0.000
no
Token no
Feature activation+0.000
business
Token business
Feature activation+1.661
,
Token,
Feature activation+2.968
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.525
,
Token,
Feature activation+6.232
decree
Token decree
Feature activation+2.934
ing
Tokening
Feature activation+0.000
a
Token a
Feature activation+0.000
challenge
Token challenge
Feature activation+0.000
for
Token for
Feature activation+0.000
robots
Token robots
Feature activation+0.000
:
Token:
Feature activation+0.567
perce
Token perce
Feature activation+3.197
iving
Tokeniving
Feature activation+0.000
and
Token and
Feature activation+0.862
manipulating
Token manipulating
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.920
in
Token in
Feature activation+0.381
brightly
Token brightly
Feature activation+0.000
colored
Token colored
Feature activation+0.000
pol
Token pol
Feature activation+0.000
o
Tokeno
Feature activation+0.000
shirts
Token shirts
Feature activation+3.295
and
Token and
Feature activation+1.332
noticeably
Token noticeably
Feature activation+0.265
wa
Token wa
Feature activation+0.000
ver
Tokenver
Feature activation+0.000
ing
Tokening
Feature activation+0.000

INTERVAL 2.222 - 2.963
CONTAINS 0.032%

our
Token our
Feature activation+0.000
time
Token time
Feature activation+0.000
was
Token was
Feature activation+0.000
spent
Token spent
Feature activation+1.705
a
Token a
Feature activation+1.578
hundred
Token hundred
Feature activation+2.467
-
Token-
Feature activation+0.079
fold
Tokenfold
Feature activation+4.639
during
Token during
Feature activation+0.374
this
Token this
Feature activation+0.000
period
Token period
Feature activation+4.064
the
Token the
Feature activation+0.000
Union
Token Union
Feature activation+0.000
of
Token of
Feature activation+0.000
Concern
Token Concern
Feature activation+0.000
ed
Tokened
Feature activation+0.000
Scientists
Token Scientists
Feature activation+2.265
suggesting
Token suggesting
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
's
Token's
Feature activation+0.000
been
Token been
Feature activation+0.000
oul
Tokenoul
Feature activation+0.000
key
Tokenkey
Feature activation+0.000
-
Token-
Feature activation+0.000
is
Tokenis
Feature activation+0.000
-
Token-
Feature activation+0.868
stream
Tokenstream
Feature activation+2.292
ing
Tokening
Feature activation+0.000
-
Token-
Feature activation+0.000
bro
Tokenbro
Feature activation+0.000
od
Tokenod
Feature activation+0.000
-
Token-
Feature activation+0.000
County
Token County
Feature activation+0.000
Sheriff
Token Sheriff
Feature activation+0.000
's
Token's
Feature activation+0.000
Office
Token Office
Feature activation+0.000
is
Token is
Feature activation+0.000
alert
Token alert
Feature activation+2.710
ing
Tokening
Feature activation+0.061
users
Token users
Feature activation+0.000
of
Token of
Feature activation+0.608
a
Token a
Feature activation+0.000
popular
Token popular
Feature activation+0.000
and
Token and
Feature activation+0.000
would
Token would
Feature activation+0.000
instead
Token instead
Feature activation+0.000
focus
Token focus
Feature activation+0.000
on
Token on
Feature activation+0.000
equ
Token equ
Feature activation+2.224
ipping
Tokenipping
Feature activation+1.059
and
Token and
Feature activation+0.000
providing
Token providing
Feature activation+0.000
direct
Token direct
Feature activation+0.000
air
Token air
Feature activation+0.000

INTERVAL 1.481 - 2.222
CONTAINS 0.077%

port
Tokenport
Feature activation+0.000
even
Token even
Feature activation+0.000
though
Token though
Feature activation+0.000
we
Token we
Feature activation+0.000
started
Token started
Feature activation+0.000
real
Token real
Feature activation+1.559
poor
Token poor
Feature activation+0.806
in
Token in
Feature activation+0.000
working
Token working
Feature activation+0.000
class
Token class
Feature activation+0.007
Sheffield
Token Sheffield
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
always
Token always
Feature activation+0.000
worth
Token worth
Feature activation+0.736
a
Token a
Feature activation+1.655
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
reading
Tokenreading
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
case
Token case
Feature activation+0.000
of
Token of
Feature activation+0.000
The
Token The
Feature activation+0.000
Emperor
Token Emperor
Feature activation+0.000
is
Token is
Feature activation+1.029
Dead
Token Dead
Feature activation+1.940
,
Token,
Feature activation+0.000
long
Token long
Feature activation+0.000
live
Token live
Feature activation+0.000
the
Token the
Feature activation+0.000
Emperor
Token Emperor
Feature activation+0.000
parents
Token parents
Feature activation+0.000
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+0.000
merely
Token merely
Feature activation+1.542
handing
Token handing
Feature activation+0.000
them
Token them
Feature activation+0.000
checks
Token checks
Feature activation+0.000
,
Token,
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
Def
Token Def
Feature activation+0.000
ends
Tokenends
Feature activation+0.000
Video
Token Video
Feature activation+0.000
Of
Token Of
Feature activation+0.000
Marines
Token Marines
Feature activation+1.681
Reported
Token Reported
Feature activation+1.602
ly
Tokenly
Feature activation+3.105
Ur
Token Ur
Feature activation+4.345
inating
Tokeninating
Feature activation+0.000
On
Token On
Feature activation+0.000
Dead
Token Dead
Feature activation+0.000

INTERVAL 0.741 - 1.481
CONTAINS 0.270%

.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
means
Token means
Feature activation+0.089
that
Token that
Feature activation+0.138
not
Token not
Feature activation+0.270
only
Token only
Feature activation+1.222
does
Token does
Feature activation+0.570
the
Token the
Feature activation+0.086
brisk
Token brisk
Feature activation+0.000
et
Tokenet
Feature activation+0.148
have
Token have
Feature activation+0.000
began
Token began
Feature activation+0.000
on
Token on
Feature activation+0.000
September
Token September
Feature activation+0.000
14
Token 14
Feature activation+0.331
,
Token,
Feature activation+0.000
1901
Token 1901
Feature activation+0.835
,
Token,
Feature activation+0.593
when
Token when
Feature activation+0.000
Theodore
Token Theodore
Feature activation+0.000
Roosevelt
Token Roosevelt
Feature activation+0.000
became
Token became
Feature activation+0.000
in
Token in
Feature activation+0.000
Holly
Token Holly
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.687
s
Tokens
Feature activation+0.000
bedroom
Token bedroom
Feature activation+0.927
which
Token which
Feature activation+0.000
described
Token described
Feature activation+0.000
her
Token her
Feature activation+0.000
experiences
Token experiences
Feature activation+0.000
at
Token at
Feature activation+0.000
and
Token and
Feature activation+0.045
undoubtedly
Token undoubtedly
Feature activation+0.151
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
while
Token while
Feature activation+1.075
after
Token after
Feature activation+0.711
the
Token the
Feature activation+0.000
session
Token session
Feature activation+7.220
getting
Token getting
Feature activation+0.000
sand
Token sand
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.055
various
Token various
Feature activation+0.000
characters
Token characters
Feature activation+0.434
and
Token and
Feature activation+0.111
stories
Token stories
Feature activation+0.967
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.569
because
Token because
Feature activation+1.083
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000

INTERVAL 0.000 - 0.741
CONTAINS 99.590%

end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
rotation
Token rotation
Feature activation+0.000
?
Token?
Feature activation+0.000
Even
Token Even
Feature activation+0.000
as
Token as
Feature activation+0.000
you
Token you
Feature activation+0.000
move
Token move
Feature activation+0.000
down
Token down
Feature activation+0.000
our
Token our
Feature activation+0.000
or
Token or
Feature activation+0.000
where
Token where
Feature activation+0.000
state
Token state
Feature activation+0.000
suppression
Token suppression
Feature activation+0.000
of
Token of
Feature activation+0.000
targeted
Token targeted
Feature activation+0.000
expression
Token expression
Feature activation+0.000
supports
Token supports
Feature activation+0.000
the
Token the
Feature activation+0.000
geopolitical
Token geopolitical
Feature activation+0.000
goals
Token goals
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
been
Token been
Feature activation+0.000
blogging
Token blogging
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
about
Token about
Feature activation+0.000
what
Token what
Feature activation+0.000
we
Token we
Feature activation+0.000
learnt
Token learnt
Feature activation+0.080
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
already
Token already
Feature activation+0.000
being
Token being
Feature activation+0.000
secretly
Token secretly
Feature activation+0.000
tested
Token tested
Feature activation+0.000
while
Token while
Feature activation+0.000
DAR
Token DAR
Feature activation+0.000
PA
TokenPA
Feature activation+0.000
's
Token's
Feature activation+0.000
last
Token last
Feature activation+0.000
Robotics
Token Robotics
Feature activation+0.000
Challenge
Token Challenge
Feature activation+0.000
fighters
Token fighters
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Kurdish
Token Kurdish
Feature activation+0.000
Regional
Token Regional
Feature activation+0.000
Government
Token Government
Feature activation+0.000
(
Token (
Feature activation+0.000
KR
TokenKR
Feature activation+0.000
G
TokenG
Feature activation+0.000
),
Token),
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 1 in H10.9: (feature 2385)

TOP ACTIVATIONS
MAX = 5.220

Ċ
TokenĊ
Feature activation+0.000
Ukraine
TokenUkraine
Feature activation+0.000
is
Token is
Feature activation+0.000
accused
Token accused
Feature activation+0.000
by
Token by
Feature activation+0.000
Moscow
Token Moscow
Feature activation+5.220
of
Token of
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
destabil
Token destabil
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
the
Token the
Feature activation+0.000
hands
Token hands
Feature activation+0.007
,
Token,
Feature activation+0.204
or
Token or
Feature activation+0.143
feet
Token feet
Feature activation+0.000
,
Token,
Feature activation+4.988
of
Token of
Feature activation+0.000
Ap
Token Ap
Feature activation+0.000
od
Tokenod
Feature activation+0.000
aca
Tokenaca
Feature activation+0.000
.
Token.
Feature activation+0.000
US
Token US
Feature activation+0.000
,
Token,
Feature activation+0.000
mindful
Token mindful
Feature activation+0.000
,
Token,
Feature activation+0.051
perhaps
Token perhaps
Feature activation+0.340
,
Token,
Feature activation+4.960
of
Token of
Feature activation+0.198
the
Token the
Feature activation+0.000
Mormon
Token Mormon
Feature activation+0.000
community
Token community
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
a
Token a
Feature activation+0.000
leading
Token leading
Feature activation+0.000
left
Token left
Feature activation+0.000
-
Token-
Feature activation+0.000
wing
Tokenwing
Feature activation+0.000
campaigner
Token campaigner
Feature activation+4.872
of
Token of
Feature activation+0.000
being
Token being
Feature activation+0.000
disl
Token disl
Feature activation+0.000
oyal
Tokenoyal
Feature activation+0.000
to
Token to
Feature activation+0.000
same
Token same
Feature activation+0.000
elite
Token elite
Feature activation+0.000
neighborhoods
Token neighborhoods
Feature activation+0.000
consists
Token consists
Feature activation+0.000
almost
Token almost
Feature activation+1.011
wholly
Token wholly
Feature activation+4.766
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
with
Token with
Feature activation+0.000
college
Token college
Feature activation+0.000
degrees
Token degrees
Feature activation+0.053
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
presence
Token presence
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
community
Token community
Feature activation+4.663
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
company
Token company
Feature activation+0.000
that
Token that
Feature activation+0.000
participates
Token participates
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
accused
Token accused
Feature activation+0.000
previously
Token previously
Feature activation+4.532
of
Token of
Feature activation+0.000
not
Token not
Feature activation+0.000
making
Token making
Feature activation+0.000
clear
Token clear
Feature activation+0.000
to
Token to
Feature activation+0.000
ex
Token ex
Feature activation+0.000
-
Token-
Feature activation+0.000
girlfriend
Tokengirlfriend
Feature activation+0.536
Col
Token Col
Feature activation+0.000
leen
Tokenleen
Feature activation+0.000
Crowley
Token Crowley
Feature activation+4.418
of
Token of
Feature activation+0.000
hitting
Token hitting
Feature activation+0.399
her
Token her
Feature activation+0.000
and
Token and
Feature activation+0.000
threatening
Token threatening
Feature activation+0.063
we
Token we
Feature activation+0.000
made
Token made
Feature activation+0.000
mention
Token mention
Feature activation+0.057
as
Token as
Feature activation+0.692
a
Token a
Feature activation+0.000
group
Token group
Feature activation+4.312
of
Token of
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
15
Token 15
Feature activation+0.000
prospects
Token prospects
Feature activation+0.000
for
Token for
Feature activation+0.000
not
Token not
Feature activation+0.000
lose
Token lose
Feature activation+0.000
sight
Token sight
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.011
,
Token,
Feature activation+4.276
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
unnecessary
Token unnecessary
Feature activation+0.000
burden
Token burden
Feature activation+0.000
placed
Token placed
Feature activation+0.000
not
Token not
Feature activation+0.000
"
Token "
Feature activation+0.000
specific
Tokenspecific
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
aware
Token aware
Feature activation+0.000
''
Token''
Feature activation+4.124
of
Token of
Feature activation+0.116
the
Token the
Feature activation+0.000
outcome
Token outcome
Feature activation+0.182
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
being
Token being
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
cover
Token cover
Feature activation+0.567
in
Token in
Feature activation+0.115
2000
Token 2000
Feature activation+4.119
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.321
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
liquids
Token liquids
Feature activation+0.000
are
Token are
Feature activation+0.000
composed
Token composed
Feature activation+0.000
primarily
Token primarily
Feature activation+4.109
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.030
particles
Token particles
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
Sullivan
TokenSullivan
Feature activation+0.000
also
Token also
Feature activation+0.000
was
Token was
Feature activation+0.000
convicted
Token convicted
Feature activation+0.000
in
Token in
Feature activation+0.000
2009
Token 2009
Feature activation+4.001
of
Token of
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000
mischief
Token mischief
Feature activation+0.000
and
Token and
Feature activation+0.000
possession
Token possession
Feature activation+0.000
been
Token been
Feature activation+0.000
"
Token "
Feature activation+0.000
broad
Tokenbroad
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
supportive
Token supportive
Feature activation+0.000
"
Token"
Feature activation+3.955
of
Token of
Feature activation+0.000
methods
Token methods
Feature activation+0.000
to
Token to
Feature activation+0.000
increase
Token increase
Feature activation+0.000
safety
Token safety
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
after
Token after
Feature activation+0.000
being
Token being
Feature activation+0.000
convicted
Token convicted
Feature activation+0.000
in
Token in
Feature activation+0.010
June
Token June
Feature activation+3.940
of
Token of
Feature activation+0.000
two
Token two
Feature activation+0.000
cases
Token cases
Feature activation+0.391
of
Token of
Feature activation+0.000
indecent
Token indecent
Feature activation+0.000
or
Token or
Feature activation+0.000
even
Token even
Feature activation+0.000
tens
Token tens
Feature activation+0.280
of
Token of
Feature activation+0.410
thousands
Token thousands
Feature activation+2.225
,
Token,
Feature activation+3.890
of
Token of
Feature activation+0.112
speedy
Token speedy
Feature activation+0.000
GPUs
Token GPUs
Feature activation+0.000
,
Token,
Feature activation+0.000
100
Token 100
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
aware
Token aware
Feature activation+0.000
in
Token in
Feature activation+0.486
fact
Token fact
Feature activation+3.735
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
VERY
Token VERY
Feature activation+0.000
CLE
Token CLE
Feature activation+0.000
AR
TokenAR
Feature activation+0.049
accuse
Token accuse
Feature activation+0.000
her
Token her
Feature activation+0.155
critics
Token critics
Feature activation+1.081
on
Token on
Feature activation+0.061
social
Token social
Feature activation+0.000
media
Token media
Feature activation+3.689
of
Token of
Feature activation+0.000
being
Token being
Feature activation+0.000
big
Token big
Feature activation+0.000
oted
Tokenoted
Feature activation+0.000
.
Token.
Feature activation+0.000
with
Token with
Feature activation+0.000
favor
Token favor
Feature activation+0.267
the
Token the
Feature activation+0.000
establishment
Token establishment
Feature activation+0.000
in
Token in
Feature activation+0.520
Palestine
Token Palestine
Feature activation+3.642
of
Token of
Feature activation+0.535
a
Token a
Feature activation+0.000
national
Token national
Feature activation+0.000
home
Token home
Feature activation+0.000
for
Token for
Feature activation+0.061

Top DFA by src position
MAX = 5.915

".
Token".
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ukraine
TokenUkraine
Feature activation-0.002
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
accused
Token accused
Feature activation+5.915
Top resid features:
by
Token by
Feature activation+0.026
Top resid features:
Moscow
Token Moscow
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
trying
Token trying
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.040
Top resid features:
records
Token records
Feature activation+0.014
Top resid features:
fall
Token fall
Feature activation+0.030
Top resid features:
at
Token at
Feature activation-0.004
Top resid features:
the
Token the
Feature activation-0.135
Top resid features:
hands
Token hands
Feature activation+5.616
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.008
Top resid features:
feet
Token feet
Feature activation+0.042
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
travel
Token travel
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
US
Token US
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
mindful
Token mindful
Feature activation+5.566
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
perhaps
Token perhaps
Feature activation+0.043
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
back
Token back
Feature activation-0.016
Top resid features:
today
Token today
Feature activation-0.007
Top resid features:
after
Token after
Feature activation-0.010
Top resid features:
he
Token he
Feature activation-0.002
Top resid features:
was
Token was
Feature activation+0.009
Top resid features:
accused
Token accused
Feature activation+5.425
Top resid features:
by
Token by
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
leading
Token leading
Feature activation+0.000
Top resid features:
left
Token left
Feature activation-0.009
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
those
Token those
Feature activation-0.000
Top resid features:
same
Token same
Feature activation-0.001
Top resid features:
elite
Token elite
Feature activation+0.001
Top resid features:
neighborhoods
Token neighborhoods
Feature activation+0.004
Top resid features:
consists
Token consists
Feature activation+5.280
Top resid features:
almost
Token almost
Feature activation+0.010
Top resid features:
wholly
Token wholly
Feature activation+0.026
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
time
Tokentime
Feature activation+0.003
Top resid features:
Durham
Token Durham
Feature activation-0.000
Top resid features:
resident
Token resident
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
presence
Token presence
Feature activation+5.163
Top resid features:
in
Token in
Feature activation+0.018
Top resid features:
my
Token my
Feature activation+0.044
Top resid features:
community
Token community
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
only
Token only
Feature activation-0.008
Top resid features:
last
Token last
Feature activation-0.002
Top resid features:
year
Token year
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.015
Top resid features:
was
Token was
Feature activation-0.004
Top resid features:
accused
Token accused
Feature activation+5.084
Top resid features:
previously
Token previously
Feature activation+0.077
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
making
Token making
Feature activation+0.000
Top resid features:
clear
Token clear
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
&
Token&
Feature activation-0.000
Top resid features:
M
TokenM
Feature activation-0.000
Top resid features:
star
Token star
Feature activation-0.000
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
accused
Token accused
Feature activation+5.111
Top resid features:
by
Token by
Feature activation+0.021
Top resid features:
ex
Token ex
Feature activation-0.001
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
girlfriend
Tokengirlfriend
Feature activation-0.007
Top resid features:
Col
Token Col
Feature activation+0.003
Top resid features:
our
Token our
Feature activation+0.004
Top resid features:
list
Token list
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
we
Token we
Feature activation+0.012
Top resid features:
made
Token made
Feature activation-0.004
Top resid features:
mention
Token mention
Feature activation+4.912
Top resid features:
as
Token as
Feature activation-0.024
Top resid features:
a
Token a
Feature activation-0.004
Top resid features:
group
Token group
Feature activation+0.028
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
nearly
Token nearly
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
We
Token We
Feature activation+0.017
Top resid features:
should
Token should
Feature activation+0.006
Top resid features:
not
Token not
Feature activation-0.002
Top resid features:
lose
Token lose
Feature activation-0.001
Top resid features:
sight
Token sight
Feature activation+4.913
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
however
Token however
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.003
Top resid features:
not
Token not
Feature activation-0.004
Top resid features:
"
Token "
Feature activation-0.000
Top resid features:
specific
Tokenspecific
Feature activation+0.036
Top resid features:
ally
Tokenally
Feature activation+0.002
Top resid features:
aware
Token aware
Feature activation+4.689
Top resid features:
''
Token''
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
outcome
Token outcome
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Jeff
Token Jeff
Feature activation+0.000
Top resid features:
Bezos
Token Bezos
Feature activation-0.023
Top resid features:
being
Token being
Feature activation+0.011
Top resid features:
on
Token on
Feature activation+0.039
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
cover
Token cover
Feature activation+4.666
Top resid features:
in
Token in
Feature activation+0.052
Top resid features:
2000
Token 2000
Feature activation+0.029
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
top
Token top
Feature activation+0.000
Top resid features:
particles
Token particles
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
All
Token All
Feature activation-0.000
Top resid features:
liquids
Token liquids
Feature activation-0.005
Top resid features:
are
Token are
Feature activation+0.003
Top resid features:
composed
Token composed
Feature activation+4.552
Top resid features:
primarily
Token primarily
Feature activation+0.057
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
these
Token these
Feature activation+0.000
Top resid features:
particles
Token particles
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Sullivan
TokenSullivan
Feature activation-0.000
Top resid features:
also
Token also
Feature activation+0.002
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
convicted
Token convicted
Feature activation+4.628
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
2009
Token 2009
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
criminal
Token criminal
Feature activation+0.000
Top resid features:
mischief
Token mischief
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.016
Top resid features:
been
Token been
Feature activation+0.009
Top resid features:
"
Token "
Feature activation+0.003
Top resid features:
broad
Tokenbroad
Feature activation+0.010
Top resid features:
ly
Tokenly
Feature activation-0.002
Top resid features:
supportive
Token supportive
Feature activation+4.489
Top resid features:
"
Token"
Feature activation+0.017
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
methods
Token methods
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
increase
Token increase
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
court
Token court
Feature activation-0.002
Top resid features:
Tuesday
Token Tuesday
Feature activation-0.001
Top resid features:
after
Token after
Feature activation+0.002
Top resid features:
being
Token being
Feature activation+0.003
Top resid features:
convicted
Token convicted
Feature activation+4.547
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
June
Token June
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
cases
Token cases
Feature activation+0.000
Top resid features:
proprietary
Token proprietary
Feature activation+0.006
Top resid features:
machine
Token machine
Feature activation-0.002
Top resid features:
learning
Token learning
Feature activation-0.024
Top resid features:
algorithms
Token algorithms
Feature activation-0.002
Top resid features:
with
Token with
Feature activation-0.001
Top resid features:
thousands
Token thousands
Feature activation+4.005
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
or
Token or
Feature activation+0.005
Top resid features:
even
Token even
Feature activation-0.001
Top resid features:
tens
Token tens
Feature activation+0.249
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
FBI
Token FBI
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
all
Token all
Feature activation+0.232
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
are
Token are
Feature activation+0.042
Top resid features:
aware
Token aware
Feature activation+4.196
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:
fact
Token fact
Feature activation+0.085
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
VERY
Token VERY
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
appeared
Token appeared
Feature activation-0.004
Top resid features:
to
Token to
Feature activation-0.009
Top resid features:
accuse
Token accuse
Feature activation-0.016
Top resid features:
her
Token her
Feature activation+0.024
Top resid features:
critics
Token critics
Feature activation+4.319
Top resid features:
on
Token on
Feature activation+0.007
Top resid features:
social
Token social
Feature activation+0.000
Top resid features:
media
Token media
Feature activation-0.004
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
being
Token being
Feature activation+0.000
Top resid features:
government
Token government
Feature activation+0.001
Top resid features:
view
Token view
Feature activation+0.076
Top resid features:
with
Token with
Feature activation+0.001
Top resid features:
favor
Token favor
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
establishment
Token establishment
Feature activation+4.003
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
Palestine
Token Palestine
Feature activation+0.158
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
national
Token national
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.02

Head 3: 0.03

Head 4: 0.03

Head 5: 0.08

Head 6: 0.02

Head 7: 0.02

Head 8: 0.01

Head 9: 0.69

Head 10: 0.02

Head 11: 0.03

Positive logits

of3.89

of3.57

thereof2.91

Of2.75

OF2.70

OF2.65

Of2.65

oft1.58

onym1.49

owment1.34

ful1.25

most1.25

DPRK1.25

belonging1.19

afore1.19

among1.14

ynthesis1.13

(%1.13

beard1.12

ography1.11

Negative logits

emort-1.64

BuyableInstoreAndOnline-1.55

redes-1.40

icable-1.36

verages-1.33

ilaterally-1.32

streng-1.30

Eva-1.29

edin-1.27

vier-1.25

calmed-1.25

ansson-1.24

ombo-1.23

inarily-1.23

tradem-1.22

blat-1.21

ermanent-1.21

igroup-1.20

mbuds-1.20

Leaks-1.19

INTERVAL 4.698 - 5.220
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ukraine
TokenUkraine
Feature activation+0.000
is
Token is
Feature activation+0.000
accused
Token accused
Feature activation+0.000
by
Token by
Feature activation+0.000
Moscow
Token Moscow
Feature activation+5.220
of
Token of
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
destabil
Token destabil
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
same
Token same
Feature activation+0.000
elite
Token elite
Feature activation+0.000
neighborhoods
Token neighborhoods
Feature activation+0.000
consists
Token consists
Feature activation+0.000
almost
Token almost
Feature activation+1.011
wholly
Token wholly
Feature activation+4.766
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
with
Token with
Feature activation+0.000
college
Token college
Feature activation+0.000
degrees
Token degrees
Feature activation+0.053
a
Token a
Feature activation+0.000
leading
Token leading
Feature activation+0.000
left
Token left
Feature activation+0.000
-
Token-
Feature activation+0.000
wing
Tokenwing
Feature activation+0.000
campaigner
Token campaigner
Feature activation+4.872
of
Token of
Feature activation+0.000
being
Token being
Feature activation+0.000
disl
Token disl
Feature activation+0.000
oyal
Tokenoyal
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
hands
Token hands
Feature activation+0.007
,
Token,
Feature activation+0.204
or
Token or
Feature activation+0.143
feet
Token feet
Feature activation+0.000
,
Token,
Feature activation+4.988
of
Token of
Feature activation+0.000
Ap
Token Ap
Feature activation+0.000
od
Tokenod
Feature activation+0.000
aca
Tokenaca
Feature activation+0.000
.
Token.
Feature activation+0.000
US
Token US
Feature activation+0.000
,
Token,
Feature activation+0.000
mindful
Token mindful
Feature activation+0.000
,
Token,
Feature activation+0.051
perhaps
Token perhaps
Feature activation+0.340
,
Token,
Feature activation+4.960
of
Token of
Feature activation+0.198
the
Token the
Feature activation+0.000
Mormon
Token Mormon
Feature activation+0.000
community
Token community
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 4.176 - 4.698
CONTAINS 0.001%

we
Token we
Feature activation+0.000
made
Token made
Feature activation+0.000
mention
Token mention
Feature activation+0.057
as
Token as
Feature activation+0.692
a
Token a
Feature activation+0.000
group
Token group
Feature activation+4.312
of
Token of
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
15
Token 15
Feature activation+0.000
prospects
Token prospects
Feature activation+0.000
for
Token for
Feature activation+0.000
ex
Token ex
Feature activation+0.000
-
Token-
Feature activation+0.000
girlfriend
Tokengirlfriend
Feature activation+0.536
Col
Token Col
Feature activation+0.000
leen
Tokenleen
Feature activation+0.000
Crowley
Token Crowley
Feature activation+4.418
of
Token of
Feature activation+0.000
hitting
Token hitting
Feature activation+0.399
her
Token her
Feature activation+0.000
and
Token and
Feature activation+0.000
threatening
Token threatening
Feature activation+0.063
not
Token not
Feature activation+0.000
lose
Token lose
Feature activation+0.000
sight
Token sight
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.011
,
Token,
Feature activation+4.276
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
unnecessary
Token unnecessary
Feature activation+0.000
burden
Token burden
Feature activation+0.000
placed
Token placed
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
accused
Token accused
Feature activation+0.000
previously
Token previously
Feature activation+4.532
of
Token of
Feature activation+0.000
not
Token not
Feature activation+0.000
making
Token making
Feature activation+0.000
clear
Token clear
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
presence
Token presence
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
community
Token community
Feature activation+4.663
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
company
Token company
Feature activation+0.000
that
Token that
Feature activation+0.000
participates
Token participates
Feature activation+0.000

INTERVAL 3.654 - 4.176
CONTAINS 0.001%

being
Token being
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
cover
Token cover
Feature activation+0.567
in
Token in
Feature activation+0.115
2000
Token 2000
Feature activation+4.119
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.321
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
liquids
Token liquids
Feature activation+0.000
are
Token are
Feature activation+0.000
composed
Token composed
Feature activation+0.000
primarily
Token primarily
Feature activation+4.109
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.030
particles
Token particles
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
accuse
Token accuse
Feature activation+0.000
her
Token her
Feature activation+0.155
critics
Token critics
Feature activation+1.081
on
Token on
Feature activation+0.061
social
Token social
Feature activation+0.000
media
Token media
Feature activation+3.689
of
Token of
Feature activation+0.000
being
Token being
Feature activation+0.000
big
Token big
Feature activation+0.000
oted
Tokenoted
Feature activation+0.000
.
Token.
Feature activation+0.000
Sullivan
TokenSullivan
Feature activation+0.000
also
Token also
Feature activation+0.000
was
Token was
Feature activation+0.000
convicted
Token convicted
Feature activation+0.000
in
Token in
Feature activation+0.000
2009
Token 2009
Feature activation+4.001
of
Token of
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000
mischief
Token mischief
Feature activation+0.000
and
Token and
Feature activation+0.000
possession
Token possession
Feature activation+0.000
been
Token been
Feature activation+0.000
"
Token "
Feature activation+0.000
broad
Tokenbroad
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
supportive
Token supportive
Feature activation+0.000
"
Token"
Feature activation+3.955
of
Token of
Feature activation+0.000
methods
Token methods
Feature activation+0.000
to
Token to
Feature activation+0.000
increase
Token increase
Feature activation+0.000
safety
Token safety
Feature activation+0.000

INTERVAL 3.132 - 3.654
CONTAINS 0.002%

ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Over
Token Over
Feature activation+0.000
coat
Tokencoat
Feature activation+0.279
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+3.247
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
text
Token text
Feature activation+0.000
message
Token message
Feature activation+0.000
exchange
Token exchange
Feature activation+0.000
found
Token found
Feature activation+0.000
a
Token a
Feature activation+0.000
"
Token "
Feature activation+0.000
small
Tokensmall
Feature activation+0.000
quantity
Token quantity
Feature activation+0.000
"
Token"
Feature activation+3.233
of
Token of
Feature activation+0.000
heroin
Token heroin
Feature activation+0.376
...
Token ...
Feature activation+0.000
along
Token along
Feature activation+0.000
with
Token with
Feature activation+0.000
target
Token target
Feature activation+0.000
.
Token.
Feature activation+0.000
Beware
Token Beware
Feature activation+0.000
,
Token,
Feature activation+0.343
however
Token however
Feature activation+1.705
,
Token,
Feature activation+3.205
the
Token the
Feature activation+0.000
l
Token l
Feature activation+0.000
asso
Tokenasso
Feature activation+0.000
does
Token does
Feature activation+0.000
cause
Token cause
Feature activation+0.000
"
Token "
Feature activation+0.000
radical
Tokenradical
Feature activation+0.000
re
Token re
Feature activation+0.000
interpret
Tokeninterpret
Feature activation+0.000
ation
Tokenation
Feature activation+0.000
"
Token"
Feature activation+3.574
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Civil
Token Civil
Feature activation+0.000
Rights
Token Rights
Feature activation+0.000
Act
Token Act
Feature activation+0.217
,
Token,
Feature activation+0.272
raised
Token raised
Feature activation+0.000
the
Token the
Feature activation+0.000
possibility
Token possibility
Feature activation+0.000
in
Token in
Feature activation+0.000
2009
Token 2009
Feature activation+3.168
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
between
Token between
Feature activation+0.000
Bill
Token Bill
Feature activation+0.000

INTERVAL 2.610 - 3.132
CONTAINS 0.004%

ask
Tokenask
Feature activation+0.000
ed
Tokened
Feature activation+0.000
the
Token the
Feature activation+0.024
identities
Token identities
Feature activation+0.124
and
Token and
Feature activation+0.159
conversations
Token conversations
Feature activation+2.747
of
Token of
Feature activation+0.037
several
Token several
Feature activation+0.000
Americans
Token Americans
Feature activation+0.419
in
Token in
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
by
Token by
Feature activation+0.000
accusing
Token accusing
Feature activation+0.000
Michael
Token Michael
Feature activation+0.000
D
Token D
Feature activation+0.000
uk
Tokenuk
Feature activation+0.000
akis
Tokenakis
Feature activation+2.745
of
Token of
Feature activation+0.000
putting
Token putting
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
public
Tokenpublic
Feature activation+0.000
was
Token was
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
p
Tokenp
Feature activation+0.000
roud
Tokenroud
Feature activation+0.000
generally
Token generally
Feature activation+2.837
âĢ
TokenâĢ
Feature activation+2.398
Ŀ
TokenĿ
Feature activation+2.861
of
Token of
Feature activation+0.100
what
Token what
Feature activation+0.084
US
Token US
Feature activation+0.000
ates
Tokenates
Feature activation+0.000
of
Token of
Feature activation+0.000
nominees
Token nominees
Feature activation+0.000
made
Token made
Feature activation+0.000
up
Token up
Feature activation+0.000
mostly
Token mostly
Feature activation+2.633
of
Token of
Feature activation+0.000
white
Token white
Feature activation+0.000
men
Token men
Feature activation+0.000
.
Token.
Feature activation+0.000
K
Token K
Feature activation+0.000
interest
Token interest
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
wider
Token wider
Feature activation+0.000
Java
Token Java
Feature activation+0.000
ecosystem
Token ecosystem
Feature activation+2.877
to
Token to
Feature activation+0.000
proceed
Token proceed
Feature activation+0.000
so
Token so
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000

INTERVAL 2.088 - 2.610
CONTAINS 0.010%

book
Tokenbook
Feature activation+0.000
-
Token-
Feature activation+0.000
club
Tokenclub
Feature activation+0.000
-
Token-
Feature activation+0.000
heart
Tokenheart
Feature activation+0.000
-
Token-
Feature activation+2.370
of
Tokenof
Feature activation+0.000
-
Token-
Feature activation+0.000
dark
Tokendark
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
/
Token/
Feature activation+0.000
"
Token "
Feature activation+0.000
I
TokenI
Feature activation+0.000
am
Token am
Feature activation+0.000
sick
Token sick
Feature activation+0.000
to
Token to
Feature activation+0.000
death
Token death
Feature activation+2.448
of
Token of
Feature activation+0.000
portals
Token portals
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
upon
Token upon
Feature activation+0.000
thousands
Token thousands
Feature activation+2.121
of
Token of
Feature activation+0.000
tear
Token tear
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
,
Token,
Feature activation+0.000
faithful
Token faithful
Feature activation+0.000
mention
Token mention
Feature activation+0.000
both
Token both
Feature activation+0.000
strands
Token strands
Feature activation+0.228
of
Token of
Feature activation+0.130
the
Token the
Feature activation+0.000
literature
Token literature
Feature activation+2.102
.
Token.
Feature activation+0.000
Nevertheless
Token Nevertheless
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
possible
Token possible
Feature activation+0.000
influence
Token influence
Feature activation+0.000
of
Token of
Feature activation+0.000
genetics
Token genetics
Feature activation+2.541
and
Token and
Feature activation+0.887
environmental
Token environmental
Feature activation+0.000
factors
Token factors
Feature activation+1.629
,"
Token,"
Feature activation+0.000
she
Token she
Feature activation+0.000

INTERVAL 1.566 - 2.088
CONTAINS 0.025%

small
Tokensmall
Feature activation+0.000
reminders
Token reminders
Feature activation+0.000
from
Token from
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
time
Token time
Feature activation+1.651
"
Token"
Feature activation+1.631
of
Token of
Feature activation+0.000
racism
Token racism
Feature activation+0.000
when
Token when
Feature activation+0.000
they
Token they
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
break
Token break
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+1.711
that
Token that
Feature activation+0.000
forced
Token forced
Feature activation+0.000
Ge
Token Ge
Feature activation+0.000
og
Tokenog
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
the
Token the
Feature activation+0.000
greater
Token greater
Feature activation+0.000
whole
Token whole
Feature activation+1.761
of
Token of
Feature activation+0.103
western
Token western
Feature activation+0.000
society
Token society
Feature activation+1.929
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
threat
Tokenthreat
Feature activation+0.000
en
Tokenen
Feature activation+0.000
hundreds
Token hundreds
Feature activation+0.000
of
Token of
Feature activation+0.000
thousands
Token thousands
Feature activation+1.688
of
Token of
Feature activation+0.515
middle
Token middle
Feature activation+0.000
class
Token class
Feature activation+0.000
jobs
Token jobs
Feature activation+0.950
.
Token.
Feature activation+0.000
any
Token any
Feature activation+0.000
constructive
Token constructive
Feature activation+0.000
way
Token way
Feature activation+0.000
,
Token,
Feature activation+0.000
instead
Token instead
Feature activation+0.000
fe
Token fe
Feature activation+1.633
eb
Tokeneb
Feature activation+2.136
ly
Tokenly
Feature activation+0.828
adding
Token adding
Feature activation+0.000
their
Token their
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000

INTERVAL 1.044 - 1.566
CONTAINS 0.087%

into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
secret
Token secret
Feature activation+0.000
computer
Token computer
Feature activation+0.893
system
Token system
Feature activation+1.293
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
Federal
Token Federal
Feature activation+0.000
Bureau
Token Bureau
Feature activation+0.000
Opp
Token Opp
Feature activation+0.000
onents
Tokenonents
Feature activation+0.006
delayed
Token delayed
Feature activation+0.000
passage
Token passage
Feature activation+0.086
for
Token for
Feature activation+0.000
months
Token months
Feature activation+1.559
while
Token while
Feature activation+0.278
ber
Token ber
Feature activation+0.000
ating
Tokenating
Feature activation+0.000
the
Token the
Feature activation+0.000
administration
Token administration
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
location
Token location
Feature activation+0.000
after
Token after
Feature activation+0.000
their
Token their
Feature activation+0.000
name
Token name
Feature activation+1.258
indicates
Token indicates
Feature activation+0.000
the
Token the
Feature activation+0.000
race
Token race
Feature activation+0.000
they
Token they
Feature activation+0.000
learned
Token learned
Feature activation+0.000
.
Token.
Feature activation+0.000
An
Token An
Feature activation+0.000
additional
Token additional
Feature activation+0.000
weekend
Token weekend
Feature activation+0.221
or
Token or
Feature activation+0.000
two
Token two
Feature activation+1.115
will
Token will
Feature activation+0.290
be
Token be
Feature activation+0.000
spent
Token spent
Feature activation+0.000
evaluating
Token evaluating
Feature activation+0.000
options
Token options
Feature activation+0.000
,
Token,
Feature activation+0.000
southwest
Token southwest
Feature activation+0.089
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
western
Token western
Feature activation+0.842
areas
Token areas
Feature activation+1.288
of
Token of
Feature activation+0.126
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
war
Tokenwar
Feature activation+0.176
Czech
Token Czech
Feature activation+0.000

INTERVAL 0.522 - 1.044
CONTAINS 0.357%

Inter
Token Inter
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
captain
Token captain
Feature activation+0.320
last
Token last
Feature activation+0.000
season
Token season
Feature activation+0.554
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
he
Token he
Feature activation+0.000
within
Token within
Feature activation+0.000
the
Token the
Feature activation+0.000
continental
Token continental
Feature activation+0.179
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.450
S
TokenS
Feature activation+0.812
.
Token.
Feature activation+0.686
excludes
Token excludes
Feature activation+0.000
Hawaii
Token Hawaii
Feature activation+0.000
,
Token,
Feature activation+0.000
Alaska
Token Alaska
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
sworn
Token sworn
Feature activation+0.000
brother
Token brother
Feature activation+0.561
of
Token of
Feature activation+0.000
Ta
Token Ta
Feature activation+0.000
iga
Tokeniga
Feature activation+0.000
S
Token S
Feature activation+0.000
ae
Tokenae
Feature activation+0.000
classical
Token classical
Feature activation+0.000
definition
Token definition
Feature activation+0.162
Hil
Token Hil
Feature activation+0.000
fer
Tokenfer
Feature activation+0.000
ding
Tokending
Feature activation+0.000
used
Token used
Feature activation+0.666
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
capital
Tokencapital
Feature activation+0.000
at
Token at
Feature activation+0.000
MPs
Token MPs
Feature activation+0.000
snapped
Token snapped
Feature activation+0.000
photos
Token photos
Feature activation+0.000
with
Token with
Feature activation+0.000
their
Token their
Feature activation+0.000
phones
Token phones
Feature activation+0.646
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.522
CONTAINS 99.513%

in
Token in
Feature activation+0.000
income
Token income
Feature activation+0.000
taxes
Token taxes
Feature activation+0.000
he
Token he
Feature activation+0.000
cut
Token cut
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
current
Token current
Feature activation+0.000
two
Token two
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
clearly
Token clearly
Feature activation+0.000
shares
Token shares
Feature activation+0.000
in
Token in
Feature activation+0.000
common
Token common
Feature activation+0.000
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
renowned
Token renowned
Feature activation+0.000
ideological
Token ideological
Feature activation+0.000
rivals
Token rivals
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
information
Token information
Feature activation+0.000
,
Token,
Feature activation+0.000
contact
Token contact
Feature activation+0.000
AX
Token AX
Feature activation+0.000
S
TokenS
Feature activation+0.000
at
Token at
Feature activation+0.000
ax
Token ax
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
or
Token or
Feature activation+0.000
my
Token my
Feature activation+0.000
dream
Token dream
Feature activation+0.000
ended
Token ended
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
was
Token was
Feature activation+0.000
mostly
Token mostly
Feature activation+0.000
struck
Token struck
Feature activation+0.000
by
Token by
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
the
Token the
Feature activation+0.000
need
Token need
Feature activation+0.000
for
Token for
Feature activation+0.000
developing
Token developing
Feature activation+0.000
API
Token API
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
to
Token to
Feature activation+0.000
access
Token access
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 H10.9: (feature 12966)

TOP ACTIVATIONS
MAX = 9.238

few
Token few
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
,
Token,
Feature activation+9.238
to
Token to
Feature activation+0.521
spark
Token spark
Feature activation+0.000
an
Token an
Feature activation+0.000
elusive
Token elusive
Feature activation+0.000
form
Token form
Feature activation+0.000
al
Tokenal
Feature activation+0.000
em
Tokenem
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
referring
Token referring
Feature activation+0.000
specifically
Token specifically
Feature activation+8.250
to
Token to
Feature activation+0.000
rebel
Token rebel
Feature activation+0.000
-
Token-
Feature activation+0.000
held
Tokenheld
Feature activation+0.000
Idlib
Token Idlib
Feature activation+0.000
Romney
Token Romney
Feature activation+3.724
voters
Token voters
Feature activation+7.120
(
Token (
Feature activation+0.000
59
Token59
Feature activation+0.000
percent
Token percent
Feature activation+0.008
)
Token)
Feature activation+8.118
to
Token to
Feature activation+0.213
say
Token say
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
satisfied
Token satisfied
Feature activation+0.000
women
Token women
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.000
than
Token than
Feature activation+0.000
men
Token men
Feature activation+7.856
to
Token to
Feature activation+0.000
interrupt
Token interrupt
Feature activation+0.003
their
Token their
Feature activation+0.000
careers
Token careers
Feature activation+0.076
for
Token for
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
capitalism
Token capitalism
Feature activation+0.000
's
Token's
Feature activation+0.000
inability
Token inability
Feature activation+0.000
"
Token "
Feature activation+7.593
to
Tokento
Feature activation+0.361
deliver
Token deliver
Feature activation+0.006
the
Token the
Feature activation+0.000
goods
Token goods
Feature activation+0.000
"
Token"
Feature activation+0.102
likely
Token likely
Feature activation+0.125
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
average
Token average
Feature activation+0.819
internet
Token internet
Feature activation+0.163
user
Token user
Feature activation+7.173
to
Token to
Feature activation+0.067
watch
Token watch
Feature activation+0.000
ABC
Token ABC
Feature activation+0.000
programs
Token programs
Feature activation+0.000
like
Token like
Feature activation+0.000
much
Token much
Feature activation+0.000
more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.000
than
Token than
Feature activation+0.135
Romney
Token Romney
Feature activation+3.724
voters
Token voters
Feature activation+7.120
(
Token (
Feature activation+0.000
59
Token59
Feature activation+0.000
percent
Token percent
Feature activation+0.008
)
Token)
Feature activation+8.118
to
Token to
Feature activation+0.213
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
That
TokenThat
Feature activation+0.000
would
Token would
Feature activation+0.000
lead
Token lead
Feature activation+0.088
directly
Token directly
Feature activation+7.096
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
$
Token $
Feature activation+0.000
800
Token800
Feature activation+0.000
billion
Token billion
Feature activation+0.000
are
Token are
Feature activation+0.000
less
Token less
Feature activation+0.000
likely
Token likely
Feature activation+0.000
than
Token than
Feature activation+0.000
American
Token American
Feature activation+0.000
men
Token men
Feature activation+6.973
to
Token to
Feature activation+0.000
ride
Token ride
Feature activation+0.000
bikes
Token bikes
Feature activation+0.000
in
Token in
Feature activation+0.000
cities
Token cities
Feature activation+0.000
the
Token the
Feature activation+0.000
show
Token show
Feature activation+0.000
rumored
Token rumored
Feature activation+0.000
at
Token at
Feature activation+0.764
one
Token one
Feature activation+0.008
point
Token point
Feature activation+6.811
to
Token to
Feature activation+1.098
be
Token be
Feature activation+0.116
pushed
Token pushed
Feature activation+0.000
to
Token to
Feature activation+0.256
2017
Token 2017
Feature activation+0.000
for
Token for
Feature activation+0.113
that
Token that
Feature activation+0.000
matter
Token matter
Feature activation+0.000
,
Token,
Feature activation+0.000
ability
Token ability
Feature activation+0.124
)
Token)
Feature activation+6.692
to
Token to
Feature activation+0.000
invest
Token invest
Feature activation+0.000
money
Token money
Feature activation+0.000
where
Token where
Feature activation+0.000
you
Token you
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+0.000
as
Token as
Feature activation+0.000
not
Token not
Feature activation+6.504
to
Token to
Feature activation+0.815
offend
Token offend
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
so
Token so
Feature activation+0.104
arn
Tokenarn
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
.
Token.
Feature activation+0.000
Due
Token Due
Feature activation+0.000
in
Token in
Feature activation+1.369
part
Token part
Feature activation+6.324
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
early
Token early
Feature activation+0.000
season
Token season
Feature activation+0.000
struggles
Token struggles
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
impossible
Token impossible
Feature activation+0.447
in
Token in
Feature activation+0.644
principle
Token principle
Feature activation+6.300
to
Token to
Feature activation+0.328
obtain
Token obtain
Feature activation+0.000
the
Token the
Feature activation+0.000
information
Token information
Feature activation+0.000
sought
Token sought
Feature activation+0.000
minimum
Token minimum
Feature activation+0.000
wages
Token wages
Feature activation+0.000
(
Token (
Feature activation+0.000
not
Tokennot
Feature activation+0.000
relating
Token relating
Feature activation+0.000
specifically
Token specifically
Feature activation+6.286
to
Token to
Feature activation+0.000
LGBT
Token LGBT
Feature activation+0.000
people
Token people
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+1.100
expected
Token expected
Feature activation+1.168
as
Token as
Feature activation+0.437
soon
Token soon
Feature activation+0.000
as
Token as
Feature activation+0.000
this
Token this
Feature activation+0.000
week
Token week
Feature activation+6.212
to
Token to
Feature activation+0.613
unveil
Token unveil
Feature activation+0.000
details
Token details
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Congress
TokenCongress
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
refusal
Token refusal
Feature activation+0.000
in
Token in
Feature activation+0.256
2011
Token 2011
Feature activation+6.147
to
Token to
Feature activation+0.000
raise
Token raise
Feature activation+0.000
the
Token the
Feature activation+0.000
debt
Token debt
Feature activation+0.000
ceiling
Token ceiling
Feature activation+0.000
who
Token who
Feature activation+0.000
had
Token had
Feature activation+0.000
the
Token the
Feature activation+0.000
aud
Token aud
Feature activation+0.670
acity
Tokenacity
Feature activation+0.243
not
Token not
Feature activation+6.097
to
Token to
Feature activation+0.000
feel
Token feel
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
represented
Tokenrepresented
Feature activation+0.000
200
Token200
Feature activation+1.010
,
Token,
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
in
Token in
Feature activation+0.000
large
Token large
Feature activation+3.218
part
Token part
Feature activation+6.061
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
involvement
Token involvement
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.000
Beer
Token Beer
Feature activation+0.000
Institute
Token Institute
Feature activation+0.000
is
Token is
Feature activation+0.000
committed
Token committed
Feature activation+0.161
today
Token today
Feature activation+6.031
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
development
Token development
Feature activation+0.000
of
Token of
Feature activation+0.000
sound
Token sound
Feature activation+0.000

Top DFA by src position
MAX = 9.763

-
Token -
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
job
Token job
Feature activation-0.012
Top resid features:
seeker
Token seeker
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.019
Top resid features:
ability
Token ability
Feature activation+9.763
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
within
Token within
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
first
Token first
Feature activation+0.001
Top resid features:
few
Token few
Feature activation-0.002
Top resid features:
Mou
Token Mou
Feature activation+0.000
Top resid features:
al
Tokenal
Feature activation+0.003
Top resid features:
em
Tokenem
Feature activation+0.001
Top resid features:
said
Token said
Feature activation+0.009
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
referring
Token referring
Feature activation+8.749
Top resid features:
specifically
Token specifically
Feature activation+0.123
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
rebel
Token rebel
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
held
Tokenheld
Feature activation+0.000
Top resid features:
percent
Token percent
Feature activation+0.003
Top resid features:
)
Token)
Feature activation+0.016
Top resid features:
are
Token are
Feature activation+0.012
Top resid features:
much
Token much
Feature activation-0.001
Top resid features:
more
Token more
Feature activation+0.011
Top resid features:
likely
Token likely
Feature activation+8.561
Top resid features:
than
Token than
Feature activation+0.009
Top resid features:
Romney
Token Romney
Feature activation+0.017
Top resid features:
voters
Token voters
Feature activation+0.048
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
59
Token59
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
because
Token because
Feature activation+0.006
Top resid features:
women
Token women
Feature activation-0.003
Top resid features:
are
Token are
Feature activation+0.008
Top resid features:
more
Token more
Feature activation+0.001
Top resid features:
likely
Token likely
Feature activation+8.148
Top resid features:
than
Token than
Feature activation+0.100
Top resid features:
men
Token men
Feature activation+0.215
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
interrupt
Token interrupt
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.002
Top resid features:
well
Token well
Feature activation-0.007
Top resid features:
as
Token as
Feature activation+0.001
Top resid features:
capitalism
Token capitalism
Feature activation-0.008
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
inability
Token inability
Feature activation+8.168
Top resid features:
"
Token "
Feature activation+0.061
Top resid features:
to
Tokento
Feature activation+0.000
Top resid features:
deliver
Token deliver
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
goods
Token goods
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
cut
Tokencut
Feature activation+0.002
Top resid features:
ters
Tokenters
Feature activation+0.001
Top resid features:
are
Token are
Feature activation-0.002
Top resid features:
more
Token more
Feature activation+0.003
Top resid features:
likely
Token likely
Feature activation+7.420
Top resid features:
than
Token than
Feature activation+0.094
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
average
Token average
Feature activation+0.060
Top resid features:
internet
Token internet
Feature activation+0.008
Top resid features:
user
Token user
Feature activation+0.217
Top resid features:
percent
Token percent
Feature activation+0.032
Top resid features:
)
Token)
Feature activation+0.026
Top resid features:
are
Token are
Feature activation-0.005
Top resid features:
much
Token much
Feature activation+0.001
Top resid features:
more
Token more
Feature activation+0.003
Top resid features:
likely
Token likely
Feature activation+7.538
Top resid features:
than
Token than
Feature activation+0.022
Top resid features:
Romney
Token Romney
Feature activation+0.038
Top resid features:
voters
Token voters
Feature activation+0.008
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
59
Token59
Feature activation+0.000
Top resid features:
26
Token26
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
"
Token "
Feature activation+0.004
Top resid features:
That
TokenThat
Feature activation+0.009
Top resid features:
would
Token would
Feature activation-0.008
Top resid features:
lead
Token lead
Feature activation+7.716
Top resid features:
directly
Token directly
Feature activation+0.013
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
800
Token800
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
American
Token American
Feature activation+0.001
Top resid features:
women
Token women
Feature activation+0.004
Top resid features:
are
Token are
Feature activation+0.009
Top resid features:
less
Token less
Feature activation-0.009
Top resid features:
likely
Token likely
Feature activation+7.498
Top resid features:
than
Token than
Feature activation+0.013
Top resid features:
American
Token American
Feature activation+0.005
Top resid features:
men
Token men
Feature activation+0.078
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
ride
Token ride
Feature activation+0.000
Top resid features:
scripts
Token scripts
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
with
Token with
Feature activation-0.025
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
show
Token show
Feature activation+0.109
Top resid features:
rumored
Token rumored
Feature activation+7.124
Top resid features:
at
Token at
Feature activation+0.006
Top resid features:
one
Token one
Feature activation-0.004
Top resid features:
point
Token point
Feature activation+0.066
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
Chrysler
Token Chrysler
Feature activation-0.030
Top resid features:
âĢ
TokenâĢ
Feature activation-0.047
Top resid features:
Ļ
TokenĻ
Feature activation+0.017
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
newfound
Token newfound
Feature activation+0.003
Top resid features:
willingness
Token willingness
Feature activation+6.866
Top resid features:
(
Token (
Feature activation+0.001
Top resid features:
and
Tokenand
Feature activation+0.002
Top resid features:
for
Token for
Feature activation+0.001
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
matter
Token matter
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
They
Token They
Feature activation+0.001
Top resid features:
changed
Token changed
Feature activation-0.003
Top resid features:
it
Token it
Feature activation+0.053
Top resid features:
so
Token so
Feature activation+0.007
Top resid features:
as
Token as
Feature activation+5.990
Top resid features:
not
Token not
Feature activation+1.055
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
offend
Token offend
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
In
Token In
Feature activation+0.000
Top resid features:
Chandler
Token Chandler
Feature activation+0.001
Top resid features:
H
Token H
Feature activation+0.002
Top resid features:
arn
Tokenarn
Feature activation+0.000
Top resid features:
ish
Tokenish
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Due
Token Due
Feature activation+6.750
Top resid features:
in
Token in
Feature activation+0.094
Top resid features:
part
Token part
Feature activation+0.021
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
early
Token early
Feature activation+0.000
Top resid features:
common
Token common
Feature activation-0.001
Top resid features:
cases
Token cases
Feature activation+0.002
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
would
Token would
Feature activation-0.003
Top resid features:
be
Token be
Feature activation-0.000
Top resid features:
impossible
Token impossible
Feature activation+6.815
Top resid features:
in
Token in
Feature activation-0.007
Top resid features:
principle
Token principle
Feature activation+0.041
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
obtain
Token obtain
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
higher
Token higher
Feature activation-0.001
Top resid features:
minimum
Token minimum
Feature activation-0.001
Top resid features:
wages
Token wages
Feature activation-0.002
Top resid features:
(
Token (
Feature activation+0.015
Top resid features:
not
Tokennot
Feature activation+0.042
Top resid features:
relating
Token relating
Feature activation+6.634
Top resid features:
specifically
Token specifically
Feature activation+0.182
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
LGBT
Token LGBT
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Eight
Token Eight
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
âĢ
TokenâĢ
Feature activation-0.016
Top resid features:
Ŀ
TokenĿ
Feature activation+0.006
Top resid features:
is
Token is
Feature activation+0.022
Top resid features:
expected
Token expected
Feature activation+6.638
Top resid features:
as
Token as
Feature activation+0.018
Top resid features:
soon
Token soon
Feature activation+0.042
Top resid features:
as
Token as
Feature activation-0.003
Top resid features:
this
Token this
Feature activation+0.007
Top resid features:
week
Token week
Feature activation+0.122
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Congress
TokenCongress
Feature activation+0.001
Top resid features:
âĢ
TokenâĢ
Feature activation-0.053
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
refusal
Token refusal
Feature activation+6.739
Top resid features:
in
Token in
Feature activation+0.033
Top resid features:
2011
Token 2011
Feature activation+0.037
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
raise
Token raise
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
women
Token women
Feature activation-0.033
Top resid features:
who
Token who
Feature activation-0.017
Top resid features:
had
Token had
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.170
Top resid features:
aud
Token aud
Feature activation+0.136
Top resid features:
acity
Tokenacity
Feature activation+6.296
Top resid features:
not
Token not
Feature activation+0.105
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
feel
Token feel
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
over
Token over
Feature activation-0.000
Top resid features:
28
Token 28
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
200
Token200
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
thanks
Token thanks
Feature activation+6.595
Top resid features:
in
Token in
Feature activation+0.036
Top resid features:
large
Token large
Feature activation-0.002
Top resid features:
part
Token part
Feature activation+0.016
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
Beer
Token Beer
Feature activation-0.001
Top resid features:
Institute
Token Institute
Feature activation-0.006
Top resid features:
is
Token is
Feature activation-0.004
Top resid features:
committed
Token committed
Feature activation+6.674
Top resid features:
today
Token today
Feature activation+0.016
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
development
Token development
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.01

Head 1: 0.01

Head 2: 0.03

Head 3: 0.04

Head 4: 0.04

Head 5: 0.09

Head 6: 0.02

Head 7: 0.02

Head 8: 0.01

Head 9: 0.69

Head 10: 0.02

Head 11: 0.03

Positive logits

to4.91

to4.37

To3.54

To3.52

TO3.45

thereto3.17

TO2.56

ta2.55

unto2.39

ot1.97

eto1.97

toward1.92

toc1.91

towards1.90

assetsadobe1.81

toget1.73

Disclaimer1.54

onward1.51

lest1.49

1.49

Negative logits

retty-1.98

izoph-1.73

icol-1.59

eda-1.55

natureconservancy-1.46

ersed-1.46

uked-1.42

edIn-1.40

irie-1.40

quished-1.40

hend-1.40

ench-1.39

assed-1.35

stood-1.34

iled-1.33

ife-1.33

erguson-1.33

bys-1.33

cade-1.31

-1.31

INTERVAL 8.314 - 9.238
CONTAINS 0.000%

few
Token few
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
,
Token,
Feature activation+9.238
to
Token to
Feature activation+0.521
spark
Token spark
Feature activation+0.000
an
Token an
Feature activation+0.000
elusive
Token elusive
Feature activation+0.000
form
Token form
Feature activation+0.000

INTERVAL 7.390 - 8.314
CONTAINS 0.000%

Romney
Token Romney
Feature activation+3.724
voters
Token voters
Feature activation+7.120
(
Token (
Feature activation+0.000
59
Token59
Feature activation+0.000
percent
Token percent
Feature activation+0.008
)
Token)
Feature activation+8.118
to
Token to
Feature activation+0.213
say
Token say
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
satisfied
Token satisfied
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
capitalism
Token capitalism
Feature activation+0.000
's
Token's
Feature activation+0.000
inability
Token inability
Feature activation+0.000
"
Token "
Feature activation+7.593
to
Tokento
Feature activation+0.361
deliver
Token deliver
Feature activation+0.006
the
Token the
Feature activation+0.000
goods
Token goods
Feature activation+0.000
"
Token"
Feature activation+0.102
al
Tokenal
Feature activation+0.000
em
Tokenem
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
referring
Token referring
Feature activation+0.000
specifically
Token specifically
Feature activation+8.250
to
Token to
Feature activation+0.000
rebel
Token rebel
Feature activation+0.000
-
Token-
Feature activation+0.000
held
Tokenheld
Feature activation+0.000
Idlib
Token Idlib
Feature activation+0.000
women
Token women
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.000
than
Token than
Feature activation+0.000
men
Token men
Feature activation+7.856
to
Token to
Feature activation+0.000
interrupt
Token interrupt
Feature activation+0.003
their
Token their
Feature activation+0.000
careers
Token careers
Feature activation+0.076
for
Token for
Feature activation+0.000

INTERVAL 6.466 - 7.390
CONTAINS 0.001%

much
Token much
Feature activation+0.000
more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.000
than
Token than
Feature activation+0.135
Romney
Token Romney
Feature activation+3.724
voters
Token voters
Feature activation+7.120
(
Token (
Feature activation+0.000
59
Token59
Feature activation+0.000
percent
Token percent
Feature activation+0.008
)
Token)
Feature activation+8.118
to
Token to
Feature activation+0.213
are
Token are
Feature activation+0.000
less
Token less
Feature activation+0.000
likely
Token likely
Feature activation+0.000
than
Token than
Feature activation+0.000
American
Token American
Feature activation+0.000
men
Token men
Feature activation+6.973
to
Token to
Feature activation+0.000
ride
Token ride
Feature activation+0.000
bikes
Token bikes
Feature activation+0.000
in
Token in
Feature activation+0.000
cities
Token cities
Feature activation+0.000
the
Token the
Feature activation+0.000
show
Token show
Feature activation+0.000
rumored
Token rumored
Feature activation+0.000
at
Token at
Feature activation+0.764
one
Token one
Feature activation+0.008
point
Token point
Feature activation+6.811
to
Token to
Feature activation+1.098
be
Token be
Feature activation+0.116
pushed
Token pushed
Feature activation+0.000
to
Token to
Feature activation+0.256
2017
Token 2017
Feature activation+0.000
for
Token for
Feature activation+0.113
that
Token that
Feature activation+0.000
matter
Token matter
Feature activation+0.000
,
Token,
Feature activation+0.000
ability
Token ability
Feature activation+0.124
)
Token)
Feature activation+6.692
to
Token to
Feature activation+0.000
invest
Token invest
Feature activation+0.000
money
Token money
Feature activation+0.000
where
Token where
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
That
TokenThat
Feature activation+0.000
would
Token would
Feature activation+0.000
lead
Token lead
Feature activation+0.088
directly
Token directly
Feature activation+7.096
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
$
Token $
Feature activation+0.000
800
Token800
Feature activation+0.000
billion
Token billion
Feature activation+0.000

INTERVAL 5.543 - 6.466
CONTAINS 0.002%

Bass
Token Bass
Feature activation+0.000
in
Tokenin
Feature activation+0.000
explains
Token explains
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.176
"
Token "
Feature activation+5.733
to
Tokento
Feature activation+0.000
isolate
Token isolate
Feature activation+0.000
the
Token the
Feature activation+0.000
effects
Token effects
Feature activation+0.000
of
Token of
Feature activation+0.000
expected
Token expected
Feature activation+1.168
as
Token as
Feature activation+0.437
soon
Token soon
Feature activation+0.000
as
Token as
Feature activation+0.000
this
Token this
Feature activation+0.000
week
Token week
Feature activation+6.212
to
Token to
Feature activation+0.613
unveil
Token unveil
Feature activation+0.000
details
Token details
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
impossible
Token impossible
Feature activation+0.447
in
Token in
Feature activation+0.644
principle
Token principle
Feature activation+6.300
to
Token to
Feature activation+0.328
obtain
Token obtain
Feature activation+0.000
the
Token the
Feature activation+0.000
information
Token information
Feature activation+0.000
sought
Token sought
Feature activation+0.000
and
Token and
Feature activation+0.000
perhaps
Token perhaps
Feature activation+0.000
no
Token no
Feature activation+0.000
similarity
Token similarity
Feature activation+1.505
at
Token at
Feature activation+0.000
all
Token all
Feature activation+6.008
to
Token to
Feature activation+0.000
Hook
Token Hook
Feature activation+0.000
&
Token &
Feature activation+0.000
S
Token S
Feature activation+0.000
ling
Tokenling
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
ought
Tokenought
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.228
Ŀ
TokenĿ
Feature activation+5.961
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
suggestion
Token suggestion
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
not
Token not
Feature activation+0.000

INTERVAL 4.619 - 5.543
CONTAINS 0.004%

about
Token about
Feature activation+0.000
sincerity
Token sincerity
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.000
leads
Token leads
Feature activation+0.000
not
Token not
Feature activation+5.231
to
Token to
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000
but
Token but
Feature activation+2.192
to
Token to
Feature activation+0.080
myst
Token myst
Feature activation+0.000
S
TokenS
Feature activation+0.000
VR
TokenVR
Feature activation+0.000
),
Token),
Feature activation+0.000
a
Token a
Feature activation+0.000
successor
Token successor
Feature activation+0.155
agency
Token agency
Feature activation+4.651
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
KGB
Token KGB
Feature activation+2.521
,
Token,
Feature activation+0.000
issued
Token issued
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
great
Token great
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.072
âĢ
TokenâĢ
Feature activation+2.126
Ŀ
TokenĿ
Feature activation+4.755
to
Token to
Feature activation+0.000
expose
Token expose
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
d
Tokend
Feature activation+0.000
ahl
Tokenahl
Feature activation+0.000
pleaded
Token pleaded
Feature activation+0.000
guilty
Token guilty
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+4.690
to
Token to
Feature activation+0.000
desert
Token desert
Feature activation+0.000
ion
Tokenion
Feature activation+0.000
and
Token and
Feature activation+0.000
end
Token end
Feature activation+0.000
likely
Token likely
Feature activation+0.720
team
Token team
Feature activation+0.736
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
East
Token East
Feature activation+3.914
Division
Token Division
Feature activation+4.922
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Last
TokenLast
Feature activation+0.000
week
Token week
Feature activation+0.000

INTERVAL 3.695 - 4.619
CONTAINS 0.010%

the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
unveiled
Token unveiled
Feature activation+0.000
its
Token its
Feature activation+0.000
plan
Token plan
Feature activation+0.000
not
Token not
Feature activation+4.273
only
Token only
Feature activation+5.679
to
Token to
Feature activation+0.000
sell
Token sell
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
devices
Token devices
Feature activation+0.190
countries
Token countries
Feature activation+3.262
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
China
Token China
Feature activation+3.650
and
Token and
Feature activation+0.000
Thailand
Token Thailand
Feature activation+3.749
to
Token to
Feature activation+0.232
flood
Token flood
Feature activation+0.000
the
Token the
Feature activation+0.000
North
Token North
Feature activation+0.000
American
Token American
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
an
Token an
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
here
Token here
Feature activation+4.019
,
Token,
Feature activation+0.552
as
Token as
Feature activation+0.058
Roman
Token Roman
Feature activation+0.000
Hindi
Token Hindi
Feature activation+0.000
can
Token can
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
bel
Tokenbel
Feature activation+0.000
ievers
Tokenievers
Feature activation+3.892
to
Token to
Feature activation+0.519
score
Token score
Feature activation+0.000
poorly
Token poorly
Feature activation+0.000
and
Token and
Feature activation+0.000
be
Token be
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
K
TokenK
Feature activation+0.000
een
Tokeneen
Feature activation+0.313
as
Token as
Feature activation+0.590
Starr
Token Starr
Feature activation+0.529
was
Token was
Feature activation+4.140
to
Token to
Feature activation+0.272
compile
Token compile
Feature activation+0.117
a
Token a
Feature activation+0.000
thoroughly
Token thoroughly
Feature activation+0.000
damning
Token damning
Feature activation+0.000

INTERVAL 2.771 - 3.695
CONTAINS 0.030%

money
Token money
Feature activation+0.000
could
Token could
Feature activation+0.000
instead
Token instead
Feature activation+0.000
be
Token be
Feature activation+0.000
paid
Token paid
Feature activation+0.711
directly
Token directly
Feature activation+2.927
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
merchants
Token merchants
Feature activation+0.000
that
Token that
Feature activation+0.000
might
Token might
Feature activation+0.000
Dec
Token Dec
Feature activation+0.000
orum
Tokenorum
Feature activation+0.000
:
Token:
Feature activation+0.000
Please
Token Please
Feature activation+0.000
try
Token try
Feature activation+0.000
not
Token not
Feature activation+2.976
to
Token to
Feature activation+0.347
wear
Token wear
Feature activation+0.000
beach
Token beach
Feature activation+0.000
shorts
Token shorts
Feature activation+0.000
,
Token,
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
incredibly
Token incredibly
Feature activation+0.000
destabil
Token destabil
Feature activation+0.038
ising
Tokenising
Feature activation+0.410
politically
Token politically
Feature activation+2.806
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
get
Token get
Feature activation+0.000
this
Token this
Feature activation+0.000
reform
Token reform
Feature activation+0.000
about
Tokenabout
Feature activation+0.000
$
Token $
Feature activation+0.000
26
Token26
Feature activation+0.000
billion
Token billion
Feature activation+0.566
a
Token a
Feature activation+0.000
year
Token year
Feature activation+2.817
,
Token,
Feature activation+0.161
and
Token and
Feature activation+0.000
often
Token often
Feature activation+0.071
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
a
Token a
Feature activation+0.000
big
Token big
Feature activation+0.000
deal
Token deal
Feature activation+0.057
in
Token in
Feature activation+0.000
Saudi
Token Saudi
Feature activation+0.119
Arabia
Token Arabia
Feature activation+2.848
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 1.848 - 2.771
CONTAINS 0.081%

not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
Bundes
Token Bundes
Feature activation+0.000
bank
Tokenbank
Feature activation+1.810
official
Token official
Feature activation+2.294
to
Token to
Feature activation+0.500
publicly
Token publicly
Feature activation+0.000
defend
Token defend
Feature activation+0.139
cash
Token cash
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.055
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.150
s
Tokens
Feature activation+0.000
voters
Token voters
Feature activation+1.851
to
Token to
Feature activation+0.248
write
Token write
Feature activation+0.188
in
Token in
Feature activation+0.186
another
Token another
Feature activation+0.060
Republican
Token Republican
Feature activation+0.499
Ċ
TokenĊ
Feature activation+0.000
Opp
TokenOpp
Feature activation+0.000
osition
Tokenosition
Feature activation+0.000
from
Token from
Feature activation+0.000
regulated
Token regulated
Feature activation+0.000
utilities
Token utilities
Feature activation+2.484
could
Token could
Feature activation+0.000
stop
Token stop
Feature activation+0.000
a
Token a
Feature activation+0.000
solar
Token solar
Feature activation+0.000
boom
Token boom
Feature activation+0.000
As
TokenAs
Feature activation+0.000
close
Token close
Feature activation+0.000
as
Token as
Feature activation+0.138
you
Token you
Feature activation+0.000
can
Token can
Feature activation+1.821
stand
Token stand
Feature activation+1.989
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.003
.[
Token.[
Feature activation+0.000
d
Tokend
Feature activation+0.000
movies
Token movies
Feature activation+0.285
and
Token and
Feature activation+0.000
digital
Token digital
Feature activation+0.000
-
Token-
Feature activation+0.000
video
Tokenvideo
Feature activation+1.407
favorites
Token favorites
Feature activation+2.523
to
Token to
Feature activation+0.561
deepen
Token deepen
Feature activation+0.617
the
Token the
Feature activation+0.000
entertainment
Token entertainment
Feature activation+0.000
experience
Token experience
Feature activation+0.000

INTERVAL 0.924 - 1.848
CONTAINS 0.356%

illegally
Token illegally
Feature activation+0.000
employing
Token employing
Feature activation+0.000
steel
Token steel
Feature activation+0.000
chairs
Token chairs
Feature activation+0.561
and
Token and
Feature activation+0.000
chains
Token chains
Feature activation+1.473
into
Token into
Feature activation+0.000
his
Token his
Feature activation+0.000
offense
Token offense
Feature activation+1.054
,
Token,
Feature activation+0.178
including
Token including
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Other
TokenOther
Feature activation+0.000
demands
Token demands
Feature activation+0.000
require
Token require
Feature activation+0.000
the
Token the
Feature activation+0.000
groups
Token groups
Feature activation+0.932
to
Token to
Feature activation+0.356
be
Token be
Feature activation+0.000
more
Token more
Feature activation+0.000
balanced
Token balanced
Feature activation+0.000
and
Token and
Feature activation+0.000
and
Token and
Feature activation+0.000
closure
Token closure
Feature activation+0.000
ropes
Token ropes
Feature activation+2.780
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
area
Token area
Feature activation+0.994
âĢ
TokenâĢ
Feature activation+0.282
Ļ
TokenĻ
Feature activation+1.708
s
Tokens
Feature activation+0.207
1
Token 1
Feature activation+0.000
,
Token,
Feature activation+0.000
J
Token J
Feature activation+0.000
SA
TokenSA
Feature activation+0.000
go
Token go
Feature activation+0.000
back
Token back
Feature activation+0.073
in
Token in
Feature activation+0.336
time
Token time
Feature activation+1.465
themselves
Token themselves
Feature activation+3.047
to
Token to
Feature activation+0.364
the
Token the
Feature activation+0.000
1950
Token 1950
Feature activation+0.000
s
Tokens
Feature activation+1.541
]
Token]
Feature activation+0.000
plan
Token plan
Feature activation+0.000
that
Token that
Feature activation+0.000
adds
Token adds
Feature activation+0.000
one
Token one
Feature activation+0.000
dime
Token dime
Feature activation+1.366
to
Token to
Feature activation+0.000
our
Token our
Feature activation+0.000
deficits
Token deficits
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 0.000 - 0.924
CONTAINS 99.517%

racist
Token racist
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
video
Token video
Feature activation+0.000
shows
Token shows
Feature activation+0.000
Weinstein
Token Weinstein
Feature activation+0.000
attempting
Token attempting
Feature activation+0.000
to
Token to
Feature activation+0.000
respond
Token respond
Feature activation+0.000
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.000
surpass
Token surpass
Feature activation+0.000
oil
Token oil
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
key
Token key
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
global
Token global
Feature activation+0.000
economy
Token economy
Feature activation+0.000
by
Token by
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
priced
Token priced
Feature activation+0.000
as
Token as
Feature activation+0.000
some
Token some
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
of
Token of
Feature activation+0.000
earnings
Token earnings
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
is
Token is
Feature activation+0.000
imp
Token imp
Feature activation+0.000
eded
Tokeneded
Feature activation+0.000
by
Token by
Feature activation+0.000
trends
Token trends
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
Finland
Token Finland
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
look
Token look
Feature activation+0.000
great
Token great
Feature activation+0.000
and
Token and
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
't
Token't
Feature activation+0.000
require
Token require
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.031
details
Token details
Feature activation+0.561
.
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 H10.9: (feature 22525)

TOP ACTIVATIONS
MAX = 4.858

the
Token the
Feature activation+0.000
clandestine
Token clandestine
Feature activation+0.000
service
Token service
Feature activation+0.000
,
Token,
Feature activation+0.000
dealt
Token dealt
Feature activation+0.000
firsthand
Token firsthand
Feature activation+4.858
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
enhanced
Token enhanced
Feature activation+0.000
interrogation
Token interrogation
Feature activation+0.000
program
Token program
Feature activation+0.000
the
Token the
Feature activation+0.000
federal
Token federal
Feature activation+0.000
government
Token government
Feature activation+0.000
to
Token to
Feature activation+0.000
dealing
Token dealing
Feature activation+0.000
exclusively
Token exclusively
Feature activation+4.656
with
Token with
Feature activation+0.000
Irving
Token Irving
Feature activation+0.000
Ship
Token Ship
Feature activation+0.000
building
Tokenbuilding
Feature activation+0.000
in
Token in
Feature activation+0.000
ler
Tokenler
Feature activation+0.000
is
Token is
Feature activation+0.000
filled
Token filled
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
brim
Token brim
Feature activation+4.615
with
Token with
Feature activation+0.000
vast
Token vast
Feature activation+0.000
maps
Token maps
Feature activation+0.000
to
Token to
Feature activation+0.000
explore
Token explore
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
this
Token this
Feature activation+0.000
coincides
Token coincides
Feature activation+0.000
suspicious
Token suspicious
Feature activation+3.232
ly
Tokenly
Feature activation+4.425
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
tax
Token tax
Feature activation+0.000
plan
Token plan
Feature activation+0.000
estimates
Token estimates
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
find
Token find
Feature activation+0.000
it
Token it
Feature activation+0.000
pairs
Token pairs
Feature activation+0.000
nicely
Token nicely
Feature activation+3.850
with
Token with
Feature activation+0.000
more
Token more
Feature activation+0.000
eclectic
Token eclectic
Feature activation+0.000
and
Token and
Feature activation+0.000
international
Token international
Feature activation+0.000
communication
Token communication
Feature activation+0.013
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
sure
Token sure
Feature activation+0.395
,
Token,
Feature activation+3.714
with
Token with
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
players
Token players
Feature activation+0.058
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Ill
Token Ill
Feature activation+0.000
icit
Tokenicit
Feature activation+0.000
Finance
Token Finance
Feature activation+0.000
Group
Token Group
Feature activation+3.586
with
Token with
Feature activation+0.000
finding
Token finding
Feature activation+0.000
information
Token information
Feature activation+0.000
that
Token that
Feature activation+0.000
might
Token might
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
get
Token get
Feature activation+0.000
along
Token along
Feature activation+0.000
well
Token well
Feature activation+3.532
with
Token with
Feature activation+0.000
others
Token others
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.000
't
Token't
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
equate
Token equate
Feature activation+0.000
it
Token it
Feature activation+0.568
even
Token even
Feature activation+3.481
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
ant
Token ant
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
this
Token this
Feature activation+0.000
coincides
Token coincides
Feature activation+0.000
suspicious
Token suspicious
Feature activation+3.232
ly
Tokenly
Feature activation+4.425
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
tax
Token tax
Feature activation+0.000
plan
Token plan
Feature activation+0.000
said
Token said
Feature activation+0.000
-
Token -
Feature activation+0.000
how
Token how
Feature activation+0.000
compatible
Token compatible
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+3.209
with
Token with
Feature activation+0.000
other
Token other
Feature activation+0.000
parties
Token parties
Feature activation+0.000
depended
Token depended
Feature activation+0.000
in
Token in
Feature activation+0.000
or
Token or
Feature activation+0.000
experience
Token experience
Feature activation+0.000
,
Token,
Feature activation+0.948
compare
Token compare
Feature activation+0.405
it
Token it
Feature activation+1.405
directly
Token directly
Feature activation+3.176
with
Token with
Feature activation+0.000
observation
Token observation
Feature activation+0.000
,
Token,
Feature activation+0.689
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
reconcile
Token reconcile
Feature activation+0.020
somewhat
Token somewhat
Feature activation+3.133
what
Token what
Feature activation+0.000
Stephen
Token Stephen
Feature activation+0.000
writes
Token writes
Feature activation+1.202
and
Token and
Feature activation+0.000
what
Token what
Feature activation+0.015
stance
Token stance
Feature activation+0.000
on
Token on
Feature activation+0.000
North
Token North
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
align
Token align
Feature activation+0.000
s
Tokens
Feature activation+3.067
with
Token with
Feature activation+0.000
that
Token that
Feature activation+0.000
of
Token of
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
pair
Token pair
Feature activation+0.000
well
Token well
Feature activation+3.009
after
Token after
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.399
ve
Tokenve
Feature activation+0.000
trailers
Token trailers
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
that
Token that
Feature activation+0.000
align
Token align
Feature activation+0.000
s
Tokens
Feature activation+2.983
with
Token with
Feature activation+0.000
what
Token what
Feature activation+0.000
happens
Token happens
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
choices
Token choices
Feature activation+0.000
interact
Token interact
Feature activation+0.102
badly
Token badly
Feature activation+2.969
with
Token with
Feature activation+0.000
that
Token that
Feature activation+0.000
intervention
Token intervention
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
statistic
Token statistic
Feature activation+0.000
that
Token that
Feature activation+0.000
compares
Token compares
Feature activation+0.000
favour
Token favour
Feature activation+0.533
ably
Tokenably
Feature activation+2.934
with
Token with
Feature activation+0.000
60
Token 60
Feature activation+0.000
m
Tokenm
Feature activation+0.000
sold
Token sold
Feature activation+0.000
in
Token in
Feature activation+0.000
National
Token National
Feature activation+0.000
Rape
Token Rape
Feature activation+0.000
Day
Token Day
Feature activation+0.000
and
Token and
Feature activation+0.000
replace
Token replace
Feature activation+0.000
it
Token it
Feature activation+2.901
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
deserving
Token deserving
Feature activation+0.000
federal
Token federal
Feature activation+0.000
ush
Tokenush
Feature activation+0.000
tops
Token tops
Feature activation+0.876
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
b
Token b
Feature activation+0.000
uns
Tokenuns
Feature activation+2.837
with
Token with
Feature activation+0.000
your
Token your
Feature activation+0.000
unbeaten
Token unbeaten
Feature activation+0.000
egg
Token egg
Feature activation+0.000
whites
Token whites
Feature activation+0.000

Top DFA by src position
MAX = 5.320

in
Token in
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
clandestine
Token clandestine
Feature activation+0.005
Top resid features:
service
Token service
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
dealt
Token dealt
Feature activation+5.320
Top resid features:
firsthand
Token firsthand
Feature activation+0.026
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
enhanced
Token enhanced
Feature activation+0.000
Top resid features:
interrogation
Token interrogation
Feature activation+0.000
Top resid features:
commits
Token commits
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
federal
Token federal
Feature activation+0.003
Top resid features:
government
Token government
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
dealing
Token dealing
Feature activation+5.052
Top resid features:
exclusively
Token exclusively
Feature activation+0.038
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Irving
Token Irving
Feature activation+0.000
Top resid features:
Ship
Token Ship
Feature activation+0.000
Top resid features:
building
Tokenbuilding
Feature activation+0.000
Top resid features:
ike
Tokenike
Feature activation+0.007
Top resid features:
dungeon
Token dungeon
Feature activation+0.004
Top resid features:
craw
Token craw
Feature activation-0.000
Top resid features:
ler
Tokenler
Feature activation+0.002
Top resid features:
is
Token is
Feature activation-0.042
Top resid features:
filled
Token filled
Feature activation+4.071
Top resid features:
to
Token to
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
brim
Token brim
Feature activation+0.954
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
vast
Token vast
Feature activation+0.000
Top resid features:
six
Token six
Feature activation-0.000
Top resid features:
years
Token years
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
though
Token though
Feature activation+0.004
Top resid features:
this
Token this
Feature activation-0.001
Top resid features:
coincides
Token coincides
Feature activation+4.826
Top resid features:
suspicious
Token suspicious
Feature activation+0.044
Top resid features:
ly
Tokenly
Feature activation+0.031
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
tax
Token tax
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
I
Token I
Feature activation-0.008
Top resid features:
find
Token find
Feature activation+0.021
Top resid features:
it
Token it
Feature activation-0.001
Top resid features:
pairs
Token pairs
Feature activation+4.248
Top resid features:
nicely
Token nicely
Feature activation+0.103
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
eclectic
Token eclectic
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
"
Token "
Feature activation-0.026
Top resid features:
He
TokenHe
Feature activation-0.001
Top resid features:
's
Token's
Feature activation-0.000
Top resid features:
had
Token had
Feature activation-0.002
Top resid features:
some
Token some
Feature activation-0.006
Top resid features:
communication
Token communication
Feature activation+4.258
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
I
Token I
Feature activation-0.009
Top resid features:
'm
Token'm
Feature activation-0.023
Top resid features:
sure
Token sure
Feature activation-0.006
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
corruption
Tokencorruption
Feature activation+0.001
Top resid features:
."
Token."
Feature activation+0.009
Top resid features:
Lev
Token Lev
Feature activation-0.001
Top resid features:
inson
Tokeninson
Feature activation-0.001
Top resid features:
was
Token was
Feature activation-0.003
Top resid features:
tasked
Token tasked
Feature activation+4.018
Top resid features:
by
Token by
Feature activation+0.031
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
Ill
Token Ill
Feature activation-0.000
Top resid features:
icit
Tokenicit
Feature activation-0.002
Top resid features:
Finance
Token Finance
Feature activation+0.000
Top resid features:
doesn
Token doesn
Feature activation-0.010
Top resid features:
âĢ
TokenâĢ
Feature activation-0.075
Top resid features:
Ļ
TokenĻ
Feature activation+0.028
Top resid features:
t
Tokent
Feature activation+0.005
Top resid features:
get
Token get
Feature activation+0.015
Top resid features:
along
Token along
Feature activation+3.599
Top resid features:
well
Token well
Feature activation+0.454
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
others
Token others
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:
wouldn
Token wouldn
Feature activation-0.004
Top resid features:
't
Token't
Feature activation-0.001
Top resid features:
want
Token want
Feature activation+0.008
Top resid features:
to
Token to
Feature activation-0.017
Top resid features:
equate
Token equate
Feature activation+0.672
Top resid features:
it
Token it
Feature activation+3.281
Top resid features:
even
Token even
Feature activation+0.012
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
ant
Token ant
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
six
Token six
Feature activation-0.000
Top resid features:
years
Token years
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
though
Token though
Feature activation+0.009
Top resid features:
this
Token this
Feature activation-0.001
Top resid features:
coincides
Token coincides
Feature activation+3.399
Top resid features:
suspicious
Token suspicious
Feature activation+0.311
Top resid features:
ly
Tokenly
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
tax
Token tax
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.001
Top resid features:
he
Token he
Feature activation-0.002
Top resid features:
said
Token said
Feature activation+0.002
Top resid features:
-
Token -
Feature activation-0.019
Top resid features:
how
Token how
Feature activation+0.029
Top resid features:
compatible
Token compatible
Feature activation+3.492
Top resid features:
they
Token they
Feature activation+0.024
Top resid features:
were
Token were
Feature activation+0.052
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
parties
Token parties
Feature activation+0.000
Top resid features:
experiment
Token experiment
Feature activation-0.007
Top resid features:
or
Token or
Feature activation+0.014
Top resid features:
experience
Token experience
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
compare
Token compare
Feature activation+0.640
Top resid features:
it
Token it
Feature activation+2.867
Top resid features:
directly
Token directly
Feature activation+0.039
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
observation
Token observation
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
helping
Token helping
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
To
TokenTo
Feature activation+0.005
Top resid features:
reconcile
Token reconcile
Feature activation+3.568
Top resid features:
somewhat
Token somewhat
Feature activation+0.015
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
Stephen
Token Stephen
Feature activation+0.000
Top resid features:
writes
Token writes
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
her
Token her
Feature activation-0.002
Top resid features:
stance
Token stance
Feature activation-0.005
Top resid features:
on
Token on
Feature activation-0.002
Top resid features:
North
Token North
Feature activation+0.005
Top resid features:
Korea
Token Korea
Feature activation-0.011
Top resid features:
align
Token align
Feature activation+3.443
Top resid features:
s
Tokens
Feature activation+0.114
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
U
Token U
Feature activation+0.000
Top resid features:
styles
Token styles
Feature activation-0.006
Top resid features:
don
Token don
Feature activation-0.006
Top resid features:
âĢ
TokenâĢ
Feature activation-0.085
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
t
Tokent
Feature activation-0.000
Top resid features:
pair
Token pair
Feature activation+3.213
Top resid features:
well
Token well
Feature activation+0.439
Top resid features:
after
Token after
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
Ragnarok
Token Ragnarok
Feature activation-0.012
Top resid features:
trailers
Token trailers
Feature activation-0.020
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
how
Token how
Feature activation-0.053
Top resid features:
that
Token that
Feature activation-0.017
Top resid features:
align
Token align
Feature activation+3.241
Top resid features:
s
Tokens
Feature activation+0.311
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
happens
Token happens
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.005
Top resid features:
âĢ
TokenâĢ
Feature activation-0.010
Top resid features:
Ļ
TokenĻ
Feature activation+0.005
Top resid features:
s
Tokens
Feature activation+0.011
Top resid features:
choices
Token choices
Feature activation+0.011
Top resid features:
interact
Token interact
Feature activation+3.302
Top resid features:
badly
Token badly
Feature activation+0.083
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
intervention
Token intervention
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
month
Token month
Feature activation+0.008
Top resid features:
-
Token -
Feature activation+0.003
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
statistic
Token statistic
Feature activation-0.006
Top resid features:
that
Token that
Feature activation-0.012
Top resid features:
compares
Token compares
Feature activation+2.538
Top resid features:
favour
Token favour
Feature activation+0.323
Top resid features:
ably
Tokenably
Feature activation+0.564
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
60
Token 60
Feature activation+0.000
Top resid features:
m
Tokenm
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
National
Token National
Feature activation-0.001
Top resid features:
Rape
Token Rape
Feature activation-0.003
Top resid features:
Day
Token Day
Feature activation+0.008
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
replace
Token replace
Feature activation+3.219
Top resid features:
it
Token it
Feature activation+0.119
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
deserving
Token deserving
Feature activation+0.000
Top resid features:
apart
Token apart
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Br
TokenBr
Feature activation+0.004
Top resid features:
ush
Tokenush
Feature activation+2.225
Top resid features:
tops
Token tops
Feature activation+1.094
Top resid features:
of
Token of
Feature activation+0.066
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
b
Token b
Feature activation+0.002
Top resid features:
uns
Tokenuns
Feature activation+0.024
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.03

Head 3: 0.03

Head 4: 0.03

Head 5: 0.08

Head 6: 0.02

Head 7: 0.03

Head 8: 0.01

Head 9: 0.68

Head 10: 0.02

Head 11: 0.03

Positive logits

with4.65

with4.35

withd4.10

WITH4.09

With3.96

With3.69

wi2.67

WithNo2.51

wit2.33

together1.97

Without1.91

aman1.85

DragonMagazine1.85

iance1.83

between1.79

venture1.72

against1.69

bernatorial1.67

untled1.67

iaz1.65

Negative logits

commencement-1.80

agara-1.77

eers-1.76

Discuss-1.75

redo-1.72

til-1.57

guiActiveUnfocused-1.52

loo-1.50

Synopsis-1.49

Cutter-1.49

ilings-1.49

iren-1.48

arak-1.46

takeoff-1.45

ternity-1.44

hung-1.43

itary-1.42

orno-1.42

Citation-1.41

apologies-1.40

INTERVAL 4.372 - 4.858
CONTAINS 0.000%

,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
this
Token this
Feature activation+0.000
coincides
Token coincides
Feature activation+0.000
suspicious
Token suspicious
Feature activation+3.232
ly
Tokenly
Feature activation+4.425
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
tax
Token tax
Feature activation+0.000
plan
Token plan
Feature activation+0.000
estimates
Token estimates
Feature activation+0.000
the
Token the
Feature activation+0.000
federal
Token federal
Feature activation+0.000
government
Token government
Feature activation+0.000
to
Token to
Feature activation+0.000
dealing
Token dealing
Feature activation+0.000
exclusively
Token exclusively
Feature activation+4.656
with
Token with
Feature activation+0.000
Irving
Token Irving
Feature activation+0.000
Ship
Token Ship
Feature activation+0.000
building
Tokenbuilding
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
clandestine
Token clandestine
Feature activation+0.000
service
Token service
Feature activation+0.000
,
Token,
Feature activation+0.000
dealt
Token dealt
Feature activation+0.000
firsthand
Token firsthand
Feature activation+4.858
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
enhanced
Token enhanced
Feature activation+0.000
interrogation
Token interrogation
Feature activation+0.000
program
Token program
Feature activation+0.000
ler
Tokenler
Feature activation+0.000
is
Token is
Feature activation+0.000
filled
Token filled
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
brim
Token brim
Feature activation+4.615
with
Token with
Feature activation+0.000
vast
Token vast
Feature activation+0.000
maps
Token maps
Feature activation+0.000
to
Token to
Feature activation+0.000
explore
Token explore
Feature activation+0.000

INTERVAL 3.886 - 4.372
CONTAINS 0.000%

INTERVAL 3.400 - 3.886
CONTAINS 0.001%

and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
find
Token find
Feature activation+0.000
it
Token it
Feature activation+0.000
pairs
Token pairs
Feature activation+0.000
nicely
Token nicely
Feature activation+3.850
with
Token with
Feature activation+0.000
more
Token more
Feature activation+0.000
eclectic
Token eclectic
Feature activation+0.000
and
Token and
Feature activation+0.000
international
Token international
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
get
Token get
Feature activation+0.000
along
Token along
Feature activation+0.000
well
Token well
Feature activation+3.532
with
Token with
Feature activation+0.000
others
Token others
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Ill
Token Ill
Feature activation+0.000
icit
Tokenicit
Feature activation+0.000
Finance
Token Finance
Feature activation+0.000
Group
Token Group
Feature activation+3.586
with
Token with
Feature activation+0.000
finding
Token finding
Feature activation+0.000
information
Token information
Feature activation+0.000
that
Token that
Feature activation+0.000
might
Token might
Feature activation+0.000
't
Token't
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
equate
Token equate
Feature activation+0.000
it
Token it
Feature activation+0.568
even
Token even
Feature activation+3.481
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
ant
Token ant
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
communication
Token communication
Feature activation+0.013
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
sure
Token sure
Feature activation+0.395
,
Token,
Feature activation+3.714
with
Token with
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
players
Token players
Feature activation+0.058

INTERVAL 2.915 - 3.400
CONTAINS 0.001%

years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
this
Token this
Feature activation+0.000
coincides
Token coincides
Feature activation+0.000
suspicious
Token suspicious
Feature activation+3.232
ly
Tokenly
Feature activation+4.425
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
tax
Token tax
Feature activation+0.000
plan
Token plan
Feature activation+0.000
a
Token a
Feature activation+0.000
statistic
Token statistic
Feature activation+0.000
that
Token that
Feature activation+0.000
compares
Token compares
Feature activation+0.000
favour
Token favour
Feature activation+0.533
ably
Tokenably
Feature activation+2.934
with
Token with
Feature activation+0.000
60
Token 60
Feature activation+0.000
m
Tokenm
Feature activation+0.000
sold
Token sold
Feature activation+0.000
in
Token in
Feature activation+0.000
stance
Token stance
Feature activation+0.000
on
Token on
Feature activation+0.000
North
Token North
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
align
Token align
Feature activation+0.000
s
Tokens
Feature activation+3.067
with
Token with
Feature activation+0.000
that
Token that
Feature activation+0.000
of
Token of
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
trailers
Token trailers
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
that
Token that
Feature activation+0.000
align
Token align
Feature activation+0.000
s
Tokens
Feature activation+2.983
with
Token with
Feature activation+0.000
what
Token what
Feature activation+0.000
happens
Token happens
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
or
Token or
Feature activation+0.000
experience
Token experience
Feature activation+0.000
,
Token,
Feature activation+0.948
compare
Token compare
Feature activation+0.405
it
Token it
Feature activation+1.405
directly
Token directly
Feature activation+3.176
with
Token with
Feature activation+0.000
observation
Token observation
Feature activation+0.000
,
Token,
Feature activation+0.689
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000

INTERVAL 2.429 - 2.915
CONTAINS 0.002%

think
Token think
Feature activation+0.000
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
conflict
Token conflict
Feature activation+0.119
too
Token too
Feature activation+1.522
much
Token much
Feature activation+2.680
let
Token let
Feature activation+0.000
me
Token me
Feature activation+0.000
know
Token know
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
an
Token an
Feature activation+0.000
interview
Token interview
Feature activation+0.000
in
Token in
Feature activation+0.000
December
Token December
Feature activation+2.794
,
Token,
Feature activation+0.000
Pelosi
Token Pelosi
Feature activation+0.000
also
Token also
Feature activation+0.000
drew
Token drew
Feature activation+0.000
attention
Token attention
Feature activation+0.000
that
Token that
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
clearly
Token clearly
Feature activation+0.000
shares
Token shares
Feature activation+0.048
in
Token in
Feature activation+0.000
common
Token common
Feature activation+2.747
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
renowned
Token renowned
Feature activation+0.000
ideological
Token ideological
Feature activation+0.000
rivals
Token rivals
Feature activation+0.060
National
Token National
Feature activation+0.000
Rape
Token Rape
Feature activation+0.000
Day
Token Day
Feature activation+0.000
and
Token and
Feature activation+0.000
replace
Token replace
Feature activation+0.000
it
Token it
Feature activation+2.901
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
deserving
Token deserving
Feature activation+0.000
federal
Token federal
Feature activation+0.000
21
Token 21
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
diagnosed
Token diagnosed
Feature activation+0.014
in
Token in
Feature activation+0.514
April
Token April
Feature activation+2.627
and
Token and
Feature activation+0.069
May
Token May
Feature activation+2.392
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.943 - 2.429
CONTAINS 0.007%

,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
no
Token no
Feature activation+0.000
contact
Token contact
Feature activation+0.000
from
Token from
Feature activation+0.000
Britain
Token Britain
Feature activation+2.177
's
Token's
Feature activation+0.000
Foreign
Token Foreign
Feature activation+0.000
Office
Token Office
Feature activation+2.385
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
issue
Token issue
Feature activation+0.000
reson
Token reson
Feature activation+0.000
ates
Tokenates
Feature activation+0.167
strongly
Token strongly
Feature activation+2.062
with
Token with
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.819
,
Token,
Feature activation+0.000
whose
Token whose
Feature activation+0.000
Justice
Token Justice
Feature activation+0.000
Department
Token Department
Feature activation+0.000
charged
Token charged
Feature activation+0.000
Snowden
Token Snowden
Feature activation+1.977
with
Token with
Feature activation+0.000
leaking
Token leaking
Feature activation+0.000
classified
Token classified
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
documents
Token documents
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
blessed
Token blessed
Feature activation+0.000
beyond
Token beyond
Feature activation+0.125
measure
Token measure
Feature activation+2.051
and
Token and
Feature activation+0.000
can
Token can
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
all
Tokenall
Feature activation+0.114
Hor
Token Hor
Feature activation+0.000
an
Tokenan
Feature activation+1.607
'
Token '
Feature activation+0.343
s
Tokens
Feature activation+0.206
tissues
Token tissues
Feature activation+2.075
with
Token with
Feature activation+0.066
Sw
Token Sw
Feature activation+0.000
arov
Tokenarov
Feature activation+0.000
ski
Tokenski
Feature activation+0.000
crystals
Token crystals
Feature activation+0.321

INTERVAL 1.457 - 1.943
CONTAINS 0.016%

in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
couple
Token couple
Feature activation+0.000
of
Token of
Feature activation+0.000
days
Token days
Feature activation+1.794
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
they
Token they
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
pling
Tokenpling
Feature activation+0.000
this
Token this
Feature activation+0.412
level
Token level
Feature activation+0.257
of
Token of
Feature activation+0.165
aerial
Token aerial
Feature activation+0.144
surveillance
Token surveillance
Feature activation+1.597
with
Token with
Feature activation+0.000
cellphone
Token cellphone
Feature activation+0.000
data
Token data
Feature activation+0.000
provided
Token provided
Feature activation+0.000
by
Token by
Feature activation+0.000
Congress
Token Congress
Feature activation+0.000
(
Token (
Feature activation+0.000
who
Tokenwho
Feature activation+0.000
associated
Token associated
Feature activation+0.000
the
Token the
Feature activation+0.000
agency
Token agency
Feature activation+1.481
with
Token with
Feature activation+0.463
the
Token the
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
health
Token health
Feature activation+0.000
-
Token-
Feature activation+0.000
analytics
Token analytics
Feature activation+0.000
,
Token,
Feature activation+0.000
intrusion
Token intrusion
Feature activation+0.000
alerts
Token alerts
Feature activation+0.051
and
Token and
Feature activation+0.000
more
Token more
Feature activation+1.614
onto
Token onto
Feature activation+0.000
a
Token a
Feature activation+0.000
single
Token single
Feature activation+0.000
network
Token network
Feature activation+0.000
ed
Tokened
Feature activation+0.000
was
Token was
Feature activation+0.000
charged
Token charged
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
arch
Token arch
Feature activation+0.000
angel
Tokenangel
Feature activation+1.469
Gabriel
Token Gabriel
Feature activation+2.227
to
Token to
Feature activation+0.000
write
Token write
Feature activation+0.000
books
Token books
Feature activation+0.000
revealing
Token revealing
Feature activation+0.000

INTERVAL 0.972 - 1.457
CONTAINS 0.043%

ve
Tokenve
Feature activation+0.000
been
Token been
Feature activation+0.000
lav
Token lav
Feature activation+0.000
ishing
Tokenishing
Feature activation+0.000
our
Token our
Feature activation+0.000
homes
Token homes
Feature activation+1.132
with
Token with
Feature activation+0.000
p
Token p
Feature activation+0.000
otted
Tokenotted
Feature activation+0.000
flowers
Token flowers
Feature activation+0.000
and
Token and
Feature activation+0.000
and
Token and
Feature activation+0.000
credits
Token credits
Feature activation+0.000
ML
Token ML
Feature activation+0.000
SE
TokenSE
Feature activation+0.685
âĢ
TokenâĢ
Feature activation+0.005
Ļ
TokenĻ
Feature activation+1.148
s
Tokens
Feature activation+0.467
board
Token board
Feature activation+0.615
for
Token for
Feature activation+0.208
approving
Token approving
Feature activation+0.060
the
Token the
Feature activation+0.000
a
Token a
Feature activation+0.000
recent
Token recent
Feature activation+0.000
pact
Token pact
Feature activation+0.000
with
Token with
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Cruz
Token Cruz
Feature activation+1.127
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
In
TokenIn
Feature activation+0.000
return
Token return
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
his
Token his
Feature activation+0.000
discussions
Token discussions
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
ambassador
Token ambassador
Feature activation+1.209
âĢĵ
Token âĢĵ
Feature activation+0.000
which
Token which
Feature activation+0.000
were
Token were
Feature activation+0.000
completely
Token completely
Feature activation+0.000
legal
Token legal
Feature activation+0.000
problem
Token problem
Feature activation+0.000
for
Token for
Feature activation+0.000
Sk
Token Sk
Feature activation+0.000
illing
Tokenilling
Feature activation+0.729
and
Token and
Feature activation+0.000
Black
Token Black
Feature activation+1.110
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
convicted
Token convicted
Feature activation+0.000

INTERVAL 0.486 - 0.972
CONTAINS 0.146%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
)
Token)
Feature activation+0.214
feathers
Token feathers
Feature activation+0.268
âĢ
TokenâĢ
Feature activation+0.033
Ŀ
TokenĿ
Feature activation+0.923
and
Token and
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
raise
Tokenraise
Feature activation+0.000
(
Token (
Feature activation+0.000
campaign
Token campaign
Feature activation+0.445
with
Token with
Feature activation+0.029
endorsements
Token endorsements
Feature activation+0.436
and
Token and
Feature activation+0.000
stories
Token stories
Feature activation+0.491
that
Token that
Feature activation+0.514
legitim
Token legitim
Feature activation+0.000
ized
Tokenized
Feature activation+1.062
her
Token her
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
SA
TokenSA
Feature activation+0.000
)
Token)
Feature activation+0.000
clash
Token clash
Feature activation+0.024
with
Token with
Feature activation+0.000
regime
Token regime
Feature activation+0.609
forces
Token forces
Feature activation+0.873
.
Token.
Feature activation+0.000
Salem
Token Salem
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
nature
Token nature
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
se
Tokense
Feature activation+0.000
emed
Tokenemed
Feature activation+0.000
pumped
Token pumped
Feature activation+0.000
up
Token up
Feature activation+0.571
about
Token about
Feature activation+0.000
killing
Token killing
Feature activation+0.000
Arabs
Token Arabs
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
to
Token to
Feature activation+0.000
integrate
Token integrate
Feature activation+0.000
a
Token a
Feature activation+0.000
Bitcoin
Token Bitcoin
Feature activation+0.000
wallet
Token wallet
Feature activation+0.816
into
Token into
Feature activation+0.762
their
Token their
Feature activation+0.000
shops
Token shops
Feature activation+0.255
easily
Token easily
Feature activation+0.000
.
Token.
Feature activation+0.000
Merchants
Token Merchants
Feature activation+0.000

INTERVAL 0.000 - 0.486
CONTAINS 99.783%

attempting
Token attempting
Feature activation+0.000
to
Token to
Feature activation+0.000
retreat
Token retreat
Feature activation+0.000
.
Token.
Feature activation+0.000
Deputy
Token Deputy
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
dj
Tokendj
Feature activation+0.000
en
Tokenen
Feature activation+0.000
ovich
Tokenovich
Feature activation+0.000
fired
Token fired
Feature activation+0.000
his
Token his
Feature activation+0.000
't
Token't
Feature activation+0.000
break
Token break
Feature activation+0.000
down
Token down
Feature activation+0.000
cellul
Token cellul
Feature activation+0.000
ose
Tokenose
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
laboratory
Token laboratory
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
AD
TokenAD
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.000
Capital
Token Capital
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Authority
Token Authority
Feature activation+0.000
(
Token (
Feature activation+0.000
C
TokenC
Feature activation+0.000
DA
TokenDA
Feature activation+0.000
)
Token)
Feature activation+0.000
on
Token on
Feature activation+0.000
modest
Token modest
Feature activation+0.000
means
Token means
Feature activation+0.000
?
Token?
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
"
Token"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
a
Token a
Feature activation+0.000
statement
Token statement
Feature activation+0.000
issued
Token issued
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
office
Token office
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
President
Token President
Feature activation+0.000
Vladimir
Token Vladimir
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 H10.9: (feature 13673)

TOP ACTIVATIONS
MAX = 6.795

the
Token the
Feature activation+0.000
receiver
Token receiver
Feature activation+0.000
is
Token is
Feature activation+0.000
responsible
Token responsible
Feature activation+0.112
not
Token not
Feature activation+5.200
only
Token only
Feature activation+6.795
for
Token for
Feature activation+0.000
underneath
Token underneath
Feature activation+0.000
routes
Token routes
Feature activation+0.000
but
Token but
Feature activation+0.477
also
Token also
Feature activation+1.280
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
room
Token room
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
trails
Token trails
Feature activation+6.525
for
Token for
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.109
us
Token us
Feature activation+0.821
,
Token,
Feature activation+0.048
employee
Token employee
Feature activation+0.000
lock
Token lock
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
,
Token,
Feature activation+0.000
waiting
Token waiting
Feature activation+0.000
patiently
Token patiently
Feature activation+5.358
as
Token as
Feature activation+0.012
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.127
the
Token the
Feature activation+0.000
girls
Token girls
Feature activation+0.000
on
Token on
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
as
Token as
Feature activation+0.000
preparations
Token preparations
Feature activation+0.983
took
Token took
Feature activation+1.230
place
Token place
Feature activation+5.280
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
aim
Token aim
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
receiver
Token receiver
Feature activation+0.000
is
Token is
Feature activation+0.000
responsible
Token responsible
Feature activation+0.112
not
Token not
Feature activation+5.200
only
Token only
Feature activation+6.795
for
Token for
Feature activation+0.000
underneath
Token underneath
Feature activation+0.000
routes
Token routes
Feature activation+0.000
but
Token but
Feature activation+0.477
been
Token been
Feature activation+0.000
waiting
Token waiting
Feature activation+0.603
with
Token with
Feature activation+0.000
ba
Token ba
Feature activation+2.155
ited
Tokenited
Feature activation+0.008
breath
Token breath
Feature activation+5.086
for
Token for
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
finale
Token finale
Feature activation+0.000
.
Token.
Feature activation+0.000
Wales
Token Wales
Feature activation+0.000
and
Token and
Feature activation+0.000
Northern
Token Northern
Feature activation+0.000
Ireland
Token Ireland
Feature activation+0.000
too
Token too
Feature activation+0.000
-
Token -
Feature activation+5.053
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
nations
Token nations
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
reason
Token reason
Feature activation+0.373
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.058
world
Token world
Feature activation+5.038
for
Token for
Feature activation+0.489
why
Token why
Feature activation+0.024
I
Token I
Feature activation+0.000
did
Token did
Feature activation+0.000
the
Token the
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
make
Token make
Feature activation+0.000
room
Token room
Feature activation+0.068
âĢ
TokenâĢ
Feature activation+1.077
Ŀ
TokenĿ
Feature activation+5.001
âĢĵ
Token âĢĵ
Feature activation+0.000
George
Token George
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
,
Token,
Feature activation+0.000
41
Token 41
Feature activation+0.000
been
Token been
Feature activation+0.000
waiting
Token waiting
Feature activation+0.000
a
Token a
Feature activation+0.205
very
Token very
Feature activation+0.652
long
Token long
Feature activation+0.689
time
Token time
Feature activation+4.789
for
Token for
Feature activation+0.000
more
Token more
Feature activation+0.000
just
Token just
Feature activation+0.000
and
Token and
Feature activation+0.000
equitable
Token equitable
Feature activation+0.000
Barcelona
Token Barcelona
Feature activation+0.000
and
Token and
Feature activation+0.000
Real
Token Real
Feature activation+0.000
Madrid
Token Madrid
Feature activation+0.000
destined
Token destined
Feature activation+0.000
only
Token only
Feature activation+4.718
to
Token to
Feature activation+0.183
cross
Token cross
Feature activation+0.000
paths
Token paths
Feature activation+0.000
if
Token if
Feature activation+0.000
both
Token both
Feature activation+0.000
unusual
Token unusual
Feature activation+0.353
in
Token in
Feature activation+0.005
post
Token post
Feature activation+0.068
-
Token-
Feature activation+0.000
war
Tokenwar
Feature activation+0.853
Germany
Token Germany
Feature activation+4.694
to
Token to
Feature activation+0.051
recycle
Token recycle
Feature activation+0.000
debris
Token debris
Feature activation+0.000
in
Token in
Feature activation+0.000
new
Token new
Feature activation+0.000
it
Token it
Feature activation+0.000
"
Token "
Feature activation+0.000
much
Tokenmuch
Feature activation+0.000
more
Token more
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
"
Token"
Feature activation+4.623
for
Token for
Feature activation+0.000
people
Token people
Feature activation+0.000
to
Token to
Feature activation+0.000
find
Token find
Feature activation+0.000
legal
Token legal
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000
preparations
Token preparations
Feature activation+0.000
were
Token were
Feature activation+0.000
being
Token being
Feature activation+0.104
made
Token made
Feature activation+4.623
for
Token for
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
part
Token part
Feature activation+0.000
cities
Token cities
Feature activation+0.000
and
Token and
Feature activation+0.000
towns
Token towns
Feature activation+0.000
looking
Token looking
Feature activation+0.000
int
Token int
Feature activation+0.474
ently
Tokenently
Feature activation+4.457
at
Token at
Feature activation+0.000
their
Token their
Feature activation+0.000
phones
Token phones
Feature activation+0.000
disreg
Token disreg
Feature activation+0.010
arding
Tokenarding
Feature activation+0.000
an
Token an
Feature activation+0.000
adequate
Token adequate
Feature activation+0.000
justification
Token justification
Feature activation+1.359
in
Token in
Feature activation+0.128
some
Token some
Feature activation+0.000
cases
Token cases
Feature activation+4.443
,
Token,
Feature activation+0.316
but
Token but
Feature activation+0.176
inadequate
Token inadequate
Feature activation+0.079
in
Token in
Feature activation+0.000
other
Token other
Feature activation+0.000
hospital
Token hospital
Feature activation+0.000
finances
Token finances
Feature activation+0.000
.
Token.
Feature activation+0.000
Calls
Token Calls
Feature activation+0.000
by
Token by
Feature activation+0.000
regulators
Token regulators
Feature activation+4.396
for
Token for
Feature activation+0.000
higher
Token higher
Feature activation+0.000
staff
Token staff
Feature activation+0.000
numbers
Token numbers
Feature activation+0.802
following
Token following
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
definitely
Token definitely
Feature activation+0.000
the
Token the
Feature activation+0.000
poster
Token poster
Feature activation+0.000
boy
Token boy
Feature activation+4.321
for
Token for
Feature activation+0.000
curly
Token curly
Feature activation+0.000
hair
Token hair
Feature activation+0.000
.
Token.
Feature activation+0.000
Su
Token Su
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
common
Token common
Feature activation+0.222
and
Token and
Feature activation+0.084
legal
Token legal
Feature activation+4.279
for
Token for
Feature activation+0.000
private
Token private
Feature activation+0.000
universities
Token universities
Feature activation+0.291
to
Token to
Feature activation+0.000
not
Token not
Feature activation+0.000
plenty
Token plenty
Feature activation+0.000
of
Token of
Feature activation+0.000
room
Token room
Feature activation+0.129
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.043
bottom
Token bottom
Feature activation+4.270
.
Token.
Feature activation+0.000
Room
Token Room
Feature activation+0.000
to
Token to
Feature activation+0.000
build
Token build
Feature activation+0.044
complex
Token complex
Feature activation+0.000

Top DFA by src position
MAX = 7.236

slot
Token slot
Feature activation+0.009
Top resid features:
where
Token where
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
receiver
Token receiver
Feature activation+0.047
Top resid features:
is
Token is
Feature activation+0.028
Top resid features:
responsible
Token responsible
Feature activation+7.236
Top resid features:
not
Token not
Feature activation+0.003
Top resid features:
only
Token only
Feature activation+0.002
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
underneath
Token underneath
Feature activation+0.000
Top resid features:
routes
Token routes
Feature activation+0.000
Top resid features:
rians
Tokenrians
Feature activation+0.000
Top resid features:
understand
Token understand
Feature activation+0.017
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
there
Token there
Feature activation+0.011
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
room
Token room
Feature activation+6.993
Top resid features:
on
Token on
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
trails
Token trails
Feature activation+0.043
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
employee
Token employee
Feature activation-0.004
Top resid features:
lock
Token lock
Feature activation-0.001
Top resid features:
ers
Tokeners
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
waiting
Token waiting
Feature activation+5.801
Top resid features:
patiently
Token patiently
Feature activation+0.101
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
RNC
Token RNC
Feature activation-0.024
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.017
Top resid features:
as
Token as
Feature activation+0.011
Top resid features:
preparations
Token preparations
Feature activation+5.621
Top resid features:
took
Token took
Feature activation-0.001
Top resid features:
place
Token place
Feature activation+0.077
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:
slot
Token slot
Feature activation+0.005
Top resid features:
where
Token where
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
receiver
Token receiver
Feature activation-0.003
Top resid features:
is
Token is
Feature activation-0.051
Top resid features:
responsible
Token responsible
Feature activation+5.783
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
underneath
Token underneath
Feature activation+0.000
Top resid features:
routes
Token routes
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.054
Top resid features:
Ļ
TokenĻ
Feature activation-0.013
Top resid features:
ve
Tokenve
Feature activation-0.002
Top resid features:
all
Token all
Feature activation+0.004
Top resid features:
been
Token been
Feature activation-0.026
Top resid features:
waiting
Token waiting
Feature activation+5.740
Top resid features:
with
Token with
Feature activation+0.007
Top resid features:
ba
Token ba
Feature activation+0.004
Top resid features:
ited
Tokenited
Feature activation-0.020
Top resid features:
breath
Token breath
Feature activation+0.014
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
broadcasting
Token broadcasting
Feature activation+0.004
Top resid features:
there
Token there
Feature activation+0.014
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
clear
Token clear
Feature activation+0.007
Top resid features:
demand
Token demand
Feature activation+5.532
Top resid features:
-
Token -
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
it
Token it
Feature activation+0.004
Top resid features:
comes
Token comes
Feature activation-0.006
Top resid features:
from
Token from
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation-0.004
Top resid features:
not
Token not
Feature activation-0.013
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
good
Token good
Feature activation+0.029
Top resid features:
reason
Token reason
Feature activation+5.611
Top resid features:
in
Token in
Feature activation-0.023
Top resid features:
this
Token this
Feature activation+0.003
Top resid features:
world
Token world
Feature activation+0.007
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
why
Token why
Feature activation+0.000
Top resid features:
we
Token we
Feature activation-0.020
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
ll
Tokenll
Feature activation+0.007
Top resid features:
make
Token make
Feature activation+0.017
Top resid features:
room
Token room
Feature activation+5.245
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+0.017
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
George
Token George
Feature activation+0.000
Top resid features:
Bush
Token Bush
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.004
Top resid features:
for
Token for
Feature activation-0.003
Top resid features:
one
Token one
Feature activation-0.004
Top resid features:
have
Token have
Feature activation-0.001
Top resid features:
been
Token been
Feature activation-0.006
Top resid features:
waiting
Token waiting
Feature activation+5.290
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
very
Token very
Feature activation-0.025
Top resid features:
long
Token long
Feature activation+0.082
Top resid features:
time
Token time
Feature activation+0.064
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.001
Top resid features:
Barcelona
Token Barcelona
Feature activation-0.006
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
Real
Token Real
Feature activation+0.008
Top resid features:
Madrid
Token Madrid
Feature activation-0.005
Top resid features:
destined
Token destined
Feature activation+5.215
Top resid features:
only
Token only
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
cross
Token cross
Feature activation+0.000
Top resid features:
paths
Token paths
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
It
TokenIt
Feature activation+0.001
Top resid features:
was
Token was
Feature activation+0.004
Top resid features:
not
Token not
Feature activation-0.000
Top resid features:
unusual
Token unusual
Feature activation+5.210
Top resid features:
in
Token in
Feature activation+0.025
Top resid features:
post
Token post
Feature activation-0.008
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
war
Tokenwar
Feature activation-0.009
Top resid features:
Germany
Token Germany
Feature activation+0.011
Top resid features:
making
Token making
Feature activation-0.003
Top resid features:
it
Token it
Feature activation-0.000
Top resid features:
"
Token "
Feature activation-0.002
Top resid features:
much
Tokenmuch
Feature activation+0.005
Top resid features:
more
Token more
Feature activation+0.014
Top resid features:
difficult
Token difficult
Feature activation+5.061
Top resid features:
"
Token"
Feature activation+0.015
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
find
Token find
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.009
Top resid features:
Y
Token Y
Feature activation-0.000
Top resid features:
avin
Tokenavin
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
however
Token however
Feature activation+0.008
Top resid features:
preparations
Token preparations
Feature activation+4.934
Top resid features:
were
Token were
Feature activation+0.056
Top resid features:
being
Token being
Feature activation+0.056
Top resid features:
made
Token made
Feature activation+0.096
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
walking
Token walking
Feature activation-0.016
Top resid features:
around
Token around
Feature activation-0.005
Top resid features:
cities
Token cities
Feature activation-0.003
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
towns
Token towns
Feature activation-0.006
Top resid features:
looking
Token looking
Feature activation+5.016
Top resid features:
int
Token int
Feature activation+0.009
Top resid features:
ently
Tokenently
Feature activation+0.036
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
phones
Token phones
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.004
Top resid features:
will
Token will
Feature activation+0.015
Top resid features:
is
Token is
Feature activation+0.011
Top resid features:
an
Token an
Feature activation-0.006
Top resid features:
adequate
Token adequate
Feature activation+0.089
Top resid features:
justification
Token justification
Feature activation+4.892
Top resid features:
in
Token in
Feature activation-0.025
Top resid features:
some
Token some
Feature activation+0.001
Top resid features:
cases
Token cases
Feature activation+0.049
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
pressures
Token pressures
Feature activation+0.038
Top resid features:
on
Token on
Feature activation+0.005
Top resid features:
hospital
Token hospital
Feature activation-0.002
Top resid features:
finances
Token finances
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Calls
Token Calls
Feature activation+4.862
Top resid features:
by
Token by
Feature activation+0.031
Top resid features:
regulators
Token regulators
Feature activation+0.018
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
higher
Token higher
Feature activation+0.000
Top resid features:
staff
Token staff
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.038
Top resid features:
Ļ
TokenĻ
Feature activation-0.000
Top resid features:
s
Tokens
Feature activation+0.012
Top resid features:
definitely
Token definitely
Feature activation+0.054
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
poster
Token poster
Feature activation+4.710
Top resid features:
boy
Token boy
Feature activation+0.137
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
curly
Token curly
Feature activation+0.000
Top resid features:
hair
Token hair
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
policy
Token policy
Feature activation+0.003
Top resid features:
said
Token said
Feature activation+0.005
Top resid features:
that
Token that
Feature activation-0.002
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
common
Token common
Feature activation+4.761
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
legal
Token legal
Feature activation+0.069
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
private
Token private
Feature activation+0.000
Top resid features:
universities
Token universities
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
there
Token there
Feature activation+0.006
Top resid features:
's
Token's
Feature activation+0.007
Top resid features:
plenty
Token plenty
Feature activation+0.171
Top resid features:
of
Token of
Feature activation+0.027
Top resid features:
room
Token room
Feature activation+4.223
Top resid features:
at
Token at
Feature activation+0.029
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
bottom
Token bottom
Feature activation+0.313
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Room
Token Room
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.02

Head 3: 0.03

Head 4: 0.04

Head 5: 0.09

Head 6: 0.02

Head 7: 0.02

Head 8: 0.01

Head 9: 0.68

Head 10: 0.02

Head 11: 0.03

Positive logits

for4.87

for4.21

For3.44

FOR3.40

For3.16

FOR2.87

Frie1.98

behalf1.86

orers1.72

to1.70

fort1.68

rals1.67

suitable1.62

fore1.62

awaiting1.59

irection1.57

arag1.56

towards1.51

toward1.46

reserved1.44

Negative logits

Introduced-1.77

uron-1.65

-1.62

acia-1.62

lected-1.62

izoph-1.59

construct-1.58

asted-1.51

rained-1.51

ierrez-1.50

76561-1.46

ゼウス-1.46

tackle-1.46

Appearances-1.45

-1.45

-1.42

illance-1.41

Problem-1.41

��-1.39

rican-1.38

INTERVAL 6.116 - 6.795
CONTAINS 0.000%

the
Token the
Feature activation+0.000
receiver
Token receiver
Feature activation+0.000
is
Token is
Feature activation+0.000
responsible
Token responsible
Feature activation+0.112
not
Token not
Feature activation+5.200
only
Token only
Feature activation+6.795
for
Token for
Feature activation+0.000
underneath
Token underneath
Feature activation+0.000
routes
Token routes
Feature activation+0.000
but
Token but
Feature activation+0.477
also
Token also
Feature activation+1.280
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
room
Token room
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
trails
Token trails
Feature activation+6.525
for
Token for
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.109
us
Token us
Feature activation+0.821
,
Token,
Feature activation+0.048

INTERVAL 5.436 - 6.116
CONTAINS 0.000%

INTERVAL 4.757 - 5.436
CONTAINS 0.001%

been
Token been
Feature activation+0.000
waiting
Token waiting
Feature activation+0.603
with
Token with
Feature activation+0.000
ba
Token ba
Feature activation+2.155
ited
Tokenited
Feature activation+0.008
breath
Token breath
Feature activation+5.086
for
Token for
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
finale
Token finale
Feature activation+0.000
.
Token.
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
receiver
Token receiver
Feature activation+0.000
is
Token is
Feature activation+0.000
responsible
Token responsible
Feature activation+0.112
not
Token not
Feature activation+5.200
only
Token only
Feature activation+6.795
for
Token for
Feature activation+0.000
underneath
Token underneath
Feature activation+0.000
routes
Token routes
Feature activation+0.000
but
Token but
Feature activation+0.477
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
reason
Token reason
Feature activation+0.373
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.058
world
Token world
Feature activation+5.038
for
Token for
Feature activation+0.489
why
Token why
Feature activation+0.024
I
Token I
Feature activation+0.000
did
Token did
Feature activation+0.000
the
Token the
Feature activation+0.000
Wales
Token Wales
Feature activation+0.000
and
Token and
Feature activation+0.000
Northern
Token Northern
Feature activation+0.000
Ireland
Token Ireland
Feature activation+0.000
too
Token too
Feature activation+0.000
-
Token -
Feature activation+5.053
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
nations
Token nations
Feature activation+0.000
and
Token and
Feature activation+0.000
on
Token on
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
as
Token as
Feature activation+0.000
preparations
Token preparations
Feature activation+0.983
took
Token took
Feature activation+1.230
place
Token place
Feature activation+5.280
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
aim
Token aim
Feature activation+0.000

INTERVAL 4.077 - 4.757
CONTAINS 0.001%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
definitely
Token definitely
Feature activation+0.000
the
Token the
Feature activation+0.000
poster
Token poster
Feature activation+0.000
boy
Token boy
Feature activation+4.321
for
Token for
Feature activation+0.000
curly
Token curly
Feature activation+0.000
hair
Token hair
Feature activation+0.000
.
Token.
Feature activation+0.000
Su
Token Su
Feature activation+0.000
it
Token it
Feature activation+0.000
"
Token "
Feature activation+0.000
much
Tokenmuch
Feature activation+0.000
more
Token more
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
"
Token"
Feature activation+4.623
for
Token for
Feature activation+0.000
people
Token people
Feature activation+0.000
to
Token to
Feature activation+0.000
find
Token find
Feature activation+0.000
legal
Token legal
Feature activation+0.000
unusual
Token unusual
Feature activation+0.353
in
Token in
Feature activation+0.005
post
Token post
Feature activation+0.068
-
Token-
Feature activation+0.000
war
Tokenwar
Feature activation+0.853
Germany
Token Germany
Feature activation+4.694
to
Token to
Feature activation+0.051
recycle
Token recycle
Feature activation+0.000
debris
Token debris
Feature activation+0.000
in
Token in
Feature activation+0.000
new
Token new
Feature activation+0.000
hospital
Token hospital
Feature activation+0.000
finances
Token finances
Feature activation+0.000
.
Token.
Feature activation+0.000
Calls
Token Calls
Feature activation+0.000
by
Token by
Feature activation+0.000
regulators
Token regulators
Feature activation+4.396
for
Token for
Feature activation+0.000
higher
Token higher
Feature activation+0.000
staff
Token staff
Feature activation+0.000
numbers
Token numbers
Feature activation+0.802
following
Token following
Feature activation+0.000
finished
Token finished
Feature activation+0.000
tied
Token tied
Feature activation+0.000
with
Token with
Feature activation+0.000
De
Token De
Feature activation+0.000
Ros
Token Ros
Feature activation+0.000
ario
Tokenario
Feature activation+4.171
for
Token for
Feature activation+0.000
leading
Token leading
Feature activation+0.000
goals
Token goals
Feature activation+0.000
core
Tokencore
Feature activation+0.000
r
Tokenr
Feature activation+0.000

INTERVAL 3.398 - 4.077
CONTAINS 0.003%

province
Token province
Feature activation+0.000
and
Token and
Feature activation+0.000
best
Token best
Feature activation+0.000
known
Token known
Feature activation+0.387
in
Token in
Feature activation+0.000
China
Token China
Feature activation+3.953
as
Token as
Feature activation+0.294
the
Token the
Feature activation+0.305
site
Token site
Feature activation+0.730
of
Token of
Feature activation+0.369
a
Token a
Feature activation+0.000
that
Token that
Feature activation+0.000
alone
Token alone
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
reason
Token reason
Feature activation+0.282
enough
Token enough
Feature activation+3.559
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
Guns
Token Guns
Feature activation+0.000
have
Token have
Feature activation+0.000
become
Token become
Feature activation+0.000
the
Token the
Feature activation+0.000
poster
Token poster
Feature activation+0.000
child
Token child
Feature activation+3.471
of
Token of
Feature activation+0.000
American
Token American
Feature activation+0.000
individual
Token individual
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
,
Token,
Feature activation+0.273
ients
Tokenients
Feature activation+0.000
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
waiting
Token waiting
Feature activation+0.000
desperately
Token desperately
Feature activation+3.699
for
Token for
Feature activation+0.000
legal
Token legal
Feature activation+0.000
protection
Token protection
Feature activation+0.313
have
Token have
Feature activation+0.000
yet
Token yet
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
Are
TokenAre
Feature activation+0.000
you
Token you
Feature activation+0.000
ready
Token ready
Feature activation+0.000
now
Token now
Feature activation+3.615
?"
Token?"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Am
TokenAm
Feature activation+0.000
anda
Tokenanda
Feature activation+0.000

INTERVAL 2.718 - 3.398
CONTAINS 0.006%

would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
be
Token be
Feature activation+0.000
famous
Token famous
Feature activation+0.000
above
Token above
Feature activation+0.561
all
Token all
Feature activation+2.751
else
Token else
Feature activation+3.443
for
Token for
Feature activation+0.233
one
Token one
Feature activation+0.000
saying
Token saying
Feature activation+0.000
:
Token:
Feature activation+0.000
called
Token called
Feature activation+0.000
on
Token on
Feature activation+0.000
Patrick
Token Patrick
Feature activation+0.000
to
Token to
Feature activation+0.000
apologize
Token apologize
Feature activation+0.000
immediately
Token immediately
Feature activation+2.838
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Act
Token Act
Feature activation+0.000
includes
Token includes
Feature activation+0.000
financial
Token financial
Feature activation+0.000
rewards
Token rewards
Feature activation+0.301
and
Token and
Feature activation+0.000
penalties
Token penalties
Feature activation+2.723
to
Token to
Feature activation+0.000
deal
Token deal
Feature activation+0.000
with
Token with
Feature activation+0.198
the
Token the
Feature activation+0.000
read
Token read
Feature activation+0.000
million
Token million
Feature activation+0.390
in
Token in
Feature activation+0.000
funding
Token funding
Feature activation+1.109
over
Token over
Feature activation+0.000
five
Token five
Feature activation+0.000
years
Token years
Feature activation+3.007
to
Token to
Feature activation+0.010
develop
Token develop
Feature activation+0.000
its
Token its
Feature activation+0.000
SM
Token SM
Feature activation+0.000
R
TokenR
Feature activation+0.000
I
Token I
Feature activation+0.000
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
be
Token be
Feature activation+0.000
eline
Tokeneline
Feature activation+0.000
straight
Token straight
Feature activation+2.901
to
Token to
Feature activation+0.000
Tough
Token Tough
Feature activation+0.000
ie
Tokenie
Feature activation+0.309
's
Token's
Feature activation+0.000
small
Token small
Feature activation+0.000

INTERVAL 2.039 - 2.718
CONTAINS 0.016%

Police
TokenPolice
Feature activation+0.000
obtained
Token obtained
Feature activation+0.000
a
Token a
Feature activation+0.000
warrant
Token warrant
Feature activation+0.234
on
Token on
Feature activation+0.000
Friday
Token Friday
Feature activation+2.701
and
Token and
Feature activation+0.000
on
Token on
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.389
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.000
rallying
Token rallying
Feature activation+0.000
cry
Token cry
Feature activation+2.264
for
Token for
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
across
Token across
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
receipt
Token receipt
Feature activation+0.000
from
Token from
Feature activation+0.000
Dollar
Token Dollar
Feature activation+0.000
ama
Tokenama
Feature activation+2.135
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
receipt
Token receipt
Feature activation+0.000
acre
Token acre
Feature activation+1.938
just
Token just
Feature activation+0.342
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
years
Token years
Feature activation+0.000
ago
Token ago
Feature activation+2.323
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.419
fetch
Token fetch
Feature activation+0.507
ing
Tokening
Feature activation+0.009
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
players
Token players
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
hunt
Token hunt
Feature activation+2.367
for
Token for
Feature activation+0.000
Lawrence
Token Lawrence
Feature activation+0.000
's
Token's
Feature activation+0.000
top
Token top
Feature activation+0.000
spot
Token spot
Feature activation+0.000

INTERVAL 1.359 - 2.039
CONTAINS 0.048%

We
TokenWe
Feature activation+0.000
commend
Token commend
Feature activation+0.000
the
Token the
Feature activation+0.000
Denver
Token Denver
Feature activation+0.000
Sheriff
Token Sheriff
Feature activation+0.728
Department
Token Department
Feature activation+1.406
for
Token for
Feature activation+0.561
its
Token its
Feature activation+0.000
cooperation
Token cooperation
Feature activation+0.000
and
Token and
Feature activation+0.095
commitment
Token commitment
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
vice
Token vice
Feature activation+0.000
president
Token president
Feature activation+0.041
of
Token of
Feature activation+0.000
finance
Token finance
Feature activation+1.659
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
are
Token are
Feature activation+0.000
s
Tokens
Feature activation+0.000
not
Token not
Feature activation+0.000
good
Token good
Feature activation+0.436
for
Token for
Feature activation+0.000
human
Token human
Feature activation+0.000
beings
Token beings
Feature activation+1.559
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Historical
Token Historical
Feature activation+0.000
examples
Token examples
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ra
TokenRa
Feature activation+0.000
ising
Tokenising
Feature activation+0.000
the
Token the
Feature activation+0.000
eligibility
Token eligibility
Feature activation+0.000
age
Token age
Feature activation+1.897
creates
Token creates
Feature activation+0.000
new
Token new
Feature activation+0.000
pressures
Token pressures
Feature activation+0.870
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
minds
Token minds
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Thanks
TokenThanks
Feature activation+0.000
,
Token,
Feature activation+1.603
my
Token my
Feature activation+0.000
first
Token first
Feature activation+0.000
time
Token time
Feature activation+0.000
ever
Token ever
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 0.680 - 1.359
CONTAINS 0.235%

he
Token he
Feature activation+0.000
sought
Token sought
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
pay
Token pay
Feature activation+0.000
back
Tokenback
Feature activation+0.688
against
Token against
Feature activation+0.000
a
Token a
Feature activation+0.000
North
Token North
Feature activation+0.000
Brunswick
Token Brunswick
Feature activation+0.000
officer
Token officer
Feature activation+0.941
when
Token when
Feature activation+0.000
Hitler
Token Hitler
Feature activation+0.000
demanded
Token demanded
Feature activation+0.000
self
Token self
Feature activation+0.000
-
Token-
Feature activation+0.000
determination
Tokendetermination
Feature activation+1.091
for
Token for
Feature activation+0.000
all
Token all
Feature activation+0.000
Germans
Token Germans
Feature activation+0.000
in
Token in
Feature activation+0.000
Austria
Token Austria
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pl
TokenPl
Feature activation+0.000
ans
Tokenans
Feature activation+0.106
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
hotel
Token hotel
Feature activation+1.269
are
Token are
Feature activation+0.000
well
Token well
Feature activation+0.000
underway
Token underway
Feature activation+0.454
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.000
otto
Tokenotto
Feature activation+0.000
apologized
Token apologized
Feature activation+0.000
to
Token to
Feature activation+0.000
everyone
Token everyone
Feature activation+0.998
who
Token who
Feature activation+0.243
took
Token took
Feature activation+0.644
offense
Token offense
Feature activation+0.691
with
Token with
Feature activation+0.139
his
Token his
Feature activation+0.000
ir
Tokenir
Feature activation+0.000
ap
Tokenap
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
.
Token.
Feature activation+0.000
Unfortunately
Token Unfortunately
Feature activation+0.000
,
Token,
Feature activation+0.980
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
tracked
Token tracked
Feature activation+0.000
down
Token down
Feature activation+0.000
by
Token by
Feature activation+0.000

INTERVAL 0.000 - 0.680
CONTAINS 99.690%

gay
Token gay
Feature activation+0.000
customers
Token customers
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
also
Token also
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
gathered
Token gathered
Feature activation+0.000
her
Token her
Feature activation+0.000
w
Token w
Feature activation+0.000
its
Tokenits
Feature activation+0.000
about
Token about
Feature activation+0.000
her
Token her
Feature activation+0.000
,
Token,
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
ascertain
Token ascertain
Feature activation+0.000
what
Token what
Feature activation+0.000
Executive
Token Executive
Feature activation+0.000
Committee
Token Committee
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
provincial
Token provincial
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
political
Token political
Feature activation+0.000
power
Token power
Feature activation+0.000
is
Token is
Feature activation+0.000
Arg
Token Arg
Feature activation+0.000
uments
Tokenuments
Feature activation+0.000
which
Token which
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
Brexit
Token Brexit
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
UK
Token UK
Feature activation+0.000
will
Token will
Feature activation+0.000
the
Token the
Feature activation+0.000
dress
Token dress
Feature activation+0.000
code
Token code
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
pupils
Token pupils
Feature activation+0.000
were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.000
being
Token being
Feature activation+0.000
segregated
Token segregated
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 5 in H10.9: (feature 18826)

TOP ACTIVATIONS
MAX = 6.521

entirely
Token entirely
Feature activation+0.000
new
Token new
Feature activation+0.000
models
Token models
Feature activation+0.000
that
Token that
Feature activation+0.000
depend
Token depend
Feature activation+0.000
entirely
Token entirely
Feature activation+6.521
on
Token on
Feature activation+0.000
existing
Token existing
Feature activation+0.000
or
Token or
Feature activation+0.000
emer
Token emer
Feature activation+0.000
gent
Tokengent
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.015
Ŀ
TokenĿ
Feature activation+0.126
exercise
Token exercise
Feature activation+0.000
that
Token that
Feature activation+0.000
relies
Token relies
Feature activation+0.000
heavily
Token heavily
Feature activation+6.304
on
Token on
Feature activation+0.143
using
Token using
Feature activation+0.000
one
Token one
Feature activation+0.000
set
Token set
Feature activation+0.000
of
Token of
Feature activation+0.000
must
Token must
Feature activation+0.000
all
Token all
Feature activation+0.000
depend
Token depend
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.401
mind
Token mind
Feature activation+6.212
on
Token on
Feature activation+0.322
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
words
Token words
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Carson
Token Carson
Feature activation+0.000
and
Token and
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
to
Token to
Feature activation+0.000
rely
Token rely
Feature activation+0.000
less
Token less
Feature activation+6.161
on
Token on
Feature activation+0.501
sound
Token sound
Feature activation+0.000
bites
Token bites
Feature activation+0.000
and
Token and
Feature activation+1.155
performance
Token performance
Feature activation+0.000
with
Token with
Feature activation+0.000
other
Token other
Feature activation+0.000
parties
Token parties
Feature activation+0.000
depended
Token depended
Feature activation+0.000
in
Token in
Feature activation+0.154
part
Token part
Feature activation+6.018
,
Token,
Feature activation+0.591
on
Token on
Feature activation+0.354
the
Token the
Feature activation+0.000
mandate
Token mandate
Feature activation+0.000
given
Token given
Feature activation+0.000
countries
Token countries
Feature activation+0.000
and
Token and
Feature activation+0.000
those
Token those
Feature activation+0.000
which
Token which
Feature activation+0.000
rely
Token rely
Feature activation+0.000
most
Token most
Feature activation+5.969
on
Token on
Feature activation+0.000
EU
Token EU
Feature activation+0.000
funding
Token funding
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
assessment
Token assessment
Feature activation+0.000
is
Token is
Feature activation+0.000
based
Token based
Feature activation+0.000
largely
Token largely
Feature activation+5.785
on
Token on
Feature activation+0.000
accounts
Token accounts
Feature activation+0.000
from
Token from
Feature activation+0.000
parish
Token parish
Feature activation+0.000
ion
Tokenion
Feature activation+0.000
Guys
Token Guys
Feature activation+0.000
are
Token are
Feature activation+0.000
relying
Token relying
Feature activation+0.000
more
Token more
Feature activation+1.670
and
Token and
Feature activation+0.000
more
Token more
Feature activation+5.716
on
Token on
Feature activation+0.000
these
Token these
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
virtual
Tokenvirtual
Feature activation+0.000
who
Token who
Feature activation+0.000
may
Token may
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
capitalize
Token capitalize
Feature activation+0.000
politically
Token politically
Feature activation+5.700
on
Token on
Feature activation+0.203
these
Token these
Feature activation+0.000
leaks
Token leaks
Feature activation+0.137
:
Token:
Feature activation+0.000
Today
Token Today
Feature activation+0.000
focus
Token focus
Feature activation+0.000
was
Token was
Feature activation+0.898
trained
Token trained
Feature activation+3.035
all
Token all
Feature activation+2.698
last
Token last
Feature activation+0.447
month
Token month
Feature activation+5.552
on
Token on
Feature activation+0.000
Argentina
Token Argentina
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.462
âĢĶ
Token âĢĶ
Feature activation+0.000
which
Token which
Feature activation+0.000
focuses
Token focuses
Feature activation+0.000
almost
Token almost
Feature activation+0.314
entirely
Token entirely
Feature activation+5.540
on
Token on
Feature activation+0.164
writings
Token writings
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
perspective
Token perspective
Feature activation+0.000
online
Token online
Feature activation+0.000
education
Token education
Feature activation+0.000
sites
Token sites
Feature activation+0.000
are
Token are
Feature activation+0.000
focused
Token focused
Feature activation+0.000
mostly
Token mostly
Feature activation+5.462
on
Token on
Feature activation+0.000
beginners
Token beginners
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
are
Token are
Feature activation+0.000
to
Token to
Feature activation+0.000
comment
Token comment
Feature activation+0.000
with
Token with
Feature activation+0.346
greater
Token greater
Feature activation+0.438
regular
Token regular
Feature activation+0.729
ity
Tokenity
Feature activation+5.453
and
Token and
Feature activation+0.375
specificity
Token specificity
Feature activation+5.385
about
Token about
Feature activation+0.000
both
Token both
Feature activation+0.000
blockchain
Token blockchain
Feature activation+0.000
with
Token with
Feature activation+0.346
greater
Token greater
Feature activation+0.438
regular
Token regular
Feature activation+0.729
ity
Tokenity
Feature activation+5.453
and
Token and
Feature activation+0.375
specificity
Token specificity
Feature activation+5.385
about
Token about
Feature activation+0.000
both
Token both
Feature activation+0.000
blockchain
Token blockchain
Feature activation+0.000
and
Token and
Feature activation+0.000
crypto
Token crypto
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
system
Token system
Feature activation+0.000
would
Token would
Feature activation+0.000
rely
Token rely
Feature activation+0.000
heavily
Token heavily
Feature activation+5.238
on
Token on
Feature activation+0.000
use
Token use
Feature activation+0.000
of
Token of
Feature activation+0.000
bi
Token bi
Feature activation+0.000
omet
Tokenomet
Feature activation+0.000
was
Token was
Feature activation+0.000
based
Token based
Feature activation+0.000
in
Token in
Feature activation+0.000
no
Token no
Feature activation+2.363
small
Token small
Feature activation+1.011
part
Token part
Feature activation+4.984
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
critique
Token critique
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
defend
Token defend
Feature activation+0.000
its
Token its
Feature activation+0.000
human
Token human
Feature activation+0.000
rights
Token rights
Feature activation+0.000
based
Token based
Feature activation+0.000
solely
Token solely
Feature activation+4.959
on
Token on
Feature activation+0.000
that
Token that
Feature activation+0.000
fact
Token fact
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
books
Token books
Feature activation+0.677
,
Token,
Feature activation+0.000
none
Token none
Feature activation+0.000
have
Token have
Feature activation+0.000
focused
Token focused
Feature activation+0.000
directly
Token directly
Feature activation+4.896
on
Token on
Feature activation+0.000
lowering
Token lowering
Feature activation+0.000
scores
Token scores
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.000
housing
Token housing
Feature activation+0.000
and
Token and
Feature activation+0.000
focus
Token focus
Feature activation+0.000
instead
Token instead
Feature activation+4.833
on
Token on
Feature activation+0.030
the
Token the
Feature activation+0.000
consequences
Token consequences
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
places
Token places
Feature activation+0.000
focused
Token focused
Feature activation+0.234
disproportion
Token disproportion
Feature activation+2.894
ally
Tokenally
Feature activation+4.705
on
Token on
Feature activation+0.000
specifics
Token specifics
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
were
Token were
Feature activation+0.000

Top DFA by src position
MAX = 7.011

created
Token created
Feature activation-0.001
Top resid features:
entirely
Token entirely
Feature activation+0.003
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
models
Token models
Feature activation+0.005
Top resid features:
that
Token that
Feature activation+0.011
Top resid features:
depend
Token depend
Feature activation+7.011
Top resid features:
entirely
Token entirely
Feature activation+0.027
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
existing
Token existing
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
emer
Token emer
Feature activation+0.000
Top resid features:
choose
Token choose
Feature activation+0.028
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ŀ
TokenĿ
Feature activation-0.004
Top resid features:
exercise
Token exercise
Feature activation+0.002
Top resid features:
that
Token that
Feature activation+0.005
Top resid features:
relies
Token relies
Feature activation+6.805
Top resid features:
heavily
Token heavily
Feature activation+0.069
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
using
Token using
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
set
Token set
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ŀ
TokenĿ
Feature activation+0.001
Top resid features:
It
Token It
Feature activation+0.003
Top resid features:
must
Token must
Feature activation+0.027
Top resid features:
all
Token all
Feature activation+0.004
Top resid features:
depend
Token depend
Feature activation+6.699
Top resid features:
in
Token in
Feature activation+0.019
Top resid features:
his
Token his
Feature activation-0.002
Top resid features:
mind
Token mind
Feature activation+0.030
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.007
Top resid features:
Carson
Token Carson
Feature activation-0.006
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
Trump
Token Trump
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
rely
Token rely
Feature activation+6.700
Top resid features:
less
Token less
Feature activation+0.081
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
sound
Token sound
Feature activation+0.000
Top resid features:
bites
Token bites
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.002
Top resid features:
were
Token were
Feature activation+0.001
Top resid features:
with
Token with
Feature activation+0.004
Top resid features:
other
Token other
Feature activation+0.001
Top resid features:
parties
Token parties
Feature activation+0.001
Top resid features:
depended
Token depended
Feature activation+6.652
Top resid features:
in
Token in
Feature activation+0.012
Top resid features:
part
Token part
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
richer
Token richer
Feature activation+0.009
Top resid features:
countries
Token countries
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
those
Token those
Feature activation+0.003
Top resid features:
which
Token which
Feature activation+0.021
Top resid features:
rely
Token rely
Feature activation+6.573
Top resid features:
most
Token most
Feature activation+0.006
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
EU
Token EU
Feature activation+0.000
Top resid features:
funding
Token funding
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
thousands
Token thousands
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
His
Token His
Feature activation-0.002
Top resid features:
assessment
Token assessment
Feature activation+0.004
Top resid features:
is
Token is
Feature activation+0.009
Top resid features:
based
Token based
Feature activation+6.370
Top resid features:
largely
Token largely
Feature activation+0.043
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
accounts
Token accounts
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
parish
Token parish
Feature activation+0.000
Top resid features:
social
Token social
Feature activation-0.001
Top resid features:
media
Token media
Feature activation-0.015
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Guys
Token Guys
Feature activation+0.008
Top resid features:
are
Token are
Feature activation+0.001
Top resid features:
relying
Token relying
Feature activation+6.202
Top resid features:
more
Token more
Feature activation+0.086
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
more
Token more
Feature activation+0.041
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
these
Token these
Feature activation+0.000
Top resid features:
Republicans
Token Republicans
Feature activation+0.002
Top resid features:
who
Token who
Feature activation+0.002
Top resid features:
may
Token may
Feature activation+0.000
Top resid features:
want
Token want
Feature activation-0.016
Top resid features:
to
Token to
Feature activation-0.008
Top resid features:
capitalize
Token capitalize
Feature activation+6.330
Top resid features:
politically
Token politically
Feature activation+0.006
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
these
Token these
Feature activation+0.000
Top resid features:
leaks
Token leaks
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Thus
Token Thus
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
focus
Token focus
Feature activation+0.249
Top resid features:
was
Token was
Feature activation+0.053
Top resid features:
trained
Token trained
Feature activation+5.823
Top resid features:
all
Token all
Feature activation+0.021
Top resid features:
last
Token last
Feature activation+0.004
Top resid features:
month
Token month
Feature activation+0.006
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Argentina
Token Argentina
Feature activation+0.000
Top resid features:
11
Token11
Feature activation+0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.003
Top resid features:
Ŀ
TokenĿ
Feature activation+0.001
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.012
Top resid features:
which
Token which
Feature activation+0.009
Top resid features:
focuses
Token focuses
Feature activation+6.125
Top resid features:
almost
Token almost
Feature activation+0.013
Top resid features:
entirely
Token entirely
Feature activation+0.018
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
writings
Token writings
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
existing
Token existing
Feature activation-0.000
Top resid features:
online
Token online
Feature activation-0.006
Top resid features:
education
Token education
Feature activation+0.001
Top resid features:
sites
Token sites
Feature activation-0.001
Top resid features:
are
Token are
Feature activation-0.003
Top resid features:
focused
Token focused
Feature activation+5.995
Top resid features:
mostly
Token mostly
Feature activation+0.030
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
beginners
Token beginners
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
They
Token They
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
world
Token world
Feature activation+0.003
Top resid features:
are
Token are
Feature activation+0.006
Top resid features:
beginning
Token beginning
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
comment
Token comment
Feature activation+5.924
Top resid features:
with
Token with
Feature activation+0.013
Top resid features:
greater
Token greater
Feature activation+0.038
Top resid features:
regular
Token regular
Feature activation+0.043
Top resid features:
ity
Tokenity
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
world
Token world
Feature activation+0.002
Top resid features:
are
Token are
Feature activation+0.006
Top resid features:
beginning
Token beginning
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
comment
Token comment
Feature activation+5.824
Top resid features:
with
Token with
Feature activation+0.014
Top resid features:
greater
Token greater
Feature activation+0.037
Top resid features:
regular
Token regular
Feature activation+0.033
Top resid features:
ity
Tokenity
Feature activation+0.022
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
faster
Token faster
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
The
Token The
Feature activation+0.015
Top resid features:
system
Token system
Feature activation+0.001
Top resid features:
would
Token would
Feature activation+0.006
Top resid features:
rely
Token rely
Feature activation+5.741
Top resid features:
heavily
Token heavily
Feature activation+0.076
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
use
Token use
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
bi
Token bi
Feature activation+0.000
Top resid features:
Wave
Token Wave
Feature activation+0.003
Top resid features:
feminist
Token feminist
Feature activation+0.001
Top resid features:
movement
Token movement
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
was
Token was
Feature activation+0.007
Top resid features:
based
Token based
Feature activation+5.478
Top resid features:
in
Token in
Feature activation+0.036
Top resid features:
no
Token no
Feature activation+0.003
Top resid features:
small
Token small
Feature activation+0.027
Top resid features:
part
Token part
Feature activation+0.085
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
never
Token never
Feature activation-0.000
Top resid features:
defend
Token defend
Feature activation+0.045
Top resid features:
its
Token its
Feature activation-0.001
Top resid features:
human
Token human
Feature activation+0.001
Top resid features:
rights
Token rights
Feature activation-0.031
Top resid features:
based
Token based
Feature activation+5.549
Top resid features:
solely
Token solely
Feature activation+0.048
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
fact
Token fact
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
books
Token books
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
none
Token none
Feature activation-0.004
Top resid features:
have
Token have
Feature activation-0.007
Top resid features:
focused
Token focused
Feature activation+5.442
Top resid features:
directly
Token directly
Feature activation+0.058
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
lowering
Token lowering
Feature activation+0.000
Top resid features:
scores
Token scores
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
more
Token more
Feature activation+0.001
Top resid features:
housing
Token housing
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
focus
Token focus
Feature activation+5.366
Top resid features:
instead
Token instead
Feature activation+0.069
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
consequences
Token consequences
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
ose
Tokenose
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
places
Token places
Feature activation-0.003
Top resid features:
focused
Token focused
Feature activation+5.245
Top resid features:
disproportion
Token disproportion
Feature activation+0.049
Top resid features:
ally
Tokenally
Feature activation+0.050
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
specifics
Token specifics
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.02

Head 3: 0.03

Head 4: 0.03

Head 5: 0.07

Head 6: 0.02

Head 7: 0.04

Head 8: 0.02

Head 9: 0.67

Head 10: 0.02

Head 11: 0.03

Positive logits

on4.65

upon4.45

On4.04

On4.01

ON3.79

on3.52

onto3.42

upon3.30

onite2.90

Upon2.86

onboard2.43

aboard2.43

atop2.39

ON2.25

onial2.21

enance2.17

ONS2.16

Upon2.14

ons2.12

onian2.07

Negative logits

behalf-2.06

ymes-2.02

ibaba-1.90

-1.77

chase-1.68

Leader-1.64

erous-1.60

worth-1.58

aez-1.57

龍�-1.54

emo-1.50

Saga-1.48

イト-1.47

ilda-1.46

strugg-1.46

bie-1.45

ey-1.43

¯¯¯¯¯¯¯¯-1.43

inders-1.42

rampage-1.42

INTERVAL 5.869 - 6.521
CONTAINS 0.001%

countries
Token countries
Feature activation+0.000
and
Token and
Feature activation+0.000
those
Token those
Feature activation+0.000
which
Token which
Feature activation+0.000
rely
Token rely
Feature activation+0.000
most
Token most
Feature activation+5.969
on
Token on
Feature activation+0.000
EU
Token EU
Feature activation+0.000
funding
Token funding
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
entirely
Token entirely
Feature activation+0.000
new
Token new
Feature activation+0.000
models
Token models
Feature activation+0.000
that
Token that
Feature activation+0.000
depend
Token depend
Feature activation+0.000
entirely
Token entirely
Feature activation+6.521
on
Token on
Feature activation+0.000
existing
Token existing
Feature activation+0.000
or
Token or
Feature activation+0.000
emer
Token emer
Feature activation+0.000
gent
Tokengent
Feature activation+0.000
must
Token must
Feature activation+0.000
all
Token all
Feature activation+0.000
depend
Token depend
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.401
mind
Token mind
Feature activation+6.212
on
Token on
Feature activation+0.322
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
words
Token words
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.015
Ŀ
TokenĿ
Feature activation+0.126
exercise
Token exercise
Feature activation+0.000
that
Token that
Feature activation+0.000
relies
Token relies
Feature activation+0.000
heavily
Token heavily
Feature activation+6.304
on
Token on
Feature activation+0.143
using
Token using
Feature activation+0.000
one
Token one
Feature activation+0.000
set
Token set
Feature activation+0.000
of
Token of
Feature activation+0.000
with
Token with
Feature activation+0.000
other
Token other
Feature activation+0.000
parties
Token parties
Feature activation+0.000
depended
Token depended
Feature activation+0.000
in
Token in
Feature activation+0.154
part
Token part
Feature activation+6.018
,
Token,
Feature activation+0.591
on
Token on
Feature activation+0.354
the
Token the
Feature activation+0.000
mandate
Token mandate
Feature activation+0.000
given
Token given
Feature activation+0.000

INTERVAL 5.217 - 5.869
CONTAINS 0.001%

with
Token with
Feature activation+0.346
greater
Token greater
Feature activation+0.438
regular
Token regular
Feature activation+0.729
ity
Tokenity
Feature activation+5.453
and
Token and
Feature activation+0.375
specificity
Token specificity
Feature activation+5.385
about
Token about
Feature activation+0.000
both
Token both
Feature activation+0.000
blockchain
Token blockchain
Feature activation+0.000
and
Token and
Feature activation+0.000
crypto
Token crypto
Feature activation+0.000
to
Token to
Feature activation+0.000
comment
Token comment
Feature activation+0.000
with
Token with
Feature activation+0.346
greater
Token greater
Feature activation+0.438
regular
Token regular
Feature activation+0.729
ity
Tokenity
Feature activation+5.453
and
Token and
Feature activation+0.375
specificity
Token specificity
Feature activation+5.385
about
Token about
Feature activation+0.000
both
Token both
Feature activation+0.000
blockchain
Token blockchain
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
assessment
Token assessment
Feature activation+0.000
is
Token is
Feature activation+0.000
based
Token based
Feature activation+0.000
largely
Token largely
Feature activation+5.785
on
Token on
Feature activation+0.000
accounts
Token accounts
Feature activation+0.000
from
Token from
Feature activation+0.000
parish
Token parish
Feature activation+0.000
ion
Tokenion
Feature activation+0.000
Guys
Token Guys
Feature activation+0.000
are
Token are
Feature activation+0.000
relying
Token relying
Feature activation+0.000
more
Token more
Feature activation+1.670
and
Token and
Feature activation+0.000
more
Token more
Feature activation+5.716
on
Token on
Feature activation+0.000
these
Token these
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
virtual
Tokenvirtual
Feature activation+0.000
online
Token online
Feature activation+0.000
education
Token education
Feature activation+0.000
sites
Token sites
Feature activation+0.000
are
Token are
Feature activation+0.000
focused
Token focused
Feature activation+0.000
mostly
Token mostly
Feature activation+5.462
on
Token on
Feature activation+0.000
beginners
Token beginners
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
are
Token are
Feature activation+0.000

INTERVAL 4.565 - 5.217
CONTAINS 0.001%

and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
places
Token places
Feature activation+0.000
focused
Token focused
Feature activation+0.234
disproportion
Token disproportion
Feature activation+2.894
ally
Tokenally
Feature activation+4.705
on
Token on
Feature activation+0.000
specifics
Token specifics
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
were
Token were
Feature activation+0.000
books
Token books
Feature activation+0.677
,
Token,
Feature activation+0.000
none
Token none
Feature activation+0.000
have
Token have
Feature activation+0.000
focused
Token focused
Feature activation+0.000
directly
Token directly
Feature activation+4.896
on
Token on
Feature activation+0.000
lowering
Token lowering
Feature activation+0.000
scores
Token scores
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
defend
Token defend
Feature activation+0.000
its
Token its
Feature activation+0.000
human
Token human
Feature activation+0.000
rights
Token rights
Feature activation+0.000
based
Token based
Feature activation+0.000
solely
Token solely
Feature activation+4.959
on
Token on
Feature activation+0.000
that
Token that
Feature activation+0.000
fact
Token fact
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ability
Token ability
Feature activation+0.000
to
Token to
Feature activation+0.000
focus
Token focus
Feature activation+0.001
,
Token,
Feature activation+0.059
not
Token not
Feature activation+1.107
only
Token only
Feature activation+4.632
just
Token just
Feature activation+4.475
on
Token on
Feature activation+0.311
inside
Token inside
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.000
housing
Token housing
Feature activation+0.000
and
Token and
Feature activation+0.000
focus
Token focus
Feature activation+0.000
instead
Token instead
Feature activation+4.833
on
Token on
Feature activation+0.030
the
Token the
Feature activation+0.000
consequences
Token consequences
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000

INTERVAL 3.913 - 4.565
CONTAINS 0.002%

must
Token must
Feature activation+0.000
focus
Token focus
Feature activation+0.000
,
Token,
Feature activation+0.243
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.213
,
Token,
Feature activation+4.019
on
Token on
Feature activation+0.148
four
Token four
Feature activation+0.000
or
Token or
Feature activation+0.000
five
Token five
Feature activation+0.000
simple
Token simple
Feature activation+0.000
that
Token that
Feature activation+0.000
seems
Token seems
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
based
Token based
Feature activation+0.000
entirely
Token entirely
Feature activation+4.226
on
Token on
Feature activation+0.000
critically
Token critically
Feature activation+0.000
assigning
Token assigning
Feature activation+0.000
numerical
Token numerical
Feature activation+0.000
ratings
Token ratings
Feature activation+0.000
by
Token by
Feature activation+0.000
Som
Token Som
Feature activation+0.000
atic
Tokenatic
Feature activation+0.000
Labs
Token Labs
Feature activation+0.000
relies
Token relies
Feature activation+0.000
instead
Token instead
Feature activation+4.348
on
Token on
Feature activation+0.000
touch
Token touch
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
impact
Token impact
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
offending
Token offending
Feature activation+4.070
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
victims
Token victims
Feature activation+0.000
;
Token;
Feature activation+0.000
one
Token one
Feature activation+0.000
ions
Tokenions
Feature activation+0.000
,
Token,
Feature activation+0.000
Farmer
Token Farmer
Feature activation+0.000
focuses
Token focuses
Feature activation+0.000
minute
Token minute
Feature activation+2.164
ly
Tokenly
Feature activation+4.093
on
Token on
Feature activation+0.027
newly
Token newly
Feature activation+0.000
available
Token available
Feature activation+0.000
transcripts
Token transcripts
Feature activation+0.000
from
Token from
Feature activation+0.000

INTERVAL 3.260 - 3.913
CONTAINS 0.002%

,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.000
contrast
Token contrast
Feature activation+0.000
,
Token,
Feature activation+0.000
focuses
Token focuses
Feature activation+0.000
more
Token more
Feature activation+3.490
on
Token on
Feature activation+0.627
software
Token software
Feature activation+0.000
than
Token than
Feature activation+1.588
hardware
Token hardware
Feature activation+0.000
:
Token:
Feature activation+1.564
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
chiefly
Token chiefly
Feature activation+0.000
focused
Token focused
Feature activation+0.000
its
Token its
Feature activation+0.422
enforcement
Token enforcement
Feature activation+3.522
effort
Token effort
Feature activation+3.518
at
Token at
Feature activation+0.000
undocumented
Token undocumented
Feature activation+0.000
immigrants
Token immigrants
Feature activation+0.000
convicted
Token convicted
Feature activation+0.000
have
Token have
Feature activation+0.000
studied
Token studied
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
age
Token age
Feature activation+3.779
on
Token on
Feature activation+0.000
productivity
Token productivity
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
classroom
Token classroom
Feature activation+0.000
to
Token to
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
gas
Token gas
Feature activation+2.626
migration
Token migration
Feature activation+3.629
on
Token on
Feature activation+0.000
aqu
Token aqu
Feature activation+0.000
if
Tokenif
Feature activation+0.000
ers
Tokeners
Feature activation+0.241
in
Token in
Feature activation+0.000
university
Token university
Feature activation+0.000
,
Token,
Feature activation+0.739
but
Token but
Feature activation+1.350
to
Token to
Feature activation+0.175
focus
Token focus
Feature activation+0.240
externally
Token externally
Feature activation+3.724
around
Token around
Feature activation+0.143
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
makes
Token makes
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 2.608 - 3.260
CONTAINS 0.005%

show
Token show
Feature activation+0.000
ered
Tokenered
Feature activation+0.000
attention
Token attention
Feature activation+0.736
and
Token and
Feature activation+0.108
fav
Token fav
Feature activation+0.000
ours
Tokenours
Feature activation+3.027
on
Token on
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
's
Token's
Feature activation+0.000
rising
Token rising
Feature activation+0.000
populist
Token populist
Feature activation+0.000
set
Token set
Feature activation+0.000
to
Token to
Feature activation+0.000
vote
Token vote
Feature activation+0.000
Nov
Token Nov
Feature activation+0.000
.
Token.
Feature activation+0.000
19
Token 19
Feature activation+2.789
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
rate
Token rate
Feature activation+0.000
increase
Token increase
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
places
Token places
Feature activation+0.000
focused
Token focused
Feature activation+0.234
disproportion
Token disproportion
Feature activation+2.894
ally
Tokenally
Feature activation+4.705
on
Token on
Feature activation+0.000
specifics
Token specifics
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
collect
Token collect
Feature activation+0.000
data
Token data
Feature activation+0.000
to
Token to
Feature activation+0.000
advise
Token advise
Feature activation+0.059
policy
Token policy
Feature activation+0.374
makers
Token makers
Feature activation+2.704
on
Token on
Feature activation+0.250
deep
Token deep
Feature activation+0.000
-
Token-
Feature activation+0.000
green
Tokengreen
Feature activation+0.000
buildings
Token buildings
Feature activation+0.000
wants
Token wants
Feature activation+0.000
the
Token the
Feature activation+0.000
House
Token House
Feature activation+0.000
to
Token to
Feature activation+0.000
vote
Token vote
Feature activation+0.000
Friday
Token Friday
Feature activation+2.690
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
legislation
Token legislation
Feature activation+0.000
to
Token to
Feature activation+0.000
begin
Token begin
Feature activation+0.000

INTERVAL 1.956 - 2.608
CONTAINS 0.009%

realistically
Token realistically
Feature activation+0.000
.
Token.
Feature activation+0.000
B
Token B
Feature activation+0.000
asing
Tokenasing
Feature activation+0.000
this
Token this
Feature activation+0.961
competition
Token competition
Feature activation+2.094
largely
Token largely
Feature activation+2.512
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
not
Token not
Feature activation+0.101
entirely
Token entirely
Feature activation+0.664
Friday
Token Friday
Feature activation+1.006
after
Token after
Feature activation+0.000
undergoing
Token undergoing
Feature activation+0.000
surgery
Token surgery
Feature activation+0.415
in
Token in
Feature activation+0.000
April
Token April
Feature activation+2.100
to
Token to
Feature activation+0.000
repair
Token repair
Feature activation+0.000
a
Token a
Feature activation+0.000
left
Token left
Feature activation+0.000
knee
Token knee
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
declined
Token declined
Feature activation+0.000
to
Token to
Feature activation+0.000
comment
Token comment
Feature activation+0.000
to
Token to
Feature activation+0.000
Reuters
Token Reuters
Feature activation+1.982
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
nature
Token nature
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
assault
Token assault
Feature activation+0.000
sprang
Token sprang
Feature activation+0.782
out
Token out
Feature activation+2.550
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.825
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
They
TokenThey
Feature activation+0.000
blame
Token blame
Feature activation+0.000
everything
Token everything
Feature activation+0.000
in
Token in
Feature activation+0.015
their
Token their
Feature activation+0.000
life
Token life
Feature activation+2.112
on
Token on
Feature activation+0.000
somebody
Token somebody
Feature activation+0.000
else
Token else
Feature activation+0.000
.
Token.
Feature activation+0.000
Good
Token Good
Feature activation+0.000

INTERVAL 1.304 - 1.956
CONTAINS 0.024%

There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
information
Token information
Feature activation+0.000
available
Token available
Feature activation+1.171
yet
Token yet
Feature activation+1.645
on
Token on
Feature activation+0.000
how
Token how
Feature activation+0.000
much
Token much
Feature activation+0.000
electricity
Token electricity
Feature activation+0.000
one
Token one
Feature activation+0.000
,
Token,
Feature activation+0.000
before
Token before
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.145
abroad
Token abroad
Feature activation+1.942
for
Token for
Feature activation+0.007
over
Token over
Feature activation+0.000
a
Token a
Feature activation+0.000
decade
Token decade
Feature activation+1.791
.
Token.
Feature activation+0.000
will
Token will
Feature activation+0.000
decide
Token decide
Feature activation+0.000
on
Token on
Feature activation+0.000
May
Token May
Feature activation+0.024
22
Token 22
Feature activation+1.842
nd
Tokennd
Feature activation+1.871
on
Token on
Feature activation+0.044
whether
Token whether
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
their
Token their
Feature activation+0.000
(
Token (
Feature activation+0.000
1
Token1
Feature activation+0.000
,
Token,
Feature activation+0.000
276
Token276
Feature activation+0.000
strikes
Token strikes
Feature activation+0.000
)
Token)
Feature activation+1.763
on
Token on
Feature activation+0.000
Syria
Token Syria
Feature activation+0.000
and
Token and
Feature activation+0.000
Iraq
Token Iraq
Feature activation+0.257
in
Token in
Feature activation+0.000
unrest
Token unrest
Feature activation+0.023
at
Token at
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
's
Token's
Feature activation+0.000
detention
Token detention
Feature activation+0.000
facilities
Token facilities
Feature activation+1.412
on
Token on
Feature activation+0.000
over
Token over
Feature activation+0.000
-
Token-
Feature activation+0.000
c
Tokenc
Feature activation+0.000
rowd
Tokenrowd
Feature activation+0.000

INTERVAL 0.652 - 1.304
CONTAINS 0.106%

,
Token,
Feature activation+0.000
despite
Token despite
Feature activation+0.000
western
Token western
Feature activation+0.000
opinions
Token opinions
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.819
contrary
Token contrary
Feature activation+0.284
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
think
Token think
Feature activation+0.000
he
Token he
Feature activation+0.000
Professor
TokenProfessor
Feature activation+0.000
Rosen
Token Rosen
Feature activation+0.000
has
Token has
Feature activation+0.000
advised
Token advised
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.992
to
Token to
Feature activation+0.000
throw
Token throw
Feature activation+0.000
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
old
Token old
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
largely
Token largely
Feature activation+0.000
successful
Token successful
Feature activation+0.000
pressure
Token pressure
Feature activation+0.000
has
Token has
Feature activation+0.797
been
Token been
Feature activation+0.560
especially
Token especially
Feature activation+0.844
intense
Token intense
Feature activation+1.018
to
Token to
Feature activation+0.000
stop
Token stop
Feature activation+0.000
,
Token,
Feature activation+0.089
which
Token which
Feature activation+0.000
was
Token was
Feature activation+0.000
considered
Token considered
Feature activation+0.000
successful
Token successful
Feature activation+0.000
,
Token,
Feature activation+1.181
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
28
Token 28
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
electrodes
Token electrodes
Feature activation+0.277
([
Token ([
Feature activation+0.000
13
Token13
Feature activation+0.000
])
Token])
Feature activation+0.684
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
details
Token details
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.000 - 0.652
CONTAINS 99.850%

consistent
Token consistent
Feature activation+0.000
and
Token and
Feature activation+0.000
known
Token known
Feature activation+0.000
to
Token to
Feature activation+0.000
us
Token us
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
Edmonton
Token Edmonton
Feature activation+0.000
Esk
Token Esk
Feature activation+0.000
park
Token park
Feature activation+0.000
now
Token now
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
take
Token take
Feature activation+0.000
an
Token an
Feature activation+0.000
overall
Token overall
Feature activation+0.000
view
Token view
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
entrance
Token entrance
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
race
Token race
Feature activation+0.000
,
Token,
Feature activation+0.000
creed
Token creed
Feature activation+0.000
,
Token,
Feature activation+0.000
skin
Token skin
Feature activation+0.000
colour
Token colour
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
break
Token break
Feature activation+0.000
the
Token the
Feature activation+0.000
cycle
Token cycle
Feature activation+0.000
of
Token of
Feature activation+0.000
pain
Token pain
Feature activation+0.000
and
Token and
Feature activation+0.000
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
route
Tokenroute
Feature activation+0.000
the
Token the
Feature activation+0.000
some
Token some
Feature activation+0.000
previous
Token previous
Feature activation+0.000
advice
Token advice
Feature activation+0.000
from
Token from
Feature activation+0.000
other
Token other
Feature activation+0.000
sections
Token sections
Feature activation+0.491
and
Token and
Feature activation+0.000
highlighting
Token highlighting
Feature activation+0.000
its
Token its
Feature activation+0.000
vital
Token vital
Feature activation+0.000
role
Token role
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 H10.9: (feature 17566)

TOP ACTIVATIONS
MAX = 4.516

to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
crib
Token crib
Feature activation+0.012
bed
Tokenbed
Feature activation+0.663
directly
Token directly
Feature activation+4.516
from
Token from
Feature activation+0.000
rules
Token rules
Feature activation+0.000
enacted
Token enacted
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
a
Token a
Feature activation+0.000
world
Token world
Feature activation+0.000
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
benefited
Token benefited
Feature activation+0.000
enormously
Token enormously
Feature activation+4.349
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
international
Token international
Feature activation+0.000
order
Token order
Feature activation+0.000
that
Token that
Feature activation+0.000
to
Token to
Feature activation+0.000
deter
Token deter
Feature activation+0.000
us
Token us
Feature activation+1.345
by
Token by
Feature activation+0.562
military
Token military
Feature activation+0.360
means
Token means
Feature activation+4.141
from
Token from
Feature activation+0.359
attacking
Token attacking
Feature activation+0.873
the
Token the
Feature activation+0.000
things
Token things
Feature activation+0.093
they
Token they
Feature activation+0.000
who
Token who
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
collect
Token collect
Feature activation+0.000
money
Token money
Feature activation+0.872
directly
Token directly
Feature activation+4.056
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
freaking
Token freaking
Feature activation+0.000
government
Token government
Feature activation+2.401
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
T
TokenT
Feature activation+0.000
otally
Tokenotally
Feature activation+0.000
disconnected
Token disconnected
Feature activation+0.000
'
Token'
Feature activation+3.821
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mar
TokenMar
Feature activation+0.000
wan
Tokenwan
Feature activation+0.000
B
Token B
Feature activation+0.000
an
Token an
Feature activation+0.000
Oklahoma
Token Oklahoma
Feature activation+0.000
initiative
Token initiative
Feature activation+0.000
barring
Token barring
Feature activation+0.000
judges
Token judges
Feature activation+0.442
there
Token there
Feature activation+3.642
from
Token from
Feature activation+0.316
considering
Token considering
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
law
Token law
Feature activation+0.000
in
Token in
Feature activation+0.682
be
Token be
Feature activation+0.000
disqualified
Token disqualified
Feature activation+0.000
on
Token on
Feature activation+0.073
date
Token date
Feature activation+0.982
of
Token of
Feature activation+0.358
conviction
Token conviction
Feature activation+3.626
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
members
Token members
Feature activation+0.000
might
Token might
Feature activation+0.000
wonder
Token wonder
Feature activation+0.000
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.000
detract
Token detract
Feature activation+0.000
s
Tokens
Feature activation+3.587
from
Token from
Feature activation+0.207
what
Token what
Feature activation+0.000
lured
Token lured
Feature activation+0.000
us
Token us
Feature activation+0.000
all
Token all
Feature activation+0.000
reported
Token reported
Feature activation+0.000
performance
Token performance
Feature activation+0.000
dev
Token dev
Feature activation+0.000
iated
Tokeniated
Feature activation+0.000
unreal
Token unreal
Feature activation+3.347
istically
Tokenistically
Feature activation+3.575
far
Token far
Feature activation+1.904
from
Token from
Feature activation+0.000
this
Token this
Feature activation+0.000
20
Token 20
Feature activation+0.000
%
Token%
Feature activation+0.000
Rebellion
Token Rebellion
Feature activation+0.000
is
Token is
Feature activation+0.000
fundamentally
Token fundamentally
Feature activation+0.000
different
Token different
Feature activation+0.000
in
Token in
Feature activation+0.000
character
Token character
Feature activation+3.517
from
Token from
Feature activation+0.000
its
Token its
Feature activation+0.000
enemy
Token enemy
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
gotten
Token gotten
Feature activation+0.000
protection
Token protection
Feature activation+0.458
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+3.488
and
Token and
Feature activation+0.206
apparently
Token apparently
Feature activation+1.180
will
Token will
Feature activation+0.000
get
Token get
Feature activation+0.218
away
Token away
Feature activation+0.000
That
Token That
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
up
Token up
Feature activation+0.000
substantially
Token substantially
Feature activation+3.472
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
42
Token 42
Feature activation+0.000
percent
Token percent
Feature activation+0.000
who
Token who
Feature activation+0.000
atton
Tokenatton
Feature activation+0.000
will
Token will
Feature activation+0.000
separate
Token separate
Feature activation+0.000
fact
Token fact
Feature activation+0.568
from
Token from
Feature activation+0.000
fiction
Token fiction
Feature activation+3.405
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.400
play
Token play
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
reported
Token reported
Feature activation+0.000
performance
Token performance
Feature activation+0.000
dev
Token dev
Feature activation+0.000
iated
Tokeniated
Feature activation+0.000
unreal
Token unreal
Feature activation+3.347
istically
Tokenistically
Feature activation+3.575
far
Token far
Feature activation+1.904
from
Token from
Feature activation+0.000
this
Token this
Feature activation+0.000
20
Token 20
Feature activation+0.000
Notice
Token Notice
Feature activation+0.000
ably
Tokenably
Feature activation+0.000
missing
Token missing
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.360
,
Token,
Feature activation+3.304
is
Token is
Feature activation+0.029
any
Token any
Feature activation+0.000
mention
Token mention
Feature activation+0.000
of
Token of
Feature activation+0.000
LTE
Token LTE
Feature activation+0.000
-
Token-
Feature activation+0.051
owned
Tokenowned
Feature activation+0.333
utilities
Token utilities
Feature activation+2.556
in
Token in
Feature activation+0.597
Puerto
Token Puerto
Feature activation+0.000
Rico
Token Rico
Feature activation+3.278
from
Token from
Feature activation+0.427
declaring
Token declaring
Feature activation+0.000
bankruptcy
Token bankruptcy
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
performance
Token performance
Feature activation+0.000
presented
Token presented
Feature activation+0.000
here
Token here
Feature activation+0.000
ranges
Token ranges
Feature activation+0.000
widely
Token widely
Feature activation+3.253
over
Token over
Feature activation+0.590
terrain
Token terrain
Feature activation+0.000
both
Token both
Feature activation+0.067
new
Token new
Feature activation+0.000
and
Token and
Feature activation+0.000
endings
Token endings
Feature activation+0.000
,
Token,
Feature activation+0.000
preventing
Token preventing
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.244
s
Tokens
Feature activation+0.357
destruction
Token destruction
Feature activation+0.833
is
Token is
Feature activation+0.000
your
Token your
Feature activation+0.000
immediate
Token immediate
Feature activation+0.000
"
Token "
Feature activation+0.000
d
Tokend
Feature activation+0.000
iver
Tokeniver
Feature activation+0.000
t
Tokent
Feature activation+0.844
attention
Token attention
Feature activation+1.627
"
Token"
Feature activation+3.162
away
Token away
Feature activation+2.646
from
Token from
Feature activation+0.159
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
of
Token of
Feature activation+0.000
Jane
Token Jane
Feature activation+0.000
Do
Token Do
Feature activation+0.000
herty
Tokenherty
Feature activation+0.000
,
Token,
Feature activation+0.000
second
Token second
Feature activation+0.000
right
Token right
Feature activation+3.161
,
Token,
Feature activation+0.221
protest
Token protest
Feature activation+0.000
outside
Token outside
Feature activation+0.000
Lloyd
Token Lloyd
Feature activation+0.000
George
Token George
Feature activation+0.000

Top DFA by src position
MAX = 4.725

appear
Token appear
Feature activation-0.006
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
have
Token have
Feature activation-0.002
Top resid features:
been
Token been
Feature activation+0.002
Top resid features:
crib
Token crib
Feature activation+0.336
Top resid features:
bed
Tokenbed
Feature activation+4.660
Top resid features:
directly
Token directly
Feature activation+0.034
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
rules
Token rules
Feature activation+0.000
Top resid features:
enacted
Token enacted
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
upon
Token upon
Feature activation+0.042
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
world
Token world
Feature activation-0.016
Top resid features:
that
Token that
Feature activation+0.005
Top resid features:
has
Token has
Feature activation+0.014
Top resid features:
benefited
Token benefited
Feature activation+4.725
Top resid features:
enormously
Token enormously
Feature activation+0.210
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
international
Token international
Feature activation+0.000
Top resid features:
order
Token order
Feature activation+0.000
Top resid features:
democracy
Token democracy
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
but
Token but
Feature activation-0.026
Top resid features:
to
Token to
Feature activation-0.034
Top resid features:
deter
Token deter
Feature activation+0.957
Top resid features:
us
Token us
Feature activation+3.855
Top resid features:
by
Token by
Feature activation-0.014
Top resid features:
military
Token military
Feature activation-0.025
Top resid features:
means
Token means
Feature activation-0.007
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
attacking
Token attacking
Feature activation+0.000
Top resid features:
camp
Token camp
Feature activation-0.001
Top resid features:
who
Token who
Feature activation+0.002
Top resid features:
don
Token don
Feature activation+0.008
Top resid features:
't
Token't
Feature activation+0.007
Top resid features:
collect
Token collect
Feature activation+0.415
Top resid features:
money
Token money
Feature activation+4.124
Top resid features:
directly
Token directly
Feature activation+0.055
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
freaking
Token freaking
Feature activation+0.000
Top resid features:
government
Token government
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
'
Token'
Feature activation+0.010
Top resid features:
T
TokenT
Feature activation+0.001
Top resid features:
otally
Tokenotally
Feature activation+0.004
Top resid features:
disconnected
Token disconnected
Feature activation+4.366
Top resid features:
'
Token'
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Mar
TokenMar
Feature activation+0.000
Top resid features:
wan
Tokenwan
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
an
Token an
Feature activation+0.001
Top resid features:
Oklahoma
Token Oklahoma
Feature activation-0.006
Top resid features:
initiative
Token initiative
Feature activation-0.005
Top resid features:
barring
Token barring
Feature activation+0.128
Top resid features:
judges
Token judges
Feature activation+3.997
Top resid features:
there
Token there
Feature activation+0.091
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
considering
Token considering
Feature activation+0.000
Top resid features:
Islamic
Token Islamic
Feature activation+0.000
Top resid features:
law
Token law
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
they
Token they
Feature activation+0.008
Top resid features:
stand
Token stand
Feature activation+0.006
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
be
Token be
Feature activation+0.008
Top resid features:
disqualified
Token disqualified
Feature activation+3.632
Top resid features:
on
Token on
Feature activation+0.052
Top resid features:
date
Token date
Feature activation+0.029
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
conviction
Token conviction
Feature activation+0.426
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
you
Token you
Feature activation-0.001
Top resid features:
might
Token might
Feature activation-0.003
Top resid features:
wonder
Token wonder
Feature activation-0.015
Top resid features:
if
Token if
Feature activation+0.025
Top resid features:
it
Token it
Feature activation+0.020
Top resid features:
detract
Token detract
Feature activation+4.037
Top resid features:
s
Tokens
Feature activation+0.078
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
lured
Token lured
Feature activation+0.000
Top resid features:
us
Token us
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.057
Top resid features:
Ļ
TokenĻ
Feature activation+0.013
Top resid features:
reported
Token reported
Feature activation+0.015
Top resid features:
performance
Token performance
Feature activation-0.023
Top resid features:
dev
Token dev
Feature activation+0.005
Top resid features:
iated
Tokeniated
Feature activation+3.940
Top resid features:
unreal
Token unreal
Feature activation+0.007
Top resid features:
istically
Tokenistically
Feature activation+0.115
Top resid features:
far
Token far
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
Rebellion
Token Rebellion
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.004
Top resid features:
fundamentally
Token fundamentally
Feature activation+0.009
Top resid features:
different
Token different
Feature activation+3.428
Top resid features:
in
Token in
Feature activation+0.184
Top resid features:
character
Token character
Feature activation+0.355
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
enemy
Token enemy
Feature activation+0.000
Top resid features:
however
Token however
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
Brennan
Token Brennan
Feature activation+0.001
Top resid features:
has
Token has
Feature activation-0.006
Top resid features:
gotten
Token gotten
Feature activation-0.014
Top resid features:
protection
Token protection
Feature activation+4.020
Top resid features:
from
Token from
Feature activation+0.038
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
White
Token White
Feature activation-0.006
Top resid features:
House
Token House
Feature activation+0.022
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
That
Token That
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+0.032
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
s
Tokens
Feature activation-0.003
Top resid features:
up
Token up
Feature activation+3.794
Top resid features:
substantially
Token substantially
Feature activation+0.211
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
42
Token 42
Feature activation+0.000
Top resid features:
percent
Token percent
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Br
TokenBr
Feature activation+0.002
Top resid features:
atton
Tokenatton
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.020
Top resid features:
separate
Token separate
Feature activation+3.603
Top resid features:
fact
Token fact
Feature activation+0.376
Top resid features:
from
Token from
Feature activation-0.005
Top resid features:
fiction
Token fiction
Feature activation-0.032
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.020
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
reported
Token reported
Feature activation+0.008
Top resid features:
performance
Token performance
Feature activation-0.019
Top resid features:
dev
Token dev
Feature activation+0.002
Top resid features:
iated
Tokeniated
Feature activation+3.859
Top resid features:
unreal
Token unreal
Feature activation+0.005
Top resid features:
istically
Tokenistically
Feature activation+0.000
Top resid features:
far
Token far
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
included
Token included
Feature activation-0.018
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Notice
Token Notice
Feature activation+0.115
Top resid features:
ably
Tokenably
Feature activation+0.013
Top resid features:
missing
Token missing
Feature activation+3.838
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
however
Token however
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
agencies
Token agencies
Feature activation+0.075
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
government
Token government
Feature activation+0.098
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
owned
Tokenowned
Feature activation+0.004
Top resid features:
utilities
Token utilities
Feature activation+1.878
Top resid features:
in
Token in
Feature activation+0.037
Top resid features:
Puerto
Token Puerto
Feature activation-0.004
Top resid features:
Rico
Token Rico
Feature activation+0.126
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
declaring
Token declaring
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.064
Top resid features:
performance
Token performance
Feature activation-0.009
Top resid features:
presented
Token presented
Feature activation-0.016
Top resid features:
here
Token here
Feature activation+0.003
Top resid features:
ranges
Token ranges
Feature activation+3.788
Top resid features:
widely
Token widely
Feature activation+0.049
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
terrain
Token terrain
Feature activation+0.000
Top resid features:
both
Token both
Feature activation+0.000
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
With
Token With
Feature activation-0.006
Top resid features:
multiple
Token multiple
Feature activation-0.006
Top resid features:
endings
Token endings
Feature activation-0.029
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
preventing
Token preventing
Feature activation+0.178
Top resid features:
Earth
Token Earth
Feature activation+3.631
Top resid features:
âĢ
TokenâĢ
Feature activation+0.024
Top resid features:
Ļ
TokenĻ
Feature activation+0.055
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
destruction
Token destruction
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.012
Top resid features:
"
Token "
Feature activation+0.001
Top resid features:
d
Tokend
Feature activation-0.001
Top resid features:
iver
Tokeniver
Feature activation+0.026
Top resid features:
t
Tokent
Feature activation+1.385
Top resid features:
attention
Token attention
Feature activation+2.223
Top resid features:
"
Token"
Feature activation+0.017
Top resid features:
away
Token away
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
work
Token work
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.019
Top resid features:
Jane
Token Jane
Feature activation-0.001
Top resid features:
Do
Token Do
Feature activation-0.002
Top resid features:
herty
Tokenherty
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.023
Top resid features:
second
Token second
Feature activation+3.697
Top resid features:
right
Token right
Feature activation+0.088
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
protest
Token protest
Feature activation+0.000
Top resid features:
outside
Token outside
Feature activation+0.000
Top resid features:
Lloyd
Token Lloyd
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.02

Head 3: 0.03

Head 4: 0.03

Head 5: 0.09

Head 6: 0.02

Head 7: 0.03

Head 8: 0.01

Head 9: 0.66

Head 10: 0.02

Head 11: 0.04

Positive logits

from5.29

from4.92

FROM4.33

From4.29

From3.97

iation2.23

originating2.21

fro2.15

heid1.98

iates1.95

assis1.67

liest1.64

iations1.63

derived1.63

iated1.63

courtesy1.62

oward1.61

thence1.59

wholesale1.58

through1.57

Negative logits

vity-1.86

��-1.85

hani-1.81

ularity-1.80

nosis-1.77

imble-1.73

AMA-1.73

oller-1.72

forth-1.71

Dragonbound-1.71

ativity-1.66

arks-1.61

iola-1.58

onwards-1.57

ppa-1.57

acha-1.56

inka-1.54

antically-1.53

+=-1.52

heng-1.49

INTERVAL 4.065 - 4.516
CONTAINS 0.000%

to
Token to
Feature activation+0.000
deter
Token deter
Feature activation+0.000
us
Token us
Feature activation+1.345
by
Token by
Feature activation+0.562
military
Token military
Feature activation+0.360
means
Token means
Feature activation+4.141
from
Token from
Feature activation+0.359
attacking
Token attacking
Feature activation+0.873
the
Token the
Feature activation+0.000
things
Token things
Feature activation+0.093
they
Token they
Feature activation+0.000
a
Token a
Feature activation+0.000
world
Token world
Feature activation+0.000
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
benefited
Token benefited
Feature activation+0.000
enormously
Token enormously
Feature activation+4.349
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
international
Token international
Feature activation+0.000
order
Token order
Feature activation+0.000
that
Token that
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
crib
Token crib
Feature activation+0.012
bed
Tokenbed
Feature activation+0.663
directly
Token directly
Feature activation+4.516
from
Token from
Feature activation+0.000
rules
Token rules
Feature activation+0.000
enacted
Token enacted
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 3.613 - 4.065
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
T
TokenT
Feature activation+0.000
otally
Tokenotally
Feature activation+0.000
disconnected
Token disconnected
Feature activation+0.000
'
Token'
Feature activation+3.821
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mar
TokenMar
Feature activation+0.000
wan
Tokenwan
Feature activation+0.000
B
Token B
Feature activation+0.000
who
Token who
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
collect
Token collect
Feature activation+0.000
money
Token money
Feature activation+0.872
directly
Token directly
Feature activation+4.056
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
freaking
Token freaking
Feature activation+0.000
government
Token government
Feature activation+2.401
?
Token?
Feature activation+0.000
an
Token an
Feature activation+0.000
Oklahoma
Token Oklahoma
Feature activation+0.000
initiative
Token initiative
Feature activation+0.000
barring
Token barring
Feature activation+0.000
judges
Token judges
Feature activation+0.442
there
Token there
Feature activation+3.642
from
Token from
Feature activation+0.316
considering
Token considering
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
law
Token law
Feature activation+0.000
in
Token in
Feature activation+0.682
be
Token be
Feature activation+0.000
disqualified
Token disqualified
Feature activation+0.000
on
Token on
Feature activation+0.073
date
Token date
Feature activation+0.982
of
Token of
Feature activation+0.358
conviction
Token conviction
Feature activation+3.626
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
members
Token members
Feature activation+0.000

INTERVAL 3.161 - 3.613
CONTAINS 0.001%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
performance
Token performance
Feature activation+0.000
presented
Token presented
Feature activation+0.000
here
Token here
Feature activation+0.000
ranges
Token ranges
Feature activation+0.000
widely
Token widely
Feature activation+3.253
over
Token over
Feature activation+0.590
terrain
Token terrain
Feature activation+0.000
both
Token both
Feature activation+0.067
new
Token new
Feature activation+0.000
and
Token and
Feature activation+0.000
Notice
Token Notice
Feature activation+0.000
ably
Tokenably
Feature activation+0.000
missing
Token missing
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.360
,
Token,
Feature activation+3.304
is
Token is
Feature activation+0.029
any
Token any
Feature activation+0.000
mention
Token mention
Feature activation+0.000
of
Token of
Feature activation+0.000
LTE
Token LTE
Feature activation+0.000
-
Token-
Feature activation+0.051
owned
Tokenowned
Feature activation+0.333
utilities
Token utilities
Feature activation+2.556
in
Token in
Feature activation+0.597
Puerto
Token Puerto
Feature activation+0.000
Rico
Token Rico
Feature activation+3.278
from
Token from
Feature activation+0.427
declaring
Token declaring
Feature activation+0.000
bankruptcy
Token bankruptcy
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
That
Token That
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
up
Token up
Feature activation+0.000
substantially
Token substantially
Feature activation+3.472
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
42
Token 42
Feature activation+0.000
percent
Token percent
Feature activation+0.000
who
Token who
Feature activation+0.000
endings
Token endings
Feature activation+0.000
,
Token,
Feature activation+0.000
preventing
Token preventing
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+3.244
s
Tokens
Feature activation+0.357
destruction
Token destruction
Feature activation+0.833
is
Token is
Feature activation+0.000
your
Token your
Feature activation+0.000
immediate
Token immediate
Feature activation+0.000

INTERVAL 2.710 - 3.161
CONTAINS 0.002%

enough
Token enough
Feature activation+0.000
in
Token in
Feature activation+0.000
protecting
Token protecting
Feature activation+0.000
individuals
Token individuals
Feature activation+1.127
and
Token and
Feature activation+0.000
consumers
Token consumers
Feature activation+2.712
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
warned
Token warned
Feature activation+0.000
had
Token had
Feature activation+0.000
had
Token had
Feature activation+0.000
assurances
Token assurances
Feature activation+0.200
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+2.755
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+1.869
.
Token.
Feature activation+0.000
walked
Token walked
Feature activation+0.000
away
Token away
Feature activation+0.000
under
Token under
Feature activation+0.000
cover
Token cover
Feature activation+0.000
of
Token of
Feature activation+0.000
darkness
Token darkness
Feature activation+2.719
on
Token on
Feature activation+0.000
June
Token June
Feature activation+0.000
30
Token 30
Feature activation+1.434
,
Token,
Feature activation+0.000
2009
Token 2009
Feature activation+0.734
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
received
Token received
Feature activation+0.000
the
Token the
Feature activation+0.000
letter
Token letter
Feature activation+0.875
yesterday
Token yesterday
Feature activation+2.987
âĢ¦
TokenâĢ¦
Feature activation+0.828
earlier
Token earlier
Feature activation+0.251
today
Token today
Feature activation+1.382
,
Token,
Feature activation+1.117
there
Token there
Feature activation+0.000
hearing
Token hearing
Feature activation+0.081
stories
Token stories
Feature activation+1.178
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.822
every
Tokenevery
Feature activation+0.110
week
Token week
Feature activation+2.753
,
Token,
Feature activation+1.375
if
Token if
Feature activation+0.000
not
Token not
Feature activation+0.000
every
Token every
Feature activation+0.000
day
Token day
Feature activation+2.139

INTERVAL 2.258 - 2.710
CONTAINS 0.006%

save
Token save
Feature activation+0.000
stranded
Token stranded
Feature activation+0.000
people
Token people
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
woods
Token woods
Feature activation+2.372
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
have
Token have
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
withdraw
Token withdraw
Feature activation+0.026
the
Token the
Feature activation+0.626
product
Token product
Feature activation+2.468
off
Token off
Feature activation+0.434
the
Token the
Feature activation+0.095
shelves
Token shelves
Feature activation+1.305
,
Token,
Feature activation+0.323
despite
Token despite
Feature activation+0.236
just
Token just
Feature activation+1.722
20
Token 20
Feature activation+0.000
%
Token%
Feature activation+2.558
from
Token from
Feature activation+0.000
last
Token last
Feature activation+0.000
weekend
Token weekend
Feature activation+2.490
.
Token.
Feature activation+0.000
Tr
Token Tr
Feature activation+0.000
istar
Tokenistar
Feature activation+0.000
keeps
Token keeps
Feature activation+0.000
adding
Token adding
Feature activation+0.000
and
Token and
Feature activation+0.000
Queen
Token Queen
Feature activation+0.000
threatened
Token threatened
Feature activation+0.000
to
Token to
Feature activation+0.000
withdraw
Token withdraw
Feature activation+0.000
Spain
Token Spain
Feature activation+2.346
's
Token's
Feature activation+0.246
troops
Token troops
Feature activation+1.912
from
Token from
Feature activation+1.013
defending
Token defending
Feature activation+0.766
the
Token the
Feature activation+0.000
subject
Token subject
Feature activation+0.000
to
Token to
Feature activation+0.226
domestic
Token domestic
Feature activation+0.000
violence
Token violence
Feature activation+0.929
restraining
Token restraining
Feature activation+0.637
orders
Token orders
Feature activation+2.542
from
Token from
Feature activation+1.363
possessing
Token possessing
Feature activation+0.318
firearms
Token firearms
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000

INTERVAL 1.807 - 2.258
CONTAINS 0.012%

is
Token is
Feature activation+0.000
never
Token never
Feature activation+0.000
one
Token one
Feature activation+0.000
to
Token to
Feature activation+0.000
shrink
Token shrink
Feature activation+0.000
back
Token back
Feature activation+1.963
when
Token when
Feature activation+0.106
accused
Token accused
Feature activation+0.000
.
Token.
Feature activation+0.000
What
Token What
Feature activation+0.000
was
Token was
Feature activation+0.000
face
Token face
Feature activation+0.000
criticism
Token criticism
Feature activation+0.083
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
conservative
Token conservative
Feature activation+0.000
opposition
Token opposition
Feature activation+1.807
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Cru
TokenCru
Feature activation+0.000
cially
Tokencially
Feature activation+0.000
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+2.755
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+1.869
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Bey
TokenBey
Feature activation+0.000
on
Tokenon
Feature activation+0.000
she
Token she
Feature activation+0.000
"
Token "
Feature activation+0.000
bor
Tokenbor
Feature activation+0.000
row
Tokenrow
Feature activation+0.000
ed
Tokened
Feature activation+0.377
"
Token"
Feature activation+1.976
from
Token from
Feature activation+0.000
M
Token M
Feature activation+0.000
AGES
TokenAGES
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
banks
Token banks
Feature activation+0.000
were
Token were
Feature activation+0.000
used
Token used
Feature activation+0.000
to
Token to
Feature activation+0.000
divert
Token divert
Feature activation+0.000
money
Token money
Feature activation+1.905
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.716
through
Token through
Feature activation+0.000
loans
Token loans
Feature activation+0.000

INTERVAL 1.355 - 1.807
CONTAINS 0.028%

clear
Token clear
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.752
at
Token at
Feature activation+0.000
this
Token this
Feature activation+0.000
stage
Token stage
Feature activation+1.657
that
Token that
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Snowden
Token Snowden
Feature activation+0.000
.
Token .
Feature activation+0.000
responsibilities
Token responsibilities
Feature activation+0.122
for
Token for
Feature activation+0.000
those
Token those
Feature activation+0.000
claiming
Token claiming
Feature activation+0.000
this
Token this
Feature activation+0.000
right
Token right
Feature activation+1.364
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Wisconsin
Token Wisconsin
Feature activation+0.000
find
Token find
Feature activation+0.000
much
Token much
Feature activation+0.000
support
Token support
Feature activation+0.011
from
Token from
Feature activation+0.000
Roth
Token Roth
Feature activation+0.000
bard
Tokenbard
Feature activation+1.529
ians
Tokenians
Feature activation+1.636
when
Token when
Feature activation+0.000
they
Token they
Feature activation+0.000
define
Token define
Feature activation+0.000
their
Token their
Feature activation+0.000
rankings
Token rankings
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
received
Token received
Feature activation+0.000
scholarship
Token scholarship
Feature activation+0.000
offers
Token offers
Feature activation+1.444
from
Token from
Feature activation+0.000
Duke
Token Duke
Feature activation+0.000
and
Token and
Feature activation+0.000
Kentucky
Token Kentucky
Feature activation+0.593
on
Token on
Feature activation+0.000
web
Token web
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
shift
Token shift
Feature activation+0.052
away
Token away
Feature activation+1.603
from
Token from
Feature activation+0.303
using
Token using
Feature activation+0.000
proprietary
Token proprietary
Feature activation+0.000
plugin
Token plugin
Feature activation+0.000
technologies
Token technologies
Feature activation+0.000

INTERVAL 0.903 - 1.355
CONTAINS 0.070%

friend
Token friend
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
watching
Token watching
Feature activation+0.478
the
Token the
Feature activation+0.000
game
Token game
Feature activation+1.016
at
Token at
Feature activation+0.000
my
Token my
Feature activation+0.000
place
Token place
Feature activation+0.432
stood
Token stood
Feature activation+0.000
up
Token up
Feature activation+0.000
:
Token:
Feature activation+0.000
'
Token '
Feature activation+0.000
I
TokenI
Feature activation+0.000
fully
Token fully
Feature activation+0.000
expect
Token expect
Feature activation+0.000
'
Token'
Feature activation+0.963
fair
Token fair
Feature activation+0.157
treatment
Token treatment
Feature activation+0.000
by
Token by
Feature activation+0.000
DNC
Token DNC
Feature activation+0.000
in
Token in
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000
investigators
Token investigators
Feature activation+1.684
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.440
,
Token,
Feature activation+0.000
particularly
Token particularly
Feature activation+0.990
since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
investigators
Token investigators
Feature activation+0.000
have
Token have
Feature activation+0.000
shown
Token shown
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
received
Token received
Feature activation+0.000
a
Token a
Feature activation+0.000
muted
Token muted
Feature activation+0.000
response
Token response
Feature activation+1.020
from
Token from
Feature activation+0.000
analysts
Token analysts
Feature activation+1.165
and
Token and
Feature activation+0.028
investors
Token investors
Feature activation+0.727
since
Token since
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
ret
Tokenret
Feature activation+0.000
ired
Tokenired
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.244
and
Token and
Feature activation+0.000
came
Token came
Feature activation+0.000
back
Token back
Feature activation+0.000
twice
Token twice
Feature activation+0.265
,
Token,
Feature activation+0.000

INTERVAL 0.452 - 0.903
CONTAINS 0.252%

idi
Tokenidi
Feature activation+0.446
women
Token women
Feature activation+0.087
and
Token and
Feature activation+0.000
children
Token children
Feature activation+0.649
as
Token as
Feature activation+0.000
slaves
Token slaves
Feature activation+0.818
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
had
Token had
Feature activation+0.000
Taking
Token Taking
Feature activation+0.000
away
Token away
Feature activation+0.000
folks
Token folks
Feature activation+0.030
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.044
homes
Token homes
Feature activation+0.624
and
Token and
Feature activation+0.000
farms
Token farms
Feature activation+1.340
for
Token for
Feature activation+0.152
political
Token political
Feature activation+0.000
theater
Token theater
Feature activation+0.398
,
Token,
Feature activation+0.000
taking
Token taking
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
federal
Token federal
Feature activation+0.000
government
Token government
Feature activation+0.655
the
Token the
Feature activation+0.000
power
Token power
Feature activation+0.000
of
Token of
Feature activation+0.000
borrowing
Token borrowing
Feature activation+0.000
.
Token.
Feature activation+0.000
where
Token where
Feature activation+0.000
contributions
Token contributions
Feature activation+0.000
to
Token to
Feature activation+0.000
production
Token production
Feature activation+0.703
and
Token and
Feature activation+0.000
consumption
Token consumption
Feature activation+0.629
must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.000
measured
Token measured
Feature activation+0.000
in
Token in
Feature activation+0.000
minute
Token minute
Feature activation+0.000
_
Token_
Feature activation+0.420
id
Tokenid
Feature activation+0.759
,
Token ,
Feature activation+0.074
name
Token name
Feature activation+0.320
,
Token ,
Feature activation+0.108
passage
Token passage
Feature activation+0.613
,
Token ,
Feature activation+0.536
t
Token t
Feature activation+0.000
sv
Tokensv
Feature activation+0.338
FROM
Token FROM
Feature activation+0.000
(
Token (
Feature activation+0.000

INTERVAL 0.000 - 0.452
CONTAINS 99.628%

next
Token next
Feature activation+0.000
year
Token year
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
/
Token/
Feature activation+0.000
18
Token18
Feature activation+0.000
,
Token,
Feature activation+0.000
Ontario
Token Ontario
Feature activation+0.000
otherwise
Token otherwise
Feature activation+0.000
plastic
Token plastic
Feature activation+0.000
gun
Token gun
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
C
TokenC
Feature activation+0.000
rim
Tokenrim
Feature activation+0.000
inals
Tokeninals
Feature activation+0.000
can
Token can
Feature activation+0.000
then
Token then
Feature activation+0.000
an
Token an
Feature activation+0.000
unused
Token unused
Feature activation+0.000
sub
Token sub
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
national
Token national
Feature activation+0.000
team
Token team
Feature activation+0.000
<
Token <
Feature activation+0.000
boost
Tokenboost
Feature activation+0.000
/
Token/
Feature activation+0.000
int
Tokenint
Feature activation+0.000
r
Tokenr
Feature activation+0.000
usive
Tokenusive
Feature activation+0.000
_
Token_
Feature activation+0.000
ptr
Tokenptr
Feature activation+0.000
.
Token.
Feature activation+0.000
h
Tokenh
Feature activation+0.000
pp
Tokenpp
Feature activation+0.000
that
Token that
Feature activation+0.000
made
Token made
Feature activation+0.000
him
Token him
Feature activation+0.000
the
Token the
Feature activation+0.000
No
Token No
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token 4
Feature activation+0.000
overall
Token overall
Feature activation+0.000
selection
Token selection
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
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 H10.9: (feature 18866)

TOP ACTIVATIONS
MAX = 4.451

the
Token the
Feature activation+0.000
charges
Token charges
Feature activation+0.000
against
Token against
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Anderson
Token Anderson
Feature activation+4.451
dismissed
Token dismissed
Feature activation+0.000
,
Token,
Feature activation+0.000
acknowledging
Token acknowledging
Feature activation+0.484
that
Token that
Feature activation+0.421
the
Token the
Feature activation+0.000
Arabia
Token Arabia
Feature activation+0.000
was
Token was
Feature activation+0.000
kidnapped
Token kidnapped
Feature activation+0.000
and
Token and
Feature activation+0.000
gang
Token gang
Feature activation+0.205
-
Token-
Feature activation+4.195
raped
Tokenraped
Feature activation+0.000
by
Token by
Feature activation+0.102
seven
Token seven
Feature activation+0.000
men
Token men
Feature activation+0.000
.
Token.
Feature activation+0.131
re
Token re
Feature activation+0.474
-
Token-
Feature activation+1.645
painted
Tokenpainted
Feature activation+0.000
and
Token and
Feature activation+0.715
re
Token re
Feature activation+1.626
-
Token-
Feature activation+3.835
used
Tokenused
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
Pre
TokenPre
Feature activation+0.000
vent
Tokenvent
Feature activation+0.000
strategy
Token strategy
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.153
ramp
Token ramp
Feature activation+3.633
ed
Tokened
Feature activation+0.612
up
Token up
Feature activation+0.000
despite
Token despite
Feature activation+0.000
'
Token '
Feature activation+0.000
big
Tokenbig
Feature activation+0.000
still
Token still
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.000
be
Tokenbe
Feature activation+0.000
-
Token-
Feature activation+3.591
named
Tokennamed
Feature activation+0.000
pick
Token pick
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
.
Token .
Feature activation+0.000
.
Token .
Feature activation+0.000
is
Token is
Feature activation+0.000
being
Token being
Feature activation+0.241
very
Token very
Feature activation+2.823
aggressively
Token aggressively
Feature activation+3.582
pursued
Token pursued
Feature activation+0.000
by
Token by
Feature activation+0.022
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
national
Token national
Feature activation+0.000
the
Token the
Feature activation+0.000
bug
Token bug
Feature activation+0.000
was
Token was
Feature activation+0.000
being
Token being
Feature activation+0.000
frequently
Token frequently
Feature activation+1.375
rep
Token rep
Feature activation+3.436
rogram
Tokenrogram
Feature activation+3.205
med
Tokenmed
Feature activation+0.219
to
Token to
Feature activation+0.026
target
Token target
Feature activation+0.032
different
Token different
Feature activation+0.000
of
Token of
Feature activation+0.075
their
Token their
Feature activation+0.000
spending
Token spending
Feature activation+0.000
promises
Token promises
Feature activation+0.000
being
Token being
Feature activation+0.027
ramp
Token ramp
Feature activation+3.303
ed
Tokened
Feature activation+0.922
up
Token up
Feature activation+0.000
over
Token over
Feature activation+0.000
a
Token a
Feature activation+0.000
four
Token four
Feature activation+0.000
duct
Token duct
Feature activation+0.000
s
Tokens
Feature activation+0.000
and
Token and
Feature activation+0.000
inside
Token inside
Feature activation+0.000
specially
Token specially
Feature activation+0.266
-
Token-
Feature activation+3.247
designed
Tokendesigned
Feature activation+0.371
smoke
Token smoke
Feature activation+0.000
detectors
Token detectors
Feature activation+0.000
that
Token that
Feature activation+0.000
had
Token had
Feature activation+0.000
fight
Token fight
Feature activation+0.000
is
Token is
Feature activation+0.000
extremely
Token extremely
Feature activation+0.116
well
Token well
Feature activation+0.803
-
Token-
Feature activation+2.523
re
Tokenre
Feature activation+3.232
he
Tokenhe
Feature activation+2.053
ars
Tokenars
Feature activation+2.479
ed
Tokened
Feature activation+0.996
and
Token and
Feature activation+0.137
that
Token that
Feature activation+0.143
bug
Token bug
Feature activation+0.000
was
Token was
Feature activation+0.000
being
Token being
Feature activation+0.000
frequently
Token frequently
Feature activation+1.375
rep
Token rep
Feature activation+3.436
rogram
Tokenrogram
Feature activation+3.205
med
Tokenmed
Feature activation+0.219
to
Token to
Feature activation+0.026
target
Token target
Feature activation+0.032
different
Token different
Feature activation+0.000
sites
Token sites
Feature activation+0.000
sn
Token sn
Feature activation+0.000
acking
Tokenacking
Feature activation+0.000
on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
freshly
Token freshly
Feature activation+0.000
m
Token m
Feature activation+3.205
owed
Tokenowed
Feature activation+0.000
lawn
Token lawn
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ess
Tokeness
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
oft
Token oft
Feature activation+0.000
-
Token-
Feature activation+1.268
c
Tokenc
Feature activation+3.196
ited
Tokenited
Feature activation+0.000
article
Token article
Feature activation+0.000
about
Token about
Feature activation+0.000
free
Token free
Feature activation+0.000
mon
Token mon
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
newly
Token newly
Feature activation+0.000
-
Token-
Feature activation+2.871
disc
Tokendisc
Feature activation+3.194
overed
Tokenovered
Feature activation+0.000
Hammer
Token Hammer
Feature activation+0.000
t
Tokent
Feature activation+0.000
oss
Tokenoss
Feature activation+0.000
malware
Token malware
Feature activation+0.000
federal
Token federal
Feature activation+0.000
controls
Token controls
Feature activation+0.000
on
Token on
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
be
Token be
Feature activation+0.000
loos
Token loos
Feature activation+3.130
ened
Tokenened
Feature activation+0.351
slightly
Token slightly
Feature activation+0.011
to
Token to
Feature activation+0.000
account
Token account
Feature activation+0.000
for
Token for
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
have
Token have
Feature activation+0.019
financially
Token financially
Feature activation+1.823
not
Token not
Feature activation+3.123
been
Token been
Feature activation+0.418
feasible
Token feasible
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
rank
Token rank
Feature activation+0.000
les
Tokenles
Feature activation+0.000
at
Token at
Feature activation+0.000
being
Token being
Feature activation+0.000
object
Token object
Feature activation+3.087
ified
Tokenified
Feature activation+0.000
and
Token and
Feature activation+0.729
she
Token she
Feature activation+0.000
and
Token and
Feature activation+0.000
Don
Token Don
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000
memes
Token memes
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
freshly
Token freshly
Feature activation+0.000
mint
Token mint
Feature activation+3.079
ed
Tokened
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
account
Token account
Feature activation+0.000
).
Token).
Feature activation+0.000
As
Token As
Feature activation+0.000
's
Token's
Feature activation+0.000
innovations
Token innovations
Feature activation+0.000
must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.120
"
Token "
Feature activation+2.520
im
Tokenim
Feature activation+3.074
ple
Tokenple
Feature activation+2.513
mented
Tokenmented
Feature activation+0.000
with
Token with
Feature activation+0.021
all
Token all
Feature activation+0.077
speed
Token speed
Feature activation+0.000
Repe
Token Repe
Feature activation+0.000
al
Tokenal
Feature activation+0.000
Bill
Token Bill
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
be
Token be
Feature activation+0.000
t
Token t
Feature activation+3.048
abled
Tokenabled
Feature activation+0.000
by
Token by
Feature activation+0.000
an
Token an
Feature activation+0.000
opposition
Token opposition
Feature activation+0.000
party
Token party
Feature activation+0.000

Top DFA by src position
MAX = 5.146

attorney
Token attorney
Feature activation+0.001
Top resid features:
moved
Token moved
Feature activation-0.028
Top resid features:
to
Token to
Feature activation-0.006
Top resid features:
have
Token have
Feature activation-0.100
Top resid features:
the
Token the
Feature activation-0.025
Top resid features:
charges
Token charges
Feature activation+5.146
Top resid features:
against
Token against
Feature activation-0.007
Top resid features:
Mr
Token Mr
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Anderson
Token Anderson
Feature activation+0.011
Top resid features:
dismissed
Token dismissed
Feature activation+0.000
Top resid features:
Saudi
Token Saudi
Feature activation-0.001
Top resid features:
Arabia
Token Arabia
Feature activation+0.002
Top resid features:
was
Token was
Feature activation+0.088
Top resid features:
kidnapped
Token kidnapped
Feature activation-0.009
Top resid features:
and
Token and
Feature activation+0.566
Top resid features:
gang
Token gang
Feature activation+3.886
Top resid features:
-
Token-
Feature activation+0.016
Top resid features:
raped
Tokenraped
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
seven
Token seven
Feature activation+0.000
Top resid features:
men
Token men
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.183
Top resid features:
re
Token re
Feature activation+0.271
Top resid features:
-
Token-
Feature activation+0.024
Top resid features:
painted
Tokenpainted
Feature activation+0.036
Top resid features:
and
Token and
Feature activation+1.310
Top resid features:
re
Token re
Feature activation+2.257
Top resid features:
-
Token-
Feature activation+0.063
Top resid features:
used
Tokenused
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
number
Token number
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Pre
TokenPre
Feature activation-0.001
Top resid features:
vent
Tokenvent
Feature activation-0.004
Top resid features:
strategy
Token strategy
Feature activation-0.011
Top resid features:
to
Token to
Feature activation+0.036
Top resid features:
be
Token be
Feature activation+3.912
Top resid features:
ramp
Token ramp
Feature activation+0.007
Top resid features:
ed
Tokened
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
despite
Token despite
Feature activation+0.000
Top resid features:
'
Token '
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.002
Top resid features:
still
Token still
Feature activation-0.012
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
to
Tokento
Feature activation+0.064
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
be
Tokenbe
Feature activation+4.021
Top resid features:
-
Token-
Feature activation+0.030
Top resid features:
named
Tokennamed
Feature activation+0.000
Top resid features:
pick
Token pick
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:
Snowden
Token Snowden
Feature activation-0.005
Top resid features:
.
Token .
Feature activation+0.002
Top resid features:
.
Token .
Feature activation+0.000
Top resid features:
.
Token .
Feature activation+0.002
Top resid features:
is
Token is
Feature activation-0.032
Top resid features:
being
Token being
Feature activation+3.315
Top resid features:
very
Token very
Feature activation+0.210
Top resid features:
aggressively
Token aggressively
Feature activation+0.467
Top resid features:
pursued
Token pursued
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
bug
Token bug
Feature activation-0.002
Top resid features:
was
Token was
Feature activation+0.102
Top resid features:
being
Token being
Feature activation+1.628
Top resid features:
frequently
Token frequently
Feature activation+2.113
Top resid features:
rep
Token rep
Feature activation+0.027
Top resid features:
rogram
Tokenrogram
Feature activation+0.000
Top resid features:
med
Tokenmed
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
target
Token target
Feature activation+0.000
Top resid features:
much
Token much
Feature activation+0.009
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
their
Token their
Feature activation-0.001
Top resid features:
spending
Token spending
Feature activation+0.005
Top resid features:
promises
Token promises
Feature activation+0.012
Top resid features:
being
Token being
Feature activation+3.608
Top resid features:
ramp
Token ramp
Feature activation+0.016
Top resid features:
ed
Tokened
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
air
Token air
Feature activation+0.003
Top resid features:
duct
Token duct
Feature activation-0.003
Top resid features:
s
Tokens
Feature activation-0.004
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
inside
Token inside
Feature activation+0.001
Top resid features:
specially
Token specially
Feature activation+3.370
Top resid features:
-
Token-
Feature activation+0.247
Top resid features:
designed
Tokendesigned
Feature activation+0.000
Top resid features:
smoke
Token smoke
Feature activation+0.000
Top resid features:
detectors
Token detectors
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
every
Token every
Feature activation-0.000
Top resid features:
fight
Token fight
Feature activation-0.014
Top resid features:
is
Token is
Feature activation+0.112
Top resid features:
extremely
Token extremely
Feature activation+0.046
Top resid features:
well
Token well
Feature activation+2.282
Top resid features:
-
Token-
Feature activation+1.157
Top resid features:
re
Tokenre
Feature activation+0.004
Top resid features:
he
Tokenhe
Feature activation+0.000
Top resid features:
ars
Tokenars
Feature activation+0.000
Top resid features:
ed
Tokened
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
bug
Token bug
Feature activation-0.001
Top resid features:
was
Token was
Feature activation+0.084
Top resid features:
being
Token being
Feature activation+1.048
Top resid features:
frequently
Token frequently
Feature activation+1.997
Top resid features:
rep
Token rep
Feature activation+0.425
Top resid features:
rogram
Tokenrogram
Feature activation+0.023
Top resid features:
med
Tokenmed
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
target
Token target
Feature activation+0.000
Top resid features:
began
Token began
Feature activation-0.037
Top resid features:
sn
Token sn
Feature activation-0.004
Top resid features:
acking
Tokenacking
Feature activation-0.001
Top resid features:
on
Token on
Feature activation-0.002
Top resid features:
their
Token their
Feature activation-0.014
Top resid features:
freshly
Token freshly
Feature activation+3.644
Top resid features:
m
Token m
Feature activation+0.003
Top resid features:
owed
Tokenowed
Feature activation+0.000
Top resid features:
lawn
Token lawn
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
reen
Tokenreen
Feature activation+0.002
Top resid features:
ess
Tokeness
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
oft
Token oft
Feature activation+1.159
Top resid features:
-
Token-
Feature activation+2.369
Top resid features:
c
Tokenc
Feature activation+0.018
Top resid features:
ited
Tokenited
Feature activation+0.000
Top resid features:
article
Token article
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
free
Token free
Feature activation+0.000
Top resid features:
ant
Tokenant
Feature activation-0.000
Top resid features:
ec
Tokenec
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
The
TokenThe
Feature activation-0.006
Top resid features:
newly
Token newly
Feature activation+2.208
Top resid features:
-
Token-
Feature activation+1.348
Top resid features:
disc
Tokendisc
Feature activation+0.015
Top resid features:
overed
Tokenovered
Feature activation+0.000
Top resid features:
Hammer
Token Hammer
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.003
Top resid features:
federal
Token federal
Feature activation+0.000
Top resid features:
controls
Token controls
Feature activation+0.022
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
marijuana
Token marijuana
Feature activation+0.006
Top resid features:
be
Token be
Feature activation+3.453
Top resid features:
loos
Token loos
Feature activation+0.021
Top resid features:
ened
Tokenened
Feature activation+0.000
Top resid features:
slightly
Token slightly
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
account
Token account
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.034
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
it
Token it
Feature activation+0.018
Top resid features:
would
Token would
Feature activation+0.058
Top resid features:
have
Token have
Feature activation+0.431
Top resid features:
financially
Token financially
Feature activation+2.906
Top resid features:
not
Token not
Feature activation+0.024
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
feasible
Token feasible
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
York
Token York
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
rank
Token rank
Feature activation+0.001
Top resid features:
les
Tokenles
Feature activation-0.005
Top resid features:
at
Token at
Feature activation-0.003
Top resid features:
being
Token being
Feature activation+3.447
Top resid features:
object
Token object
Feature activation+0.011
Top resid features:
ified
Tokenified
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
she
Token she
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
posting
Token posting
Feature activation-0.002
Top resid features:
liberal
Token liberal
Feature activation+0.004
Top resid features:
memes
Token memes
Feature activation-0.003
Top resid features:
on
Token on
Feature activation-0.003
Top resid features:
his
Token his
Feature activation-0.013
Top resid features:
freshly
Token freshly
Feature activation+3.446
Top resid features:
mint
Token mint
Feature activation+0.010
Top resid features:
ed
Tokened
Feature activation+0.000
Top resid features:
Facebook
Token Facebook
Feature activation+0.000
Top resid features:
account
Token account
Feature activation+0.000
Top resid features:
).
Token).
Feature activation+0.000
Top resid features:
ves
Tokenves
Feature activation-0.000
Top resid features:
on
Tokenon
Feature activation+0.001
Top resid features:
's
Token's
Feature activation+0.001
Top resid features:
innovations
Token innovations
Feature activation-0.001
Top resid features:
must
Token must
Feature activation+0.015
Top resid features:
be
Token be
Feature activation+1.790
Top resid features:
"
Token "
Feature activation+1.486
Top resid features:
im
Tokenim
Feature activation+0.141
Top resid features:
ple
Tokenple
Feature activation+0.000
Top resid features:
mented
Tokenmented
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Services
Token Services
Feature activation-0.000
Top resid features:
Repe
Token Repe
Feature activation-0.001
Top resid features:
al
Tokenal
Feature activation-0.001
Top resid features:
Bill
Token Bill
Feature activation-0.006
Top resid features:
cannot
Token cannot
Feature activation+0.096
Top resid features:
be
Token be
Feature activation+3.319
Top resid features:
t
Token t
Feature activation+0.029
Top resid features:
abled
Tokenabled
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
opposition
Token opposition
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.03

Head 3: 0.03

Head 4: 0.04

Head 5: 0.05

Head 6: 0.02

Head 7: 0.04

Head 8: 0.02

Head 9: 0.65

Head 10: 0.03

Head 11: 0.04

Positive logits

lished4.97

checked4.86

urated4.81

handled4.75

ledged4.65

oided4.37

rendered4.35

rolled4.32

rupted4.32

stood4.32

ened4.31

ized4.29

opted4.28

washed4.27

changed4.26

ised4.25

lied4.24

eded4.23

arthed4.19

treated4.18

Negative logits

asms-2.08

ifference-1.95

Tsukuyomi-1.92

existence-1.91

Associ-1.88

harbor-1.84

pause-1.81

USE-1.81

vac-1.80

Feeling-1.78

Statements-1.76

inqu-1.75

compose-1.75

sense-1.73

mosqu-1.73

othing-1.73

harbour-1.73

Monitoring-1.72

asking-1.71

itiveness-1.71

INTERVAL 4.006 - 4.451
CONTAINS 0.000%

Arabia
Token Arabia
Feature activation+0.000
was
Token was
Feature activation+0.000
kidnapped
Token kidnapped
Feature activation+0.000
and
Token and
Feature activation+0.000
gang
Token gang
Feature activation+0.205
-
Token-
Feature activation+4.195
raped
Tokenraped
Feature activation+0.000
by
Token by
Feature activation+0.102
seven
Token seven
Feature activation+0.000
men
Token men
Feature activation+0.000
.
Token.
Feature activation+0.131
the
Token the
Feature activation+0.000
charges
Token charges
Feature activation+0.000
against
Token against
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Anderson
Token Anderson
Feature activation+4.451
dismissed
Token dismissed
Feature activation+0.000
,
Token,
Feature activation+0.000
acknowledging
Token acknowledging
Feature activation+0.484
that
Token that
Feature activation+0.421
the
Token the
Feature activation+0.000

INTERVAL 3.561 - 4.006
CONTAINS 0.001%

Pre
TokenPre
Feature activation+0.000
vent
Tokenvent
Feature activation+0.000
strategy
Token strategy
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.153
ramp
Token ramp
Feature activation+3.633
ed
Tokened
Feature activation+0.612
up
Token up
Feature activation+0.000
despite
Token despite
Feature activation+0.000
'
Token '
Feature activation+0.000
big
Tokenbig
Feature activation+0.000
still
Token still
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.000
be
Tokenbe
Feature activation+0.000
-
Token-
Feature activation+3.591
named
Tokennamed
Feature activation+0.000
pick
Token pick
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
.
Token .
Feature activation+0.000
.
Token .
Feature activation+0.000
is
Token is
Feature activation+0.000
being
Token being
Feature activation+0.241
very
Token very
Feature activation+2.823
aggressively
Token aggressively
Feature activation+3.582
pursued
Token pursued
Feature activation+0.000
by
Token by
Feature activation+0.022
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
national
Token national
Feature activation+0.000
re
Token re
Feature activation+0.474
-
Token-
Feature activation+1.645
painted
Tokenpainted
Feature activation+0.000
and
Token and
Feature activation+0.715
re
Token re
Feature activation+1.626
-
Token-
Feature activation+3.835
used
Tokenused
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 3.115 - 3.561
CONTAINS 0.001%

duct
Token duct
Feature activation+0.000
s
Tokens
Feature activation+0.000
and
Token and
Feature activation+0.000
inside
Token inside
Feature activation+0.000
specially
Token specially
Feature activation+0.266
-
Token-
Feature activation+3.247
designed
Tokendesigned
Feature activation+0.371
smoke
Token smoke
Feature activation+0.000
detectors
Token detectors
Feature activation+0.000
that
Token that
Feature activation+0.000
had
Token had
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
have
Token have
Feature activation+0.019
financially
Token financially
Feature activation+1.823
not
Token not
Feature activation+3.123
been
Token been
Feature activation+0.418
feasible
Token feasible
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
sn
Token sn
Feature activation+0.000
acking
Tokenacking
Feature activation+0.000
on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
freshly
Token freshly
Feature activation+0.000
m
Token m
Feature activation+3.205
owed
Tokenowed
Feature activation+0.000
lawn
Token lawn
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
bug
Token bug
Feature activation+0.000
was
Token was
Feature activation+0.000
being
Token being
Feature activation+0.000
frequently
Token frequently
Feature activation+1.375
rep
Token rep
Feature activation+3.436
rogram
Tokenrogram
Feature activation+3.205
med
Tokenmed
Feature activation+0.219
to
Token to
Feature activation+0.026
target
Token target
Feature activation+0.032
different
Token different
Feature activation+0.000
sites
Token sites
Feature activation+0.000
of
Token of
Feature activation+0.075
their
Token their
Feature activation+0.000
spending
Token spending
Feature activation+0.000
promises
Token promises
Feature activation+0.000
being
Token being
Feature activation+0.027
ramp
Token ramp
Feature activation+3.303
ed
Tokened
Feature activation+0.922
up
Token up
Feature activation+0.000
over
Token over
Feature activation+0.000
a
Token a
Feature activation+0.000
four
Token four
Feature activation+0.000

INTERVAL 2.670 - 3.115
CONTAINS 0.003%

-
Token-
Feature activation+0.000
length
Tokenlength
Feature activation+0.000
video
Token video
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.727
instantly
Token instantly
Feature activation+2.671
accessed
Token accessed
Feature activation+0.000
for
Token for
Feature activation+0.010
immediate
Token immediate
Feature activation+0.000
consumption
Token consumption
Feature activation+0.000
without
Token without
Feature activation+0.000
captured
Token captured
Feature activation+0.000
and
Token and
Feature activation+0.032
later
Token later
Feature activation+0.720
re
Token re
Feature activation+1.812
-
Token-
Feature activation+2.617
upload
Tokenupload
Feature activation+2.780
ed
Tokened
Feature activation+0.000
to
Token to
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
by
Token by
Feature activation+0.000
content
Token content
Feature activation+0.000
Germany
Token Germany
Feature activation+0.000
was
Token was
Feature activation+0.000
planned
Token planned
Feature activation+0.000
but
Token but
Feature activation+0.258
never
Token never
Feature activation+0.217
material
Token material
Feature activation+2.813
ized
Tokenized
Feature activation+0.049
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
aerial
Token aerial
Feature activation+0.000
bombing
Token bombing
Feature activation+0.000
his
Token his
Feature activation+0.000
sponsors
Token sponsors
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
newly
Token newly
Feature activation+0.000
-
Token-
Feature activation+2.875
ink
Tokenink
Feature activation+2.436
ed
Tokened
Feature activation+0.000
Re
Token Re
Feature activation+0.000
eb
Tokeneb
Feature activation+0.000
ok
Tokenok
Feature activation+0.000
additional
Token additional
Feature activation+0.000
financing
Token financing
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
mis
Token mis
Feature activation+1.743
appropri
Tokenappropri
Feature activation+2.742
ated
Tokenated
Feature activation+0.000
by
Token by
Feature activation+0.000
Iv
Token Iv
Feature activation+0.000
orian
Tokenorian
Feature activation+0.000
officials
Token officials
Feature activation+0.000

INTERVAL 2.225 - 2.670
CONTAINS 0.009%

suggesting
Token suggesting
Feature activation+0.000
it
Token it
Feature activation+0.000
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.101
ner
Token ner
Feature activation+2.589
fed
Tokenfed
Feature activation+0.000
/
Token/
Feature activation+1.970
rem
Tokenrem
Feature activation+2.778
oved
Tokenoved
Feature activation+0.000
/
Token/
Feature activation+2.131
and
Token and
Feature activation+0.007
how
Token how
Feature activation+0.113
this
Token this
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.673
best
Token best
Feature activation+2.479
realized
Token realized
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
community
Token community
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.055
portion
Token portion
Feature activation+0.230
of
Token of
Feature activation+0.589
their
Token their
Feature activation+0.136
middle
Token middle
Feature activation+0.570
frequencies
Token frequencies
Feature activation+2.356
carefully
Token carefully
Feature activation+1.978
lad
Token lad
Feature activation+2.870
led
Tokenled
Feature activation+0.180
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.088
every
Token every
Feature activation+0.000
fight
Token fight
Feature activation+0.000
is
Token is
Feature activation+0.000
extremely
Token extremely
Feature activation+0.116
well
Token well
Feature activation+0.803
-
Token-
Feature activation+2.523
re
Tokenre
Feature activation+3.232
he
Tokenhe
Feature activation+2.053
ars
Tokenars
Feature activation+2.479
ed
Tokened
Feature activation+0.996
and
Token and
Feature activation+0.137
the
Token the
Feature activation+0.000
Greg
Token Greg
Feature activation+0.000
orian
Tokenorian
Feature activation+0.000
Calendar
Token Calendar
Feature activation+0.000
had
Token had
Feature activation+0.000
in
Token in
Feature activation+2.429
fact
Token fact
Feature activation+2.042
advanced
Token advanced
Feature activation+0.000
to
Token to
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000

INTERVAL 1.780 - 2.225
CONTAINS 0.016%

needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.101
ner
Token ner
Feature activation+2.589
fed
Tokenfed
Feature activation+0.000
/
Token/
Feature activation+1.970
rem
Tokenrem
Feature activation+2.778
oved
Tokenoved
Feature activation+0.000
/
Token/
Feature activation+2.131
changed
Tokenchanged
Feature activation+0.000
.
Token.
Feature activation+0.000
examined
Token examined
Feature activation+2.293
since
Token since
Feature activation+0.195
last
Token last
Feature activation+0.000
July
Token July
Feature activation+1.820
re
Token re
Feature activation+0.693
-
Token-
Feature activation+1.807
tested
Tokentested
Feature activation+0.524
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
a
Token a
Feature activation+0.000
tradition
Token tradition
Feature activation+0.000
of
Token of
Feature activation+0.000
cases
Token cases
Feature activation+0.000
being
Token being
Feature activation+0.000
religiously
Token religiously
Feature activation+2.114
taken
Token taken
Feature activation+0.000
in
Token in
Feature activation+0.069
order
Token order
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.297
be
Token be
Feature activation+0.153
developed
Token developed
Feature activation+0.716
and
Token and
Feature activation+0.663
then
Token then
Feature activation+2.042
edited
Token edited
Feature activation+0.000
,
Token,
Feature activation+0.415
rem
Token rem
Feature activation+0.198
ade
Tokenade
Feature activation+0.000
and
Token and
Feature activation+1.194
was
Token was
Feature activation+0.000
being
Token being
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.100
ľ
Tokenľ
Feature activation+2.230
dis
Tokendis
Feature activation+1.497
rupt
Tokenrupt
Feature activation+1.786
ive
Tokenive
Feature activation+0.719
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 1.335 - 1.780
CONTAINS 0.034%

I
Token I
Feature activation+0.000
said
Token said
Feature activation+0.000
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
being
Token being
Feature activation+0.179
ev
Token ev
Feature activation+1.687
icted
Tokenicted
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
need
Token need
Feature activation+0.000
a
Token a
Feature activation+0.000
THIS
Token THIS
Feature activation+0.000
BOOK
Token BOOK
Feature activation+0.000
MAY
Token MAY
Feature activation+0.012
BE
Token BE
Feature activation+0.116
RE
Token RE
Feature activation+2.141
PRO
TokenPRO
Feature activation+1.621
-
Token-
Feature activation+1.477
D
Token D
Feature activation+2.014
UC
TokenUC
Feature activation+2.282
ED
TokenED
Feature activation+0.192
IN
Token IN
Feature activation+0.000
handed
Tokenhanded
Feature activation+0.000
but
Token but
Feature activation+0.000
still
Token still
Feature activation+0.000
government
Token government
Feature activation+0.000
-
Token-
Feature activation+0.000
mand
Tokenmand
Feature activation+1.395
ated
Tokenated
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
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
misrepresent
Token misrepresent
Feature activation+1.477
ed
Tokened
Feature activation+0.000
by
Token by
Feature activation+0.000
Sinn
Token Sinn
Feature activation+0.000
F
Token F
Feature activation+0.000
é
Tokené
Feature activation+0.000
ryan
Tokenryan
Feature activation+0.000
part
Token part
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.562
been
Token been
Feature activation+0.153
very
Token very
Feature activation+1.542
clearly
Token clearly
Feature activation+1.607
explained
Token explained
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
with
Token with
Feature activation+0.000

INTERVAL 0.890 - 1.335
CONTAINS 0.070%

the
Token the
Feature activation+0.000
hood
Token hood
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
publicly
Token publicly
Feature activation+0.000
-
Token-
Feature activation+1.201
available
Tokenavailable
Feature activation+0.000
kernel
Token kernel
Feature activation+0.000
files
Token files
Feature activation+0.000
.
Token.
Feature activation+0.000
Motorola
Token Motorola
Feature activation+0.000
't
Token't
Feature activation+0.000
be
Token be
Feature activation+0.000
morally
Token morally
Feature activation+0.327
or
Token or
Feature activation+0.000
eth
Token eth
Feature activation+0.000
ically
Tokenically
Feature activation+1.325
right
Token right
Feature activation+0.000
but
Token but
Feature activation+0.000
will
Token will
Feature activation+0.000
also
Token also
Feature activation+0.000
have
Token have
Feature activation+0.000
that
Token that
Feature activation+0.000
an
Token an
Feature activation+0.000
innocent
Token innocent
Feature activation+0.000
student
Token student
Feature activation+0.000
has
Token has
Feature activation+0.000
as
Token as
Feature activation+0.964
much
Token much
Feature activation+0.000
as
Token as
Feature activation+0.474
a
Token a
Feature activation+0.205
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
scanned
Token scanned
Feature activation+0.000
the
Token the
Feature activation+0.000
metal
Token metal
Feature activation+0.000
box
Token box
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.979
took
Token took
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
building
Token building
Feature activation+0.000
19
Token 19
Feature activation+0.000
April
Token April
Feature activation+0.000
having
Token having
Feature activation+0.000
been
Token been
Feature activation+0.000
pen
Token pen
Feature activation+1.305
c
Tokenc
Feature activation+0.992
illed
Tokenilled
Feature activation+0.000
in
Token in
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
comeback
Token comeback
Feature activation+0.000

INTERVAL 0.445 - 0.890
CONTAINS 0.205%

among
Token among
Feature activation+0.000
the
Token the
Feature activation+0.000
hackers
Token hackers
Feature activation+0.000
who
Token who
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.711
ve
Tokenve
Feature activation+0.390
been
Token been
Feature activation+0.000
messing
Token messing
Feature activation+0.000
with
Token with
Feature activation+0.000
electronic
Token electronic
Feature activation+0.000
tracks
Token tracks
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
was
Token was
Feature activation+0.000
fatally
Token fatally
Feature activation+0.702
struck
Token struck
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
bus
Token bus
Feature activation+0.000
while
Token while
Feature activation+0.000
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.084
compost
Token compost
Feature activation+1.399
ed
Tokened
Feature activation+0.721
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
may
Token may
Feature activation+0.000
contain
Token contain
Feature activation+0.000
pathogens
Token pathogens
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
result
Token result
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
just
Token just
Feature activation+0.582
the
Token the
Feature activation+0.000
opposite
Token opposite
Feature activation+0.000
:
Token:
Feature activation+0.000
to
Token to
Feature activation+0.000
strengthen
Token strengthen
Feature activation+0.000
living
Token living
Feature activation+0.000
in
Token in
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
un
Tokenun
Feature activation+0.000
aff
Tokenaff
Feature activation+0.506
ordable
Tokenordable
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
housing
Token housing
Feature activation+0.000
across
Token across
Feature activation+0.000

INTERVAL 0.000 - 0.445
CONTAINS 99.661%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
guarantee
Token guarantee
Feature activation+0.000
exposure
Token exposure
Feature activation+0.000
to
Token to
Feature activation+0.000
$
Token $
Feature activation+0.000
13
Token13
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
million
Token million
Feature activation+0.000
has
Token has
Feature activation+0.000
attracted
Token attracted
Feature activation+0.000
said
Token said
Feature activation+0.000
mockery
Token mockery
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
of
Token of
Feature activation+0.000
course
Token course
Feature activation+0.000
led
Token led
Feature activation+0.000
Image
Token Image
Feature activation+0.000
1
Token 1
Feature activation+0.000
of
Token of
Feature activation+0.000
/
Token /
Feature activation+0.000
17
Token 17
Feature activation+0.000
Caption
Token Caption
Feature activation+0.000
Close
Token Close
Feature activation+0.000
'
Token '
Feature activation+0.000
My
TokenMy
Feature activation+0.000
stery
Tokenstery
Feature activation+0.000
aircraft
Token aircraft
Feature activation+0.000
buses
Token buses
Feature activation+0.000
allows
Token allows
Feature activation+0.000
residents
Token residents
Feature activation+0.000
of
Token of
Feature activation+0.000
many
Token many
Feature activation+0.000
cities
Token cities
Feature activation+0.000
in
Token in
Feature activation+0.000
Southern
Token Southern
Feature activation+0.000
England
Token England
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
including
Tokenincluding
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
story
Token story
Feature activation+0.000
encaps
Token encaps
Feature activation+0.000
ulates
Tokenulates
Feature activation+0.000
everything
Token everything
Feature activation+0.000
that
Token that
Feature activation+0.000
happened
Token happened
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 H10.9: (feature 10923)

TOP ACTIVATIONS
MAX = 7.513

take
Token take
Feature activation+0.000
a
Token a
Feature activation+0.000
look
Token look
Feature activation+0.000
,
Token,
Feature activation+2.389
then
Token then
Feature activation+3.476
,
Token,
Feature activation+7.513
at
Token at
Feature activation+0.114
the
Token the
Feature activation+0.000
paternal
Token paternal
Feature activation+0.000
burden
Token burden
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
aimed
Token aimed
Feature activation+0.083
not
Token not
Feature activation+7.480
at
Token at
Feature activation+0.032
Latinos
Token Latinos
Feature activation+0.000
,
Token,
Feature activation+0.317
but
Token but
Feature activation+5.535
at
Token at
Feature activation+0.189
of
Token of
Feature activation+0.000
National
Token National
Feature activation+0.000
Focus
Token Focus
Feature activation+0.000
goals
Token goals
Feature activation+0.000
aimed
Token aimed
Feature activation+0.511
squarely
Token squarely
Feature activation+7.101
at
Token at
Feature activation+0.000
annoying
Token annoying
Feature activation+0.000
Great
Token Great
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
.
Token.
Feature activation+0.000
aimed
Token aimed
Feature activation+0.083
not
Token not
Feature activation+7.480
at
Token at
Feature activation+0.032
Latinos
Token Latinos
Feature activation+0.000
,
Token,
Feature activation+0.317
but
Token but
Feature activation+5.535
at
Token at
Feature activation+0.189
stupid
Token stupid
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
and
Token and
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
stare
Token stare
Feature activation+0.055
long
Token long
Feature activation+0.818
enough
Token enough
Feature activation+5.282
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
find
Token find
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
most
Token most
Feature activation+0.000
detailed
Token detailed
Feature activation+0.000
look
Token look
Feature activation+0.272
yet
Token yet
Feature activation+4.966
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
energy
Token energy
Feature activation+0.000
from
Token from
Feature activation+0.000
stellar
Token stellar
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
not
Token not
Feature activation+0.000
looking
Token looking
Feature activation+0.000
so
Token so
Feature activation+1.991
much
Token much
Feature activation+4.725
for
Token for
Feature activation+0.000
profiling
Token profiling
Feature activation+0.000
--
Token --
Feature activation+0.000
obvious
Token obvious
Feature activation+0.000
this
Token this
Feature activation+0.000
must
Token must
Feature activation+0.000
start
Token start
Feature activation+0.000
aiming
Token aiming
Feature activation+0.000
their
Token their
Feature activation+0.663
politics
Token politics
Feature activation+2.397
squarely
Token squarely
Feature activation+4.511
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
working
Token working
Feature activation+0.000
class
Token class
Feature activation+0.000
.
Token.
Feature activation+0.000
Gl
Token Gl
Feature activation+0.000
aston
Tokenaston
Feature activation+0.000
bury
Tokenbury
Feature activation+0.000
,
Token,
Feature activation+0.000
hint
Token hint
Feature activation+0.000
ing
Tokening
Feature activation+4.149
at
Token at
Feature activation+0.099
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
future
Token future
Feature activation+0.000
might
Token might
Feature activation+0.000
administration
Token administration
Feature activation+0.000
is
Token is
Feature activation+0.000
looking
Token looking
Feature activation+0.000
more
Token more
Feature activation+0.976
and
Token and
Feature activation+0.000
more
Token more
Feature activation+4.060
like
Token like
Feature activation+0.303
the
Token the
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+0.000
every
Token every
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
look
Token look
Feature activation+0.000
back
Token back
Feature activation+2.076
and
Token and
Feature activation+3.978
as
Token as
Feature activation+0.993
an
Token an
Feature activation+0.115
affirmation
Token affirmation
Feature activation+0.697
of
Token of
Feature activation+0.000
identity
Token identity
Feature activation+0.000
actor
Token actor
Feature activation+0.000
Charlie
Token Charlie
Feature activation+0.000
Sheen
Token Sheen
Feature activation+0.000
lashed
Token lashed
Feature activation+0.000
out
Token out
Feature activation+0.000
Monday
Token Monday
Feature activation+3.885
at
Token at
Feature activation+0.000
addiction
Token addiction
Feature activation+0.000
specialists
Token specialists
Feature activation+0.000
and
Token and
Feature activation+0.000
sitcom
Token sitcom
Feature activation+0.000
peek
Token peek
Feature activation+1.146
(
Token (
Feature activation+0.116
or
Tokenor
Feature activation+0.039
pe
Token pe
Feature activation+0.239
eks
Tokeneks
Feature activation+0.000
)
Token)
Feature activation+3.840
from
Token from
Feature activation+0.000
upcoming
Token upcoming
Feature activation+0.000
product
Token product
Feature activation+0.000
releases
Token releases
Feature activation+0.048
.
Token.
Feature activation+0.000
that
Token that
Feature activation+0.000
allow
Token allow
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
stare
Token stare
Feature activation+0.122
directly
Token directly
Feature activation+3.833
at
Token at
Feature activation+0.323
an
Token an
Feature activation+0.000
eclipse
Token eclipse
Feature activation+0.355
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
bombs
Token bombs
Feature activation+0.542
and
Token and
Feature activation+0.000
tear
Token tear
Feature activation+0.000
gas
Token gas
Feature activation+2.186
can
Token can
Feature activation+1.029
isters
Tokenisters
Feature activation+3.663
at
Token at
Feature activation+0.000
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
a
Token a
Feature activation+0.000
effort
Token effort
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
while
Token while
Feature activation+0.000
staring
Token staring
Feature activation+0.012
directly
Token directly
Feature activation+3.617
at
Token at
Feature activation+1.113
the
Token the
Feature activation+0.000
face
Token face
Feature activation+0.000
of
Token of
Feature activation+0.225
war
Token war
Feature activation+0.000
Wall
Token Wall
Feature activation+0.000
.
Token.
Feature activation+0.000
Yet
Token Yet
Feature activation+0.000
to
Token to
Feature activation+0.000
look
Token look
Feature activation+0.000
only
Token only
Feature activation+3.597
at
Token at
Feature activation+0.000
these
Token these
Feature activation+0.000
headlines
Token headlines
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
look
Token look
Feature activation+0.000
no
Token no
Feature activation+3.528
further
Token further
Feature activation+0.066
than
Token than
Feature activation+0.000
Afghanistan
Token Afghanistan
Feature activation+0.512
to
Token to
Feature activation+0.000
assess
Token assess
Feature activation+0.000
s
Tokens
Feature activation+0.000
take
Token take
Feature activation+0.000
a
Token a
Feature activation+0.000
look
Token look
Feature activation+0.000
,
Token,
Feature activation+2.389
then
Token then
Feature activation+3.476
,
Token,
Feature activation+7.513
at
Token at
Feature activation+0.114
the
Token the
Feature activation+0.000
paternal
Token paternal
Feature activation+0.000
burden
Token burden
Feature activation+0.000
we
Token we
Feature activation+0.000
normally
Token normally
Feature activation+0.000
turn
Token turn
Feature activation+0.000
our
Token our
Feature activation+0.000
noses
Token noses
Feature activation+0.000
up
Token up
Feature activation+3.475
at
Token at
Feature activation+0.000
smart
Token smart
Feature activation+0.000
telev
Token telev
Feature activation+0.000
isions
Tokenisions
Feature activation+0.000
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 8.062

âĢ
TokenâĢ
Feature activation+0.013
Top resid features:
Ļ
TokenĻ
Feature activation-0.003
Top resid features:
s
Tokens
Feature activation-0.051
Top resid features:
take
Token take
Feature activation-0.031
Top resid features:
a
Token a
Feature activation-0.013
Top resid features:
look
Token look
Feature activation+8.062
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
then
Token then
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
case
Token case
Feature activation+0.001
Top resid features:
it
Token it
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation-0.003
Top resid features:
Ļ
TokenĻ
Feature activation-0.003
Top resid features:
s
Tokens
Feature activation-0.002
Top resid features:
aimed
Token aimed
Feature activation+7.989
Top resid features:
not
Token not
Feature activation-0.002
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
Latinos
Token Latinos
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:
set
Token set
Feature activation+0.003
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
National
Token National
Feature activation-0.007
Top resid features:
Focus
Token Focus
Feature activation-0.004
Top resid features:
goals
Token goals
Feature activation-0.008
Top resid features:
aimed
Token aimed
Feature activation+7.581
Top resid features:
squarely
Token squarely
Feature activation+0.098
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
annoying
Token annoying
Feature activation+0.000
Top resid features:
Great
Token Great
Feature activation+0.000
Top resid features:
Britain
Token Britain
Feature activation+0.000
Top resid features:
case
Token case
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.009
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
s
Tokens
Feature activation-0.019
Top resid features:
aimed
Token aimed
Feature activation+4.994
Top resid features:
not
Token not
Feature activation+0.276
Top resid features:
at
Token at
Feature activation+0.284
Top resid features:
Latinos
Token Latinos
Feature activation+0.110
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
but
Token but
Feature activation+0.349
Top resid features:
high
Token high
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
if
Token if
Feature activation-0.005
Top resid features:
you
Token you
Feature activation+0.011
Top resid features:
stare
Token stare
Feature activation+5.043
Top resid features:
long
Token long
Feature activation+0.320
Top resid features:
enough
Token enough
Feature activation+0.421
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
find
Token find
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
The
TokenThe
Feature activation-0.004
Top resid features:
most
Token most
Feature activation-0.002
Top resid features:
detailed
Token detailed
Feature activation+0.054
Top resid features:
look
Token look
Feature activation+5.423
Top resid features:
yet
Token yet
Feature activation+0.022
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
energy
Token energy
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
>
Token >
Feature activation+0.027
Top resid features:
>
Token >
Feature activation+0.015
Top resid features:
I
Token I
Feature activation-0.005
Top resid features:
'm
Token'm
Feature activation-0.018
Top resid features:
not
Token not
Feature activation+0.004
Top resid features:
looking
Token looking
Feature activation+4.403
Top resid features:
so
Token so
Feature activation+0.548
Top resid features:
much
Token much
Feature activation+0.293
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
profiling
Token profiling
Feature activation+0.000
Top resid features:
--
Token --
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
but
Token but
Feature activation+0.005
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
must
Token must
Feature activation-0.021
Top resid features:
start
Token start
Feature activation+0.002
Top resid features:
aiming
Token aiming
Feature activation+2.981
Top resid features:
their
Token their
Feature activation+0.092
Top resid features:
politics
Token politics
Feature activation+1.775
Top resid features:
squarely
Token squarely
Feature activation+0.186
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
at
Token at
Feature activation-0.001
Top resid features:
Gl
Token Gl
Feature activation-0.002
Top resid features:
aston
Tokenaston
Feature activation-0.008
Top resid features:
bury
Tokenbury
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
hint
Token hint
Feature activation+4.371
Top resid features:
ing
Tokening
Feature activation+0.398
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
future
Token future
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
Donald
Token Donald
Feature activation-0.008
Top resid features:
Trump
Token Trump
Feature activation-0.019
Top resid features:
administration
Token administration
Feature activation-0.001
Top resid features:
is
Token is
Feature activation+0.011
Top resid features:
looking
Token looking
Feature activation+4.033
Top resid features:
more
Token more
Feature activation+0.520
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
more
Token more
Feature activation+0.080
Top resid features:
like
Token like
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Cent
Token Cent
Feature activation+0.000
Top resid features:
enary
Tokenenary
Feature activation+0.007
Top resid features:
,
Token,
Feature activation-0.014
Top resid features:
as
Token as
Feature activation-0.034
Top resid features:
a
Token a
Feature activation-0.033
Top resid features:
look
Token look
Feature activation+3.756
Top resid features:
back
Token back
Feature activation+0.927
Top resid features:
and
Token and
Feature activation+0.027
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
affirmation
Token affirmation
Feature activation+0.000
Top resid features:
embattled
Token embattled
Feature activation-0.004
Top resid features:
actor
Token actor
Feature activation-0.008
Top resid features:
Charlie
Token Charlie
Feature activation-0.005
Top resid features:
Sheen
Token Sheen
Feature activation+0.011
Top resid features:
lashed
Token lashed
Feature activation+0.170
Top resid features:
out
Token out
Feature activation+4.418
Top resid features:
Monday
Token Monday
Feature activation-0.134
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
addiction
Token addiction
Feature activation+0.000
Top resid features:
specialists
Token specialists
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
will
Token will
Feature activation-0.017
Top resid features:
also
Token also
Feature activation-0.011
Top resid features:
include
Token include
Feature activation-0.004
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
sneak
Token sneak
Feature activation+0.080
Top resid features:
peek
Token peek
Feature activation+4.297
Top resid features:
(
Token (
Feature activation-0.008
Top resid features:
or
Tokenor
Feature activation-0.007
Top resid features:
pe
Token pe
Feature activation+0.005
Top resid features:
eks
Tokeneks
Feature activation+0.028
Top resid features:
)
Token)
Feature activation+0.006
Top resid features:
lenses
Token lenses
Feature activation+0.002
Top resid features:
that
Token that
Feature activation-0.002
Top resid features:
allow
Token allow
Feature activation+0.008
Top resid features:
you
Token you
Feature activation+0.007
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
stare
Token stare
Feature activation+4.157
Top resid features:
directly
Token directly
Feature activation+0.174
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
eclipse
Token eclipse
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
rubber
Token rubber
Feature activation+0.003
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
co
Tokenco
Feature activation-0.000
Top resid features:
ated
Tokenated
Feature activation-0.001
Top resid features:
metal
Token metal
Feature activation+0.097
Top resid features:
bullets
Token bullets
Feature activation+3.183
Top resid features:
,
Token ,
Feature activation+0.030
Top resid features:
sound
Token sound
Feature activation+0.004
Top resid features:
bombs
Token bombs
Feature activation+0.010
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
tear
Token tear
Feature activation+0.017
Top resid features:
humanitarian
Token humanitarian
Feature activation-0.007
Top resid features:
effort
Token effort
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
even
Token even
Feature activation-0.001
Top resid features:
while
Token while
Feature activation-0.010
Top resid features:
staring
Token staring
Feature activation+3.989
Top resid features:
directly
Token directly
Feature activation+0.173
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
face
Token face
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Western
Token Western
Feature activation-0.003
Top resid features:
Wall
Token Wall
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Yet
Token Yet
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
look
Token look
Feature activation+3.982
Top resid features:
only
Token only
Feature activation+0.169
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
these
Token these
Feature activation+0.000
Top resid features:
headlines
Token headlines
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
terrorism
Tokenterrorism
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
You
Token You
Feature activation-0.002
Top resid features:
have
Token have
Feature activation-0.002
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
look
Token look
Feature activation+3.943
Top resid features:
no
Token no
Feature activation+0.117
Top resid features:
further
Token further
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
Afghanistan
Token Afghanistan
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.015
Top resid features:
Ļ
TokenĻ
Feature activation-0.008
Top resid features:
s
Tokens
Feature activation+0.030
Top resid features:
take
Token take
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.024
Top resid features:
look
Token look
Feature activation+3.516
Top resid features:
,
Token,
Feature activation+0.371
Top resid features:
then
Token then
Feature activation+0.062
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.004
Top resid features:
normally
Token normally
Feature activation-0.011
Top resid features:
turn
Token turn
Feature activation+0.007
Top resid features:
our
Token our
Feature activation-0.000
Top resid features:
noses
Token noses
Feature activation+1.500
Top resid features:
up
Token up
Feature activation+2.508
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
smart
Token smart
Feature activation+0.000
Top resid features:
telev
Token telev
Feature activation+0.000
Top resid features:
isions
Tokenisions
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: 0.03

Head 4: 0.04

Head 5: 0.07

Head 6: 0.02

Head 7: 0.04

Head 8: 0.02

Head 9: 0.65

Head 10: 0.02

Head 11: 0.04

Positive logits

at4.32

At3.69

At3.66

at3.65

AT2.94

@2.49

@2.28

atography2.28

AT2.16

nat2.12

Antiqu2.05

の�2.00

��2.00

atical1.99

WHERE1.88

atan1.88

into1.86

Into1.86

TIT1.82

ats1.81

Negative logits

essel-1.84

joining-1.81

accompan-1.79

recol-1.77

joined-1.73

aunder-1.72

ugi-1.72

rue-1.71

essa-1.70

landslide-1.69

landsl-1.69

MSN-1.66

referrals-1.65

mentioned-1.65

undle-1.64

conversions-1.64

cooperating-1.62

married-1.59

inherit-1.58

defect-1.58

INTERVAL 6.762 - 7.513
CONTAINS 0.000%

it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
aimed
Token aimed
Feature activation+0.083
not
Token not
Feature activation+7.480
at
Token at
Feature activation+0.032
Latinos
Token Latinos
Feature activation+0.000
,
Token,
Feature activation+0.317
but
Token but
Feature activation+5.535
at
Token at
Feature activation+0.189
of
Token of
Feature activation+0.000
National
Token National
Feature activation+0.000
Focus
Token Focus
Feature activation+0.000
goals
Token goals
Feature activation+0.000
aimed
Token aimed
Feature activation+0.511
squarely
Token squarely
Feature activation+7.101
at
Token at
Feature activation+0.000
annoying
Token annoying
Feature activation+0.000
Great
Token Great
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
.
Token.
Feature activation+0.000
take
Token take
Feature activation+0.000
a
Token a
Feature activation+0.000
look
Token look
Feature activation+0.000
,
Token,
Feature activation+2.389
then
Token then
Feature activation+3.476
,
Token,
Feature activation+7.513
at
Token at
Feature activation+0.114
the
Token the
Feature activation+0.000
paternal
Token paternal
Feature activation+0.000
burden
Token burden
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000

INTERVAL 6.010 - 6.762
CONTAINS 0.000%

INTERVAL 5.259 - 6.010
CONTAINS 0.000%

aimed
Token aimed
Feature activation+0.083
not
Token not
Feature activation+7.480
at
Token at
Feature activation+0.032
Latinos
Token Latinos
Feature activation+0.000
,
Token,
Feature activation+0.317
but
Token but
Feature activation+5.535
at
Token at
Feature activation+0.189
stupid
Token stupid
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
and
Token and
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
stare
Token stare
Feature activation+0.055
long
Token long
Feature activation+0.818
enough
Token enough
Feature activation+5.282
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
find
Token find
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 4.508 - 5.259
CONTAINS 0.000%

I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
not
Token not
Feature activation+0.000
looking
Token looking
Feature activation+0.000
so
Token so
Feature activation+1.991
much
Token much
Feature activation+4.725
for
Token for
Feature activation+0.000
profiling
Token profiling
Feature activation+0.000
--
Token --
Feature activation+0.000
obvious
Token obvious
Feature activation+0.000
this
Token this
Feature activation+0.000
must
Token must
Feature activation+0.000
start
Token start
Feature activation+0.000
aiming
Token aiming
Feature activation+0.000
their
Token their
Feature activation+0.663
politics
Token politics
Feature activation+2.397
squarely
Token squarely
Feature activation+4.511
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
working
Token working
Feature activation+0.000
class
Token class
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
most
Token most
Feature activation+0.000
detailed
Token detailed
Feature activation+0.000
look
Token look
Feature activation+0.272
yet
Token yet
Feature activation+4.966
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
energy
Token energy
Feature activation+0.000
from
Token from
Feature activation+0.000
stellar
Token stellar
Feature activation+0.000

INTERVAL 3.757 - 4.508
CONTAINS 0.001%

,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
look
Token look
Feature activation+0.000
back
Token back
Feature activation+2.076
and
Token and
Feature activation+3.978
as
Token as
Feature activation+0.993
an
Token an
Feature activation+0.115
affirmation
Token affirmation
Feature activation+0.697
of
Token of
Feature activation+0.000
identity
Token identity
Feature activation+0.000
peek
Token peek
Feature activation+1.146
(
Token (
Feature activation+0.116
or
Tokenor
Feature activation+0.039
pe
Token pe
Feature activation+0.239
eks
Tokeneks
Feature activation+0.000
)
Token)
Feature activation+3.840
from
Token from
Feature activation+0.000
upcoming
Token upcoming
Feature activation+0.000
product
Token product
Feature activation+0.000
releases
Token releases
Feature activation+0.048
.
Token.
Feature activation+0.000
that
Token that
Feature activation+0.000
allow
Token allow
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
stare
Token stare
Feature activation+0.122
directly
Token directly
Feature activation+3.833
at
Token at
Feature activation+0.323
an
Token an
Feature activation+0.000
eclipse
Token eclipse
Feature activation+0.355
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
actor
Token actor
Feature activation+0.000
Charlie
Token Charlie
Feature activation+0.000
Sheen
Token Sheen
Feature activation+0.000
lashed
Token lashed
Feature activation+0.000
out
Token out
Feature activation+0.000
Monday
Token Monday
Feature activation+3.885
at
Token at
Feature activation+0.000
addiction
Token addiction
Feature activation+0.000
specialists
Token specialists
Feature activation+0.000
and
Token and
Feature activation+0.000
sitcom
Token sitcom
Feature activation+0.000
Gl
Token Gl
Feature activation+0.000
aston
Tokenaston
Feature activation+0.000
bury
Tokenbury
Feature activation+0.000
,
Token,
Feature activation+0.000
hint
Token hint
Feature activation+0.000
ing
Tokening
Feature activation+4.149
at
Token at
Feature activation+0.099
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
future
Token future
Feature activation+0.000
might
Token might
Feature activation+0.000

INTERVAL 3.005 - 3.757
CONTAINS 0.002%

Wall
Token Wall
Feature activation+0.000
.
Token.
Feature activation+0.000
Yet
Token Yet
Feature activation+0.000
to
Token to
Feature activation+0.000
look
Token look
Feature activation+0.000
only
Token only
Feature activation+3.597
at
Token at
Feature activation+0.000
these
Token these
Feature activation+0.000
headlines
Token headlines
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
Fl
TokenFl
Feature activation+0.000
ab
Tokenab
Feature activation+0.000
berg
Tokenberg
Feature activation+0.000
asted
Tokenasted
Feature activation+1.557
âĢ
TokenâĢ
Feature activation+2.303
Ļ
TokenĻ
Feature activation+3.320
By
Token By
Feature activation+0.000
Obama
Token Obama
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
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
looking
Token looking
Feature activation+0.000
closer
Token closer
Feature activation+3.435
to
Token to
Feature activation+0.000
D
Token D
Feature activation+0.000
une
Tokenune
Feature activation+0.490
!
Token!
Feature activation+1.385
with
Token with
Feature activation+0.000
people
Token people
Feature activation+0.000
were
Token were
Feature activation+0.000
in
Token in
Feature activation+0.000
attendance
Token attendance
Feature activation+0.457
that
Token that
Feature activation+0.000
day
Token day
Feature activation+3.012
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
drones
Token drones
Feature activation+0.000
returned
Token returned
Feature activation+0.000
for
Token for
Feature activation+0.000
we
Token we
Feature activation+0.000
normally
Token normally
Feature activation+0.000
turn
Token turn
Feature activation+0.000
our
Token our
Feature activation+0.000
noses
Token noses
Feature activation+0.000
up
Token up
Feature activation+3.475
at
Token at
Feature activation+0.000
smart
Token smart
Feature activation+0.000
telev
Token telev
Feature activation+0.000
isions
Tokenisions
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.254 - 3.005
CONTAINS 0.003%

and
Token and
Feature activation+0.000
h
Token h
Feature activation+0.000
url
Tokenurl
Feature activation+0.000
exp
Token exp
Feature activation+0.074
let
Tokenlet
Feature activation+1.260
ives
Tokenives
Feature activation+2.703
,
Token,
Feature activation+0.000
tried
Token tried
Feature activation+0.151
to
Token to
Feature activation+0.000
grab
Token grab
Feature activation+0.000
a
Token a
Feature activation+0.000
side
Token side
Feature activation+0.000
was
Token was
Feature activation+0.000
"
Token "
Feature activation+0.000
very
Tokenvery
Feature activation+0.000
angry
Token angry
Feature activation+0.000
"
Token"
Feature activation+2.574
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.061
Poland
Token Poland
Feature activation+0.000
behaved
Token behaved
Feature activation+0.000
"
Token "
Feature activation+0.000
a
Token a
Feature activation+0.000
look
Token look
Feature activation+0.552
in
Token in
Feature activation+0.317
Reno
Token Reno
Feature activation+1.045
,
Token,
Feature activation+0.063
Nevada
Token Nevada
Feature activation+2.759
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
only
Token only
Feature activation+0.000
five
Token five
Feature activation+0.000
when
Token when
Feature activation+0.000
you
Token you
Feature activation+0.000
do
Token do
Feature activation+0.000
and
Token and
Feature activation+0.000
look
Token look
Feature activation+0.000
back
Token back
Feature activation+2.771
,
Token,
Feature activation+0.663
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
all
Token all
Feature activation+0.000
worth
Token worth
Feature activation+0.000
Poké
Token Poké
Feature activation+0.000
balls
Tokenballs
Feature activation+1.932
out
Token out
Feature activation+0.018
left
Token left
Feature activation+0.283
and
Token and
Feature activation+0.000
right
Token right
Feature activation+2.634
,
Token,
Feature activation+0.000
pay
Token pay
Feature activation+0.000
attention
Token attention
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.503 - 2.254
CONTAINS 0.009%

a
Token a
Feature activation+0.000
search
Token search
Feature activation+0.000
warrant
Token warrant
Feature activation+0.435
on
Token on
Feature activation+0.000
December
Token December
Feature activation+0.000
15
Token 15
Feature activation+1.548
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Her
Token Her
Feature activation+0.000
r
Tokenr
Feature activation+0.000
mans
Tokenmans
Feature activation+0.000
ought
Token ought
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
look
Token look
Feature activation+0.165
around
Token around
Feature activation+1.506
his
Token his
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
office
Token office
Feature activation+1.132
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
sentence
Token sentence
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
first
Token first
Feature activation+0.000
look
Token look
Feature activation+0.000
was
Token was
Feature activation+2.049
one
Token one
Feature activation+0.151
of
Token of
Feature activation+0.000
pure
Token pure
Feature activation+0.321
disbelief
Token disbelief
Feature activation+0.352
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
more
Token more
Feature activation+0.000
pissed
Token pissed
Feature activation+0.000
all
Token all
Feature activation+0.411
the
Token the
Feature activation+0.067
time
Token time
Feature activation+1.583
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
;
Token;
Feature activation+0.000
too
Token too
Feature activation+0.000
proper
Token proper
Feature activation+0.466
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
bar
Token bar
Feature activation+2.122
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000

INTERVAL 0.751 - 1.503
CONTAINS 0.032%

earlier
Token earlier
Feature activation+0.000
estimates
Token estimates
Feature activation+0.000
that
Token that
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.809
of
Token of
Feature activation+0.000
school
Token school
Feature activation+0.000
children
Token children
Feature activation+0.121
who
Token who
Feature activation+0.000
died
Token died
Feature activation+0.000
Matrix
Token Matrix
Feature activation+0.000
as
Token as
Feature activation+0.000
reality
Token reality
Feature activation+0.000
is
Token is
Feature activation+0.000
scoff
Token scoff
Feature activation+0.000
ed
Tokened
Feature activation+1.102
at
Token at
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
illusion
Token illusion
Feature activation+0.000
becomes
Token becomes
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
governor
Token governor
Feature activation+0.000
brist
Token brist
Feature activation+0.000
led
Tokenled
Feature activation+0.000
in
Token in
Feature activation+0.000
response
Token response
Feature activation+0.963
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
question
Token question
Feature activation+0.000
about
Token about
Feature activation+0.000
early
Token early
Feature activation+0.000
some
Token some
Feature activation+0.000
700
Token 700
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
workers
Token workers
Feature activation+0.000
nationally
Token nationally
Feature activation+0.800
,
Token,
Feature activation+0.000
making
Token making
Feature activation+0.000
it
Token it
Feature activation+0.000
by
Token by
Feature activation+0.000
far
Token far
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
rooms
Token rooms
Feature activation+0.000
and
Token and
Feature activation+0.000
stare
Token stare
Feature activation+0.000
out
Token out
Feature activation+1.123
the
Token the
Feature activation+0.000
window
Token window
Feature activation+3.366
.
Token.
Feature activation+0.000
El
Token El
Feature activation+0.000
sie
Tokensie
Feature activation+0.000

INTERVAL 0.000 - 0.751
CONTAINS 99.952%

NCAA
Token NCAA
Feature activation+0.000
gymn
Token gymn
Feature activation+0.000
astics
Tokenastics
Feature activation+0.000
is
Token is
Feature activation+0.000
here
Token here
Feature activation+0.000
to
Token to
Feature activation+0.000
soar
Token soar
Feature activation+0.000
to
Token to
Feature activation+0.000
your
Token your
Feature activation+0.000
rescue
Token rescue
Feature activation+0.000
,
Token,
Feature activation+0.000
ec
Tokenec
Feature activation+0.000
il
Tokenil
Feature activation+0.000
's
Token's
Feature activation+0.000
playing
Token playing
Feature activation+0.000
days
Token days
Feature activation+0.000
were
Token were
Feature activation+0.000
before
Token before
Feature activation+0.000
my
Token my
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
child
Token child
Feature activation+0.000
matches
Token matches
Feature activation+0.000
the
Token the
Feature activation+0.000
t
Token t
Feature activation+0.000
eddy
Tokeneddy
Feature activation+0.000
bear
Token bear
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Use
TokenUse
Feature activation+0.000
Steam
Token Steam
Feature activation+0.000
neurological
Token neurological
Feature activation+0.000
disorders
Token disorders
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
clinical
Token clinical
Feature activation+0.000
setting
Token setting
Feature activation+0.000
and
Token and
Feature activation+0.000
trans
Token trans
Feature activation+0.000
pose
Tokenpose
Feature activation+0.000
those
Token those
Feature activation+0.000
into
Token into
Feature activation+0.000
shorts
Token shorts
Feature activation+0.000
veterans
Token veterans
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
wants
Token wants
Feature activation+0.000
a
Token a
Feature activation+0.000
programs
Token programs
Feature activation+0.000
so
Token so
Feature activation+0.000
restricted
Token restricted
Feature activation+0.000
by
Token by
Feature activation+0.000
tight
Token tight
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 H10.9: (feature 7931)

TOP ACTIVATIONS
MAX = 6.998

it
Token it
Feature activation+0.000
for
Token for
Feature activation+0.000
granted
Token granted
Feature activation+0.000
,
Token,
Feature activation+0.000
too
Token too
Feature activation+0.711
,
Token,
Feature activation+6.998
that
Token that
Feature activation+0.000
most
Token most
Feature activation+0.000
people
Token people
Feature activation+0.000
are
Token are
Feature activation+0.000
satisfied
Token satisfied
Feature activation+0.000
both
Token both
Feature activation+0.782
climate
Token climate
Feature activation+0.000
modeling
Token modeling
Feature activation+0.000
and
Token and
Feature activation+1.123
observation
Token observation
Feature activation+6.137
data
Token data
Feature activation+6.145
that
Token that
Feature activation+0.000
solar
Token solar
Feature activation+0.000
activity
Token activity
Feature activation+0.000
plays
Token plays
Feature activation+0.000
a
Token a
Feature activation+0.000
from
Token from
Feature activation+0.000
both
Token both
Feature activation+0.782
climate
Token climate
Feature activation+0.000
modeling
Token modeling
Feature activation+0.000
and
Token and
Feature activation+1.123
observation
Token observation
Feature activation+6.137
data
Token data
Feature activation+6.145
that
Token that
Feature activation+0.000
solar
Token solar
Feature activation+0.000
activity
Token activity
Feature activation+0.000
plays
Token plays
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+3.799
the
Token the
Feature activation+0.000
reviewer
Token reviewer
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
bitterly
Token bitterly
Feature activation+1.012
,
Token,
Feature activation+5.067
âĢ
Token âĢ
Feature activation+3.241
ľ
Tokenľ
Feature activation+4.081
that
Tokenthat
Feature activation+0.000
the
Token the
Feature activation+0.000
German
Token German
Feature activation+0.000
US
Token US
Feature activation+0.000
,
Token,
Feature activation+0.000
mindful
Token mindful
Feature activation+0.000
,
Token,
Feature activation+0.000
perhaps
Token perhaps
Feature activation+0.000
,
Token,
Feature activation+4.621
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Mormon
Token Mormon
Feature activation+0.000
community
Token community
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
and
Token and
Feature activation+0.180
one
Token one
Feature activation+0.000
chlor
Token chlor
Feature activation+0.000
op
Tokenop
Feature activation+0.000
last
Tokenlast
Feature activation+0.272
,
Token,
Feature activation+4.496
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
as
Token as
Feature activation+0.000
ative
Tokenative
Feature activation+0.000
years
Token years
Feature activation+0.171
as
Token as
Feature activation+0.164
a
Token a
Feature activation+0.000
budding
Token budding
Feature activation+0.000
Republican
Token Republican
Feature activation+4.350
operative
Token operative
Feature activation+4.342
that
Token that
Feature activation+0.000
Karl
Token Karl
Feature activation+0.000
Rove
Token Rove
Feature activation+0.000
learned
Token learned
Feature activation+0.000
years
Token years
Feature activation+0.171
as
Token as
Feature activation+0.164
a
Token a
Feature activation+0.000
budding
Token budding
Feature activation+0.000
Republican
Token Republican
Feature activation+4.350
operative
Token operative
Feature activation+4.342
that
Token that
Feature activation+0.000
Karl
Token Karl
Feature activation+0.000
Rove
Token Rove
Feature activation+0.000
learned
Token learned
Feature activation+0.000
the
Token the
Feature activation+0.000
supported
Token supported
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
medical
Token medical
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
,
Token,
Feature activation+4.146
that
Token that
Feature activation+0.000
her
Token her
Feature activation+0.000
death
Token death
Feature activation+0.000
may
Token may
Feature activation+0.000
have
Token have
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Studies
Token Studies
Feature activation+0.000
professors
Token professors
Feature activation+0.000
,
Token,
Feature activation+4.130
that
Token that
Feature activation+0.000
my
Token my
Feature activation+0.000
father
Token father
Feature activation+0.000
left
Token left
Feature activation+0.000
us
Token us
Feature activation+0.000
We
TokenWe
Feature activation+0.000
must
Token must
Feature activation+0.000
also
Token also
Feature activation+0.000
conclude
Token conclude
Feature activation+0.036
from
Token from
Feature activation+0.000
today
Token today
Feature activation+4.085
's
Token's
Feature activation+0.000
study
Token study
Feature activation+3.531
that
Token that
Feature activation+0.000
malaria
Token malaria
Feature activation+0.000
might
Token might
Feature activation+0.000
reviewer
Token reviewer
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
bitterly
Token bitterly
Feature activation+1.012
,
Token,
Feature activation+5.067
âĢ
Token âĢ
Feature activation+3.241
ľ
Tokenľ
Feature activation+4.081
that
Tokenthat
Feature activation+0.000
the
Token the
Feature activation+0.000
German
Token German
Feature activation+0.000
was
Token was
Feature activation+0.000
somehow
Token somehow
Feature activation+0.000
The
Token The
Feature activation+0.000
Congressional
Token Congressional
Feature activation+0.000
Budget
Token Budget
Feature activation+0.000
Office
Token Office
Feature activation+0.000
estimated
Token estimated
Feature activation+0.086
Wednesday
Token Wednesday
Feature activation+4.053
that
Token that
Feature activation+0.000
as
Token as
Feature activation+0.000
many
Token many
Feature activation+0.000
as
Token as
Feature activation+0.000
16
Token 16
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
been
Token been
Feature activation+0.000
pointed
Token pointed
Feature activation+0.000
out
Token out
Feature activation+0.000
before
Token before
Feature activation+4.046
that
Token that
Feature activation+0.000
printer
Token printer
Feature activation+0.000
ink
Token ink
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
realize
Token realize
Feature activation+0.000
now
Token now
Feature activation+4.028
,
Token,
Feature activation+0.559
after
Token after
Feature activation+0.000
analyzing
Token analyzing
Feature activation+0.000
my
Token my
Feature activation+0.000
childhood
Token childhood
Feature activation+0.000
on
Tokenon
Feature activation+0.000
also
Token also
Feature activation+0.000
noted
Token noted
Feature activation+0.751
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.259
,
Token,
Feature activation+4.023
that
Token that
Feature activation+0.592
L
Token L
Feature activation+0.000
NS
TokenNS
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
note
Token note
Feature activation+0.000
,
Token,
Feature activation+0.126
before
Token before
Feature activation+0.232
the
Token the
Feature activation+0.000
presentation
Token presentation
Feature activation+0.126
,
Token,
Feature activation+4.013
that
Token that
Feature activation+0.039
in
Token in
Feature activation+0.000
assembling
Token assembling
Feature activation+0.000
this
Token this
Feature activation+0.000
set
Token set
Feature activation+0.000
"
Token"
Feature activation+0.000
We
TokenWe
Feature activation+0.000
recognise
Token recognise
Feature activation+0.000
.
Token .
Feature activation+2.150
.
Token .
Feature activation+2.890
.
Token .
Feature activation+3.854
Israel
Token Israel
Feature activation+0.000
's
Token's
Feature activation+0.000
unique
Token unique
Feature activation+0.000
security
Token security
Feature activation+0.000
circumstances
Token circumstances
Feature activation+0.000
given
Token given
Feature activation+0.000
a
Token a
Feature activation+0.000
guarantee
Token guarantee
Feature activation+0.000
from
Token from
Feature activation+0.000
day
Token day
Feature activation+0.000
one
Token one
Feature activation+3.846
,
Token,
Feature activation+0.321
instead
Token instead
Feature activation+0.000
she
Token she
Feature activation+0.000
has
Token has
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
latest
Token latest
Feature activation+0.000
report
Token report
Feature activation+0.000
states
Token states
Feature activation+0.286
further
Token further
Feature activation+3.816
investigation
Token investigation
Feature activation+0.000
appears
Token appears
Feature activation+0.000
to
Token to
Feature activation+0.000
show
Token show
Feature activation+0.347
the
Token the
Feature activation+0.000

Top DFA by src position
MAX = 7.528

.
Token.
Feature activation-0.001
Top resid features:
He
Token He
Feature activation+0.017
Top resid features:
takes
Token takes
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.154
Top resid features:
for
Token for
Feature activation+0.013
Top resid features:
granted
Token granted
Feature activation+7.528
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
too
Token too
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
âĢ¦
Token âĢ¦
Feature activation+0.015
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
has
Token has
Feature activation-0.004
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
widely
Token widely
Feature activation+0.007
Top resid features:
suggested
Token suggested
Feature activation+6.711
Top resid features:
from
Token from
Feature activation+0.021
Top resid features:
both
Token both
Feature activation+0.010
Top resid features:
climate
Token climate
Feature activation+0.002
Top resid features:
modeling
Token modeling
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
âĢ¦
Token âĢ¦
Feature activation+0.017
Top resid features:
It
Token It
Feature activation-0.001
Top resid features:
has
Token has
Feature activation-0.006
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
widely
Token widely
Feature activation+0.008
Top resid features:
suggested
Token suggested
Feature activation+6.686
Top resid features:
from
Token from
Feature activation+0.044
Top resid features:
both
Token both
Feature activation+0.029
Top resid features:
climate
Token climate
Feature activation+0.003
Top resid features:
modeling
Token modeling
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
One
TokenOne
Feature activation-0.005
Top resid features:
begins
Token begins
Feature activation-0.060
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
get
Token get
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
impression
Token impression
Feature activation+5.878
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
âĢ
TokenâĢ
Feature activation-0.105
Top resid features:
Ŀ
TokenĿ
Feature activation+0.010
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
reviewer
Token reviewer
Feature activation+0.000
Top resid features:
travel
Token travel
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
US
Token US
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
mindful
Token mindful
Feature activation+5.222
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
perhaps
Token perhaps
Feature activation+0.078
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
transcription
Token transcription
Feature activation-0.003
Top resid features:
al
Tokenal
Feature activation-0.001
Top resid features:
noise
Token noise
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
We
Token We
Feature activation+0.031
Top resid features:
show
Token show
Feature activation+5.101
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
by
Token by
Feature activation+0.010
Top resid features:
comparative
Token comparative
Feature activation-0.003
Top resid features:
transcript
Token transcript
Feature activation-0.000
Top resid features:
omics
Tokenomics
Feature activation-0.002
Top resid features:
was
Token was
Feature activation+0.031
Top resid features:
during
Token during
Feature activation+0.029
Top resid features:
these
Token these
Feature activation+0.004
Top resid features:
form
Token form
Feature activation+0.008
Top resid features:
ative
Tokenative
Feature activation+0.007
Top resid features:
years
Token years
Feature activation+4.948
Top resid features:
as
Token as
Feature activation+0.042
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
budding
Token budding
Feature activation-0.042
Top resid features:
Republican
Token Republican
Feature activation+0.019
Top resid features:
operative
Token operative
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.033
Top resid features:
during
Token during
Feature activation+0.025
Top resid features:
these
Token these
Feature activation+0.035
Top resid features:
form
Token form
Feature activation+0.022
Top resid features:
ative
Tokenative
Feature activation+0.006
Top resid features:
years
Token years
Feature activation+4.708
Top resid features:
as
Token as
Feature activation+0.035
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
budding
Token budding
Feature activation+0.005
Top resid features:
Republican
Token Republican
Feature activation+0.019
Top resid features:
operative
Token operative
Feature activation+0.141
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
"
Token"
Feature activation-0.002
Top resid features:
It
TokenIt
Feature activation+0.010
Top resid features:
is
Token is
Feature activation-0.002
Top resid features:
our
Token our
Feature activation+0.007
Top resid features:
belief
Token belief
Feature activation+4.788
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
supported
Token supported
Feature activation+0.006
Top resid features:
by
Token by
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
medical
Token medical
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
I
Token I
Feature activation+0.001
Top resid features:
have
Token have
Feature activation-0.002
Top resid features:
come
Token come
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
realize
Token realize
Feature activation+4.330
Top resid features:
now
Token now
Feature activation+0.414
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
after
Token after
Feature activation-0.005
Top resid features:
analyzing
Token analyzing
Feature activation+0.020
Top resid features:
my
Token my
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
We
TokenWe
Feature activation+0.005
Top resid features:
must
Token must
Feature activation+0.008
Top resid features:
also
Token also
Feature activation+0.010
Top resid features:
conclude
Token conclude
Feature activation+4.535
Top resid features:
from
Token from
Feature activation+0.067
Top resid features:
today
Token today
Feature activation+0.069
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
study
Token study
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
One
TokenOne
Feature activation-0.002
Top resid features:
begins
Token begins
Feature activation-0.134
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
get
Token get
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
impression
Token impression
Feature activation+4.767
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
âĢ
TokenâĢ
Feature activation-0.037
Top resid features:
Ŀ
TokenĿ
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
reviewer
Token reviewer
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
The
Token The
Feature activation-0.004
Top resid features:
Congressional
Token Congressional
Feature activation+0.003
Top resid features:
Budget
Token Budget
Feature activation+0.007
Top resid features:
Office
Token Office
Feature activation+0.044
Top resid features:
estimated
Token estimated
Feature activation+4.789
Top resid features:
Wednesday
Token Wednesday
Feature activation-0.083
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
many
Token many
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.043
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.007
Top resid features:
been
Token been
Feature activation+0.023
Top resid features:
pointed
Token pointed
Feature activation+0.072
Top resid features:
out
Token out
Feature activation+4.656
Top resid features:
before
Token before
Feature activation+0.051
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
printer
Token printer
Feature activation+0.000
Top resid features:
ink
Token ink
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
I
Token I
Feature activation+0.010
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
come
Token come
Feature activation+0.009
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
realize
Token realize
Feature activation+4.488
Top resid features:
now
Token now
Feature activation+0.178
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
after
Token after
Feature activation+0.000
Top resid features:
analyzing
Token analyzing
Feature activation+0.000
Top resid features:
my
Token my
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
E
TokenE
Feature activation-0.000
Top resid features:
ricks
Tokenricks
Feature activation-0.005
Top resid features:
on
Tokenon
Feature activation+0.004
Top resid features:
also
Token also
Feature activation+0.004
Top resid features:
noted
Token noted
Feature activation+4.478
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
however
Token however
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
L
Token L
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
I
TokenI
Feature activation+0.005
Top resid features:
wish
Token wish
Feature activation+0.494
Top resid features:
to
Token to
Feature activation+0.018
Top resid features:
note
Token note
Feature activation+4.082
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
before
Token before
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
presentation
Token presentation
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
"
Token"
Feature activation+0.053
Top resid features:
We
TokenWe
Feature activation+0.011
Top resid features:
recognise
Token recognise
Feature activation+4.211
Top resid features:
.
Token .
Feature activation+0.035
Top resid features:
.
Token .
Feature activation+0.019
Top resid features:
.
Token .
Feature activation+0.169
Top resid features:
Israel
Token Israel
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.001
Top resid features:
could
Token could
Feature activation+0.003
Top resid features:
have
Token have
Feature activation-0.027
Top resid features:
given
Token given
Feature activation+0.005
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
guarantee
Token guarantee
Feature activation+4.392
Top resid features:
from
Token from
Feature activation+0.010
Top resid features:
day
Token day
Feature activation+0.016
Top resid features:
one
Token one
Feature activation-0.007
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
instead
Token instead
Feature activation+0.000
Top resid features:
Further
TokenFurther
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
latest
Token latest
Feature activation-0.005
Top resid features:
report
Token report
Feature activation+0.016
Top resid features:
states
Token states
Feature activation+4.373
Top resid features:
further
Token further
Feature activation+0.066
Top resid features:
investigation
Token investigation
Feature activation+0.000
Top resid features:
appears
Token appears
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
show
Token show
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.03

Head 3: 0.03

Head 4: 0.04

Head 5: 0.09

Head 6: 0.02

Head 7: 0.03

Head 8: 0.02

Head 9: 0.64

Head 10: 0.02

Head 11: 0.04

Positive logits

that4.27

that3.89

THAT3.18

That3.03

That3.00

thats1.97

dat1.80

those1.79

tha1.63

they1.62

Dems1.55

ITNESS1.55

Reader1.54

else1.53

Lauder1.51

clos1.51

Those1.49

]:1.49

*:1.44

:]1.42

Negative logits

ilan-2.41

estyles-2.26

ivated-2.11

ciating-1.94

pire-1.92

raits-1.90

ois-1.82

inguished-1.81

ograp-1.80

outed-1.79

arte-1.79

pee-1.79

izo-1.77

figure-1.77

semble-1.76

accompanied-1.71

Untitled-1.71

oland-1.70

wordpress-1.70

peg-1.67

INTERVAL 6.298 - 6.998
CONTAINS 0.000%

it
Token it
Feature activation+0.000
for
Token for
Feature activation+0.000
granted
Token granted
Feature activation+0.000
,
Token,
Feature activation+0.000
too
Token too
Feature activation+0.711
,
Token,
Feature activation+6.998
that
Token that
Feature activation+0.000
most
Token most
Feature activation+0.000
people
Token people
Feature activation+0.000
are
Token are
Feature activation+0.000
satisfied
Token satisfied
Feature activation+0.000

INTERVAL 5.598 - 6.298
CONTAINS 0.000%

from
Token from
Feature activation+0.000
both
Token both
Feature activation+0.782
climate
Token climate
Feature activation+0.000
modeling
Token modeling
Feature activation+0.000
and
Token and
Feature activation+1.123
observation
Token observation
Feature activation+6.137
data
Token data
Feature activation+6.145
that
Token that
Feature activation+0.000
solar
Token solar
Feature activation+0.000
activity
Token activity
Feature activation+0.000
plays
Token plays
Feature activation+0.000
both
Token both
Feature activation+0.782
climate
Token climate
Feature activation+0.000
modeling
Token modeling
Feature activation+0.000
and
Token and
Feature activation+1.123
observation
Token observation
Feature activation+6.137
data
Token data
Feature activation+6.145
that
Token that
Feature activation+0.000
solar
Token solar
Feature activation+0.000
activity
Token activity
Feature activation+0.000
plays
Token plays
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 4.898 - 5.598
CONTAINS 0.000%

Ŀ
TokenĿ
Feature activation+3.799
the
Token the
Feature activation+0.000
reviewer
Token reviewer
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
bitterly
Token bitterly
Feature activation+1.012
,
Token,
Feature activation+5.067
âĢ
Token âĢ
Feature activation+3.241
ľ
Tokenľ
Feature activation+4.081
that
Tokenthat
Feature activation+0.000
the
Token the
Feature activation+0.000
German
Token German
Feature activation+0.000

INTERVAL 4.199 - 4.898
CONTAINS 0.000%

ative
Tokenative
Feature activation+0.000
years
Token years
Feature activation+0.171
as
Token as
Feature activation+0.164
a
Token a
Feature activation+0.000
budding
Token budding
Feature activation+0.000
Republican
Token Republican
Feature activation+4.350
operative
Token operative
Feature activation+4.342
that
Token that
Feature activation+0.000
Karl
Token Karl
Feature activation+0.000
Rove
Token Rove
Feature activation+0.000
learned
Token learned
Feature activation+0.000
years
Token years
Feature activation+0.171
as
Token as
Feature activation+0.164
a
Token a
Feature activation+0.000
budding
Token budding
Feature activation+0.000
Republican
Token Republican
Feature activation+4.350
operative
Token operative
Feature activation+4.342
that
Token that
Feature activation+0.000
Karl
Token Karl
Feature activation+0.000
Rove
Token Rove
Feature activation+0.000
learned
Token learned
Feature activation+0.000
the
Token the
Feature activation+0.000
and
Token and
Feature activation+0.180
one
Token one
Feature activation+0.000
chlor
Token chlor
Feature activation+0.000
op
Tokenop
Feature activation+0.000
last
Tokenlast
Feature activation+0.272
,
Token,
Feature activation+4.496
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
as
Token as
Feature activation+0.000
US
Token US
Feature activation+0.000
,
Token,
Feature activation+0.000
mindful
Token mindful
Feature activation+0.000
,
Token,
Feature activation+0.000
perhaps
Token perhaps
Feature activation+0.000
,
Token,
Feature activation+4.621
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Mormon
Token Mormon
Feature activation+0.000
community
Token community
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 3.499 - 4.199
CONTAINS 0.002%

"
Token"
Feature activation+0.000
We
TokenWe
Feature activation+0.000
recognise
Token recognise
Feature activation+0.000
.
Token .
Feature activation+2.150
.
Token .
Feature activation+2.890
.
Token .
Feature activation+3.854
Israel
Token Israel
Feature activation+0.000
's
Token's
Feature activation+0.000
unique
Token unique
Feature activation+0.000
security
Token security
Feature activation+0.000
circumstances
Token circumstances
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
realize
Token realize
Feature activation+0.000
now
Token now
Feature activation+4.028
,
Token,
Feature activation+0.559
after
Token after
Feature activation+0.000
analyzing
Token analyzing
Feature activation+0.000
my
Token my
Feature activation+0.000
childhood
Token childhood
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
latest
Token latest
Feature activation+0.000
report
Token report
Feature activation+0.000
states
Token states
Feature activation+0.286
further
Token further
Feature activation+3.816
investigation
Token investigation
Feature activation+0.000
appears
Token appears
Feature activation+0.000
to
Token to
Feature activation+0.000
show
Token show
Feature activation+0.347
the
Token the
Feature activation+0.000
supported
Token supported
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
medical
Token medical
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
,
Token,
Feature activation+4.146
that
Token that
Feature activation+0.000
her
Token her
Feature activation+0.000
death
Token death
Feature activation+0.000
may
Token may
Feature activation+0.000
have
Token have
Feature activation+0.000
ites
Tokenites
Feature activation+0.000
,
Token,
Feature activation+0.000
despite
Token despite
Feature activation+0.000
clearly
Token clearly
Feature activation+0.201
stating
Token stating
Feature activation+0.000
elsewhere
Token elsewhere
Feature activation+3.523
that
Token that
Feature activation+0.023
none
Token none
Feature activation+0.000
of
Token of
Feature activation+0.000
Noah
Token Noah
Feature activation+0.000
's
Token's
Feature activation+0.000

INTERVAL 2.799 - 3.499
CONTAINS 0.007%

of
Token of
Feature activation+0.000
Turk
Token Turk
Feature activation+0.000
u
Tokenu
Feature activation+0.000
,
Token,
Feature activation+0.000
estimated
Token estimated
Feature activation+0.000
similarly
Token similarly
Feature activation+3.352
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
decision
Token decision
Feature activation+0.000
is
Token is
Feature activation+0.000
testament
Token testament
Feature activation+0.000
a
Token a
Feature activation+0.000
tip
Token tip
Feature activation+0.000
-
Token-
Feature activation+0.732
off
Tokenoff
Feature activation+0.500
in
Token in
Feature activation+0.000
Glasgow
Token Glasgow
Feature activation+3.028
about
Token about
Feature activation+0.000
a
Token a
Feature activation+0.000
woman
Token woman
Feature activation+0.000
called
Token called
Feature activation+0.000
Fiona
Token Fiona
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
time
Token time
Feature activation+0.319
in
Token in
Feature activation+0.000
five
Token five
Feature activation+0.189
years
Token years
Feature activation+2.917
of
Token of
Feature activation+0.100
writing
Token writing
Feature activation+2.146
for
Token for
Feature activation+0.199
the
Token the
Feature activation+0.000
site
Token site
Feature activation+3.329
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
believe
Token believe
Feature activation+0.000
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
do
Token do
Feature activation+3.111
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
some
Token some
Feature activation+0.000
value
Token value
Feature activation+0.000
so
Token so
Feature activation+0.000
powerful
Token powerful
Feature activation+0.447
during
Token during
Feature activation+0.000
re
Token re
Feature activation+0.010
-
Token-
Feature activation+0.000
entry
Tokenentry
Feature activation+3.389
that
Token that
Feature activation+0.773
the
Token the
Feature activation+0.000
heat
Token heat
Feature activation+0.000
is
Token is
Feature activation+0.000
enough
Token enough
Feature activation+0.000

INTERVAL 2.099 - 2.799
CONTAINS 0.015%

he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
"
Token "
Feature activation+0.000
thank
Tokenthank
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
"
Token"
Feature activation+2.212
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
experience
Token experience
Feature activation+0.000
afforded
Token afforded
Feature activation+0.000
him
Token him
Feature activation+0.000
art
Tokenart
Feature activation+0.000
is
Tokenis
Feature activation+0.000
had
Token had
Feature activation+0.000
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
September
Token September
Feature activation+2.527
that
Token that
Feature activation+0.164
Zy
Token Zy
Feature activation+0.000
k
Tokenk
Feature activation+0.000
adia
Tokenadia
Feature activation+0.000
had
Token had
Feature activation+0.000
2017
Token2017
Feature activation+0.000
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
found
Token found
Feature activation+0.000
out
Token out
Feature activation+0.305
recently
Token recently
Feature activation+2.751
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
F
Token F
Feature activation+0.000
23
Token23
Feature activation+0.000
.
Token.
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
These
TokenThese
Feature activation+0.000
permits
Token permits
Feature activation+0.000
suggest
Token suggest
Feature activation+0.000
very
Token very
Feature activation+0.454
strongly
Token strongly
Feature activation+2.751
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
these
Token these
Feature activation+0.000
ancouver
Tokenancouver
Feature activation+0.000
White
Token White
Feature activation+0.000
caps
Tokencaps
Feature activation+0.000
FC
Token FC
Feature activation+0.000
announced
Token announced
Feature activation+0.000
today
Token today
Feature activation+2.345
the
Token the
Feature activation+0.454
acquisition
Token acquisition
Feature activation+0.000
of
Token of
Feature activation+0.104
Malt
Token Malt
Feature activation+0.000
ese
Tokenese
Feature activation+0.000

INTERVAL 1.400 - 2.099
CONTAINS 0.032%

occurred
Token occurred
Feature activation+0.000
to
Token to
Feature activation+0.548
me
Token me
Feature activation+0.916
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.774
said
Token said
Feature activation+0.000
Kat
Token Kat
Feature activation+0.000
bi
Tokenbi
Feature activation+0.000
.
Token.
Feature activation+0.897
âĢ
Token âĢ
Feature activation+0.000
reminders
Token reminders
Feature activation+0.000
from
Token from
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
time
Token time
Feature activation+1.768
"
Token"
Feature activation+1.722
of
Token of
Feature activation+0.000
racism
Token racism
Feature activation+0.013
when
Token when
Feature activation+0.000
they
Token they
Feature activation+0.000
go
Token go
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
with
Token with
Feature activation+0.000
100
Token 100
Feature activation+0.000
%
Token%
Feature activation+0.000
certainty
Token certainty
Feature activation+0.079
âĢĶ
Token âĢĶ
Feature activation+1.737
that
Token that
Feature activation+0.000
she
Token she
Feature activation+0.000
would
Token would
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
on
Token on
Feature activation+0.000
real
Token real
Feature activation+0.236
argument
Token argument
Feature activation+0.021
,
Token,
Feature activation+1.879
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
made
Token made
Feature activation+1.729
that
Token that
Feature activation+0.386
the
Token the
Feature activation+0.000
budget
Token budget
Feature activation+0.000
must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.000
Committee
Token Committee
Feature activation+0.245
in
Token in
Feature activation+0.024
testimony
Token testimony
Feature activation+0.738
earlier
Token earlier
Feature activation+0.000
this
Token this
Feature activation+0.000
month
Token month
Feature activation+1.844
that
Token that
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
never
Token never
Feature activation+0.000
asked
Token asked
Feature activation+0.000
him
Token him
Feature activation+0.000

INTERVAL 0.700 - 1.400
CONTAINS 0.103%

is
Token is
Feature activation+0.259
,
Token,
Feature activation+0.696
with
Token with
Feature activation+0.000
surprising
Token surprising
Feature activation+0.000
frequency
Token frequency
Feature activation+0.863
,
Token,
Feature activation+1.324
the
Token the
Feature activation+0.000
attacker
Token attacker
Feature activation+0.000
is
Token is
Feature activation+0.000
someone
Token someone
Feature activation+0.000
who
Token who
Feature activation+0.000
old
Tokenold
Feature activation+0.000
showed
Token showed
Feature activation+0.000
the
Token the
Feature activation+0.000
full
Token full
Feature activation+0.000
extent
Token extent
Feature activation+0.000
of
Token of
Feature activation+0.883
his
Token his
Feature activation+0.000
abilities
Token abilities
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.000
stopped
Token stopped
Feature activation+0.000
Abbott
Token Abbott
Feature activation+0.000
issues
Token issues
Feature activation+0.000
the
Token the
Feature activation+0.000
warning
Token warning
Feature activation+0.000
on
Token on
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.775
morning
Token morning
Feature activation+0.725
.
Token.
Feature activation+0.000
Credit
Token Credit
Feature activation+0.000
:
Token:
Feature activation+0.000
Alex
TokenAlex
Feature activation+0.000
offic
Tokenoffic
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
were
Token were
Feature activation+0.000
informed
Token informed
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.461
Ŀ
TokenĿ
Feature activation+0.959
of
Token of
Feature activation+0.000
St
Token St
Feature activation+0.000
umbo
Tokenumbo
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Intelligence
Token Intelligence
Feature activation+0.000
Community
Token Community
Feature activation+0.665
(
Token (
Feature activation+0.000
IC
TokenIC
Feature activation+0.000
)
Token)
Feature activation+0.730
agencies
Token agencies
Feature activation+0.994
indicating
Token indicating
Feature activation+0.094
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
developed
Token developed
Feature activation+0.000

INTERVAL 0.000 - 0.700
CONTAINS 99.841%

found
Token found
Feature activation+0.000
in
Token in
Feature activation+0.060
2014
Token 2014
Feature activation+3.389
that
Token that
Feature activation+0.000
Philadelphia
Token Philadelphia
Feature activation+0.000
is
Token is
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
"
Token "
Feature activation+0.000
re
Tokenre
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
dark
Token dark
Feature activation+0.000
navy
Token navy
Feature activation+0.000
suit
Token suit
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
79
Token 79
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
was
Token was
Feature activation+0.000
just
Token just
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Orange
Token Orange
Feature activation+0.000
Bowl
Token Bowl
Feature activation+0.000
and
Token and
Feature activation+0.000
playing
Token playing
Feature activation+0.000
in
Token in
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
for
Token for
Feature activation+0.000
additional
Token additional
Feature activation+0.000
details
Token details
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Please
TokenPlease
Feature activation+0.000
highlight
Token highlight
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
terrible
Token terrible
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
run
Token run
Feature activation+0.000
an
Token an
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
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
Organisation
Token Organisation
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
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
.
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
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
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.360
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.045
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+0.360
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.045
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.360
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.045
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
Saturday
Token Saturday
Feature activation+0.360
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.045
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
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
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
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
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
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
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
.
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
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
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
Ċ
TokenĊ
Feature activation+0.045
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
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.045
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+0.045
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