H11.5 top features

Top feature 0 in H11.5: (feature 1307)

TOP ACTIVATIONS
MAX = 7.725

chicken
Token chicken
Feature activation+0.000
.
Token.
Feature activation+0.145
(
Token (
Feature activation+1.052
Photo
TokenPhoto
Feature activation+0.000
11
Token11
Feature activation+0.000
:
Token:
Feature activation+7.725
Has
Token Has
Feature activation+0.000
bro
Tokenbro
Feature activation+0.000
)
Token)
Feature activation+0.117
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.515
define
Token define
Feature activation+0.000
(
Token (
Feature activation+0.000
has
Token has
Feature activation+0.067
-
Token-
Feature activation+1.305
sym
Tokensym
Feature activation+4.512
?
Token?
Feature activation+6.126
l
Token l
Feature activation+1.585
st
Tokenst
Feature activation+2.891
s
Token s
Feature activation+0.000
)
Token )
Feature activation+3.413
(
Token (
Feature activation+2.398
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
W
TokenW
Feature activation+0.000
aters
Tokenaters
Feature activation+0.000
:
Token:
Feature activation+0.000
Everybody
Token Everybody
Feature activation+6.097
has
Token has
Feature activation+0.417
a
Token a
Feature activation+0.000
mother
Token mother
Feature activation+0.000
not
Token not
Feature activation+0.000
quite
Token quite
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
playing
Token playing
Feature activation+0.000
but
Token but
Feature activation+0.075
they
Token they
Feature activation+5.885
have
Token have
Feature activation+2.614
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
given
Token given
Feature activation+0.000
psychological
Token psychological
Feature activation+0.000
guarding
Token guarding
Feature activation+0.000
position
Token position
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
offensive
Token offensive
Feature activation+0.000
player
Token player
Feature activation+5.817
has
Token has
Feature activation+1.601
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.000
in
Token in
Feature activation+0.000
control
Token control
Feature activation+0.000
training
Token training
Feature activation+0.000
,
Token,
Feature activation+0.000
workers
Token workers
Feature activation+5.402
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
ground
Token ground
Feature activation+5.446
had
Token had
Feature activation+3.315
to
Token to
Feature activation+0.000
ensure
Token ensure
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
of
Token of
Feature activation+0.000
hours
Token hours
Feature activation+0.000
of
Token of
Feature activation+0.000
training
Token training
Feature activation+0.000
,
Token,
Feature activation+0.000
workers
Token workers
Feature activation+5.402
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
ground
Token ground
Feature activation+5.446
had
Token had
Feature activation+3.315
to
Token to
Feature activation+0.000
Tok
TokenTok
Feature activation+0.000
iw
Tokeniw
Feature activation+0.000
ak
Tokenak
Feature activation+0.000
ita
Tokenita
Feature activation+0.000
(
Token (
Feature activation+0.000
Time
TokenTime
Feature activation+5.187
Has
Token Has
Feature activation+1.030
Come
Token Come
Feature activation+0.000
)"
Token)"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.062
More
TokenMore
Feature activation+0.000
than
Token than
Feature activation+0.000
once
Token once
Feature activation+0.506
I
Token I
Feature activation+4.930
have
Token have
Feature activation+0.189
helped
Token helped
Feature activation+0.000
push
Token push
Feature activation+0.000
a
Token a
Feature activation+0.000
stranger
Token stranger
Feature activation+0.000
humans
Token humans
Feature activation+0.320
have
Token have
Feature activation+0.000
23
Token 23
Feature activation+0.000
pairs
Token pairs
Feature activation+0.000
and
Token and
Feature activation+0.000
apes
Token apes
Feature activation+4.920
have
Token have
Feature activation+0.000
24
Token 24
Feature activation+0.000
pairs
Token pairs
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
beard
Token beard
Feature activation+0.000
,
Token,
Feature activation+0.000
my
Token my
Feature activation+0.000
father
Token father
Feature activation+4.779
and
Token and
Feature activation+0.000
grandfather
Token grandfather
Feature activation+3.817
all
Token all
Feature activation+1.849
had
Token had
Feature activation+0.000
be
Token be
Feature activation+0.000
quite
Token quite
Feature activation+0.000
like
Token like
Feature activation+0.000
this
Token this
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
everybody
Token everybody
Feature activation+4.689
has
Token has
Feature activation+0.610
a
Token a
Feature activation+0.000
mother
Token mother
Feature activation+0.000
who
Token who
Feature activation+0.998
has
Token has
Feature activation+0.000
(
Token(
Feature activation+0.000
define
Token define
Feature activation+0.000
(
Token (
Feature activation+0.000
has
Token has
Feature activation+0.067
-
Token-
Feature activation+1.305
sym
Tokensym
Feature activation+4.512
?
Token?
Feature activation+6.126
l
Token l
Feature activation+1.585
st
Tokenst
Feature activation+2.891
s
Token s
Feature activation+0.000
)
Token )
Feature activation+3.413
seen
Token seen
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+4.481
have
Token have
Feature activation+1.735
should
Token should
Feature activation+0.000
know
Token know
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
what
Token what
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
rules
Token rules
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
defender
Token defender
Feature activation+4.310
stip
Token stip
Feature activation+0.000
ulate
Tokenulate
Feature activation+0.000
specifically
Token specifically
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.269
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Blessed
Token Blessed
Feature activation+0.000
Virgin
Token Virgin
Feature activation+0.797
Mary
Token Mary
Feature activation+3.074
Parish
Token Parish
Feature activation+4.282
at
Token at
Feature activation+0.000
219
Token 219
Feature activation+0.000
W
Token W
Feature activation+0.000
.
Token.
Feature activation+0.000
Magn
Token Magn
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
drib
Token drib
Feature activation+0.000
bler
Tokenbler
Feature activation+4.171
has
Token has
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
right
Token right
Feature activation+0.000
to
Token to
Feature activation+0.000
of
Token of
Feature activation+0.640
a
Token a
Feature activation+0.000
dementia
Token dementia
Feature activation+0.000
diagnosis
Token diagnosis
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+4.095
having
Token having
Feature activation+3.458
just
Token just
Feature activation+1.701
an
Token an
Feature activation+0.337
anxiety
Token anxiety
Feature activation+0.000
diagnosis
Token diagnosis
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
controversial
Token controversial
Feature activation+0.000
topic
Token topic
Feature activation+0.000
in
Token in
Feature activation+4.069
some
Token some
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
societies
Token societies
Feature activation+0.000
,
Token,
Feature activation+1.464
these
Token these
Feature activation+0.000
fl
Token fl
Feature activation+0.000
aky
Tokenaky
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
't
Token't
Feature activation+3.909
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
stiff
Token stiff
Feature activation+0.000
and
Token and
Feature activation+0.000

Top DFA by src position
MAX = 9.021

.
Token.
Feature activation+0.043
Top resid features:
(
Token (
Feature activation+0.045
Top resid features:
Photo
TokenPhoto
Feature activation+0.024
Top resid features:
11
Token11
Feature activation+0.009
Top resid features:
:
Token:
Feature activation+0.017
Top resid features:
Has
Token Has
Feature activation+9.021
Top resid features:
bro
Tokenbro
Feature activation+0.071
Top resid features:
)
Token)
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Shadow
TokenShadow
Feature activation+0.180
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
(
Token(
Feature activation+0.001
Top resid features:
define
Token define
Feature activation-0.106
Top resid features:
(
Token (
Feature activation-0.006
Top resid features:
has
Token has
Feature activation+7.923
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
sym
Tokensym
Feature activation+0.010
Top resid features:
?
Token?
Feature activation-0.063
Top resid features:
l
Token l
Feature activation+0.000
Top resid features:
st
Tokenst
Feature activation+0.000
Top resid features:
aste
Tokenaste
Feature activation-0.014
Top resid features:
:
Token:
Feature activation+0.038
Top resid features:
Now
Token Now
Feature activation+0.020
Top resid features:
if
Token if
Feature activation+0.012
Top resid features:
everybody
Token everybody
Feature activation+0.021
Top resid features:
has
Token has
Feature activation+7.171
Top resid features:
a
Token a
Feature activation+0.077
Top resid features:
mother
Token mother
Feature activation+0.016
Top resid features:
like
Token like
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.105
Top resid features:
Serial
Token Serial
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
"
Token"
Feature activation+0.033
Top resid features:
They
TokenThey
Feature activation+0.026
Top resid features:
not
Token not
Feature activation-0.008
Top resid features:
only
Token only
Feature activation+0.012
Top resid features:
have
Token have
Feature activation+7.297
Top resid features:
to
Token to
Feature activation+0.019
Top resid features:
keep
Token keep
Feature activation+0.009
Top resid features:
playing
Token playing
Feature activation+0.032
Top resid features:
but
Token but
Feature activation+0.048
Top resid features:
they
Token they
Feature activation+0.031
Top resid features:
illegal
Token illegal
Feature activation+0.007
Top resid features:
contact
Token contact
Feature activation-0.031
Top resid features:
.
Token.
Feature activation+0.061
Top resid features:
The
Token The
Feature activation+0.045
Top resid features:
defender
Token defender
Feature activation+0.021
Top resid features:
has
Token has
Feature activation+7.212
Top resid features:
to
Token to
Feature activation+0.035
Top resid features:
establish
Token establish
Feature activation+0.040
Top resid features:
legal
Token legal
Feature activation+0.010
Top resid features:
guarding
Token guarding
Feature activation-0.027
Top resid features:
position
Token position
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
perfect
Token perfect
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
A
Token A
Feature activation-0.002
Top resid features:
crew
Token crew
Feature activation+0.007
Top resid features:
had
Token had
Feature activation+4.801
Top resid features:
to
Token to
Feature activation+0.043
Top resid features:
go
Token go
Feature activation+0.002
Top resid features:
through
Token through
Feature activation-0.005
Top resid features:
collective
Token collective
Feature activation-0.008
Top resid features:
thousands
Token thousands
Feature activation-0.005
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
perfect
Token perfect
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
A
Token A
Feature activation+0.004
Top resid features:
crew
Token crew
Feature activation-0.000
Top resid features:
had
Token had
Feature activation+4.517
Top resid features:
to
Token to
Feature activation+0.054
Top resid features:
go
Token go
Feature activation-0.002
Top resid features:
through
Token through
Feature activation-0.010
Top resid features:
collective
Token collective
Feature activation-0.013
Top resid features:
thousands
Token thousands
Feature activation-0.005
Top resid features:
iw
Tokeniw
Feature activation-0.010
Top resid features:
ak
Tokenak
Feature activation+0.006
Top resid features:
ita
Tokenita
Feature activation+0.008
Top resid features:
(
Token (
Feature activation+0.043
Top resid features:
Time
TokenTime
Feature activation+0.010
Top resid features:
Has
Token Has
Feature activation+5.824
Top resid features:
Come
Token Come
Feature activation+0.852
Top resid features:
)"
Token)"
Feature activation+0.001
Top resid features:
âĸº
Token âĸº
Feature activation+0.013
Top resid features:
H
Token H
Feature activation-0.009
Top resid features:
ideo
Tokenideo
Feature activation+0.006
Top resid features:
Very
TokenVery
Feature activation+0.002
Top resid features:
Often
Token Often
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
I
TokenI
Feature activation+0.003
Top resid features:
have
Token have
Feature activation+1.430
Top resid features:
helped
Token helped
Feature activation+0.025
Top resid features:
push
Token push
Feature activation-0.006
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
stranger
Token stranger
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
number
Token number
Feature activation-0.008
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
chromosomes
Token chromosomes
Feature activation+0.034
Top resid features:
-
Token -
Feature activation+0.016
Top resid features:
humans
Token humans
Feature activation-0.012
Top resid features:
have
Token have
Feature activation+5.452
Top resid features:
23
Token 23
Feature activation-0.060
Top resid features:
pairs
Token pairs
Feature activation-0.027
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
apes
Token apes
Feature activation+0.008
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
âĢ
Token âĢ
Feature activation-0.006
Top resid features:
ľ
Tokenľ
Feature activation+0.002
Top resid features:
My
TokenMy
Feature activation+0.170
Top resid features:
son
Token son
Feature activation+0.031
Top resid features:
has
Token has
Feature activation+5.507
Top resid features:
a
Token a
Feature activation+0.292
Top resid features:
beard
Token beard
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.063
Top resid features:
my
Token my
Feature activation+0.074
Top resid features:
father
Token father
Feature activation+0.035
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
W
TokenW
Feature activation+0.002
Top resid features:
aters
Tokenaters
Feature activation+0.015
Top resid features:
:
Token:
Feature activation+0.030
Top resid features:
Everybody
Token Everybody
Feature activation+0.077
Top resid features:
has
Token has
Feature activation+3.557
Top resid features:
a
Token a
Feature activation+0.115
Top resid features:
mother
Token mother
Feature activation+0.022
Top resid features:
not
Token not
Feature activation+0.054
Top resid features:
quite
Token quite
Feature activation-0.009
Top resid features:
like
Token like
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
(
Token(
Feature activation+0.011
Top resid features:
define
Token define
Feature activation-0.061
Top resid features:
(
Token (
Feature activation-0.025
Top resid features:
has
Token has
Feature activation+6.041
Top resid features:
-
Token-
Feature activation-0.014
Top resid features:
sym
Tokensym
Feature activation+0.013
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
l
Token l
Feature activation+0.000
Top resid features:
st
Tokenst
Feature activation+0.000
Top resid features:
those
Token those
Feature activation-0.013
Top resid features:
who
Token who
Feature activation+0.012
Top resid features:
haven
Token haven
Feature activation+0.116
Top resid features:
âĢ
TokenâĢ
Feature activation-0.144
Top resid features:
Ļ
TokenĻ
Feature activation+0.051
Top resid features:
t
Tokent
Feature activation+6.095
Top resid features:
seen
Token seen
Feature activation+0.031
Top resid features:
it
Token it
Feature activation+0.036
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
but
Token but
Feature activation+0.015
Top resid features:
those
Token those
Feature activation-0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
But
TokenBut
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
drib
Token drib
Feature activation+0.013
Top resid features:
bler
Tokenbler
Feature activation-0.000
Top resid features:
has
Token has
Feature activation+2.547
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
first
Token first
Feature activation+0.013
Top resid features:
right
Token right
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.022
Top resid features:
any
Token any
Feature activation+0.007
Top resid features:
-
Token-
Feature activation+0.020
Top resid features:
Valley
Token Valley
Feature activation+0.013
Top resid features:
Mills
Token Mills
Feature activation-0.000
Top resid features:
Nursing
Token Nursing
Feature activation-0.022
Top resid features:
Home
Token Home
Feature activation-0.032
Top resid features:
has
Token has
Feature activation+5.794
Top resid features:
rooms
Token rooms
Feature activation+0.088
Top resid features:
available
Token available
Feature activation+0.092
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
nursing
Token nursing
Feature activation+0.006
Top resid features:
home
Token home
Feature activation-0.003
Top resid features:
position
Token position
Feature activation+0.014
Top resid features:
.
Token.
Feature activation+0.033
Top resid features:
The
Token The
Feature activation+0.035
Top resid features:
offensive
Token offensive
Feature activation-0.015
Top resid features:
player
Token player
Feature activation+0.013
Top resid features:
has
Token has
Feature activation+2.806
Top resid features:
to
Token to
Feature activation+0.049
Top resid features:
stay
Token stay
Feature activation+0.007
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
control
Token control
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:
depression
Token depression
Feature activation+0.010
Top resid features:
and
Token and
Feature activation+0.022
Top resid features:
anxiety
Token anxiety
Feature activation+0.010
Top resid features:
showed
Token showed
Feature activation+0.041
Top resid features:
that
Token that
Feature activation+0.057
Top resid features:
having
Token having
Feature activation+4.451
Top resid features:
only
Token only
Feature activation+0.794
Top resid features:
depression
Token depression
Feature activation+0.037
Top resid features:
was
Token was
Feature activation-0.001
Top resid features:
associated
Token associated
Feature activation+0.004
Top resid features:
with
Token with
Feature activation+0.032
Top resid features:
groups
Token groups
Feature activation+0.006
Top resid features:
competing
Token competing
Feature activation+0.004
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
supremacy
Token supremacy
Feature activation+0.019
Top resid features:
in
Token in
Feature activation+0.007
Top resid features:
Has
Token Has
Feature activation+5.654
Top resid features:
ake
Tokenake
Feature activation+0.015
Top resid features:
h
Tokenh
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
L
Token L
Feature activation+0.006
Top resid features:
acking
Tokenacking
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
"
Token "
Feature activation-0.021
Top resid features:
It
TokenIt
Feature activation+0.024
Top resid features:
doesn
Token doesn
Feature activation-0.060
Top resid features:
't
Token't
Feature activation-0.038
Top resid features:
have
Token have
Feature activation+5.509
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
be
Token be
Feature activation-0.011
Top resid features:
fl
Token fl
Feature activation+0.006
Top resid features:
aky
Tokenaky
Feature activation+0.018
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.05

Head 2: 0.04

Head 3: 0.05

Head 4: 0.03

Head 5: 0.47

Head 6: 0.09

Head 7: 0.03

Head 8: 0.06

Head 9: 0.06

Head 10: 0.05

Head 11: 0.04

Positive logits

Has6.80

Has6.41

has5.90

has5.28

have5.16

HAS5.11

Have5.05

have4.68

Have4.47

HAVE4.16

hath3.96

Had3.92

hasn3.90

had3.69

Had3.67

had3.65

having3.35

having3.26

haven3.19

Having3.05

Negative logits

SPONSORED-2.20

opsis-2.10

nant-2.09

gae-2.07

Ping-2.06

venant-2.04

united-2.00

-1.99

outh-1.96

atos-1.95

tein-1.94

erve-1.92

pn-1.91

piracy-1.91

rawdownloadcloneembedreportprint-1.91

rive-1.89

の�-1.88

portation-1.88

-1.87

oway-1.87

INTERVAL 6.953 - 7.725
CONTAINS 0.000%

chicken
Token chicken
Feature activation+0.000
.
Token.
Feature activation+0.145
(
Token (
Feature activation+1.052
Photo
TokenPhoto
Feature activation+0.000
11
Token11
Feature activation+0.000
:
Token:
Feature activation+7.725
Has
Token Has
Feature activation+0.000
bro
Tokenbro
Feature activation+0.000
)
Token)
Feature activation+0.117
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.515

INTERVAL 6.180 - 6.953
CONTAINS 0.000%

INTERVAL 5.408 - 6.180
CONTAINS 0.001%

guarding
Token guarding
Feature activation+0.000
position
Token position
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
offensive
Token offensive
Feature activation+0.000
player
Token player
Feature activation+5.817
has
Token has
Feature activation+1.601
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.000
in
Token in
Feature activation+0.000
control
Token control
Feature activation+0.000
training
Token training
Feature activation+0.000
,
Token,
Feature activation+0.000
workers
Token workers
Feature activation+5.402
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
ground
Token ground
Feature activation+5.446
had
Token had
Feature activation+3.315
to
Token to
Feature activation+0.000
ensure
Token ensure
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
W
TokenW
Feature activation+0.000
aters
Tokenaters
Feature activation+0.000
:
Token:
Feature activation+0.000
Everybody
Token Everybody
Feature activation+6.097
has
Token has
Feature activation+0.417
a
Token a
Feature activation+0.000
mother
Token mother
Feature activation+0.000
not
Token not
Feature activation+0.000
quite
Token quite
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
playing
Token playing
Feature activation+0.000
but
Token but
Feature activation+0.075
they
Token they
Feature activation+5.885
have
Token have
Feature activation+2.614
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
given
Token given
Feature activation+0.000
psychological
Token psychological
Feature activation+0.000
define
Token define
Feature activation+0.000
(
Token (
Feature activation+0.000
has
Token has
Feature activation+0.067
-
Token-
Feature activation+1.305
sym
Tokensym
Feature activation+4.512
?
Token?
Feature activation+6.126
l
Token l
Feature activation+1.585
st
Tokenst
Feature activation+2.891
s
Token s
Feature activation+0.000
)
Token )
Feature activation+3.413
(
Token (
Feature activation+2.398

INTERVAL 4.635 - 5.408
CONTAINS 0.001%

humans
Token humans
Feature activation+0.320
have
Token have
Feature activation+0.000
23
Token 23
Feature activation+0.000
pairs
Token pairs
Feature activation+0.000
and
Token and
Feature activation+0.000
apes
Token apes
Feature activation+4.920
have
Token have
Feature activation+0.000
24
Token 24
Feature activation+0.000
pairs
Token pairs
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
of
Token of
Feature activation+0.000
hours
Token hours
Feature activation+0.000
of
Token of
Feature activation+0.000
training
Token training
Feature activation+0.000
,
Token,
Feature activation+0.000
workers
Token workers
Feature activation+5.402
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
ground
Token ground
Feature activation+5.446
had
Token had
Feature activation+3.315
to
Token to
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
beard
Token beard
Feature activation+0.000
,
Token,
Feature activation+0.000
my
Token my
Feature activation+0.000
father
Token father
Feature activation+4.779
and
Token and
Feature activation+0.000
grandfather
Token grandfather
Feature activation+3.817
all
Token all
Feature activation+1.849
had
Token had
Feature activation+0.000
be
Token be
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.062
More
TokenMore
Feature activation+0.000
than
Token than
Feature activation+0.000
once
Token once
Feature activation+0.506
I
Token I
Feature activation+4.930
have
Token have
Feature activation+0.189
helped
Token helped
Feature activation+0.000
push
Token push
Feature activation+0.000
a
Token a
Feature activation+0.000
stranger
Token stranger
Feature activation+0.000
quite
Token quite
Feature activation+0.000
like
Token like
Feature activation+0.000
this
Token this
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
everybody
Token everybody
Feature activation+4.689
has
Token has
Feature activation+0.610
a
Token a
Feature activation+0.000
mother
Token mother
Feature activation+0.000
who
Token who
Feature activation+0.998
has
Token has
Feature activation+0.000

INTERVAL 3.863 - 4.635
CONTAINS 0.001%

seen
Token seen
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+4.481
have
Token have
Feature activation+1.735
should
Token should
Feature activation+0.000
know
Token know
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
what
Token what
Feature activation+0.000
of
Token of
Feature activation+0.640
a
Token a
Feature activation+0.000
dementia
Token dementia
Feature activation+0.000
diagnosis
Token diagnosis
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+4.095
having
Token having
Feature activation+3.458
just
Token just
Feature activation+1.701
an
Token an
Feature activation+0.337
anxiety
Token anxiety
Feature activation+0.000
diagnosis
Token diagnosis
Feature activation+0.000
:
Token:
Feature activation+0.000
Well
Token Well
Feature activation+0.000
,
Token,
Feature activation+0.000
having
Token having
Feature activation+0.000
an
Token an
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+3.879
it
Token it
Feature activation+0.357
had
Token had
Feature activation+0.958
an
Token an
Feature activation+0.000
effect
Token effect
Feature activation+0.000
on
Token on
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Blessed
Token Blessed
Feature activation+0.000
Virgin
Token Virgin
Feature activation+0.797
Mary
Token Mary
Feature activation+3.074
Parish
Token Parish
Feature activation+4.282
at
Token at
Feature activation+0.000
219
Token 219
Feature activation+0.000
W
Token W
Feature activation+0.000
.
Token.
Feature activation+0.000
Magn
Token Magn
Feature activation+0.000
(
Token(
Feature activation+0.000
define
Token define
Feature activation+0.000
(
Token (
Feature activation+0.000
has
Token has
Feature activation+0.067
-
Token-
Feature activation+1.305
sym
Tokensym
Feature activation+4.512
?
Token?
Feature activation+6.126
l
Token l
Feature activation+1.585
st
Tokenst
Feature activation+2.891
s
Token s
Feature activation+0.000
)
Token )
Feature activation+3.413

INTERVAL 3.090 - 3.863
CONTAINS 0.002%

.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
if
Token if
Feature activation+0.000
Extreme
Token Extreme
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
Loud
Token Loud
Feature activation+3.288
and
Token and
Feature activation+0.000
Inc
Token Inc
Feature activation+0.000
redibly
Tokenredibly
Feature activation+0.000
Close
Token Close
Feature activation+1.455
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
dementia
Token dementia
Feature activation+0.000
diagnosis
Token diagnosis
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+4.095
having
Token having
Feature activation+3.458
just
Token just
Feature activation+1.701
an
Token an
Feature activation+0.337
anxiety
Token anxiety
Feature activation+0.000
diagnosis
Token diagnosis
Feature activation+0.000
.
Token.
Feature activation+1.010
per
Token per
Feature activation+0.000
verted
Tokenverted
Feature activation+0.000
view
Token view
Feature activation+0.000
of
Token of
Feature activation+0.000
Islam
Token Islam
Feature activation+0.000
,
Token,
Feature activation+3.848
ISIL
Token ISIL
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
followers
Token followers
Feature activation+0.000
factors
Token factors
Feature activation+0.000
.
Token.
Feature activation+0.508
The
Token The
Feature activation+0.000
independent
Token independent
Feature activation+0.000
effect
Token effect
Feature activation+0.000
of
Token of
Feature activation+3.111
depression
Token depression
Feature activation+0.000
was
Token was
Feature activation+0.000
weaker
Token weaker
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+3.538
219
Token 219
Feature activation+0.000
W
Token W
Feature activation+0.000
.
Token.
Feature activation+0.000
Magn
Token Magn
Feature activation+0.000
olia
Tokenolia
Feature activation+0.000
Street
Token Street
Feature activation+3.372
,
Token,
Feature activation+0.000
Pen
Token Pen
Feature activation+0.000
elope
Tokenelope
Feature activation+0.000
,
Token,
Feature activation+0.000
TX
Token TX
Feature activation+0.000

INTERVAL 2.318 - 3.090
CONTAINS 0.005%

of
Token of
Feature activation+0.000
Islam
Token Islam
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Clinton
Token Clinton
Feature activation+2.582
has
Token has
Feature activation+0.000
tweeted
Token tweeted
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
this
Token this
Feature activation+0.000
?
Token?
Feature activation+0.461
Although
Token Although
Feature activation+1.977
the
Token the
Feature activation+0.715
representation
Token representation
Feature activation+0.000
of
Token of
Feature activation+2.378
humans
Token humans
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
controversial
Token controversial
Feature activation+0.000
Giants
Token Giants
Feature activation+0.000
up
Token up
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
it
Token it
Feature activation+1.718
certainly
Token certainly
Feature activation+2.662
has
Token has
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
a
Token a
Feature activation+0.000
merely
Token merely
Feature activation+0.000
the
Token the
Feature activation+0.000
snow
Token snow
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.970
I
TokenI
Feature activation+3.001
have
Token have
Feature activation+0.000
helped
Token helped
Feature activation+0.000
push
Token push
Feature activation+0.000
a
Token a
Feature activation+0.000
stranger
Token stranger
Feature activation+0.000
,
Token,
Feature activation+0.000
decree
Token decree
Feature activation+0.000
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+3.006
may
Token may
Feature activation+3.705
not
Token not
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
contract
Token contract
Feature activation+0.000

INTERVAL 1.545 - 2.318
CONTAINS 0.008%

of
Token of
Feature activation+0.712
the
Token the
Feature activation+0.000
TLS
Token TLS
Feature activation+0.000
certificate
Token certificate
Feature activation+0.000
returned
Token returned
Feature activation+0.000
by
Token by
Feature activation+1.635
the
Token the
Feature activation+0.041
server
Token server
Feature activation+0.000
:
Token:
Feature activation+0.015
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
national
Token national
Feature activation+0.000
infrastructure
Token infrastructure
Feature activation+2.638
of
Token of
Feature activation+0.000
airports
Token airports
Feature activation+1.613
and
Token and
Feature activation+0.000
traffic
Token traffic
Feature activation+0.000
control
Token control
Feature activation+0.441
had
Token had
Feature activation+3.162
to
Token to
Feature activation+0.000
faces
Token faces
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Mid
Token Mid
Feature activation+0.000
r
Tokenr
Feature activation+0.000
ash
Tokenash
Feature activation+2.114
teaches
Token teaches
Feature activation+0.000
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
suggest
Token suggest
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
either
Token either
Feature activation+0.000
unaware
Token unaware
Feature activation+0.000
that
Token that
Feature activation+2.967
some
Token some
Feature activation+0.000
of
Token of
Feature activation+1.592
the
Token the
Feature activation+0.000
great
Token great
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
civil
Token civil
Feature activation+0.000
isations
Tokenisations
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
debate
Token debate
Feature activation+0.000
answer
Token answer
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+1.876
it
Token it
Feature activation+1.349
had
Token had
Feature activation+0.653
an
Token an
Feature activation+0.000
effect
Token effect
Feature activation+0.405
on
Token on
Feature activation+0.002

INTERVAL 0.773 - 1.545
CONTAINS 0.024%

having
Token having
Feature activation+0.000
to
Token to
Feature activation+0.000
prove
Token prove
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
laws
Token laws
Feature activation+0.844
actually
Token actually
Feature activation+0.241
benefit
Token benefit
Feature activation+0.000
women
Token women
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
defensive
Token defensive
Feature activation+0.000
player
Token player
Feature activation+3.286
guarding
Token guarding
Feature activation+0.012
a
Token a
Feature activation+0.000
player
Token player
Feature activation+1.445
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
ball
Token ball
Feature activation+1.406
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
snow
Token snow
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.787
Never
TokenNever
Feature activation+0.962
I
Token I
Feature activation+1.265
have
Token have
Feature activation+0.537
helped
Token helped
Feature activation+0.000
push
Token push
Feature activation+0.000
a
Token a
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.223
Orig
TokenOrig
Feature activation+0.000
inated
Tokeninated
Feature activation+0.000
the
Token the
Feature activation+0.000
role
Token role
Feature activation+0.000
of
Token of
Feature activation+0.784
Antonio
Token Antonio
Feature activation+0.000
Sal
Token Sal
Feature activation+0.000
ieri
Tokenieri
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
drafting
Token drafting
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+1.002
a
Token a
Feature activation+0.000
mix
Token mix
Feature activation+0.000
of
Token of
Feature activation+0.000
Hero
Token Hero
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.773
CONTAINS 99.959%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
An
TokenAn
Feature activation+0.000
affiliate
Token affiliate
Feature activation+0.000
of
Token of
Feature activation+0.000
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
J
TokenJ
Feature activation+0.000
azeera
Tokenazeera
Feature activation+0.000
Media
Token Media
Feature activation+0.000
Networks
Token Networks
Feature activation+0.000
stars
Token stars
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
couple
Token couple
Feature activation+0.000
of
Token of
Feature activation+0.000
seasons
Token seasons
Feature activation+0.000
that
Token that
Feature activation+0.000
any
Token any
Feature activation+0.000
fan
Token fan
Feature activation+0.000
would
Token would
Feature activation+0.000
the
Token the
Feature activation+0.000
job
Token job
Feature activation+0.000
search
Token search
Feature activation+0.000
.
Token.
Feature activation+0.000
Nearly
Token Nearly
Feature activation+0.000
9
Token 9
Feature activation+0.000
million
Token million
Feature activation+0.000
are
Token are
Feature activation+0.000
employed
Token employed
Feature activation+0.000
part
Token part
Feature activation+0.000
-
Token-
Feature activation+0.000
with
Token with
Feature activation+0.000
D
Token D
Feature activation+0.000
VR
TokenVR
Feature activation+0.000
and
Token and
Feature activation+0.000
streaming
Token streaming
Feature activation+0.000
video
Token video
Feature activation+0.000
services
Token services
Feature activation+0.000
it
Token it
Feature activation+0.000
looks
Token looks
Feature activation+0.000
more
Token more
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
I
Token I
Feature activation+0.000
suffered
Token suffered
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
boy
Token boy
Feature activation+0.000
and
Token and
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
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 H11.5: (feature 5191)

TOP ACTIVATIONS
MAX = 8.285

these
Token these
Feature activation+1.784
giant
Token giant
Feature activation+1.602
photos
Token photos
Feature activation+0.000
above
Token above
Feature activation+6.413
one
Token one
Feature activation+0.283
of
Token of
Feature activation+8.285
the
Token the
Feature activation+2.680
maintenance
Token maintenance
Feature activation+0.000
areas
Token areas
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
specs
Token specs
Feature activation+0.000
of
Token of
Feature activation+1.274
the
Token the
Feature activation+6.704
Mic
Token Mic
Feature activation+0.000
rom
Tokenrom
Feature activation+0.000
ax
Tokenax
Feature activation+7.362
Can
Token Can
Feature activation+0.000
vas
Tokenvas
Feature activation+6.691
Spark
Token Spark
Feature activation+3.950
:
Token:
Feature activation+0.147
Ċ
TokenĊ
Feature activation+0.000
at
Token at
Feature activation+0.000
Stamford
Token Stamford
Feature activation+0.000
Bridge
Token Bridge
Feature activation+0.000
.
Token.
Feature activation+3.709
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.935
Can
TokenCan
Feature activation+0.000
missed
Token missed
Feature activation+0.000
the
Token the
Feature activation+0.000
games
Token games
Feature activation+0.000
against
Token against
Feature activation+0.000
trip
Token trip
Feature activation+0.000
to
Token to
Feature activation+0.000
Chelsea
Token Chelsea
Feature activation+0.000
.
Token.
Feature activation+4.627
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.870
The
TokenThe
Feature activation+0.000
German
Token German
Feature activation+0.000
international
Token international
Feature activation+0.000
midfielder
Token midfielder
Feature activation+0.000
is
Token is
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
key
Token key
Feature activation+0.000
specs
Token specs
Feature activation+0.000
of
Token of
Feature activation+1.274
the
Token the
Feature activation+6.704
Mic
Token Mic
Feature activation+0.000
rom
Tokenrom
Feature activation+0.000
ax
Tokenax
Feature activation+7.362
Can
Token Can
Feature activation+0.000
vas
Tokenvas
Feature activation+6.691
the
Token the
Feature activation+6.704
Mic
Token Mic
Feature activation+0.000
rom
Tokenrom
Feature activation+0.000
ax
Tokenax
Feature activation+7.362
Can
Token Can
Feature activation+0.000
vas
Tokenvas
Feature activation+6.691
Spark
Token Spark
Feature activation+3.950
:
Token:
Feature activation+0.147
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.623
Display
TokenDisplay
Feature activation+0.000
pet
Token pet
Feature activation+0.000
project
Token project
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
sign
Token sign
Feature activation+6.585
the
Token the
Feature activation+0.000
25
Token 25
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
take
Token take
Feature activation+0.000
back
Token back
Feature activation+0.000
anything
Token anything
Feature activation+0.000
,
Token,
Feature activation+6.538
I
Token I
Feature activation+0.607
love
Token love
Feature activation+0.000
what
Token what
Feature activation+0.000
I
Token I
Feature activation+0.000
do
Token do
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.031
It
TokenIt
Feature activation+0.000
was
Token was
Feature activation+3.082
a
Token a
Feature activation+0.000
setback
Token setback
Feature activation+1.993
for
Token for
Feature activation+6.514
22
Token 22
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+6.391
been
Token been
Feature activation+0.000
involved
Token involved
Feature activation+0.000
in
Token in
Feature activation+0.000
discussions
Token discussions
Feature activation+0.000
with
Token with
Feature activation+0.121
Rio
Token Rio
Feature activation+6.495
Can
TokenCan
Feature activation+0.000
regarding
Token regarding
Feature activation+0.000
the
Token the
Feature activation+0.000
development
Token development
Feature activation+0.000
opportunities
Token opportunities
Feature activation+0.000
installation
Token installation
Feature activation+0.000
of
Token of
Feature activation+2.995
these
Token these
Feature activation+1.784
giant
Token giant
Feature activation+1.602
photos
Token photos
Feature activation+0.000
above
Token above
Feature activation+6.413
one
Token one
Feature activation+0.283
of
Token of
Feature activation+8.285
the
Token the
Feature activation+2.680
maintenance
Token maintenance
Feature activation+0.000
areas
Token areas
Feature activation+0.000
for
Token for
Feature activation+6.514
22
Token 22
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+6.391
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
had
Token had
Feature activation+0.000
returned
Token returned
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+3.689
clerk
Token clerk
Feature activation+0.000
insists
Token insists
Feature activation+0.000
on
Token on
Feature activation+0.000
putting
Token putting
Feature activation+0.350
the
Token the
Feature activation+6.357
items
Token items
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+3.961
plastic
Token plastic
Feature activation+0.969
bag
Token bag
Feature activation+0.000
ik
Tokenik
Feature activation+0.000
Can
Token Can
Feature activation+0.000
a
Tokena
Feature activation+0.000
.
Token.
Feature activation+3.002
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.152
L
TokenL
Feature activation+0.000
or
Tokenor
Feature activation+0.000
ik
Tokenik
Feature activation+2.481
Can
Token Can
Feature activation+0.000
a
Tokena
Feature activation+0.000
Albion
Token Albion
Feature activation+0.000
last
Token last
Feature activation+0.000
month
Token month
Feature activation+0.000
.
Token.
Feature activation+2.762
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.031
It
TokenIt
Feature activation+0.000
was
Token was
Feature activation+3.082
a
Token a
Feature activation+0.000
setback
Token setback
Feature activation+1.993
for
Token for
Feature activation+6.514
donate
Token donate
Feature activation+0.000
.
Token.
Feature activation+0.000
if
Token if
Feature activation+0.000
your
Token your
Feature activation+0.000
Volunteer
Token Volunteer
Feature activation+1.097
association
Token association
Feature activation+5.914
can
Token can
Feature activation+0.935
-
Token-
Feature activation+0.000
please
Tokenplease
Feature activation+0.685
donate
Token donate
Feature activation+0.000
.
Token.
Feature activation+0.000
recent
Token recent
Feature activation+4.416
addition
Token addition
Feature activation+0.000
to
Token to
Feature activation+5.649
the
Token the
Feature activation+3.039
shop
Token shop
Feature activation+0.000
was
Token was
Feature activation+5.652
the
Token the
Feature activation+4.089
installation
Token installation
Feature activation+0.000
of
Token of
Feature activation+2.995
these
Token these
Feature activation+1.784
giant
Token giant
Feature activation+1.602
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.474
One
TokenOne
Feature activation+0.134
recent
Token recent
Feature activation+4.416
addition
Token addition
Feature activation+0.000
to
Token to
Feature activation+5.649
the
Token the
Feature activation+3.039
shop
Token shop
Feature activation+0.000
was
Token was
Feature activation+5.652
the
Token the
Feature activation+4.089
installation
Token installation
Feature activation+0.000
for
Token for
Feature activation+4.467
the
Token the
Feature activation+0.000
Yankees
Token Yankees
Feature activation+0.000
to
Token to
Feature activation+0.000
forget
Token forget
Feature activation+3.005
about
Token about
Feature activation+5.597
their
Token their
Feature activation+0.000
financial
Token financial
Feature activation+0.000
pet
Token pet
Feature activation+0.000
project
Token project
Feature activation+0.000
in
Token in
Feature activation+0.000
to
Token to
Feature activation+1.359
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.307
s
Tokens
Feature activation+5.582
sensational
Token sensational
Feature activation+4.080
Se
Token Se
Feature activation+0.000
ager
Tokenager
Feature activation+0.000
Road
Token Road
Feature activation+0.000
ster
Tokenster
Feature activation+0.388

Top DFA by src position
MAX = 8.991

progress
Token progress
Feature activation+0.003
Top resid features:
had
Token had
Feature activation+0.003
Top resid features:
been
Token been
Feature activation+0.002
Top resid features:
made
Token made
Feature activation+0.001
Top resid features:
on
Token on
Feature activation+0.015
Top resid features:
Can
Token Can
Feature activation+8.991
Top resid features:
ep
Tokenep
Feature activation-0.000
Top resid features:
a
Tokena
Feature activation+0.042
Top resid features:
âĢ
TokenâĢ
Feature activation+0.033
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
s
Tokens
Feature activation+0.053
Top resid features:
brand
Token brand
Feature activation-0.007
Top resid features:
new
Token new
Feature activation-0.002
Top resid features:
Mic
Token Mic
Feature activation+0.015
Top resid features:
rom
Tokenrom
Feature activation-0.018
Top resid features:
ax
Tokenax
Feature activation+0.033
Top resid features:
Can
Token Can
Feature activation+8.749
Top resid features:
vas
Tokenvas
Feature activation+0.102
Top resid features:
Spark
Token Spark
Feature activation+0.226
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
Black
Token Black
Feature activation+0.002
Top resid features:
color
Token color
Feature activation-0.015
Top resid features:
Email
Token Email
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Em
TokenEm
Feature activation-0.131
Top resid features:
re
Tokenre
Feature activation+0.022
Top resid features:
Can
Token Can
Feature activation+8.866
Top resid features:
is
Token is
Feature activation+0.011
Top resid features:
set
Token set
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
hand
Token hand
Feature activation+0.005
Top resid features:
J
Token J
Feature activation-0.035
Top resid features:
Email
Token Email
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Em
TokenEm
Feature activation-0.183
Top resid features:
re
Tokenre
Feature activation+0.030
Top resid features:
Can
Token Can
Feature activation+8.924
Top resid features:
is
Token is
Feature activation+0.022
Top resid features:
set
Token set
Feature activation-0.002
Top resid features:
to
Token to
Feature activation+0.013
Top resid features:
hand
Token hand
Feature activation+0.007
Top resid features:
J
Token J
Feature activation-0.043
Top resid features:
brand
Token brand
Feature activation-0.023
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
Mic
Token Mic
Feature activation+0.080
Top resid features:
rom
Tokenrom
Feature activation-0.008
Top resid features:
ax
Tokenax
Feature activation+0.032
Top resid features:
Can
Token Can
Feature activation+8.120
Top resid features:
vas
Tokenvas
Feature activation+0.082
Top resid features:
Spark
Token Spark
Feature activation+0.239
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
Black
Token Black
Feature activation+0.003
Top resid features:
color
Token color
Feature activation-0.031
Top resid features:
brand
Token brand
Feature activation+0.003
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
Mic
Token Mic
Feature activation-0.007
Top resid features:
rom
Tokenrom
Feature activation-0.014
Top resid features:
ax
Tokenax
Feature activation+0.019
Top resid features:
Can
Token Can
Feature activation+6.083
Top resid features:
vas
Tokenvas
Feature activation+0.090
Top resid features:
Spark
Token Spark
Feature activation+0.249
Top resid features:
in
Token in
Feature activation+0.018
Top resid features:
Black
Token Black
Feature activation+0.003
Top resid features:
color
Token color
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
Seattle
Token Seattle
Feature activation-0.001
Top resid features:
Mariners
Token Mariners
Feature activation-0.001
Top resid features:
for
Token for
Feature activation+0.016
Top resid features:
Robinson
Token Robinson
Feature activation+0.001
Top resid features:
Can
Token Can
Feature activation+7.996
Top resid features:
o
Tokeno
Feature activation+0.032
Top resid features:
.
Token.
Feature activation+0.035
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Now
TokenNow
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.058
Top resid features:
I
Token I
Feature activation+0.003
Top resid features:
can
Token can
Feature activation+0.762
Top resid features:
âĢ
TokenâĢ
Feature activation+0.013
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
t
Tokent
Feature activation+7.327
Top resid features:
take
Token take
Feature activation+0.024
Top resid features:
back
Token back
Feature activation+0.016
Top resid features:
anything
Token anything
Feature activation+0.021
Top resid features:
,
Token,
Feature activation-0.025
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
Email
Token Email
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Em
TokenEm
Feature activation-0.029
Top resid features:
re
Tokenre
Feature activation+0.019
Top resid features:
Can
Token Can
Feature activation+6.519
Top resid features:
is
Token is
Feature activation+0.004
Top resid features:
set
Token set
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
hand
Token hand
Feature activation+0.002
Top resid features:
J
Token J
Feature activation-0.036
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
battle
Token battle
Feature activation+0.002
Top resid features:
unfolded
Token unfolded
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
Rio
Token Rio
Feature activation+0.014
Top resid features:
Can
TokenCan
Feature activation+8.012
Top resid features:
filed
Token filed
Feature activation+0.001
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
pre
Token pre
Feature activation+0.002
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
application
Tokenapplication
Feature activation+0.004
Top resid features:
progress
Token progress
Feature activation+0.001
Top resid features:
had
Token had
Feature activation+0.002
Top resid features:
been
Token been
Feature activation+0.002
Top resid features:
made
Token made
Feature activation+0.001
Top resid features:
on
Token on
Feature activation+0.010
Top resid features:
Can
Token Can
Feature activation+7.468
Top resid features:
ep
Tokenep
Feature activation-0.000
Top resid features:
a
Tokena
Feature activation+0.038
Top resid features:
âĢ
TokenâĢ
Feature activation+0.008
Top resid features:
Ļ
TokenĻ
Feature activation+0.019
Top resid features:
s
Tokens
Feature activation+0.060
Top resid features:
Email
Token Email
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Em
TokenEm
Feature activation-0.055
Top resid features:
re
Tokenre
Feature activation+0.018
Top resid features:
Can
Token Can
Feature activation+6.968
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
set
Token set
Feature activation-0.006
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
hand
Token hand
Feature activation+0.001
Top resid features:
J
Token J
Feature activation-0.039
Top resid features:
bothered
Token bothered
Feature activation+0.005
Top resid features:
when
Token when
Feature activation+0.011
Top resid features:
I
Token I
Feature activation+0.005
Top resid features:
buy
Token buy
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
can
Token can
Feature activation+7.934
Top resid features:
of
Token of
Feature activation+0.048
Top resid features:
soda
Token soda
Feature activation+0.031
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
or
Token or
Feature activation+0.006
Top resid features:
a
Token a
Feature activation+0.019
Top resid features:
equal
Token equal
Feature activation+0.002
Top resid features:
iser
Tokeniser
Feature activation-0.001
Top resid features:
from
Token from
Feature activation+0.023
Top resid features:
Lor
Token Lor
Feature activation-0.014
Top resid features:
ik
Tokenik
Feature activation-0.002
Top resid features:
Can
Token Can
Feature activation+8.077
Top resid features:
a
Tokena
Feature activation+0.017
Top resid features:
.
Token.
Feature activation-0.031
Top resid features:
Ċ
TokenĊ
Feature activation-0.038
Top resid features:
Ċ
TokenĊ
Feature activation-0.081
Top resid features:
L
TokenL
Feature activation+0.000
Top resid features:
Email
Token Email
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:
Em
TokenEm
Feature activation-0.076
Top resid features:
re
Tokenre
Feature activation+0.014
Top resid features:
Can
Token Can
Feature activation+4.858
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
set
Token set
Feature activation-0.003
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
hand
Token hand
Feature activation+0.005
Top resid features:
J
Token J
Feature activation-0.028
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
If
Token If
Feature activation+0.004
Top resid features:
your
Token your
Feature activation-0.005
Top resid features:
Union
Token Union
Feature activation-0.038
Top resid features:
local
Token local
Feature activation+0.007
Top resid features:
can
Token can
Feature activation+6.844
Top resid features:
-
Token-
Feature activation+0.101
Top resid features:
please
Tokenplease
Feature activation+0.042
Top resid features:
donate
Token donate
Feature activation-0.092
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
if
Token if
Feature activation-0.004
Top resid features:
progress
Token progress
Feature activation+0.002
Top resid features:
had
Token had
Feature activation+0.002
Top resid features:
been
Token been
Feature activation+0.002
Top resid features:
made
Token made
Feature activation-0.003
Top resid features:
on
Token on
Feature activation+0.010
Top resid features:
Can
Token Can
Feature activation+6.555
Top resid features:
ep
Tokenep
Feature activation+0.003
Top resid features:
a
Tokena
Feature activation+0.019
Top resid features:
âĢ
TokenâĢ
Feature activation+0.019
Top resid features:
Ļ
TokenĻ
Feature activation+0.011
Top resid features:
s
Tokens
Feature activation+0.035
Top resid features:
progress
Token progress
Feature activation+0.009
Top resid features:
had
Token had
Feature activation+0.003
Top resid features:
been
Token been
Feature activation+0.003
Top resid features:
made
Token made
Feature activation+0.001
Top resid features:
on
Token on
Feature activation+0.008
Top resid features:
Can
Token Can
Feature activation+6.429
Top resid features:
ep
Tokenep
Feature activation+0.010
Top resid features:
a
Tokena
Feature activation+0.048
Top resid features:
âĢ
TokenâĢ
Feature activation+0.067
Top resid features:
Ļ
TokenĻ
Feature activation+0.012
Top resid features:
s
Tokens
Feature activation+0.048
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
Seattle
Token Seattle
Feature activation-0.000
Top resid features:
Mariners
Token Mariners
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.023
Top resid features:
Robinson
Token Robinson
Feature activation+0.011
Top resid features:
Can
Token Can
Feature activation+7.101
Top resid features:
o
Tokeno
Feature activation+0.020
Top resid features:
.
Token.
Feature activation+0.029
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Now
TokenNow
Feature activation+0.009
Top resid features:
from
Token from
Feature activation+0.079
Top resid features:
the
Token the
Feature activation+0.069
Top resid features:
240
Token 240
Feature activation+0.016
Top resid features:
million
Token million
Feature activation+0.002
Top resid features:
dollar
Token dollar
Feature activation-0.005
Top resid features:
Can
Token Can
Feature activation+6.699
Top resid features:
o
Tokeno
Feature activation+0.129
Top resid features:
R
Token R
Feature activation-0.017
Top resid features:
-
Token-
Feature activation+0.019
Top resid features:
Type
TokenType
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+0.052
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.04

Head 2: 0.05

Head 3: 0.04

Head 4: 0.04

Head 5: 0.46

Head 6: 0.07

Head 7: 0.04

Head 8: 0.05

Head 9: 0.06

Head 10: 0.04

Head 11: 0.04

Positive logits

Can7.97

Can7.70

can7.15

can6.94

CAN5.63

CAN5.12

cannot4.69

cans4.13

Cannot4.08

Could3.80

Could3.70

could3.70

could3.56

Has3.44

annot3.42

cant3.35

Must3.30

cano3.11

Must3.08

able3.03

Negative logits

rawdownloadcloneembedreportprint-2.31

ospons-2.17

ospace-2.17

avis-2.15

hesda-2.11

ensions-2.08

IELD-2.07

adesh-2.06

susp-2.02

vard-2.02

bor-1.98

ilities-1.97

tre-1.97

-1.95

aten-1.94

ilit-1.94

-1.92

bringing-1.92

olphin-1.92

ived-1.89

INTERVAL 7.457 - 8.285
CONTAINS 0.000%

these
Token these
Feature activation+1.784
giant
Token giant
Feature activation+1.602
photos
Token photos
Feature activation+0.000
above
Token above
Feature activation+6.413
one
Token one
Feature activation+0.283
of
Token of
Feature activation+8.285
the
Token the
Feature activation+2.680
maintenance
Token maintenance
Feature activation+0.000
areas
Token areas
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000

INTERVAL 6.628 - 7.457
CONTAINS 0.001%

trip
Token trip
Feature activation+0.000
to
Token to
Feature activation+0.000
Chelsea
Token Chelsea
Feature activation+0.000
.
Token.
Feature activation+4.627
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.870
The
TokenThe
Feature activation+0.000
German
Token German
Feature activation+0.000
international
Token international
Feature activation+0.000
midfielder
Token midfielder
Feature activation+0.000
is
Token is
Feature activation+0.000
at
Token at
Feature activation+0.000
Stamford
Token Stamford
Feature activation+0.000
Bridge
Token Bridge
Feature activation+0.000
.
Token.
Feature activation+3.709
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.935
Can
TokenCan
Feature activation+0.000
missed
Token missed
Feature activation+0.000
the
Token the
Feature activation+0.000
games
Token games
Feature activation+0.000
against
Token against
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
key
Token key
Feature activation+0.000
specs
Token specs
Feature activation+0.000
of
Token of
Feature activation+1.274
the
Token the
Feature activation+6.704
Mic
Token Mic
Feature activation+0.000
rom
Tokenrom
Feature activation+0.000
ax
Tokenax
Feature activation+7.362
Can
Token Can
Feature activation+0.000
vas
Tokenvas
Feature activation+6.691
specs
Token specs
Feature activation+0.000
of
Token of
Feature activation+1.274
the
Token the
Feature activation+6.704
Mic
Token Mic
Feature activation+0.000
rom
Tokenrom
Feature activation+0.000
ax
Tokenax
Feature activation+7.362
Can
Token Can
Feature activation+0.000
vas
Tokenvas
Feature activation+6.691
Spark
Token Spark
Feature activation+3.950
:
Token:
Feature activation+0.147
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+6.704
Mic
Token Mic
Feature activation+0.000
rom
Tokenrom
Feature activation+0.000
ax
Tokenax
Feature activation+7.362
Can
Token Can
Feature activation+0.000
vas
Tokenvas
Feature activation+6.691
Spark
Token Spark
Feature activation+3.950
:
Token:
Feature activation+0.147
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.623
Display
TokenDisplay
Feature activation+0.000

INTERVAL 5.800 - 6.628
CONTAINS 0.001%

donate
Token donate
Feature activation+0.000
.
Token.
Feature activation+0.000
if
Token if
Feature activation+0.000
your
Token your
Feature activation+0.000
Volunteer
Token Volunteer
Feature activation+1.097
association
Token association
Feature activation+5.914
can
Token can
Feature activation+0.935
-
Token-
Feature activation+0.000
please
Tokenplease
Feature activation+0.685
donate
Token donate
Feature activation+0.000
.
Token.
Feature activation+0.000
been
Token been
Feature activation+0.000
involved
Token involved
Feature activation+0.000
in
Token in
Feature activation+0.000
discussions
Token discussions
Feature activation+0.000
with
Token with
Feature activation+0.121
Rio
Token Rio
Feature activation+6.495
Can
TokenCan
Feature activation+0.000
regarding
Token regarding
Feature activation+0.000
the
Token the
Feature activation+0.000
development
Token development
Feature activation+0.000
opportunities
Token opportunities
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
take
Token take
Feature activation+0.000
back
Token back
Feature activation+0.000
anything
Token anything
Feature activation+0.000
,
Token,
Feature activation+6.538
I
Token I
Feature activation+0.607
love
Token love
Feature activation+0.000
what
Token what
Feature activation+0.000
I
Token I
Feature activation+0.000
do
Token do
Feature activation+0.000
installation
Token installation
Feature activation+0.000
of
Token of
Feature activation+2.995
these
Token these
Feature activation+1.784
giant
Token giant
Feature activation+1.602
photos
Token photos
Feature activation+0.000
above
Token above
Feature activation+6.413
one
Token one
Feature activation+0.283
of
Token of
Feature activation+8.285
the
Token the
Feature activation+2.680
maintenance
Token maintenance
Feature activation+0.000
areas
Token areas
Feature activation+0.000
ik
Tokenik
Feature activation+0.000
Can
Token Can
Feature activation+0.000
a
Tokena
Feature activation+0.000
.
Token.
Feature activation+3.002
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.152
L
TokenL
Feature activation+0.000
or
Tokenor
Feature activation+0.000
ik
Tokenik
Feature activation+2.481
Can
Token Can
Feature activation+0.000
a
Tokena
Feature activation+0.000

INTERVAL 4.971 - 5.800
CONTAINS 0.001%

recent
Token recent
Feature activation+4.416
addition
Token addition
Feature activation+0.000
to
Token to
Feature activation+5.649
the
Token the
Feature activation+3.039
shop
Token shop
Feature activation+0.000
was
Token was
Feature activation+5.652
the
Token the
Feature activation+4.089
installation
Token installation
Feature activation+0.000
of
Token of
Feature activation+2.995
these
Token these
Feature activation+1.784
giant
Token giant
Feature activation+1.602
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.474
One
TokenOne
Feature activation+0.134
recent
Token recent
Feature activation+4.416
addition
Token addition
Feature activation+0.000
to
Token to
Feature activation+5.649
the
Token the
Feature activation+3.039
shop
Token shop
Feature activation+0.000
was
Token was
Feature activation+5.652
the
Token the
Feature activation+4.089
installation
Token installation
Feature activation+0.000
it
Token it
Feature activation+0.000
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.287
best
Token best
Feature activation+5.045
smartphones
Token smartphones
Feature activation+1.086
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
get
Token get
Feature activation+0.000
under
Token under
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
City
Token City
Feature activation+0.000
automatically
Token automatically
Feature activation+0.000
put
Token put
Feature activation+2.477
your
Token your
Feature activation+5.582
can
Token can
Feature activation+0.482
of
Token of
Feature activation+2.703
soda
Token soda
Feature activation+2.304
,
Token,
Feature activation+0.150
or
Token or
Feature activation+2.394
can
Token can
Feature activation+0.000
of
Token of
Feature activation+1.928
soda
Token soda
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
a
Token a
Feature activation+5.289
few
Token few
Feature activation+1.825
items
Token items
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.647
grocery
Token grocery
Feature activation+0.000

INTERVAL 4.143 - 4.971
CONTAINS 0.001%

Fred
Token Fred
Feature activation+0.000
Perry
Token Perry
Feature activation+5.200
airline
Token airline
Feature activation+2.453
bag
Token bag
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+4.359
stores
Token stores
Feature activation+0.000
in
Token in
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
City
Token City
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
trip
Token trip
Feature activation+0.000
to
Token to
Feature activation+0.000
Chelsea
Token Chelsea
Feature activation+0.000
.
Token.
Feature activation+4.627
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.870
The
TokenThe
Feature activation+0.000
German
Token German
Feature activation+0.000
international
Token international
Feature activation+0.000
projects
Token projects
Feature activation+0.000
.
Token.
Feature activation+1.032
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.474
One
TokenOne
Feature activation+0.134
recent
Token recent
Feature activation+4.416
addition
Token addition
Feature activation+0.000
to
Token to
Feature activation+5.649
the
Token the
Feature activation+3.039
shop
Token shop
Feature activation+0.000
was
Token was
Feature activation+5.652
the
Token the
Feature activation+0.000
good
Token good
Feature activation+0.000
people
Token people
Feature activation+0.000
of
Token of
Feature activation+0.000
Palestine
Token Palestine
Feature activation+0.000
,
Token,
Feature activation+4.338
innocent
Token innocent
Feature activation+0.000
men
Token men
Feature activation+0.000
,
Token,
Feature activation+0.000
women
Token women
Feature activation+0.000
and
Token and
Feature activation+0.000
argument
Token argument
Feature activation+0.632
that
Token that
Feature activation+4.025
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
worthwhile
Token worthwhile
Feature activation+0.000
for
Token for
Feature activation+4.467
the
Token the
Feature activation+0.000
Yankees
Token Yankees
Feature activation+0.000
to
Token to
Feature activation+0.000
forget
Token forget
Feature activation+3.005
about
Token about
Feature activation+5.597

INTERVAL 3.314 - 4.143
CONTAINS 0.002%

Mic
Token Mic
Feature activation+0.000
rom
Tokenrom
Feature activation+0.000
ax
Tokenax
Feature activation+7.362
Can
Token Can
Feature activation+0.000
vas
Tokenvas
Feature activation+6.691
Spark
Token Spark
Feature activation+3.950
:
Token:
Feature activation+0.147
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.623
Display
TokenDisplay
Feature activation+0.000
:
Token :
Feature activation+0.000
renters
Token renters
Feature activation+0.000
were
Token were
Feature activation+0.000
living
Token living
Feature activation+0.000
in
Token in
Feature activation+0.000
housing
Token housing
Feature activation+0.000
that
Token that
Feature activation+3.338
took
Token took
Feature activation+0.000
up
Token up
Feature activation+0.000
30
Token 30
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
Can
TokenCan
Feature activation+0.000
you
Token you
Feature activation+0.000
believe
Token believe
Feature activation+0.000
that
Token that
Feature activation+0.000
?
Token?
Feature activation+3.843
...
Token...
Feature activation+3.559
Somebody
Token Somebody
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.718
oh
Token oh
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
you
Token you
Feature activation+0.000
want
Token want
Feature activation+2.150
it
Token it
Feature activation+1.460
to
Token to
Feature activation+0.000
be
Token be
Feature activation+3.817
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
depend
Token depend
Feature activation+0.000
ant
Tokenant
Feature activation+0.000
on
Token on
Feature activation+0.000
offerings
Token offerings
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
releg
Token releg
Feature activation+0.000
ates
Tokenates
Feature activation+2.641
the
Token the
Feature activation+3.831
Mon
Token Mon
Feature activation+0.000
ter
Tokenter
Feature activation+0.000
o
Tokeno
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 2.486 - 3.314
CONTAINS 0.005%

o
Tokeno
Feature activation+0.000
.
Token.
Feature activation+3.112
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.848
Now
TokenNow
Feature activation+2.486
,
Token,
Feature activation+2.998
Mas
Token Mas
Feature activation+0.000
ah
Tokenah
Feature activation+0.000
iro
Tokeniro
Feature activation+0.000
Tanaka
Token Tanaka
Feature activation+0.000
is
Token is
Feature activation+0.000
too
Token too
Feature activation+0.000
.
Token.
Feature activation+0.949
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.337
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+2.963
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.235
Th
TokenTh
Feature activation+0.000
an
Tokenan
Feature activation+0.000
atos
Tokenatos
Feature activation+0.000
from
Token from
Feature activation+0.000
Lor
Token Lor
Feature activation+0.000
ik
Tokenik
Feature activation+0.000
Can
Token Can
Feature activation+0.000
a
Tokena
Feature activation+0.000
.
Token.
Feature activation+3.002
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.152
L
TokenL
Feature activation+0.000
or
Tokenor
Feature activation+0.000
ik
Tokenik
Feature activation+2.481
and
Token and
Feature activation+0.000
uncover
Token uncover
Feature activation+3.370
the
Token the
Feature activation+0.380
violence
Token violence
Feature activation+0.000
of
Token of
Feature activation+3.081
linguistic
Token linguistic
Feature activation+3.167
able
Token able
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
(
Token (
Feature activation+0.000
how
Tokenhow
Feature activation+0.000
able
Token able
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
And
TokenAnd
Feature activation+0.719
she
Token she
Feature activation+2.909
will
Token will
Feature activation+0.000
tell
Token tell
Feature activation+0.000
you
Token you
Feature activation+0.000
how
Token how
Feature activation+0.000
years
Token years
Feature activation+0.000

INTERVAL 1.657 - 2.486
CONTAINS 0.007%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.730
How
TokenHow
Feature activation+0.501
often
Token often
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+2.347
?
Token?
Feature activation+0.000
I
Token I
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
once
Token once
Feature activation+0.000
every
Token every
Feature activation+0.000
identified
Token identified
Feature activation+0.000
with
Token with
Feature activation+0.000
as
Token as
Feature activation+0.000
easily
Token easily
Feature activation+0.000
as
Token as
Feature activation+0.000
humans
Token humans
Feature activation+2.445
.
Token.
Feature activation+0.000
âĢ¦
Token âĢ¦
Feature activation+0.000
Could
Token Could
Feature activation+0.000
it
Token it
Feature activation+0.000
be
Token be
Feature activation+0.000
automatically
Token automatically
Feature activation+0.000
put
Token put
Feature activation+2.477
your
Token your
Feature activation+5.582
can
Token can
Feature activation+0.482
of
Token of
Feature activation+2.703
soda
Token soda
Feature activation+2.304
,
Token,
Feature activation+0.150
or
Token or
Feature activation+2.394
packet
Token packet
Feature activation+0.000
of
Token of
Feature activation+0.000
peanuts
Token peanuts
Feature activation+0.000
shop
Token shop
Feature activation+0.000
was
Token was
Feature activation+5.652
the
Token the
Feature activation+4.089
installation
Token installation
Feature activation+0.000
of
Token of
Feature activation+2.995
these
Token these
Feature activation+1.784
giant
Token giant
Feature activation+1.602
photos
Token photos
Feature activation+0.000
above
Token above
Feature activation+6.413
one
Token one
Feature activation+0.283
of
Token of
Feature activation+8.285
when
Token when
Feature activation+0.000
I
Token I
Feature activation+0.000
buy
Token buy
Feature activation+0.000
a
Token a
Feature activation+0.000
can
Token can
Feature activation+0.000
of
Token of
Feature activation+1.928
soda
Token soda
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
a
Token a
Feature activation+5.289
few
Token few
Feature activation+1.825

INTERVAL 0.829 - 1.657
CONTAINS 0.016%

60
Token 60
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+1.456
barrels
Token barrels
Feature activation+0.000
for
Token for
Feature activation+3.031
domestic
Token domestic
Feature activation+1.366
brewers
Token brewers
Feature activation+0.000
producing
Token producing
Feature activation+1.072
fewer
Token fewer
Feature activation+0.000
than
Token than
Feature activation+0.000
2
Token 2
Feature activation+0.000
care
Token care
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
grandchildren
Token grandchildren
Feature activation+0.000
?
Token?
Feature activation+0.956
How
Token How
Feature activation+0.000
does
Token does
Feature activation+0.027
a
Token a
Feature activation+0.000
government
Token government
Feature activation+0.000
official
Token official
Feature activation+0.000
ongoing
Token ongoing
Feature activation+1.403
restoration
Token restoration
Feature activation+0.000
projects
Token projects
Feature activation+0.000
.
Token.
Feature activation+1.032
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.474
One
TokenOne
Feature activation+0.134
recent
Token recent
Feature activation+4.416
addition
Token addition
Feature activation+0.000
to
Token to
Feature activation+5.649
the
Token the
Feature activation+3.039
then
Token then
Feature activation+0.137
sorry
Token sorry
Feature activation+0.000
,
Token,
Feature activation+2.414
Can
Token Can
Feature activation+0.000
't
Token't
Feature activation+0.000
say
Token say
Feature activation+1.568
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.490
User
TokenUser
Feature activation+0.000
Info
Token Info
Feature activation+0.000
:
Token:
Feature activation+1.627
ant
Tokenant
Feature activation+0.000
on
Token on
Feature activation+0.000
other
Token other
Feature activation+0.000
people
Token people
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.247
s
Tokens
Feature activation+0.000
line
Token line
Feature activation+0.000
ups
Tokenups
Feature activation+0.408
.
Token.
Feature activation+1.456
Daily
Token Daily
Feature activation+0.000

INTERVAL 0.000 - 0.829
CONTAINS 99.967%

b
Tokenb
Feature activation+0.000
arg
Tokenarg
Feature activation+0.000
at
Tokenat
Feature activation+0.000
ze
Tokenze
Feature activation+0.000
)
Token)
Feature activation+0.000
May
Token May
Feature activation+0.000
14
Token 14
Feature activation+0.000
,
Token,
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
of
Token of
Feature activation+0.000
products
Token products
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
gotten
Token gotten
Feature activation+0.000
all
Token all
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
assistance
Token assistance
Feature activation+0.000
at
Token at
Feature activation+0.000
that
Token that
Feature activation+0.000
time
Token time
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.000
also
Token also
Feature activation+0.000
technology
Token technology
Feature activation+0.000
employs
Token employs
Feature activation+0.000
a
Token a
Feature activation+0.000
high
Token high
Feature activation+0.000
-
Token-
Feature activation+0.000
sol
Tokensol
Feature activation+0.000
ids
Tokenids
Feature activation+0.000
an
Token an
Feature activation+0.000
aer
Tokenaer
Feature activation+0.000
obic
Tokenobic
Feature activation+0.000
dig
Token dig
Feature activation+0.000
s
Tokens
Feature activation+0.000
the
Token the
Feature activation+0.000
tip
Token tip
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
plastic
Token plastic
Feature activation+0.000
iceberg
Token iceberg
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
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 H11.5: (feature 15499)

TOP ACTIVATIONS
MAX = 10.025

to
Token to
Feature activation+4.443
a
Token a
Feature activation+0.000
company
Token company
Feature activation+0.000
news
Token news
Feature activation+0.000
release
Token release
Feature activation+0.000
,
Token,
Feature activation+10.025
be
Token be
Feature activation+0.000
IN
TokenIN
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
,
Token,
Feature activation+0.649
with
Token with
Feature activation+1.404
-
Token-
Feature activation+0.000
J
TokenJ
Feature activation+0.000
azeera
Tokenazeera
Feature activation+0.000
Media
Token Media
Feature activation+0.000
Networks
Token Networks
Feature activation+0.087
,
Token,
Feature activation+9.108
be
Token be
Feature activation+0.000
IN
TokenIN
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
will
Token will
Feature activation+0.000
also
Token also
Feature activation+0.000
.
Token.
Feature activation+5.242
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.146
An
TokenAn
Feature activation+1.251
affiliate
Token affiliate
Feature activation+0.000
of
Token of
Feature activation+8.856
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
J
TokenJ
Feature activation+0.000
azeera
Tokenazeera
Feature activation+0.000
Media
Token Media
Feature activation+0.000
Commission
Token Commission
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.294
guidelines
Token guidelines
Feature activation+0.000
say
Token say
Feature activation+8.595
creed
Token creed
Feature activation+0.000
can
Token can
Feature activation+0.000
include
Token include
Feature activation+4.059
non
Token non
Feature activation+0.365
-
Token-
Feature activation+1.380
the
Token the
Feature activation+0.000
freedom
Token freedom
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
press
Token press
Feature activation+0.000
;
Token ;
Feature activation+8.123
be
Token be
Feature activation+0.279
it
Token it
Feature activation+0.000
the
Token the
Feature activation+0.000
Cal
Token Cal
Feature activation+0.000
iban
Tokeniban
Feature activation+0.000
to
Token to
Feature activation+0.000
tell
Token tell
Feature activation+0.000
the
Token the
Feature activation+0.000
fascinating
Token fascinating
Feature activation+0.000
story
Token story
Feature activation+0.000
of
Token of
Feature activation+7.320
a
Token a
Feature activation+0.000
magnificent
Token magnificent
Feature activation+0.539
collaboration
Token collaboration
Feature activation+0.000
between
Token between
Feature activation+6.434
crown
Token crown
Feature activation+0.000
my
Token my
Feature activation+0.571
father
Token father
Feature activation+0.000
and
Token and
Feature activation+0.000
grandfather
Token grandfather
Feature activation+0.000
all
Token all
Feature activation+0.070
had
Token had
Feature activation+7.252
be
Token be
Feature activation+0.000
ards
Tokenards
Feature activation+1.076
âĢ¦
TokenâĢ¦
Feature activation+1.790
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Philippines
Token Philippines
Feature activation+0.000
and
Token and
Feature activation+0.000
Taiwan
Token Taiwan
Feature activation+0.000
.
Token.
Feature activation+5.242
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.146
An
TokenAn
Feature activation+1.251
affiliate
Token affiliate
Feature activation+0.000
of
Token of
Feature activation+8.856
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
s
Tokens
Feature activation+0.000
like
Token like
Feature activation+0.000
this
Token this
Feature activation+0.000
be
Token be
Feature activation+0.000
ached
Tokenached
Feature activation+0.000
Titanic
Token Titanic
Feature activation+6.496
âĢ¦
TokenâĢ¦
Feature activation+3.361
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
story
Token story
Feature activation+0.000
of
Token of
Feature activation+7.320
a
Token a
Feature activation+0.000
magnificent
Token magnificent
Feature activation+0.539
collaboration
Token collaboration
Feature activation+0.000
between
Token between
Feature activation+6.434
crown
Token crown
Feature activation+0.000
and
Token and
Feature activation+0.445
camera
Token camera
Feature activation+0.000
.
Token.
Feature activation+3.379
Ċ
TokenĊ
Feature activation+0.000
be
Token be
Feature activation+0.000
agle
Tokenagle
Feature activation+0.000
actor
Token actor
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+4.135
days
Token days
Feature activation+6.297
he
Token he
Feature activation+0.000
only
Token only
Feature activation+0.000
gets
Token gets
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.760
But
TokenBut
Feature activation+2.196
he
Token he
Feature activation+0.000
also
Token also
Feature activation+0.000
stressed
Token stressed
Feature activation+6.090
that
Token that
Feature activation+4.502
Sweden
Token Sweden
Feature activation+0.000
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
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
just
Token just
Feature activation+0.786
this
Token this
Feature activation+6.081
long
Token long
Feature activation+2.219
building
Token building
Feature activation+3.201
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
bunch
Token bunch
Feature activation+0.000
be
Token be
Feature activation+0.000
IN
TokenIN
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
will
Token will
Feature activation+0.000
also
Token also
Feature activation+0.000
broadcast
Token broadcast
Feature activation+5.918
games
Token games
Feature activation+0.000
from
Token from
Feature activation+5.238
Italy
Token Italy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
A
TokenA
Feature activation+0.000
premier
Token premier
Feature activation+0.000
portrait
Token portrait
Feature activation+0.000
photographer
Token photographer
Feature activation+0.466
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.817
C
TokenC
Feature activation+0.000
ec
Tokenec
Feature activation+0.000
il
Tokenil
Feature activation+1.484
Beat
Token Beat
Feature activation+0.000
on
Tokenon
Feature activation+3.084
effects
Token effects
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.450
"
Token"
Feature activation+1.287
If
TokenIf
Feature activation+5.702
this
Token this
Feature activation+0.000
gets
Token gets
Feature activation+0.000
more
Token more
Feature activation+0.000
parents
Token parents
Feature activation+0.000
involved
Token involved
Feature activation+0.000
crown
Token crown
Feature activation+0.000
and
Token and
Feature activation+0.445
camera
Token camera
Feature activation+0.000
.
Token.
Feature activation+3.379
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.700
A
TokenA
Feature activation+0.000
premier
Token premier
Feature activation+0.000
portrait
Token portrait
Feature activation+0.000
photographer
Token photographer
Feature activation+0.466
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.085
the
Token the
Feature activation+0.000
Philippines
Token Philippines
Feature activation+0.000
and
Token and
Feature activation+0.000
Taiwan
Token Taiwan
Feature activation+0.000
.
Token.
Feature activation+5.242
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.146
An
TokenAn
Feature activation+1.251
affiliate
Token affiliate
Feature activation+0.000
of
Token of
Feature activation+8.856
Sport
Token Sport
Feature activation+0.000
will
Token will
Feature activation+0.000
also
Token also
Feature activation+0.000
broadcast
Token broadcast
Feature activation+5.918
games
Token games
Feature activation+0.000
from
Token from
Feature activation+5.238
Italy
Token Italy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Serie
Token Serie
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
My
TokenMy
Feature activation+1.926
son
Token son
Feature activation+0.000
has
Token has
Feature activation+1.260
a
Token a
Feature activation+5.101
beard
Token beard
Feature activation+0.000
,
Token,
Feature activation+0.000
my
Token my
Feature activation+0.571
father
Token father
Feature activation+0.000
and
Token and
Feature activation+0.000

Top DFA by src position
MAX = 9.519

for
Token for
Feature activation+0.024
Top resid features:
soccer
Token soccer
Feature activation-0.034
Top resid features:
fans
Token fans
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
with
Token with
Feature activation+0.028
Top resid features:
be
Token be
Feature activation+9.519
Top resid features:
IN
TokenIN
Feature activation-0.012
Top resid features:
Sport
Token Sport
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
new
Token new
Feature activation+0.014
Top resid features:
player
Token player
Feature activation+0.031
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
company
Token company
Feature activation+0.016
Top resid features:
news
Token news
Feature activation-0.001
Top resid features:
release
Token release
Feature activation-0.016
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
be
Token be
Feature activation+8.672
Top resid features:
IN
TokenIN
Feature activation+0.005
Top resid features:
Sport
Token Sport
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
with
Token with
Feature activation+0.008
Top resid features:
its
Token its
Feature activation+0.012
Top resid features:
a
Token a
Feature activation+0.010
Top resid features:
company
Token company
Feature activation+0.010
Top resid features:
news
Token news
Feature activation+0.003
Top resid features:
release
Token release
Feature activation-0.005
Top resid features:
,
Token,
Feature activation-0.038
Top resid features:
be
Token be
Feature activation+8.604
Top resid features:
IN
TokenIN
Feature activation+0.023
Top resid features:
Sport
Token Sport
Feature activation+0.007
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
with
Token with
Feature activation-0.003
Top resid features:
its
Token its
Feature activation+0.011
Top resid features:
beliefs
Token beliefs
Feature activation+0.007
Top resid features:
required
Token required
Feature activation+0.015
Top resid features:
them
Token them
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
wear
Token wear
Feature activation+0.011
Top resid features:
be
Token be
Feature activation+5.659
Top resid features:
ards
Tokenards
Feature activation+0.009
Top resid features:
or
Token or
Feature activation+0.007
Top resid features:
long
Token long
Feature activation+0.026
Top resid features:
hair
Token hair
Feature activation+0.007
Top resid features:
.
Token.
Feature activation-0.036
Top resid features:
for
Token for
Feature activation+0.008
Top resid features:
anything
Token anything
Feature activation+0.023
Top resid features:
they
Token they
Feature activation+0.024
Top resid features:
do
Token do
Feature activation-0.008
Top resid features:
;
Token ;
Feature activation+0.099
Top resid features:
be
Token be
Feature activation+5.808
Top resid features:
it
Token it
Feature activation+0.108
Top resid features:
a
Token a
Feature activation+0.073
Top resid features:
misunderstanding
Token misunderstanding
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.038
Top resid features:
.
Token.
Feature activation-0.025
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.040
Top resid features:
Be
TokenBe
Feature activation+3.980
Top resid features:
aton
Tokenaton
Feature activation+0.327
Top resid features:
be
Token be
Feature activation+4.951
Top resid features:
qu
Tokenqu
Feature activation+0.002
Top resid features:
eat
Tokeneat
Feature activation+0.010
Top resid features:
hed
Tokenhed
Feature activation+0.019
Top resid features:
his
Token his
Feature activation+0.056
Top resid features:
archive
Token archive
Feature activation+0.003
Top resid features:
beliefs
Token beliefs
Feature activation+0.003
Top resid features:
required
Token required
Feature activation+0.007
Top resid features:
them
Token them
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.016
Top resid features:
wear
Token wear
Feature activation+0.002
Top resid features:
be
Token be
Feature activation+9.025
Top resid features:
ards
Tokenards
Feature activation+0.025
Top resid features:
or
Token or
Feature activation+0.014
Top resid features:
long
Token long
Feature activation+0.056
Top resid features:
hair
Token hair
Feature activation+0.027
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.017
Top resid features:
company
Token company
Feature activation+0.011
Top resid features:
news
Token news
Feature activation-0.006
Top resid features:
release
Token release
Feature activation-0.023
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
be
Token be
Feature activation+5.548
Top resid features:
IN
TokenIN
Feature activation+0.007
Top resid features:
Sport
Token Sport
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
with
Token with
Feature activation+0.014
Top resid features:
its
Token its
Feature activation+0.016
Top resid features:
âĢ
TokenâĢ
Feature activation+0.038
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
s
Tokens
Feature activation-0.008
Top resid features:
like
Token like
Feature activation+0.027
Top resid features:
this
Token this
Feature activation+0.091
Top resid features:
be
Token be
Feature activation+7.418
Top resid features:
ached
Tokenached
Feature activation+0.251
Top resid features:
Titanic
Token Titanic
Feature activation+0.213
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.000
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.044
Top resid features:
Be
TokenBe
Feature activation+2.595
Top resid features:
aton
Tokenaton
Feature activation+0.300
Top resid features:
be
Token be
Feature activation+5.400
Top resid features:
qu
Tokenqu
Feature activation+0.001
Top resid features:
eat
Tokeneat
Feature activation+0.006
Top resid features:
hed
Tokenhed
Feature activation+0.011
Top resid features:
his
Token his
Feature activation+0.042
Top resid features:
archive
Token archive
Feature activation+0.009
Top resid features:
are
Token are
Feature activation+0.020
Top resid features:
loving
Token loving
Feature activation+0.034
Top resid features:
our
Token our
Feature activation+0.034
Top resid features:
amazingly
Token amazingly
Feature activation+0.005
Top resid features:
talented
Token talented
Feature activation+0.015
Top resid features:
be
Token be
Feature activation+8.095
Top resid features:
agle
Tokenagle
Feature activation-0.050
Top resid features:
actor
Token actor
Feature activation-0.143
Top resid features:
.
Token.
Feature activation+0.402
Top resid features:
These
Token These
Feature activation+0.072
Top resid features:
days
Token days
Feature activation+0.083
Top resid features:
on
Tokenon
Feature activation+0.001
Top resid features:
bl
Tokenbl
Feature activation-0.003
Top resid features:
ad
Tokenad
Feature activation-0.002
Top resid features:
et
Tokenet
Feature activation+0.004
Top resid features:
that
Token that
Feature activation+0.159
Top resid features:
be
Token be
Feature activation+7.344
Top resid features:
believed
Token believed
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.148
Top resid features:
new
Token new
Feature activation+0.090
Top resid features:
regulation
Token regulation
Feature activation+0.035
Top resid features:
could
Token could
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.009
Top resid features:
Ļ
TokenĻ
Feature activation+0.011
Top resid features:
s
Tokens
Feature activation+0.019
Top resid features:
like
Token like
Feature activation+0.012
Top resid features:
this
Token this
Feature activation+0.049
Top resid features:
be
Token be
Feature activation+6.795
Top resid features:
ached
Tokenached
Feature activation+0.122
Top resid features:
Titanic
Token Titanic
Feature activation+0.360
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.054
Top resid features:
It
Token It
Feature activation+0.018
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
a
Token a
Feature activation+0.013
Top resid features:
company
Token company
Feature activation+0.007
Top resid features:
news
Token news
Feature activation-0.000
Top resid features:
release
Token release
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
be
Token be
Feature activation+3.317
Top resid features:
IN
TokenIN
Feature activation+0.018
Top resid features:
Sport
Token Sport
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.009
Top resid features:
perfect
Token perfect
Feature activation+0.006
Top resid features:
shot
Token shot
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.033
Top resid features:
Ċ
TokenĊ
Feature activation+0.045
Top resid features:
Be
TokenBe
Feature activation+5.798
Top resid features:
aton
Tokenaton
Feature activation+0.107
Top resid features:
be
Token be
Feature activation+1.216
Top resid features:
qu
Tokenqu
Feature activation+0.001
Top resid features:
eat
Tokeneat
Feature activation+0.002
Top resid features:
hed
Tokenhed
Feature activation+0.013
Top resid features:
on
Tokenon
Feature activation-0.002
Top resid features:
bl
Tokenbl
Feature activation-0.003
Top resid features:
ad
Tokenad
Feature activation-0.001
Top resid features:
et
Tokenet
Feature activation+0.002
Top resid features:
that
Token that
Feature activation+0.158
Top resid features:
be
Token be
Feature activation+7.009
Top resid features:
believed
Token believed
Feature activation+0.026
Top resid features:
the
Token the
Feature activation+0.148
Top resid features:
new
Token new
Feature activation+0.119
Top resid features:
regulation
Token regulation
Feature activation+0.067
Top resid features:
could
Token could
Feature activation-0.001
Top resid features:
perfect
Token perfect
Feature activation+0.006
Top resid features:
shot
Token shot
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.045
Top resid features:
Ċ
TokenĊ
Feature activation+0.060
Top resid features:
Be
TokenBe
Feature activation+5.916
Top resid features:
aton
Tokenaton
Feature activation+0.133
Top resid features:
be
Token be
Feature activation+0.997
Top resid features:
qu
Tokenqu
Feature activation+0.001
Top resid features:
eat
Tokeneat
Feature activation+0.003
Top resid features:
hed
Tokenhed
Feature activation+0.016
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
company
Token company
Feature activation+0.009
Top resid features:
news
Token news
Feature activation+0.002
Top resid features:
release
Token release
Feature activation-0.023
Top resid features:
,
Token,
Feature activation-0.017
Top resid features:
be
Token be
Feature activation+4.145
Top resid features:
IN
TokenIN
Feature activation+0.004
Top resid features:
Sport
Token Sport
Feature activation-0.008
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
with
Token with
Feature activation+0.009
Top resid features:
its
Token its
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
company
Token company
Feature activation+0.004
Top resid features:
news
Token news
Feature activation+0.001
Top resid features:
release
Token release
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
be
Token be
Feature activation+3.525
Top resid features:
IN
TokenIN
Feature activation+0.012
Top resid features:
Sport
Token Sport
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
with
Token with
Feature activation+0.004
Top resid features:
its
Token its
Feature activation+0.012
Top resid features:
beliefs
Token beliefs
Feature activation+0.003
Top resid features:
required
Token required
Feature activation+0.006
Top resid features:
them
Token them
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
wear
Token wear
Feature activation+0.003
Top resid features:
be
Token be
Feature activation+7.100
Top resid features:
ards
Tokenards
Feature activation+0.039
Top resid features:
or
Token or
Feature activation+0.011
Top resid features:
long
Token long
Feature activation+0.056
Top resid features:
hair
Token hair
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.06

Head 2: 0.05

Head 3: 0.06

Head 4: 0.04

Head 5: 0.45

Head 6: 0.06

Head 7: 0.05

Head 8: 0.06

Head 9: 0.05

Head 10: 0.04

Head 11: 0.05

Positive logits

be7.39

Be5.76

Be5.73

be5.31

BE4.72

being3.55

Bey3.40

been3.12

remain3.11

being3.01

Being3.00

been2.98

Being2.96

Beaver2.96

become2.93

BE2.79

beware2.71

beet2.64

Been2.61

suffice2.58

Negative logits

maxwell-3.19

Did-2.64

ashes-2.61

ITNESS-2.59

latable-2.38

eatures-2.35

ilateral-2.32

/+-2.30

infeld-2.27

miah-2.27

ollow-2.27

rency-2.26

resents-2.21

Didn-2.16

guiActiveUn-2.16

itte-2.16

imaru-2.16

ourced-2.15

Turns-2.13

jong-2.12

INTERVAL 9.022 - 10.025
CONTAINS 0.000%

to
Token to
Feature activation+4.443
a
Token a
Feature activation+0.000
company
Token company
Feature activation+0.000
news
Token news
Feature activation+0.000
release
Token release
Feature activation+0.000
,
Token,
Feature activation+10.025
be
Token be
Feature activation+0.000
IN
TokenIN
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
,
Token,
Feature activation+0.649
with
Token with
Feature activation+1.404
-
Token-
Feature activation+0.000
J
TokenJ
Feature activation+0.000
azeera
Tokenazeera
Feature activation+0.000
Media
Token Media
Feature activation+0.000
Networks
Token Networks
Feature activation+0.087
,
Token,
Feature activation+9.108
be
Token be
Feature activation+0.000
IN
TokenIN
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
will
Token will
Feature activation+0.000
also
Token also
Feature activation+0.000

INTERVAL 8.020 - 9.022
CONTAINS 0.000%

the
Token the
Feature activation+0.000
freedom
Token freedom
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
press
Token press
Feature activation+0.000
;
Token ;
Feature activation+8.123
be
Token be
Feature activation+0.279
it
Token it
Feature activation+0.000
the
Token the
Feature activation+0.000
Cal
Token Cal
Feature activation+0.000
iban
Tokeniban
Feature activation+0.000
.
Token.
Feature activation+5.242
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.146
An
TokenAn
Feature activation+1.251
affiliate
Token affiliate
Feature activation+0.000
of
Token of
Feature activation+8.856
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
J
TokenJ
Feature activation+0.000
azeera
Tokenazeera
Feature activation+0.000
Media
Token Media
Feature activation+0.000
Commission
Token Commission
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.294
guidelines
Token guidelines
Feature activation+0.000
say
Token say
Feature activation+8.595
creed
Token creed
Feature activation+0.000
can
Token can
Feature activation+0.000
include
Token include
Feature activation+4.059
non
Token non
Feature activation+0.365
-
Token-
Feature activation+1.380

INTERVAL 7.017 - 8.020
CONTAINS 0.000%

Philippines
Token Philippines
Feature activation+0.000
and
Token and
Feature activation+0.000
Taiwan
Token Taiwan
Feature activation+0.000
.
Token.
Feature activation+5.242
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.146
An
TokenAn
Feature activation+1.251
affiliate
Token affiliate
Feature activation+0.000
of
Token of
Feature activation+8.856
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
my
Token my
Feature activation+0.571
father
Token father
Feature activation+0.000
and
Token and
Feature activation+0.000
grandfather
Token grandfather
Feature activation+0.000
all
Token all
Feature activation+0.070
had
Token had
Feature activation+7.252
be
Token be
Feature activation+0.000
ards
Tokenards
Feature activation+1.076
âĢ¦
TokenâĢ¦
Feature activation+1.790
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
to
Token to
Feature activation+0.000
tell
Token tell
Feature activation+0.000
the
Token the
Feature activation+0.000
fascinating
Token fascinating
Feature activation+0.000
story
Token story
Feature activation+0.000
of
Token of
Feature activation+7.320
a
Token a
Feature activation+0.000
magnificent
Token magnificent
Feature activation+0.539
collaboration
Token collaboration
Feature activation+0.000
between
Token between
Feature activation+6.434
crown
Token crown
Feature activation+0.000

INTERVAL 6.015 - 7.017
CONTAINS 0.001%

s
Tokens
Feature activation+0.000
like
Token like
Feature activation+0.000
this
Token this
Feature activation+0.000
be
Token be
Feature activation+0.000
ached
Tokenached
Feature activation+0.000
Titanic
Token Titanic
Feature activation+6.496
âĢ¦
TokenâĢ¦
Feature activation+3.361
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
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
just
Token just
Feature activation+0.786
this
Token this
Feature activation+6.081
long
Token long
Feature activation+2.219
building
Token building
Feature activation+3.201
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
bunch
Token bunch
Feature activation+0.000
story
Token story
Feature activation+0.000
of
Token of
Feature activation+7.320
a
Token a
Feature activation+0.000
magnificent
Token magnificent
Feature activation+0.539
collaboration
Token collaboration
Feature activation+0.000
between
Token between
Feature activation+6.434
crown
Token crown
Feature activation+0.000
and
Token and
Feature activation+0.445
camera
Token camera
Feature activation+0.000
.
Token.
Feature activation+3.379
Ċ
TokenĊ
Feature activation+0.000
be
Token be
Feature activation+0.000
agle
Tokenagle
Feature activation+0.000
actor
Token actor
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+4.135
days
Token days
Feature activation+6.297
he
Token he
Feature activation+0.000
only
Token only
Feature activation+0.000
gets
Token gets
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.760
But
TokenBut
Feature activation+2.196
he
Token he
Feature activation+0.000
also
Token also
Feature activation+0.000
stressed
Token stressed
Feature activation+6.090
that
Token that
Feature activation+4.502
Sweden
Token Sweden
Feature activation+0.000
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.000

INTERVAL 5.012 - 6.015
CONTAINS 0.001%

A
TokenA
Feature activation+0.000
premier
Token premier
Feature activation+0.000
portrait
Token portrait
Feature activation+0.000
photographer
Token photographer
Feature activation+0.466
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.817
C
TokenC
Feature activation+0.000
ec
Tokenec
Feature activation+0.000
il
Tokenil
Feature activation+1.484
Beat
Token Beat
Feature activation+0.000
on
Tokenon
Feature activation+3.084
effects
Token effects
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.450
"
Token"
Feature activation+1.287
If
TokenIf
Feature activation+5.702
this
Token this
Feature activation+0.000
gets
Token gets
Feature activation+0.000
more
Token more
Feature activation+0.000
parents
Token parents
Feature activation+0.000
involved
Token involved
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
will
Token will
Feature activation+0.000
also
Token also
Feature activation+0.000
broadcast
Token broadcast
Feature activation+5.918
games
Token games
Feature activation+0.000
from
Token from
Feature activation+5.238
Italy
Token Italy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Serie
Token Serie
Feature activation+0.000
be
Token be
Feature activation+0.000
IN
TokenIN
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
will
Token will
Feature activation+0.000
also
Token also
Feature activation+0.000
broadcast
Token broadcast
Feature activation+5.918
games
Token games
Feature activation+0.000
from
Token from
Feature activation+5.238
Italy
Token Italy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
My
TokenMy
Feature activation+1.926
son
Token son
Feature activation+0.000
has
Token has
Feature activation+1.260
a
Token a
Feature activation+5.101
beard
Token beard
Feature activation+0.000
,
Token,
Feature activation+0.000
my
Token my
Feature activation+0.571
father
Token father
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 4.010 - 5.012
CONTAINS 0.002%

secured
Token secured
Feature activation+1.642
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
distribution
Token distribution
Feature activation+0.000
rights
Token rights
Feature activation+0.000
for
Token for
Feature activation+4.953
Premier
Token Premier
Feature activation+0.000
League
Token League
Feature activation+1.497
games
Token games
Feature activation+0.000
for
Token for
Feature activation+0.776
the
Token the
Feature activation+0.000
town
Token town
Feature activation+0.000
.
Token.
Feature activation+4.923
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.960
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+4.443
a
Token a
Feature activation+0.000
company
Token company
Feature activation+0.000
news
Token news
Feature activation+0.000
release
Token release
Feature activation+0.000
,
Token,
Feature activation+10.025
ed
Tokened
Feature activation+1.024
on
Token on
Feature activation+0.400
IR
Token IR
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.288
>
Token>
Feature activation+4.091
Get
Token Get
Feature activation+0.000
your
Token your
Feature activation+0.000
fastest
Token fastest
Feature activation+0.000
TE
Token TE
Feature activation+0.000
s
Tokens
Feature activation+0.556
cause
Token cause
Feature activation+0.000
we
Token we
Feature activation+0.000
did
Token did
Feature activation+0.000
some
Token some
Feature activation+0.000
good
Token good
Feature activation+0.918
things
Token things
Feature activation+4.135
,
Token,
Feature activation+1.210
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.855
,"
Token,"
Feature activation+0.000
T
Token T
Feature activation+0.000
with
Token with
Feature activation+0.000
riding
Token riding
Feature activation+0.000
for
Token for
Feature activation+0.000
women
Token women
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+4.901
not
Token not
Feature activation+4.166
for
Token for
Feature activation+1.956
men
Token men
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.007 - 4.010
CONTAINS 0.003%

default
Token default
Feature activation+0.000
ed
Tokened
Feature activation+1.024
on
Token on
Feature activation+0.400
IR
Token IR
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.288
>
Token>
Feature activation+4.091
Get
Token Get
Feature activation+0.000
your
Token your
Feature activation+0.000
fastest
Token fastest
Feature activation+0.000
TE
Token TE
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Most
TokenMost
Feature activation+0.000
likely
Token likely
Feature activation+0.436
,
Token,
Feature activation+3.210
the
Token the
Feature activation+0.114
amp
Token amp
Feature activation+0.000
het
Tokenhet
Feature activation+0.000
amines
Tokenamines
Feature activation+0.053
in
Token in
Feature activation+1.963
funded
Token funded
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
believes
Token believes
Feature activation+3.419
in
Token in
Feature activation+0.114
the
Token the
Feature activation+0.000
Dro
Token Dro
Feature activation+0.000
pp
Tokenpp
Feature activation+0.000
i
Tokeni
Feature activation+0.000
IN
TokenIN
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
,
Token,
Feature activation+0.649
with
Token with
Feature activation+1.404
its
Token its
Feature activation+0.680
partner
Token partner
Feature activation+3.188
MP
Token MP
Feature activation+0.000
&
Token &
Feature activation+0.000
Silva
Token Silva
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
with
Token with
Feature activation+0.000
kindred
Token kindred
Feature activation+0.000
spirits
Token spirits
Feature activation+0.000
.
Token.
Feature activation+3.644
Be
Token Be
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
to
Token to
Feature activation+0.000
hear
Token hear
Feature activation+0.000

INTERVAL 2.005 - 3.007
CONTAINS 0.007%

,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
z
Token z
Feature activation+0.000
en
Tokenen
Feature activation+2.164
or
Token or
Feature activation+0.000
goodness
Token goodness
Feature activation+2.873
being
Token being
Feature activation+0.000
the
Token the
Feature activation+0.000
compassionate
Token compassionate
Feature activation+0.000
service
Token service
Feature activation+0.000
piece
Token piece
Feature activation+0.000
s
Tokens
Feature activation+0.256
always
Token always
Feature activation+0.855
a
Token a
Feature activation+0.000
question
Token question
Feature activation+0.000
of
Token of
Feature activation+0.020
whether
Token whether
Feature activation+2.684
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
grow
Token grow
Feature activation+2.835
a
Token a
Feature activation+2.782
better
Token better
Feature activation+3.321
iov
Tokeniov
Feature activation+0.000
anni
Tokenanni
Feature activation+0.000
Es
Token Es
Feature activation+0.000
pos
Tokenpos
Feature activation+0.000
ito
Tokenito
Feature activation+0.000
,
Token,
Feature activation+2.337
50
Token 50
Feature activation+0.000
,
Token,
Feature activation+0.000
once
Token once
Feature activation+0.000
a
Token a
Feature activation+0.000
chassis
Token chassis
Feature activation+0.000
home
Token home
Feature activation+0.000
run
Token run
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
diversity
Token diversity
Feature activation+0.000
standpoint
Token standpoint
Feature activation+2.390
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.124
Car
TokenCar
Feature activation+0.000
le
Tokenle
Feature activation+0.000
Kit
Token Kit
Feature activation+0.000
Kat
TokenKat
Feature activation+0.000
or
Token or
Feature activation+0.000
Loll
Token Loll
Feature activation+0.000
ipop
Tokenipop
Feature activation+1.388
build
Token build
Feature activation+2.914
.
Token.
Feature activation+0.976
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Initial
TokenInitial
Feature activation+0.000
impressions
Token impressions
Feature activation+0.000

INTERVAL 1.002 - 2.005
CONTAINS 0.019%

first
Token first
Feature activation+0.000
son
Token son
Feature activation+0.000
off
Token off
Feature activation+0.000
ing
Tokening
Feature activation+0.000
himself
Token himself
Feature activation+0.000
.
Token.
Feature activation+1.394
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
hope
Token hope
Feature activation+0.000
she
Token she
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
elaborate
Token elaborate
Feature activation+0.000
traps
Token traps
Feature activation+0.189
too
Token too
Feature activation+3.065
.
Token.
Feature activation+1.524
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.477
Def
TokenDef
Feature activation+0.000
end
Tokenend
Feature activation+0.000
:
Token:
Feature activation+0.110
the
Token the
Feature activation+0.000
map
Token map
Feature activation+0.000
own
Token own
Feature activation+0.000
conversion
Token conversion
Feature activation+0.000
story
Token story
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.378
Dou
TokenDou
Feature activation+0.000
glas
Tokenglas
Feature activation+0.000
M
Token M
Feature activation+0.000
.
Token.
Feature activation+0.000
Be
Token Be
Feature activation+0.000
t
Tokent
Feature activation+0.000
blame
Token blame
Feature activation+0.000
herself
Token herself
Feature activation+0.000
for
Token for
Feature activation+0.000
it
Token it
Feature activation+0.299
.
Token.
Feature activation+1.182
Perhaps
Token Perhaps
Feature activation+0.000
my
Token my
Feature activation+0.000
recently
Token recently
Feature activation+0.000
ex
Token ex
Feature activation+0.000
-
Token-
Feature activation+0.000
district
Token district
Feature activation+0.000
.
Token.
Feature activation+0.223
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.924
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+1.898
Cele
TokenCele
Feature activation+0.000
br
Tokenbr
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
will
Token will
Feature activation+0.000
not
Token not
Feature activation+0.000

INTERVAL 0.000 - 1.002
CONTAINS 99.968%

jumped
Token jumped
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
battle
Token battle
Feature activation+0.000
along
Token along
Feature activation+0.000
with
Token with
Feature activation+0.000
Phil
Token Phil
Feature activation+0.000
Mic
Token Mic
Feature activation+0.000
kel
Tokenkel
Feature activation+0.000
son
Tokenson
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Asked
TokenAsked
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
if
Token if
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
had
Token had
Feature activation+0.000
considered
Token considered
Feature activation+0.000
what
Token what
Feature activation+0.000
life
Token life
Feature activation+0.000
to
Token to
Feature activation+0.000
8
Token 8
Feature activation+0.000
84
Token84
Feature activation+0.000
MHz
Token MHz
Feature activation+0.000
wireless
Token wireless
Feature activation+0.000
signals
Token signals
Feature activation+0.000
components
Token components
Feature activation+0.000
of
Token of
Feature activation+0.000
sleep
Token sleep
Feature activation+0.000
believed
Token believed
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Care
TokenCare
Feature activation+0.000
y
Tokeny
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
longtime
Token longtime
Feature activation+0.000
Libertarian
Token Libertarian
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
lush
Token lush
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
mel
Tokenmel
Feature activation+0.000
odies
Tokenodies
Feature activation+0.000
crafted
Token crafted
Feature activation+0.000
by
Token by
Feature activation+0.000
Chuck
Token Chuck
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
Beh
Token Beh
Feature activation+0.000
ring
Tokenring
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 H11.5: (feature 980)

TOP ACTIVATIONS
MAX = 12.343

Are
Token Are
Feature activation+12.105
Was
Token Was
Feature activation+0.000
ps
Tokenps
Feature activation+0.492
?
Token?
Feature activation+10.455
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+12.343
Was
TokenWas
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
near
Token near
Feature activation+3.907
the
Token the
Feature activation+0.826
home
Token home
Feature activation+0.000
.
Token.
Feature activation+7.508
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.856
How
TokenHow
Feature activation+7.424
Serious
Token Serious
Feature activation+2.969
Are
Token Are
Feature activation+12.105
Was
Token Was
Feature activation+0.000
ps
Tokenps
Feature activation+0.492
?
Token?
Feature activation+10.455
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+12.343
prey
Token prey
Feature activation+0.000
for
Token for
Feature activation+11.650
both
Token both
Feature activation+10.544
developing
Token developing
Feature activation+10.505
and
Token and
Feature activation+1.580
mature
Token mature
Feature activation+11.889
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
.
Token.
Feature activation+8.567
Contrary
Token Contrary
Feature activation+0.000
to
Token to
Feature activation+1.666
and
Token and
Feature activation+0.999
spiders
Token spiders
Feature activation+0.000
provide
Token provide
Feature activation+7.983
ample
Token ample
Feature activation+2.379
prey
Token prey
Feature activation+0.000
for
Token for
Feature activation+11.650
both
Token both
Feature activation+10.544
developing
Token developing
Feature activation+10.505
and
Token and
Feature activation+1.580
mature
Token mature
Feature activation+11.889
was
Token was
Feature activation+0.000
beliefs
Token beliefs
Feature activation+0.000
,
Token,
Feature activation+11.018
nests
Token nests
Feature activation+0.000
left
Token left
Feature activation+0.000
behind
Token behind
Feature activation+0.000
by
Token by
Feature activation+11.414
was
Token was
Feature activation+0.000
p
Tokenp
Feature activation+0.878
populations
Token populations
Feature activation+0.000
that
Token that
Feature activation+0.000
die
Token die
Feature activation+0.000
not
Token not
Feature activation+7.019
reused
Token reused
Feature activation+0.000
by
Token by
Feature activation+11.103
subsequent
Token subsequent
Feature activation+10.967
generations
Token generations
Feature activation+0.000
of
Token of
Feature activation+11.363
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
.
Token.
Feature activation+7.508
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.856
months
Token months
Feature activation+0.000
are
Token are
Feature activation+0.000
generally
Token generally
Feature activation+0.000
not
Token not
Feature activation+7.019
reused
Token reused
Feature activation+0.000
by
Token by
Feature activation+11.103
subsequent
Token subsequent
Feature activation+10.967
generations
Token generations
Feature activation+0.000
of
Token of
Feature activation+11.363
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
popular
Token popular
Feature activation+0.000
,
Token,
Feature activation+0.002
but
Token but
Feature activation+0.000
inaccurate
Token inaccurate
Feature activation+0.000
beliefs
Token beliefs
Feature activation+0.000
,
Token,
Feature activation+11.018
nests
Token nests
Feature activation+0.000
left
Token left
Feature activation+0.000
behind
Token behind
Feature activation+0.000
by
Token by
Feature activation+11.414
was
Token was
Feature activation+0.000
are
Token are
Feature activation+0.000
generally
Token generally
Feature activation+0.000
not
Token not
Feature activation+7.019
reused
Token reused
Feature activation+0.000
by
Token by
Feature activation+11.103
subsequent
Token subsequent
Feature activation+10.967
generations
Token generations
Feature activation+0.000
of
Token of
Feature activation+11.363
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
.
Token.
Feature activation+7.508
spiders
Token spiders
Feature activation+0.000
provide
Token provide
Feature activation+7.983
ample
Token ample
Feature activation+2.379
prey
Token prey
Feature activation+0.000
for
Token for
Feature activation+11.650
both
Token both
Feature activation+10.544
developing
Token developing
Feature activation+10.505
and
Token and
Feature activation+1.580
mature
Token mature
Feature activation+11.889
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
provide
Token provide
Feature activation+7.983
ample
Token ample
Feature activation+2.379
prey
Token prey
Feature activation+0.000
for
Token for
Feature activation+11.650
both
Token both
Feature activation+10.544
developing
Token developing
Feature activation+10.505
and
Token and
Feature activation+1.580
mature
Token mature
Feature activation+11.889
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
.
Token.
Feature activation+8.567
How
TokenHow
Feature activation+7.424
Serious
Token Serious
Feature activation+2.969
Are
Token Are
Feature activation+12.105
Was
Token Was
Feature activation+0.000
ps
Tokenps
Feature activation+0.492
?
Token?
Feature activation+10.455
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+12.343
Was
TokenWas
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
near
Token near
Feature activation+3.907
seeking
Token seeking
Feature activation+2.699
sources
Token sources
Feature activation+0.000
food
Token food
Feature activation+0.000
.
Token.
Feature activation+6.721
Properties
Token Properties
Feature activation+0.000
with
Token with
Feature activation+9.535
abundant
Token abundant
Feature activation+9.048
insects
Token insects
Feature activation+0.000
and
Token and
Feature activation+0.999
spiders
Token spiders
Feature activation+0.000
provide
Token provide
Feature activation+7.983
sources
Token sources
Feature activation+0.000
food
Token food
Feature activation+0.000
.
Token.
Feature activation+6.721
Properties
Token Properties
Feature activation+0.000
with
Token with
Feature activation+9.535
abundant
Token abundant
Feature activation+9.048
insects
Token insects
Feature activation+0.000
and
Token and
Feature activation+0.999
spiders
Token spiders
Feature activation+0.000
provide
Token provide
Feature activation+7.983
ample
Token ample
Feature activation+2.379
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Jonathan
TokenJonathan
Feature activation+0.000
Joseph
Token Joseph
Feature activation+0.000
(
Token (
Feature activation+9.000
B
TokenB
Feature activation+0.000
ath
Tokenath
Feature activation+0.000
Rugby
Token Rugby
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
developing
Token developing
Feature activation+10.505
and
Token and
Feature activation+1.580
mature
Token mature
Feature activation+11.889
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
.
Token.
Feature activation+8.567
Contrary
Token Contrary
Feature activation+0.000
to
Token to
Feature activation+1.666
popular
Token popular
Feature activation+0.000
,
Token,
Feature activation+0.002
but
Token but
Feature activation+0.000
with
Token with
Feature activation+9.535
abundant
Token abundant
Feature activation+9.048
insects
Token insects
Feature activation+0.000
and
Token and
Feature activation+0.999
spiders
Token spiders
Feature activation+0.000
provide
Token provide
Feature activation+7.983
ample
Token ample
Feature activation+2.379
prey
Token prey
Feature activation+0.000
for
Token for
Feature activation+11.650
both
Token both
Feature activation+10.544
developing
Token developing
Feature activation+10.505
of
Token of
Feature activation+11.363
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
.
Token.
Feature activation+7.508
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.856
How
TokenHow
Feature activation+7.424
Serious
Token Serious
Feature activation+2.969
Are
Token Are
Feature activation+12.105
Was
Token Was
Feature activation+0.000
ps
Tokenps
Feature activation+0.492
subsequent
Token subsequent
Feature activation+10.967
generations
Token generations
Feature activation+0.000
of
Token of
Feature activation+11.363
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
.
Token.
Feature activation+7.508
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.856
How
TokenHow
Feature activation+7.424
Serious
Token Serious
Feature activation+2.969
Are
Token Are
Feature activation+12.105
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
.
Token.
Feature activation+7.508
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.856
How
TokenHow
Feature activation+7.424
Serious
Token Serious
Feature activation+2.969
Are
Token Are
Feature activation+12.105
Was
Token Was
Feature activation+0.000
ps
Tokenps
Feature activation+0.492
?
Token?
Feature activation+10.455

Top DFA by src position
MAX = 13.009

Ċ
TokenĊ
Feature activation+0.053
Top resid features:
Ċ
TokenĊ
Feature activation+0.071
Top resid features:
How
TokenHow
Feature activation-0.004
Top resid features:
Serious
Token Serious
Feature activation+0.008
Top resid features:
Are
Token Are
Feature activation-0.009
Top resid features:
Was
Token Was
Feature activation+9.832
Top resid features:
ps
Tokenps
Feature activation-0.007
Top resid features:
?
Token?
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.041
Top resid features:
Ċ
TokenĊ
Feature activation+0.070
Top resid features:
Was
TokenWas
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
regularly
Token regularly
Feature activation+0.002
Top resid features:
emptied
Token emptied
Feature activation+0.001
Top resid features:
also
Token also
Feature activation+0.002
Top resid features:
attract
Token attract
Feature activation-0.006
Top resid features:
was
Token was
Feature activation+5.470
Top resid features:
ps
Tokenps
Feature activation+0.027
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
are
Token are
Feature activation+0.009
Top resid features:
seeking
Token seeking
Feature activation+0.002
Top resid features:
sources
Token sources
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
regularly
Token regularly
Feature activation+0.008
Top resid features:
emptied
Token emptied
Feature activation+0.001
Top resid features:
also
Token also
Feature activation+0.005
Top resid features:
attract
Token attract
Feature activation-0.033
Top resid features:
was
Token was
Feature activation+13.009
Top resid features:
ps
Tokenps
Feature activation+0.036
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
are
Token are
Feature activation+0.033
Top resid features:
seeking
Token seeking
Feature activation+0.006
Top resid features:
sources
Token sources
Feature activation+0.008
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
regularly
Token regularly
Feature activation+0.014
Top resid features:
emptied
Token emptied
Feature activation+0.003
Top resid features:
also
Token also
Feature activation+0.011
Top resid features:
attract
Token attract
Feature activation-0.026
Top resid features:
was
Token was
Feature activation+12.612
Top resid features:
ps
Tokenps
Feature activation+0.030
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
are
Token are
Feature activation+0.026
Top resid features:
seeking
Token seeking
Feature activation+0.024
Top resid features:
sources
Token sources
Feature activation+0.019
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
regularly
Token regularly
Feature activation+0.011
Top resid features:
emptied
Token emptied
Feature activation+0.001
Top resid features:
also
Token also
Feature activation+0.004
Top resid features:
attract
Token attract
Feature activation-0.005
Top resid features:
was
Token was
Feature activation+8.336
Top resid features:
ps
Tokenps
Feature activation+0.019
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
are
Token are
Feature activation+0.021
Top resid features:
seeking
Token seeking
Feature activation+0.010
Top resid features:
sources
Token sources
Feature activation+0.010
Top resid features:
for
Token for
Feature activation+0.022
Top resid features:
both
Token both
Feature activation+0.025
Top resid features:
developing
Token developing
Feature activation-0.007
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
mature
Token mature
Feature activation-0.012
Top resid features:
was
Token was
Feature activation+5.350
Top resid features:
ps
Tokenps
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Contrary
Token Contrary
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
popular
Token popular
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
regularly
Token regularly
Feature activation+0.008
Top resid features:
emptied
Token emptied
Feature activation+0.001
Top resid features:
also
Token also
Feature activation+0.004
Top resid features:
attract
Token attract
Feature activation-0.002
Top resid features:
was
Token was
Feature activation+4.586
Top resid features:
ps
Tokenps
Feature activation+0.016
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
are
Token are
Feature activation+0.014
Top resid features:
seeking
Token seeking
Feature activation+0.012
Top resid features:
sources
Token sources
Feature activation+0.010
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
regularly
Token regularly
Feature activation+0.012
Top resid features:
emptied
Token emptied
Feature activation+0.007
Top resid features:
also
Token also
Feature activation+0.011
Top resid features:
attract
Token attract
Feature activation-0.013
Top resid features:
was
Token was
Feature activation+7.960
Top resid features:
ps
Tokenps
Feature activation+0.032
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
are
Token are
Feature activation+0.019
Top resid features:
seeking
Token seeking
Feature activation+0.007
Top resid features:
sources
Token sources
Feature activation+0.012
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
both
Token both
Feature activation+0.019
Top resid features:
developing
Token developing
Feature activation+0.012
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
mature
Token mature
Feature activation+0.005
Top resid features:
was
Token was
Feature activation+5.861
Top resid features:
ps
Tokenps
Feature activation+0.018
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Contrary
Token Contrary
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
popular
Token popular
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
regularly
Token regularly
Feature activation+0.011
Top resid features:
emptied
Token emptied
Feature activation+0.003
Top resid features:
also
Token also
Feature activation+0.008
Top resid features:
attract
Token attract
Feature activation-0.047
Top resid features:
was
Token was
Feature activation+11.612
Top resid features:
ps
Tokenps
Feature activation+0.037
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
are
Token are
Feature activation+0.025
Top resid features:
seeking
Token seeking
Feature activation+0.021
Top resid features:
sources
Token sources
Feature activation+0.016
Top resid features:
and
Token and
Feature activation+0.012
Top resid features:
regularly
Token regularly
Feature activation+0.017
Top resid features:
emptied
Token emptied
Feature activation+0.003
Top resid features:
also
Token also
Feature activation+0.008
Top resid features:
attract
Token attract
Feature activation-0.028
Top resid features:
was
Token was
Feature activation+11.693
Top resid features:
ps
Tokenps
Feature activation+0.022
Top resid features:
that
Token that
Feature activation-0.008
Top resid features:
are
Token are
Feature activation+0.029
Top resid features:
seeking
Token seeking
Feature activation+0.012
Top resid features:
sources
Token sources
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.151
Top resid features:
Ċ
TokenĊ
Feature activation+0.138
Top resid features:
How
TokenHow
Feature activation-0.024
Top resid features:
Serious
Token Serious
Feature activation+0.024
Top resid features:
Are
Token Are
Feature activation-0.010
Top resid features:
Was
Token Was
Feature activation+7.516
Top resid features:
ps
Tokenps
Feature activation+0.038
Top resid features:
?
Token?
Feature activation+0.071
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Was
TokenWas
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.024
Top resid features:
regularly
Token regularly
Feature activation+0.041
Top resid features:
emptied
Token emptied
Feature activation+0.007
Top resid features:
also
Token also
Feature activation+0.010
Top resid features:
attract
Token attract
Feature activation-0.011
Top resid features:
was
Token was
Feature activation+10.464
Top resid features:
ps
Tokenps
Feature activation+0.059
Top resid features:
that
Token that
Feature activation+0.005
Top resid features:
are
Token are
Feature activation+0.032
Top resid features:
seeking
Token seeking
Feature activation+0.026
Top resid features:
sources
Token sources
Feature activation+0.020
Top resid features:
and
Token and
Feature activation+0.017
Top resid features:
regularly
Token regularly
Feature activation+0.036
Top resid features:
emptied
Token emptied
Feature activation+0.004
Top resid features:
also
Token also
Feature activation+0.007
Top resid features:
attract
Token attract
Feature activation-0.012
Top resid features:
was
Token was
Feature activation+10.121
Top resid features:
ps
Tokenps
Feature activation+0.048
Top resid features:
that
Token that
Feature activation+0.007
Top resid features:
are
Token are
Feature activation+0.046
Top resid features:
seeking
Token seeking
Feature activation+0.024
Top resid features:
sources
Token sources
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
James
TokenJames
Feature activation-0.008
Top resid features:
Haskell
Token Haskell
Feature activation+0.002
Top resid features:
(
Token (
Feature activation+0.004
Top resid features:
Was
TokenWas
Feature activation+11.142
Top resid features:
ps
Tokenps
Feature activation-0.002
Top resid features:
)
Token)
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
Jonathan
TokenJonathan
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
regularly
Token regularly
Feature activation+0.005
Top resid features:
emptied
Token emptied
Feature activation+0.002
Top resid features:
also
Token also
Feature activation+0.003
Top resid features:
attract
Token attract
Feature activation-0.028
Top resid features:
was
Token was
Feature activation+4.752
Top resid features:
ps
Tokenps
Feature activation+0.021
Top resid features:
that
Token that
Feature activation-0.002
Top resid features:
are
Token are
Feature activation+0.006
Top resid features:
seeking
Token seeking
Feature activation+0.005
Top resid features:
sources
Token sources
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
regularly
Token regularly
Feature activation+0.016
Top resid features:
emptied
Token emptied
Feature activation+0.003
Top resid features:
also
Token also
Feature activation+0.009
Top resid features:
attract
Token attract
Feature activation-0.034
Top resid features:
was
Token was
Feature activation+8.977
Top resid features:
ps
Tokenps
Feature activation+0.040
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
are
Token are
Feature activation+0.027
Top resid features:
seeking
Token seeking
Feature activation+0.028
Top resid features:
sources
Token sources
Feature activation+0.008
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
regularly
Token regularly
Feature activation+0.008
Top resid features:
emptied
Token emptied
Feature activation+0.001
Top resid features:
also
Token also
Feature activation+0.006
Top resid features:
attract
Token attract
Feature activation-0.016
Top resid features:
was
Token was
Feature activation+3.053
Top resid features:
ps
Tokenps
Feature activation+0.008
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
are
Token are
Feature activation+0.008
Top resid features:
seeking
Token seeking
Feature activation+0.005
Top resid features:
sources
Token sources
Feature activation-0.000
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
regularly
Token regularly
Feature activation+0.003
Top resid features:
emptied
Token emptied
Feature activation+0.002
Top resid features:
also
Token also
Feature activation+0.001
Top resid features:
attract
Token attract
Feature activation-0.019
Top resid features:
was
Token was
Feature activation+2.642
Top resid features:
ps
Tokenps
Feature activation+0.016
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
are
Token are
Feature activation+0.003
Top resid features:
seeking
Token seeking
Feature activation+0.003
Top resid features:
sources
Token sources
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
regularly
Token regularly
Feature activation+0.005
Top resid features:
emptied
Token emptied
Feature activation+0.002
Top resid features:
also
Token also
Feature activation+0.005
Top resid features:
attract
Token attract
Feature activation-0.057
Top resid features:
was
Token was
Feature activation+3.161
Top resid features:
ps
Tokenps
Feature activation+0.019
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
are
Token are
Feature activation+0.019
Top resid features:
seeking
Token seeking
Feature activation+0.004
Top resid features:
sources
Token sources
Feature activation+0.009
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.04

Head 3: 0.06

Head 4: 0.04

Head 5: 0.44

Head 6: 0.06

Head 7: 0.05

Head 8: 0.07

Head 9: 0.07

Head 10: 0.05

Head 11: 0.04

Positive logits

Was7.09

was6.95

Was6.88

WAS5.91

was5.90

wasn5.16

Were5.07

were5.01

Were4.63

were4.54

Had4.26

weren4.24

remained3.95

Did3.89

Had3.80

had3.77

didn3.70

Did3.66

hadn3.66

had3.56

Negative logits

ettle-2.70

ovember-2.67

externalToEVAOnly-2.52

fuse-2.32

perty-2.24

lict-2.16

srf-2.16

preferably-2.13

Prepare-2.11

Flavoring-2.10

ruciating-2.10

morrow-2.10

amaru-2.04

soever-2.02

Metatron-1.99

owship-1.98

tein-1.96

pour-1.96

sofar-1.94

agy-1.94

INTERVAL 11.109 - 12.343
CONTAINS 0.001%

and
Token and
Feature activation+0.999
spiders
Token spiders
Feature activation+0.000
provide
Token provide
Feature activation+7.983
ample
Token ample
Feature activation+2.379
prey
Token prey
Feature activation+0.000
for
Token for
Feature activation+11.650
both
Token both
Feature activation+10.544
developing
Token developing
Feature activation+10.505
and
Token and
Feature activation+1.580
mature
Token mature
Feature activation+11.889
was
Token was
Feature activation+0.000
beliefs
Token beliefs
Feature activation+0.000
,
Token,
Feature activation+11.018
nests
Token nests
Feature activation+0.000
left
Token left
Feature activation+0.000
behind
Token behind
Feature activation+0.000
by
Token by
Feature activation+11.414
was
Token was
Feature activation+0.000
p
Tokenp
Feature activation+0.878
populations
Token populations
Feature activation+0.000
that
Token that
Feature activation+0.000
die
Token die
Feature activation+0.000
Are
Token Are
Feature activation+12.105
Was
Token Was
Feature activation+0.000
ps
Tokenps
Feature activation+0.492
?
Token?
Feature activation+10.455
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+12.343
Was
TokenWas
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
near
Token near
Feature activation+3.907
the
Token the
Feature activation+0.826
home
Token home
Feature activation+0.000
not
Token not
Feature activation+7.019
reused
Token reused
Feature activation+0.000
by
Token by
Feature activation+11.103
subsequent
Token subsequent
Feature activation+10.967
generations
Token generations
Feature activation+0.000
of
Token of
Feature activation+11.363
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
.
Token.
Feature activation+7.508
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.856
.
Token.
Feature activation+7.508
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.856
How
TokenHow
Feature activation+7.424
Serious
Token Serious
Feature activation+2.969
Are
Token Are
Feature activation+12.105
Was
Token Was
Feature activation+0.000
ps
Tokenps
Feature activation+0.492
?
Token?
Feature activation+10.455
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+12.343

INTERVAL 9.875 - 11.109
CONTAINS 0.001%

How
TokenHow
Feature activation+7.424
Serious
Token Serious
Feature activation+2.969
Are
Token Are
Feature activation+12.105
Was
Token Was
Feature activation+0.000
ps
Tokenps
Feature activation+0.492
?
Token?
Feature activation+10.455
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+12.343
Was
TokenWas
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
near
Token near
Feature activation+3.907
popular
Token popular
Feature activation+0.000
,
Token,
Feature activation+0.002
but
Token but
Feature activation+0.000
inaccurate
Token inaccurate
Feature activation+0.000
beliefs
Token beliefs
Feature activation+0.000
,
Token,
Feature activation+11.018
nests
Token nests
Feature activation+0.000
left
Token left
Feature activation+0.000
behind
Token behind
Feature activation+0.000
by
Token by
Feature activation+11.414
was
Token was
Feature activation+0.000
spiders
Token spiders
Feature activation+0.000
provide
Token provide
Feature activation+7.983
ample
Token ample
Feature activation+2.379
prey
Token prey
Feature activation+0.000
for
Token for
Feature activation+11.650
both
Token both
Feature activation+10.544
developing
Token developing
Feature activation+10.505
and
Token and
Feature activation+1.580
mature
Token mature
Feature activation+11.889
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
are
Token are
Feature activation+0.000
generally
Token generally
Feature activation+0.000
not
Token not
Feature activation+7.019
reused
Token reused
Feature activation+0.000
by
Token by
Feature activation+11.103
subsequent
Token subsequent
Feature activation+10.967
generations
Token generations
Feature activation+0.000
of
Token of
Feature activation+11.363
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
.
Token.
Feature activation+7.508
months
Token months
Feature activation+0.000
are
Token are
Feature activation+0.000
generally
Token generally
Feature activation+0.000
not
Token not
Feature activation+7.019
reused
Token reused
Feature activation+0.000
by
Token by
Feature activation+11.103
subsequent
Token subsequent
Feature activation+10.967
generations
Token generations
Feature activation+0.000
of
Token of
Feature activation+11.363
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000

INTERVAL 8.640 - 9.875
CONTAINS 0.000%

)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Jonathan
TokenJonathan
Feature activation+0.000
Joseph
Token Joseph
Feature activation+0.000
(
Token (
Feature activation+9.000
B
TokenB
Feature activation+0.000
ath
Tokenath
Feature activation+0.000
Rugby
Token Rugby
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
seeking
Token seeking
Feature activation+2.699
sources
Token sources
Feature activation+0.000
food
Token food
Feature activation+0.000
.
Token.
Feature activation+6.721
Properties
Token Properties
Feature activation+0.000
with
Token with
Feature activation+9.535
abundant
Token abundant
Feature activation+9.048
insects
Token insects
Feature activation+0.000
and
Token and
Feature activation+0.999
spiders
Token spiders
Feature activation+0.000
provide
Token provide
Feature activation+7.983
sources
Token sources
Feature activation+0.000
food
Token food
Feature activation+0.000
.
Token.
Feature activation+6.721
Properties
Token Properties
Feature activation+0.000
with
Token with
Feature activation+9.535
abundant
Token abundant
Feature activation+9.048
insects
Token insects
Feature activation+0.000
and
Token and
Feature activation+0.999
spiders
Token spiders
Feature activation+0.000
provide
Token provide
Feature activation+7.983
ample
Token ample
Feature activation+2.379

INTERVAL 7.406 - 8.640
CONTAINS 0.001%

with
Token with
Feature activation+9.535
abundant
Token abundant
Feature activation+9.048
insects
Token insects
Feature activation+0.000
and
Token and
Feature activation+0.999
spiders
Token spiders
Feature activation+0.000
provide
Token provide
Feature activation+7.983
ample
Token ample
Feature activation+2.379
prey
Token prey
Feature activation+0.000
for
Token for
Feature activation+11.650
both
Token both
Feature activation+10.544
developing
Token developing
Feature activation+10.505
developing
Token developing
Feature activation+10.505
and
Token and
Feature activation+1.580
mature
Token mature
Feature activation+11.889
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
.
Token.
Feature activation+8.567
Contrary
Token Contrary
Feature activation+0.000
to
Token to
Feature activation+1.666
popular
Token popular
Feature activation+0.000
,
Token,
Feature activation+0.002
but
Token but
Feature activation+0.000
subsequent
Token subsequent
Feature activation+10.967
generations
Token generations
Feature activation+0.000
of
Token of
Feature activation+11.363
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
.
Token.
Feature activation+7.508
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.856
How
TokenHow
Feature activation+7.424
Serious
Token Serious
Feature activation+2.969
Are
Token Are
Feature activation+12.105
of
Token of
Feature activation+11.363
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
.
Token.
Feature activation+7.508
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.856
How
TokenHow
Feature activation+7.424
Serious
Token Serious
Feature activation+2.969
Are
Token Are
Feature activation+12.105
Was
Token Was
Feature activation+0.000
ps
Tokenps
Feature activation+0.492
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
.
Token.
Feature activation+7.508
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.856
How
TokenHow
Feature activation+7.424
Serious
Token Serious
Feature activation+2.969
Are
Token Are
Feature activation+12.105
Was
Token Was
Feature activation+0.000
ps
Tokenps
Feature activation+0.492
?
Token?
Feature activation+10.455

INTERVAL 6.172 - 7.406
CONTAINS 0.001%

inging
Tokeninging
Feature activation+0.000
insects
Token insects
Feature activation+0.000
are
Token are
Feature activation+0.000
still
Token still
Feature activation+0.000
banned
Token banned
Feature activation+0.000
.
Token.
Feature activation+6.260
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.745
-----
Token-----
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
read
Token read
Feature activation+0.000
more
Token more
Feature activation+0.000
about
Token about
Feature activation+7.135
gardening
Token gardening
Feature activation+0.000
,
Token,
Feature activation+0.000
see
Token see
Feature activation+0.000
the
Token the
Feature activation+0.307
Monitor
Token Monitor
Feature activation+0.000
and
Token and
Feature activation+0.000
our
Token our
Feature activation+1.694
lively
Token lively
Feature activation+0.000
gardening
Token gardening
Feature activation+0.000
blog
Token blog
Feature activation+0.357
,
Token,
Feature activation+6.305
Dig
Token Dig
Feature activation+0.040
gin
Tokengin
Feature activation+2.066
'
Token'
Feature activation+4.436
It
Token It
Feature activation+0.000
.
Token.
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.300
seeking
Token seeking
Feature activation+2.699
sources
Token sources
Feature activation+0.000
food
Token food
Feature activation+0.000
.
Token.
Feature activation+6.721
Properties
Token Properties
Feature activation+0.000
with
Token with
Feature activation+9.535
abundant
Token abundant
Feature activation+9.048
insects
Token insects
Feature activation+0.000
and
Token and
Feature activation+0.999
cold
Token cold
Feature activation+0.000
weather
Token weather
Feature activation+0.000
months
Token months
Feature activation+0.000
are
Token are
Feature activation+0.000
generally
Token generally
Feature activation+0.000
not
Token not
Feature activation+7.019
reused
Token reused
Feature activation+0.000
by
Token by
Feature activation+11.103
subsequent
Token subsequent
Feature activation+10.967
generations
Token generations
Feature activation+0.000
of
Token of
Feature activation+11.363

INTERVAL 4.937 - 6.172
CONTAINS 0.000%

are
Token are
Feature activation+0.000
still
Token still
Feature activation+0.000
banned
Token banned
Feature activation+0.000
.
Token.
Feature activation+6.260
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.745
-----
Token-----
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
read
Token read
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
250
Token 250
Feature activation+0.000
inmates
Token inmates
Feature activation+0.000
,
Token,
Feature activation+6.011
but
Token but
Feature activation+0.000
you
Token you
Feature activation+2.613
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000

INTERVAL 3.703 - 4.937
CONTAINS 0.000%

gardening
Token gardening
Feature activation+0.000
blog
Token blog
Feature activation+0.357
,
Token,
Feature activation+6.305
Dig
Token Dig
Feature activation+0.040
gin
Tokengin
Feature activation+2.066
'
Token'
Feature activation+4.436
It
Token It
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.000
of
Token of
Feature activation+0.853
these
Token these
Feature activation+0.000
bombing
Token bombing
Feature activation+0.000
the
Token the
Feature activation+0.000
Middle
Token Middle
Feature activation+0.000
East
Token East
Feature activation+0.000
;
Token;
Feature activation+0.430
you
Token you
Feature activation+4.704
just
Token just
Feature activation+2.159
have
Token have
Feature activation+0.000
internal
Token internal
Feature activation+0.000
ised
Tokenised
Feature activation+0.000
misogyny
Token misogyny
Feature activation+0.000
?
Token?
Feature activation+10.455
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+12.343
Was
TokenWas
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
near
Token near
Feature activation+3.907
the
Token the
Feature activation+0.826
home
Token home
Feature activation+0.000
can
Token can
Feature activation+0.161
ruin
Token ruin
Feature activation+2.349
outdoor
Token outdoor
Feature activation+1.241
Paul
Token Paul
Feature activation+0.000
Ant
Token Ant
Feature activation+0.000
oine
Tokenoine
Feature activation+1.593
,
Token,
Feature activation+0.000
28
Token 28
Feature activation+0.000
,
Token,
Feature activation+4.403
was
Token was
Feature activation+0.000
arrested
Token arrested
Feature activation+0.000
Sunday
Token Sunday
Feature activation+0.000
in
Token in
Feature activation+0.000
San
Token San
Feature activation+0.000

INTERVAL 2.469 - 3.703
CONTAINS 0.002%

wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
enough
Token enough
Feature activation+0.000
,
Token,
Feature activation+2.947
apparently
Token apparently
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Here
TokenHere
Feature activation+0.000
of
Token of
Feature activation+2.980
a
Token a
Feature activation+2.018
sum
Token sum
Feature activation+0.000
ÂŃ
TokenÂŃ
Feature activation+0.000
mary
Tokenmary
Feature activation+0.000
of
Token of
Feature activation+2.818
the
Token the
Feature activation+1.831
ori
Token ori
Feature activation+0.000
ÂŃ
TokenÂŃ
Feature activation+0.000
gin
Tokengin
Feature activation+0.000
ÂŃ
TokenÂŃ
Feature activation+0.000
covered
Token covered
Feature activation+0.000
and
Token and
Feature activation+0.000
regularly
Token regularly
Feature activation+0.000
emptied
Token emptied
Feature activation+0.000
also
Token also
Feature activation+0.000
attract
Token attract
Feature activation+3.200
was
Token was
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.300
seeking
Token seeking
Feature activation+2.699
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
say
Token say
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
were
Tokenwere
Feature activation+2.629
to
Token to
Feature activation+0.000
/
Token/
Feature activation+0.000
would
Tokenwould
Feature activation+0.000
.
Token.
Feature activation+0.148
âĢ
TokenâĢ
Feature activation+0.000
museum
Token museum
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
reason
Token reason
Feature activation+0.000
you
Token you
Feature activation+3.403
and
Token and
Feature activation+0.000
your
Token your
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000

INTERVAL 1.234 - 2.469
CONTAINS 0.006%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
National
Token National
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
Air
Token Air
Feature activation+0.000
Force
Token Force
Feature activation+1.753
were
Token were
Feature activation+0.000
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.000
468
Token468
Feature activation+0.000
aircraft
Token aircraft
Feature activation+0.000
abundant
Token abundant
Feature activation+9.048
insects
Token insects
Feature activation+0.000
and
Token and
Feature activation+0.999
spiders
Token spiders
Feature activation+0.000
provide
Token provide
Feature activation+7.983
ample
Token ample
Feature activation+2.379
prey
Token prey
Feature activation+0.000
for
Token for
Feature activation+11.650
both
Token both
Feature activation+10.544
developing
Token developing
Feature activation+10.505
and
Token and
Feature activation+1.580
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
answer
Token answer
Feature activation+0.000
the
Token the
Feature activation+0.000
question
Token question
Feature activation+0.000
,
Token,
Feature activation+2.311
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.491
Todd
Token Todd
Feature activation+0.000
noted
Token noted
Feature activation+0.000
.
Token.
Feature activation+0.000
getting
Token getting
Feature activation+0.000
off
Token off
Feature activation+0.000
the
Token the
Feature activation+0.000
ground
Token ground
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+1.263
flourishing
Token flourishing
Feature activation+0.000
.
Token.
Feature activation+0.000
Blockchain
Token Blockchain
Feature activation+0.000
crowdfunding
Token crowdfunding
Feature activation+0.000
might
Token might
Feature activation+0.000
a
Token a
Feature activation+2.018
sum
Token sum
Feature activation+0.000
ÂŃ
TokenÂŃ
Feature activation+0.000
mary
Tokenmary
Feature activation+0.000
of
Token of
Feature activation+2.818
the
Token the
Feature activation+1.831
ori
Token ori
Feature activation+0.000
ÂŃ
TokenÂŃ
Feature activation+0.000
gin
Tokengin
Feature activation+0.000
ÂŃ
TokenÂŃ
Feature activation+0.000
al
Tokenal
Feature activation+0.000

INTERVAL 0.000 - 1.234
CONTAINS 99.989%

,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
likely
Token likely
Feature activation+0.000
that
Token that
Feature activation+0.000
Gareth
Token Gareth
Feature activation+0.000
Barry
Token Barry
Feature activation+0.000
will
Token will
Feature activation+0.000
bounds
Token bounds
Feature activation+0.000
of
Token of
Feature activation+0.000
good
Token good
Feature activation+0.000
taste
Token taste
Feature activation+0.000
).
Token).
Feature activation+0.000
This
Token This
Feature activation+0.000
theory
Token theory
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
supported
Token supported
Feature activation+0.000
by
Token by
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
CLOSE
TokenCLOSE
Feature activation+0.000
We
Token We
Feature activation+0.000
talked
Token talked
Feature activation+0.000
to
Token to
Feature activation+0.000
experts
Token experts
Feature activation+0.000
and
Token and
Feature activation+0.000
got
Token got
Feature activation+0.000
their
Token their
Feature activation+0.000
advice
Token advice
Feature activation+0.000
for
Token for
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
Nations
Token Nations
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
step
Token step
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
time
Token time
Feature activation+0.000
and
Token and
Feature activation+0.000
effort
Token effort
Feature activation+0.000
to
Token to
Feature activation+0.000
mine
Token mine
Feature activation+0.000
its
Token its
Feature activation+0.000
treasure
Token treasure
Feature activation+0.000
trove
Token trove
Feature activation+0.000
of
Token of
Feature activation+0.000
av
Token av
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 H11.5: (feature 19681)

TOP ACTIVATIONS
MAX = 13.349

At
TokenAt
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
55
Token55
Feature activation+0.000
am
Tokenam
Feature activation+0.000
a
Token a
Feature activation+13.349
do
Token do
Feature activation+0.000
orman
Tokenorman
Feature activation+0.000
approached
Token approached
Feature activation+1.718
the
Token the
Feature activation+6.778
couple
Token couple
Feature activation+0.000
bra
Tokenbra
Feature activation+0.000
ith
Tokenith
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+11.546
couple
Token couple
Feature activation+0.000
remained
Token remained
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+2.395
bar
Token bar
Feature activation+0.000
SM
TokenSM
Feature activation+0.000
Rs
TokenRs
Feature activation+0.000
).
Token).
Feature activation+9.117
Earlier
Token Earlier
Feature activation+7.304
this
Token this
Feature activation+0.000
year
Token year
Feature activation+11.036
,
Token,
Feature activation+10.530
the
Token the
Feature activation+5.039
Do
Token Do
Feature activation+0.000
E
TokenE
Feature activation+1.260
signed
Token signed
Feature activation+0.220
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.855
the
Token the
Feature activation+10.845
pair
Token pair
Feature activation+0.000
exiting
Token exiting
Feature activation+0.000
the
Token the
Feature activation+2.980
bar
Token bar
Feature activation+0.000
quickly
Token quickly
Feature activation+0.000
bra
Tokenbra
Feature activation+0.000
ith
Tokenith
Feature activation+0.000
is
Token is
Feature activation+0.000
seen
Token seen
Feature activation+0.000
questioning
Token questioning
Feature activation+0.000
the
Token the
Feature activation+10.769
do
Token do
Feature activation+0.000
orman
Tokenorman
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.597
street
Token street
Feature activation+0.000
Rs
TokenRs
Feature activation+0.000
).
Token).
Feature activation+9.117
Earlier
Token Earlier
Feature activation+7.304
this
Token this
Feature activation+0.000
year
Token year
Feature activation+11.036
,
Token,
Feature activation+10.530
the
Token the
Feature activation+5.039
Do
Token Do
Feature activation+0.000
E
TokenE
Feature activation+1.260
signed
Token signed
Feature activation+0.220
a
Token a
Feature activation+0.000
modular
Token modular
Feature activation+0.000
reactors
Token reactors
Feature activation+0.000
(
Token (
Feature activation+0.000
SM
TokenSM
Feature activation+0.000
Rs
TokenRs
Feature activation+0.000
).
Token).
Feature activation+9.117
Earlier
Token Earlier
Feature activation+7.304
this
Token this
Feature activation+0.000
year
Token year
Feature activation+11.036
,
Token,
Feature activation+10.530
the
Token the
Feature activation+5.039
s
Tokens
Feature activation+0.000
best
Token best
Feature activation+0.000
fighters
Token fighters
Feature activation+0.000
and
Token and
Feature activation+0.000
bombers
Token bombers
Feature activation+0.000
,
Token,
Feature activation+8.481
and
Token and
Feature activation+0.112
O
Token O
Feature activation+0.000
sp
Tokensp
Feature activation+0.000
rey
Tokenrey
Feature activation+0.000
hybrid
Token hybrid
Feature activation+0.000
in
Token in
Feature activation+0.000
1984
Token 1984
Feature activation+0.464
History
Token History
Feature activation+1.797
Japan
Token Japan
Feature activation+0.497
Name
Token Name
Feature activation+6.305
:
Token:
Feature activation+8.348
H
Token H
Feature activation+0.000
ime
Tokenime
Feature activation+2.327
y
Tokeny
Feature activation+0.464
uri
Tokenuri
Feature activation+6.060
Mar
Token Mar
Feature activation+0.000
its
Token its
Feature activation+1.158
SM
Token SM
Feature activation+0.000
R
TokenR
Feature activation+0.000
design
Token design
Feature activation+0.000
,
Token,
Feature activation+0.630
with
Token with
Feature activation+7.913
industrial
Token industrial
Feature activation+0.000
partners
Token partners
Feature activation+3.586
expected
Token expected
Feature activation+0.000
at
Token at
Feature activation+2.542
least
Token least
Feature activation+0.000
partners
Token partners
Feature activation+3.586
expected
Token expected
Feature activation+0.000
at
Token at
Feature activation+2.542
least
Token least
Feature activation+0.000
to
Token to
Feature activation+0.000
match
Token match
Feature activation+7.382
the
Token the
Feature activation+3.865
federal
Token federal
Feature activation+0.000
investment
Token investment
Feature activation+0.000
.
Token.
Feature activation+9.644
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+0.000
US
Token US
Feature activation+0.000
base
Token base
Feature activation+0.000
in
Token in
Feature activation+0.000
Okinawa
Token Okinawa
Feature activation+0.000
,
Token,
Feature activation+7.376
Japan
Token Japan
Feature activation+0.000
.
Token.
Feature activation+4.568
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.755
The
TokenThe
Feature activation+0.817
reactors
Token reactors
Feature activation+0.000
(
Token (
Feature activation+0.000
SM
TokenSM
Feature activation+0.000
Rs
TokenRs
Feature activation+0.000
).
Token).
Feature activation+9.117
Earlier
Token Earlier
Feature activation+7.304
this
Token this
Feature activation+0.000
year
Token year
Feature activation+11.036
,
Token,
Feature activation+10.530
the
Token the
Feature activation+5.039
Do
Token Do
Feature activation+0.000
az
Tokenaz
Feature activation+0.744
in
Token in
Feature activation+0.000
1981
Token 1981
Feature activation+0.371
Ref
Token Ref
Feature activation+0.000
it
Tokenit
Feature activation+0.000
:
Token:
Feature activation+6.980
After
Token After
Feature activation+1.342
a
Token a
Feature activation+0.000
fire
Token fire
Feature activation+0.000
onboard
Token onboard
Feature activation+2.612
June
Token June
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.636
area
Token area
Feature activation+0.000
twice
Token twice
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+6.945
couple
Token couple
Feature activation+0.000
is
Token is
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.247
bar
Token bar
Feature activation+0.000
am
Tokenam
Feature activation+0.000
a
Token a
Feature activation+13.349
do
Token do
Feature activation+0.000
orman
Tokenorman
Feature activation+0.000
approached
Token approached
Feature activation+1.718
the
Token the
Feature activation+6.778
couple
Token couple
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.862
corner
Token corner
Feature activation+0.000
and
Token and
Feature activation+2.451
Okinawa
Token Okinawa
Feature activation+0.000
,
Token,
Feature activation+7.376
Japan
Token Japan
Feature activation+0.000
.
Token.
Feature activation+4.568
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.755
The
TokenThe
Feature activation+0.817
purpose
Token purpose
Feature activation+0.000
is
Token is
Feature activation+0.000
officially
Token officially
Feature activation+0.000
for
Token for
Feature activation+0.000
an
Tokenan
Feature activation+1.250
in
Token in
Feature activation+0.000
1984
Token 1984
Feature activation+0.464
History
Token History
Feature activation+1.797
Japan
Token Japan
Feature activation+0.497
Name
Token Name
Feature activation+6.305
:
Token:
Feature activation+8.348
H
Token H
Feature activation+0.000
ime
Tokenime
Feature activation+2.327
y
Tokeny
Feature activation+0.464
uri
Tokenuri
Feature activation+6.060
com
Tokencom
Feature activation+0.000
.
Token.
Feature activation+0.000
au
Tokenau
Feature activation+0.000
.
Token.
Feature activation+2.744
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.303
Some
TokenSome
Feature activation+0.000
of
Token of
Feature activation+4.302
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pl
TokenPl
Feature activation+0.000
á
Tokená
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ás
Tokenás
Feature activation+0.000
/
Token /
Feature activation+6.084
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+4.322
pl
Tokenpl
Feature activation+0.000
É
TokenÉ
Feature activation+0.000
Ķ
TokenĶ
Feature activation+0.000

Top DFA by src position
MAX = 14.643

cheek
Token cheek
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
A
TokenA
Feature activation+0.014
Top resid features:
do
Token do
Feature activation+14.643
Top resid features:
orman
Tokenorman
Feature activation-0.010
Top resid features:
is
Token is
Feature activation+0.011
Top resid features:
seen
Token seen
Feature activation-0.004
Top resid features:
walking
Token walking
Feature activation+0.002
Top resid features:
through
Token through
Feature activation+0.003
Top resid features:
cheek
Token cheek
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
A
TokenA
Feature activation+0.021
Top resid features:
do
Token do
Feature activation+12.887
Top resid features:
orman
Tokenorman
Feature activation-0.019
Top resid features:
is
Token is
Feature activation+0.016
Top resid features:
seen
Token seen
Feature activation-0.009
Top resid features:
walking
Token walking
Feature activation-0.001
Top resid features:
through
Token through
Feature activation+0.001
Top resid features:
supporting
Token supporting
Feature activation+0.005
Top resid features:
advanced
Token advanced
Feature activation+0.005
Top resid features:
reactor
Token reactor
Feature activation+0.010
Top resid features:
technology
Token technology
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
Do
Token Do
Feature activation+11.817
Top resid features:
E
TokenE
Feature activation+0.120
Top resid features:
is
Token is
Feature activation+0.007
Top resid features:
also
Token also
Feature activation+0.004
Top resid features:
providing
Token providing
Feature activation+0.015
Top resid features:
funds
Token funds
Feature activation+0.016
Top resid features:
2
Token 2
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
55
Token55
Feature activation-0.000
Top resid features:
am
Tokenam
Feature activation+0.006
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
do
Token do
Feature activation+7.284
Top resid features:
orman
Tokenorman
Feature activation+0.010
Top resid features:
approached
Token approached
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
couple
Token couple
Feature activation-0.028
Top resid features:
in
Token in
Feature activation+0.011
Top resid features:
cheek
Token cheek
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
A
TokenA
Feature activation+0.017
Top resid features:
do
Token do
Feature activation+7.140
Top resid features:
orman
Tokenorman
Feature activation-0.028
Top resid features:
is
Token is
Feature activation+0.012
Top resid features:
seen
Token seen
Feature activation-0.003
Top resid features:
walking
Token walking
Feature activation-0.007
Top resid features:
through
Token through
Feature activation+0.001
Top resid features:
supporting
Token supporting
Feature activation+0.004
Top resid features:
advanced
Token advanced
Feature activation+0.005
Top resid features:
reactor
Token reactor
Feature activation+0.000
Top resid features:
technology
Token technology
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
Do
Token Do
Feature activation+11.309
Top resid features:
E
TokenE
Feature activation+0.102
Top resid features:
is
Token is
Feature activation+0.007
Top resid features:
also
Token also
Feature activation+0.004
Top resid features:
providing
Token providing
Feature activation+0.012
Top resid features:
funds
Token funds
Feature activation+0.010
Top resid features:
supporting
Token supporting
Feature activation+0.003
Top resid features:
advanced
Token advanced
Feature activation+0.005
Top resid features:
reactor
Token reactor
Feature activation+0.003
Top resid features:
technology
Token technology
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
Do
Token Do
Feature activation+9.917
Top resid features:
E
TokenE
Feature activation+0.036
Top resid features:
is
Token is
Feature activation+0.008
Top resid features:
also
Token also
Feature activation+0.006
Top resid features:
providing
Token providing
Feature activation+0.009
Top resid features:
funds
Token funds
Feature activation+0.005
Top resid features:
rifles
Token rifles
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ŀ
TokenĿ
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
Denis
Token Denis
Feature activation-0.062
Top resid features:
Do
Token Do
Feature activation+9.427
Top resid features:
herty
Tokenherty
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.032
Top resid features:
national
Token national
Feature activation+0.012
Top resid features:
co
Token co
Feature activation+0.020
Top resid features:
-
Token-
Feature activation+0.009
Top resid features:
you
Token you
Feature activation+0.001
Top resid features:
say
Token say
Feature activation+0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.000
Top resid features:
M
TokenM
Feature activation-0.066
Top resid features:
V
TokenV
Feature activation-0.037
Top resid features:
Do
Token Do
Feature activation+7.594
Top resid features:
ña
Tokenña
Feature activation-0.019
Top resid features:
P
Token P
Feature activation-0.010
Top resid features:
az
Tokenaz
Feature activation+0.015
Top resid features:
Do
Token Do
Feature activation+2.504
Top resid features:
ña
Tokenña
Feature activation+0.002
Top resid features:
supporting
Token supporting
Feature activation+0.004
Top resid features:
advanced
Token advanced
Feature activation+0.007
Top resid features:
reactor
Token reactor
Feature activation+0.008
Top resid features:
technology
Token technology
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
Do
Token Do
Feature activation+6.691
Top resid features:
E
TokenE
Feature activation+0.044
Top resid features:
is
Token is
Feature activation+0.007
Top resid features:
also
Token also
Feature activation+0.003
Top resid features:
providing
Token providing
Feature activation+0.016
Top resid features:
funds
Token funds
Feature activation+0.007
Top resid features:
supporting
Token supporting
Feature activation+0.003
Top resid features:
advanced
Token advanced
Feature activation+0.007
Top resid features:
reactor
Token reactor
Feature activation+0.011
Top resid features:
technology
Token technology
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
Do
Token Do
Feature activation+5.144
Top resid features:
E
TokenE
Feature activation+0.053
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
also
Token also
Feature activation+0.002
Top resid features:
providing
Token providing
Feature activation+0.008
Top resid features:
funds
Token funds
Feature activation+0.009
Top resid features:
rifles
Token rifles
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
Denis
Token Denis
Feature activation-0.037
Top resid features:
Do
Token Do
Feature activation+8.438
Top resid features:
herty
Tokenherty
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
national
Token national
Feature activation+0.008
Top resid features:
co
Token co
Feature activation+0.007
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
supporting
Token supporting
Feature activation+0.003
Top resid features:
advanced
Token advanced
Feature activation+0.002
Top resid features:
reactor
Token reactor
Feature activation+0.009
Top resid features:
technology
Token technology
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
Do
Token Do
Feature activation+8.278
Top resid features:
E
TokenE
Feature activation+0.071
Top resid features:
is
Token is
Feature activation+0.017
Top resid features:
also
Token also
Feature activation+0.008
Top resid features:
providing
Token providing
Feature activation+0.017
Top resid features:
funds
Token funds
Feature activation+0.023
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.085
Top resid features:
Ren
Token Ren
Feature activation-0.086
Top resid features:
amed
Tokenamed
Feature activation+0.004
Top resid features:
:
Token:
Feature activation+0.078
Top resid features:
Do
Token Do
Feature activation+8.408
Top resid features:
ña
Tokenña
Feature activation+0.024
Top resid features:
P
Token P
Feature activation-0.010
Top resid features:
az
Tokenaz
Feature activation+0.024
Top resid features:
in
Token in
Feature activation+0.031
Top resid features:
1981
Token 1981
Feature activation+0.029
Top resid features:
cheek
Token cheek
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
A
TokenA
Feature activation+0.034
Top resid features:
do
Token do
Feature activation+8.394
Top resid features:
orman
Tokenorman
Feature activation-0.013
Top resid features:
is
Token is
Feature activation+0.039
Top resid features:
seen
Token seen
Feature activation-0.013
Top resid features:
walking
Token walking
Feature activation-0.003
Top resid features:
through
Token through
Feature activation-0.002
Top resid features:
2
Token 2
Feature activation+0.009
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
55
Token55
Feature activation+0.000
Top resid features:
am
Tokenam
Feature activation-0.016
Top resid features:
a
Token a
Feature activation+0.015
Top resid features:
do
Token do
Feature activation+5.167
Top resid features:
orman
Tokenorman
Feature activation+0.006
Top resid features:
approached
Token approached
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
couple
Token couple
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
rifles
Token rifles
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
Denis
Token Denis
Feature activation+0.006
Top resid features:
Do
Token Do
Feature activation+8.002
Top resid features:
herty
Tokenherty
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
national
Token national
Feature activation+0.006
Top resid features:
co
Token co
Feature activation+0.008
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
say
Token say
Feature activation+0.006
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.014
Top resid features:
M
TokenM
Feature activation-0.045
Top resid features:
V
TokenV
Feature activation-0.045
Top resid features:
Do
Token Do
Feature activation+6.424
Top resid features:
ña
Tokenña
Feature activation-0.058
Top resid features:
P
Token P
Feature activation-0.003
Top resid features:
az
Tokenaz
Feature activation+0.014
Top resid features:
Do
Token Do
Feature activation+1.872
Top resid features:
ña
Tokenña
Feature activation-0.007
Top resid features:
rifles
Token rifles
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation-0.010
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
Denis
Token Denis
Feature activation+0.017
Top resid features:
Do
Token Do
Feature activation+7.481
Top resid features:
herty
Tokenherty
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
national
Token national
Feature activation+0.011
Top resid features:
co
Token co
Feature activation+0.012
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.038
Top resid features:
phrase
Token phrase
Feature activation+0.005
Top resid features:
sounded
Token sounded
Feature activation+0.001
Top resid features:
like
Token like
Feature activation-0.002
Top resid features:
/
Token /
Feature activation+0.010
Top resid features:
do
Tokendo
Feature activation+7.348
Top resid features:
:
Token:
Feature activation+0.027
Top resid features:
âĢ
TokenâĢ
Feature activation-0.025
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
ma
Tokenma
Feature activation+0.073
Top resid features:
É
TokenÉ
Feature activation+0.021
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.04

Head 3: 0.04

Head 4: 0.05

Head 5: 0.42

Head 6: 0.08

Head 7: 0.04

Head 8: 0.07

Head 9: 0.06

Head 10: 0.05

Head 11: 0.04

Positive logits

Do8.02

Do7.06

do7.04

do6.57

DO5.86

Did5.02

did4.88

Does4.83

Doing4.75

does4.72

doing4.58

does4.56

did4.51

doing4.46

DO4.44

done4.38

Done3.76

done3.76

Did3.73

DID3.59

Negative logits

dayName-3.03

packed-2.42

advis-2.35

iHUD-2.27

anchester-2.19

licks-2.11

ounters-2.08

urated-2.05

immer-2.05

icket-2.04

../-2.04

swick-2.03

uve-1.99

sails-1.96

uffs-1.95

quickShipAvailable-1.95

aved-1.94

witch-1.92

unks-1.90

EStream-1.90

INTERVAL 12.015 - 13.349
CONTAINS 0.000%

At
TokenAt
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
55
Token55
Feature activation+0.000
am
Tokenam
Feature activation+0.000
a
Token a
Feature activation+13.349
do
Token do
Feature activation+0.000
orman
Tokenorman
Feature activation+0.000
approached
Token approached
Feature activation+1.718
the
Token the
Feature activation+6.778
couple
Token couple
Feature activation+0.000

INTERVAL 10.680 - 12.015
CONTAINS 0.000%

bra
Tokenbra
Feature activation+0.000
ith
Tokenith
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+11.546
couple
Token couple
Feature activation+0.000
remained
Token remained
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+2.395
bar
Token bar
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.855
the
Token the
Feature activation+10.845
pair
Token pair
Feature activation+0.000
exiting
Token exiting
Feature activation+0.000
the
Token the
Feature activation+2.980
bar
Token bar
Feature activation+0.000
quickly
Token quickly
Feature activation+0.000
bra
Tokenbra
Feature activation+0.000
ith
Tokenith
Feature activation+0.000
is
Token is
Feature activation+0.000
seen
Token seen
Feature activation+0.000
questioning
Token questioning
Feature activation+0.000
the
Token the
Feature activation+10.769
do
Token do
Feature activation+0.000
orman
Tokenorman
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+1.597
street
Token street
Feature activation+0.000
SM
TokenSM
Feature activation+0.000
Rs
TokenRs
Feature activation+0.000
).
Token).
Feature activation+9.117
Earlier
Token Earlier
Feature activation+7.304
this
Token this
Feature activation+0.000
year
Token year
Feature activation+11.036
,
Token,
Feature activation+10.530
the
Token the
Feature activation+5.039
Do
Token Do
Feature activation+0.000
E
TokenE
Feature activation+1.260
signed
Token signed
Feature activation+0.220

INTERVAL 9.345 - 10.680
CONTAINS 0.000%

Rs
TokenRs
Feature activation+0.000
).
Token).
Feature activation+9.117
Earlier
Token Earlier
Feature activation+7.304
this
Token this
Feature activation+0.000
year
Token year
Feature activation+11.036
,
Token,
Feature activation+10.530
the
Token the
Feature activation+5.039
Do
Token Do
Feature activation+0.000
E
TokenE
Feature activation+1.260
signed
Token signed
Feature activation+0.220
a
Token a
Feature activation+0.000

INTERVAL 8.010 - 9.345
CONTAINS 0.000%

s
Tokens
Feature activation+0.000
best
Token best
Feature activation+0.000
fighters
Token fighters
Feature activation+0.000
and
Token and
Feature activation+0.000
bombers
Token bombers
Feature activation+0.000
,
Token,
Feature activation+8.481
and
Token and
Feature activation+0.112
O
Token O
Feature activation+0.000
sp
Tokensp
Feature activation+0.000
rey
Tokenrey
Feature activation+0.000
hybrid
Token hybrid
Feature activation+0.000
in
Token in
Feature activation+0.000
1984
Token 1984
Feature activation+0.464
History
Token History
Feature activation+1.797
Japan
Token Japan
Feature activation+0.497
Name
Token Name
Feature activation+6.305
:
Token:
Feature activation+8.348
H
Token H
Feature activation+0.000
ime
Tokenime
Feature activation+2.327
y
Tokeny
Feature activation+0.464
uri
Tokenuri
Feature activation+6.060
Mar
Token Mar
Feature activation+0.000
modular
Token modular
Feature activation+0.000
reactors
Token reactors
Feature activation+0.000
(
Token (
Feature activation+0.000
SM
TokenSM
Feature activation+0.000
Rs
TokenRs
Feature activation+0.000
).
Token).
Feature activation+9.117
Earlier
Token Earlier
Feature activation+7.304
this
Token this
Feature activation+0.000
year
Token year
Feature activation+11.036
,
Token,
Feature activation+10.530
the
Token the
Feature activation+5.039

INTERVAL 6.675 - 8.010
CONTAINS 0.001%

Okinawa
Token Okinawa
Feature activation+0.000
,
Token,
Feature activation+7.376
Japan
Token Japan
Feature activation+0.000
.
Token.
Feature activation+4.568
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.755
The
TokenThe
Feature activation+0.817
purpose
Token purpose
Feature activation+0.000
is
Token is
Feature activation+0.000
officially
Token officially
Feature activation+0.000
for
Token for
Feature activation+0.000
reactors
Token reactors
Feature activation+0.000
(
Token (
Feature activation+0.000
SM
TokenSM
Feature activation+0.000
Rs
TokenRs
Feature activation+0.000
).
Token).
Feature activation+9.117
Earlier
Token Earlier
Feature activation+7.304
this
Token this
Feature activation+0.000
year
Token year
Feature activation+11.036
,
Token,
Feature activation+10.530
the
Token the
Feature activation+5.039
Do
Token Do
Feature activation+0.000
az
Tokenaz
Feature activation+0.744
in
Token in
Feature activation+0.000
1981
Token 1981
Feature activation+0.371
Ref
Token Ref
Feature activation+0.000
it
Tokenit
Feature activation+0.000
:
Token:
Feature activation+6.980
After
Token After
Feature activation+1.342
a
Token a
Feature activation+0.000
fire
Token fire
Feature activation+0.000
onboard
Token onboard
Feature activation+2.612
June
Token June
Feature activation+0.000
a
Token a
Feature activation+0.000
US
Token US
Feature activation+0.000
base
Token base
Feature activation+0.000
in
Token in
Feature activation+0.000
Okinawa
Token Okinawa
Feature activation+0.000
,
Token,
Feature activation+7.376
Japan
Token Japan
Feature activation+0.000
.
Token.
Feature activation+4.568
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.755
The
TokenThe
Feature activation+0.817
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.636
area
Token area
Feature activation+0.000
twice
Token twice
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+6.945
couple
Token couple
Feature activation+0.000
is
Token is
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.247
bar
Token bar
Feature activation+0.000

INTERVAL 5.340 - 6.675
CONTAINS 0.001%

Name
Token Name
Feature activation+1.279
:
Token:
Feature activation+4.151
Don
Token Don
Feature activation+0.521
Sul
Token Sul
Feature activation+0.000
pic
Tokenpic
Feature activation+0.000
io
Tokenio
Feature activation+5.612
Owner
Token Owner
Feature activation+0.000
:
Token:
Feature activation+0.550
Sul
Token Sul
Feature activation+0.000
pic
Tokenpic
Feature activation+0.000
io
Tokenio
Feature activation+2.703
Do
Token Do
Feature activation+0.000
ña
Tokenña
Feature activation+5.235
P
Token P
Feature activation+0.000
az
Tokenaz
Feature activation+0.197
was
Token was
Feature activation+0.000
a
Token a
Feature activation+5.763
Philippine
Token Philippine
Feature activation+1.298
-
Token-
Feature activation+0.000
registered
Tokenregistered
Feature activation+5.554
passenger
Token passenger
Feature activation+0.000
ferry
Token ferry
Feature activation+0.000
are
Token are
Feature activation+0.000
both
Token both
Feature activation+0.000
Buzz
Token Buzz
Feature activation+0.000
Light
Token Light
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
does
Token does
Feature activation+5.929
anything
Token anything
Feature activation+0.311
.
Token.
Feature activation+0.000
Personally
Token Personally
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
az
Tokenaz
Feature activation+0.197
was
Token was
Feature activation+0.000
a
Token a
Feature activation+5.763
Philippine
Token Philippine
Feature activation+1.298
-
Token-
Feature activation+0.000
registered
Tokenregistered
Feature activation+5.554
passenger
Token passenger
Feature activation+0.000
ferry
Token ferry
Feature activation+0.000
that
Token that
Feature activation+0.000
sank
Token sank
Feature activation+0.000
after
Token after
Feature activation+0.000
com
Tokencom
Feature activation+0.000
.
Token.
Feature activation+0.000
au
Tokenau
Feature activation+0.000
.
Token.
Feature activation+2.744
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.303
Some
TokenSome
Feature activation+0.000
of
Token of
Feature activation+4.302
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 4.005 - 5.340
CONTAINS 0.002%

Mar
Token Mar
Feature activation+0.000
u
Tokenu
Feature activation+4.163
Owner
Token Owner
Feature activation+0.230
:
Token:
Feature activation+2.910
R
Token R
Feature activation+0.000
KK
TokenKK
Feature activation+4.238
Line
Token Line
Feature activation+0.000
Port
Token Port
Feature activation+0.000
of
Token of
Feature activation+0.000
registry
Token registry
Feature activation+0.000
:
Token:
Feature activation+0.119
ert
Tokenert
Feature activation+0.000
hed
Tokenhed
Feature activation+2.378
at
Token at
Feature activation+1.445
b
Token b
Feature activation+0.000
ert
Tokenert
Feature activation+0.000
hed
Tokenhed
Feature activation+4.926
at
Token at
Feature activation+3.148
Tac
Token Tac
Feature activation+0.000
l
Tokenl
Feature activation+0.000
ob
Tokenob
Feature activation+0.000
an
Tokenan
Feature activation+1.250
base
Token base
Feature activation+0.000
in
Token in
Feature activation+0.000
Okinawa
Token Okinawa
Feature activation+0.000
,
Token,
Feature activation+7.376
Japan
Token Japan
Feature activation+0.000
.
Token.
Feature activation+4.568
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.755
The
TokenThe
Feature activation+0.817
purpose
Token purpose
Feature activation+0.000
is
Token is
Feature activation+0.000
on
Token on
Feature activation+0.000
my
Token my
Feature activation+0.000
worst
Token worst
Feature activation+0.000
day
Token day
Feature activation+0.000
,"
Token,"
Feature activation+0.000
S
Token S
Feature activation+4.977
do
Tokendo
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
New
Token New
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
M
TokenM
Feature activation+0.000
V
TokenV
Feature activation+0.000
Do
Token Do
Feature activation+0.000
ña
Tokenña
Feature activation+5.235
P
Token P
Feature activation+0.000
az
Tokenaz
Feature activation+0.197
was
Token was
Feature activation+0.000
a
Token a
Feature activation+5.763
Philippine
Token Philippine
Feature activation+1.298

INTERVAL 2.670 - 4.005
CONTAINS 0.004%

be
Token be
Feature activation+0.000
played
Token played
Feature activation+0.000
in
Token in
Feature activation+0.000
perfect
Token perfect
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
?
Token?
Feature activation+3.465
Do
Token Do
Feature activation+0.000
you
Token you
Feature activation+0.000
want
Token want
Feature activation+0.000
the
Token the
Feature activation+0.000
elements
Token elements
Feature activation+0.000
stuff
Token stuff
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
here
Token here
Feature activation+0.000
I
Token I
Feature activation+0.000
am
Token am
Feature activation+2.918
19
Token 19
Feature activation+0.000
-
Token-
Feature activation+0.000
years
Tokenyears
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+1.252
âĢ
Token âĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.133
pl
Tokenpl
Feature activation+0.000
É
TokenÉ
Feature activation+0.000
Ķ
TokenĶ
Feature activation+0.683
:
Token:
Feature activation+3.614
m
Tokenm
Feature activation+1.267
É
TokenÉ
Feature activation+0.000
Ķ
TokenĶ
Feature activation+1.605
:
Token:
Feature activation+2.808
s
Tokens
Feature activation+0.161
news
Token news
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
.
Token.
Feature activation+0.000
au
Tokenau
Feature activation+0.000
.
Token.
Feature activation+2.744
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.303
Some
TokenSome
Feature activation+0.000
of
Token of
Feature activation+4.302
the
Token the
Feature activation+0.000
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
candidate
Token candidate
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+3.230
There
Token There
Feature activation+0.000
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
concrete
Token concrete
Feature activation+0.000

INTERVAL 1.335 - 2.670
CONTAINS 0.015%

well
Token well
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
National
Token National
Feature activation+0.000
Hockey
Token Hockey
Feature activation+0.000
League
Token League
Feature activation+1.462
awards
Token awards
Feature activation+0.000
three
Token three
Feature activation+0.000
stars
Token stars
Feature activation+0.000
during
Token during
Feature activation+0.000
every
Token every
Feature activation+0.000
deal
Token deal
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
on
Token on
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+1.809
good
Tokengood
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
spontaneously
Token spontaneously
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
topic
Token topic
Feature activation+0.000
of
Token of
Feature activation+2.644
racism
Token racism
Feature activation+0.000
has
Token has
Feature activation+0.000
arrived
Token arrived
Feature activation+0.000
per
Token per
Feature activation+0.000
force
Token force
Feature activation+0.000
two
Token two
Feature activation+0.000
decades
Token decades
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+1.352
website
Token website
Feature activation+0.000
stated
Token stated
Feature activation+0.000
,
Token,
Feature activation+0.000
although
Token although
Feature activation+0.000
no
Token no
Feature activation+0.000
of
Token of
Feature activation+0.000
your
Token your
Feature activation+0.000
interpret
Token interpret
Feature activation+0.000
ive
Tokenive
Feature activation+0.000
framework
Token framework
Feature activation+0.000
).
Token).
Feature activation+1.351
They
Token They
Feature activation+0.000
are
Token are
Feature activation+0.000
faithful
Token faithful
Feature activation+0.000
and
Token and
Feature activation+0.000
informed
Token informed
Feature activation+0.000

INTERVAL 0.000 - 1.335
CONTAINS 99.976%

.
Token.
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
there
Token there
Feature activation+0.000
the
Token the
Feature activation+0.000
to
Token to
Feature activation+0.000
Stream
TokenStream
Feature activation+0.000
ing
Tokening
Feature activation+0.000
URI
TokenURI
Feature activation+0.000
sales
Token sales
Feature activation+0.000
;
Token;
Feature activation+0.000
they
Token they
Feature activation+0.000
pay
Token pay
Feature activation+0.000
zero
Token zero
Feature activation+0.000
tax
Token tax
Feature activation+0.000
on
Token on
Feature activation+0.000
income
Token income
Feature activation+0.000
from
Token from
Feature activation+0.000
municipal
Token municipal
Feature activation+0.000
bonds
Token bonds
Feature activation+0.000
this
Token this
Feature activation+0.000
slippery
Token slippery
Feature activation+0.000
stuff
Token stuff
Feature activation+0.000
covered
Token covered
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
fifth
Tokenfifth
Feature activation+0.000
of
Token of
Feature activation+0.000
Erie
Token Erie
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
leaks
Token leaks
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Post
Token Post
Feature activation+0.000
reporter
Token reporter
Feature activation+0.000
Barton
Token Barton
Feature activation+0.000
G
Token G
Feature activation+0.000
ell
Tokenell
Feature activation+0.000
man
Tokenman
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
English
Token English
Feature activation+0.000
clothing
Token clothing
Feature activation+0.000
guides
Token guides
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
Cl
Token Cl
Feature activation+0.000
othes
Tokenothes
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 5 in H11.5: (feature 2527)

TOP ACTIVATIONS
MAX = 8.382

size
Token size
Feature activation+0.000
.
Token.
Feature activation+3.565
Due
Token Due
Feature activation+0.000
to
Token to
Feature activation+5.983
the
Token the
Feature activation+3.818
way
Token way
Feature activation+8.314
this
Token this
Feature activation+1.255
optimization
Token optimization
Feature activation+0.000
is
Token is
Feature activation+0.000
implemented
Token implemented
Feature activation+0.000
,
Token,
Feature activation+3.834
object
Token object
Feature activation+0.000
type
Token type
Feature activation+0.000
that
Token that
Feature activation+0.309
you
Token you
Feature activation+0.522
use
Token use
Feature activation+1.959
with
Token with
Feature activation+8.050
make
Token make
Feature activation+0.122
_
Token_
Feature activation+1.081
shared
Tokenshared
Feature activation+0.000
()
Token()
Feature activation+0.445
.
Token .
Feature activation+2.215
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
single
Token single
Feature activation+0.000
memory
Token memory
Feature activation+0.000
block
Token block
Feature activation+0.000
.
Token.
Feature activation+7.753
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
approach
Token approach
Feature activation+0.000
.
Token.
Feature activation+4.467
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.614
Firstly
TokenFirstly
Feature activation+1.685
,
Token,
Feature activation+7.439
if
Token if
Feature activation+4.234
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
weak
Token weak
Feature activation+0.000
pointing
Token pointing
Feature activation+0.000
to
Token to
Feature activation+0.000
this
Token this
Feature activation+0.000
object
Token object
Feature activation+0.000
),
Token),
Feature activation+5.120
then
Token then
Feature activation+7.194
that
Token that
Feature activation+0.000
weak
Token weak
Feature activation+0.000
_
Token_
Feature activation+0.000
ptr
Tokenptr
Feature activation+0.000
will
Token will
Feature activation+0.000
other
Token other
Feature activation+0.000
penalties
Token penalties
Feature activation+0.000
and
Token and
Feature activation+0.000
limitations
Token limitations
Feature activation+0.000
associated
Token associated
Feature activation+0.000
with
Token with
Feature activation+7.144
this
Token this
Feature activation+0.000
approach
Token approach
Feature activation+0.000
.
Token.
Feature activation+4.467
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.614
(
Token(
Feature activation+0.000
list
Tokenlist
Feature activation+0.000
=>
Token =>
Feature activation+0.000
(),
Token (),
Feature activation+0.000
made
Token made
Feature activation+0.000
=>
Token =>
Feature activation+6.721
Any
Token Any
Feature activation+0.571
,
Token,
Feature activation+1.172
pos
Token pos
Feature activation+0.000
=>
Token =>
Feature activation+3.583
7
Token 7
Feature activation+0.000
the
Token the
Feature activation+1.972
better
Token better
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
opened
Token opened
Feature activation+6.598
the
Token the
Feature activation+4.078
sentence
Token sentence
Feature activation+0.396
that
Token that
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
()
Token()
Feature activation+0.445
.
Token .
Feature activation+2.215
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.657
Finally
TokenFinally
Feature activation+3.032
,
Token,
Feature activation+6.314
make
Token make
Feature activation+0.000
_
Token_
Feature activation+0.000
shared
Tokenshared
Feature activation+0.000
()
Token()
Feature activation+0.000
will
Token will
Feature activation+0.000
percent
Token percent
Feature activation+0.000
broadband
Token broadband
Feature activation+0.000
adoption
Token adoption
Feature activation+0.000
rate
Token rate
Feature activation+0.000
with
Token with
Feature activation+0.000
households
Token households
Feature activation+6.114
making
Token making
Feature activation+0.000
over
Token over
Feature activation+0.000
$
Token $
Feature activation+0.000
50
Token50
Feature activation+0.000
,
Token,
Feature activation+0.000
object
Token object
Feature activation+0.000
code
Token code
Feature activation+0.000
size
Token size
Feature activation+0.000
.
Token.
Feature activation+3.565
Due
Token Due
Feature activation+0.000
to
Token to
Feature activation+5.983
the
Token the
Feature activation+3.818
way
Token way
Feature activation+8.314
this
Token this
Feature activation+1.255
optimization
Token optimization
Feature activation+0.000
is
Token is
Feature activation+0.000
new
Tokennew
Feature activation+0.000
BMW
Token BMW
Feature activation+0.000
M
Token M
Feature activation+0.000
5
Token5
Feature activation+0.000
will
Token will
Feature activation+3.962
also
Token also
Feature activation+5.628
be
Token be
Feature activation+1.330
featured
Token featured
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
with
Token with
Feature activation+7.144
this
Token this
Feature activation+0.000
approach
Token approach
Feature activation+0.000
.
Token.
Feature activation+4.467
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.614
Firstly
TokenFirstly
Feature activation+1.685
,
Token,
Feature activation+7.439
if
Token if
Feature activation+4.234
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
promoted
Token promoted
Feature activation+0.000
drug
Token drug
Feature activation+0.000
on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
list
Token list
Feature activation+0.614
,
Token,
Feature activation+5.442
Type
Token Type
Feature activation+0.000
-
Token-
Feature activation+0.000
2
Token2
Feature activation+0.000
diabetes
Token diabetes
Feature activation+0.000
drug
Token drug
Feature activation+0.000
diabetes
Token diabetes
Feature activation+0.000
drug
Token drug
Feature activation+0.000
Vict
Token Vict
Feature activation+0.000
o
Tokeno
Feature activation+0.000
za
Tokenza
Feature activation+0.591
,
Token,
Feature activation+5.253
spent
Token spent
Feature activation+0.000
$
Token $
Feature activation+0.000
8
Token8
Feature activation+0.000
16
Token16
Feature activation+0.000
,
Token,
Feature activation+0.000
hash
Token hash
Feature activation+0.000
=>
Token =>
Feature activation+2.068
Map
Token Map
Feature activation+0.000
.
Token.
Feature activation+0.000
new
Tokennew
Feature activation+0.000
(
Token(
Feature activation+5.134
()
Token()
Feature activation+0.000
),
Token),
Feature activation+1.936
orig
Token orig
Feature activation+0.000
=>
Token =>
Feature activation+3.671
"
Token "
Feature activation+0.090
instances
Token instances
Feature activation+0.000
pointing
Token pointing
Feature activation+0.000
to
Token to
Feature activation+0.000
this
Token this
Feature activation+0.000
object
Token object
Feature activation+0.000
),
Token),
Feature activation+5.120
then
Token then
Feature activation+7.194
that
Token that
Feature activation+0.000
weak
Token weak
Feature activation+0.000
_
Token_
Feature activation+0.000
ptr
Tokenptr
Feature activation+0.000
,
Token,
Feature activation+0.000
make
Token make
Feature activation+0.000
_
Token_
Feature activation+0.000
shared
Tokenshared
Feature activation+0.000
()
Token()
Feature activation+0.000
and
Token and
Feature activation+4.951
allocate
Token allocate
Feature activation+0.000
_
Token_
Feature activation+0.000
shared
Tokenshared
Feature activation+0.000
()
Token()
Feature activation+0.000
,
Token ,
Feature activation+0.881
Makes
Token Makes
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.958
There
TokenThere
Feature activation+0.000
were
Token were
Feature activation+0.000
more
Token more
Feature activation+4.482
mentions
Token mentions
Feature activation+0.000
of
Token of
Feature activation+4.099
Cadillac
Token Cadillac
Feature activation+0.656
relative
Token relative
Feature activation+0.440
to
Token to
Feature activation+0.886
limitations
Token limitations
Feature activation+0.000
associated
Token associated
Feature activation+0.000
with
Token with
Feature activation+7.144
this
Token this
Feature activation+0.000
approach
Token approach
Feature activation+0.000
.
Token.
Feature activation+4.467
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.614
Firstly
TokenFirstly
Feature activation+1.685
,
Token,
Feature activation+7.439
if
Token if
Feature activation+4.234

Top DFA by src position
MAX = 10.133

The
TokenThe
Feature activation+0.034
Top resid features:
other
Token other
Feature activation+0.005
Top resid features:
drawback
Token drawback
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
make
Token make
Feature activation+10.133
Top resid features:
_
Token_
Feature activation+0.093
Top resid features:
shared
Tokenshared
Feature activation+0.015
Top resid features:
()
Token()
Feature activation+0.008
Top resid features:
implementation
Token implementation
Feature activation+0.007
Top resid features:
is
Token is
Feature activation+0.008
Top resid features:
The
TokenThe
Feature activation+0.029
Top resid features:
other
Token other
Feature activation+0.005
Top resid features:
drawback
Token drawback
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.028
Top resid features:
make
Token make
Feature activation+9.712
Top resid features:
_
Token_
Feature activation+0.119
Top resid features:
shared
Tokenshared
Feature activation+0.019
Top resid features:
()
Token()
Feature activation+0.008
Top resid features:
implementation
Token implementation
Feature activation+0.003
Top resid features:
is
Token is
Feature activation+0.008
Top resid features:
provides
Token provides
Feature activation-0.007
Top resid features:
two
Token two
Feature activation+0.003
Top resid features:
helper
Token helper
Feature activation-0.007
Top resid features:
functions
Token functions
Feature activation+0.027
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
make
Token make
Feature activation+9.114
Top resid features:
_
Token_
Feature activation+0.070
Top resid features:
shared
Tokenshared
Feature activation-0.021
Top resid features:
()
Token()
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
allocate
Token allocate
Feature activation+0.126
Top resid features:
provides
Token provides
Feature activation+0.002
Top resid features:
two
Token two
Feature activation+0.001
Top resid features:
helper
Token helper
Feature activation-0.002
Top resid features:
functions
Token functions
Feature activation+0.025
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
make
Token make
Feature activation+8.843
Top resid features:
_
Token_
Feature activation+0.113
Top resid features:
shared
Tokenshared
Feature activation-0.033
Top resid features:
()
Token()
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
allocate
Token allocate
Feature activation+0.111
Top resid features:
provides
Token provides
Feature activation+0.003
Top resid features:
two
Token two
Feature activation+0.001
Top resid features:
helper
Token helper
Feature activation-0.000
Top resid features:
functions
Token functions
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
make
Token make
Feature activation+8.552
Top resid features:
_
Token_
Feature activation+0.113
Top resid features:
shared
Tokenshared
Feature activation+0.003
Top resid features:
()
Token()
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
allocate
Token allocate
Feature activation+0.170
Top resid features:
provides
Token provides
Feature activation+0.008
Top resid features:
two
Token two
Feature activation-0.003
Top resid features:
helper
Token helper
Feature activation-0.021
Top resid features:
functions
Token functions
Feature activation+0.033
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
make
Token make
Feature activation+8.530
Top resid features:
_
Token_
Feature activation+0.176
Top resid features:
shared
Tokenshared
Feature activation-0.009
Top resid features:
()
Token()
Feature activation+0.011
Top resid features:
and
Token and
Feature activation+0.017
Top resid features:
allocate
Token allocate
Feature activation+0.085
Top resid features:
new
Tokennew
Feature activation-0.021
Top resid features:
(
Token(
Feature activation+0.019
Top resid features:
list
Tokenlist
Feature activation-0.102
Top resid features:
=>
Token =>
Feature activation+0.064
Top resid features:
(),
Token (),
Feature activation+0.065
Top resid features:
made
Token made
Feature activation+8.091
Top resid features:
=>
Token =>
Feature activation+0.111
Top resid features:
Any
Token Any
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
pos
Token pos
Feature activation+0.000
Top resid features:
=>
Token =>
Feature activation+0.000
Top resid features:
forced
Token forced
Feature activation+0.007
Top resid features:
me
Token me
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
learn
Token learn
Feature activation-0.008
Top resid features:
about
Token about
Feature activation+0.009
Top resid features:
Make
Token Make
Feature activation+6.906
Top resid features:
and
Token and
Feature activation+0.049
Top resid features:
make
Token make
Feature activation+1.067
Top resid features:
files
Tokenfiles
Feature activation+0.032
Top resid features:
(
Token (
Feature activation+0.012
Top resid features:
this
Tokenthis
Feature activation+0.030
Top resid features:
type
Token type
Feature activation+0.006
Top resid features:
that
Token that
Feature activation+0.008
Top resid features:
you
Token you
Feature activation-0.054
Top resid features:
use
Token use
Feature activation-0.004
Top resid features:
with
Token with
Feature activation+0.007
Top resid features:
make
Token make
Feature activation+3.966
Top resid features:
_
Token_
Feature activation+0.038
Top resid features:
shared
Tokenshared
Feature activation-0.007
Top resid features:
()
Token()
Feature activation-0.001
Top resid features:
.
Token .
Feature activation-0.042
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
(
Token (
Feature activation+0.017
Top resid features:
specific
Tokenspecific
Feature activation+0.004
Top resid features:
ally
Tokenally
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
households
Token households
Feature activation+0.001
Top resid features:
making
Token making
Feature activation+7.533
Top resid features:
under
Token under
Feature activation+0.020
Top resid features:
$
Token $
Feature activation+0.014
Top resid features:
20
Token20
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
000
Token000
Feature activation-0.004
Top resid features:
The
TokenThe
Feature activation+0.034
Top resid features:
other
Token other
Feature activation+0.005
Top resid features:
drawback
Token drawback
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
make
Token make
Feature activation+7.662
Top resid features:
_
Token_
Feature activation+0.143
Top resid features:
shared
Tokenshared
Feature activation-0.016
Top resid features:
()
Token()
Feature activation+0.020
Top resid features:
implementation
Token implementation
Feature activation+0.004
Top resid features:
is
Token is
Feature activation+0.012
Top resid features:
M
Token M
Feature activation+0.000
Top resid features:
3
Token3
Feature activation-0.003
Top resid features:
CS
Token CS
Feature activation+0.003
Top resid features:
will
Token will
Feature activation+0.031
Top resid features:
also
Token also
Feature activation+0.036
Top resid features:
make
Token make
Feature activation+4.496
Top resid features:
its
Token its
Feature activation+0.145
Top resid features:
world
Token world
Feature activation+0.046
Top resid features:
premiere
Token premiere
Feature activation+0.070
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
and
Token and
Feature activation+0.029
Top resid features:
provides
Token provides
Feature activation+0.003
Top resid features:
two
Token two
Feature activation+0.001
Top resid features:
helper
Token helper
Feature activation-0.008
Top resid features:
functions
Token functions
Feature activation+0.020
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
make
Token make
Feature activation+7.008
Top resid features:
_
Token_
Feature activation+0.077
Top resid features:
shared
Tokenshared
Feature activation-0.024
Top resid features:
()
Token()
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
allocate
Token allocate
Feature activation+0.056
Top resid features:
il
Tokenil
Feature activation+0.003
Top resid features:
int
Tokenint
Feature activation+0.003
Top resid features:
a
Tokena
Feature activation+0.006
Top resid features:
's
Token's
Feature activation+0.029
Top resid features:
manufacturers
Token manufacturers
Feature activation+0.016
Top resid features:
made
Token made
Feature activation+6.880
Top resid features:
63
Token 63
Feature activation+0.045
Top resid features:
payments
Token payments
Feature activation+0.032
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
doctors
Token doctors
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
il
Tokenil
Feature activation+0.002
Top resid features:
int
Tokenint
Feature activation+0.002
Top resid features:
a
Tokena
Feature activation+0.005
Top resid features:
's
Token's
Feature activation+0.024
Top resid features:
manufacturers
Token manufacturers
Feature activation-0.002
Top resid features:
made
Token made
Feature activation+6.659
Top resid features:
63
Token 63
Feature activation+0.046
Top resid features:
payments
Token payments
Feature activation+0.029
Top resid features:
to
Token to
Feature activation+0.018
Top resid features:
doctors
Token doctors
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
new
Tokennew
Feature activation-0.003
Top resid features:
(
Token(
Feature activation+0.009
Top resid features:
list
Tokenlist
Feature activation-0.069
Top resid features:
=>
Token =>
Feature activation+0.037
Top resid features:
(),
Token (),
Feature activation+0.020
Top resid features:
made
Token made
Feature activation+6.733
Top resid features:
=>
Token =>
Feature activation+0.037
Top resid features:
Any
Token Any
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
pos
Token pos
Feature activation+0.003
Top resid features:
=>
Token =>
Feature activation+0.036
Top resid features:
provides
Token provides
Feature activation+0.002
Top resid features:
two
Token two
Feature activation+0.005
Top resid features:
helper
Token helper
Feature activation+0.001
Top resid features:
functions
Token functions
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
make
Token make
Feature activation+6.326
Top resid features:
_
Token_
Feature activation+0.149
Top resid features:
shared
Tokenshared
Feature activation+0.016
Top resid features:
()
Token()
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
allocate
Token allocate
Feature activation+0.161
Top resid features:
provides
Token provides
Feature activation-0.001
Top resid features:
two
Token two
Feature activation+0.007
Top resid features:
helper
Token helper
Feature activation-0.001
Top resid features:
functions
Token functions
Feature activation+0.018
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
make
Token make
Feature activation+6.374
Top resid features:
_
Token_
Feature activation+0.238
Top resid features:
shared
Tokenshared
Feature activation+0.042
Top resid features:
()
Token()
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+0.060
Top resid features:
allocate
Token allocate
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Top
TokenTop
Feature activation-0.020
Top resid features:
3
Token 3
Feature activation-0.008
Top resid features:
Makes
Token Makes
Feature activation+5.944
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
There
TokenThere
Feature activation+0.005
Top resid features:
were
Token were
Feature activation+0.017
Top resid features:
more
Token more
Feature activation+0.183
Top resid features:
provides
Token provides
Feature activation-0.006
Top resid features:
two
Token two
Feature activation+0.002
Top resid features:
helper
Token helper
Feature activation-0.004
Top resid features:
functions
Token functions
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
make
Token make
Feature activation+5.675
Top resid features:
_
Token_
Feature activation+0.076
Top resid features:
shared
Tokenshared
Feature activation-0.011
Top resid features:
()
Token()
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
allocate
Token allocate
Feature activation+0.074
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.03

Head 3: 0.05

Head 4: 0.05

Head 5: 0.42

Head 6: 0.05

Head 7: 0.04

Head 8: 0.06

Head 9: 0.08

Head 10: 0.05

Head 11: 0.07

Positive logits

Make7.34

make7.07

make6.89

Make6.68

made6.63

MAKE6.54

Making6.50

making6.48

Made6.38

Making5.86

Made5.62

makes5.62

made5.56

makes5.48

Makes5.43

making5.35

maker4.05

maker3.86

makers3.85

makers3.54

Negative logits

icter-2.88

icum-2.74

largeDownload-2.71

cest-2.58

heed-2.57

heit-2.56

raph-2.55

inar-2.54

MpServer-2.52

Stage-2.46

20439-2.46

Response-2.46

tremend-2.39

Stage-2.36

mberg-2.35

ivas-2.28

EStreamFrame-2.28

rams-2.26

rama-2.24

REG-2.23

INTERVAL 7.544 - 8.382
CONTAINS 0.000%

as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
single
Token single
Feature activation+0.000
memory
Token memory
Feature activation+0.000
block
Token block
Feature activation+0.000
.
Token.
Feature activation+7.753
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
size
Token size
Feature activation+0.000
.
Token.
Feature activation+3.565
Due
Token Due
Feature activation+0.000
to
Token to
Feature activation+5.983
the
Token the
Feature activation+3.818
way
Token way
Feature activation+8.314
this
Token this
Feature activation+1.255
optimization
Token optimization
Feature activation+0.000
is
Token is
Feature activation+0.000
implemented
Token implemented
Feature activation+0.000
,
Token,
Feature activation+3.834
object
Token object
Feature activation+0.000
type
Token type
Feature activation+0.000
that
Token that
Feature activation+0.309
you
Token you
Feature activation+0.522
use
Token use
Feature activation+1.959
with
Token with
Feature activation+8.050
make
Token make
Feature activation+0.122
_
Token_
Feature activation+1.081
shared
Tokenshared
Feature activation+0.000
()
Token()
Feature activation+0.445
.
Token .
Feature activation+2.215

INTERVAL 6.705 - 7.544
CONTAINS 0.000%

(
Token(
Feature activation+0.000
list
Tokenlist
Feature activation+0.000
=>
Token =>
Feature activation+0.000
(),
Token (),
Feature activation+0.000
made
Token made
Feature activation+0.000
=>
Token =>
Feature activation+6.721
Any
Token Any
Feature activation+0.571
,
Token,
Feature activation+1.172
pos
Token pos
Feature activation+0.000
=>
Token =>
Feature activation+3.583
7
Token 7
Feature activation+0.000
other
Token other
Feature activation+0.000
penalties
Token penalties
Feature activation+0.000
and
Token and
Feature activation+0.000
limitations
Token limitations
Feature activation+0.000
associated
Token associated
Feature activation+0.000
with
Token with
Feature activation+7.144
this
Token this
Feature activation+0.000
approach
Token approach
Feature activation+0.000
.
Token.
Feature activation+4.467
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.614
approach
Token approach
Feature activation+0.000
.
Token.
Feature activation+4.467
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.614
Firstly
TokenFirstly
Feature activation+1.685
,
Token,
Feature activation+7.439
if
Token if
Feature activation+4.234
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
weak
Token weak
Feature activation+0.000
pointing
Token pointing
Feature activation+0.000
to
Token to
Feature activation+0.000
this
Token this
Feature activation+0.000
object
Token object
Feature activation+0.000
),
Token),
Feature activation+5.120
then
Token then
Feature activation+7.194
that
Token that
Feature activation+0.000
weak
Token weak
Feature activation+0.000
_
Token_
Feature activation+0.000
ptr
Tokenptr
Feature activation+0.000
will
Token will
Feature activation+0.000

INTERVAL 5.867 - 6.705
CONTAINS 0.000%

the
Token the
Feature activation+1.972
better
Token better
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
opened
Token opened
Feature activation+6.598
the
Token the
Feature activation+4.078
sentence
Token sentence
Feature activation+0.396
that
Token that
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
object
Token object
Feature activation+0.000
code
Token code
Feature activation+0.000
size
Token size
Feature activation+0.000
.
Token.
Feature activation+3.565
Due
Token Due
Feature activation+0.000
to
Token to
Feature activation+5.983
the
Token the
Feature activation+3.818
way
Token way
Feature activation+8.314
this
Token this
Feature activation+1.255
optimization
Token optimization
Feature activation+0.000
is
Token is
Feature activation+0.000
()
Token()
Feature activation+0.445
.
Token .
Feature activation+2.215
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.657
Finally
TokenFinally
Feature activation+3.032
,
Token,
Feature activation+6.314
make
Token make
Feature activation+0.000
_
Token_
Feature activation+0.000
shared
Tokenshared
Feature activation+0.000
()
Token()
Feature activation+0.000
will
Token will
Feature activation+0.000
percent
Token percent
Feature activation+0.000
broadband
Token broadband
Feature activation+0.000
adoption
Token adoption
Feature activation+0.000
rate
Token rate
Feature activation+0.000
with
Token with
Feature activation+0.000
households
Token households
Feature activation+6.114
making
Token making
Feature activation+0.000
over
Token over
Feature activation+0.000
$
Token $
Feature activation+0.000
50
Token50
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 5.029 - 5.867
CONTAINS 0.001%

hash
Token hash
Feature activation+0.000
=>
Token =>
Feature activation+2.068
Map
Token Map
Feature activation+0.000
.
Token.
Feature activation+0.000
new
Tokennew
Feature activation+0.000
(
Token(
Feature activation+5.134
()
Token()
Feature activation+0.000
),
Token),
Feature activation+1.936
orig
Token orig
Feature activation+0.000
=>
Token =>
Feature activation+3.671
"
Token "
Feature activation+0.090
promoted
Token promoted
Feature activation+0.000
drug
Token drug
Feature activation+0.000
on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
list
Token list
Feature activation+0.614
,
Token,
Feature activation+5.442
Type
Token Type
Feature activation+0.000
-
Token-
Feature activation+0.000
2
Token2
Feature activation+0.000
diabetes
Token diabetes
Feature activation+0.000
drug
Token drug
Feature activation+0.000
diabetes
Token diabetes
Feature activation+0.000
drug
Token drug
Feature activation+0.000
Vict
Token Vict
Feature activation+0.000
o
Tokeno
Feature activation+0.000
za
Tokenza
Feature activation+0.591
,
Token,
Feature activation+5.253
spent
Token spent
Feature activation+0.000
$
Token $
Feature activation+0.000
8
Token8
Feature activation+0.000
16
Token16
Feature activation+0.000
,
Token,
Feature activation+0.000
new
Tokennew
Feature activation+0.000
BMW
Token BMW
Feature activation+0.000
M
Token M
Feature activation+0.000
5
Token5
Feature activation+0.000
will
Token will
Feature activation+3.962
also
Token also
Feature activation+5.628
be
Token be
Feature activation+1.330
featured
Token featured
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
with
Token with
Feature activation+7.144
this
Token this
Feature activation+0.000
approach
Token approach
Feature activation+0.000
.
Token.
Feature activation+4.467
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.614
Firstly
TokenFirstly
Feature activation+1.685
,
Token,
Feature activation+7.439
if
Token if
Feature activation+4.234
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000

INTERVAL 4.191 - 5.029
CONTAINS 0.001%

Islands
Token Islands
Feature activation+0.000
independent
Token independent
Feature activation+0.000
Jean
Token Jean
Feature activation+0.000
Ur
Token Ur
Feature activation+0.000
qu
Tokenqu
Feature activation+0.000
hart
Tokenhart
Feature activation+4.450
who
Token who
Feature activation+3.718
has
Token has
Feature activation+1.049
the
Token the
Feature activation+0.000
longest
Token longest
Feature activation+0.000
commute
Token commute
Feature activation+0.000
,
Token,
Feature activation+0.000
make
Token make
Feature activation+0.000
_
Token_
Feature activation+0.000
shared
Tokenshared
Feature activation+0.000
()
Token()
Feature activation+0.000
and
Token and
Feature activation+4.951
allocate
Token allocate
Feature activation+0.000
_
Token_
Feature activation+0.000
shared
Tokenshared
Feature activation+0.000
()
Token()
Feature activation+0.000
,
Token ,
Feature activation+0.881
being
Token being
Feature activation+0.000
freed
Token freed
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
because
Token because
Feature activation+4.363
the
Token the
Feature activation+0.000
reference
Token reference
Feature activation+0.000
counter
Token counter
Feature activation+0.000
used
Token used
Feature activation+0.000
by
Token by
Feature activation+8.382
#
Token#
Feature activation+2.406
Make
Token Make
Feature activation+1.338
file
Tokenfile
Feature activation+2.621
who
Token who
Feature activation+0.000
ami
Tokenami
Feature activation+1.628
:=
Token :=
Feature activation+4.200
$(
Token $(
Feature activation+4.162
shell
Tokenshell
Feature activation+0.989
who
Token who
Feature activation+0.000
ami
Tokenami
Feature activation+0.680
)
Token)
Feature activation+0.907
Makes
Token Makes
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.958
There
TokenThere
Feature activation+0.000
were
Token were
Feature activation+0.000
more
Token more
Feature activation+4.482
mentions
Token mentions
Feature activation+0.000
of
Token of
Feature activation+4.099
Cadillac
Token Cadillac
Feature activation+0.656
relative
Token relative
Feature activation+0.440
to
Token to
Feature activation+0.886

INTERVAL 3.353 - 4.191
CONTAINS 0.003%

-
Token-
Feature activation+0.000
new
Tokennew
Feature activation+0.000
BMW
Token BMW
Feature activation+0.000
M
Token M
Feature activation+0.000
5
Token5
Feature activation+0.000
will
Token will
Feature activation+3.962
also
Token also
Feature activation+5.628
be
Token be
Feature activation+1.330
featured
Token featured
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
better
Token better
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
opened
Token opened
Feature activation+6.598
the
Token the
Feature activation+4.078
sentence
Token sentence
Feature activation+0.396
that
Token that
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
sound
Token sound
Feature activation+0.000
believe
Token believe
Feature activation+0.000
PC
Token PC
Feature activation+0.000
Leader
Token Leader
Feature activation+0.000
Brian
Token Brian
Feature activation+0.000
Pall
Token Pall
Feature activation+0.000
ister
Tokenister
Feature activation+3.366
would
Token would
Feature activation+3.608
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
Premier
Token Premier
Feature activation+0.000
.
Token.
Feature activation+0.000
Made
Token Made
Feature activation+0.000
to
Token to
Feature activation+0.000
hate
Token hate
Feature activation+0.000
themselves
Token themselves
Feature activation+0.110
.
Token.
Feature activation+3.454
Made
Token Made
Feature activation+0.201
to
Token to
Feature activation+0.000
wish
Token wish
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
made
Token made
Feature activation+0.000
=>
Token =>
Feature activation+6.721
Any
Token Any
Feature activation+0.571
,
Token,
Feature activation+1.172
pos
Token pos
Feature activation+0.000
=>
Token =>
Feature activation+3.583
7
Token 7
Feature activation+0.000
,
Token,
Feature activation+2.003
hash
Token hash
Feature activation+0.000
=>
Token =>
Feature activation+2.068
Map
Token Map
Feature activation+0.000

INTERVAL 2.515 - 3.353
CONTAINS 0.004%

incredibly
Token incredibly
Feature activation+0.000
intricate
Token intricate
Feature activation+0.000
geared
Token geared
Feature activation+0.000
hubs
Token hubs
Feature activation+0.000
,
Token,
Feature activation+0.000
Honda
Token Honda
Feature activation+3.211
put
Token put
Feature activation+0.000
a
Token a
Feature activation+0.000
mech
Token mech
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
-
Token-
Feature activation+0.000
bel
Tokenbel
Feature activation+0.000
ieve
Tokenieve
Feature activation+0.707
adventures
Token adventures
Feature activation+0.000
with
Token with
Feature activation+0.000
his
Token his
Feature activation+2.653
dog
Token dog
Feature activation+0.000
Henry
Token Henry
Feature activation+0.000
-
Token -
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.000
use
Token use
Feature activation+0.000
a
Token a
Feature activation+0.000
Make
Token Make
Feature activation+0.000
file
Tokenfile
Feature activation+0.000
that
Token that
Feature activation+0.000
provides
Token provides
Feature activation+3.220
a
Token a
Feature activation+4.142
set
Token set
Feature activation+0.000
of
Token of
Feature activation+1.760
commands
Token commands
Feature activation+0.000
.
Token.
Feature activation+0.037
shared
Tokenshared
Feature activation+0.000
()
Token()
Feature activation+0.445
.
Token .
Feature activation+2.215
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.657
Finally
TokenFinally
Feature activation+3.032
,
Token,
Feature activation+6.314
make
Token make
Feature activation+0.000
_
Token_
Feature activation+0.000
shared
Tokenshared
Feature activation+0.000
()
Token()
Feature activation+0.000
and
Tokenand
Feature activation+0.000
(
Token (
Feature activation+0.000
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+0.000
NY
TokenNY
Feature activation+0.000
)
Token)
Feature activation+3.226
gave
Token gave
Feature activation+0.000
$
Token $
Feature activation+0.000
10
Token10
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000

INTERVAL 1.676 - 2.515
CONTAINS 0.008%

file
Tokenfile
Feature activation+0.000
that
Token that
Feature activation+0.000
provides
Token provides
Feature activation+3.220
a
Token a
Feature activation+4.142
set
Token set
Feature activation+0.000
of
Token of
Feature activation+1.760
commands
Token commands
Feature activation+0.000
.
Token.
Feature activation+0.037
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.318
#
Token#
Feature activation+2.406
nervous
Token nervous
Feature activation+0.000
_
Token_
Feature activation+0.000
test
Tokentest
Feature activation+0.000
p
Tokenp
Feature activation+0.000
ilot
Tokenilot
Feature activation+0.000
and
Token and
Feature activation+1.896
Bryan
Token Bryan
Feature activation+0.000
Henderson
Token Henderson
Feature activation+0.000
.
Token.
Feature activation+0.000
A
TokenA
Feature activation+0.000
young
Token young
Feature activation+0.000
riding
Token riding
Feature activation+0.000
your
Token your
Feature activation+0.000
best
Token best
Feature activation+0.000
friend
Token friend
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.752
s
Tokens
Feature activation+0.000
bicycle
Token bicycle
Feature activation+0.014
in
Token in
Feature activation+0.000
fuzzy
Token fuzzy
Feature activation+0.000
sl
Token sl
Feature activation+0.000
make
Token make
Feature activation+0.085
files
Tokenfiles
Feature activation+0.000
(
Token (
Feature activation+1.364
this
Tokenthis
Feature activation+0.000
is
Token is
Feature activation+0.000
for
Token for
Feature activation+1.849
the
Token the
Feature activation+1.972
better
Token better
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
!
Token!
Feature activation+0.070
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.272
See
TokenSee
Feature activation+0.000
how
Token how
Feature activation+0.000
easy
Token easy
Feature activation+1.817
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.113
to
Token to
Feature activation+1.405
use
Token use
Feature activation+0.037
this
Token this
Feature activation+0.000

INTERVAL 0.838 - 1.676
CONTAINS 0.021%

DON
Token DON
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
T
TokenT
Feature activation+0.860
WANT
Token WANT
Feature activation+0.000
TO
Token TO
Feature activation+0.931
TA
Token TA
Feature activation+0.000
KE
TokenKE
Feature activation+0.000
THAT
Token THAT
Feature activation+0.000
CH
Token CH
Feature activation+0.000
ANCE
TokenANCE
Feature activation+0.000
super
Token super
Feature activation+0.000
happy
Token happy
Feature activation+1.669
when
Token when
Feature activation+1.611
i
Token i
Feature activation+0.951
came
Token came
Feature activation+0.000
across
Token across
Feature activation+1.495
it
Token it
Feature activation+0.859
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.108
Hey
TokenHey
Feature activation+0.256
there
Token there
Feature activation+0.000
so
Token so
Feature activation+0.000
i
Token i
Feature activation+0.000
was
Token was
Feature activation+0.000
super
Token super
Feature activation+0.000
happy
Token happy
Feature activation+1.669
when
Token when
Feature activation+1.611
i
Token i
Feature activation+0.951
came
Token came
Feature activation+0.000
across
Token across
Feature activation+1.495
it
Token it
Feature activation+0.859
Ċ
TokenĊ
Feature activation+0.000
migration
Token migration
Feature activation+0.722
-
Token-
Feature activation+0.355
up
Tokenup
Feature activation+0.000
:
Token:
Feature activation+1.309
docker
Token docker
Feature activation+0.272
-
Token-
Feature activation+0.844
com
Tokencom
Feature activation+0.000
pose
Tokenpose
Feature activation+0.000
run
Token run
Feature activation+0.415
--
Token --
Feature activation+1.096
rm
Tokenrm
Feature activation+0.525
them
Token them
Feature activation+0.000
memor
Token memor
Feature activation+0.000
ize
Tokenize
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+2.565
and
Token and
Feature activation+1.090
then
Token then
Feature activation+1.486
fl
Token fl
Feature activation+0.000
unk
Tokenunk
Feature activation+0.000
them
Token them
Feature activation+0.000
at
Token at
Feature activation+0.000

INTERVAL 0.000 - 0.838
CONTAINS 99.962%

While
TokenWhile
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
care
Token care
Feature activation+0.000
of
Token of
Feature activation+0.000
Anne
Token Anne
Feature activation+0.000
,
Token,
Feature activation+0.000
Louise
Token Louise
Feature activation+0.000
was
Token was
Feature activation+0.000
never
Token never
Feature activation+0.000
more
Token more
Feature activation+0.000
)
Token)
Feature activation+0.000
circles
Token circles
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
somehow
Token somehow
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
loss
Token loss
Feature activation+0.000
of
Token of
Feature activation+0.000
life
Token life
Feature activation+0.000
from
Token from
Feature activation+0.000
on
Token on
Feature activation+0.000
1
Token 1
Feature activation+0.000
April
Token April
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
.
Token.
Feature activation+0.000
Under
Token Under
Feature activation+0.000
the
Token the
Feature activation+0.000
terms
Token terms
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
initiative
Token initiative
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
explosion
Token explosion
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
labels
Token labels
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
same
Token same
Feature activation+0.000
thing
Token thing
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
more
Token more
Feature activation+0.000
diplom
Token diplom
Feature activation+0.000
atically
Tokenatically
Feature activation+0.000
,
Token,
Feature activation+0.000
asking
Token asking
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 H11.5: (feature 18040)

TOP ACTIVATIONS
MAX = 7.652

killed
Token killed
Feature activation+0.000
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
to
Token to
Feature activation+0.000
28
Token 28
Feature activation+0.000
.
Token.
Feature activation+7.652
H
Token H
Feature activation+0.000
é
Tokené
Feature activation+0.000
ctor
Tokenctor
Feature activation+1.059
Belt
Token Belt
Feature activation+0.000
r
Tokenr
Feature activation+0.000
rou
Tokenrou
Feature activation+0.000
ng
Tokenng
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
?
Token?
Feature activation+3.975
With
Token With
Feature activation+0.000
housing
Token housing
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
being
Token being
Feature activation+0.000
cut
Token cut
Feature activation+0.000
wear
Token wear
Feature activation+0.000
short
Token short
Feature activation+0.000
skirts
Token skirts
Feature activation+0.000
feels
Token feels
Feature activation+0.000
wrong
Token wrong
Feature activation+0.000
,
Token,
Feature activation+3.740
Say
Token Say
Feature activation+0.000
re
Tokenre
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
being
Token being
Feature activation+0.000
held
Token held
Feature activation+0.000
against
Token against
Feature activation+0.000
their
Token their
Feature activation+0.000
will
Token will
Feature activation+0.000
?
Token?
Feature activation+2.870
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
That
TokenThat
Feature activation+0.000
Must
Token Must
Feature activation+0.000
Enter
Token Enter
Feature activation+0.000
are
Token are
Feature activation+0.000
they
Token they
Feature activation+0.000
supposed
Token supposed
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
?
Token?
Feature activation+2.627
Sell
Token Sell
Feature activation+0.000
matches
Token matches
Feature activation+0.000
?
Token?
Feature activation+0.000
Cater
Token Cater
Feature activation+0.000
to
Token to
Feature activation+0.000
Are
Token Are
Feature activation+0.000
they
Token they
Feature activation+0.000
unable
Token unable
Feature activation+0.000
to
Token to
Feature activation+0.000
move
Token move
Feature activation+0.000
?
Token?
Feature activation+2.625
Are
Token Are
Feature activation+0.000
they
Token they
Feature activation+0.000
being
Token being
Feature activation+0.000
held
Token held
Feature activation+0.000
against
Token against
Feature activation+0.000
welfare
Token welfare
Feature activation+0.000
state
Token state
Feature activation+0.000
incompatible
Token incompatible
Feature activation+0.000
?
Token?
Feature activation+1.904
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.573
Since
TokenSince
Feature activation+0.000
the
Token the
Feature activation+0.000
1970
Token 1970
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
told
Token told
Feature activation+0.000
NEW
Token NEW
Feature activation+0.000
SW
TokenSW
Feature activation+0.000
EEK
TokenEEK
Feature activation+0.000
that
Token that
Feature activation+2.256
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000
president
Tokenpresident
Feature activation+0.000
declass
Token declass
Feature activation+0.000
ified
Tokenified
Feature activation+0.000
a
Token a
Feature activation+0.000
cunt
Token cunt
Feature activation+0.000
to
Token to
Feature activation+0.000
them
Token them
Feature activation+0.000
too
Token too
Feature activation+0.000
?
Token?
Feature activation+2.221
Are
Token Are
Feature activation+0.000
they
Token they
Feature activation+0.000
m
Token m
Feature activation+0.000
olly
Tokenolly
Feature activation+0.000
c
Tokenc
Feature activation+0.000
Are
Token Are
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
ano
Tokenano
Feature activation+0.000
was
Token was
Feature activation+0.000
arrested
Token arrested
Feature activation+0.000
by
Token by
Feature activation+2.189
soldiers
Token soldiers
Feature activation+0.000
of
Token of
Feature activation+0.244
the
Token the
Feature activation+0.000
Mexican
Token Mexican
Feature activation+0.000
Army
Token Army
Feature activation+0.000
what
Token what
Feature activation+0.000
you
Token you
Feature activation+0.000
see
Token see
Feature activation+0.000
.
Token.
Feature activation+0.429
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.154
Get
TokenGet
Feature activation+0.000
the
Token the
Feature activation+0.000
local
Token local
Feature activation+0.000
report
Token report
Feature activation+0.000
from
Token from
Feature activation+0.137
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
lawyer
Token lawyer
Feature activation+0.000
familiar
Token familiar
Feature activation+0.000
with
Token with
Feature activation+1.939
the
Token the
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
asked
Token asked
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
welfare
Token welfare
Feature activation+0.000
state
Token state
Feature activation+0.000
incompatible
Token incompatible
Feature activation+0.000
?
Token?
Feature activation+1.904
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.573
Since
TokenSince
Feature activation+0.000
the
Token the
Feature activation+0.000
1970
Token 1970
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
needed
Token needed
Feature activation+0.000
anymore
Token anymore
Feature activation+0.000
.
Token.
Feature activation+1.850
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.394
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
midst
Token midst
Feature activation+0.000
partner
Token partner
Feature activation+0.000
could
Token could
Feature activation+0.000
search
Token search
Feature activation+0.000
the
Token the
Feature activation+0.000
car
Token car
Feature activation+0.000
.
Token.
Feature activation+1.831
The
Token The
Feature activation+0.000
officers
Token officers
Feature activation+0.000
found
Token found
Feature activation+0.000
the
Token the
Feature activation+0.000
couple
Token couple
Feature activation+0.000
with
Token with
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
specific
Token specific
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
?
Token?
Feature activation+1.798
For
Token For
Feature activation+0.000
instance
Token instance
Feature activation+1.531
,
Token,
Feature activation+1.354
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
more
Token more
Feature activation+0.000
years
Token years
Feature activation+0.000
?
Token?
Feature activation+1.764
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
"
Token "
Feature activation+0.860
That
TokenThat
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
decision
Token decision
Feature activation+0.000
.
Token.
Feature activation+1.612
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.348
I
TokenI
Feature activation+0.000
believe
Token believe
Feature activation+0.000
we
Token we
Feature activation+0.000
tell
Token tell
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+1.611
are
Token are
Feature activation+0.000
cats
Token cats
Feature activation+0.000
smarter
Token smarter
Feature activation+0.000
because
Token because
Feature activation+0.000
they
Token they
Feature activation+0.000
,
Token,
Feature activation+0.000
B
Token B
Feature activation+0.000
aja
Tokenaja
Feature activation+0.000
California
Token California
Feature activation+0.000
,
Token,
Feature activation+0.000
bringing
Token bringing
Feature activation+1.573
the
Token the
Feature activation+0.000
total
Token total
Feature activation+0.000
captured
Token captured
Feature activation+0.000
or
Token or
Feature activation+0.000
killed
Token killed
Feature activation+0.000

Top DFA by src position
MAX = 8.742

Fernando
Token Fernando
Feature activation+0.057
Top resid features:
S
Token S
Feature activation+0.144
Top resid features:
án
Tokenán
Feature activation-0.021
Top resid features:
che
Tokenche
Feature activation+0.003
Top resid features:
z
Tokenz
Feature activation+0.001
Top resid features:
Are
Token Are
Feature activation+8.742
Top resid features:
ll
Tokenll
Feature activation+0.061
Top resid features:
ano
Tokenano
Feature activation+0.037
Top resid features:
was
Token was
Feature activation-0.004
Top resid features:
arrested
Token arrested
Feature activation-0.006
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.001
Top resid features:
they
Token they
Feature activation+0.001
Top resid features:
had
Token had
Feature activation-0.001
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.355
Top resid features:
Are
Token Are
Feature activation+2.808
Top resid features:
you
Token you
Feature activation+0.250
Top resid features:
going
Token going
Feature activation-0.004
Top resid features:
to
Token to
Feature activation-0.034
Top resid features:
be
Token be
Feature activation-0.023
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
âĢ
TokenâĢ
Feature activation-0.023
Top resid features:
Ŀ
TokenĿ
Feature activation+0.049
Top resid features:
L
Token L
Feature activation+0.205
Top resid features:
arkin
Tokenarkin
Feature activation+0.079
Top resid features:
Say
Token Say
Feature activation+4.645
Top resid features:
re
Tokenre
Feature activation+0.158
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
sophomore
Token sophomore
Feature activation+0.008
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
answer
Token answer
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
door
Token door
Feature activation+0.003
Top resid features:
:
Token:
Feature activation+0.094
Top resid features:
Are
Token Are
Feature activation+2.810
Top resid features:
they
Token they
Feature activation+0.097
Top resid features:
dead
Token dead
Feature activation+0.003
Top resid features:
?
Token?
Feature activation+0.255
Top resid features:
Are
Token Are
Feature activation+0.871
Top resid features:
they
Token they
Feature activation+0.016
Top resid features:
than
Token than
Feature activation+0.001
Top resid features:
they
Token they
Feature activation-0.000
Top resid features:
had
Token had
Feature activation-0.001
Top resid features:
before
Token before
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.284
Top resid features:
Are
Token Are
Feature activation+1.698
Top resid features:
you
Token you
Feature activation+0.124
Top resid features:
going
Token going
Feature activation-0.004
Top resid features:
to
Token to
Feature activation-0.040
Top resid features:
be
Token be
Feature activation-0.038
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
answer
Token answer
Feature activation+0.013
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
door
Token door
Feature activation+0.006
Top resid features:
:
Token:
Feature activation+0.104
Top resid features:
Are
Token Are
Feature activation+2.860
Top resid features:
they
Token they
Feature activation+0.152
Top resid features:
dead
Token dead
Feature activation+0.009
Top resid features:
?
Token?
Feature activation+0.334
Top resid features:
Are
Token Are
Feature activation+1.049
Top resid features:
they
Token they
Feature activation+0.032
Top resid features:
problems
Token problems
Feature activation-0.008
Top resid features:
presents
Token presents
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.243
Top resid features:
Ċ
TokenĊ
Feature activation+0.116
Top resid features:
Ċ
TokenĊ
Feature activation+0.207
Top resid features:
Are
TokenAre
Feature activation+3.519
Top resid features:
sustainable
Token sustainable
Feature activation+0.029
Top resid features:
growth
Token growth
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
the
Token the
Feature activation-0.011
Top resid features:
welfare
Token welfare
Feature activation+0.038
Top resid features:
believe
Token believe
Feature activation+0.040
Top resid features:
it
Token it
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
Michael
Token Michael
Feature activation+0.037
Top resid features:
Is
Token Is
Feature activation+3.226
Top resid features:
ik
Tokenik
Feature activation-0.011
Top resid features:
off
Tokenoff
Feature activation+0.007
Top resid features:
piece
Token piece
Feature activation+0.008
Top resid features:
?
Token?
Feature activation+0.040
Top resid features:
Ċ
TokenĊ
Feature activation+0.036
Top resid features:
than
Token than
Feature activation+0.002
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
had
Token had
Feature activation-0.002
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.427
Top resid features:
Are
Token Are
Feature activation+3.136
Top resid features:
you
Token you
Feature activation+0.408
Top resid features:
going
Token going
Feature activation-0.011
Top resid features:
to
Token to
Feature activation-0.049
Top resid features:
be
Token be
Feature activation-0.048
Top resid features:
a
Token a
Feature activation+0.011
Top resid features:
Fernando
Token Fernando
Feature activation+0.006
Top resid features:
S
Token S
Feature activation+0.065
Top resid features:
án
Tokenán
Feature activation+0.005
Top resid features:
che
Tokenche
Feature activation+0.004
Top resid features:
z
Tokenz
Feature activation+0.006
Top resid features:
Are
Token Are
Feature activation+3.734
Top resid features:
ll
Tokenll
Feature activation+0.073
Top resid features:
ano
Tokenano
Feature activation+0.015
Top resid features:
was
Token was
Feature activation+0.039
Top resid features:
arrested
Token arrested
Feature activation+0.043
Top resid features:
by
Token by
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
aging
Token aging
Feature activation-0.003
Top resid features:
population
Token population
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.063
Top resid features:
Are
TokenAre
Feature activation+3.219
Top resid features:
you
Token you
Feature activation+0.136
Top resid features:
there
Token there
Feature activation+0.043
Top resid features:
?
Token?
Feature activation+0.236
Top resid features:
Tell
Token Tell
Feature activation-0.018
Top resid features:
i
Token i
Feature activation+0.136
Top resid features:
believe
Token believe
Feature activation+0.045
Top resid features:
it
Token it
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
a
Token a
Feature activation+0.049
Top resid features:
Michael
Token Michael
Feature activation+0.094
Top resid features:
Is
Token Is
Feature activation+2.859
Top resid features:
ik
Tokenik
Feature activation-0.018
Top resid features:
off
Tokenoff
Feature activation+0.014
Top resid features:
piece
Token piece
Feature activation-0.000
Top resid features:
?
Token?
Feature activation+0.084
Top resid features:
Ċ
TokenĊ
Feature activation+0.033
Top resid features:
problems
Token problems
Feature activation-0.004
Top resid features:
presents
Token presents
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.327
Top resid features:
Ċ
TokenĊ
Feature activation+0.161
Top resid features:
Ċ
TokenĊ
Feature activation+0.134
Top resid features:
Are
TokenAre
Feature activation+3.026
Top resid features:
sustainable
Token sustainable
Feature activation+0.049
Top resid features:
growth
Token growth
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
welfare
Token welfare
Feature activation+0.055
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.083
Top resid features:
.
Token.
Feature activation+0.072
Top resid features:
Are
Token Are
Feature activation+1.684
Top resid features:
there
Token there
Feature activation+0.508
Top resid features:
any
Token any
Feature activation+0.038
Top resid features:
no
Token no
Feature activation+0.023
Top resid features:
-
Token-
Feature activation+0.005
Top resid features:
long
Tokenlong
Feature activation+0.003
Top resid features:
way
Token way
Feature activation-0.000
Top resid features:
onto
Token onto
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
highway
Token highway
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.073
Top resid features:
Were
Token Were
Feature activation+2.857
Top resid features:
there
Token there
Feature activation+0.170
Top resid features:
any
Token any
Feature activation+0.009
Top resid features:
drugs
Token drugs
Feature activation-0.018
Top resid features:
in
Token in
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.112
Top resid features:
.
Token.
Feature activation+0.128
Top resid features:
Are
Token Are
Feature activation+1.542
Top resid features:
there
Token there
Feature activation+0.631
Top resid features:
any
Token any
Feature activation+0.052
Top resid features:
no
Token no
Feature activation+0.027
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
long
Tokenlong
Feature activation+0.007
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
World
Token World
Feature activation-0.002
Top resid features:
Series
Token Series
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.079
Top resid features:
are
Token are
Feature activation+2.139
Top resid features:
you
Token you
Feature activation+0.840
Top resid features:
really
Token really
Feature activation+0.073
Top resid features:
going
Token going
Feature activation-0.005
Top resid features:
to
Token to
Feature activation-0.012
Top resid features:
push
Token push
Feature activation-0.018
Top resid features:
had
Token had
Feature activation-0.007
Top resid features:
to
Token to
Feature activation-0.011
Top resid features:
make
Token make
Feature activation-0.011
Top resid features:
was
Token was
Feature activation+0.014
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
are
Token are
Feature activation+2.577
Top resid features:
we
Token we
Feature activation+0.126
Top resid features:
going
Token going
Feature activation-0.005
Top resid features:
to
Token to
Feature activation-0.009
Top resid features:
cut
Token cut
Feature activation+0.034
Top resid features:
out
Token out
Feature activation+0.019
Top resid features:
.
Token.
Feature activation+0.057
Top resid features:
The
Token The
Feature activation-0.023
Top resid features:
argument
Token argument
Feature activation-0.003
Top resid features:
is
Token is
Feature activation+0.058
Top resid features:
:
Token:
Feature activation+0.032
Top resid features:
are
Token are
Feature activation+3.484
Top resid features:
dogs
Token dogs
Feature activation+0.113
Top resid features:
smarter
Token smarter
Feature activation-0.047
Top resid features:
than
Token than
Feature activation+0.001
Top resid features:
cats
Token cats
Feature activation-0.026
Top resid features:
because
Token because
Feature activation+0.050
Top resid features:
Fernando
Token Fernando
Feature activation+0.000
Top resid features:
S
Token S
Feature activation+0.092
Top resid features:
án
Tokenán
Feature activation-0.084
Top resid features:
che
Tokenche
Feature activation+0.004
Top resid features:
z
Tokenz
Feature activation-0.000
Top resid features:
Are
Token Are
Feature activation+2.641
Top resid features:
ll
Tokenll
Feature activation+0.136
Top resid features:
ano
Tokenano
Feature activation+0.026
Top resid features:
was
Token was
Feature activation+0.011
Top resid features:
arrested
Token arrested
Feature activation-0.007
Top resid features:
by
Token by
Feature activation+0.013
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.06

Head 2: 0.04

Head 3: 0.05

Head 4: 0.04

Head 5: 0.41

Head 6: 0.08

Head 7: 0.03

Head 8: 0.07

Head 9: 0.06

Head 10: 0.06

Head 11: 0.05

Positive logits

Are7.63

Are6.20

ARE5.38

are5.09

are4.84

Were4.82

Aren4.58

Were4.22

aren3.95

were3.74

Is3.66

Aren3.60

Do3.56

ARE3.55

Do3.49

Have3.42

were3.34

Have3.29

're3.27

Is3.18

Negative logits

rawdownloadcloneembedreportprint-2.39

pretended-2.20

drawing-2.19

draws-2.18

ONSORED-2.15

Austral-2.12

ounced-2.10

dismant-2.10

tremend-2.09

casts-2.04

ulz-2.03

drew-2.03

played-2.03

Works-2.03

arij-2.02

shed-2.02

ibur-2.01

oston-2.01

aughs-1.99

Anarchy-1.97

INTERVAL 6.886 - 7.652
CONTAINS 0.000%

killed
Token killed
Feature activation+0.000
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
to
Token to
Feature activation+0.000
28
Token 28
Feature activation+0.000
.
Token.
Feature activation+7.652
H
Token H
Feature activation+0.000
é
Tokené
Feature activation+0.000
ctor
Tokenctor
Feature activation+1.059
Belt
Token Belt
Feature activation+0.000
r
Tokenr
Feature activation+0.000

INTERVAL 6.121 - 6.886
CONTAINS 0.000%

INTERVAL 5.356 - 6.121
CONTAINS 0.000%

INTERVAL 4.591 - 5.356
CONTAINS 0.000%

INTERVAL 3.826 - 4.591
CONTAINS 0.000%

rou
Tokenrou
Feature activation+0.000
ng
Tokenng
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
?
Token?
Feature activation+3.975
With
Token With
Feature activation+0.000
housing
Token housing
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
being
Token being
Feature activation+0.000
cut
Token cut
Feature activation+0.000

INTERVAL 3.061 - 3.826
CONTAINS 0.000%

wear
Token wear
Feature activation+0.000
short
Token short
Feature activation+0.000
skirts
Token skirts
Feature activation+0.000
feels
Token feels
Feature activation+0.000
wrong
Token wrong
Feature activation+0.000
,
Token,
Feature activation+3.740
Say
Token Say
Feature activation+0.000
re
Tokenre
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000

INTERVAL 2.295 - 3.061
CONTAINS 0.000%

welfare
Token welfare
Feature activation+0.000
state
Token state
Feature activation+0.000
incompatible
Token incompatible
Feature activation+0.000
?
Token?
Feature activation+1.904
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.573
Since
TokenSince
Feature activation+0.000
the
Token the
Feature activation+0.000
1970
Token 1970
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
they
Token they
Feature activation+0.000
supposed
Token supposed
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
?
Token?
Feature activation+2.627
Sell
Token Sell
Feature activation+0.000
matches
Token matches
Feature activation+0.000
?
Token?
Feature activation+0.000
Cater
Token Cater
Feature activation+0.000
to
Token to
Feature activation+0.000
Are
Token Are
Feature activation+0.000
they
Token they
Feature activation+0.000
unable
Token unable
Feature activation+0.000
to
Token to
Feature activation+0.000
move
Token move
Feature activation+0.000
?
Token?
Feature activation+2.625
Are
Token Are
Feature activation+0.000
they
Token they
Feature activation+0.000
being
Token being
Feature activation+0.000
held
Token held
Feature activation+0.000
against
Token against
Feature activation+0.000
being
Token being
Feature activation+0.000
held
Token held
Feature activation+0.000
against
Token against
Feature activation+0.000
their
Token their
Feature activation+0.000
will
Token will
Feature activation+0.000
?
Token?
Feature activation+2.870
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
That
TokenThat
Feature activation+0.000
Must
Token Must
Feature activation+0.000
Enter
Token Enter
Feature activation+0.000

INTERVAL 1.530 - 2.295
CONTAINS 0.002%

partner
Token partner
Feature activation+0.000
could
Token could
Feature activation+0.000
search
Token search
Feature activation+0.000
the
Token the
Feature activation+0.000
car
Token car
Feature activation+0.000
.
Token.
Feature activation+1.831
The
Token The
Feature activation+0.000
officers
Token officers
Feature activation+0.000
found
Token found
Feature activation+0.000
the
Token the
Feature activation+0.000
couple
Token couple
Feature activation+0.000
,
Token,
Feature activation+0.000
B
Token B
Feature activation+0.000
aja
Tokenaja
Feature activation+0.000
California
Token California
Feature activation+0.000
,
Token,
Feature activation+0.000
bringing
Token bringing
Feature activation+1.573
the
Token the
Feature activation+0.000
total
Token total
Feature activation+0.000
captured
Token captured
Feature activation+0.000
or
Token or
Feature activation+0.000
killed
Token killed
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
lawyer
Token lawyer
Feature activation+0.000
familiar
Token familiar
Feature activation+0.000
with
Token with
Feature activation+1.939
the
Token the
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
asked
Token asked
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
needed
Token needed
Feature activation+0.000
anymore
Token anymore
Feature activation+0.000
.
Token.
Feature activation+1.850
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.394
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
midst
Token midst
Feature activation+0.000
"
Token "
Feature activation+0.860
That
TokenThat
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
decision
Token decision
Feature activation+0.000
.
Token.
Feature activation+1.612
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.348
I
TokenI
Feature activation+0.000
believe
Token believe
Feature activation+0.000

INTERVAL 0.765 - 1.530
CONTAINS 0.004%

YOU
Token YOU
Feature activation+0.000
in
Token in
Feature activation+0.000
mind
Token mind
Feature activation+0.000
?
Token?
Feature activation+0.797
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.344
Then
TokenThen
Feature activation+0.686
,
Token,
Feature activation+0.814
you
Token you
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
Technology
Token Technology
Feature activation+0.000
told
Token told
Feature activation+0.000
NPR
Token NPR
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.845
Suggest
TokenSuggest
Feature activation+0.000
ing
Tokening
Feature activation+0.000
women
Token women
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
?
Token?
Feature activation+1.798
For
Token For
Feature activation+0.000
instance
Token instance
Feature activation+1.531
,
Token,
Feature activation+1.354
if
Token if
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
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
So
TokenSo
Feature activation+0.406
,
Token,
Feature activation+1.096
shall
Token shall
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
party
Token party
Feature activation+0.000
Pyrrha
Token Pyrrha
Feature activation+0.000
asked
Token asked
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+1.517
Oh
TokenOh
Feature activation+0.000
yeah
Token yeah
Feature activation+0.000
."
Token."
Feature activation+0.000
Sun
Token Sun
Feature activation+0.000
said
Token said
Feature activation+0.000

INTERVAL 0.000 - 0.765
CONTAINS 99.994%

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
not
Token not
Feature activation+0.000
incredibly
Token incredibly
Feature activation+0.000
common
Token common
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
of
Token of
Feature activation+0.000
under
Token under
Feature activation+0.000
app
Tokenapp
Feature activation+0.000
reci
Tokenreci
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
journey
Token journey
Feature activation+0.000
men
Tokenmen
Feature activation+0.000
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
shown
Token shown
Feature activation+0.000
a
Token a
Feature activation+0.000
will
Token will
Feature activation+0.000
create
Token create
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Obamacare
Token Obamacare
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
health
Token health
Feature activation+0.000
-
Token-
Feature activation+0.000
ins
Tokenins
Feature activation+0.000
then
Token then
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
released
Token released
Feature activation+0.000
his
Token his
Feature activation+0.000
actual
Token actual
Feature activation+0.000
tax
Token tax
Feature activation+0.000
plan
Token plan
Feature activation+0.000
âĢĶ
Token âĢĶ
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
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
In
TokenIn
Feature activation+0.000
addition
Token addition
Feature activation+0.000
to
Token to
Feature activation+0.000
seeking
Token seeking
Feature activation+0.000
an
Token an
Feature activation+0.000
emergency
Token emergency
Feature activation+0.000
declaration
Token declaration
Feature activation+0.000
,
Token,
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 H11.5: (feature 970)

TOP ACTIVATIONS
MAX = 7.166

that
Token that
Feature activation+0.486
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
word
Token word
Feature activation+6.323
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+7.166
t
Tokent
Feature activation+4.528
akes
Tokenakes
Feature activation+2.062
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
Heritage
Token Heritage
Feature activation+0.000
Dictionary
Token Dictionary
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+6.896
61
Token 61
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
usage
Token usage
Feature activation+0.000
as
Token as
Feature activation+0.000
The
Token The
Feature activation+0.000
opinion
Token opinion
Feature activation+0.000
noted
Token noted
Feature activation+0.000
that
Token that
Feature activation+0.395
the
Token the
Feature activation+0.000
word
Token word
Feature activation+6.480
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+6.394
t
Tokent
Feature activation+1.812
akes
Tokenakes
Feature activation+0.957
âĢ
TokenâĢ
Feature activation+0.000
noted
Token noted
Feature activation+0.000
that
Token that
Feature activation+0.395
the
Token the
Feature activation+0.000
word
Token word
Feature activation+6.480
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+6.394
t
Tokent
Feature activation+1.812
akes
Tokenakes
Feature activation+0.957
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
property
Token property
Feature activation+0.000
.
Token.
Feature activation+0.000
Nor
Token Nor
Feature activation+0.000
does
Token does
Feature activation+2.006
the
Token the
Feature activation+0.000
word
Token word
Feature activation+6.338
require
Token require
Feature activation+0.000
movement
Token movement
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
common
Token common
Feature activation+0.000
also
Token also
Feature activation+0.000
said
Token said
Feature activation+0.428
that
Token that
Feature activation+0.486
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
word
Token word
Feature activation+6.323
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+7.166
t
Tokent
Feature activation+4.528
akes
Tokenakes
Feature activation+2.062
âĢ
TokenâĢ
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
just
Token just
Feature activation+0.000
7
Token 7
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+6.278
saying
Token saying
Feature activation+0.000
earth
Token earth
Feature activation+0.000
has
Token has
Feature activation+0.000
definitely
Token definitely
Feature activation+0.000
been
Token been
Feature activation+0.000
movement
Token movement
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
word
Token word
Feature activation+2.419
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+6.078
would
Tokenwould
Feature activation+0.000
become
Token become
Feature activation+0.000
entirely
Token entirely
Feature activation+0.000
interchangeable
Token interchangeable
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
owners
Token owners
Feature activation+0.000
alike
Token alike
Feature activation+0.000
,
Token,
Feature activation+1.239
the
Token the
Feature activation+0.669
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+6.001
Take
TokenTake
Feature activation+0.136
a
Token a
Feature activation+0.000
knee
Token knee
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
near
Token near
Feature activation+0.000
the
Token the
Feature activation+0.000
enormous
Token enormous
Feature activation+0.737
per
Token per
Feature activation+0.000
-
Token-
Feature activation+0.000
screen
Tokenscreen
Feature activation+5.235
average
Token average
Feature activation+0.000
of
Token of
Feature activation+0.000
an
Token an
Feature activation+0.000
blockbuster
Token blockbuster
Feature activation+0.000
new
Token new
Feature activation+0.000
The
Token The
Feature activation+0.996
Franco
Token Franco
Feature activation+0.000
-
Token-
Feature activation+0.000
English
TokenEnglish
Feature activation+0.000
name
Token name
Feature activation+0.537
of
Token of
Feature activation+5.003
the
Token the
Feature activation+0.653
is
Token is
Feature activation+0.000
lets
Tokenlets
Feature activation+0.000
derives
Token derives
Feature activation+0.000
from
Token from
Feature activation+4.316
âĢĵ
TokenâĢĵ
Feature activation+0.000
When
Token When
Feature activation+0.605
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+4.916
taking
Token taking
Feature activation+0.000
off
Token off
Feature activation+0.000
your
Token your
Feature activation+0.071
walk
Token walk
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
are
Token are
Feature activation+0.000
holding
Token holding
Feature activation+0.000
a
Token a
Feature activation+0.000
relay
Token relay
Feature activation+0.000
swim
Token swim
Feature activation+0.000
of
Token of
Feature activation+4.872
220
Token 220
Feature activation+0.000
km
Token km
Feature activation+0.000
from
Token from
Feature activation+3.936
the
Token the
Feature activation+0.000
South
Token South
Feature activation+0.000
Policy
Token Policy
Feature activation+0.000
here
Token here
Feature activation+0.000
.
Token.
Feature activation+0.000
Sign
Token Sign
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+4.827
Take
Token Take
Feature activation+0.000
Action
Token Action
Feature activation+0.000
Now
Token Now
Feature activation+0.000
and
Token and
Feature activation+0.000
get
Token get
Feature activation+0.000
will
Token will
Feature activation+0.000
receive
Token receive
Feature activation+3.413
occasional
Token occasional
Feature activation+2.069
promotional
Token promotional
Feature activation+0.000
offers
Token offers
Feature activation+0.000
for
Token for
Feature activation+4.751
programs
Token programs
Feature activation+0.000
that
Token that
Feature activation+0.000
support
Token support
Feature activation+4.638
The
Token The
Feature activation+2.955
Nation
Token Nation
Feature activation+0.000
promotional
Token promotional
Feature activation+0.000
offers
Token offers
Feature activation+0.000
for
Token for
Feature activation+4.751
programs
Token programs
Feature activation+0.000
that
Token that
Feature activation+0.000
support
Token support
Feature activation+4.638
The
Token The
Feature activation+2.955
Nation
Token Nation
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
property
Token property
Feature activation+0.000
;
Token;
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+4.605
government
Token government
Feature activation+0.771
entity
Token entity
Feature activation+0.000
to
Token to
Feature activation+0.700
be
Token be
Feature activation+0.433
responsible
Token responsible
Feature activation+0.000
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
word
Token word
Feature activation+6.323
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+7.166
t
Tokent
Feature activation+4.528
akes
Tokenakes
Feature activation+2.062
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
you
Token you
Feature activation+0.000
would
Token would
Feature activation+0.000
get
Token get
Feature activation+0.000
in
Token in
Feature activation+0.000
trouble
Token trouble
Feature activation+0.000
for
Token for
Feature activation+4.418
taking
Token taking
Feature activation+0.000
a
Token a
Feature activation+0.000
gun
Token gun
Feature activation+0.000
to
Token to
Feature activation+0.000
class
Token class
Feature activation+0.000
of
Token of
Feature activation+5.003
the
Token the
Feature activation+0.653
is
Token is
Feature activation+0.000
lets
Tokenlets
Feature activation+0.000
derives
Token derives
Feature activation+0.000
from
Token from
Feature activation+4.316
Le
Token Le
Feature activation+0.000
L
Token L
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
court
Tokencourt
Feature activation+0.000
,
Token,
Feature activation+0.424

Top DFA by src position
MAX = 8.103

definition
Token definition
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.015
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.005
Top resid features:
t
Tokent
Feature activation+0.122
Top resid features:
akes
Tokenakes
Feature activation+4.512
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation-0.001
Top resid features:
one
Tokenone
Feature activation+0.005
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
The
TokenThe
Feature activation+0.028
Top resid features:
word
Token word
Feature activation+0.001
Top resid features:
âĢ
Token âĢ
Feature activation+0.177
Top resid features:
ľ
Tokenľ
Feature activation-0.011
Top resid features:
take
Tokentake
Feature activation+8.103
Top resid features:
âĢ
TokenâĢ
Feature activation+0.054
Top resid features:
Ŀ
TokenĿ
Feature activation+0.036
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
ambiguous
Token ambiguous
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
definition
Token definition
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.025
Top resid features:
âĢ
Token âĢ
Feature activation+0.093
Top resid features:
ľ
Tokenľ
Feature activation+0.020
Top resid features:
t
Tokent
Feature activation+0.059
Top resid features:
akes
Tokenakes
Feature activation+7.638
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
Ŀ
TokenĿ
Feature activation+0.024
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.016
Top resid features:
one
Tokenone
Feature activation+0.019
Top resid features:
that
Token that
Feature activation+0.013
Top resid features:
definition
Token definition
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.034
Top resid features:
âĢ
Token âĢ
Feature activation+0.011
Top resid features:
ľ
Tokenľ
Feature activation+0.013
Top resid features:
t
Tokent
Feature activation+0.231
Top resid features:
akes
Tokenakes
Feature activation+7.437
Top resid features:
âĢ
TokenâĢ
Feature activation+0.003
Top resid features:
Ŀ
TokenĿ
Feature activation+0.019
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.005
Top resid features:
one
Tokenone
Feature activation+0.024
Top resid features:
that
Token that
Feature activation+0.015
Top resid features:
definition
Token definition
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.018
Top resid features:
âĢ
Token âĢ
Feature activation+0.022
Top resid features:
ľ
Tokenľ
Feature activation+0.016
Top resid features:
t
Tokent
Feature activation+0.028
Top resid features:
akes
Tokenakes
Feature activation+4.894
Top resid features:
âĢ
TokenâĢ
Feature activation+0.003
Top resid features:
Ŀ
TokenĿ
Feature activation+0.011
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.009
Top resid features:
one
Tokenone
Feature activation+0.006
Top resid features:
that
Token that
Feature activation+0.005
Top resid features:
definition
Token definition
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
âĢ
Token âĢ
Feature activation+0.070
Top resid features:
ľ
Tokenľ
Feature activation+0.011
Top resid features:
t
Tokent
Feature activation+0.012
Top resid features:
akes
Tokenakes
Feature activation+4.885
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+0.009
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.004
Top resid features:
one
Tokenone
Feature activation+0.004
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
are
Token are
Feature activation+0.013
Top resid features:
equally
Token equally
Feature activation+0.002
Top resid features:
as
Token as
Feature activation+0.004
Top resid features:
likely
Token likely
Feature activation+0.007
Top resid features:
to
Token to
Feature activation+0.017
Top resid features:
take
Token take
Feature activation+7.908
Top resid features:
each
Token each
Feature activation+0.007
Top resid features:
side
Token side
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
debate
Token debate
Feature activation+0.006
Top resid features:
definition
Token definition
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:
âĢ
Token âĢ
Feature activation+0.001
Top resid features:
ľ
Tokenľ
Feature activation+0.002
Top resid features:
t
Tokent
Feature activation+0.071
Top resid features:
akes
Tokenakes
Feature activation+3.250
Top resid features:
âĢ
TokenâĢ
Feature activation-0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.005
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation-0.001
Top resid features:
one
Tokenone
Feature activation+0.004
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
stance
Token stance
Feature activation+0.028
Top resid features:
against
Token against
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
âĢ
Token âĢ
Feature activation+0.007
Top resid features:
ĺ
Tokenĺ
Feature activation+0.009
Top resid features:
Take
TokenTake
Feature activation+6.705
Top resid features:
a
Token a
Feature activation+0.246
Top resid features:
knee
Token knee
Feature activation+0.094
Top resid features:
âĢ
TokenâĢ
Feature activation+0.024
Top resid features:
Ļ
TokenĻ
Feature activation+0.025
Top resid features:
anthem
Token anthem
Feature activation+0.009
Top resid features:
Sources
Token Sources
Feature activation+0.006
Top resid features:
say
Token say
Feature activation+0.014
Top resid features:
an
Token an
Feature activation-0.005
Top resid features:
average
Token average
Feature activation-0.000
Top resid features:
weekend
Token weekend
Feature activation-0.032
Top resid features:
take
Token take
Feature activation+6.880
Top resid features:
for
Token for
Feature activation+0.019
Top resid features:
an
Token an
Feature activation+0.001
Top resid features:
I
Token I
Feature activation+0.170
Top resid features:
MAX
TokenMAX
Feature activation+0.003
Top resid features:
theater
Token theater
Feature activation+0.027
Top resid features:
fecture
Tokenfecture
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+0.044
Top resid features:
calls
Token calls
Feature activation+0.027
Top resid features:
them
Token them
Feature activation+0.018
Top resid features:
Takes
Token Takes
Feature activation+6.293
Top resid features:
h
Tokenh
Feature activation+0.039
Top resid features:
ima
Tokenima
Feature activation+0.013
Top resid features:
(
Token (
Feature activation+0.038
Top resid features:
ç«
Tokenç«
Feature activation+0.002
Top resid features:
¹
Token¹
Feature activation+0.004
Top resid features:
When
Token When
Feature activation+0.004
Top resid features:
you
Token you
Feature activation+0.006
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.021
Top resid features:
re
Tokenre
Feature activation+0.020
Top resid features:
taking
Token taking
Feature activation+6.342
Top resid features:
off
Token off
Feature activation+0.051
Top resid features:
your
Token your
Feature activation+0.014
Top resid features:
walk
Token walk
Feature activation-0.005
Top resid features:
ie
Tokenie
Feature activation+0.003
Top resid features:
talk
Token talk
Feature activation+0.002
Top resid features:
do
Tokendo
Feature activation+0.097
Top resid features:
in
Token in
Feature activation+0.047
Top resid features:
South
Token South
Feature activation+0.002
Top resid features:
Korea
Token Korea
Feature activation+0.022
Top resid features:
and
Token and
Feature activation+0.034
Top resid features:
Takes
Token Takes
Feature activation+6.070
Top resid features:
h
Tokenh
Feature activation+0.055
Top resid features:
ima
Tokenima
Feature activation+0.039
Top resid features:
in
Token in
Feature activation+0.013
Top resid features:
Japan
Token Japan
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
back
Token back
Feature activation+0.009
Top resid features:
?
Token?
Feature activation-0.003
Top resid features:
Sign
Token Sign
Feature activation-0.019
Top resid features:
up
Token up
Feature activation+0.007
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
Take
Token Take
Feature activation+6.499
Top resid features:
Action
Token Action
Feature activation+0.111
Top resid features:
Now
Token Now
Feature activation+0.032
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
get
Token get
Feature activation+0.016
Top resid features:
three
Token three
Feature activation-0.011
Top resid features:
back
Token back
Feature activation+0.005
Top resid features:
?
Token?
Feature activation-0.001
Top resid features:
Sign
Token Sign
Feature activation-0.044
Top resid features:
up
Token up
Feature activation+0.007
Top resid features:
for
Token for
Feature activation+0.013
Top resid features:
Take
Token Take
Feature activation+6.676
Top resid features:
Action
Token Action
Feature activation+0.037
Top resid features:
Now
Token Now
Feature activation+0.056
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
get
Token get
Feature activation+0.004
Top resid features:
three
Token three
Feature activation-0.020
Top resid features:
back
Token back
Feature activation+0.025
Top resid features:
?
Token?
Feature activation+0.007
Top resid features:
Sign
Token Sign
Feature activation-0.001
Top resid features:
up
Token up
Feature activation+0.009
Top resid features:
for
Token for
Feature activation+0.016
Top resid features:
Take
Token Take
Feature activation+6.419
Top resid features:
Action
Token Action
Feature activation+0.089
Top resid features:
Now
Token Now
Feature activation+0.106
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
get
Token get
Feature activation+0.006
Top resid features:
three
Token three
Feature activation+0.000
Top resid features:
passive
Token passive
Feature activation+0.085
Top resid features:
inaction
Token inaction
Feature activation+0.015
Top resid features:
was
Token was
Feature activation+0.003
Top resid features:
not
Token not
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.015
Top resid features:
taking
Token taking
Feature activation+5.824
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
or
Token or
Feature activation+0.007
Top resid features:
condemnation
Token condemnation
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.036
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
word
Token word
Feature activation+0.004
Top resid features:
âĢ
Token âĢ
Feature activation+0.003
Top resid features:
ľ
Tokenľ
Feature activation-0.002
Top resid features:
t
Tokent
Feature activation+0.038
Top resid features:
akes
Tokenakes
Feature activation+3.850
Top resid features:
âĢ
TokenâĢ
Feature activation+0.008
Top resid features:
Ŀ
TokenĿ
Feature activation-0.003
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
state
Token state
Feature activation+0.003
Top resid features:
would
Token would
Feature activation-0.009
Top resid features:
receive
Token receive
Feature activation+0.016
Top resid features:
a
Token a
Feature activation+0.011
Top resid features:
citation
Token citation
Feature activation+0.010
Top resid features:
for
Token for
Feature activation+0.016
Top resid features:
taking
Token taking
Feature activation+5.658
Top resid features:
a
Token a
Feature activation+0.261
Top resid features:
D
Token D
Feature activation-0.130
Top resid features:
IL
TokenIL
Feature activation+0.012
Top resid features:
DO
TokenDO
Feature activation+0.092
Top resid features:
to
Token to
Feature activation+0.070
Top resid features:
fecture
Tokenfecture
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+0.027
Top resid features:
calls
Token calls
Feature activation+0.012
Top resid features:
them
Token them
Feature activation+0.013
Top resid features:
Takes
Token Takes
Feature activation+5.460
Top resid features:
h
Tokenh
Feature activation+0.033
Top resid features:
ima
Tokenima
Feature activation+0.013
Top resid features:
(
Token (
Feature activation+0.043
Top resid features:
ç«
Tokenç«
Feature activation+0.004
Top resid features:
¹
Token¹
Feature activation+0.010
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.04

Head 3: 0.06

Head 4: 0.04

Head 5: 0.41

Head 6: 0.06

Head 7: 0.03

Head 8: 0.06

Head 9: 0.09

Head 10: 0.04

Head 11: 0.07

Positive logits

Take8.23

Take7.80

take7.27

take7.00

takes5.81

Taking5.76

Taking5.70

taking5.67

Takes5.62

taken5.51

taking5.46

took5.44

Taken5.23

heimer2.75

takeaway2.73

retake2.65

Consider2.65

Consider2.63

seize2.57

Onion2.56

Negative logits

ulhu-2.48

glers-2.47

ortex-2.45

bright-2.43

iment-2.35

ench-2.33

wit-2.27

hid-2.26

ilk-2.24

ieu-2.22

idth-2.18

etime-2.17

ula-2.17

ourt-2.16

atten-2.15

��-2.14

ern-2.13

cle-2.13

piping-2.11

acci-2.10

INTERVAL 6.449 - 7.166
CONTAINS 0.000%

The
Token The
Feature activation+0.000
opinion
Token opinion
Feature activation+0.000
noted
Token noted
Feature activation+0.000
that
Token that
Feature activation+0.395
the
Token the
Feature activation+0.000
word
Token word
Feature activation+6.480
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+6.394
t
Tokent
Feature activation+1.812
akes
Tokenakes
Feature activation+0.957
âĢ
TokenâĢ
Feature activation+0.000
that
Token that
Feature activation+0.486
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
word
Token word
Feature activation+6.323
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+7.166
t
Tokent
Feature activation+4.528
akes
Tokenakes
Feature activation+2.062
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
Heritage
Token Heritage
Feature activation+0.000
Dictionary
Token Dictionary
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+6.896
61
Token 61
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
usage
Token usage
Feature activation+0.000
as
Token as
Feature activation+0.000

INTERVAL 5.733 - 6.449
CONTAINS 0.001%

also
Token also
Feature activation+0.000
said
Token said
Feature activation+0.428
that
Token that
Feature activation+0.486
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
word
Token word
Feature activation+6.323
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+7.166
t
Tokent
Feature activation+4.528
akes
Tokenakes
Feature activation+2.062
âĢ
TokenâĢ
Feature activation+0.000
movement
Token movement
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
word
Token word
Feature activation+2.419
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+6.078
would
Tokenwould
Feature activation+0.000
become
Token become
Feature activation+0.000
entirely
Token entirely
Feature activation+0.000
interchangeable
Token interchangeable
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
owners
Token owners
Feature activation+0.000
alike
Token alike
Feature activation+0.000
,
Token,
Feature activation+1.239
the
Token the
Feature activation+0.669
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+6.001
Take
TokenTake
Feature activation+0.136
a
Token a
Feature activation+0.000
knee
Token knee
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
noted
Token noted
Feature activation+0.000
that
Token that
Feature activation+0.395
the
Token the
Feature activation+0.000
word
Token word
Feature activation+6.480
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+6.394
t
Tokent
Feature activation+1.812
akes
Tokenakes
Feature activation+0.957
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
just
Token just
Feature activation+0.000
7
Token 7
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+6.278
saying
Token saying
Feature activation+0.000
earth
Token earth
Feature activation+0.000
has
Token has
Feature activation+0.000
definitely
Token definitely
Feature activation+0.000
been
Token been
Feature activation+0.000

INTERVAL 5.016 - 5.733
CONTAINS 0.000%

near
Token near
Feature activation+0.000
the
Token the
Feature activation+0.000
enormous
Token enormous
Feature activation+0.737
per
Token per
Feature activation+0.000
-
Token-
Feature activation+0.000
screen
Tokenscreen
Feature activation+5.235
average
Token average
Feature activation+0.000
of
Token of
Feature activation+0.000
an
Token an
Feature activation+0.000
blockbuster
Token blockbuster
Feature activation+0.000
new
Token new
Feature activation+0.000

INTERVAL 4.299 - 5.016
CONTAINS 0.001%

The
Token The
Feature activation+0.996
Franco
Token Franco
Feature activation+0.000
-
Token-
Feature activation+0.000
English
TokenEnglish
Feature activation+0.000
name
Token name
Feature activation+0.537
of
Token of
Feature activation+5.003
the
Token the
Feature activation+0.653
is
Token is
Feature activation+0.000
lets
Tokenlets
Feature activation+0.000
derives
Token derives
Feature activation+0.000
from
Token from
Feature activation+4.316
you
Token you
Feature activation+0.000
would
Token would
Feature activation+0.000
get
Token get
Feature activation+0.000
in
Token in
Feature activation+0.000
trouble
Token trouble
Feature activation+0.000
for
Token for
Feature activation+4.418
taking
Token taking
Feature activation+0.000
a
Token a
Feature activation+0.000
gun
Token gun
Feature activation+0.000
to
Token to
Feature activation+0.000
class
Token class
Feature activation+0.000
Policy
Token Policy
Feature activation+0.000
here
Token here
Feature activation+0.000
.
Token.
Feature activation+0.000
Sign
Token Sign
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+4.827
Take
Token Take
Feature activation+0.000
Action
Token Action
Feature activation+0.000
Now
Token Now
Feature activation+0.000
and
Token and
Feature activation+0.000
get
Token get
Feature activation+0.000
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
word
Token word
Feature activation+6.323
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+7.166
t
Tokent
Feature activation+4.528
akes
Tokenakes
Feature activation+2.062
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
property
Token property
Feature activation+0.000
;
Token;
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+4.605
government
Token government
Feature activation+0.771
entity
Token entity
Feature activation+0.000
to
Token to
Feature activation+0.700
be
Token be
Feature activation+0.433
responsible
Token responsible
Feature activation+0.000

INTERVAL 3.583 - 4.299
CONTAINS 0.001%

;
Token;
Feature activation+4.289
the
Token the
Feature activation+0.419
total
Token total
Feature activation+0.000
surface
Token surface
Feature activation+0.000
area
Token area
Feature activation+0.000
of
Token of
Feature activation+3.808
the
Token the
Feature activation+0.000
is
Token is
Feature activation+0.000
lets
Tokenlets
Feature activation+0.000
is
Token is
Feature activation+0.000
0
Token 0
Feature activation+0.000
from
Token from
Feature activation+3.936
the
Token the
Feature activation+0.000
South
Token South
Feature activation+0.000
Korean
Token Korean
Feature activation+0.000
coast
Token coast
Feature activation+0.000
to
Token to
Feature activation+4.064
the
Token the
Feature activation+0.576
islands
Token islands
Feature activation+0.000
in
Token in
Feature activation+0.067
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.758
t
Tokent
Feature activation+0.000
include
Token include
Feature activation+2.907
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+3.865
to
Tokento
Feature activation+2.880
seize
Token seize
Feature activation+0.000
with
Token with
Feature activation+0.435
authority
Token authority
Feature activation+0.000
or
Token or
Feature activation+0.418
in
Token in
Feature activation+0.000
official
Token official
Feature activation+0.000
competitions
Token competitions
Feature activation+0.000
;
Token;
Feature activation+0.000
Arena
Token Arena
Feature activation+0.316
17
Token 17
Feature activation+3.880
of
Token of
Feature activation+0.000
45
Token 45
Feature activation+0.938
;
Token;
Feature activation+0.000
Bradley
Token Bradley
Feature activation+0.000
10
Token 10
Feature activation+0.000
Policy
Token Policy
Feature activation+0.000
here
Token here
Feature activation+0.000
.
Token.
Feature activation+0.000
Sign
Token Sign
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+3.971
Take
Token Take
Feature activation+0.000
Action
Token Action
Feature activation+0.000
Now
Token Now
Feature activation+0.000
and
Token and
Feature activation+0.000
get
Token get
Feature activation+0.000

INTERVAL 2.866 - 3.583
CONTAINS 0.002%

ľ
Tokenľ
Feature activation+0.009
if
Tokenif
Feature activation+0.083
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+3.100
involved
Token involved
Feature activation+0.000
in
Token in
Feature activation+0.797
something
Token something
Feature activation+0.310
important
Token important
Feature activation+0.000
,
Token,
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
fired
Token fired
Feature activation+0.000
.
Token.
Feature activation+0.241
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.917
While
TokenWhile
Feature activation+2.342
his
Token his
Feature activation+0.000
comments
Token comments
Feature activation+0.000
caused
Token caused
Feature activation+0.000
a
Token a
Feature activation+0.000
offers
Token offers
Feature activation+0.000
for
Token for
Feature activation+4.751
programs
Token programs
Feature activation+0.000
that
Token that
Feature activation+0.000
support
Token support
Feature activation+4.638
The
Token The
Feature activation+2.955
Nation
Token Nation
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
journalism
Token journalism
Feature activation+0.000
that
Token that
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.758
t
Tokent
Feature activation+0.000
include
Token include
Feature activation+2.907
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+3.865
to
Tokento
Feature activation+2.880
seize
Token seize
Feature activation+0.000
with
Token with
Feature activation+0.435
every
Token every
Feature activation+0.000
week
Token week
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
will
Token will
Feature activation+0.000
receive
Token receive
Feature activation+3.413
occasional
Token occasional
Feature activation+2.069
promotional
Token promotional
Feature activation+0.000
offers
Token offers
Feature activation+0.000
for
Token for
Feature activation+4.751
programs
Token programs
Feature activation+0.000

INTERVAL 2.150 - 2.866
CONTAINS 0.003%

percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
Hornets
Token Hornets
Feature activation+0.366
fans
Token fans
Feature activation+0.233
would
Token would
Feature activation+2.252
have
Token have
Feature activation+2.388
picked
Token picked
Feature activation+0.000
another
Token another
Feature activation+0.000
player
Token player
Feature activation+0.000
over
Token over
Feature activation+0.000
Monk
Token Monk
Feature activation+0.000
immers
Tokenimmers
Feature activation+0.000
,
Token,
Feature activation+0.000
led
Token led
Feature activation+0.000
by
Token by
Feature activation+0.727
pop
Token pop
Feature activation+0.000
singer
Token singer
Feature activation+2.771
Kim
Token Kim
Feature activation+0.144
J
Token J
Feature activation+0.000
ang
Tokenang
Feature activation+0.000
-
Token-
Feature activation+0.000
h
Tokenh
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
with
Token with
Feature activation+0.000
bipolar
Token bipolar
Feature activation+0.000
disorder
Token disorder
Feature activation+4.097
,
Token,
Feature activation+1.294
then
Token then
Feature activation+2.550
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
buy
Token buy
Feature activation+0.000
came
Token came
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+0.000
being
Token being
Feature activation+0.000
wrecked
Token wrecked
Feature activation+0.000
on
Token on
Feature activation+2.801
the
Token the
Feature activation+0.934
rocks
Token rocks
Feature activation+0.000
in
Token in
Feature activation+3.513
18
Token 18
Feature activation+0.000
49
Token49
Feature activation+0.000
shouldn
Token shouldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
go
Token go
Feature activation+0.000
.
Token.
Feature activation+2.429
But
Token But
Feature activation+0.000
âĢ¦.
TokenâĢ¦.
Feature activation+0.653
ok
Tokenok
Feature activation+0.000
.
Token.
Feature activation+2.483
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 1.433 - 2.150
CONTAINS 0.005%

.
Token.
Feature activation+1.450
At
Token At
Feature activation+0.000
114
Token 114
Feature activation+0.000
gold
Token gold
Feature activation+0.392
a
Token a
Feature activation+0.000
minute
Token minute
Feature activation+1.665
,
Token,
Feature activation+1.629
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
week
Token week
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
will
Token will
Feature activation+0.000
receive
Token receive
Feature activation+3.413
occasional
Token occasional
Feature activation+2.069
promotional
Token promotional
Feature activation+0.000
offers
Token offers
Feature activation+0.000
for
Token for
Feature activation+4.751
programs
Token programs
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.105
a
Token a
Feature activation+0.000
boolean
Token boolean
Feature activation+0.000
to
Token to
Feature activation+0.000
not
Token not
Feature activation+1.754
interrupt
Token interrupt
Feature activation+0.274
when
Token when
Feature activation+1.849
a
Token a
Feature activation+0.278
dialog
Token dialog
Feature activation+0.000
is
Token is
Feature activation+0.078
because
Token because
Feature activation+0.000
a
Token a
Feature activation+0.000
smartphone
Token smartphone
Feature activation+0.000
will
Token will
Feature activation+0.678
not
Token not
Feature activation+2.156
always
Token always
Feature activation+1.906
utilize
Token utilize
Feature activation+0.000
its
Token its
Feature activation+0.000
maximum
Token maximum
Feature activation+0.000
charging
Token charging
Feature activation+0.000
speed
Token speed
Feature activation+0.000
majority
Token majority
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
rights
Token rights
Feature activation+0.000
...
Token...
Feature activation+0.687
And
Token And
Feature activation+1.525
,
Token,
Feature activation+0.000
by
Token by
Feature activation+1.786
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
,
Token,
Feature activation+2.200

INTERVAL 0.717 - 1.433
CONTAINS 0.014%

from
Token from
Feature activation+0.000
taking
Token taking
Feature activation+0.000
race
Token race
Feature activation+0.000
into
Token into
Feature activation+0.000
account
Token account
Feature activation+0.000
when
Token when
Feature activation+1.344
assigning
Token assigning
Feature activation+0.000
pupils
Token pupils
Feature activation+0.000
to
Token to
Feature activation+0.000
schools
Token schools
Feature activation+0.000
in
Token in
Feature activation+0.000
take
Token take
Feature activation+0.000
notes
Token notes
Feature activation+0.000
and
Token and
Feature activation+0.000
people
Token people
Feature activation+0.000
like
Token like
Feature activation+0.000
me
Token me
Feature activation+0.810
often
Token often
Feature activation+0.444
fight
Token fight
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
those
Token those
Feature activation+0.021
the
Token the
Feature activation+0.000
word
Token word
Feature activation+6.480
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+6.394
t
Tokent
Feature activation+1.812
akes
Tokenakes
Feature activation+0.957
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.275
Some
TokenSome
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
steps
Token steps
Feature activation+0.000
include
Token include
Feature activation+0.844
requesting
Token requesting
Feature activation+0.000
the
Token the
Feature activation+0.000
post
Token post
Feature activation+0.000
-
Token-
Feature activation+0.000
office
Tokenoffice
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+2.812
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.860
defend
Token defend
Feature activation+0.000
us
Token us
Feature activation+0.000
,
Token,
Feature activation+0.321
they
Token they
Feature activation+1.195
kill
Token kill
Feature activation+0.000

INTERVAL 0.000 - 0.717
CONTAINS 99.973%

reports
Token reports
Feature activation+0.000
on
Token on
Feature activation+0.000
Github
Token Github
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
AT
TokenAT
Feature activation+0.000
F
TokenF
Feature activation+0.000
domestic
Token domestic
Feature activation+0.000
sting
Token sting
Feature activation+0.000
operations
Token operations
Feature activation+0.000
eclipse
Token eclipse
Feature activation+0.000
a
Token a
Feature activation+0.000
person
Token person
Feature activation+0.000
of
Token of
Feature activation+0.000
interest
Token interest
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
shooting
Token shooting
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
morning
Token morning
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
it
Token it
Feature activation+0.000
belongs
Token belongs
Feature activation+0.000
to
Token to
Feature activation+0.000
Eva
Token Eva
Feature activation+0.000
-
Token-
Feature activation+0.000
Maria
TokenMaria
Feature activation+0.000
Ste
Token Ste
Feature activation+0.000
idel
Tokenidel
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
building
Token building
Feature activation+0.000
"
Token"
Feature activation+0.000
soup
Token soup
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
traditional
Token traditional
Feature activation+0.000
of
Token of
Feature activation+0.000
Iranian
Token Iranian
Feature activation+0.000
breakfast
Token breakfast
Feature activation+0.000
dishes
Token dishes
Feature activation+0.000
.
Token.
Feature activation+0.000
awesome
Token awesome
Feature activation+0.000
timing
Token timing
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
a
Tokena
Feature activation+0.000
pack
Token pack
Feature activation+0.000
of
Token of
Feature activation+0.000
Mic
Token Mic
Feature activation+0.000
ron
Tokenron
Feature activation+0.000
pens
Token pens
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 H11.5: (feature 268)

TOP ACTIVATIONS
MAX = 8.996

your
Token your
Feature activation+0.000
companies
Token companies
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.448
Also
TokenAlso
Feature activation+8.996
in
Token in
Feature activation+0.000
attendance
Token attendance
Feature activation+0.000
at
Token at
Feature activation+0.000
that
Token that
Feature activation+0.000
conference
Token conference
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.552
Community
TokenCommunity
Feature activation+0.000
-
Token -
Feature activation+0.000
6
Token 6
Feature activation+8.231
/
Token/
Feature activation+0.000
1
Token1
Feature activation+0.000
shot
Token shot
Feature activation+0.000
at
Token at
Feature activation+0.000
renewal
Token renewal
Feature activation+0.000
reconsider
Token reconsider
Feature activation+0.000
my
Token my
Feature activation+0.000
career
Token career
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.280
Ċ
TokenĊ
Feature activation+7.984
Sadly
TokenSadly
Feature activation+0.000
,
Token,
Feature activation+0.231
luck
Token luck
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
meetings
Token meetings
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.377
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+2.679
At
TokenAt
Feature activation+0.000
that
Token that
Feature activation+0.000
stage
Token stage
Feature activation+0.000
learned
Token learned
Feature activation+0.000
a
Token a
Feature activation+0.000
thing
Token thing
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.535
MH
TokenMH
Feature activation+0.000
I
Token I
Feature activation+0.000
get
Token get
Feature activation+0.000
the
Token the
Feature activation+0.000
impression
Token impression
Feature activation+0.172
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Also
TokenAlso
Feature activation+6.532
Read
Token Read
Feature activation+0.000
:
Token:
Feature activation+0.000
Art
Token Art
Feature activation+0.000
of
Token of
Feature activation+0.000
Living
Token Living
Feature activation+0.000
the
Token the
Feature activation+0.000
GOP
Token GOP
Feature activation+0.000
brand
Token brand
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.390
Yet
TokenYet
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
-
Token-
Feature activation+0.000
day
Tokenday
Feature activation+0.000
prosperity
Token prosperity
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.307
Almost
TokenAlmost
Feature activation+0.000
30
Token 30
Feature activation+4.106
years
Token years
Feature activation+0.000
on
Token on
Feature activation+0.160
,
Token,
Feature activation+0.286
ortality
Tokenortality
Feature activation+0.000
rates
Token rates
Feature activation+0.000
improve
Token improve
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.092
Think
TokenThink
Feature activation+0.000
local
Token local
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.747
Reg
TokenReg
Feature activation+0.000
oration
Tokenoration
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.879
Only
TokenOnly
Feature activation+0.000
2
Token 2
Feature activation+6.090
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
are
Token are
Feature activation+0.000
aware
Token aware
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
rule
Token rule
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.950
N
TokenN
Feature activation+0.000
igel
Tokenigel
Feature activation+0.000
Lawson
Token Lawson
Feature activation+1.466
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
9
Token9
Feature activation+5.929
Tom
Token Tom
Feature activation+0.000
H
Token H
Feature activation+0.000
anks
Tokenanks
Feature activation+0.000
posed
Token posed
Feature activation+0.000
with
Token with
Feature activation+0.000
in
Token in
Feature activation+0.000
big
Token big
Feature activation+0.000
earthquakes
Token earthquakes
Feature activation+0.000
predicted
Token predicted
Feature activation+0.515
for
Token for
Feature activation+0.000
2018
Token 2018
Feature activation+5.304
as
Token as
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
rotation
Token rotation
Feature activation+0.000
slows
Token slows
Feature activation+3.276
Read
Token Read
Feature activation+0.000
A
TokenA
Feature activation+0.000
spokesman
Token spokesman
Feature activation+0.000
for
Token for
Feature activation+0.000
Motorola
Token Motorola
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+5.054
"
Token "
Feature activation+0.000
Microsoft
TokenMicrosoft
Feature activation+0.000
continues
Token continues
Feature activation+0.000
to
Token to
Feature activation+0.000
infring
Token infring
Feature activation+0.000
late
Token late
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
least
Token least
Feature activation+0.000
3
Token 3
Feature activation+4.991
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
people
Token people
Feature activation+0.000
died
Token died
Feature activation+0.000
in
Token in
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
seized
Token seized
Feature activation+0.000
about
Token about
Feature activation+0.000
$
Token $
Feature activation+0.000
75
Token75
Feature activation+4.971
m
Tokenm
Feature activation+0.000
in
Token in
Feature activation+0.000
fake
Token fake
Feature activation+0.000
bills
Token bills
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+4.960
''
Token ''
Feature activation+0.000
We
TokenWe
Feature activation+0.000
discussed
Token discussed
Feature activation+0.000
the
Token the
Feature activation+0.000
problems
Token problems
Feature activation+0.000
is
Token is
Feature activation+0.000
only
Token only
Feature activation+0.000
increasing
Token increasing
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.416
Ċ
TokenĊ
Feature activation+4.847
Britain
TokenBritain
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
claim
Token claim
Feature activation+0.000
the
Token the
Feature activation+0.000
music
Token music
Feature activation+0.000
the
Token the
Feature activation+0.000
history
Token history
Feature activation+0.000
of
Token of
Feature activation+0.000
Western
Token Western
Feature activation+0.000
colonialism
Token colonialism
Feature activation+0.000
:
Token:
Feature activation+4.516
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
About
TokenAbout
Feature activation+0.000
a
Token a
Feature activation+0.000
dozen
Token dozen
Feature activation+0.000
trucks
Token trucks
Feature activation+0.000
essed
Tokenessed
Feature activation+0.000
West
Token West
Feature activation+0.000
Country
Token Country
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.447
Ċ
TokenĊ
Feature activation+4.424
In
TokenIn
Feature activation+0.000
London
Token London
Feature activation+0.000
,
Token,
Feature activation+0.373
I
Token I
Feature activation+0.000
rent
Token rent
Feature activation+0.000

Top DFA by src position
MAX = 10.176

't
Token't
Feature activation-0.001
Top resid features:
need
Token need
Feature activation-0.006
Top resid features:
your
Token your
Feature activation-0.001
Top resid features:
companies
Token companies
Feature activation-0.001
Top resid features:
."
Token."
Feature activation+0.039
Top resid features:
Ċ
TokenĊ
Feature activation+10.176
Top resid features:
Ċ
TokenĊ
Feature activation+0.094
Top resid features:
Also
TokenAlso
Feature activation-0.004
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
attendance
Token attendance
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
least
Token least
Feature activation-0.002
Top resid features:
a
Token a
Feature activation-0.008
Top resid features:
second
Token second
Feature activation-0.002
Top resid features:
season
Token season
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+5.339
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
Show
TokenShow
Feature activation-0.003
Top resid features:
runners
Tokenrunners
Feature activation-0.002
Top resid features:
Maur
Token Maur
Feature activation-0.000
Top resid features:
issa
Tokenissa
Feature activation-0.000
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
reconsider
Token reconsider
Feature activation-0.000
Top resid features:
my
Token my
Feature activation-0.004
Top resid features:
career
Token career
Feature activation-0.004
Top resid features:
."
Token."
Feature activation+0.220
Top resid features:
Ċ
TokenĊ
Feature activation+8.278
Top resid features:
Ċ
TokenĊ
Feature activation+0.927
Top resid features:
Sadly
TokenSadly
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
luck
Token luck
Feature activation+0.000
Top resid features:
wasn
Token wasn
Feature activation+0.000
Top resid features:
briefed
Token briefed
Feature activation-0.006
Top resid features:
about
Token about
Feature activation-0.010
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
meetings
Token meetings
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.167
Top resid features:
Ċ
TokenĊ
Feature activation+8.102
Top resid features:
Ċ
TokenĊ
Feature activation+0.606
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
At
TokenAt
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
us
Token us
Feature activation+0.061
Top resid features:
learned
Token learned
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
thing
Token thing
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.182
Top resid features:
Ċ
TokenĊ
Feature activation+6.938
Top resid features:
Ċ
TokenĊ
Feature activation+0.729
Top resid features:
MH
TokenMH
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
joke
Token joke
Feature activation-0.004
Top resid features:
,"
Token,"
Feature activation+0.009
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
said
Token said
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.044
Top resid features:
Ċ
TokenĊ
Feature activation+7.244
Top resid features:
Ċ
TokenĊ
Feature activation+0.121
Top resid features:
Also
TokenAlso
Feature activation-0.037
Top resid features:
Read
Token Read
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
Art
Token Art
Feature activation+0.000
Top resid features:
destroying
Token destroying
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
GOP
Token GOP
Feature activation-0.000
Top resid features:
brand
Token brand
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.094
Top resid features:
Ċ
TokenĊ
Feature activation+7.559
Top resid features:
Ċ
TokenĊ
Feature activation+0.437
Top resid features:
Yet
TokenYet
Feature activation+0.000
Top resid features:
Mr
Token Mr
Feature activation+0.000
Top resid features:
Trump
Token Trump
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
present
Token present
Feature activation+0.001
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
day
Tokenday
Feature activation-0.004
Top resid features:
prosperity
Token prosperity
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.213
Top resid features:
Ċ
TokenĊ
Feature activation+6.623
Top resid features:
Ċ
TokenĊ
Feature activation+1.027
Top resid features:
Almost
TokenAlmost
Feature activation+0.000
Top resid features:
30
Token 30
Feature activation+0.000
Top resid features:
years
Token years
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
m
Tokenm
Feature activation+0.001
Top resid features:
ortality
Tokenortality
Feature activation-0.003
Top resid features:
rates
Token rates
Feature activation-0.002
Top resid features:
improve
Token improve
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.114
Top resid features:
Ċ
TokenĊ
Feature activation+6.811
Top resid features:
Ċ
TokenĊ
Feature activation+0.553
Top resid features:
Think
TokenThink
Feature activation+0.000
Top resid features:
local
Token local
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:
and
Token and
Feature activation-0.002
Top resid features:
shared
Token shared
Feature activation-0.002
Top resid features:
commem
Token commem
Feature activation+0.005
Top resid features:
oration
Tokenoration
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.029
Top resid features:
Ċ
TokenĊ
Feature activation+4.425
Top resid features:
Ċ
TokenĊ
Feature activation+0.052
Top resid features:
Only
TokenOnly
Feature activation+0.001
Top resid features:
2
Token 2
Feature activation+0.023
Top resid features:
%
Token%
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
30
Token 30
Feature activation+0.003
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
year
Tokenyear
Feature activation-0.000
Top resid features:
rule
Token rule
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.128
Top resid features:
Ċ
TokenĊ
Feature activation+4.921
Top resid features:
Ċ
TokenĊ
Feature activation+0.413
Top resid features:
N
TokenN
Feature activation+0.000
Top resid features:
igel
Tokenigel
Feature activation+0.000
Top resid features:
Lawson
Token Lawson
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.007
Top resid features:
Budapest
Token Budapest
Feature activation+0.010
Top resid features:
last
Token last
Feature activation-0.005
Top resid features:
year
Token year
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.023
Top resid features:
Ċ
TokenĊ
Feature activation+6.334
Top resid features:
Ċ
TokenĊ
Feature activation+0.118
Top resid features:
9
Token9
Feature activation+0.139
Top resid features:
Tom
Token Tom
Feature activation+0.000
Top resid features:
H
Token H
Feature activation+0.000
Top resid features:
anks
Tokenanks
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
damage
Token damage
Feature activation-0.003
Top resid features:
or
Token or
Feature activation-0.001
Top resid features:
injuries
Token injuries
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+5.994
Top resid features:
Ċ
TokenĊ
Feature activation+0.070
Top resid features:
U
TokenU
Feature activation+0.018
Top resid features:
ps
Tokenps
Feature activation+0.004
Top resid features:
ur
Tokenur
Feature activation+0.004
Top resid features:
ge
Tokenge
Feature activation+0.020
Top resid features:
-
Token -
Feature activation+0.004
Top resid features:
disputes
Token disputes
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
figure
Token figure
Feature activation+0.007
Top resid features:
.
Token.
Feature activation-0.051
Top resid features:
Ċ
TokenĊ
Feature activation+3.751
Top resid features:
Ċ
TokenĊ
Feature activation+0.075
Top resid features:
A
TokenA
Feature activation+0.003
Top resid features:
spokesman
Token spokesman
Feature activation+0.005
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
Motorola
Token Motorola
Feature activation+0.049
Top resid features:
G
TokenG
Feature activation+0.005
Top resid features:
bag
Tokenbag
Feature activation+0.004
Top resid features:
bo
Tokenbo
Feature activation-0.007
Top resid features:
refugees
Token refugees
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.035
Top resid features:
Ċ
TokenĊ
Feature activation+2.914
Top resid features:
Ċ
TokenĊ
Feature activation+0.045
Top resid features:
The
TokenThe
Feature activation+0.002
Top resid features:
experts
Token experts
Feature activation+0.003
Top resid features:
said
Token said
Feature activation-0.003
Top resid features:
they
Token they
Feature activation+0.001
Top resid features:
Jonathan
Token Jonathan
Feature activation-0.002
Top resid features:
Franklin
Token Franklin
Feature activation-0.001
Top resid features:
for
Token for
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
Guardian
Token Guardian
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+5.629
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
âĢ
TokenâĢ
Feature activation+0.025
Top resid features:
ľ
Tokenľ
Feature activation+0.004
Top resid features:
Since
TokenSince
Feature activation-0.005
Top resid features:
2009
Token 2009
Feature activation+0.002
Top resid features:
boys
Token boys
Feature activation+0.001
Top resid features:
being
Token being
Feature activation+0.001
Top resid features:
treated
Token treated
Feature activation+0.001
Top resid features:
equally
Token equally
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.016
Top resid features:
Ċ
TokenĊ
Feature activation+2.483
Top resid features:
Ċ
TokenĊ
Feature activation+0.073
Top resid features:
Of
TokenOf
Feature activation-0.007
Top resid features:
sted
Tokensted
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
not
Token not
Feature activation+0.001
Top resid features:
number
Token number
Feature activation-0.007
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
only
Token only
Feature activation+0.005
Top resid features:
increasing
Token increasing
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.081
Top resid features:
Ċ
TokenĊ
Feature activation+5.913
Top resid features:
Ċ
TokenĊ
Feature activation+0.610
Top resid features:
Britain
TokenBritain
Feature activation+0.000
Top resid features:
cannot
Token cannot
Feature activation+0.000
Top resid features:
claim
Token claim
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
ired
Tokenired
Feature activation-0.003
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
el
Token el
Feature activation-0.037
Top resid features:
itism
Tokenitism
Feature activation-0.010
Top resid features:
".
Token".
Feature activation+0.110
Top resid features:
Ċ
TokenĊ
Feature activation+2.829
Top resid features:
Ċ
TokenĊ
Feature activation+0.095
Top resid features:
The
TokenThe
Feature activation+0.006
Top resid features:
writer
Token writer
Feature activation+0.016
Top resid features:
said
Token said
Feature activation+0.036
Top resid features:
neither
Token neither
Feature activation-0.003
Top resid features:
obs
Tokenobs
Feature activation-0.003
Top resid features:
essed
Tokenessed
Feature activation-0.003
Top resid features:
West
Token West
Feature activation-0.005
Top resid features:
Country
Token Country
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.312
Top resid features:
Ċ
TokenĊ
Feature activation+4.761
Top resid features:
Ċ
TokenĊ
Feature activation+0.843
Top resid features:
In
TokenIn
Feature activation+0.000
Top resid features:
London
Token London
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.04

Head 2: 0.03

Head 3: 0.05

Head 4: 0.04

Head 5: 0.41

Head 6: 0.03

Head 7: 0.06

Head 8: 0.15

Head 9: 0.02

Head 10: 0.04

Head 11: 0.06

Positive logits

Get5.43

GET3.13

get2.72

Get2.65

orthern2.63

show2.55

Article2.51

nesday2.32

Shape2.20

gets2.20

bro2.15

2.14

Brighton2.13

RGB2.10

dp2.09

ドラ2.09

show2.08

Facebook2.03

alloc2.00

grow1.99

Negative logits

-2.43

tracks-2.38

Franch-2.23

-2.20

targ-2.11

racted-2.08

works-1.97

arnaev-1.96

Works-1.94

sie-1.94

Gul-1.94

intact-1.93

chwitz-1.92

-1.92

netted-1.92

clud-1.89

xual-1.88

cases-1.87

volumes-1.84

hooked-1.82

INTERVAL 8.096 - 8.996
CONTAINS 0.000%

your
Token your
Feature activation+0.000
companies
Token companies
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.448
Also
TokenAlso
Feature activation+8.996
in
Token in
Feature activation+0.000
attendance
Token attendance
Feature activation+0.000
at
Token at
Feature activation+0.000
that
Token that
Feature activation+0.000
conference
Token conference
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.552
Community
TokenCommunity
Feature activation+0.000
-
Token -
Feature activation+0.000
6
Token 6
Feature activation+8.231
/
Token/
Feature activation+0.000
1
Token1
Feature activation+0.000
shot
Token shot
Feature activation+0.000
at
Token at
Feature activation+0.000
renewal
Token renewal
Feature activation+0.000

INTERVAL 7.196 - 8.096
CONTAINS 0.000%

about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
meetings
Token meetings
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.377
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+2.679
At
TokenAt
Feature activation+0.000
that
Token that
Feature activation+0.000
stage
Token stage
Feature activation+0.000
reconsider
Token reconsider
Feature activation+0.000
my
Token my
Feature activation+0.000
career
Token career
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.280
Ċ
TokenĊ
Feature activation+7.984
Sadly
TokenSadly
Feature activation+0.000
,
Token,
Feature activation+0.231
luck
Token luck
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 6.297 - 7.196
CONTAINS 0.001%

-
Token-
Feature activation+0.000
day
Tokenday
Feature activation+0.000
prosperity
Token prosperity
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.307
Almost
TokenAlmost
Feature activation+0.000
30
Token 30
Feature activation+4.106
years
Token years
Feature activation+0.000
on
Token on
Feature activation+0.160
,
Token,
Feature activation+0.286
the
Token the
Feature activation+0.000
GOP
Token GOP
Feature activation+0.000
brand
Token brand
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.390
Yet
TokenYet
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Also
TokenAlso
Feature activation+6.532
Read
Token Read
Feature activation+0.000
:
Token:
Feature activation+0.000
Art
Token Art
Feature activation+0.000
of
Token of
Feature activation+0.000
Living
Token Living
Feature activation+0.000
learned
Token learned
Feature activation+0.000
a
Token a
Feature activation+0.000
thing
Token thing
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.535
MH
TokenMH
Feature activation+0.000
I
Token I
Feature activation+0.000
get
Token get
Feature activation+0.000
the
Token the
Feature activation+0.000
impression
Token impression
Feature activation+0.172

INTERVAL 5.397 - 6.297
CONTAINS 0.000%

oration
Tokenoration
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.879
Only
TokenOnly
Feature activation+0.000
2
Token 2
Feature activation+6.090
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
are
Token are
Feature activation+0.000
aware
Token aware
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
9
Token9
Feature activation+5.929
Tom
Token Tom
Feature activation+0.000
H
Token H
Feature activation+0.000
anks
Tokenanks
Feature activation+0.000
posed
Token posed
Feature activation+0.000
with
Token with
Feature activation+0.000
ortality
Tokenortality
Feature activation+0.000
rates
Token rates
Feature activation+0.000
improve
Token improve
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.092
Think
TokenThink
Feature activation+0.000
local
Token local
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.747
Reg
TokenReg
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
rule
Token rule
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.950
N
TokenN
Feature activation+0.000
igel
Tokenigel
Feature activation+0.000
Lawson
Token Lawson
Feature activation+1.466
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000

INTERVAL 4.498 - 5.397
CONTAINS 0.001%

late
Token late
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
least
Token least
Feature activation+0.000
3
Token 3
Feature activation+4.991
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
people
Token people
Feature activation+0.000
died
Token died
Feature activation+0.000
in
Token in
Feature activation+0.000
in
Token in
Feature activation+0.000
big
Token big
Feature activation+0.000
earthquakes
Token earthquakes
Feature activation+0.000
predicted
Token predicted
Feature activation+0.515
for
Token for
Feature activation+0.000
2018
Token 2018
Feature activation+5.304
as
Token as
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
rotation
Token rotation
Feature activation+0.000
slows
Token slows
Feature activation+3.276
Read
Token Read
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
seized
Token seized
Feature activation+0.000
about
Token about
Feature activation+0.000
$
Token $
Feature activation+0.000
75
Token75
Feature activation+4.971
m
Tokenm
Feature activation+0.000
in
Token in
Feature activation+0.000
fake
Token fake
Feature activation+0.000
bills
Token bills
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
history
Token history
Feature activation+0.000
of
Token of
Feature activation+0.000
Western
Token Western
Feature activation+0.000
colonialism
Token colonialism
Feature activation+0.000
:
Token:
Feature activation+4.516
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
About
TokenAbout
Feature activation+0.000
a
Token a
Feature activation+0.000
dozen
Token dozen
Feature activation+0.000
trucks
Token trucks
Feature activation+0.000
is
Token is
Feature activation+0.000
only
Token only
Feature activation+0.000
increasing
Token increasing
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.416
Ċ
TokenĊ
Feature activation+4.847
Britain
TokenBritain
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
claim
Token claim
Feature activation+0.000
the
Token the
Feature activation+0.000
music
Token music
Feature activation+0.000

INTERVAL 3.598 - 4.498
CONTAINS 0.001%

Lac
Token Lac
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
ette
Tokenette
Feature activation+0.000
at
Token at
Feature activation+0.000
âĤ¬
Token âĤ¬
Feature activation+0.000
50
Token50
Feature activation+4.280
m
Tokenm
Feature activation+3.673
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
prosperity
Token prosperity
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.307
Almost
TokenAlmost
Feature activation+0.000
30
Token 30
Feature activation+4.106
years
Token years
Feature activation+0.000
on
Token on
Feature activation+0.160
,
Token,
Feature activation+0.286
Haw
Token Haw
Feature activation+0.000
ke
Tokenke
Feature activation+0.000
Bruce
Token Bruce
Feature activation+0.000
aren
Token aren
Feature activation+0.000
't
Token't
Feature activation+0.000
your
Token your
Feature activation+0.000
favourites
Token favourites
Feature activation+0.000
.
Token.
Feature activation+3.830
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
BS
TokenBS
Feature activation+0.000
I
Token I
Feature activation+0.000
know
Token know
Feature activation+0.000
the
Token the
Feature activation+0.000
decade
Token decade
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.581
Related
TokenRelated
Feature activation+3.857
Story
Token Story
Feature activation+0.000
Smart
Token Smart
Feature activation+0.000
cities
Token cities
Feature activation+0.000
,
Token,
Feature activation+0.000
smoother
Token smoother
Feature activation+0.000
essed
Tokenessed
Feature activation+0.000
West
Token West
Feature activation+0.000
Country
Token Country
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.447
Ċ
TokenĊ
Feature activation+4.424
In
TokenIn
Feature activation+0.000
London
Token London
Feature activation+0.000
,
Token,
Feature activation+0.373
I
Token I
Feature activation+0.000
rent
Token rent
Feature activation+0.000

INTERVAL 2.699 - 3.598
CONTAINS 0.003%

this
Token this
Feature activation+0.000
regard
Token regard
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Also
TokenAlso
Feature activation+2.722
Read
Token Read
Feature activation+0.000
:
Token:
Feature activation+0.000
Navy
Token Navy
Feature activation+0.000
pitches
Token pitches
Feature activation+0.000
for
Token for
Feature activation+0.000
to
Token to
Feature activation+0.000
overcome
Token overcome
Feature activation+0.000
a
Token a
Feature activation+0.000
calf
Token calf
Feature activation+0.000
problem
Token problem
Feature activation+0.000
.
Token.
Feature activation+2.866
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
hoped
Token hoped
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Comedy
Token Comedy
Feature activation+0.000
Society
Token Society
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+3.471
"
Token "
Feature activation+0.000
Despite
TokenDespite
Feature activation+0.000
many
Token many
Feature activation+0.000
complaints
Token complaints
Feature activation+0.000
from
Token from
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Related
TokenRelated
Feature activation+2.875
:
Token:
Feature activation+0.000
Latest
Token Latest
Feature activation+0.000
on
Token on
Feature activation+0.000
Turkey
Token Turkey
Feature activation+0.000
's
Token's
Feature activation+0.000
officially
Token officially
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.086
But
TokenBut
Feature activation+0.000
independent
Token independent
Feature activation+0.000
local
Token local
Feature activation+0.000
churches
Token churches
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.799 - 2.699
CONTAINS 0.005%

about
Token about
Feature activation+0.000
prehistoric
Token prehistoric
Feature activation+0.000
life
Token life
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.262
Thanks
TokenThanks
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
latest
Token latest
Feature activation+0.000
imaging
Token imaging
Feature activation+0.000
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
explosion
Token explosion
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.973
Ram
TokenRam
Feature activation+0.000
ires
Tokenires
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
when
Token when
Feature activation+0.000
provide
Token provide
Feature activation+0.000
250
Token 250
Feature activation+0.108
billion
Token billion
Feature activation+0.000
British
Token British
Feature activation+0.000
pounds
Token pounds
Feature activation+0.000
0
Token 0
Feature activation+1.827
:
Token:
Feature activation+0.000
53
Token53
Feature activation+0.904
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
cabinet
Token cabinet
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.942
The
TokenThe
Feature activation+0.000
proposals
Token proposals
Feature activation+0.000
considered
Token considered
Feature activation+0.000
by
Token by
Feature activation+0.000
her
Token her
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
headlines
Token headlines
Feature activation+0.000
.
Token.
Feature activation+0.261
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.514
Mr
TokenMr
Feature activation+0.000
P
Token P
Feature activation+0.000
ree
Tokenree
Feature activation+0.000
ce
Tokence
Feature activation+0.000
spent
Token spent
Feature activation+0.000

INTERVAL 0.900 - 1.799
CONTAINS 0.014%

Ċ
TokenĊ
Feature activation+1.130
Cost
TokenCost
Feature activation+0.000
of
Token of
Feature activation+0.000
farming
Token farming
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.983
Why
TokenWhy
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
all
Token all
Feature activation+0.000
that
Token that
Feature activation+0.000
and
Token and
Feature activation+0.000
rural
Token rural
Feature activation+0.000
areas
Token areas
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.598
Here
TokenHere
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
how
Token how
Feature activation+0.000
er
Tokener
Feature activation+0.000
ét
Tokenét
Feature activation+0.000
aro
Tokenaro
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.524
The
TokenThe
Feature activation+0.000
job
Token job
Feature activation+0.000
was
Token was
Feature activation+0.000
ret
Token ret
Feature activation+0.000
endered
Tokenendered
Feature activation+0.000
by
Token by
Feature activation+0.000
Nelson
Token Nelson
Feature activation+0.000
Mandela
Token Mandela
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.517
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
000
Token000
Feature activation+0.000
,
Token,
Feature activation+0.000
respectively
Token respectively
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.951
And
TokenAnd
Feature activation+0.000
the
Token the
Feature activation+0.000
conversation
Token conversation
Feature activation+0.000
at
Token at
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 0.000 - 0.900
CONTAINS 99.974%

channels
Token channels
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
conversion
Token conversion
Feature activation+0.000
path
Token path
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
this
Token this
Feature activation+0.000
article
Token article
Feature activation+0.000
to
Token to
Feature activation+0.000
poultry
Token poultry
Feature activation+0.000
plant
Token plant
Feature activation+0.000
employees
Token employees
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
inspectors
Token inspectors
Feature activation+0.000
would
Token would
Feature activation+0.000
spend
Token spend
Feature activation+0.000
more
Token more
Feature activation+0.000
and
Token and
Feature activation+0.000
corn
Token corn
Feature activation+0.000
fl
Tokenfl
Feature activation+0.000
akes
Tokenakes
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000
never
Token never
Feature activation+0.000
let
Token let
Feature activation+0.000
another
Token another
Feature activation+0.000
man
Token man
Feature activation+0.000
a
Token a
Feature activation+0.000
government
Token government
Feature activation+0.000
report
Token report
Feature activation+0.000
which
Token which
Feature activation+0.000
showed
Token showed
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
much
Token much
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
ch
Token ch
Feature activation+0.000
.
Token.
Feature activation+0.000
How
Token How
Feature activation+0.000
do
Token do
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
if
Token if
Feature activation+0.000
your
Token your
Feature activation+0.000
money
Token money
Feature activation+0.000
is
Token is
Feature activation+0.000
doing
Token doing
Feature activation+0.000
substantive
Token substantive
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 H11.5: (feature 10218)

TOP ACTIVATIONS
MAX = 6.674

charge
Token charge
Feature activation+0.000
F
Token F
Feature activation+0.000
of
Tokenof
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
.
Token.
Feature activation+0.000
Nor
Token Nor
Feature activation+6.674
are
Token are
Feature activation+0.000
they
Token they
Feature activation+0.589
expressing
Token expressing
Feature activation+0.000
a
Token a
Feature activation+0.000
sincerely
Token sincerely
Feature activation+0.000
not
Token not
Feature activation+0.000
here
Token here
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
money
Token money
Feature activation+0.000
,
Token,
Feature activation+5.799
we
Token we
Feature activation+3.312
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+1.683
here
Token here
Feature activation+1.085
not
Token not
Feature activation+0.000
one
Token one
Feature activation+0.117
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
teams
Token teams
Feature activation+3.476
,
Token,
Feature activation+5.645
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Donovan
Token Donovan
Feature activation+0.000
added
Token added
Feature activation+0.000
.
Token.
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
not
Token not
Feature activation+0.000
telling
Token telling
Feature activation+0.000
you
Token you
Feature activation+1.223
,
Token,
Feature activation+5.580
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
she
Token she
Feature activation+0.000
said
Token said
Feature activation+0.000
calmly
Token calmly
Feature activation+0.000
a
Token a
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
nut
Tokennut
Feature activation+0.000
job
Token job
Feature activation+0.000
,
Token,
Feature activation+5.133
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.395
as
Token as
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
described
Token described
Feature activation+0.000
of
Token of
Feature activation+0.083
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
250
Token 250
Feature activation+0.000
inmates
Token inmates
Feature activation+0.228
,
Token,
Feature activation+5.130
but
Token but
Feature activation+0.000
you
Token you
Feature activation+1.923
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
find
Token find
Feature activation+0.000
work
Token work
Feature activation+0.000
in
Token in
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
;
Token;
Feature activation+0.000
nor
Token nor
Feature activation+4.848
are
Token are
Feature activation+0.000
they
Token they
Feature activation+0.000
the
Token the
Feature activation+0.000
places
Token places
Feature activation+0.000
with
Token with
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dist
TokenDist
Feature activation+0.000
ances
Tokenances
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.258
The
TokenThe
Feature activation+4.792
L
Token L
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
court
Tokencourt
Feature activation+2.419
Rocks
Token Rocks
Feature activation+0.000
are
Token are
Feature activation+0.000
implied
Token implied
Feature activation+0.000
0
Token 0
Feature activation+0.000
;
Token;
Feature activation+0.000
if
Token if
Feature activation+0.096
the
Token the
Feature activation+0.000
card
Token card
Feature activation+4.435
is
Token is
Feature activation+0.000
present
Token present
Feature activation+0.000
then
Token then
Feature activation+0.000
it
Token it
Feature activation+0.858
represents
Token represents
Feature activation+0.000
interchangeable
Token interchangeable
Feature activation+0.000
with
Token with
Feature activation+0.000
other
Token other
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
and
Token and
Feature activation+1.704
thus
Token thus
Feature activation+4.284
worth
Token worth
Feature activation+0.000
less
Token less
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
about
Token about
Feature activation+0.000
what
Token what
Feature activation+0.000
is
Token is
Feature activation+0.000
appropriate
Token appropriate
Feature activation+0.000
and
Token and
Feature activation+0.615
what
Token what
Feature activation+4.155
isn
Token isn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.669
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.190
are
Token are
Feature activation+0.000
mentally
Token mentally
Feature activation+0.000
ill
Token ill
Feature activation+4.111
are
Token are
Feature activation+0.783
more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.000
become
Token become
Feature activation+0.000
states
Token states
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
progressive
Token progressive
Feature activation+0.000
,
Token,
Feature activation+0.000
some
Token some
Feature activation+4.023
are
Token are
Feature activation+1.832
more
Token more
Feature activation+0.000
reg
Token reg
Feature activation+0.000
ressive
Tokenressive
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Hillary
Token Hillary
Feature activation+0.000
rally
Token rally
Feature activation+0.000
.
Token.
Feature activation+0.475
We
Token We
Feature activation+4.004
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+1.593
not
Token not
Feature activation+0.846
talking
Token talking
Feature activation+0.158
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
not
Token not
Feature activation+0.000
tech
Token tech
Feature activation+0.000
ies
Tokenies
Feature activation+1.088
,
Token,
Feature activation+3.982
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Z
Token Z
Feature activation+0.000
abl
Tokenabl
Feature activation+0.000
ud
Tokenud
Feature activation+0.000
is
Token is
Feature activation+0.000
located
Token located
Feature activation+0.000
at
Token at
Feature activation+0.000
and
Token and
Feature activation+0.278
the
Token the
Feature activation+2.730
Eastern
Token Eastern
Feature activation+3.936
Is
Token Is
Feature activation+0.000
let
Tokenlet
Feature activation+1.742
is
Token is
Feature activation+0.000
located
Token located
Feature activation+0.000
at
Token at
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
worked
Token worked
Feature activation+0.000
for
Token for
Feature activation+0.000
small
Token small
Feature activation+0.000
companies
Token companies
Feature activation+3.875
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
contracted
Token contracted
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
for
Token for
Feature activation+0.000
AC
Token AC
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
smaller
Token smaller
Feature activation+1.348
one
Token one
Feature activation+3.807
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.309
is
Token is
Feature activation+0.000
for
Token for
Feature activation+0.000
bombing
Token bombing
Feature activation+0.000
the
Token the
Feature activation+0.000
Middle
Token Middle
Feature activation+0.000
East
Token East
Feature activation+0.000
;
Token;
Feature activation+1.197
you
Token you
Feature activation+3.642
just
Token just
Feature activation+1.416
have
Token have
Feature activation+0.000
internal
Token internal
Feature activation+0.000
ised
Tokenised
Feature activation+0.000
misogyny
Token misogyny
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
shortest
Token shortest
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Exodus
Token Exodus
Feature activation+3.636
is
Token is
Feature activation+0.000
longer
Token longer
Feature activation+0.000
than
Token than
Feature activation+0.000
De
Token De
Feature activation+0.000
uter
Tokenuter
Feature activation+0.000

Top DFA by src position
MAX = 7.225

:
Token:
Feature activation+0.030
Top resid features:
Canadian
Token Canadian
Feature activation+0.037
Top resid features:
law
Token law
Feature activation+0.006
Top resid features:
enforcement
Token enforcement
Feature activation+0.008
Top resid features:
is
Token is
Feature activation+1.373
Top resid features:
not
Token not
Feature activation+6.909
Top resid features:
exploiting
Token exploiting
Feature activation-0.021
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
ridiculous
Token ridiculous
Feature activation-0.004
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
outdated
Token outdated
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
We
Token We
Feature activation+0.067
Top resid features:
âĢ
TokenâĢ
Feature activation-0.048
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
re
Tokenre
Feature activation+0.786
Top resid features:
not
Token not
Feature activation+6.162
Top resid features:
here
Token here
Feature activation+0.228
Top resid features:
for
Token for
Feature activation+0.064
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
money
Token money
Feature activation+0.060
Top resid features:
,
Token,
Feature activation+0.059
Top resid features:
and
Token and
Feature activation+0.040
Top resid features:
we
Token we
Feature activation+0.033
Top resid features:
âĢ
TokenâĢ
Feature activation-0.035
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
re
Tokenre
Feature activation+0.384
Top resid features:
not
Token not
Feature activation+6.900
Top resid features:
one
Token one
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
those
Token those
Feature activation+0.008
Top resid features:
teams
Token teams
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
ľ
Tokenľ
Feature activation+0.027
Top resid features:
I
TokenI
Feature activation+0.021
Top resid features:
âĢ
TokenâĢ
Feature activation+0.036
Top resid features:
Ļ
TokenĻ
Feature activation+0.017
Top resid features:
m
Tokenm
Feature activation+0.111
Top resid features:
not
Token not
Feature activation+6.851
Top resid features:
telling
Token telling
Feature activation+0.034
Top resid features:
you
Token you
Feature activation+0.054
Top resid features:
,
Token,
Feature activation+0.141
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
he
Token he
Feature activation+0.056
Top resid features:
âĢ
TokenâĢ
Feature activation+0.032
Top resid features:
Ļ
TokenĻ
Feature activation+0.019
Top resid features:
s
Tokens
Feature activation+0.219
Top resid features:
not
Token not
Feature activation+6.368
Top resid features:
of
Token of
Feature activation+0.059
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
opinion
Token opinion
Feature activation+0.052
Top resid features:
that
Token that
Feature activation+0.045
Top resid features:
Comey
Token Comey
Feature activation-0.083
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
you
Token you
Feature activation+0.051
Top resid features:
weren
Token weren
Feature activation+0.018
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
t
Tokent
Feature activation+6.917
Top resid features:
one
Token one
Feature activation+0.016
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
first
Token first
Feature activation+0.006
Top resid features:
250
Token 250
Feature activation-0.000
Top resid features:
cities
Token cities
Feature activation+0.021
Top resid features:
that
Token that
Feature activation+0.019
Top resid features:
top
Token top
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.022
Top resid features:
list
Token list
Feature activation+0.011
Top resid features:
are
Token are
Feature activation+5.548
Top resid features:
the
Token the
Feature activation+0.047
Top resid features:
best
Token best
Feature activation+0.004
Top resid features:
places
Token places
Feature activation-0.004
Top resid features:
to
Token to
Feature activation+0.016
Top resid features:
find
Token find
Feature activation-0.007
Top resid features:
ge
Token ge
Feature activation-0.013
Top resid features:
ologist
Tokenologist
Feature activation-0.017
Top resid features:
reported
Token reported
Feature activation+0.021
Top resid features:
that
Token that
Feature activation+0.014
Top resid features:
the
Token the
Feature activation-0.032
Top resid features:
is
Token is
Feature activation+7.225
Top resid features:
lets
Tokenlets
Feature activation-0.100
Top resid features:
formed
Token formed
Feature activation+0.018
Top resid features:
4
Token 4
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
5
Token5
Feature activation-0.005
Top resid features:
0
Token 0
Feature activation+0.017
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
If
Token If
Feature activation+0.070
Top resid features:
the
Token the
Feature activation+0.041
Top resid features:
card
Token card
Feature activation+0.002
Top resid features:
is
Token is
Feature activation+5.286
Top resid features:
absent
Token absent
Feature activation-0.038
Top resid features:
from
Token from
Feature activation+0.482
Top resid features:
its
Token its
Feature activation+0.061
Top resid features:
position
Token position
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
dollars
Token dollars
Feature activation+0.005
Top resid features:
on
Token on
Feature activation+0.034
Top resid features:
this
Token this
Feature activation+0.006
Top resid features:
bank
Token bank
Feature activation+0.001
Top resid features:
account
Token account
Feature activation+0.006
Top resid features:
are
Token are
Feature activation+2.546
Top resid features:
not
Token not
Feature activation+1.228
Top resid features:
interchangeable
Token interchangeable
Feature activation-0.018
Top resid features:
with
Token with
Feature activation+0.042
Top resid features:
other
Token other
Feature activation+0.005
Top resid features:
dollars
Token dollars
Feature activation+0.005
Top resid features:
there
Token there
Feature activation+0.003
Top resid features:
are
Token are
Feature activation+0.055
Top resid features:
debates
Token debates
Feature activation+0.006
Top resid features:
about
Token about
Feature activation-0.019
Top resid features:
what
Token what
Feature activation+0.099
Top resid features:
is
Token is
Feature activation+5.369
Top resid features:
appropriate
Token appropriate
Feature activation+0.060
Top resid features:
and
Token and
Feature activation+0.070
Top resid features:
what
Token what
Feature activation+0.085
Top resid features:
isn
Token isn
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
People
Token People
Feature activation+0.032
Top resid features:
who
Token who
Feature activation+0.019
Top resid features:
are
Token are
Feature activation+0.058
Top resid features:
poor
Token poor
Feature activation+0.003
Top resid features:
are
Token are
Feature activation+4.412
Top resid features:
about
Token about
Feature activation+0.315
Top resid features:
four
Token four
Feature activation+0.028
Top resid features:
times
Token times
Feature activation+0.513
Top resid features:
as
Token as
Feature activation+0.173
Top resid features:
likely
Token likely
Feature activation+0.047
Top resid features:
for
Token for
Feature activation+0.031
Top resid features:
themselves
Token themselves
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.027
Top resid features:
Some
Token Some
Feature activation+0.038
Top resid features:
states
Token states
Feature activation+0.025
Top resid features:
are
Token are
Feature activation+2.257
Top resid features:
more
Token more
Feature activation+0.702
Top resid features:
progressive
Token progressive
Feature activation-0.022
Top resid features:
,
Token,
Feature activation+0.112
Top resid features:
some
Token some
Feature activation+0.143
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
So
TokenSo
Feature activation+0.030
Top resid features:
we
Token we
Feature activation+0.058
Top resid features:
âĢ
TokenâĢ
Feature activation-0.107
Top resid features:
Ļ
TokenĻ
Feature activation-0.046
Top resid features:
re
Tokenre
Feature activation+1.306
Top resid features:
not
Token not
Feature activation+3.744
Top resid features:
talking
Token talking
Feature activation+0.554
Top resid features:
simply
Token simply
Feature activation+0.028
Top resid features:
about
Token about
Feature activation+0.032
Top resid features:
âĢ
Token âĢ
Feature activation+0.033
Top resid features:
ľ
Tokenľ
Feature activation-0.012
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.157
Top resid features:
We
TokenWe
Feature activation+0.131
Top resid features:
âĢ
TokenâĢ
Feature activation+0.167
Top resid features:
Ļ
TokenĻ
Feature activation+0.053
Top resid features:
re
Tokenre
Feature activation+0.687
Top resid features:
not
Token not
Feature activation+4.914
Top resid features:
tech
Token tech
Feature activation+0.009
Top resid features:
ies
Tokenies
Feature activation+0.116
Top resid features:
,
Token,
Feature activation+0.111
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.009
Top resid features:
about
Token about
Feature activation-0.000
Top resid features:
.
Token .
Feature activation+0.000
Top resid features:
The
Token The
Feature activation-0.046
Top resid features:
western
Token western
Feature activation-0.094
Top resid features:
is
Token is
Feature activation+5.311
Top resid features:
let
Tokenlet
Feature activation-0.136
Top resid features:
is
Token is
Feature activation+0.834
Top resid features:
located
Token located
Feature activation-0.006
Top resid features:
at
Token at
Feature activation-0.000
Top resid features:
and
Token and
Feature activation+0.043
Top resid features:
may
Token may
Feature activation+0.037
Top resid features:
have
Token have
Feature activation+0.026
Top resid features:
lost
Token lost
Feature activation-0.002
Top resid features:
their
Token their
Feature activation+0.016
Top resid features:
jobs
Token jobs
Feature activation-0.019
Top resid features:
are
Token are
Feature activation+2.883
Top resid features:
not
Token not
Feature activation+1.815
Top resid features:
necessarily
Token necessarily
Feature activation+0.791
Top resid features:
mine
Token mine
Feature activation+0.055
Top resid features:
employees
Token employees
Feature activation+0.079
Top resid features:
but
Token but
Feature activation+0.049
Top resid features:
boxes
Token boxes
Feature activation-0.023
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
The
Token The
Feature activation+0.036
Top resid features:
larger
Token larger
Feature activation+0.002
Top resid features:
one
Token one
Feature activation+0.031
Top resid features:
is
Token is
Feature activation+4.938
Top resid features:
for
Token for
Feature activation+0.237
Top resid features:
AC
Token AC
Feature activation-0.051
Top resid features:
and
Token and
Feature activation+0.056
Top resid features:
the
Token the
Feature activation+0.081
Top resid features:
smaller
Token smaller
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
You
TokenYou
Feature activation+0.010
Top resid features:
weren
Token weren
Feature activation+0.044
Top resid features:
âĢ
TokenâĢ
Feature activation-0.013
Top resid features:
Ļ
TokenĻ
Feature activation+0.024
Top resid features:
t
Tokent
Feature activation+4.023
Top resid features:
âĢ
Token âĢ
Feature activation+0.015
Top resid features:
ľ
Tokenľ
Feature activation+0.042
Top resid features:
With
TokenWith
Feature activation+0.015
Top resid features:
Her
Token Her
Feature activation+0.010
Top resid features:
âĢ
TokenâĢ
Feature activation-0.022
Top resid features:
are
Token are
Feature activation+0.479
Top resid features:
not
Token not
Feature activation+0.122
Top resid features:
equal
Token equal
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Genesis
Token Genesis
Feature activation-0.031
Top resid features:
is
Token is
Feature activation+2.431
Top resid features:
the
Token the
Feature activation+0.043
Top resid features:
longest
Token longest
Feature activation+0.003
Top resid features:
book
Token book
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+0.056
Top resid features:
Lev
Token Lev
Feature activation+0.008
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.04

Head 2: 0.06

Head 3: 0.04

Head 4: 0.05

Head 5: 0.40

Head 6: 0.05

Head 7: 0.04

Head 8: 0.08

Head 9: 0.06

Head 10: 0.05

Head 11: 0.05

Positive logits

are3.98

is3.51

are3.28

Are2.99

ARE2.89

aren2.83

Are2.67

being2.61

is2.58

Is2.48

isn2.41

am2.41

Is2.32

were2.29

2.26

ā2.25

Being2.08

2.08

IS2.07

2.06

Negative logits

obos-2.19

itialized-2.17

ternity-2.10

MpServer-2.07

prints-2.02

arks-2.01

FontSize-1.99

perty-1.98

lined-1.93

ingen-1.89

Lets-1.88

unpublished-1.85

Attach-1.83

Write-1.81

rients-1.81

Had-1.80

iddled-1.78

externalToEVAOnly-1.77

actory-1.73

yne-1.72

INTERVAL 6.007 - 6.674
CONTAINS 0.000%

charge
Token charge
Feature activation+0.000
F
Token F
Feature activation+0.000
of
Tokenof
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
.
Token.
Feature activation+0.000
Nor
Token Nor
Feature activation+6.674
are
Token are
Feature activation+0.000
they
Token they
Feature activation+0.589
expressing
Token expressing
Feature activation+0.000
a
Token a
Feature activation+0.000
sincerely
Token sincerely
Feature activation+0.000

INTERVAL 5.340 - 6.007
CONTAINS 0.000%

Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
not
Token not
Feature activation+0.000
telling
Token telling
Feature activation+0.000
you
Token you
Feature activation+1.223
,
Token,
Feature activation+5.580
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
she
Token she
Feature activation+0.000
said
Token said
Feature activation+0.000
calmly
Token calmly
Feature activation+0.000
not
Token not
Feature activation+0.000
one
Token one
Feature activation+0.117
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
teams
Token teams
Feature activation+3.476
,
Token,
Feature activation+5.645
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Donovan
Token Donovan
Feature activation+0.000
added
Token added
Feature activation+0.000
.
Token.
Feature activation+0.000
not
Token not
Feature activation+0.000
here
Token here
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
money
Token money
Feature activation+0.000
,
Token,
Feature activation+5.799
we
Token we
Feature activation+3.312
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+1.683
here
Token here
Feature activation+1.085

INTERVAL 4.672 - 5.340
CONTAINS 0.000%

find
Token find
Feature activation+0.000
work
Token work
Feature activation+0.000
in
Token in
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
;
Token;
Feature activation+0.000
nor
Token nor
Feature activation+4.848
are
Token are
Feature activation+0.000
they
Token they
Feature activation+0.000
the
Token the
Feature activation+0.000
places
Token places
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
nut
Tokennut
Feature activation+0.000
job
Token job
Feature activation+0.000
,
Token,
Feature activation+5.133
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.395
as
Token as
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
described
Token described
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dist
TokenDist
Feature activation+0.000
ances
Tokenances
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.258
The
TokenThe
Feature activation+4.792
L
Token L
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
court
Tokencourt
Feature activation+2.419
Rocks
Token Rocks
Feature activation+0.000
are
Token are
Feature activation+0.000
of
Token of
Feature activation+0.083
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
250
Token 250
Feature activation+0.000
inmates
Token inmates
Feature activation+0.228
,
Token,
Feature activation+5.130
but
Token but
Feature activation+0.000
you
Token you
Feature activation+1.923
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000

INTERVAL 4.005 - 4.672
CONTAINS 0.001%

and
Token and
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.190
are
Token are
Feature activation+0.000
mentally
Token mentally
Feature activation+0.000
ill
Token ill
Feature activation+4.111
are
Token are
Feature activation+0.783
more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.000
become
Token become
Feature activation+0.000
about
Token about
Feature activation+0.000
what
Token what
Feature activation+0.000
is
Token is
Feature activation+0.000
appropriate
Token appropriate
Feature activation+0.000
and
Token and
Feature activation+0.615
what
Token what
Feature activation+4.155
isn
Token isn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.669
,
Token,
Feature activation+0.000
implied
Token implied
Feature activation+0.000
0
Token 0
Feature activation+0.000
;
Token;
Feature activation+0.000
if
Token if
Feature activation+0.096
the
Token the
Feature activation+0.000
card
Token card
Feature activation+4.435
is
Token is
Feature activation+0.000
present
Token present
Feature activation+0.000
then
Token then
Feature activation+0.000
it
Token it
Feature activation+0.858
represents
Token represents
Feature activation+0.000
states
Token states
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
progressive
Token progressive
Feature activation+0.000
,
Token,
Feature activation+0.000
some
Token some
Feature activation+4.023
are
Token are
Feature activation+1.832
more
Token more
Feature activation+0.000
reg
Token reg
Feature activation+0.000
ressive
Tokenressive
Feature activation+0.000
,
Token,
Feature activation+0.000
interchangeable
Token interchangeable
Feature activation+0.000
with
Token with
Feature activation+0.000
other
Token other
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
and
Token and
Feature activation+1.704
thus
Token thus
Feature activation+4.284
worth
Token worth
Feature activation+0.000
less
Token less
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.337 - 4.005
CONTAINS 0.002%

those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
worked
Token worked
Feature activation+0.000
for
Token for
Feature activation+0.000
small
Token small
Feature activation+0.000
companies
Token companies
Feature activation+3.875
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
contracted
Token contracted
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
But
Token But
Feature activation+0.000
not
Token not
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Comey
Token Comey
Feature activation+0.000
,
Token,
Feature activation+3.379
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
why
Token why
Feature activation+0.000
I
Token I
Feature activation+0.000
felt
Token felt
Feature activation+0.000
for
Token for
Feature activation+0.000
AC
Token AC
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
smaller
Token smaller
Feature activation+1.348
one
Token one
Feature activation+3.807
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.309
is
Token is
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+1.396
the
Token the
Feature activation+0.000
majority
Token majority
Feature activation+3.379
oppose
Token oppose
Feature activation+0.000
financial
Token financial
Feature activation+0.000
aid
Token aid
Feature activation+0.000
for
Token for
Feature activation+0.000
Greece
Token Greece
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
shortest
Token shortest
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Exodus
Token Exodus
Feature activation+3.636
is
Token is
Feature activation+0.000
longer
Token longer
Feature activation+0.000
than
Token than
Feature activation+0.000
De
Token De
Feature activation+0.000
uter
Tokenuter
Feature activation+0.000

INTERVAL 2.670 - 3.337
CONTAINS 0.003%

C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
Southern
Token Southern
Feature activation+0.000
parts
Token parts
Feature activation+1.174
of
Token of
Feature activation+0.000
Europe
Token Europe
Feature activation+3.089
will
Token will
Feature activation+0.000
warm
Token warm
Feature activation+0.000
least
Token least
Feature activation+0.000
,
Token,
Feature activation+0.000
say
Token say
Feature activation+0.000
web
Token web
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.000
email
Token email
Feature activation+0.000
today
Token today
Feature activation+0.066
cannot
Token cannot
Feature activation+2.675
be
Token be
Feature activation+0.000
surprised
Token surprised
Feature activation+0.000
if
Token if
Feature activation+0.000
their
Token their
Feature activation+0.000
emails
Token emails
Feature activation+0.000
world
Token world
Feature activation+0.000
-
Token-
Feature activation+0.000
sh
Tokensh
Feature activation+0.000
attering
Tokenattering
Feature activation+0.000
revelation
Token revelation
Feature activation+0.000
,
Token,
Feature activation+2.931
but
Token but
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
They
Token They
Feature activation+0.000
aren
Token aren
Feature activation+0.000
't
Token't
Feature activation+0.000
too
Token too
Feature activation+0.000
upset
Token upset
Feature activation+0.000
,
Token,
Feature activation+2.731
they
Token they
Feature activation+1.510
're
Token're
Feature activation+0.000
just
Token just
Feature activation+0.000
sh
Token sh
Feature activation+0.000
ru
Tokenru
Feature activation+0.000
the
Token the
Feature activation+0.000
photographs
Token photographs
Feature activation+0.000
and
Token and
Feature activation+0.000
videos
Token videos
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+2.817
also
Token also
Feature activation+2.051
to
Token to
Feature activation+0.000
copy
Token copy
Feature activation+0.000
them
Token them
Feature activation+0.000
,"
Token,"
Feature activation+0.000

INTERVAL 2.002 - 2.670
CONTAINS 0.008%

n
Token n
Feature activation+0.000
mi
Tokenmi
Feature activation+0.000
)
Token)
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+1.334
main
Token main
Feature activation+2.040
island
Token island
Feature activation+0.000
of
Token of
Feature activation+0.000
Japan
Token Japan
Feature activation+0.000
(
Token (
Feature activation+0.000
H
TokenH
Feature activation+0.000
photographs
Token photographs
Feature activation+0.000
and
Token and
Feature activation+0.000
videos
Token videos
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+2.817
also
Token also
Feature activation+2.051
to
Token to
Feature activation+0.000
copy
Token copy
Feature activation+0.000
them
Token them
Feature activation+0.000
,"
Token,"
Feature activation+0.000
attorney
Token attorney
Feature activation+0.000
riding
Token riding
Feature activation+0.000
for
Token for
Feature activation+0.000
women
Token women
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+2.661
not
Token not
Feature activation+2.153
for
Token for
Feature activation+0.682
men
Token men
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
W
Token W
Feature activation+0.000
ain
Tokenain
Feature activation+0.000
wright
Tokenwright
Feature activation+0.000
or
Token or
Feature activation+0.000
Felix
Token Felix
Feature activation+0.000
,
Token,
Feature activation+2.301
he
Token he
Feature activation+2.653
's
Token's
Feature activation+0.000
definitely
Token definitely
Feature activation+0.000
not
Token not
Feature activation+0.000
going
Token going
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
sc
Token sc
Feature activation+0.000
aring
Tokenaring
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+2.019
b
Token b
Feature activation+0.000
****
Token****
Feature activation+0.000
!
Token!
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000

INTERVAL 1.335 - 2.002
CONTAINS 0.015%

20
Token20
Feature activation+0.000
percent
Token percent
Feature activation+2.098
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
those
Token those
Feature activation+0.000
polled
Token polled
Feature activation+1.353
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
National
Token National
Feature activation+0.000
Committee
Token Committee
Feature activation+0.000
the
Token the
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
shred
Token shred
Feature activation+0.000
der
Tokender
Feature activation+0.000
,
Token,
Feature activation+1.248
it
Token it
Feature activation+1.735
's
Token's
Feature activation+0.098
throwing
Token throwing
Feature activation+0.000
people
Token people
Feature activation+0.000
into
Token into
Feature activation+0.000
it
Token it
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
just
Token just
Feature activation+0.000
intelligent
Token intelligent
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+1.357
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
conscious
Token conscious
Feature activation+0.000
.
Token.
Feature activation+0.000
only
Token only
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Shadow
Token Shadow
Feature activation+0.000
Cabinet
Token Cabinet
Feature activation+0.000
,
Token,
Feature activation+1.363
because
Token because
Feature activation+0.000
Jeremy
Token Jeremy
Feature activation+0.000
Corbyn
Token Corbyn
Feature activation+0.000
put
Token put
Feature activation+0.000
you
Token you
Feature activation+0.000
first
Token first
Feature activation+0.000
250
Token 250
Feature activation+0.000
inmates
Token inmates
Feature activation+0.228
,
Token,
Feature activation+5.130
but
Token but
Feature activation+0.000
you
Token you
Feature activation+1.923
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
still
Token still
Feature activation+0.000
getting
Token getting
Feature activation+0.000

INTERVAL 0.667 - 1.335
CONTAINS 0.035%

from
Token from
Feature activation+0.000
round
Token round
Feature activation+0.000
here
Token here
Feature activation+1.377
are
Token are
Feature activation+0.000
you
Token you
Feature activation+0.000
?
Token?
Feature activation+0.754
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Photo
TokenPhoto
Feature activation+0.000
Dead
Token Dead
Feature activation+0.000
,
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+0.878
(
Token (
Feature activation+0.000
Em
TokenEm
Feature activation+0.000
peror
Tokenperor
Feature activation+0.000
Mon
Token Mon
Feature activation+0.000
M
Token M
Feature activation+0.000
down
Token down
Feature activation+0.000
m
Token m
Feature activation+0.000
accordingly
Token accordingly
Feature activation+0.000
.
Token.
Feature activation+0.000
Let
Token Let
Feature activation+0.000
T
Token T
Feature activation+1.217
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
suitable
Token suitable
Feature activation+0.000
length
Token length
Feature activation+0.000
of
Token of
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
only
Token only
Feature activation+0.000
there
Token there
Feature activation+0.000
,
Token,
Feature activation+0.666
you
Token you
Feature activation+1.048
are
Token are
Feature activation+0.000
only
Token only
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Shadow
Token Shadow
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
larger
Token larger
Feature activation+0.000
phenomenon
Token phenomenon
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.927
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
that
Token that
Feature activation+0.000
Mormon
Token Mormon
Feature activation+0.000

INTERVAL 0.000 - 0.667
CONTAINS 99.937%

down
Token down
Feature activation+0.000
grading
Tokengrading
Feature activation+0.000
ties
Token ties
Feature activation+0.000
with
Token with
Feature activation+0.000
Iran
Token Iran
Feature activation+0.000
,
Token,
Feature activation+0.000
were
Token were
Feature activation+0.000
an
Token an
Feature activation+0.000
infringement
Token infringement
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
here
Token here
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
night
Token night
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
P
Token P
Feature activation+0.000
aks
Tokenaks
Feature activation+0.000
ong
Tokenong
Feature activation+0.000
idea
Token idea
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
black
Token black
Feature activation+0.000
skate
Token skate
Feature activation+0.000
boarding
Tokenboarding
Feature activation+0.000
superhero
Token superhero
Feature activation+0.000
feels
Token feels
Feature activation+0.000
pretty
Token pretty
Feature activation+0.000
current
Token current
Feature activation+0.000
in
Token in
Feature activation+0.000
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
long
Token long
Feature activation+0.000
-
Token-
Feature activation+0.000
term
Tokenterm
Feature activation+0.000
effects
Token effects
Feature activation+0.000
are
Token are
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Also
TokenAlso
Feature activation+0.000
Soviet
Token Soviet
Feature activation+0.000
Union
Token Union
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.000
no
Token no
Feature activation+0.000
charisma
Token charisma
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
is
Token is
Feature activation+0.000
obviously
Token obviously
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