H0.2 top features

Top feature 0 in H0.2: (feature 17382)

TOP ACTIVATIONS
MAX = 1.687

security
Token security
Feature activation+0.006
restrictions
Token restrictions
Feature activation+0.062
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
occupied
Token occupied
Feature activation+1.403
West
Token West
Feature activation+1.687
Bank
Token Bank
Feature activation+0.000
that
Token that
Feature activation+0.000
Palestinians
Token Palestinians
Feature activation+0.000
say
Token say
Feature activation+0.000
cripp
Token cripp
Feature activation+0.000
and
Token and
Feature activation+0.000
unmanned
Token unmanned
Feature activation+0.000
checkpoints
Token checkpoints
Feature activation+0.992
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+1.642
Bank
Token Bank
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
least
Token least
Feature activation+0.000
65
Token 65
Feature activation+0.000
press
Token press
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
to
Token to
Feature activation+0.000
halt
Token halt
Feature activation+0.000
Jewish
Token Jewish
Feature activation+0.666
settlements
Token settlements
Feature activation+1.596
and
Token and
Feature activation+0.000
ease
Token ease
Feature activation+0.062
security
Token security
Feature activation+0.006
restrictions
Token restrictions
Feature activation+0.062
in
Token in
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
's
Token's
Feature activation+0.000
expansion
Token expansion
Feature activation+0.000
of
Token of
Feature activation+0.000
Jewish
Token Jewish
Feature activation+0.319
settlements
Token settlements
Feature activation+1.593
in
Token in
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+0.000
areas
Token areas
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Israel
Token Israel
Feature activation+0.249
or
Token or
Feature activation+0.000
move
Token move
Feature activation+0.173
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+1.506
Bank
Token Bank
Feature activation+0.096
,
Token,
Feature activation+0.000
East
Token East
Feature activation+1.311
Jerusalem
Token Jerusalem
Feature activation+0.200
,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
checkpoints
Token checkpoints
Feature activation+1.204
and
Token and
Feature activation+0.000
Jewish
Token Jewish
Feature activation+0.455
settlements
Token settlements
Feature activation+1.500
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Sw
TokenSw
Feature activation+0.000
barred
Token barred
Feature activation+0.000
Chomsky
Token Chomsky
Feature activation+0.000
from
Token from
Feature activation+0.000
entering
Token entering
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+1.407
Bank
Token Bank
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
ease
Token ease
Feature activation+0.062
security
Token security
Feature activation+0.006
restrictions
Token restrictions
Feature activation+0.062
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
occupied
Token occupied
Feature activation+1.403
West
Token West
Feature activation+1.687
Bank
Token Bank
Feature activation+0.000
that
Token that
Feature activation+0.000
Palestinians
Token Palestinians
Feature activation+0.000
say
Token say
Feature activation+0.000
The
TokenThe
Feature activation+0.000
West
Token West
Feature activation+1.340
Bank
Token Bank
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.000
PA
Token PA
Feature activation+1.386
leader
Token leader
Feature activation+0.000
Mahmoud
Token Mahmoud
Feature activation+0.350
Abbas
Token Abbas
Feature activation+0.364
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
1948
Token 1948
Feature activation+1.131
/
Token/
Feature activation+0.000
9
Token9
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
1967
Token 1967
Feature activation+1.372
and
Token and
Feature activation+0.000
1973
Token 1973
Feature activation+0.060
respectively
Token respectively
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
football
Token football
Feature activation+0.000
club
Token club
Feature activation+0.000
Mac
Token Mac
Feature activation+0.000
c
Tokenc
Feature activation+0.000
abi
Tokenabi
Feature activation+0.000
Tel
Token Tel
Feature activation+1.370
Aviv
Token Aviv
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
this
Token this
Feature activation+0.000
obstacles
Token obstacles
Feature activation+0.000
to
Token to
Feature activation+0.000
movement
Token movement
Feature activation+0.282
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+1.359
Bank
Token Bank
Feature activation+0.000
(
Token (
Feature activation+0.000
including
Tokenincluding
Feature activation+0.125
East
Token East
Feature activation+1.061
Jerusalem
Token Jerusalem
Feature activation+0.000
ances
Tokenances
Feature activation+0.000
used
Token used
Feature activation+0.000
to
Token to
Feature activation+0.000
fund
Token fund
Feature activation+0.000
the
Token the
Feature activation+0.000
PA
Token PA
Feature activation+1.350
operations
Token operations
Feature activation+0.000
because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
latter
Token latter
Feature activation+0.048
Split
TokenSplit
Feature activation+0.000
authority
Token authority
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
West
Token West
Feature activation+1.340
Bank
Token Bank
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.000
PA
Token PA
Feature activation+1.386
leader
Token leader
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+1.506
Bank
Token Bank
Feature activation+0.096
,
Token,
Feature activation+0.000
East
Token East
Feature activation+1.311
Jerusalem
Token Jerusalem
Feature activation+0.200
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Gaza
Token Gaza
Feature activation+0.000
.
Token.
Feature activation+0.000
soldiers
Token soldiers
Feature activation+0.000
were
Token were
Feature activation+0.000
deployed
Token deployed
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+1.294
Bank
Token Bank
Feature activation+0.000
and
Token and
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Gaza
Token Gaza
Feature activation+0.000
arch
Token arch
Feature activation+0.000
-
Token-
Feature activation+0.000
enemy
Tokenenemy
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
PL
Token PL
Feature activation+1.263
O
TokenO
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
logistical
Token logistical
Feature activation+0.000
and
Token and
Feature activation+0.000
controlled
Tokencontrolled
Feature activation+0.000
areas
Token areas
Feature activation+0.000
divided
Token divided
Feature activation+0.000
by
Token by
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
checkpoints
Token checkpoints
Feature activation+1.204
and
Token and
Feature activation+0.000
Jewish
Token Jewish
Feature activation+0.455
settlements
Token settlements
Feature activation+1.500
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+0.000
thing
Token thing
Feature activation+0.000
called
Token called
Feature activation+0.000
the
Token the
Feature activation+0.000
Arab
Token Arab
Feature activation+0.000
boycott
Token boycott
Feature activation+1.199
;
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
the
Tokenthe
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+0.000
".
Token".
Feature activation+0.000
Eh
Token Eh
Feature activation+1.165
ud
Tokenud
Feature activation+0.775
Ol
Token Ol
Feature activation+0.000
mer
Tokenmer
Feature activation+0.000
t
Tokent
Feature activation+0.000
was
Token was
Feature activation+0.000

Top DFA by src position
MAX = 2.132

bas
Tokenbas
Feature activation+0.001
Top resid features:
urged
Token urged
Feature activation+0.006
Top resid features:
Bush
Token Bush
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
press
Token press
Feature activation+0.007
Top resid features:
Israel
Token Israel
Feature activation+0.665
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
halt
Token halt
Feature activation+0.010
Top resid features:
Jewish
Token Jewish
Feature activation+0.169
Top resid features:
settlements
Token settlements
Feature activation+0.045
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
tear
Token tear
Feature activation+0.003
Top resid features:
gas
Token gas
Feature activation+0.004
Top resid features:
inhal
Token inhal
Feature activation+0.007
Top resid features:
ation
Tokenation
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Israeli
Token Israeli
Feature activation+0.603
Top resid features:
forces
Token forces
Feature activation+0.004
Top resid features:
withdrew
Token withdrew
Feature activation+0.005
Top resid features:
later
Token later
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
no
Token no
Feature activation-0.001
Top resid features:
bas
Tokenbas
Feature activation+0.000
Top resid features:
urged
Token urged
Feature activation+0.011
Top resid features:
Bush
Token Bush
Feature activation+0.020
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
press
Token press
Feature activation+0.016
Top resid features:
Israel
Token Israel
Feature activation+1.023
Top resid features:
to
Token to
Feature activation+0.025
Top resid features:
halt
Token halt
Feature activation+0.020
Top resid features:
Jewish
Token Jewish
Feature activation+0.372
Top resid features:
settlements
Token settlements
Feature activation-0.083
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Nations
Token Nations
Feature activation+0.029
Top resid features:
Security
Token Security
Feature activation+0.014
Top resid features:
Council
Token Council
Feature activation+0.006
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
condemn
Token condemn
Feature activation+0.017
Top resid features:
Israel
Token Israel
Feature activation+1.596
Top resid features:
's
Token's
Feature activation+0.008
Top resid features:
expansion
Token expansion
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.015
Top resid features:
Jewish
Token Jewish
Feature activation+0.573
Top resid features:
settlements
Token settlements
Feature activation-0.121
Top resid features:
was
Token was
Feature activation+0.003
Top resid features:
declared
Token declared
Feature activation+0.003
Top resid features:
over
Token over
Feature activation+0.004
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
occupied
Token occupied
Feature activation+0.006
Top resid features:
Palestinian
Token Palestinian
Feature activation+0.533
Top resid features:
territory
Token territory
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
This
Token This
Feature activation-0.005
Top resid features:
was
Token was
Feature activation+0.004
Top resid features:
when
Token when
Feature activation-0.000
Top resid features:
-
Token-
Feature activation+0.014
Top resid features:
controlled
Tokencontrolled
Feature activation+0.016
Top resid features:
areas
Token areas
Feature activation+0.010
Top resid features:
divided
Token divided
Feature activation-0.015
Top resid features:
by
Token by
Feature activation+0.013
Top resid features:
Israeli
Token Israeli
Feature activation+1.064
Top resid features:
checkpoints
Token checkpoints
Feature activation+0.035
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
Jewish
Token Jewish
Feature activation+0.458
Top resid features:
settlements
Token settlements
Feature activation-0.147
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.002
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
remarks
Token remarks
Feature activation+0.005
Top resid features:
broadcast
Token broadcast
Feature activation+0.008
Top resid features:
on
Token on
Feature activation-0.000
Top resid features:
Palestinian
Token Palestinian
Feature activation+0.807
Top resid features:
television
Token television
Feature activation+0.011
Top resid features:
from
Token from
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
university
Token university
Feature activation+0.003
Top resid features:
on
Token on
Feature activation-0.001
Top resid features:
bas
Tokenbas
Feature activation+0.004
Top resid features:
urged
Token urged
Feature activation+0.014
Top resid features:
Bush
Token Bush
Feature activation+0.016
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
press
Token press
Feature activation+0.013
Top resid features:
Israel
Token Israel
Feature activation+0.700
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
halt
Token halt
Feature activation+0.017
Top resid features:
Jewish
Token Jewish
Feature activation+0.197
Top resid features:
settlements
Token settlements
Feature activation+0.046
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
ľ
Tokenľ
Feature activation+0.004
Top resid features:
We
TokenWe
Feature activation+0.002
Top resid features:
also
Token also
Feature activation+0.002
Top resid features:
urge
Token urge
Feature activation+0.022
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
Palestinian
Token Palestinian
Feature activation+1.627
Top resid features:
president
Token president
Feature activation+0.019
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
establish
Token establish
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
moratorium
Token moratorium
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
join
Token join
Feature activation+0.010
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
wars
Token wars
Feature activation+0.011
Top resid features:
on
Token on
Feature activation+0.003
Top resid features:
Israel
Token Israel
Feature activation+1.295
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
1948
Token 1948
Feature activation+0.006
Top resid features:
/
Token/
Feature activation-0.001
Top resid features:
9
Token9
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
He
TokenHe
Feature activation+0.007
Top resid features:
also
Token also
Feature activation+0.006
Top resid features:
owns
Token owns
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
Israeli
Token Israeli
Feature activation+2.132
Top resid features:
football
Token football
Feature activation+0.032
Top resid features:
club
Token club
Feature activation+0.064
Top resid features:
Mac
Token Mac
Feature activation+0.008
Top resid features:
c
Tokenc
Feature activation+0.028
Top resid features:
abi
Tokenabi
Feature activation+0.061
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.002
Top resid features:
Israel
Token Israel
Feature activation+0.205
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
occupied
Token occupied
Feature activation+0.002
Top resid features:
Palestinian
Token Palestinian
Feature activation+0.489
Top resid features:
territory
Token territory
Feature activation-0.006
Top resid features:
has
Token has
Feature activation-0.001
Top resid features:
become
Token become
Feature activation-0.006
Top resid features:
increasingly
Token increasingly
Feature activation-0.007
Top resid features:
institutional
Token institutional
Feature activation-0.002
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
pay
Token pay
Feature activation+0.003
Top resid features:
these
Token these
Feature activation-0.001
Top resid features:
victims
Token victims
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
Palestinian
Token Palestinian
Feature activation+0.842
Top resid features:
terrorism
Token terrorism
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
The
TokenThe
Feature activation+0.001
Top resid features:
ľ
Tokenľ
Feature activation+0.004
Top resid features:
We
TokenWe
Feature activation+0.004
Top resid features:
also
Token also
Feature activation+0.001
Top resid features:
urge
Token urge
Feature activation+0.009
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
Palestinian
Token Palestinian
Feature activation+1.478
Top resid features:
president
Token president
Feature activation+0.016
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
establish
Token establish
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
moratorium
Token moratorium
Feature activation+0.007
Top resid features:
was
Token was
Feature activation+0.003
Top resid features:
declared
Token declared
Feature activation+0.004
Top resid features:
over
Token over
Feature activation+0.004
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
occupied
Token occupied
Feature activation+0.006
Top resid features:
Palestinian
Token Palestinian
Feature activation+0.668
Top resid features:
territory
Token territory
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
This
Token This
Feature activation-0.005
Top resid features:
was
Token was
Feature activation+0.003
Top resid features:
when
Token when
Feature activation-0.001
Top resid features:
tires
Token tires
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
threw
Token threw
Feature activation-0.003
Top resid features:
rocks
Token rocks
Feature activation+0.001
Top resid features:
at
Token at
Feature activation+0.001
Top resid features:
Israeli
Token Israeli
Feature activation+0.484
Top resid features:
troops
Token troops
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
who
Token who
Feature activation+0.007
Top resid features:
fired
Token fired
Feature activation-0.001
Top resid features:
back
Token back
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
join
Token join
Feature activation+0.004
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
wars
Token wars
Feature activation+0.006
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Israel
Token Israel
Feature activation+1.343
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
1948
Token 1948
Feature activation+0.013
Top resid features:
/
Token/
Feature activation-0.004
Top resid features:
9
Token9
Feature activation+0.001
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
than
Token than
Feature activation+0.009
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
patch
Token patch
Feature activation+0.010
Top resid features:
work
Tokenwork
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
Palestinian
Token Palestinian
Feature activation+0.740
Top resid features:
-
Token-
Feature activation+0.019
Top resid features:
controlled
Tokencontrolled
Feature activation+0.024
Top resid features:
areas
Token areas
Feature activation+0.013
Top resid features:
divided
Token divided
Feature activation+0.004
Top resid features:
by
Token by
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
say
Token say
Feature activation+0.011
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
am
Token am
Feature activation+0.005
Top resid features:
an
Token an
Feature activation+0.008
Top resid features:
Israeli
Token Israeli
Feature activation+1.097
Top resid features:
company
Token company
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
âĢ
TokenâĢ
Feature activation+0.007
Top resid features:
Ŀ
TokenĿ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
as
Token as
Feature activation+0.001
Top resid features:
belonging
Token belonging
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
"
Token "
Feature activation+0.005
Top resid features:
the
Tokenthe
Feature activation+0.014
Top resid features:
Israeli
Token Israeli
Feature activation+1.835
Top resid features:
prime
Token prime
Feature activation+0.010
Top resid features:
minister
Token minister
Feature activation+0.023
Top resid features:
".
Token".
Feature activation+0.004
Top resid features:
Eh
Token Eh
Feature activation-0.143
Top resid features:
ud
Tokenud
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.09

Head 2: 0.39

Head 3: 0.07

Head 4: 0.05

Head 5: 0.04

Head 6: 0.05

Head 7: 0.04

Head 8: 0.05

Head 9: 0.08

Head 10: 0.07

Head 11: 0.03

Positive logits

bloc3.30

warr3.23

upgr3.17

confiscated3.12

د3.05

Arabs3.00

regime3.00

tin2.99

detonated2.95

disadvant2.94

jihadists2.91

jihadist2.90

Syrian2.89

ministerial2.88

���2.88

Galile2.87

governed2.85

Syria2.84

س2.83

caliphate2.83

Negative logits

Phys-3.49

ocket-3.35

mson-3.33

enance-3.29

Clemson-3.08

swick-3.06

SCP-3.00

Weaver-2.98

Hurricanes-2.97

Sage-2.96

umbn-2.94

ancock-2.92

bleacher-2.91

govtrack-2.91

CBI-2.89

Unknown-2.87

awaru-2.87

TION-2.87

Sox-2.86

ffield-2.86

INTERVAL 1.519 - 1.687
CONTAINS 0.000%

press
Token press
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
to
Token to
Feature activation+0.000
halt
Token halt
Feature activation+0.000
Jewish
Token Jewish
Feature activation+0.666
settlements
Token settlements
Feature activation+1.596
and
Token and
Feature activation+0.000
ease
Token ease
Feature activation+0.062
security
Token security
Feature activation+0.006
restrictions
Token restrictions
Feature activation+0.062
in
Token in
Feature activation+0.000
security
Token security
Feature activation+0.006
restrictions
Token restrictions
Feature activation+0.062
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
occupied
Token occupied
Feature activation+1.403
West
Token West
Feature activation+1.687
Bank
Token Bank
Feature activation+0.000
that
Token that
Feature activation+0.000
Palestinians
Token Palestinians
Feature activation+0.000
say
Token say
Feature activation+0.000
cripp
Token cripp
Feature activation+0.000
and
Token and
Feature activation+0.000
unmanned
Token unmanned
Feature activation+0.000
checkpoints
Token checkpoints
Feature activation+0.992
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+1.642
Bank
Token Bank
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
least
Token least
Feature activation+0.000
65
Token 65
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
's
Token's
Feature activation+0.000
expansion
Token expansion
Feature activation+0.000
of
Token of
Feature activation+0.000
Jewish
Token Jewish
Feature activation+0.319
settlements
Token settlements
Feature activation+1.593
in
Token in
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+0.000
areas
Token areas
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000

INTERVAL 1.350 - 1.519
CONTAINS 0.001%

ances
Tokenances
Feature activation+0.000
used
Token used
Feature activation+0.000
to
Token to
Feature activation+0.000
fund
Token fund
Feature activation+0.000
the
Token the
Feature activation+0.000
PA
Token PA
Feature activation+1.350
operations
Token operations
Feature activation+0.000
because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
latter
Token latter
Feature activation+0.048
ease
Token ease
Feature activation+0.062
security
Token security
Feature activation+0.006
restrictions
Token restrictions
Feature activation+0.062
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
occupied
Token occupied
Feature activation+1.403
West
Token West
Feature activation+1.687
Bank
Token Bank
Feature activation+0.000
that
Token that
Feature activation+0.000
Palestinians
Token Palestinians
Feature activation+0.000
say
Token say
Feature activation+0.000
1948
Token 1948
Feature activation+1.131
/
Token/
Feature activation+0.000
9
Token9
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
1967
Token 1967
Feature activation+1.372
and
Token and
Feature activation+0.000
1973
Token 1973
Feature activation+0.060
respectively
Token respectively
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Israel
Token Israel
Feature activation+0.249
or
Token or
Feature activation+0.000
move
Token move
Feature activation+0.173
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+1.506
Bank
Token Bank
Feature activation+0.096
,
Token,
Feature activation+0.000
East
Token East
Feature activation+1.311
Jerusalem
Token Jerusalem
Feature activation+0.200
,
Token,
Feature activation+0.000
barred
Token barred
Feature activation+0.000
Chomsky
Token Chomsky
Feature activation+0.000
from
Token from
Feature activation+0.000
entering
Token entering
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+1.407
Bank
Token Bank
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 1.181 - 1.350
CONTAINS 0.001%

Split
TokenSplit
Feature activation+0.000
authority
Token authority
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
West
Token West
Feature activation+1.340
Bank
Token Bank
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.000
PA
Token PA
Feature activation+1.386
leader
Token leader
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+1.506
Bank
Token Bank
Feature activation+0.096
,
Token,
Feature activation+0.000
East
Token East
Feature activation+1.311
Jerusalem
Token Jerusalem
Feature activation+0.200
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Gaza
Token Gaza
Feature activation+0.000
.
Token.
Feature activation+0.000
controlled
Tokencontrolled
Feature activation+0.000
areas
Token areas
Feature activation+0.000
divided
Token divided
Feature activation+0.000
by
Token by
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
checkpoints
Token checkpoints
Feature activation+1.204
and
Token and
Feature activation+0.000
Jewish
Token Jewish
Feature activation+0.455
settlements
Token settlements
Feature activation+1.500
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+0.000
thing
Token thing
Feature activation+0.000
called
Token called
Feature activation+0.000
the
Token the
Feature activation+0.000
Arab
Token Arab
Feature activation+0.000
boycott
Token boycott
Feature activation+1.199
;
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
soldiers
Token soldiers
Feature activation+0.000
were
Token were
Feature activation+0.000
deployed
Token deployed
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+1.294
Bank
Token Bank
Feature activation+0.000
and
Token and
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Gaza
Token Gaza
Feature activation+0.000

INTERVAL 1.012 - 1.181
CONTAINS 0.001%

the
Token the
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
Defense
Token Defense
Feature activation+0.000
Forces
Token Forces
Feature activation+0.000
(
Token (
Feature activation+0.000
ID
TokenID
Feature activation+1.014
F
TokenF
Feature activation+0.000
)
Token)
Feature activation+0.000
cent
Token cent
Feature activation+0.000
red
Tokenred
Feature activation+0.000
on
Token on
Feature activation+0.000
context
Token context
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
massive
Token massive
Feature activation+0.000
inc
Token inc
Feature activation+0.800
itement
Tokenitement
Feature activation+1.026
campaign
Token campaign
Feature activation+0.000
that
Token that
Feature activation+0.000
escalated
Token escalated
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
carried
Token carried
Feature activation+0.000
plac
Token plac
Feature activation+0.000
ards
Tokenards
Feature activation+0.000
calling
Token calling
Feature activation+0.000
for
Token for
Feature activation+0.000
peace
Token peace
Feature activation+1.066
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Israeli
TokenIsraeli
Feature activation+0.000
inhal
Token inhal
Feature activation+0.009
ation
Tokenation
Feature activation+0.000
.
Token.
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
forces
Token forces
Feature activation+0.000
withdrew
Token withdrew
Feature activation+1.047
later
Token later
Feature activation+0.000
and
Token and
Feature activation+0.000
no
Token no
Feature activation+0.000
arrests
Token arrests
Feature activation+0.000
were
Token were
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+0.000
".
Token".
Feature activation+0.000
Eh
Token Eh
Feature activation+1.165
ud
Tokenud
Feature activation+0.775
Ol
Token Ol
Feature activation+0.000
mer
Tokenmer
Feature activation+0.000
t
Tokent
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 0.844 - 1.012
CONTAINS 0.002%

permits
Token permits
Feature activation+0.000
to
Token to
Feature activation+0.000
move
Token move
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.985
Bank
Token Bank
Feature activation+0.000
,
Token,
Feature activation+0.000
Gaza
Token Gaza
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Netanyahu
Token Netanyahu
Feature activation+0.000
-
Token-
Feature activation+0.000
Eh
TokenEh
Feature activation+1.011
ud
Tokenud
Feature activation+0.955
Bar
Token Bar
Feature activation+0.000
ak
Tokenak
Feature activation+0.026
government
Token government
Feature activation+0.000
is
Token is
Feature activation+0.000
oblivious
Token oblivious
Feature activation+0.000
seized
Token seized
Feature activation+0.000
Soviet
Token Soviet
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
following
Token following
Feature activation+0.000
the
Token the
Feature activation+0.000
Six
Token Six
Feature activation+0.939
Day
Token Day
Feature activation+0.000
War
Token War
Feature activation+0.000
in
Token in
Feature activation+0.000
1967
Token 1967
Feature activation+0.947
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
forces
Token forces
Feature activation+0.000
moved
Token moved
Feature activation+0.000
into
Token into
Feature activation+0.000
Be
Token Be
Feature activation+0.941
it
Tokenit
Feature activation+0.000
D
Token D
Feature activation+0.000
aj
Tokenaj
Feature activation+0.000
an
Tokenan
Feature activation+0.000
village
Token village
Feature activation+0.000
deadly
Token deadly
Feature activation+0.000
year
Token year
Feature activation+0.000
in
Token in
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
-
Token-
Feature activation+0.000
Pal
TokenPal
Feature activation+0.893
estine
Tokenestine
Feature activation+0.324
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
BE
TokenBE
Feature activation+0.000
IJ
TokenIJ
Feature activation+0.000
ING
TokenING
Feature activation+0.000

INTERVAL 0.675 - 0.844
CONTAINS 0.003%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
National
Token National
Feature activation+0.000
Cyber
Token Cyber
Feature activation+0.000
Defense
Token Defense
Feature activation+0.804
Auth
Token Auth
Feature activation+0.000
ort
Tokenort
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
helps
Token helps
Feature activation+0.000
its
Token its
Feature activation+0.000
,
Token,
Feature activation+0.000
29
Token 29
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Get
TokenGet
Feature activation+0.838
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.083
of
Token of
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
's
Token's
Feature activation+0.000
could
Token could
Feature activation+0.000
pray
Token pray
Feature activation+0.000
again
Token again
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Temple
Token Temple
Feature activation+0.780
Mount
Token Mount
Feature activation+0.000
compound
Token compound
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
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
H
TokenH
Feature activation+0.111
ared
Tokenared
Feature activation+0.759
im
Tokenim
Feature activation+0.000
vote
Token vote
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
,
Token,
Feature activation+0.000
He
Token He
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.000
)
Token)
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
PM
Token PM
Feature activation+0.000
Benjamin
Token Benjamin
Feature activation+0.739
Netanyahu
Token Netanyahu
Feature activation+0.000
visits
Token visits
Feature activation+0.317
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.506 - 0.675
CONTAINS 0.003%

during
Token during
Feature activation+0.000
clashes
Token clashes
Feature activation+0.000
last
Token last
Feature activation+0.000
October
Token October
Feature activation+0.000
in
Token in
Feature activation+0.000
occupied
Token occupied
Feature activation+0.673
East
Token East
Feature activation+0.489
Jerusalem
Token Jerusalem
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
press
Token press
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
to
Token to
Feature activation+0.000
halt
Token halt
Feature activation+0.000
Jewish
Token Jewish
Feature activation+0.666
settlements
Token settlements
Feature activation+1.596
and
Token and
Feature activation+0.000
ease
Token ease
Feature activation+0.062
security
Token security
Feature activation+0.006
restrictions
Token restrictions
Feature activation+0.062
but
Token but
Feature activation+0.000
pro
Token pro
Feature activation+0.000
-
Token-
Feature activation+0.000
L
TokenL
Feature activation+0.000
ik
Tokenik
Feature activation+0.000
ud
Tokenud
Feature activation+0.595
ones
Token ones
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
but
Token but
Feature activation+0.000
an
Token an
Feature activation+0.000
IDF
Token IDF
Feature activation+0.000
officer
Token officer
Feature activation+0.000
told
Token told
Feature activation+0.000
Ha
Token Ha
Feature activation+0.529
aretz
Tokenaretz
Feature activation+0.000
newspaper
Token newspaper
Feature activation+0.000
soon
Token soon
Feature activation+0.000
afterwards
Token afterwards
Feature activation+0.000
that
Token that
Feature activation+0.000
sensible
Token sensible
Feature activation+0.000
compromise
Token compromise
Feature activation+0.000
on
Token on
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
Or
TokenOr
Feature activation+0.515
thodox
Tokenthodox
Feature activation+0.000
worship
Token worship
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Western
Token Western
Feature activation+0.000

INTERVAL 0.337 - 0.506
CONTAINS 0.004%

insignificant
Token insignificant
Feature activation+0.000
,
Token,
Feature activation+0.000
advocates
Token advocates
Feature activation+0.000
of
Token of
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+0.000
state
Token state
Feature activation+0.416
hood
Tokenhood
Feature activation+0.438
treated
Token treated
Feature activation+0.000
it
Token it
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
of
Token of
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+0.000
civilians
Token civilians
Feature activation+0.000
suffered
Token suffered
Feature activation+0.000
from
Token from
Feature activation+0.000
tear
Token tear
Feature activation+0.377
gas
Token gas
Feature activation+0.222
inhal
Token inhal
Feature activation+0.009
ation
Tokenation
Feature activation+0.000
.
Token.
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
applies
Token applies
Feature activation+0.000
to
Token to
Feature activation+0.000
this
Token this
Feature activation+0.000
region
Token region
Feature activation+0.362
.
Token .
Feature activation+0.000
.
Token .
Feature activation+0.000
.
Token .
Feature activation+0.000
all
Token all
Feature activation+0.000
states
Token states
Feature activation+0.000
end
Token end
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
walls
Token walls
Feature activation+0.000
and
Token and
Feature activation+0.000
checkpoints
Token checkpoints
Feature activation+0.461
that
Token that
Feature activation+0.000
ring
Token ring
Feature activation+0.000
the
Token the
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+0.000
town
Token town
Feature activation+0.000
or
Token or
Feature activation+0.000
writing
Token writing
Feature activation+0.000
Jewish
Token Jewish
Feature activation+0.000
languages
Token languages
Feature activation+0.000
like
Token like
Feature activation+0.000
Y
Token Y
Feature activation+0.379
idd
Tokenidd
Feature activation+0.232
ish
Tokenish
Feature activation+0.000
,
Token,
Feature activation+0.000
Hebrew
Token Hebrew
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.169 - 0.337
CONTAINS 0.007%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
self
Token self
Feature activation+0.130
-
Token-
Feature activation+0.000
decl
Tokendecl
Feature activation+0.000
ared
Tokenared
Feature activation+0.245
detachment
Token detachment
Feature activation+0.000
will
Token will
Feature activation+0.000
now
Token now
Feature activation+0.000
revive
Token revive
Feature activation+0.000
these
Token these
Feature activation+0.000
Tor
Token Tor
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ab
TokenAb
Feature activation+0.097
bas
Tokenbas
Feature activation+0.279
called
Token called
Feature activation+0.000
the
Token the
Feature activation+0.000
closure
Token closure
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
condemn
Token condemn
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
's
Token's
Feature activation+0.000
expansion
Token expansion
Feature activation+0.000
of
Token of
Feature activation+0.000
Jewish
Token Jewish
Feature activation+0.319
settlements
Token settlements
Feature activation+1.593
in
Token in
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+0.000
areas
Token areas
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
key
Token key
Feature activation+0.000
ingredient
Token ingredient
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.172
weapon
Token weapon
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
TH
TokenTH
Feature activation+0.000
UM
TokenUM
Feature activation+0.000
who
Token who
Feature activation+0.000
took
Token took
Feature activation+0.000
over
Token over
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
AD
Token AD
Feature activation+0.199
L
TokenL
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
national
Token national
Feature activation+0.000

INTERVAL 0.000 - 0.169
CONTAINS 99.978%

the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
'
Token'
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
came
Token came
Feature activation+0.000
to
Token to
Feature activation+0.000
Del
Token Del
Feature activation+0.000
ivering
Tokenivering
Feature activation+0.000
Quality
Token Quality
Feature activation+0.000
First
Token First
Feature activation+0.000
session
Token session
Feature activation+0.000
of
Token of
Feature activation+0.000
parliament
Token parliament
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
urged
Token urged
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
and
Token and
Feature activation+0.000
fellow
Token fellow
Feature activation+0.000
politicians
Token politicians
Feature activation+0.000
to
Token to
Feature activation+0.000
(@
Token (@
Feature activation+0.000
JS
TokenJS
Feature activation+0.000
OP
TokenOP
Feature activation+0.000
IO
TokenIO
Feature activation+0.000
)
Token)
Feature activation+0.000
April
Token April
Feature activation+0.000
5
Token 5
Feature activation+0.000
,
Token,
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Arabic
Token Arabic
Feature activation+0.000
is
Token is
Feature activation+0.000
always
Token always
Feature activation+0.000
a
Token a
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
thing
Token thing
Feature activation+0.000
end
Tokenend
Feature activation+0.000
erson
Tokenerson
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
true
Token true
Feature activation+0.000
master
Token master
Feature activation+0.000
of
Token of
Feature activation+0.000
distance
Token distance
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
his
Token his
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H0.2: (feature 18807)

TOP ACTIVATIONS
MAX = 2.254

age
Token age
Feature activation+0.000
21
Token 21
Feature activation+0.055
for
Token for
Feature activation+0.000
recreational
Token recreational
Feature activation+1.639
or
Token or
Feature activation+0.000
medical
Token medical
Feature activation+2.254
purposes
Token purposes
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
lawmaker
Token lawmaker
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.000
or
Token or
Feature activation+0.000
suspend
Token suspend
Feature activation+0.000
the
Token the
Feature activation+0.000
medical
Token medical
Feature activation+2.038
-
Token-
Feature activation+0.000
m
Tokenm
Feature activation+0.000
arijuana
Tokenarijuana
Feature activation+0.000
ruling
Token ruling
Feature activation+0.000
.
Token.
Feature activation+0.000
legalized
Token legalized
Feature activation+0.550
cannabis
Token cannabis
Feature activation+0.000
to
Token to
Feature activation+0.000
treat
Token treat
Feature activation+0.193
certain
Token certain
Feature activation+0.000
medical
Token medical
Feature activation+1.995
conditions
Token conditions
Feature activation+0.171
in
Token in
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
completed
Token completed
Feature activation+0.000
a
Token a
Feature activation+0.000
harvest
Token harvest
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
medical
Token medical
Feature activation+1.991
marijuana
Token marijuana
Feature activation+0.000
plants
Token plants
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
and
Token and
Feature activation+0.000
Anyone
TokenAnyone
Feature activation+0.000
can
Token can
Feature activation+0.000
go
Token go
Feature activation+0.000
get
Token get
Feature activation+0.000
a
Token a
Feature activation+0.000
medical
Token medical
Feature activation+1.990
card
Token card
Feature activation+0.000
for
Token for
Feature activation+0.000
just
Token just
Feature activation+0.000
about
Token about
Feature activation+0.000
any
Token any
Feature activation+0.000
to
Token to
Feature activation+0.000
carry
Token carry
Feature activation+0.000
higher
Token higher
Feature activation+0.000
levels
Token levels
Feature activation+0.000
of
Token of
Feature activation+0.000
tet
Token tet
Feature activation+1.824
ra
Tokenra
Feature activation+0.000
hydro
Token hydro
Feature activation+0.000
chlor
Tokenchlor
Feature activation+0.000
ide
Tokenide
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+0.000
state
Token state
Feature activation+0.043
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
medical
Token medical
Feature activation+1.817
-
Token-
Feature activation+0.000
m
Tokenm
Feature activation+0.000
arijuana
Tokenarijuana
Feature activation+0.000
program
Token program
Feature activation+0.034
to
Token to
Feature activation+0.000
sell
Token sell
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
with
Token with
Feature activation+0.000
high
Token high
Feature activation+0.000
-
Token-
Feature activation+0.000
TH
TokenTH
Feature activation+1.745
C
TokenC
Feature activation+0.000
levels
Token levels
Feature activation+0.000
as
Token as
Feature activation+0.000
early
Token early
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
state
Token state
Feature activation+0.145
where
Token where
Feature activation+0.000
manufacturing
Token manufacturing
Feature activation+0.000
is
Token is
Feature activation+0.000
legal
Token legal
Feature activation+1.713
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
requires
Token requires
Feature activation+0.000
money
Token money
Feature activation+0.000
or
Token or
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
not
Token not
Feature activation+0.000
legal
Token legal
Feature activation+1.668
to
Token to
Feature activation+0.000
prescribe
Token prescribe
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
animals
Token animals
Feature activation+0.000
So
TokenSo
Feature activation+0.000
while
Token while
Feature activation+0.000
it
Token it
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
legal
Token legal
Feature activation+1.658
for
Token for
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
yourself
Token yourself
Feature activation+0.000
adults
Token adults
Feature activation+1.044
over
Token over
Feature activation+0.000
age
Token age
Feature activation+0.000
21
Token 21
Feature activation+0.055
for
Token for
Feature activation+0.000
recreational
Token recreational
Feature activation+1.639
or
Token or
Feature activation+0.000
medical
Token medical
Feature activation+2.254
purposes
Token purposes
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
would
Token would
Feature activation+0.000
endorse
Token endorse
Feature activation+0.000
a
Token a
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
legalization
Token legalization
Feature activation+0.631
ballot
Token ballot
Feature activation+1.580
measure
Token measure
Feature activation+0.455
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
their
Token their
Feature activation+0.000
active
Token active
Feature activation+0.343
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
if
Token if
Feature activation+0.000
recreational
Token recreational
Feature activation+1.013
and
Token and
Feature activation+0.000
medical
Token medical
Feature activation+1.550
marijuana
Token marijuana
Feature activation+0.000
cost
Token cost
Feature activation+0.000
significantly
Token significantly
Feature activation+0.000
more
Token more
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
delivered
Token delivered
Feature activation+0.000
low
Token low
Feature activation+0.000
-
Token-
Feature activation+0.000
TH
TokenTH
Feature activation+0.568
C
TokenC
Feature activation+0.000
medical
Token medical
Feature activation+1.433
cannabis
Token cannabis
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
patient
Token patient
Feature activation+0.271
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
maximum
Token maximum
Feature activation+0.173
amount
Token amount
Feature activation+0.000
for
Token for
Feature activation+0.000
possession
Token possession
Feature activation+1.424
is
Token is
Feature activation+0.000
30
Token 30
Feature activation+0.000
grams
Token grams
Feature activation+0.148
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
oil
Token oil
Feature activation+0.000
across
Token across
Feature activation+0.000
state
Token state
Feature activation+0.340
lines
Token lines
Feature activation+0.772
remains
Token remains
Feature activation+0.000
illegal
Token illegal
Feature activation+1.300
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
penalties
Token penalties
Feature activation+0.242
of
Token of
Feature activation+0.000
five
Token five
Feature activation+0.000
buy
Token buy
Feature activation+0.000
cannabis
Token cannabis
Feature activation+0.000
with
Token with
Feature activation+0.000
high
Token high
Feature activation+0.000
-
Token-
Feature activation+0.000
TH
TokenTH
Feature activation+1.297
C
TokenC
Feature activation+0.000
levels
Token levels
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
March
Token March
Feature activation+0.000
product
Token product
Feature activation+0.000
online
Token online
Feature activation+0.000
and
Token and
Feature activation+0.000
must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.000
licensed
Token licensed
Feature activation+1.282
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
province
Token province
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
intoxication
Token intoxication
Feature activation+0.000
after
Token after
Feature activation+0.000
a
Token a
Feature activation+0.000
field
Token field
Feature activation+0.000
sob
Token sob
Feature activation+1.274
ri
Tokenri
Feature activation+0.000
ety
Tokenety
Feature activation+0.000
test
Token test
Feature activation+0.000
.
Token.
Feature activation+0.000
A
TokenA
Feature activation+0.000

Top DFA by src position
MAX = 2.456

by
Token by
Feature activation+0.013
Top resid features:
contrast
Token contrast
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
would
Token would
Feature activation+0.008
Top resid features:
allow
Token allow
Feature activation+0.010
Top resid features:
marijuana
Token marijuana
Feature activation+1.462
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
be
Token be
Feature activation+0.010
Top resid features:
sold
Token sold
Feature activation+0.061
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
adults
Token adults
Feature activation+0.037
Top resid features:
Ļ
TokenĻ
Feature activation+0.005
Top resid features:
s
Tokens
Feature activation+0.004
Top resid features:
medical
Token medical
Feature activation-0.031
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
m
Tokenm
Feature activation+0.005
Top resid features:
arijuana
Tokenarijuana
Feature activation+2.456
Top resid features:
law
Token law
Feature activation+0.009
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
constitutional
Token constitutional
Feature activation+0.014
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
The
Token The
Feature activation-0.002
Top resid features:
state
Token state
Feature activation+0.022
Top resid features:
legislature
Token legislature
Feature activation+0.043
Top resid features:
legalized
Token legalized
Feature activation+0.160
Top resid features:
cannabis
Token cannabis
Feature activation+1.465
Top resid features:
to
Token to
Feature activation-0.005
Top resid features:
treat
Token treat
Feature activation+0.026
Top resid features:
certain
Token certain
Feature activation+0.007
Top resid features:
medical
Token medical
Feature activation+0.224
Top resid features:
conditions
Token conditions
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
be
Token be
Feature activation+0.005
Top resid features:
able
Token able
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
sell
Token sell
Feature activation+0.020
Top resid features:
marijuana
Token marijuana
Feature activation+1.338
Top resid features:
with
Token with
Feature activation+0.007
Top resid features:
high
Token high
Feature activation+0.016
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
TH
TokenTH
Feature activation+0.009
Top resid features:
C
TokenC
Feature activation+0.006
Top resid features:
But
TokenBut
Feature activation+0.001
Top resid features:
if
Token if
Feature activation+0.003
Top resid features:
recreational
Token recreational
Feature activation+0.046
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
medical
Token medical
Feature activation-0.001
Top resid features:
marijuana
Token marijuana
Feature activation+1.552
Top resid features:
cost
Token cost
Feature activation+0.004
Top resid features:
significantly
Token significantly
Feature activation+0.006
Top resid features:
more
Token more
Feature activation+0.006
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.008
Top resid features:
at
Token at
Feature activation+0.006
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
much
Token much
Feature activation+0.009
Top resid features:
smaller
Token smaller
Feature activation+0.007
Top resid features:
room
Token room
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Marijuana
Token Marijuana
Feature activation+1.497
Top resid features:
is
Token is
Feature activation+0.007
Top resid features:
unlike
Token unlike
Feature activation+0.010
Top resid features:
other
Token other
Feature activation+0.007
Top resid features:
drugs
Token drugs
Feature activation+0.133
Top resid features:
because
Token because
Feature activation+0.010
Top resid features:
asking
Token asking
Feature activation+0.009
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
federal
Token federal
Feature activation+0.022
Top resid features:
controls
Token controls
Feature activation+0.013
Top resid features:
on
Token on
Feature activation+0.006
Top resid features:
marijuana
Token marijuana
Feature activation+2.141
Top resid features:
be
Token be
Feature activation+0.006
Top resid features:
loos
Token loos
Feature activation+0.009
Top resid features:
ened
Tokenened
Feature activation+0.001
Top resid features:
slightly
Token slightly
Feature activation+0.007
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
be
Token be
Feature activation+0.010
Top resid features:
able
Token able
Feature activation+0.011
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
sell
Token sell
Feature activation+0.021
Top resid features:
marijuana
Token marijuana
Feature activation+1.387
Top resid features:
with
Token with
Feature activation+0.017
Top resid features:
high
Token high
Feature activation+0.029
Top resid features:
-
Token-
Feature activation-0.015
Top resid features:
TH
TokenTH
Feature activation+0.155
Top resid features:
C
TokenC
Feature activation+0.000
Top resid features:
execution
Token execution
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
To
Token To
Feature activation+0.010
Top resid features:
legally
Token legally
Feature activation+0.061
Top resid features:
obtain
Token obtain
Feature activation+0.010
Top resid features:
cannabis
Token cannabis
Feature activation+1.257
Top resid features:
oil
Token oil
Feature activation+0.032
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
family
Token family
Feature activation+0.023
Top resid features:
or
Token or
Feature activation+0.011
Top resid features:
comes
Token comes
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
veterinary
Token veterinary
Feature activation+0.061
Top resid features:
applications
Token applications
Feature activation+0.025
Top resid features:
for
Token for
Feature activation+0.007
Top resid features:
cannabis
Token cannabis
Feature activation+1.436
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
âĢ
TokenâĢ
Feature activation+0.014
Top resid features:
ľ
Tokenľ
Feature activation+0.010
Top resid features:
comes
Token comes
Feature activation+0.006
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
veterinary
Token veterinary
Feature activation+0.076
Top resid features:
applications
Token applications
Feature activation+0.034
Top resid features:
for
Token for
Feature activation+0.010
Top resid features:
cannabis
Token cannabis
Feature activation+1.537
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
âĢ
TokenâĢ
Feature activation+0.018
Top resid features:
ľ
Tokenľ
Feature activation+0.015
Top resid features:
by
Token by
Feature activation+0.013
Top resid features:
contrast
Token contrast
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
would
Token would
Feature activation+0.007
Top resid features:
allow
Token allow
Feature activation+0.012
Top resid features:
marijuana
Token marijuana
Feature activation+1.427
Top resid features:
to
Token to
Feature activation+0.016
Top resid features:
be
Token be
Feature activation+0.014
Top resid features:
sold
Token sold
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.016
Top resid features:
adults
Token adults
Feature activation+0.026
Top resid features:
ending
Token ending
Feature activation+0.011
Top resid features:
prohibition
Token prohibition
Feature activation+0.079
Top resid features:
would
Token would
Feature activation+0.013
Top resid features:
endorse
Token endorse
Feature activation+0.055
Top resid features:
a
Token a
Feature activation+0.027
Top resid features:
marijuana
Token marijuana
Feature activation+0.991
Top resid features:
legalization
Token legalization
Feature activation+0.642
Top resid features:
ballot
Token ballot
Feature activation+0.154
Top resid features:
measure
Token measure
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.014
Top resid features:
restrictions
Token restrictions
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
buys
Token buys
Feature activation+0.028
Top resid features:
medical
Token medical
Feature activation-0.016
Top resid features:
marijuana
Token marijuana
Feature activation+2.255
Top resid features:
with
Token with
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
card
Token card
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
then
Token then
Feature activation-0.000
Top resid features:
disp
Token disp
Feature activation+0.023
Top resid features:
ense
Tokenense
Feature activation+0.008
Top resid features:
medical
Token medical
Feature activation-0.011
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
grade
Tokengrade
Feature activation+0.016
Top resid features:
marijuana
Token marijuana
Feature activation+2.315
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
Florida
Token Florida
Feature activation+0.027
Top resid features:
made
Token made
Feature activation+0.001
Top resid features:
its
Token its
Feature activation+0.009
Top resid features:
first
Token first
Feature activation+0.000
Top resid features:
illegal
Token illegal
Feature activation+0.055
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
as
Token as
Feature activation+0.006
Top resid features:
will
Token will
Feature activation+0.005
Top resid features:
selling
Token selling
Feature activation+0.026
Top resid features:
marijuana
Token marijuana
Feature activation+1.006
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
an
Token an
Feature activation+0.016
Top resid features:
intoxicated
Token intoxicated
Feature activation+0.094
Top resid features:
person
Token person
Feature activation+0.019
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
penalties
Token penalties
Feature activation+0.013
Top resid features:
that
Token that
Feature activation+0.006
Top resid features:
still
Token still
Feature activation+0.004
Top resid features:
apply
Token apply
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Marijuana
Token Marijuana
Feature activation+1.009
Top resid features:
remains
Token remains
Feature activation+0.011
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
Schedule
Token Schedule
Feature activation+0.039
Top resid features:
I
Token I
Feature activation+0.006
Top resid features:
drug
Token drug
Feature activation+0.182
Top resid features:
dy
Token dy
Feature activation-0.066
Top resid features:
ston
Tokenston
Feature activation+0.022
Top resid features:
ia
Tokenia
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
buy
Token buy
Feature activation+0.020
Top resid features:
cannabis
Token cannabis
Feature activation+1.823
Top resid features:
with
Token with
Feature activation+0.003
Top resid features:
high
Token high
Feature activation+0.029
Top resid features:
-
Token-
Feature activation-0.026
Top resid features:
TH
TokenTH
Feature activation+0.199
Top resid features:
C
TokenC
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Lic
TokenLic
Feature activation+0.029
Top resid features:
ensed
Tokenensed
Feature activation+0.004
Top resid features:
cannabis
Token cannabis
Feature activation+0.783
Top resid features:
retailers
Token retailers
Feature activation+0.040
Top resid features:
with
Token with
Feature activation+0.010
Top resid features:
physical
Token physical
Feature activation+0.015
Top resid features:
storefront
Token storefront
Feature activation+0.065
Top resid features:
s
Tokens
Feature activation-0.002
Top resid features:
crash
Token crash
Feature activation+0.027
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Tro
Token Tro
Feature activation+0.012
Top resid features:
opers
Tokenopers
Feature activation+0.028
Top resid features:
determined
Token determined
Feature activation+0.015
Top resid features:
marijuana
Token marijuana
Feature activation+0.951
Top resid features:
intoxication
Token intoxication
Feature activation+0.130
Top resid features:
after
Token after
Feature activation+0.020
Top resid features:
a
Token a
Feature activation+0.027
Top resid features:
field
Token field
Feature activation-0.001
Top resid features:
sob
Token sob
Feature activation+0.217
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.08

Head 2: 0.34

Head 3: 0.06

Head 4: 0.06

Head 5: 0.04

Head 6: 0.05

Head 7: 0.05

Head 8: 0.09

Head 9: 0.08

Head 10: 0.07

Head 11: 0.02

Positive logits

corrid4.45

mascul4.37

���4.16

mosqu4.04

unte3.99

tarians3.83

advoc3.82

ingested3.82

upgr3.78

enriched3.72

contrace3.69

opio3.67

satell3.66

conservancy3.62

dioxide3.62

osph3.60

pollut3.58

isphere3.55

artisan3.55

additive3.45

Negative logits

PsyNetMessage-4.02

enance-3.68

Fairfax-3.66

Weeks-3.50

rawdownloadcloneembedreportprint-3.46

REDACTED-3.46

doors-3.44

Transcript-3.40

stretched-3.35

Months-3.34

Divinity-3.32

Lans-3.22

Wr-3.21

Dear-3.19

-3.19

FontSize-3.16

1027-3.12

Magicka-3.10

FAM-3.09

Doors-3.07

INTERVAL 2.028 - 2.254
CONTAINS 0.000%

age
Token age
Feature activation+0.000
21
Token 21
Feature activation+0.055
for
Token for
Feature activation+0.000
recreational
Token recreational
Feature activation+1.639
or
Token or
Feature activation+0.000
medical
Token medical
Feature activation+2.254
purposes
Token purposes
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
lawmaker
Token lawmaker
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
stay
Token stay
Feature activation+0.000
or
Token or
Feature activation+0.000
suspend
Token suspend
Feature activation+0.000
the
Token the
Feature activation+0.000
medical
Token medical
Feature activation+2.038
-
Token-
Feature activation+0.000
m
Tokenm
Feature activation+0.000
arijuana
Tokenarijuana
Feature activation+0.000
ruling
Token ruling
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.803 - 2.028
CONTAINS 0.001%

completed
Token completed
Feature activation+0.000
a
Token a
Feature activation+0.000
harvest
Token harvest
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
medical
Token medical
Feature activation+1.991
marijuana
Token marijuana
Feature activation+0.000
plants
Token plants
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
and
Token and
Feature activation+0.000
legalized
Token legalized
Feature activation+0.550
cannabis
Token cannabis
Feature activation+0.000
to
Token to
Feature activation+0.000
treat
Token treat
Feature activation+0.193
certain
Token certain
Feature activation+0.000
medical
Token medical
Feature activation+1.995
conditions
Token conditions
Feature activation+0.171
in
Token in
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
to
Token to
Feature activation+0.000
carry
Token carry
Feature activation+0.000
higher
Token higher
Feature activation+0.000
levels
Token levels
Feature activation+0.000
of
Token of
Feature activation+0.000
tet
Token tet
Feature activation+1.824
ra
Tokenra
Feature activation+0.000
hydro
Token hydro
Feature activation+0.000
chlor
Tokenchlor
Feature activation+0.000
ide
Tokenide
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+0.000
state
Token state
Feature activation+0.043
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
medical
Token medical
Feature activation+1.817
-
Token-
Feature activation+0.000
m
Tokenm
Feature activation+0.000
arijuana
Tokenarijuana
Feature activation+0.000
program
Token program
Feature activation+0.034
to
Token to
Feature activation+0.000
Anyone
TokenAnyone
Feature activation+0.000
can
Token can
Feature activation+0.000
go
Token go
Feature activation+0.000
get
Token get
Feature activation+0.000
a
Token a
Feature activation+0.000
medical
Token medical
Feature activation+1.990
card
Token card
Feature activation+0.000
for
Token for
Feature activation+0.000
just
Token just
Feature activation+0.000
about
Token about
Feature activation+0.000
any
Token any
Feature activation+0.000

INTERVAL 1.578 - 1.803
CONTAINS 0.001%

it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
not
Token not
Feature activation+0.000
legal
Token legal
Feature activation+1.668
to
Token to
Feature activation+0.000
prescribe
Token prescribe
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
animals
Token animals
Feature activation+0.000
adults
Token adults
Feature activation+1.044
over
Token over
Feature activation+0.000
age
Token age
Feature activation+0.000
21
Token 21
Feature activation+0.055
for
Token for
Feature activation+0.000
recreational
Token recreational
Feature activation+1.639
or
Token or
Feature activation+0.000
medical
Token medical
Feature activation+2.254
purposes
Token purposes
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
So
TokenSo
Feature activation+0.000
while
Token while
Feature activation+0.000
it
Token it
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
legal
Token legal
Feature activation+1.658
for
Token for
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
yourself
Token yourself
Feature activation+0.000
would
Token would
Feature activation+0.000
endorse
Token endorse
Feature activation+0.000
a
Token a
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
legalization
Token legalization
Feature activation+0.631
ballot
Token ballot
Feature activation+1.580
measure
Token measure
Feature activation+0.455
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
their
Token their
Feature activation+0.000
active
Token active
Feature activation+0.343
a
Token a
Feature activation+0.000
state
Token state
Feature activation+0.145
where
Token where
Feature activation+0.000
manufacturing
Token manufacturing
Feature activation+0.000
is
Token is
Feature activation+0.000
legal
Token legal
Feature activation+1.713
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
requires
Token requires
Feature activation+0.000
money
Token money
Feature activation+0.000
or
Token or
Feature activation+0.000

INTERVAL 1.352 - 1.578
CONTAINS 0.001%

delivered
Token delivered
Feature activation+0.000
low
Token low
Feature activation+0.000
-
Token-
Feature activation+0.000
TH
TokenTH
Feature activation+0.568
C
TokenC
Feature activation+0.000
medical
Token medical
Feature activation+1.433
cannabis
Token cannabis
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
patient
Token patient
Feature activation+0.271
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
if
Token if
Feature activation+0.000
recreational
Token recreational
Feature activation+1.013
and
Token and
Feature activation+0.000
medical
Token medical
Feature activation+1.550
marijuana
Token marijuana
Feature activation+0.000
cost
Token cost
Feature activation+0.000
significantly
Token significantly
Feature activation+0.000
more
Token more
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
maximum
Token maximum
Feature activation+0.173
amount
Token amount
Feature activation+0.000
for
Token for
Feature activation+0.000
possession
Token possession
Feature activation+1.424
is
Token is
Feature activation+0.000
30
Token 30
Feature activation+0.000
grams
Token grams
Feature activation+0.148
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000

INTERVAL 1.127 - 1.352
CONTAINS 0.001%

ra
Tokenra
Feature activation+0.000
hydro
Token hydro
Feature activation+0.000
chlor
Tokenchlor
Feature activation+0.000
ide
Tokenide
Feature activation+0.000
(
Token (
Feature activation+0.000
TH
TokenTH
Feature activation+1.216
C
TokenC
Feature activation+0.000
),
Token),
Feature activation+0.000
which
Token which
Feature activation+0.000
gives
Token gives
Feature activation+0.000
the
Token the
Feature activation+0.000
province
Token province
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Online
TokenOnline
Feature activation+0.000
pot
Token pot
Feature activation+1.232
shoppers
Token shoppers
Feature activation+0.000
will
Token will
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
prove
Token prove
Feature activation+0.000
three
Token three
Feature activation+0.000
other
Token other
Feature activation+0.000
states
Token states
Feature activation+0.840
have
Token have
Feature activation+0.000
legalized
Token legalized
Feature activation+0.911
recreational
Token recreational
Feature activation+1.184
marijuana
Token marijuana
Feature activation+0.000
in
Token in
Feature activation+0.000
recent
Token recent
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
intoxication
Token intoxication
Feature activation+0.000
after
Token after
Feature activation+0.000
a
Token a
Feature activation+0.000
field
Token field
Feature activation+0.000
sob
Token sob
Feature activation+1.274
ri
Tokenri
Feature activation+0.000
ety
Tokenety
Feature activation+0.000
test
Token test
Feature activation+0.000
.
Token.
Feature activation+0.000
A
TokenA
Feature activation+0.000
product
Token product
Feature activation+0.000
online
Token online
Feature activation+0.000
and
Token and
Feature activation+0.000
must
Token must
Feature activation+0.000
be
Token be
Feature activation+0.000
licensed
Token licensed
Feature activation+1.282
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
province
Token province
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.901 - 1.127
CONTAINS 0.002%

that
Token that
Feature activation+0.000
she
Token she
Feature activation+0.000
admitted
Token admitted
Feature activation+0.000
to
Token to
Feature activation+0.000
smoking
Token smoking
Feature activation+0.000
pot
Token pot
Feature activation+0.914
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
crash
Token crash
Feature activation+0.000
.
Token.
Feature activation+0.000
Tro
Token Tro
Feature activation+0.000
apply
Token apply
Feature activation+0.000
.
Token.
Feature activation+0.000
Marijuana
Token Marijuana
Feature activation+0.000
remains
Token remains
Feature activation+0.000
a
Token a
Feature activation+0.000
Schedule
Token Schedule
Feature activation+1.016
I
Token I
Feature activation+0.000
drug
Token drug
Feature activation+0.000
.
Token.
Feature activation+0.000
Transportation
Token Transportation
Feature activation+0.000
of
Token of
Feature activation+0.000
support
Token support
Feature activation+0.000
the
Token the
Feature activation+0.000
trend
Token trend
Feature activation+0.000
toward
Token toward
Feature activation+0.000
a
Token a
Feature activation+0.000
plant
Token plant
Feature activation+0.914
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.000
diet
Token diet
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
ballot
Token ballot
Feature activation+0.716
initiative
Token initiative
Feature activation+0.682
passes
Token passes
Feature activation+0.000
,
Token,
Feature activation+0.000
Colorado
Token Colorado
Feature activation+0.909
did
Token did
Feature activation+0.000
lower
Token lower
Feature activation+0.000
the
Token the
Feature activation+0.000
sales
Token sales
Feature activation+0.000
tax
Token tax
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
diet
Token diet
Feature activation+0.000
free
Token free
Feature activation+0.000
of
Token of
Feature activation+0.000
animal
Token animal
Feature activation+1.068
proteins
Token proteins
Feature activation+0.000
could
Token could
Feature activation+0.000
cause
Token cause
Feature activation+0.000
a
Token a
Feature activation+0.000
deficit
Token deficit
Feature activation+0.000

INTERVAL 0.676 - 0.901
CONTAINS 0.003%

Ċ
TokenĊ
Feature activation+0.000
Regardless
TokenRegardless
Feature activation+0.000
of
Token of
Feature activation+0.000
whether
Token whether
Feature activation+0.000
the
Token the
Feature activation+0.000
ballot
Token ballot
Feature activation+0.716
initiative
Token initiative
Feature activation+0.682
passes
Token passes
Feature activation+0.000
,
Token,
Feature activation+0.000
Colorado
Token Colorado
Feature activation+0.909
did
Token did
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
controlled
Token controlled
Feature activation+0.454
substance
Token substance
Feature activation+0.264
,
Token,
Feature activation+0.000
possession
Token possession
Feature activation+0.880
of
Token of
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
and
Token and
Feature activation+0.000
criminally
Token criminally
Feature activation+0.235
using
Token using
Feature activation+0.000
with
Token with
Feature activation+0.000
fourth
Token fourth
Feature activation+0.000
-
Token-
Feature activation+0.000
degree
Tokendegree
Feature activation+0.000
criminal
Token criminal
Feature activation+0.245
possession
Token possession
Feature activation+0.731
of
Token of
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
and
Token and
Feature activation+0.000
end
Token end
Feature activation+0.000
angering
Tokenangering
Feature activation+0.000
to
Token to
Feature activation+0.000
buy
Token buy
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
illegal
Token illegal
Feature activation+0.890
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
will
Token will
Feature activation+0.000
selling
Token selling
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Medical
Token Medical
Feature activation+0.823
Marijuana
Token Marijuana
Feature activation+0.000
Program
Token Program
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
has
Token has
Feature activation+0.000

INTERVAL 0.451 - 0.676
CONTAINS 0.003%

that
Token that
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
an
Token an
Feature activation+0.000
organization
Token organization
Feature activation+0.496
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
worthy
Token worthy
Feature activation+0.000
of
Token of
Feature activation+0.000
receiving
Token receiving
Feature activation+0.000
Today
TokenToday
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
hitting
Token hitting
Feature activation+0.000
legal
Token legal
Feature activation+0.671
businesses
Token businesses
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
resulting
Token resulting
Feature activation+0.000
with
Token with
Feature activation+0.000
self
Token self
Feature activation+0.000
-
Token-
Feature activation+0.000
identified
Tokenidentified
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
voters
Token voters
Feature activation+0.579
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
margin
Token margin
Feature activation+0.000
of
Token of
Feature activation+0.000
stages
Token stages
Feature activation+0.000
of
Token of
Feature activation+0.000
pregnancy
Token pregnancy
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
pro
Token pro
Feature activation+0.632
-
Token-
Feature activation+0.000
lif
Tokenlif
Feature activation+0.660
ers
Tokeners
Feature activation+0.000
do
Token do
Feature activation+0.000
,
Token,
Feature activation+0.000
prohibition
Token prohibition
Feature activation+0.922
would
Token would
Feature activation+0.000
endorse
Token endorse
Feature activation+0.000
a
Token a
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
legalization
Token legalization
Feature activation+0.631
ballot
Token ballot
Feature activation+1.580
measure
Token measure
Feature activation+0.455
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
their
Token their
Feature activation+0.000

INTERVAL 0.225 - 0.451
CONTAINS 0.006%

a
Token a
Feature activation+0.000
corporation
Token corporation
Feature activation+0.000
selling
Token selling
Feature activation+0.000
across
Token across
Feature activation+0.000
state
Token state
Feature activation+0.000
lines
Token lines
Feature activation+0.244
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Federal
TokenFederal
Feature activation+0.000
authorities
Token authorities
Feature activation+0.000
would
Token would
Feature activation+0.000
apply
Token apply
Feature activation+0.000
to
Token to
Feature activation+0.000
gay
Token gay
Feature activation+0.000
and
Token and
Feature activation+0.000
straight
Token straight
Feature activation+0.253
couples
Token couples
Feature activation+0.000
alike
Token alike
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
both
Token both
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
makes
Token makes
Feature activation+0.000
the
Token the
Feature activation+0.000
ballot
Token ballot
Feature activation+0.401
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Pacific
Token Pacific
Feature activation+0.000
Northwest
Token Northwest
Feature activation+0.000
could
Token could
Feature activation+0.000
up
Token up
Feature activation+0.000
her
Token her
Feature activation+0.000
mind
Token mind
Feature activation+0.000
about
Token about
Feature activation+0.000
ending
Token ending
Feature activation+0.000
prohibition
Token prohibition
Feature activation+0.291
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
leaked
Token leaked
Feature activation+0.000
rate
Token rate
Feature activation+0.000
of
Token of
Feature activation+0.000
contracting
Token contracting
Feature activation+0.000
sexually
Token sexually
Feature activation+0.000
transmitted
Token transmitted
Feature activation+0.177
diseases
Token diseases
Feature activation+0.254
.
Token.
Feature activation+0.000
Well
Token Well
Feature activation+0.000
-
Token-
Feature activation+0.000
rounded
Tokenrounded
Feature activation+0.000
education
Token education
Feature activation+0.000

INTERVAL 0.000 - 0.225
CONTAINS 99.983%

generated
Token generated
Feature activation+0.000
by
Token by
Feature activation+0.000
your
Token your
Feature activation+0.000
arrival
Token arrival
Feature activation+0.000
,
Token,
Feature activation+0.000
unique
Token unique
Feature activation+0.000
to
Token to
Feature activation+0.000
you
Token you
Feature activation+0.000
unless
Token unless
Feature activation+0.000
someone
Token someone
Feature activation+0.000
else
Token else
Feature activation+0.000
could
Token could
Feature activation+0.000
include
Token include
Feature activation+0.000
these
Token these
Feature activation+0.000
words
Token words
Feature activation+0.000
from
Token from
Feature activation+0.000
God
Token God
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
had
Token had
Feature activation+0.000
provided
Token provided
Feature activation+0.000
a
Token a
Feature activation+0.000
w
Token w
Feature activation+0.000
ann
Tokenann
Feature activation+0.000
abe
Tokenabe
Feature activation+0.000
terrorist
Token terrorist
Feature activation+0.000
with
Token with
Feature activation+0.000
dummy
Token dummy
Feature activation+0.000
explosives
Token explosives
Feature activation+0.000
loaded
Token loaded
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
taxes
Token taxes
Feature activation+0.000
will
Token will
Feature activation+0.000
raise
Token raise
Feature activation+0.000
around
Token around
Feature activation+0.000
$
Token $
Feature activation+0.000
1
Token1
Feature activation+0.000
trillion
Token trillion
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Pl
TokenPl
Feature activation+0.000
"
Token "
Feature activation+0.000
Cr
TokenCr
Feature activation+0.000
ack
Tokenack
Feature activation+0.000
in
Token in
Feature activation+0.000
Time
Token Time
Feature activation+0.000
",
Token",
Feature activation+0.000
rather
Token rather
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
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 2 in H0.2: (feature 11742)

TOP ACTIVATIONS
MAX = 2.022

the
Token the
Feature activation+0.000
cost
Token cost
Feature activation+0.469
of
Token of
Feature activation+0.000
getting
Token getting
Feature activation+0.000
to
Token to
Feature activation+0.000
space
Token space
Feature activation+2.022
to
Token to
Feature activation+0.000
hundreds
Token hundreds
Feature activation+0.000
of
Token of
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
per
Token per
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
apparent
Token apparent
Feature activation+0.000
space
Token space
Feature activation+1.822
fragments
Token fragments
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
located
Token located
Feature activation+0.000
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
high
Token high
Feature activation+0.000
cost
Token cost
Feature activation+0.000
of
Token of
Feature activation+0.000
space
Token space
Feature activation+1.668
transportation
Token transportation
Feature activation+0.000
coupled
Token coupled
Feature activation+0.000
with
Token with
Feature activation+0.000
unrel
Token unrel
Feature activation+0.000
iability
Tokeniability
Feature activation+0.000
currently
Token currently
Feature activation+0.000
discour
Token discour
Feature activation+0.000
ages
Tokenages
Feature activation+0.000
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.000
space
Token space
Feature activation+1.583
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
everyday
Token everyday
Feature activation+0.000
environment
Token environment
Feature activation+0.000
.
Token.
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
relayed
Token relayed
Feature activation+0.000
the
Token the
Feature activation+0.000
discovery
Token discovery
Feature activation+0.000
of
Token of
Feature activation+0.000
space
Token space
Feature activation+1.463
debris
Token debris
Feature activation+0.000
found
Token found
Feature activation+0.000
in
Token in
Feature activation+0.000
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.000
core
Token core
Feature activation+0.000
technology
Token technology
Feature activation+0.000
program
Token program
Feature activation+0.415
for
Token for
Feature activation+0.000
all
Token all
Feature activation+0.000
space
Token space
Feature activation+1.417
transportation
Token transportation
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Advanced
Token Advanced
Feature activation+0.000
Space
Token Space
Feature activation+0.441
actually
Token actually
Feature activation+0.000
fragments
Token fragments
Feature activation+0.000
that
Token that
Feature activation+0.000
fell
Token fell
Feature activation+0.000
from
Token from
Feature activation+0.000
space
Token space
Feature activation+1.339
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Officials
TokenOfficials
Feature activation+0.000
excited
Token excited
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
NASA
TokenNASA
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
commercial
Token commercial
Feature activation+1.285
sh
Token sh
Feature activation+0.000
ipper
Tokenipper
Feature activation+0.000
,
Token,
Feature activation+0.000
Orbital
Token Orbital
Feature activation+0.001
ATK
Token ATK
Feature activation+0.000
safety
Token safety
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
reliability
Token reliability
Feature activation+0.000
of
Token of
Feature activation+0.000
space
Token space
Feature activation+1.117
transportation
Token transportation
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
to
Token to
Feature activation+0.000
satellites
Token satellites
Feature activation+0.000
to
Token to
Feature activation+0.000
capture
Token capture
Feature activation+0.000
flying
Token flying
Feature activation+0.000
space
Token space
Feature activation+1.071
debris
Token debris
Feature activation+0.003
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Check
TokenCheck
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
black
Token black
Feature activation+0.000
sky
Token sky
Feature activation+0.000
of
Token of
Feature activation+0.000
space
Token space
Feature activation+1.046
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
V
Token V
Feature activation+0.000
-
Token-
Feature activation+0.000
arm
Tokenarm
Feature activation+0.000
mounted
Token mounted
Feature activation+0.000
Mars
Token Mars
Feature activation+0.000
Hand
Token Hand
Feature activation+0.000
Lens
Token Lens
Feature activation+1.008
Im
Token Im
Feature activation+0.000
ager
Tokenager
Feature activation+0.000
(
Token (
Feature activation+0.000
MA
TokenMA
Feature activation+0.105
HL
TokenHL
Feature activation+0.000
the
Token the
Feature activation+0.000
largest
Token largest
Feature activation+0.000
convention
Token convention
Feature activation+0.000
dedicated
Token dedicated
Feature activation+0.000
to
Token to
Feature activation+0.000
unidentified
Token unidentified
Feature activation+0.961
flying
Token flying
Feature activation+0.000
objects
Token objects
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
t
Tokent
Feature activation+0.000
akes
Tokenakes
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
space
Token space
Feature activation+0.959
agency
Token agency
Feature activation+0.000
acting
Token acting
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
technical
Token technical
Feature activation+0.000
the
Token the
Feature activation+0.000
requirements
Token requirements
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Space
TokenSpace
Feature activation+0.765
X
TokenX
Feature activation+0.000
takes
Token takes
Feature activation+0.000
planetary
Token planetary
Feature activation+0.000
protection
Token protection
Feature activation+0.000
seriously
Token seriously
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
IPCC
Token IPCC
Feature activation+0.000
's
Token's
Feature activation+0.000
Fifth
Token Fifth
Feature activation+0.000
Assessment
Token Assessment
Feature activation+0.684
Report
Token Report
Feature activation+0.000
.
Token.
Feature activation+0.000
Photograph
Token Photograph
Feature activation+0.000
:
Token:
Feature activation+0.000
/
Token /
Feature activation+0.000
launched
Token launched
Feature activation+0.000
Mang
Token Mang
Feature activation+0.000
aly
Tokenaly
Feature activation+0.000
aan
Tokenaan
Feature activation+0.000
into
Token into
Feature activation+0.000
space
Token space
Feature activation+0.656
has
Token has
Feature activation+0.000
successfully
Token successfully
Feature activation+0.000
completed
Token completed
Feature activation+0.000
23
Token 23
Feature activation+0.000
out
Token out
Feature activation+0.000
're
Token're
Feature activation+0.000
flying
Token flying
Feature activation+0.000
your
Token your
Feature activation+0.000
ship
Token ship
Feature activation+0.000
in
Token in
Feature activation+0.000
space
Token space
Feature activation+0.654
"
Token"
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
introduced
Token introduced
Feature activation+0.000
in
Token in
Feature activation+0.000
s
Tokens
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
Science
Token Science
Feature activation+0.000
Dis
Token Dis
Feature activation+0.000
asters
Tokenasters
Feature activation+0.000
Program
Token Program
Feature activation+0.649
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
develop
Token develop
Feature activation+0.000
and
Token and
Feature activation+0.000
share
Token share
Feature activation+0.213
panels
Token panels
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
US
TokenUS
Feature activation+0.000
utility
Token utility
Feature activation+0.615
Duke
Token Duke
Feature activation+0.000
Energy
Token Energy
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000

Top DFA by src position
MAX = 2.095

payload
Token payload
Feature activation+0.057
Top resid features:
in
Token in
Feature activation+0.011
Top resid features:
Earth
Token Earth
Feature activation+0.171
Top resid features:
orbit
Token orbit
Feature activation+0.295
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
NASA
Token NASA
Feature activation+1.520
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ļ
TokenĻ
Feature activation+0.007
Top resid features:
s
Tokens
Feature activation+0.014
Top resid features:
goal
Token goal
Feature activation+0.021
Top resid features:
is
Token is
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
Secretary
Token Secretary
Feature activation+0.012
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
State
Token State
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
NASA
Token NASA
Feature activation+1.429
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
Department
Token Department
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
Defense
Token Defense
Feature activation+0.019
Top resid features:
payload
Token payload
Feature activation+0.033
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
Earth
Token Earth
Feature activation+0.136
Top resid features:
orbit
Token orbit
Feature activation+0.236
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
NASA
Token NASA
Feature activation+1.306
Top resid features:
âĢ
TokenâĢ
Feature activation+0.003
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation+0.004
Top resid features:
goal
Token goal
Feature activation+0.008
Top resid features:
is
Token is
Feature activation+0.005
Top resid features:
payload
Token payload
Feature activation+0.027
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Earth
Token Earth
Feature activation+0.129
Top resid features:
orbit
Token orbit
Feature activation+0.227
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
NASA
Token NASA
Feature activation+1.214
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
s
Tokens
Feature activation+0.003
Top resid features:
goal
Token goal
Feature activation+0.005
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
Earth
Token Earth
Feature activation+0.179
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
AP
Token AP
Feature activation-0.001
Top resid features:
Photo
Token Photo
Feature activation+0.001
Top resid features:
/
Token/
Feature activation-0.006
Top resid features:
NASA
TokenNASA
Feature activation+1.691
Top resid features:
/
Token/
Feature activation-0.006
Top resid features:
J
TokenJ
Feature activation-0.005
Top resid features:
PL
TokenPL
Feature activation-0.004
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
Cal
TokenCal
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.403
Top resid features:
NASA
Token NASA
Feature activation+2.050
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.016
Top resid features:
s
Tokens
Feature activation+0.042
Top resid features:
core
Token core
Feature activation+0.019
Top resid features:
technology
Token technology
Feature activation+0.089
Top resid features:
Earth
Token Earth
Feature activation+0.206
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
AP
Token AP
Feature activation+0.001
Top resid features:
Photo
Token Photo
Feature activation+0.004
Top resid features:
/
Token/
Feature activation-0.005
Top resid features:
NASA
TokenNASA
Feature activation+1.751
Top resid features:
/
Token/
Feature activation-0.004
Top resid features:
J
TokenJ
Feature activation-0.004
Top resid features:
PL
TokenPL
Feature activation-0.001
Top resid features:
-
Token-
Feature activation+0.007
Top resid features:
Cal
TokenCal
Feature activation-0.000
Top resid features:
eastern
Token eastern
Feature activation-0.007
Top resid features:
shore
Token shore
Feature activation+0.044
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
NASA
TokenNASA
Feature activation+2.095
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ļ
TokenĻ
Feature activation-0.000
Top resid features:
s
Tokens
Feature activation+0.030
Top resid features:
commercial
Token commercial
Feature activation+0.289
Top resid features:
sh
Token sh
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.150
Top resid features:
NASA
Token NASA
Feature activation+1.178
Top resid features:
âĢ
TokenâĢ
Feature activation-0.012
Top resid features:
Ļ
TokenĻ
Feature activation-0.000
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
core
Token core
Feature activation-0.002
Top resid features:
technology
Token technology
Feature activation+0.028
Top resid features:
ix
Tokenix
Feature activation+0.012
Top resid features:
ing
Tokening
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
arm
Token arm
Feature activation+0.015
Top resid features:
to
Token to
Feature activation+0.024
Top resid features:
satellites
Token satellites
Feature activation+1.543
Top resid features:
to
Token to
Feature activation+0.030
Top resid features:
capture
Token capture
Feature activation+0.017
Top resid features:
flying
Token flying
Feature activation+0.102
Top resid features:
space
Token space
Feature activation+0.662
Top resid features:
debris
Token debris
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.023
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
black
Token black
Feature activation+0.003
Top resid features:
sky
Token sky
Feature activation+0.095
Top resid features:
of
Token of
Feature activation+0.039
Top resid features:
space
Token space
Feature activation+0.650
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
After
TokenAfter
Feature activation+0.000
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
robot
Token robot
Feature activation+0.068
Top resid features:
-
Token-
Feature activation+0.014
Top resid features:
arm
Tokenarm
Feature activation+0.032
Top resid features:
mounted
Token mounted
Feature activation+0.032
Top resid features:
Mars
Token Mars
Feature activation+1.326
Top resid features:
Hand
Token Hand
Feature activation-0.016
Top resid features:
Lens
Token Lens
Feature activation+0.436
Top resid features:
Im
Token Im
Feature activation+0.000
Top resid features:
ager
Tokenager
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
head
Token head
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
International
Token International
Feature activation+0.027
Top resid features:
UFO
Token UFO
Feature activation+0.857
Top resid features:
Congress
Token Congress
Feature activation+0.021
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
The
TokenThe
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Still
TokenStill
Feature activation+0.001
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
spacecraft
Token spacecraft
Feature activation+0.925
Top resid features:
are
Token are
Feature activation+0.003
Top resid features:
already
Token already
Feature activation+0.002
Top resid features:
approved
Token approved
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
funded
Token funded
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Phil
Token Phil
Feature activation+0.021
Top resid features:
Larson
Token Larson
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
SpaceX
Token SpaceX
Feature activation+0.875
Top resid features:
official
Token official
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
said
Token said
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
company
Token company
Feature activation+0.025
Top resid features:
-
Token -
Feature activation+0.009
Top resid features:
Chapter
Token Chapter
Feature activation+0.021
Top resid features:
14
Token 14
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
IPCC
Token IPCC
Feature activation+1.490
Top resid features:
's
Token's
Feature activation+0.044
Top resid features:
Fifth
Token Fifth
Feature activation+0.027
Top resid features:
Assessment
Token Assessment
Feature activation+0.420
Top resid features:
Report
Token Report
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
launched
Token launched
Feature activation+0.060
Top resid features:
Mang
Token Mang
Feature activation+0.013
Top resid features:
aly
Tokenaly
Feature activation+0.008
Top resid features:
aan
Tokenaan
Feature activation+0.053
Top resid features:
into
Token into
Feature activation+0.076
Top resid features:
space
Token space
Feature activation+0.637
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
successfully
Token successfully
Feature activation+0.000
Top resid features:
completed
Token completed
Feature activation+0.000
Top resid features:
23
Token 23
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
're
Token're
Feature activation+0.017
Top resid features:
flying
Token flying
Feature activation+0.134
Top resid features:
your
Token your
Feature activation+0.044
Top resid features:
ship
Token ship
Feature activation+0.391
Top resid features:
in
Token in
Feature activation+0.079
Top resid features:
space
Token space
Feature activation+0.735
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
introduced
Token introduced
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Marshall
Token Marshall
Feature activation+0.043
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
as
Token as
Feature activation+0.004
Top resid features:
well
Token well
Feature activation+0.015
Top resid features:
as
Token as
Feature activation+0.005
Top resid features:
NASA
Token NASA
Feature activation+0.738
Top resid features:
âĢ
TokenâĢ
Feature activation+0.022
Top resid features:
Ļ
TokenĻ
Feature activation+0.018
Top resid features:
s
Tokens
Feature activation+0.017
Top resid features:
Earth
Token Earth
Feature activation+0.082
Top resid features:
Science
Token Science
Feature activation+0.140
Top resid features:
Energy
Token Energy
Feature activation+0.217
Top resid features:
Group
Token Group
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.010
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation+0.008
Top resid features:
solar
Token solar
Feature activation+0.846
Top resid features:
power
Token power
Feature activation+0.014
Top resid features:
plants
Token plants
Feature activation+0.026
Top resid features:
are
Token are
Feature activation+0.008
Top resid features:
striking
Token striking
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.08

Head 2: 0.33

Head 3: 0.07

Head 4: 0.06

Head 5: 0.06

Head 6: 0.04

Head 7: 0.04

Head 8: 0.08

Head 9: 0.05

Head 10: 0.08

Head 11: 0.03

Positive logits

isphere4.54

helium4.20

aircraft4.15

advoc3.96

role3.83

pollut3.76

satell3.73

gases3.70

aughed3.67

combustion3.67

propulsion3.65

spac3.63

aviation3.61

theorist3.61

icter3.60

space3.60

astronaut3.56

conservancy3.54

traject3.52

trainer3.51

Negative logits

enance-4.82

══-4.63

Interstitial-4.55

Fairfax-4.23

ettings-3.96

Amen-3.72

Gleaming-3.58

Prov-3.56

++++++++++++++++-3.56

bleacher-3.56

Seasons-3.54

CLIENT-3.54

netflix-3.47

dylib-3.46

[&-3.45

Corinth-3.41

Else-3.40

udic-3.39

Democr-3.38

Brow-3.33

INTERVAL 1.820 - 2.022
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
apparent
Token apparent
Feature activation+0.000
space
Token space
Feature activation+1.822
fragments
Token fragments
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
located
Token located
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
cost
Token cost
Feature activation+0.469
of
Token of
Feature activation+0.000
getting
Token getting
Feature activation+0.000
to
Token to
Feature activation+0.000
space
Token space
Feature activation+2.022
to
Token to
Feature activation+0.000
hundreds
Token hundreds
Feature activation+0.000
of
Token of
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
per
Token per
Feature activation+0.000

INTERVAL 1.618 - 1.820
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
high
Token high
Feature activation+0.000
cost
Token cost
Feature activation+0.000
of
Token of
Feature activation+0.000
space
Token space
Feature activation+1.668
transportation
Token transportation
Feature activation+0.000
coupled
Token coupled
Feature activation+0.000
with
Token with
Feature activation+0.000
unrel
Token unrel
Feature activation+0.000
iability
Tokeniability
Feature activation+0.000

INTERVAL 1.415 - 1.618
CONTAINS 0.000%

ly
Tokenly
Feature activation+0.000
relayed
Token relayed
Feature activation+0.000
the
Token the
Feature activation+0.000
discovery
Token discovery
Feature activation+0.000
of
Token of
Feature activation+0.000
space
Token space
Feature activation+1.463
debris
Token debris
Feature activation+0.000
found
Token found
Feature activation+0.000
in
Token in
Feature activation+0.000
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.000
core
Token core
Feature activation+0.000
technology
Token technology
Feature activation+0.000
program
Token program
Feature activation+0.415
for
Token for
Feature activation+0.000
all
Token all
Feature activation+0.000
space
Token space
Feature activation+1.417
transportation
Token transportation
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Advanced
Token Advanced
Feature activation+0.000
Space
Token Space
Feature activation+0.441
currently
Token currently
Feature activation+0.000
discour
Token discour
Feature activation+0.000
ages
Tokenages
Feature activation+0.000
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.000
space
Token space
Feature activation+1.583
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
everyday
Token everyday
Feature activation+0.000
environment
Token environment
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.213 - 1.415
CONTAINS 0.000%

actually
Token actually
Feature activation+0.000
fragments
Token fragments
Feature activation+0.000
that
Token that
Feature activation+0.000
fell
Token fell
Feature activation+0.000
from
Token from
Feature activation+0.000
space
Token space
Feature activation+1.339
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Officials
TokenOfficials
Feature activation+0.000
excited
Token excited
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
NASA
TokenNASA
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
commercial
Token commercial
Feature activation+1.285
sh
Token sh
Feature activation+0.000
ipper
Tokenipper
Feature activation+0.000
,
Token,
Feature activation+0.000
Orbital
Token Orbital
Feature activation+0.001
ATK
Token ATK
Feature activation+0.000

INTERVAL 1.011 - 1.213
CONTAINS 0.000%

from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
black
Token black
Feature activation+0.000
sky
Token sky
Feature activation+0.000
of
Token of
Feature activation+0.000
space
Token space
Feature activation+1.046
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
V
Token V
Feature activation+0.000
safety
Token safety
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
reliability
Token reliability
Feature activation+0.000
of
Token of
Feature activation+0.000
space
Token space
Feature activation+1.117
transportation
Token transportation
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
to
Token to
Feature activation+0.000
satellites
Token satellites
Feature activation+0.000
to
Token to
Feature activation+0.000
capture
Token capture
Feature activation+0.000
flying
Token flying
Feature activation+0.000
space
Token space
Feature activation+1.071
debris
Token debris
Feature activation+0.003
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Check
TokenCheck
Feature activation+0.000

INTERVAL 0.809 - 1.011
CONTAINS 0.000%

the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
space
Token space
Feature activation+0.959
agency
Token agency
Feature activation+0.000
acting
Token acting
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
technical
Token technical
Feature activation+0.000
the
Token the
Feature activation+0.000
largest
Token largest
Feature activation+0.000
convention
Token convention
Feature activation+0.000
dedicated
Token dedicated
Feature activation+0.000
to
Token to
Feature activation+0.000
unidentified
Token unidentified
Feature activation+0.961
flying
Token flying
Feature activation+0.000
objects
Token objects
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
t
Tokent
Feature activation+0.000
akes
Tokenakes
Feature activation+0.000
-
Token-
Feature activation+0.000
arm
Tokenarm
Feature activation+0.000
mounted
Token mounted
Feature activation+0.000
Mars
Token Mars
Feature activation+0.000
Hand
Token Hand
Feature activation+0.000
Lens
Token Lens
Feature activation+1.008
Im
Token Im
Feature activation+0.000
ager
Tokenager
Feature activation+0.000
(
Token (
Feature activation+0.000
MA
TokenMA
Feature activation+0.105
HL
TokenHL
Feature activation+0.000

INTERVAL 0.607 - 0.809
CONTAINS 0.001%

the
Token the
Feature activation+0.000
requirements
Token requirements
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Space
TokenSpace
Feature activation+0.765
X
TokenX
Feature activation+0.000
takes
Token takes
Feature activation+0.000
planetary
Token planetary
Feature activation+0.000
protection
Token protection
Feature activation+0.000
seriously
Token seriously
Feature activation+0.000
panels
Token panels
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
US
TokenUS
Feature activation+0.000
utility
Token utility
Feature activation+0.615
Duke
Token Duke
Feature activation+0.000
Energy
Token Energy
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
IPCC
Token IPCC
Feature activation+0.000
's
Token's
Feature activation+0.000
Fifth
Token Fifth
Feature activation+0.000
Assessment
Token Assessment
Feature activation+0.684
Report
Token Report
Feature activation+0.000
.
Token.
Feature activation+0.000
Photograph
Token Photograph
Feature activation+0.000
:
Token:
Feature activation+0.000
/
Token /
Feature activation+0.000
launched
Token launched
Feature activation+0.000
Mang
Token Mang
Feature activation+0.000
aly
Tokenaly
Feature activation+0.000
aan
Tokenaan
Feature activation+0.000
into
Token into
Feature activation+0.000
space
Token space
Feature activation+0.656
has
Token has
Feature activation+0.000
successfully
Token successfully
Feature activation+0.000
completed
Token completed
Feature activation+0.000
23
Token 23
Feature activation+0.000
out
Token out
Feature activation+0.000
s
Tokens
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
Science
Token Science
Feature activation+0.000
Dis
Token Dis
Feature activation+0.000
asters
Tokenasters
Feature activation+0.000
Program
Token Program
Feature activation+0.649
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
develop
Token develop
Feature activation+0.000
and
Token and
Feature activation+0.000
share
Token share
Feature activation+0.213

INTERVAL 0.404 - 0.607
CONTAINS 0.002%

space
Token space
Feature activation+1.417
transportation
Token transportation
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Advanced
Token Advanced
Feature activation+0.000
Space
Token Space
Feature activation+0.441
Transportation
Token Transportation
Feature activation+0.000
Program
Token Program
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Marshall
Token Marshall
Feature activation+0.069
mission
Token mission
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Soy
Token Soy
Feature activation+0.508
uz
Tokenuz
Feature activation+0.000
-
Token-
Feature activation+0.000
2
Token2
Feature activation+0.000
has
Token has
Feature activation+0.000
three
Token three
Feature activation+0.000
.
Token.
Feature activation+0.000
23
Token23
Feature activation+0.000
Ma
Token Ma
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
NO
TokenNO
Feature activation+0.520
AA
TokenAA
Feature activation+0.000
ES
Token ES
Feature activation+0.000
RL
TokenRL
Feature activation+0.000
CO
Token CO
Feature activation+0.000
2
Token2
Feature activation+0.000
Horizons
Token Horizons
Feature activation+0.000
'
Token'
Feature activation+0.000
principal
Token principal
Feature activation+0.386
investigator
Token investigator
Feature activation+0.000
at
Token at
Feature activation+0.000
Southwest
Token Southwest
Feature activation+0.581
Research
Token Research
Feature activation+0.000
Institute
Token Institute
Feature activation+0.000
,
Token,
Feature activation+0.000
during
Token during
Feature activation+0.000
a
Token a
Feature activation+0.000
restrial
Tokenrestrial
Feature activation+0.000
,
Token,
Feature activation+0.000
crops
Token crops
Feature activation+0.000
circles
Token circles
Feature activation+0.000
and
Token and
Feature activation+0.000
abduct
Token abduct
Feature activation+0.585
ee
Tokenee
Feature activation+0.000
have
Token have
Feature activation+0.000
ever
Token ever
Feature activation+0.000
p
Token p
Feature activation+0.000
iqu
Tokeniqu
Feature activation+0.000

INTERVAL 0.202 - 0.404
CONTAINS 0.004%

that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
Chinese
Token Chinese
Feature activation+0.000
hoax
Token hoax
Feature activation+0.215
--
Token --
Feature activation+0.000
an
Token an
Feature activation+0.000
irrational
Token irrational
Feature activation+0.000
,
Token,
Feature activation+0.000
nonsensical
Token nonsensical
Feature activation+0.000
international
Token international
Feature activation+0.000
pressure
Token pressure
Feature activation+0.000
to
Token to
Feature activation+0.000
abandon
Token abandon
Feature activation+0.000
its
Token its
Feature activation+0.000
arms
Token arms
Feature activation+0.358
development
Token development
Feature activation+0.000
and
Token and
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
program
Token program
Feature activation+0.000
.
Token.
Feature activation+0.000
Reuters
Token Reuters
Feature activation+0.000
/
Token/
Feature activation+0.000
HO
TokenHO
Feature activation+0.000
-
Token-
Feature activation+0.000
Air
TokenAir
Feature activation+0.035
bus
Tokenbus
Feature activation+0.286
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Britain
TokenBritain
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
,
Token,
Feature activation+0.000
European
Token European
Feature activation+0.000
a
Token a
Feature activation+0.000
ero
Tokenero
Feature activation+0.000
space
Token space
Feature activation+0.212
giant
Token giant
Feature activation+0.000
Airbus
Token Airbus
Feature activation+0.000
came
Token came
Feature activation+0.000
out
Token out
Feature activation+0.000
in
Token in
Feature activation+0.000
o
Tokeno
Feature activation+0.000
RT
TokenRT
Feature activation+0.000
)
Token)
Feature activation+0.000
at
Token at
Feature activation+0.000
NASA
Token NASA
Feature activation+0.000
Marshall
Token Marshall
Feature activation+0.396
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
NASA
Token NASA
Feature activation+0.000

INTERVAL 0.000 - 0.202
CONTAINS 99.993%

ended
Token ended
Feature activation+0.000
up
Token up
Feature activation+0.000
having
Token having
Feature activation+0.000
a
Token a
Feature activation+0.000
contest
Token contest
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
who
Token who
Feature activation+0.000
could
Token could
Feature activation+0.000
get
Token get
Feature activation+0.000
farther
Token farther
Feature activation+0.000
fall
Tokenfall
Feature activation+0.000
.
Token.
Feature activation+0.000
According
Token According
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
plaintiffs
Token plaintiffs
Feature activation+0.000
,
Token,
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
stands
Token stands
Feature activation+0.000
to
Token to
Feature activation+0.000
financially
Token financially
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Well
TokenWell
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
those
Token those
Feature activation+0.000
that
Token that
Feature activation+0.000
still
Token still
Feature activation+0.000
love
Token love
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
M
TokenM
Feature activation+0.000
isc
Tokenisc
Feature activation+0.000
onduct
Tokenonduct
Feature activation+0.000
Summary
Token Summary
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
SEA
TokenSEA
Feature activation+0.000
-
Token -
Feature activation+0.000
Os
Token Os
Feature activation+0.000
is
Token is
Feature activation+0.000
legally
Token legally
Feature activation+0.000
re
Token re
Feature activation+0.000
classified
Tokenclassified
Feature activation+0.000
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
private
Token private
Feature activation+0.000
road
Token road
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
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 H0.2: (feature 22966)

TOP ACTIVATIONS
MAX = 1.511

in
Token in
Feature activation+0.000
office
Token office
Feature activation+0.101
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
their
Token their
Feature activation+0.000
federal
Token federal
Feature activation+1.511
leader
Token leader
Feature activation+0.541
lost
Token lost
Feature activation+0.000
a
Token a
Feature activation+0.000
key
Token key
Feature activation+0.000
leadership
Token leadership
Feature activation+0.738
Nadu
Token Nadu
Feature activation+0.000
Leader
Token Leader
Feature activation+0.423
of
Token of
Feature activation+0.000
Opposition
Token Opposition
Feature activation+0.349
and
Token and
Feature activation+0.000
DM
Token DM
Feature activation+1.353
K
TokenK
Feature activation+0.000
leader
Token leader
Feature activation+0.105
M
Token M
Feature activation+0.000
K
Token K
Feature activation+0.000
Stalin
Token Stalin
Feature activation+0.000
B
Token B
Feature activation+0.551
PC
TokenPC
Feature activation+0.000
,
Token,
Feature activation+0.000
Japanese
Token Japanese
Feature activation+0.000
,
Token,
Feature activation+0.000
Commonwealth
Token Commonwealth
Feature activation+1.314
Trust
Token Trust
Feature activation+0.000
ees
Tokenees
Feature activation+0.000
hip
Tokenhip
Feature activation+0.000
and
Token and
Feature activation+0.000
N
Token N
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
west
Token west
Feature activation+0.000
coast
Token coast
Feature activation+0.273
of
Token of
Feature activation+0.000
British
Token British
Feature activation+1.262
Columbia
Token Columbia
Feature activation+0.376
[
Token[
Feature activation+0.000
4
Token4
Feature activation+0.000
]
Token]
Feature activation+0.000
to
Token to
Feature activation+0.000
17
Token 17
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
supporting
Token supporting
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
Leader
Token Leader
Feature activation+1.246
Greg
Token Greg
Feature activation+0.557
Sel
Token Sel
Feature activation+0.964
inger
Tokeninger
Feature activation+0.000
and
Token and
Feature activation+0.000
12
Token 12
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Manitoba
Token Manitoba
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Progressive
Token Progressive
Feature activation+1.241
Conservatives
Token Conservatives
Feature activation+0.000
are
Token are
Feature activation+0.000
well
Token well
Feature activation+0.000
ahead
Token ahead
Feature activation+0.000
of
Token of
Feature activation+0.000
Broad
Token Broad
Feature activation+0.000
band
Tokenband
Feature activation+0.000
Network
Token Network
Feature activation+0.242
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
Prime
Token Prime
Feature activation+1.182
Minister
Token Minister
Feature activation+0.852
-
Token-
Feature activation+0.000
elect
Tokenelect
Feature activation+0.000
Tony
Token Tony
Feature activation+1.115
Abbott
Token Abbott
Feature activation+0.547
reported
Token reported
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
spokesman
Token spokesman
Feature activation+0.000
for
Token for
Feature activation+0.000
Prime
Token Prime
Feature activation+1.116
Minister
Token Minister
Feature activation+0.860
Kevin
Token Kevin
Feature activation+0.909
Rudd
Token Rudd
Feature activation+0.637
refused
Token refused
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
Prime
Token Prime
Feature activation+1.182
Minister
Token Minister
Feature activation+0.852
-
Token-
Feature activation+0.000
elect
Tokenelect
Feature activation+0.000
Tony
Token Tony
Feature activation+1.115
Abbott
Token Abbott
Feature activation+0.547
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
highest
Token highest
Feature activation+0.083
happens
Token happens
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
UK
Token UK
Feature activation+0.030
's
Token's
Feature activation+0.000
exit
Token exit
Feature activation+1.110
deadline
Token deadline
Feature activation+0.164
is
Token is
Feature activation+0.000
30
Token 30
Feature activation+0.000
March
Token March
Feature activation+0.269
2019
Token 2019
Feature activation+0.561
Ontario
Token Ontario
Feature activation+0.000
,
Token,
Feature activation+0.000
Quebec
Token Quebec
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
provinces
Token provinces
Feature activation+1.093
put
Token put
Feature activation+0.000
in
Token in
Feature activation+0.000
place
Token place
Feature activation+0.000
stop
Token stop
Feature activation+0.000
gap
Tokengap
Feature activation+0.000
-
Token-
Feature activation+0.000
secondary
Tokensecondary
Feature activation+0.000
schools
Token schools
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
province
Token province
Feature activation+1.079
are
Token are
Feature activation+0.000
paid
Token paid
Feature activation+0.000
more
Token more
Feature activation+0.000
,
Token,
Feature activation+0.000
sometimes
Token sometimes
Feature activation+0.000
director
Token director
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
Tax
Token Tax
Feature activation+0.000
payers
Tokenpayers
Feature activation+1.079
Federation
Token Federation
Feature activation+0.343
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
e
Tokene
Feature activation+0.000
aster
Tokenaster
Feature activation+0.000
se
Tokense
Feature activation+0.000
als
Tokenals
Feature activation+0.000
.
Token.
Feature activation+0.000
ca
Tokenca
Feature activation+1.074
/
Token/
Feature activation+0.000
english
Tokenenglish
Feature activation+0.000
/
Token/
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
has
Token has
Feature activation+0.000
found
Token found
Feature activation+0.000
growing
Token growing
Feature activation+0.000
support
Token support
Feature activation+0.000
for
Token for
Feature activation+0.000
independence
Token independence
Feature activation+1.060
within
Token within
Feature activation+0.000
the
Token the
Feature activation+0.000
business
Token business
Feature activation+0.000
community
Token community
Feature activation+0.000
and
Token and
Feature activation+0.000
regional
Token regional
Feature activation+0.482
government
Token government
Feature activation+0.173
has
Token has
Feature activation+0.000
called
Token called
Feature activation+0.000
a
Token a
Feature activation+0.000
referendum
Token referendum
Feature activation+1.048
for
Token for
Feature activation+0.000
9
Token 9
Feature activation+0.000
November
Token November
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
most
Token most
Feature activation+0.000
multicultural
Token multicultural
Feature activation+1.028
elector
Token elector
Feature activation+0.345
ates
Tokenates
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
than
Token than
Feature activation+0.000
was
Token was
Feature activation+0.000
forecast
Token forecast
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
PC
Token PC
Feature activation+1.012
budget
Token budget
Feature activation+0.232
for
Token for
Feature activation+0.000
2015
Token 2015
Feature activation+0.108
-
Token-
Feature activation+0.000
16
Token16
Feature activation+0.000
s
Tokens
Feature activation+0.000
Gray
Token Gray
Feature activation+0.000
nd
Tokennd
Feature activation+0.000
ler
Tokenler
Feature activation+0.000
,
Token,
Feature activation+0.000
Kings
Token Kings
Feature activation+0.993
ford
Tokenford
Feature activation+0.000
Smith
Token Smith
Feature activation+0.000
and
Token and
Feature activation+0.000
Brad
Token Brad
Feature activation+0.000
field
Tokenfield
Feature activation+0.000
breadth
Token breadth
Feature activation+0.000
of
Token of
Feature activation+0.000
Scotland
Token Scotland
Feature activation+0.000
talking
Token talking
Feature activation+0.000
about
Token about
Feature activation+0.000
independence
Token independence
Feature activation+0.982
and
Token and
Feature activation+0.000
encouraging
Token encouraging
Feature activation+0.000
the
Token the
Feature activation+0.000
formation
Token formation
Feature activation+0.000
of
Token of
Feature activation+0.000

Top DFA by src position
MAX = 1.906

lost
Token lost
Feature activation+0.026
Top resid features:
elections
Token elections
Feature activation+0.054
Top resid features:
in
Token in
Feature activation+0.028
Top resid features:
Saskatchewan
Token Saskatchewan
Feature activation+0.511
Top resid features:
and
Token and
Feature activation+0.043
Top resid features:
Manitoba
Token Manitoba
Feature activation+1.541
Top resid features:
,
Token,
Feature activation+0.042
Top resid features:
the
Token the
Feature activation+0.042
Top resid features:
latter
Token latter
Feature activation+0.034
Top resid features:
ending
Token ending
Feature activation+0.037
Top resid features:
almost
Token almost
Feature activation+0.021
Top resid features:
notification
Token notification
Feature activation+0.020
Top resid features:
before
Token before
Feature activation+0.035
Top resid features:
commenting
Token commenting
Feature activation+0.083
Top resid features:
.
Token.
Feature activation+0.053
Top resid features:
Tamil
Token Tamil
Feature activation+0.305
Top resid features:
Nadu
Token Nadu
Feature activation+1.569
Top resid features:
Leader
Token Leader
Feature activation+0.081
Top resid features:
of
Token of
Feature activation+0.049
Top resid features:
Opposition
Token Opposition
Feature activation+0.130
Top resid features:
and
Token and
Feature activation+0.057
Top resid features:
DM
Token DM
Feature activation+0.471
Top resid features:
u
Tokenu
Feature activation+0.032
Top resid features:
ans
Tokenans
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
Germans
Token Germans
Feature activation+0.134
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
Australians
Token Australians
Feature activation+1.079
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
B
Token B
Feature activation+0.027
Top resid features:
PC
TokenPC
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
Japanese
Token Japanese
Feature activation+0.147
Top resid features:
covers
Token covers
Feature activation+0.011
Top resid features:
parts
Token parts
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.022
Top resid features:
extreme
Token extreme
Feature activation+0.011
Top resid features:
northern
Token northern
Feature activation+0.033
Top resid features:
Canada
Token Canada
Feature activation+0.984
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
Ċ
TokenĊ
Feature activation+0.049
Top resid features:
Ċ
TokenĊ
Feature activation+0.051
Top resid features:
Canada
TokenCanada
Feature activation+0.879
Top resid features:
has
Token has
Feature activation+0.029
Top resid features:
with
Token with
Feature activation+0.027
Top resid features:
17
Token 17
Feature activation+0.036
Top resid features:
per
Token per
Feature activation+0.013
Top resid features:
cent
Token cent
Feature activation+0.026
Top resid features:
supporting
Token supporting
Feature activation+0.024
Top resid features:
NDP
Token NDP
Feature activation+1.621
Top resid features:
Leader
Token Leader
Feature activation+0.319
Top resid features:
Greg
Token Greg
Feature activation+0.000
Top resid features:
Sel
Token Sel
Feature activation+0.000
Top resid features:
inger
Tokeninger
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
WIN
TokenWIN
Feature activation+0.004
Top resid features:
N
TokenN
Feature activation+0.012
Top resid features:
IP
TokenIP
Feature activation+0.015
Top resid features:
EG
TokenEG
Feature activation+0.015
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.006
Top resid features:
Manitoba
Token Manitoba
Feature activation+1.843
Top resid features:
âĢ
TokenâĢ
Feature activation-0.017
Top resid features:
Ļ
TokenĻ
Feature activation+0.029
Top resid features:
s
Tokens
Feature activation+0.022
Top resid features:
Progressive
Token Progressive
Feature activation+0.459
Top resid features:
Conservatives
Token Conservatives
Feature activation+0.000
Top resid features:
Broadcasting
Token Broadcasting
Feature activation-0.011
Top resid features:
Corporation
Token Corporation
Feature activation+0.049
Top resid features:
last
Token last
Feature activation+0.037
Top resid features:
week
Token week
Feature activation+0.040
Top resid features:
showed
Token showed
Feature activation+0.015
Top resid features:
Australians
Token Australians
Feature activation+1.080
Top resid features:
overwhelmingly
Token overwhelmingly
Feature activation+0.045
Top resid features:
believe
Token believe
Feature activation+0.072
Top resid features:
focusing
Token focusing
Feature activation+0.066
Top resid features:
on
Token on
Feature activation+0.051
Top resid features:
the
Token the
Feature activation+0.066
Top resid features:
the
Token the
Feature activation+0.031
Top resid features:
NSA
Token NSA
Feature activation+0.077
Top resid features:
programs
Token programs
Feature activation+0.030
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
The
Token The
Feature activation+0.064
Top resid features:
Australian
Token Australian
Feature activation+0.882
Top resid features:
reported
Token reported
Feature activation+0.045
Top resid features:
that
Token that
Feature activation+0.020
Top resid features:
a
Token a
Feature activation+0.028
Top resid features:
spokesman
Token spokesman
Feature activation+0.058
Top resid features:
for
Token for
Feature activation+0.016
Top resid features:
Broadcasting
Token Broadcasting
Feature activation+0.012
Top resid features:
Corporation
Token Corporation
Feature activation+0.030
Top resid features:
last
Token last
Feature activation+0.015
Top resid features:
week
Token week
Feature activation+0.023
Top resid features:
showed
Token showed
Feature activation+0.014
Top resid features:
Australians
Token Australians
Feature activation+0.847
Top resid features:
overwhelmingly
Token overwhelmingly
Feature activation+0.051
Top resid features:
believe
Token believe
Feature activation+0.023
Top resid features:
focusing
Token focusing
Feature activation+0.026
Top resid features:
on
Token on
Feature activation+0.036
Top resid features:
the
Token the
Feature activation+0.048
Top resid features:
worried
Token worried
Feature activation+0.033
Top resid features:
about
Token about
Feature activation+0.038
Top resid features:
their
Token their
Feature activation+0.037
Top resid features:
status
Token status
Feature activation+0.032
Top resid features:
once
Token once
Feature activation+0.051
Top resid features:
Brexit
Token Brexit
Feature activation+0.872
Top resid features:
happens
Token happens
Feature activation+0.038
Top resid features:
.
Token.
Feature activation+0.045
Top resid features:
The
Token The
Feature activation+0.079
Top resid features:
UK
Token UK
Feature activation+0.168
Top resid features:
's
Token's
Feature activation+0.063
Top resid features:
In
TokenIn
Feature activation+0.061
Top resid features:
response
Token response
Feature activation+0.054
Top resid features:
to
Token to
Feature activation+0.063
Top resid features:
the
Token the
Feature activation+0.060
Top resid features:
cuts
Token cuts
Feature activation+0.069
Top resid features:
Ontario
Token Ontario
Feature activation+1.006
Top resid features:
,
Token,
Feature activation+0.057
Top resid features:
Quebec
Token Quebec
Feature activation+0.827
Top resid features:
and
Token and
Feature activation+0.088
Top resid features:
other
Token other
Feature activation+0.061
Top resid features:
provinces
Token provinces
Feature activation+0.182
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.256
Top resid features:
or
Token or
Feature activation+0.025
Top resid features:
college
Token college
Feature activation+0.070
Top resid features:
in
Token in
Feature activation+0.017
Top resid features:
Alberta
Token Alberta
Feature activation+1.561
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.013
Top resid features:
especially
Token especially
Feature activation+0.006
Top resid features:
if
Token if
Feature activation+0.010
Top resid features:
you
Token you
Feature activation+0.017
Top resid features:
oversee
Token oversee
Feature activation+0.029
Top resid features:
Thomas
Token Thomas
Feature activation+0.065
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
director
Token director
Feature activation+0.063
Top resid features:
of
Token of
Feature activation+0.060
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
Canadian
Token Canadian
Feature activation+1.906
Top resid features:
Tax
Token Tax
Feature activation+0.098
Top resid features:
payers
Tokenpayers
Feature activation+0.188
Top resid features:
Federation
Token Federation
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
advocate
Token advocate
Feature activation+0.034
Top resid features:
for
Token for
Feature activation+0.023
Top resid features:
Easter
Token Easter
Feature activation+0.036
Top resid features:
Se
Token Se
Feature activation+0.037
Top resid features:
als
Tokenals
Feature activation+0.014
Top resid features:
Vancouver
Token Vancouver
Feature activation+1.483
Top resid features:
.
Token.
Feature activation+0.050
Top resid features:
Learn
Token Learn
Feature activation+0.001
Top resid features:
more
Token more
Feature activation+0.017
Top resid features:
by
Token by
Feature activation+0.044
Top resid features:
visiting
Token visiting
Feature activation+0.040
Top resid features:
Ŀ
TokenĿ
Feature activation+0.049
Top resid features:
Ċ
TokenĊ
Feature activation+0.056
Top resid features:
Ċ
TokenĊ
Feature activation+0.057
Top resid features:
Business
TokenBusiness
Feature activation+0.077
Top resid features:
for
Token for
Feature activation+0.023
Top resid features:
Scotland
Token Scotland
Feature activation+1.624
Top resid features:
has
Token has
Feature activation+0.045
Top resid features:
found
Token found
Feature activation+0.029
Top resid features:
growing
Token growing
Feature activation+0.029
Top resid features:
support
Token support
Feature activation+0.045
Top resid features:
for
Token for
Feature activation+0.018
Top resid features:
and
Token and
Feature activation+0.033
Top resid features:
many
Token many
Feature activation+0.020
Top resid features:
also
Token also
Feature activation+0.027
Top resid features:
waved
Token waved
Feature activation+0.048
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
Scottish
Token Scottish
Feature activation+0.789
Top resid features:
flag
Token flag
Feature activation+0.035
Top resid features:
.
Token.
Feature activation+0.040
Top resid features:
Ċ
TokenĊ
Feature activation+0.058
Top resid features:
Ċ
TokenĊ
Feature activation+0.061
Top resid features:
The
TokenThe
Feature activation+0.087
Top resid features:
conveniently
Token conveniently
Feature activation+0.031
Top resid features:
ignored
Token ignored
Feature activation+0.018
Top resid features:
that
Token that
Feature activation+0.013
Top resid features:
some
Token some
Feature activation+0.025
Top resid features:
of
Token of
Feature activation+0.049
Top resid features:
Australia
Token Australia
Feature activation+1.657
Top resid features:
âĢ
TokenâĢ
Feature activation+0.037
Top resid features:
Ļ
TokenĻ
Feature activation+0.080
Top resid features:
s
Tokens
Feature activation+0.066
Top resid features:
most
Token most
Feature activation+0.015
Top resid features:
multicultural
Token multicultural
Feature activation+0.452
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
spring
Token spring
Feature activation+0.014
Top resid features:
election
Token election
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
NDP
Token NDP
Feature activation+1.424
Top resid features:
campaigned
Token campaigned
Feature activation+0.049
Top resid features:
on
Token on
Feature activation+0.025
Top resid features:
a
Token a
Feature activation+0.021
Top resid features:
budget
Token budget
Feature activation+0.014
Top resid features:
with
Token with
Feature activation+0.023
Top resid features:
Victoria
Token Victoria
Feature activation+0.092
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
More
Token More
Feature activation+0.030
Top resid features:
ton
Tokenton
Feature activation+0.028
Top resid features:
in
Token in
Feature activation+0.022
Top resid features:
Brisbane
Token Brisbane
Feature activation+0.900
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
and
Token and
Feature activation+0.030
Top resid features:
Sydney
Token Sydney
Feature activation+0.680
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.036
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
length
Token length
Feature activation+0.036
Top resid features:
and
Token and
Feature activation+0.039
Top resid features:
breadth
Token breadth
Feature activation+0.019
Top resid features:
of
Token of
Feature activation+0.030
Top resid features:
Scotland
Token Scotland
Feature activation+1.624
Top resid features:
talking
Token talking
Feature activation+0.018
Top resid features:
about
Token about
Feature activation+0.031
Top resid features:
independence
Token independence
Feature activation+0.404
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
encouraging
Token encouraging
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.12

Head 2: 0.31

Head 3: 0.11

Head 4: 0.05

Head 5: 0.04

Head 6: 0.07

Head 7: 0.04

Head 8: 0.05

Head 9: 0.08

Head 10: 0.06

Head 11: 0.04

Positive logits

unemploy4.09

seiz3.99

pse3.94

citiz3.90

helicop3.86

corrid3.85

mosqu3.79

murd3.72

opio3.70

elector3.59

streng3.57

conservancy3.57

advoc3.50

ministerial3.46

resil3.41

metic3.41

etheless3.36

mathemat3.35

contrace3.34

fielded3.34

Negative logits

ONSORED-4.09

Sheep-3.72

66666666-3.69

early-3.63

YES-3.54

sole-3.53

ded-3.51

STD-3.45

reads-3.34

200000-3.33

Origin-3.23

Breath-3.21

FACE-3.14

OX-3.13

Condition-3.08

dates-3.05

6666-3.04

Curiosity-3.02

HO-3.01

Kid-3.01

INTERVAL 1.360 - 1.511
CONTAINS 0.000%

in
Token in
Feature activation+0.000
office
Token office
Feature activation+0.101
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
their
Token their
Feature activation+0.000
federal
Token federal
Feature activation+1.511
leader
Token leader
Feature activation+0.541
lost
Token lost
Feature activation+0.000
a
Token a
Feature activation+0.000
key
Token key
Feature activation+0.000
leadership
Token leadership
Feature activation+0.738

INTERVAL 1.209 - 1.360
CONTAINS 0.001%

âĢĶ
Token âĢĶ
Feature activation+0.000
Manitoba
Token Manitoba
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Progressive
Token Progressive
Feature activation+1.241
Conservatives
Token Conservatives
Feature activation+0.000
are
Token are
Feature activation+0.000
well
Token well
Feature activation+0.000
ahead
Token ahead
Feature activation+0.000
of
Token of
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
west
Token west
Feature activation+0.000
coast
Token coast
Feature activation+0.273
of
Token of
Feature activation+0.000
British
Token British
Feature activation+1.262
Columbia
Token Columbia
Feature activation+0.376
[
Token[
Feature activation+0.000
4
Token4
Feature activation+0.000
]
Token]
Feature activation+0.000
to
Token to
Feature activation+0.000
17
Token 17
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
supporting
Token supporting
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
Leader
Token Leader
Feature activation+1.246
Greg
Token Greg
Feature activation+0.557
Sel
Token Sel
Feature activation+0.964
inger
Tokeninger
Feature activation+0.000
and
Token and
Feature activation+0.000
12
Token 12
Feature activation+0.000
Nadu
Token Nadu
Feature activation+0.000
Leader
Token Leader
Feature activation+0.423
of
Token of
Feature activation+0.000
Opposition
Token Opposition
Feature activation+0.349
and
Token and
Feature activation+0.000
DM
Token DM
Feature activation+1.353
K
TokenK
Feature activation+0.000
leader
Token leader
Feature activation+0.105
M
Token M
Feature activation+0.000
K
Token K
Feature activation+0.000
Stalin
Token Stalin
Feature activation+0.000
B
Token B
Feature activation+0.551
PC
TokenPC
Feature activation+0.000
,
Token,
Feature activation+0.000
Japanese
Token Japanese
Feature activation+0.000
,
Token,
Feature activation+0.000
Commonwealth
Token Commonwealth
Feature activation+1.314
Trust
Token Trust
Feature activation+0.000
ees
Tokenees
Feature activation+0.000
hip
Tokenhip
Feature activation+0.000
and
Token and
Feature activation+0.000
N
Token N
Feature activation+0.000

INTERVAL 1.058 - 1.209
CONTAINS 0.001%

reported
Token reported
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
spokesman
Token spokesman
Feature activation+0.000
for
Token for
Feature activation+0.000
Prime
Token Prime
Feature activation+1.116
Minister
Token Minister
Feature activation+0.860
Kevin
Token Kevin
Feature activation+0.909
Rudd
Token Rudd
Feature activation+0.637
refused
Token refused
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
Prime
Token Prime
Feature activation+1.182
Minister
Token Minister
Feature activation+0.852
-
Token-
Feature activation+0.000
elect
Tokenelect
Feature activation+0.000
Tony
Token Tony
Feature activation+1.115
Abbott
Token Abbott
Feature activation+0.547
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
highest
Token highest
Feature activation+0.083
-
Token-
Feature activation+0.000
secondary
Tokensecondary
Feature activation+0.000
schools
Token schools
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
province
Token province
Feature activation+1.079
are
Token are
Feature activation+0.000
paid
Token paid
Feature activation+0.000
more
Token more
Feature activation+0.000
,
Token,
Feature activation+0.000
sometimes
Token sometimes
Feature activation+0.000
Broad
Token Broad
Feature activation+0.000
band
Tokenband
Feature activation+0.000
Network
Token Network
Feature activation+0.242
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
Prime
Token Prime
Feature activation+1.182
Minister
Token Minister
Feature activation+0.852
-
Token-
Feature activation+0.000
elect
Tokenelect
Feature activation+0.000
Tony
Token Tony
Feature activation+1.115
Abbott
Token Abbott
Feature activation+0.547
has
Token has
Feature activation+0.000
found
Token found
Feature activation+0.000
growing
Token growing
Feature activation+0.000
support
Token support
Feature activation+0.000
for
Token for
Feature activation+0.000
independence
Token independence
Feature activation+1.060
within
Token within
Feature activation+0.000
the
Token the
Feature activation+0.000
business
Token business
Feature activation+0.000
community
Token community
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.907 - 1.058
CONTAINS 0.002%

,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
former
Token former
Feature activation+0.000
Liberal
Token Liberal
Feature activation+0.000
cabinet
Token cabinet
Feature activation+0.966
minister
Token minister
Feature activation+0.000
Bill
Token Bill
Feature activation+0.126
Bennett
Token Bennett
Feature activation+0.000
told
Token told
Feature activation+0.000
me
Token me
Feature activation+0.173
matter
Token matter
Feature activation+0.000
of
Token of
Feature activation+0.000
time
Token time
Feature activation+0.000
until
Token until
Feature activation+0.000
young
Token young
Feature activation+0.000
rugby
Token rugby
Feature activation+0.908
league
Token league
Feature activation+0.000
players
Token players
Feature activation+0.000
from
Token from
Feature activation+0.000
low
Token low
Feature activation+0.000
socio
Token socio
Feature activation+0.000
addressed
Token addressed
Feature activation+0.000
a
Token a
Feature activation+0.000
gathering
Token gathering
Feature activation+0.000
that
Token that
Feature activation+0.000
included
Token included
Feature activation+0.000
Tao
Token Tao
Feature activation+0.956
ise
Tokenise
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
End
Token End
Feature activation+0.000
a
Tokena
Feature activation+0.000
Kenny
Token Kenny
Feature activation+0.609
than
Token than
Feature activation+0.000
was
Token was
Feature activation+0.000
forecast
Token forecast
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
PC
Token PC
Feature activation+1.012
budget
Token budget
Feature activation+0.232
for
Token for
Feature activation+0.000
2015
Token 2015
Feature activation+0.108
-
Token-
Feature activation+0.000
16
Token16
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
multicultural
Token multicultural
Feature activation+0.939
city
Token city
Feature activation+0.461
in
Token in
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
âĢ¦
Token âĢ¦
Feature activation+0.000
We
Token We
Feature activation+0.000

INTERVAL 0.756 - 0.907
CONTAINS 0.002%

ates
Tokenates
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
divorce
Token divorce
Feature activation+0.827
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
European
Token European
Feature activation+0.000
Union
Token Union
Feature activation+0.000
.
Token.
Feature activation+0.000
expected
Token expected
Feature activation+0.000
more
Token more
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Trudeau
Token Trudeau
Feature activation+0.003
government
Token government
Feature activation+0.792
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
ised
Tokenised
Feature activation+0.000
by
Token by
Feature activation+0.000
Scotland
Token Scotland
Feature activation+0.000
's
Token's
Feature activation+0.000
forthcoming
Token forthcoming
Feature activation+0.000
independence
Token independence
Feature activation+0.829
referendum
Token referendum
Feature activation+0.573
-
Token -
Feature activation+0.000
and
Token and
Feature activation+0.000
many
Token many
Feature activation+0.000
also
Token also
Feature activation+0.000
public
Token public
Feature activation+0.000
broadcaster
Token broadcaster
Feature activation+0.358
,
Token,
Feature activation+0.000
guarantees
Token guarantees
Feature activation+0.000
its
Token its
Feature activation+0.000
independence
Token independence
Feature activation+0.796
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
outlines
Token outlines
Feature activation+0.000
the
Token the
Feature activation+0.000
duties
Token duties
Feature activation+0.000
east
Token east
Feature activation+0.000
of
Token of
Feature activation+0.000
Toronto
Token Toronto
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Progressive
Token Progressive
Feature activation+0.815
Conservative
Token Conservative
Feature activation+0.000
Leader
Token Leader
Feature activation+0.565
said
Token said
Feature activation+0.000
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000

INTERVAL 0.605 - 0.756
CONTAINS 0.004%

across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+0.026
under
Token under
Feature activation+0.000
a
Token a
Feature activation+0.000
single
Token single
Feature activation+0.752
set
Token set
Feature activation+0.000
of
Token of
Feature activation+0.000
regulations
Token regulations
Feature activation+0.000
.
Token.
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
playoff
Token playoff
Feature activation+0.024
action
Token action
Feature activation+0.000
after
Token after
Feature activation+0.000
stunning
Token stunning
Feature activation+0.000
the
Token the
Feature activation+0.000
Hamilton
Token Hamilton
Feature activation+0.735
Tiger
Token Tiger
Feature activation+0.441
-
Token-
Feature activation+0.000
C
TokenC
Feature activation+0.000
ats
Tokenats
Feature activation+0.000
35
Token 35
Feature activation+0.000
sea
Tokensea
Feature activation+0.000
centres
Token centres
Feature activation+0.000
in
Token in
Feature activation+0.000
London
Token London
Feature activation+0.000
,
Token,
Feature activation+0.000
Old
Token Old
Feature activation+0.652
Windsor
Token Windsor
Feature activation+0.000
and
Token and
Feature activation+0.000
Brands
Token Brands
Feature activation+0.000
Hatch
Token Hatch
Feature activation+0.000
.
Token.
Feature activation+0.000
Parliament
Token Parliament
Feature activation+0.000
's
Token's
Feature activation+0.000
chief
Token chief
Feature activation+0.080
Brexit
Token Brexit
Feature activation+0.000
negotiator
Token negotiator
Feature activation+0.260
Guy
Token Guy
Feature activation+0.752
Ver
Token Ver
Feature activation+0.127
hof
Tokenhof
Feature activation+0.000
stadt
Tokenstadt
Feature activation+0.000
Getty
Token Getty
Feature activation+0.000
6
Token 6
Feature activation+0.000
4
Token 4
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
billion
Token billion
Feature activation+0.000
UK
Token UK
Feature activation+0.000
pounds
Token pounds
Feature activation+0.693
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
roughly
Token roughly
Feature activation+0.000
US
Token US
Feature activation+0.000
$
Token $
Feature activation+0.000

INTERVAL 0.453 - 0.605
CONTAINS 0.008%

of
Token of
Feature activation+0.000
Women
Token Women
Feature activation+0.413
Entreprene
Token Entreprene
Feature activation+0.358
urs
Tokenurs
Feature activation+0.000
and
Token and
Feature activation+0.000
Business
Token Business
Feature activation+0.554
Leaders
Token Leaders
Feature activation+0.648
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Photo
TokenPhoto
Feature activation+0.000
by
Token by
Feature activation+0.000
Newfoundland
Token Newfoundland
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
provincial
Token provincial
Feature activation+0.236
government
Token government
Feature activation+0.457
calculated
Token calculated
Feature activation+0.000
the
Token the
Feature activation+0.000
opening
Token opening
Feature activation+0.000
of
Token of
Feature activation+0.000
European
Token European
Feature activation+0.000
up
Token up
Feature activation+0.000
.
Token.
Feature activation+0.000
UK
Token UK
Feature activation+0.000
Prime
Token Prime
Feature activation+0.461
Minister
Token Minister
Feature activation+0.000
David
Token David
Feature activation+0.467
Cameron
Token Cameron
Feature activation+0.182
said
Token said
Feature activation+0.000
his
Token his
Feature activation+0.000
government
Token government
Feature activation+0.000
would
Token would
Feature activation+0.000
of
Token of
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
-
Token-
Feature activation+0.000
run
Tokenrun
Feature activation+0.000
Ord
Token Ord
Feature activation+0.000
nance
Tokennance
Feature activation+0.482
Fact
Token Fact
Feature activation+0.000
ories
Tokenories
Feature activation+0.000
Board
Token Board
Feature activation+0.000
overseeing
Token overseeing
Feature activation+0.000
the
Token the
Feature activation+0.000
real
Token real
Feature activation+0.000
test
Token test
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Trudeau
Token Trudeau
Feature activation+0.000
government
Token government
Feature activation+0.594
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
failed
Token failed
Feature activation+0.000
the
Token the
Feature activation+0.000
test
Token test
Feature activation+0.000

INTERVAL 0.302 - 0.453
CONTAINS 0.013%

the
Token the
Feature activation+0.000
Mexican
Token Mexican
Feature activation+0.000
state
Token state
Feature activation+0.000
of
Token of
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
ihu
Tokenihu
Feature activation+0.316
ah
Tokenah
Feature activation+0.000
ua
Tokenua
Feature activation+0.000
returned
Token returned
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
impossible
Token impossible
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Trudeau
Token Trudeau
Feature activation+0.384
government
Token government
Feature activation+0.907
to
Token to
Feature activation+0.000
honestly
Token honestly
Feature activation+0.000
square
Token square
Feature activation+0.167
this
Token this
Feature activation+0.000
was
Token was
Feature activation+0.000
long
Token long
Feature activation+0.000
overdue
Token overdue
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Government
Token Government
Feature activation+0.442
should
Token should
Feature activation+0.000
have
Token have
Feature activation+0.000
supported
Token supported
Feature activation+0.000
its
Token its
Feature activation+0.000
proposal
Token proposal
Feature activation+0.000
action
Token action
Feature activation+0.000
was
Token was
Feature activation+0.000
taken
Token taken
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
Commonwealth
Token Commonwealth
Feature activation+0.419
Attorney
Token Attorney
Feature activation+0.000
General
Token General
Feature activation+0.000
's
Token's
Feature activation+0.000
Department
Token Department
Feature activation+0.000
and
Token and
Feature activation+0.000
time
Token time
Feature activation+0.000
last
Token last
Feature activation+0.000
spring
Token spring
Feature activation+0.000
under
Token under
Feature activation+0.000
president
Token president
Feature activation+0.000
Mas
Token Mas
Feature activation+0.335
ai
Tokenai
Feature activation+0.000
U
Token U
Feature activation+0.000
j
Tokenj
Feature activation+0.000
iri
Tokeniri
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000

INTERVAL 0.151 - 0.302
CONTAINS 0.024%

cabinet
Token cabinet
Feature activation+0.966
minister
Token minister
Feature activation+0.000
Bill
Token Bill
Feature activation+0.126
Bennett
Token Bennett
Feature activation+0.000
told
Token told
Feature activation+0.000
me
Token me
Feature activation+0.173
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Unfortunately
TokenUnfortunately
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
.
Token.
Feature activation+0.000
00
Token00
Feature activation+0.000
Total
Token Total
Feature activation+0.000
of
Token of
Feature activation+0.000
Mak
Token Mak
Feature activation+0.230
ati
Tokenati
Feature activation+0.000
City
Token City
Feature activation+0.000
's
Token's
Feature activation+0.000
4
Token 4
Feature activation+0.000
Christmas
Token Christmas
Feature activation+0.000
prosecutors
Token prosecutors
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
of
Token of
Feature activation+0.000
Par
Token Par
Feature activation+0.204
á
Tokená
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
dam
Token dam
Feature activation+0.000
construction
Token construction
Feature activation+0.000
And
Token And
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
Ottawa
Token Ottawa
Feature activation+0.000
By
Token By
Feature activation+0.000
ward
Tokenward
Feature activation+0.000
Market
Token Market
Feature activation+0.158
will
Token will
Feature activation+0.000
experience
Token experience
Feature activation+0.000
the
Token the
Feature activation+0.000
personal
Token personal
Feature activation+0.000
style
Token style
Feature activation+0.000
Power
Token Power
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Summers
Token Summers
Feature activation+0.000
ide
Tokenide
Feature activation+0.000
Storm
Token Storm
Feature activation+0.237
were
Token were
Feature activation+0.000
established
Token established
Feature activation+0.000
and
Token and
Feature activation+0.000
had
Token had
Feature activation+0.000
announced
Token announced
Feature activation+0.000

INTERVAL 0.000 - 0.151
CONTAINS 99.946%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
document
Token document
Feature activation+0.000
rate
Token rate
Feature activation+0.000
changes
Token changes
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
first
Token first
Feature activation+0.000
security
Token security
Feature activation+0.000
interests
Token interests
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
productive
Token productive
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
is
Token is
Feature activation+0.000
expected
Token expected
Feature activation+0.000
to
Token to
Feature activation+0.000
youngsters
Token youngsters
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
One
TokenOne
Feature activation+0.000
simply
Token simply
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Delete
TokenDelete
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
slider
Token slider
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
pitch
Token pitch
Feature activation+0.000
moved
Token moved
Feature activation+0.000
back
Token back
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
ling
Tokenling
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
over
Token over
Feature activation+0.000
claims
Token claims
Feature activation+0.000
that
Token that
Feature activation+0.000
Di
Token Di
Feature activation+0.000
Cap
TokenCap
Feature activation+0.000
rio
Tokenrio
Feature activation+0.000
was
Token was
Feature activation+0.000
raped
Token raped
Feature activation+0.000
by
Token by
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 H0.2: (feature 13716)

TOP ACTIVATIONS
MAX = 1.814

up
Token up
Feature activation+0.000
a
Token a
Feature activation+0.000
$
Token $
Feature activation+0.000
400
Token400
Feature activation+0.000
million
Token million
Feature activation+0.000
Fisheries
Token Fisheries
Feature activation+1.814
Fund
Token Fund
Feature activation+0.000
,
Token,
Feature activation+0.000
cost
Token cost
Feature activation+0.000
-
Token-
Feature activation+0.000
shared
Tokenshared
Feature activation+0.000
support
Token support
Feature activation+0.000
the
Token the
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
minority
Token minority
Feature activation+1.765
government
Token government
Feature activation+1.227
in
Token in
Feature activation+0.000
B
Token B
Feature activation+1.227
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
in
Token in
Feature activation+0.000
annual
Token annual
Feature activation+0.000
spending
Token spending
Feature activation+0.000
.
Token.
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
Leader
Token Leader
Feature activation+1.681
Tom
Token Tom
Feature activation+0.218
Mulcair
Token Mulcair
Feature activation+0.036
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
adamant
Token adamant
Feature activation+0.671
He
Token He
Feature activation+0.000
hr
Tokenhr
Feature activation+0.000
,
Token,
Feature activation+0.000
advanced
Token advanced
Feature activation+0.000
education
Token education
Feature activation+0.000
critic
Token critic
Feature activation+1.635
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Alberta
Token Alberta
Feature activation+0.000
Liberals
Token Liberals
Feature activation+0.367
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
PC
TokenPC
Feature activation+0.503
interim
Token interim
Feature activation+0.210
Leader
Token Leader
Feature activation+1.628
Ric
Token Ric
Feature activation+0.377
Mc
Token Mc
Feature activation+0.072
I
TokenI
Feature activation+0.000
ver
Tokenver
Feature activation+0.000
said
Token said
Feature activation+0.000
mayor
Token mayor
Feature activation+0.381
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
premier
Token premier
Feature activation+1.320
of
Token of
Feature activation+0.000
British
Token British
Feature activation+1.607
Columbia
Token Columbia
Feature activation+0.597
also
Token also
Feature activation+0.000
backed
Token backed
Feature activation+0.000
the
Token the
Feature activation+0.000
call
Token call
Feature activation+0.000
four
Token four
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Alberta
Token Alberta
Feature activation+0.105
legislature
Token legislature
Feature activation+1.587
was
Token was
Feature activation+0.000
debating
Token debating
Feature activation+0.137
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.306
20
Token 20
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
Green
Token Green
Feature activation+0.500
Party
Token Party
Feature activation+0.458
Leader
Token Leader
Feature activation+1.555
Andrew
Token Andrew
Feature activation+1.243
Weaver
Token Weaver
Feature activation+1.134
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
aboriginal
Token aboriginal
Feature activation+0.000
children
Token children
Feature activation+0.000
who
Token who
Feature activation+0.000
attended
Token attended
Feature activation+0.000
the
Token the
Feature activation+0.000
residential
Token residential
Feature activation+1.481
schools
Token schools
Feature activation+0.000
died
Token died
Feature activation+0.000
at
Token at
Feature activation+0.000
school
Token school
Feature activation+0.000
or
Token or
Feature activation+0.000
),
Token),
Feature activation+0.000
Re
Token Re
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
Bank
TokenBank
Feature activation+0.121
,
Token,
Feature activation+0.000
CI
Token CI
Feature activation+1.440
BC
TokenBC
Feature activation+0.000
,
Token,
Feature activation+0.000
National
Token National
Feature activation+0.032
Bank
Token Bank
Feature activation+0.373
of
Token of
Feature activation+0.000
risk
Token risk
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Liberals
Token Liberals
Feature activation+0.000
in
Token in
Feature activation+0.000
rid
Token rid
Feature activation+1.427
ings
Tokenings
Feature activation+0.000
with
Token with
Feature activation+0.000
large
Token large
Feature activation+0.000
South
Token South
Feature activation+0.000
Asian
Token Asian
Feature activation+0.000
became
Token became
Feature activation+0.000
eligible
Token eligible
Feature activation+0.000
to
Token to
Feature activation+0.000
vote
Token vote
Feature activation+0.000
in
Token in
Feature activation+0.000
federal
Token federal
Feature activation+1.421
elections
Token elections
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
fail
Token fail
Feature activation+0.000
to
Token to
Feature activation+0.000
laughing
Token laughing
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
NDP
Token NDP
Feature activation+0.467
leader
Token leader
Feature activation+1.419
then
Token then
Feature activation+0.000
seems
Token seems
Feature activation+0.000
to
Token to
Feature activation+0.000
consult
Token consult
Feature activation+0.731
with
Token with
Feature activation+0.000
Pierre
TokenPierre
Feature activation+0.107
Trudeau
Token Trudeau
Feature activation+0.000
,
Token,
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.128
Prime
Token Prime
Feature activation+1.164
Minister
Token Minister
Feature activation+1.381
for
Token for
Feature activation+0.000
over
Token over
Feature activation+0.000
15
Token 15
Feature activation+0.000
years
Token years
Feature activation+0.000
).
Token).
Feature activation+0.000
Mulcair
Token Mulcair
Feature activation+0.036
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
adamant
Token adamant
Feature activation+0.671
his
Token his
Feature activation+0.000
party
Token party
Feature activation+1.380
wouldn
Token wouldn
Feature activation+0.000
't
Token't
Feature activation+0.000
run
Token run
Feature activation+0.220
a
Token a
Feature activation+0.000
deficit
Token deficit
Feature activation+0.556
B
Token B
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
Leader
Token Leader
Feature activation+1.362
John
Token John
Feature activation+0.149
Hor
Token Hor
Feature activation+0.769
gan
Tokengan
Feature activation+0.000
and
Token and
Feature activation+0.000
B
Token B
Feature activation+0.846
week
Token week
Feature activation+0.000
the
Token the
Feature activation+0.000
chances
Token chances
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
provincial
Token provincial
Feature activation+1.350
rival
Token rival
Feature activation+0.000
final
Token final
Feature activation+0.000
showdown
Token showdown
Feature activation+0.029
improved
Token improved
Feature activation+0.000
to
Token to
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
mayor
Token mayor
Feature activation+0.381
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
premier
Token premier
Feature activation+1.320
of
Token of
Feature activation+0.000
British
Token British
Feature activation+1.607
Columbia
Token Columbia
Feature activation+0.597
also
Token also
Feature activation+0.000
backed
Token backed
Feature activation+0.000
this
Token this
Feature activation+0.000
metric
Token metric
Feature activation+0.000
are
Token are
Feature activation+0.000
both
Token both
Feature activation+0.000
in
Token in
Feature activation+0.000
provinces
Token provinces
Feature activation+1.293
suffering
Token suffering
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
oil
Token oil
Feature activation+0.000
crash
Token crash
Feature activation+0.000
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
Green
Token Green
Feature activation+0.500
Party
Token Party
Feature activation+0.458
Leader
Token Leader
Feature activation+1.555
Andrew
Token Andrew
Feature activation+1.243
Weaver
Token Weaver
Feature activation+1.134
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

Top DFA by src position
MAX = 2.062

s
Tokens
Feature activation+0.023
Top resid features:
negotiated
Token negotiated
Feature activation+0.038
Top resid features:
an
Token an
Feature activation+0.018
Top resid features:
agreement
Token agreement
Feature activation+0.024
Top resid features:
with
Token with
Feature activation+0.031
Top resid features:
Ottawa
Token Ottawa
Feature activation+1.679
Top resid features:
to
Token to
Feature activation+0.030
Top resid features:
set
Token set
Feature activation+0.029
Top resid features:
up
Token up
Feature activation+0.028
Top resid features:
a
Token a
Feature activation+0.037
Top resid features:
$
Token $
Feature activation+0.054
Top resid features:
see
Token see
Feature activation+0.023
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
Greens
Token Greens
Feature activation+0.037
Top resid features:
support
Token support
Feature activation+0.035
Top resid features:
the
Token the
Feature activation+0.043
Top resid features:
NDP
Token NDP
Feature activation+1.349
Top resid features:
as
Token as
Feature activation+0.062
Top resid features:
a
Token a
Feature activation+0.062
Top resid features:
minority
Token minority
Feature activation+0.835
Top resid features:
government
Token government
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
billion
Token billion
Feature activation+0.042
Top resid features:
in
Token in
Feature activation+0.036
Top resid features:
annual
Token annual
Feature activation+0.031
Top resid features:
spending
Token spending
Feature activation+0.038
Top resid features:
.
Token.
Feature activation+0.067
Top resid features:
NDP
Token NDP
Feature activation+1.873
Top resid features:
Leader
Token Leader
Feature activation+0.624
Top resid features:
Tom
Token Tom
Feature activation+0.000
Top resid features:
Mulcair
Token Mulcair
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
me
Tokenme
Feature activation+0.013
Top resid features:
or
Token or
Feature activation+0.018
Top resid features:
reason
Token reason
Feature activation+0.025
Top resid features:
to
Token to
Feature activation+0.019
Top resid features:
what
Token what
Feature activation+0.024
Top resid features:
Alberta
Token Alberta
Feature activation+0.967
Top resid features:
university
Token university
Feature activation+0.066
Top resid features:
presidents
Token presidents
Feature activation+0.040
Top resid features:
are
Token are
Feature activation+0.021
Top resid features:
making
Token making
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
Not
Token Not
Feature activation+0.038
Top resid features:
ley
Tokenley
Feature activation+0.035
Top resid features:
âĢ
TokenâĢ
Feature activation+0.034
Top resid features:
Ļ
TokenĻ
Feature activation+0.031
Top resid features:
s
Tokens
Feature activation+0.037
Top resid features:
NDP
Token NDP
Feature activation+1.674
Top resid features:
.
Token.
Feature activation+0.056
Top resid features:
Ċ
TokenĊ
Feature activation+0.054
Top resid features:
Ċ
TokenĊ
Feature activation+0.058
Top resid features:
PC
TokenPC
Feature activation+0.026
Top resid features:
interim
Token interim
Feature activation+0.123
Top resid features:
to
Token to
Feature activation+0.022
Top resid features:
an
Token an
Feature activation+0.025
Top resid features:
online
Token online
Feature activation+0.034
Top resid features:
petition
Token petition
Feature activation+0.019
Top resid features:
while
Token while
Feature activation+0.020
Top resid features:
Vancouver
Token Vancouver
Feature activation+0.980
Top resid features:
âĢ
TokenâĢ
Feature activation+0.030
Top resid features:
Ļ
TokenĻ
Feature activation+0.031
Top resid features:
s
Tokens
Feature activation+0.030
Top resid features:
mayor
Token mayor
Feature activation+0.043
Top resid features:
and
Token and
Feature activation+0.051
Top resid features:
for
Token for
Feature activation+0.022
Top resid features:
four
Token four
Feature activation+0.020
Top resid features:
years
Token years
Feature activation+0.020
Top resid features:
.
Token.
Feature activation+0.046
Top resid features:
The
Token The
Feature activation+0.067
Top resid features:
Alberta
Token Alberta
Feature activation+1.212
Top resid features:
legislature
Token legislature
Feature activation+0.828
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
debating
Token debating
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
issue
Token issue
Feature activation+0.000
Top resid features:
between
Token between
Feature activation+0.017
Top resid features:
B
Token B
Feature activation+0.018
Top resid features:
.
Token.
Feature activation+0.046
Top resid features:
C
TokenC
Feature activation+0.028
Top resid features:
.
Token.
Feature activation+0.048
Top resid features:
NDP
Token NDP
Feature activation+1.908
Top resid features:
Leader
Token Leader
Feature activation+0.102
Top resid features:
John
Token John
Feature activation+0.067
Top resid features:
Hor
Token Hor
Feature activation+0.036
Top resid features:
gan
Tokengan
Feature activation+0.048
Top resid features:
and
Token and
Feature activation+0.046
Top resid features:
to
Token to
Feature activation+0.023
Top resid features:
42
Token 42
Feature activation+0.022
Top resid features:
per
Token per
Feature activation+0.018
Top resid features:
cent
Token cent
Feature activation+0.028
Top resid features:
of
Token of
Feature activation+0.033
Top resid features:
aboriginal
Token aboriginal
Feature activation+1.135
Top resid features:
children
Token children
Feature activation+0.001
Top resid features:
who
Token who
Feature activation+0.042
Top resid features:
attended
Token attended
Feature activation+0.057
Top resid features:
the
Token the
Feature activation+0.054
Top resid features:
residential
Token residential
Feature activation+0.897
Top resid features:
BS
TokenBS
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
Royal
Token Royal
Feature activation+0.045
Top resid features:
Bank
Token Bank
Feature activation+0.080
Top resid features:
of
Token of
Feature activation+0.019
Top resid features:
Canada
Token Canada
Feature activation+1.774
Top resid features:
(
Token (
Feature activation+0.049
Top resid features:
R
TokenR
Feature activation+0.036
Top resid features:
BC
TokenBC
Feature activation+0.025
Top resid features:
),
Token),
Feature activation+0.037
Top resid features:
Re
Token Re
Feature activation+0.033
Top resid features:
And
Token And
Feature activation+0.039
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
risk
Token risk
Feature activation+0.061
Top resid features:
to
Token to
Feature activation+0.051
Top resid features:
the
Token the
Feature activation+0.038
Top resid features:
Liberals
Token Liberals
Feature activation+0.953
Top resid features:
in
Token in
Feature activation+0.049
Top resid features:
rid
Token rid
Feature activation+0.856
Top resid features:
ings
Tokenings
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
large
Token large
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.022
Top resid features:
population
Token population
Feature activation+0.037
Top resid features:
]
Token]
Feature activation+0.019
Top resid features:
cannot
Token cannot
Feature activation+0.022
Top resid features:
name
Token name
Feature activation+0.024
Top resid features:
Canada
Token Canada
Feature activation+1.034
Top resid features:
âĢ
TokenâĢ
Feature activation+0.025
Top resid features:
Ļ
TokenĻ
Feature activation+0.024
Top resid features:
s
Tokens
Feature activation+0.027
Top resid features:
first
Token first
Feature activation+0.030
Top resid features:
Prime
Token Prime
Feature activation+0.046
Top resid features:
seen
Token seen
Feature activation+0.030
Top resid features:
laughing
Token laughing
Feature activation+0.026
Top resid features:
.
Token.
Feature activation+0.043
Top resid features:
But
Token But
Feature activation+0.062
Top resid features:
the
Token the
Feature activation+0.052
Top resid features:
NDP
Token NDP
Feature activation+0.923
Top resid features:
leader
Token leader
Feature activation+0.794
Top resid features:
then
Token then
Feature activation+0.000
Top resid features:
seems
Token seems
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
consult
Token consult
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.028
Top resid features:
(
Token (
Feature activation+0.055
Top resid features:
Pierre
TokenPierre
Feature activation+0.068
Top resid features:
Trudeau
Token Trudeau
Feature activation+0.489
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
Canadian
Token Canadian
Feature activation+1.321
Top resid features:
Prime
Token Prime
Feature activation+0.478
Top resid features:
Minister
Token Minister
Feature activation+0.161
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
15
Token 15
Feature activation+0.000
Top resid features:
billion
Token billion
Feature activation+0.042
Top resid features:
in
Token in
Feature activation+0.026
Top resid features:
annual
Token annual
Feature activation+0.039
Top resid features:
spending
Token spending
Feature activation+0.041
Top resid features:
.
Token.
Feature activation+0.040
Top resid features:
NDP
Token NDP
Feature activation+1.076
Top resid features:
Leader
Token Leader
Feature activation+0.082
Top resid features:
Tom
Token Tom
Feature activation+0.028
Top resid features:
Mulcair
Token Mulcair
Feature activation+0.688
Top resid features:
has
Token has
Feature activation+0.035
Top resid features:
been
Token been
Feature activation+0.040
Top resid features:
between
Token between
Feature activation+0.021
Top resid features:
B
Token B
Feature activation+0.028
Top resid features:
.
Token.
Feature activation+0.062
Top resid features:
C
TokenC
Feature activation+0.043
Top resid features:
.
Token.
Feature activation+0.064
Top resid features:
NDP
Token NDP
Feature activation+2.062
Top resid features:
Leader
Token Leader
Feature activation+0.486
Top resid features:
John
Token John
Feature activation+0.000
Top resid features:
Hor
Token Hor
Feature activation+0.000
Top resid features:
gan
Tokengan
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
simulator
Token simulator
Feature activation+0.047
Top resid features:
said
Token said
Feature activation+0.025
Top resid features:
that
Token that
Feature activation+0.021
Top resid features:
a
Token a
Feature activation+0.023
Top resid features:
Calgary
Token Calgary
Feature activation+1.139
Top resid features:
and
Token and
Feature activation+0.034
Top resid features:
Edmonton
Token Edmonton
Feature activation+0.729
Top resid features:
matchup
Token matchup
Feature activation+0.044
Top resid features:
was
Token was
Feature activation+0.023
Top resid features:
8
Token 8
Feature activation+0.024
Top resid features:
to
Token to
Feature activation+0.029
Top resid features:
an
Token an
Feature activation+0.042
Top resid features:
online
Token online
Feature activation+0.038
Top resid features:
petition
Token petition
Feature activation+0.030
Top resid features:
while
Token while
Feature activation+0.035
Top resid features:
Vancouver
Token Vancouver
Feature activation+0.809
Top resid features:
âĢ
TokenâĢ
Feature activation+0.049
Top resid features:
Ļ
TokenĻ
Feature activation+0.035
Top resid features:
s
Tokens
Feature activation+0.055
Top resid features:
mayor
Token mayor
Feature activation+0.059
Top resid features:
and
Token and
Feature activation+0.075
Top resid features:
The
Token The
Feature activation+0.040
Top resid features:
top
Token top
Feature activation+0.026
Top resid features:
two
Token two
Feature activation+0.024
Top resid features:
cities
Token cities
Feature activation+0.034
Top resid features:
in
Token in
Feature activation+0.026
Top resid features:
Canada
Token Canada
Feature activation+1.183
Top resid features:
on
Token on
Feature activation+0.023
Top resid features:
this
Token this
Feature activation+0.040
Top resid features:
metric
Token metric
Feature activation+0.046
Top resid features:
are
Token are
Feature activation+0.036
Top resid features:
both
Token both
Feature activation+0.019
Top resid features:
between
Token between
Feature activation+0.016
Top resid features:
B
Token B
Feature activation+0.024
Top resid features:
.
Token.
Feature activation+0.037
Top resid features:
C
TokenC
Feature activation+0.025
Top resid features:
.
Token.
Feature activation+0.038
Top resid features:
NDP
Token NDP
Feature activation+1.488
Top resid features:
Leader
Token Leader
Feature activation+0.069
Top resid features:
John
Token John
Feature activation+0.106
Top resid features:
Hor
Token Hor
Feature activation+0.029
Top resid features:
gan
Tokengan
Feature activation+0.052
Top resid features:
and
Token and
Feature activation+0.044
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.11

Head 2: 0.30

Head 3: 0.10

Head 4: 0.05

Head 5: 0.05

Head 6: 0.09

Head 7: 0.04

Head 8: 0.04

Head 9: 0.08

Head 10: 0.06

Head 11: 0.05

Positive logits

unemploy3.91

conservancy3.74

mosqu3.73

fielded3.68

upgr3.51

dominated3.51

querque3.46

opio3.38

honoured3.38

ageing3.32

fuelled3.28

electorate3.27

metic3.27

helicop3.25

wedd3.16

constituency3.11

reclaimed3.10

ejected3.04

incent3.04

senal3.02

Negative logits

-3.71

YES-3.70

doors-3.57

vantage-3.33

Recon-3.31

sole-3.28

utm-3.24

shows-3.22

yes-3.18

early-3.09

66666666-3.07

Known-3.06

versions-3.03

}"-3.01

potion-3.01

/+-3.00

dstg-2.99

})-2.98

close-2.97

reads-2.95

INTERVAL 1.633 - 1.814
CONTAINS 0.000%

in
Token in
Feature activation+0.000
annual
Token annual
Feature activation+0.000
spending
Token spending
Feature activation+0.000
.
Token.
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
Leader
Token Leader
Feature activation+1.681
Tom
Token Tom
Feature activation+0.218
Mulcair
Token Mulcair
Feature activation+0.036
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
adamant
Token adamant
Feature activation+0.671
He
Token He
Feature activation+0.000
hr
Tokenhr
Feature activation+0.000
,
Token,
Feature activation+0.000
advanced
Token advanced
Feature activation+0.000
education
Token education
Feature activation+0.000
critic
Token critic
Feature activation+1.635
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Alberta
Token Alberta
Feature activation+0.000
Liberals
Token Liberals
Feature activation+0.367
.
Token.
Feature activation+0.000
up
Token up
Feature activation+0.000
a
Token a
Feature activation+0.000
$
Token $
Feature activation+0.000
400
Token400
Feature activation+0.000
million
Token million
Feature activation+0.000
Fisheries
Token Fisheries
Feature activation+1.814
Fund
Token Fund
Feature activation+0.000
,
Token,
Feature activation+0.000
cost
Token cost
Feature activation+0.000
-
Token-
Feature activation+0.000
shared
Tokenshared
Feature activation+0.000
support
Token support
Feature activation+0.000
the
Token the
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
minority
Token minority
Feature activation+1.765
government
Token government
Feature activation+1.227
in
Token in
Feature activation+0.000
B
Token B
Feature activation+1.227
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000

INTERVAL 1.451 - 1.633
CONTAINS 0.001%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
PC
TokenPC
Feature activation+0.503
interim
Token interim
Feature activation+0.210
Leader
Token Leader
Feature activation+1.628
Ric
Token Ric
Feature activation+0.377
Mc
Token Mc
Feature activation+0.072
I
TokenI
Feature activation+0.000
ver
Tokenver
Feature activation+0.000
said
Token said
Feature activation+0.000
aboriginal
Token aboriginal
Feature activation+0.000
children
Token children
Feature activation+0.000
who
Token who
Feature activation+0.000
attended
Token attended
Feature activation+0.000
the
Token the
Feature activation+0.000
residential
Token residential
Feature activation+1.481
schools
Token schools
Feature activation+0.000
died
Token died
Feature activation+0.000
at
Token at
Feature activation+0.000
school
Token school
Feature activation+0.000
or
Token or
Feature activation+0.000
mayor
Token mayor
Feature activation+0.381
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
premier
Token premier
Feature activation+1.320
of
Token of
Feature activation+0.000
British
Token British
Feature activation+1.607
Columbia
Token Columbia
Feature activation+0.597
also
Token also
Feature activation+0.000
backed
Token backed
Feature activation+0.000
the
Token the
Feature activation+0.000
call
Token call
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
Green
Token Green
Feature activation+0.500
Party
Token Party
Feature activation+0.458
Leader
Token Leader
Feature activation+1.555
Andrew
Token Andrew
Feature activation+1.243
Weaver
Token Weaver
Feature activation+1.134
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
four
Token four
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Alberta
Token Alberta
Feature activation+0.105
legislature
Token legislature
Feature activation+1.587
was
Token was
Feature activation+0.000
debating
Token debating
Feature activation+0.137
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.306
20
Token 20
Feature activation+0.000

INTERVAL 1.270 - 1.451
CONTAINS 0.001%

),
Token),
Feature activation+0.000
Re
Token Re
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
Bank
TokenBank
Feature activation+0.121
,
Token,
Feature activation+0.000
CI
Token CI
Feature activation+1.440
BC
TokenBC
Feature activation+0.000
,
Token,
Feature activation+0.000
National
Token National
Feature activation+0.032
Bank
Token Bank
Feature activation+0.373
of
Token of
Feature activation+0.000
B
Token B
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
Leader
Token Leader
Feature activation+1.362
John
Token John
Feature activation+0.149
Hor
Token Hor
Feature activation+0.769
gan
Tokengan
Feature activation+0.000
and
Token and
Feature activation+0.000
B
Token B
Feature activation+0.846
risk
Token risk
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Liberals
Token Liberals
Feature activation+0.000
in
Token in
Feature activation+0.000
rid
Token rid
Feature activation+1.427
ings
Tokenings
Feature activation+0.000
with
Token with
Feature activation+0.000
large
Token large
Feature activation+0.000
South
Token South
Feature activation+0.000
Asian
Token Asian
Feature activation+0.000
week
Token week
Feature activation+0.000
the
Token the
Feature activation+0.000
chances
Token chances
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
provincial
Token provincial
Feature activation+1.350
rival
Token rival
Feature activation+0.000
final
Token final
Feature activation+0.000
showdown
Token showdown
Feature activation+0.029
improved
Token improved
Feature activation+0.000
to
Token to
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
mayor
Token mayor
Feature activation+0.381
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
premier
Token premier
Feature activation+1.320
of
Token of
Feature activation+0.000
British
Token British
Feature activation+1.607
Columbia
Token Columbia
Feature activation+0.597
also
Token also
Feature activation+0.000
backed
Token backed
Feature activation+0.000

INTERVAL 1.089 - 1.270
CONTAINS 0.002%

on
Token on
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
,
Token,
Feature activation+0.000
TTC
Token TTC
Feature activation+0.000
CEO
Token CEO
Feature activation+1.055
Andy
Token Andy
Feature activation+1.136
By
Token By
Feature activation+0.000
ford
Tokenford
Feature activation+0.000
conceded
Token conceded
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
signed
Token signed
Feature activation+0.000
with
Token with
Feature activation+0.000
Hamilton
Token Hamilton
Feature activation+1.201
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
add
Token add
Feature activation+0.000
another
Token another
Feature activation+0.000
the
Token the
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
minority
Token minority
Feature activation+1.765
government
Token government
Feature activation+1.227
in
Token in
Feature activation+0.000
B
Token B
Feature activation+1.227
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Pierre
TokenPierre
Feature activation+0.107
Trudeau
Token Trudeau
Feature activation+0.000
,
Token,
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.128
Prime
Token Prime
Feature activation+1.164
Minister
Token Minister
Feature activation+1.381
for
Token for
Feature activation+0.000
over
Token over
Feature activation+0.000
15
Token 15
Feature activation+0.000
years
Token years
Feature activation+0.000
of
Token of
Feature activation+0.000
view
Token view
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
With
TokenWith
Feature activation+1.241
regard
Token regard
Feature activation+0.000
to
Token to
Feature activation+0.000
submissions
Token submissions
Feature activation+0.000
that
Token that
Feature activation+0.000
AJ
Token AJ
Feature activation+0.000

INTERVAL 0.907 - 1.089
CONTAINS 0.002%

a
Token a
Feature activation+0.000
letter
Token letter
Feature activation+0.000
sent
Token sent
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
federal
Token federal
Feature activation+0.920
government
Token government
Feature activation+0.441
in
Token in
Feature activation+0.000
February
Token February
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
actions
Token actions
Feature activation+0.000
the
Token the
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
are
Token are
Feature activation+0.000
proposing
Token proposing
Feature activation+0.914
today
Token today
Feature activation+0.000
were
Token were
Feature activation+0.000
contained
Token contained
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
costs
Token costs
Feature activation+0.000
on
Token on
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
,
Token,
Feature activation+0.000
TTC
Token TTC
Feature activation+0.000
CEO
Token CEO
Feature activation+1.055
Andy
Token Andy
Feature activation+1.136
By
Token By
Feature activation+0.000
ford
Tokenford
Feature activation+0.000
conceded
Token conceded
Feature activation+0.000
that
Token that
Feature activation+0.000
and
Token and
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Story
TokenStory
Feature activation+0.943
continues
Token continues
Feature activation+0.000
below
Token below
Feature activation+0.000
advertisement
Token advertisement
Feature activation+0.035
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
huge
Token huge
Feature activation+0.000
profit
Token profit
Feature activation+0.000
while
Token while
Feature activation+0.000
British
Token British
Feature activation+1.040
Columb
Token Columb
Feature activation+0.002
ians
Tokenians
Feature activation+0.000
are
Token are
Feature activation+0.000
asked
Token asked
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.726 - 0.907
CONTAINS 0.004%

Bel
Token Bel
Feature activation+0.000
four
Tokenfour
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Article
TokenArticle
Feature activation+0.798
Continued
Token Continued
Feature activation+0.000
Below
Token Below
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Fred
TokenFred
Feature activation+0.000
,
Token,
Feature activation+0.000
now
Token now
Feature activation+0.000
regularly
Token regularly
Feature activation+0.000
fly
Token fly
Feature activation+0.000
into
Token into
Feature activation+0.000
Darwin
Token Darwin
Feature activation+0.731
and
Token and
Feature activation+0.000
nearby
Token nearby
Feature activation+0.000
Sho
Token Sho
Feature activation+0.000
al
Tokenal
Feature activation+0.000
Bay
Token Bay
Feature activation+0.000
has
Token has
Feature activation+0.000
renewed
Token renewed
Feature activation+0.000
calls
Token calls
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
province
Token province
Feature activation+0.727
to
Token to
Feature activation+0.000
examine
Token examine
Feature activation+0.000
executive
Token executive
Feature activation+0.000
compensation
Token compensation
Feature activation+0.000
at
Token at
Feature activation+0.000
8
Token 8
Feature activation+0.000
have
Token have
Feature activation+0.000
said
Token said
Feature activation+0.000
no
Token no
Feature activation+0.000
to
Token to
Feature activation+0.000
Site
Token Site
Feature activation+0.751
C
Token C
Feature activation+0.000
.
Token.
Feature activation+0.000
Any
Token Any
Feature activation+0.000
government
Token government
Feature activation+0.809
that
Token that
Feature activation+0.000
run
Tokenrun
Feature activation+0.000
,
Token,
Feature activation+0.000
government
Token government
Feature activation+0.092
-
Token-
Feature activation+0.000
funded
Tokenfunded
Feature activation+0.000
residential
Token residential
Feature activation+0.752
schools
Token schools
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

INTERVAL 0.544 - 0.726
CONTAINS 0.005%

cent
Token cent
Feature activation+0.000
supporting
Token supporting
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
Leader
Token Leader
Feature activation+0.789
Greg
Token Greg
Feature activation+0.000
Sel
Token Sel
Feature activation+0.713
inger
Tokeninger
Feature activation+0.000
and
Token and
Feature activation+0.000
12
Token 12
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
to
Token to
Feature activation+0.000
engage
Token engage
Feature activation+0.035
in
Token in
Feature activation+0.000
reconciliation
Token reconciliation
Feature activation+0.320
with
Token with
Feature activation+0.000
indigenous
Token indigenous
Feature activation+0.675
peoples
Token peoples
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
thought
Token thought
Feature activation+0.000
this
Token this
Feature activation+0.000
-
Token-
Feature activation+0.000
show
Tokenshow
Feature activation+0.000
host
Token host
Feature activation+0.000
at
Token at
Feature activation+0.000
Spice
Token Spice
Feature activation+0.000
Radio
Token Radio
Feature activation+0.674
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
Indo
Token Indo
Feature activation+0.000
-
Token-
Feature activation+0.000
Canadian
TokenCanadian
Feature activation+0.000
Yog
Token Yog
Feature activation+0.000
i
Tokeni
Feature activation+0.000
Bear
Token Bear
Feature activation+0.000
won
Token won
Feature activation+0.000
and
Token and
Feature activation+0.000
Maple
Token Maple
Feature activation+0.719
lost
Token lost
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Vaughan
Token Vaughan
Feature activation+0.457
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
premier
Token premier
Feature activation+1.320
of
Token of
Feature activation+0.000
British
Token British
Feature activation+1.607
Columbia
Token Columbia
Feature activation+0.597
also
Token also
Feature activation+0.000
backed
Token backed
Feature activation+0.000
the
Token the
Feature activation+0.000
call
Token call
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.363 - 0.544
CONTAINS 0.010%

Pes
Token Pes
Feature activation+0.000
at
Tokenat
Feature activation+0.000
uro
Tokenuro
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
MB
Token MB
Feature activation+0.436
TA
TokenTA
Feature activation+0.000
spokesman
Token spokesman
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
there
Token there
Feature activation+0.000
primary
Token primary
Feature activation+0.000
centre
Token centre
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Middle
Token Middle
Feature activation+0.000
Mississ
Token Mississ
Feature activation+0.416
ipp
Tokenipp
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
culture
Token culture
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
with
Token with
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
's
Token's
Feature activation+0.000
Te
Token Te
Feature activation+0.000
ck
Tokenck
Feature activation+0.000
Resources
Token Resources
Feature activation+0.480
Ltd
Token Ltd
Feature activation+0.052
T
Token T
Feature activation+0.000
ECK
TokenECK
Feature activation+0.000
b
Tokenb
Feature activation+0.000
.
Token.
Feature activation+0.000
proposes
Token proposes
Feature activation+0.609
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.161
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
terror
Tokenterror
Feature activation+0.530
law
Token law
Feature activation+0.070
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
give
Token give
Feature activation+0.000
the
Token the
Feature activation+0.000
radio
Token radio
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
opposition
Token opposition
Feature activation+0.493
,
Token,
Feature activation+0.000
meanwhile
Token meanwhile
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 0.181 - 0.363
CONTAINS 0.013%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
City
Token City
Feature activation+0.252
of
Token of
Feature activation+0.000
Vancouver
Token Vancouver
Feature activation+0.000
,
Token,
Feature activation+0.000
44
Token 44
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
backing
Token backing
Feature activation+0.000
of
Token of
Feature activation+0.000
Justin
Token Justin
Feature activation+0.305
Trudeau
Token Trudeau
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Liberals
Token Liberals
Feature activation+0.308
the
Token the
Feature activation+0.000
election
Token election
Feature activation+0.550
was
Token was
Feature activation+0.000
both
Token both
Feature activation+0.000
his
Token his
Feature activation+0.000
inexper
Token inexper
Feature activation+0.250
ience
Tokenience
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
sur
Token sur
Feature activation+0.016
m
Tokenm
Feature activation+0.000
flight
Token flight
Feature activation+0.000
in
Token in
Feature activation+0.000
Vancouver
Token Vancouver
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
CBC
TokenCBC
Feature activation+0.211
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
Tan
Token Tan
Feature activation+0.000
en
Tokenen
Feature activation+0.000
baum
Tokenbaum
Feature activation+0.000
and
Token and
Feature activation+0.000
ML
Token ML
Feature activation+0.263
SE
TokenSE
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
executive
Token executive
Feature activation+0.000

INTERVAL 0.000 - 0.181
CONTAINS 99.962%

current
Token current
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
of
Token of
Feature activation+0.000
Odd
Token Odd
Feature activation+0.000
Future
Token Future
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
one
Token one
Feature activation+0.000
point
Token point
Feature activation+0.000
on
Token on
Feature activation+0.000
June
Token June
Feature activation+0.000
1
Token 1
Feature activation+0.000
st
Tokenst
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
maybe
Token maybe
Feature activation+0.000
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
ists
Tokenists
Feature activation+0.000
planned
Token planned
Feature activation+0.000
on
Token on
Feature activation+0.000
blocking
Token blocking
Feature activation+0.000
the
Token the
Feature activation+0.000
intersection
Token intersection
Feature activation+0.000
until
Token until
Feature activation+0.000
sund
Token sund
Feature activation+0.000
own
Tokenown
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
primary
Token primary
Feature activation+0.000
states
Token states
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
into
Tokeninto
Feature activation+0.000
efforts
Token efforts
Feature activation+0.000
to
Token to
Feature activation+0.000
mobilize
Token mobilize
Feature activation+0.000
and
Token and
Feature activation+0.000
organize
Token organize
Feature activation+0.000
volunteers
Token volunteers
Feature activation+0.000
for
Token for
Feature activation+0.000
routines
Token routines
Feature activation+0.000
and
Token and
Feature activation+0.000
assessed
Token assessed
Feature activation+0.000
their
Token their
Feature activation+0.000
body
Token body
Feature activation+0.000
composition
Token composition
Feature activation+0.000
and
Token and
Feature activation+0.000
timing
Token timing
Feature activation+0.000
of
Token of
Feature activation+0.000
mel
Token mel
Feature activation+0.000
atonin
Tokenatonin
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 H0.2: (feature 16055)

TOP ACTIVATIONS
MAX = 1.210

them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
design
Token design
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
Cu
Token Cu
Feature activation+1.210
pert
Tokenpert
Feature activation+0.000
ino
Tokenino
Feature activation+0.000
headquarters
Token headquarters
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
#
Token#
Feature activation+0.000
4
Token4
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
The
Token The
Feature activation+0.000
Hal
Token Hal
Feature activation+0.000
Fin
Token Fin
Feature activation+1.142
ney
Tokenney
Feature activation+0.000
Story
Token Story
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hal
TokenHal
Feature activation+0.000
str
Token str
Feature activation+0.000
_
Token_
Feature activation+0.000
replace
Tokenreplace
Feature activation+0.000
(
Token(
Feature activation+0.000
'
Token '
Feature activation+0.000
Word
TokenWord
Feature activation+1.098
press
Tokenpress
Feature activation+0.000
',
Token',
Feature activation+0.000
'
Token '
Feature activation+0.000
Word
TokenWord
Feature activation+1.007
Press
TokenPress
Feature activation+0.000
-
Token-
Feature activation+0.000
1
Token1
Feature activation+0.000
SF
Token SF
Feature activation+0.000
)
Token)
Feature activation+0.000
at
Token at
Feature activation+0.000
Strike
Token Strike
Feature activation+1.077
force
Tokenforce
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
final
Token final
Feature activation+0.000
true
Token true
Feature activation+0.000
potential
Token potential
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
(
Token (
Feature activation+0.000
Form
TokenForm
Feature activation+1.071
ula
Tokenula
Feature activation+0.000
One
Token One
Feature activation+0.000
racing
Token racing
Feature activation+0.000
)
Token)
Feature activation+0.000
track
Token track
Feature activation+0.000
time
Tokentime
Feature activation+0.000
ride
Token ride
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
NASCAR
Token NASCAR
Feature activation+0.000
Sprint
Token Sprint
Feature activation+1.068
Cup
Token Cup
Feature activation+0.492
Series
Token Series
Feature activation+0.000
in
Token in
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
and
Token and
Feature activation+0.000
France
Token France
Feature activation+0.000
introduced
Token introduced
Feature activation+0.000
Monster
Token Monster
Feature activation+0.506
Energy
Token Energy
Feature activation+0.000
as
Token as
Feature activation+0.000
Sprint
Token Sprint
Feature activation+1.051
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
replacement
Token replacement
Feature activation+0.000
.
Token.
Feature activation+0.000
-
Token-
Feature activation+0.000
Man
TokenMan
Feature activation+0.000
"
Token"
Feature activation+0.000
Parker
Token Parker
Feature activation+0.000
's
Token's
Feature activation+0.000
Aunt
Token Aunt
Feature activation+1.013
May
Token May
Feature activation+0.000
has
Token has
Feature activation+0.000
played
Token played
Feature activation+0.000
a
Token a
Feature activation+0.000
huge
Token huge
Feature activation+0.000
'
Token '
Feature activation+0.000
Word
TokenWord
Feature activation+1.098
press
Tokenpress
Feature activation+0.000
',
Token',
Feature activation+0.000
'
Token '
Feature activation+0.000
Word
TokenWord
Feature activation+1.007
Press
TokenPress
Feature activation+0.000
',
Token',
Feature activation+0.000
$
Token $
Feature activation+0.000
text
Tokentext
Feature activation+0.000
);
Token );
Feature activation+0.000
,
Token,
Feature activation+0.000
writer
Token writer
Feature activation+0.000
of
Token of
Feature activation+0.000
Star
Token Star
Feature activation+0.000
Trek
Token Trek
Feature activation+0.000
Into
Token Into
Feature activation+0.989
Darkness
Token Darkness
Feature activation+0.000
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+0.000
co
Token co
Feature activation+0.000
-
Token-
Feature activation+0.000
it
Token it
Feature activation+0.000
with
Token with
Feature activation+0.000
another
Token another
Feature activation+0.000
convention
Token convention
Feature activation+0.000
.
Token.
Feature activation+0.000
Captain
Token Captain
Feature activation+0.948
America
Token America
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
period
Token period
Feature activation+0.000
piece
Token piece
Feature activation+0.000
statements
Token statements
Feature activation+0.000
made
Token made
Feature activation+0.000
by
Token by
Feature activation+0.000
UFC
Token UFC
Feature activation+0.000
President
Token President
Feature activation+0.000
Dana
Token Dana
Feature activation+0.940
White
Token White
Feature activation+0.000
reminded
Token reminded
Feature activation+0.000
New
Token New
Feature activation+0.000
ell
Tokenell
Feature activation+0.000
there
Token there
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
in
Token in
Feature activation+0.000
2009
Token 2009
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
Steve
Token Steve
Feature activation+0.940
Jobs
Token Jobs
Feature activation+0.798
tapped
Token tapped
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
design
Token design
Feature activation+0.000
ney
Tokenney
Feature activation+0.000
Story
Token Story
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hal
TokenHal
Feature activation+0.000
Fin
Token Fin
Feature activation+0.912
ney
Tokenney
Feature activation+0.000
,
Token,
Feature activation+0.000
perhaps
Token perhaps
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
have
Token have
Feature activation+0.000
teamed
Token teamed
Feature activation+0.015
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
downloadable
Token downloadable
Feature activation+0.902
content
Token content
Feature activation+0.000
packs
Token packs
Feature activation+0.000
to
Token to
Feature activation+0.000
Minecraft
Token Minecraft
Feature activation+0.000
for
Token for
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Samsung
TokenSamsung
Feature activation+0.000
announced
Token announced
Feature activation+0.053
the
Token the
Feature activation+0.000
Gear
Token Gear
Feature activation+0.894
VR
Token VR
Feature activation+0.000
in
Token in
Feature activation+0.000
September
Token September
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
,
Token,
Feature activation+0.000
William
Token William
Feature activation+0.831
Sh
Token Sh
Feature activation+0.000
at
Tokenat
Feature activation+0.000
ner
Tokenner
Feature activation+0.000
and
Token and
Feature activation+0.000
Leonard
Token Leonard
Feature activation+0.892
Nim
Token Nim
Feature activation+0.395
oy
Tokenoy
Feature activation+0.000
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Chelsea
TokenChelsea
Feature activation+0.000
-
Token -
Feature activation+0.000
New
Token New
Feature activation+0.000
Stamford
Token Stamford
Feature activation+0.887
Bridge
Token Bridge
Feature activation+0.000
(
Token (
Feature activation+0.000
due
Tokendue
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
UFC
Token UFC
Feature activation+0.000
for
Token for
Feature activation+0.000
The
Token The
Feature activation+0.000
Ultimate
Token Ultimate
Feature activation+0.870
Fighter
Token Fighter
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Stay
TokenStay
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
for
Token for
Feature activation+0.000
more
Token more
Feature activation+0.000
Bell
Token Bell
Feature activation+0.868
ator
Tokenator
Feature activation+0.000
news
Token news
Feature activation+0.000
and
Token and
Feature activation+0.000
updates
Token updates
Feature activation+0.000
.
Token.
Feature activation+0.000

Top DFA by src position
MAX = 1.624

Norman
Token Norman
Feature activation+0.033
Top resid features:
Foster
Token Foster
Feature activation+0.030
Top resid features:
started
Token started
Feature activation+0.027
Top resid features:
designing
Token designing
Feature activation+0.012
Top resid features:
for
Token for
Feature activation+0.026
Top resid features:
Apple
Token Apple
Feature activation+0.931
Top resid features:
in
Token in
Feature activation+0.037
Top resid features:
2009
Token 2009
Feature activation+0.029
Top resid features:
,
Token,
Feature activation+0.050
Top resid features:
when
Token when
Feature activation+0.035
Top resid features:
Steve
Token Steve
Feature activation+0.053
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
more
Token more
Feature activation+0.020
Top resid features:
epic
Token epic
Feature activation+0.040
Top resid features:
stories
Token stories
Feature activation+0.014
Top resid features:
in
Token in
Feature activation+0.024
Top resid features:
Bitcoin
Token Bitcoin
Feature activation+0.832
Top resid features:
âĢ
TokenâĢ
Feature activation+0.022
Top resid features:
Ļ
TokenĻ
Feature activation+0.015
Top resid features:
s
Tokens
Feature activation+0.031
Top resid features:
evolution
Token evolution
Feature activation+0.032
Top resid features:
.
Token.
Feature activation+0.036
Top resid features:
currently
Token currently
Feature activation+0.009
Top resid features:
active
Token active
Feature activation+0.004
Top resid features:
filter
Token filter
Feature activation+0.007
Top resid features:
is
Token is
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
WordPress
Token WordPress
Feature activation+1.411
Top resid features:
filter
Token filter
Feature activation+0.008
Top resid features:
âĢ
Token âĢ
Feature activation+0.017
Top resid features:
ĺ
Tokenĺ
Feature activation+0.013
Top resid features:
the
Tokenthe
Feature activation-0.001
Top resid features:
_
Token_
Feature activation+0.011
Top resid features:
aly
Tokenaly
Feature activation-0.001
Top resid features:
(
Token (
Feature activation+0.040
Top resid features:
28
Token28
Feature activation+0.010
Top resid features:
-
Token-
Feature activation+0.031
Top resid features:
16
Token16
Feature activation+0.012
Top resid features:
MMA
Token MMA
Feature activation+0.799
Top resid features:
,
Token,
Feature activation+0.040
Top resid features:
6
Token 6
Feature activation+0.027
Top resid features:
-
Token-
Feature activation+0.038
Top resid features:
1
Token1
Feature activation+0.019
Top resid features:
SF
Token SF
Feature activation+0.036
Top resid features:
Our
TokenOur
Feature activation+0.053
Top resid features:
mutual
Token mutual
Feature activation+0.023
Top resid features:
desire
Token desire
Feature activation+0.020
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
see
Token see
Feature activation+0.022
Top resid features:
Ferrari
Token Ferrari
Feature activation+0.942
Top resid features:
achieve
Token achieve
Feature activation+0.014
Top resid features:
its
Token its
Feature activation+0.023
Top resid features:
true
Token true
Feature activation-0.003
Top resid features:
potential
Token potential
Feature activation+0.008
Top resid features:
on
Token on
Feature activation+0.028
Top resid features:
-
Token-
Feature activation+0.057
Top resid features:
time
Tokentime
Feature activation+0.032
Top resid features:
ride
Token ride
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.076
Top resid features:
the
Token the
Feature activation+0.086
Top resid features:
NASCAR
Token NASCAR
Feature activation+1.624
Top resid features:
Sprint
Token Sprint
Feature activation+0.241
Top resid features:
Cup
Token Cup
Feature activation+0.000
Top resid features:
Series
Token Series
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
2015
Token 2015
Feature activation+0.000
Top resid features:
conference
Token conference
Feature activation+0.052
Top resid features:
in
Token in
Feature activation+0.032
Top resid features:
Las
Token Las
Feature activation+0.044
Top resid features:
Vegas
Token Vegas
Feature activation+0.054
Top resid features:
,
Token,
Feature activation+0.041
Top resid features:
NASCAR
Token NASCAR
Feature activation+1.514
Top resid features:
CEO
Token CEO
Feature activation+0.042
Top resid features:
and
Token and
Feature activation+0.051
Top resid features:
chairman
Token chairman
Feature activation+0.047
Top resid features:
Brian
Token Brian
Feature activation+0.013
Top resid features:
France
Token France
Feature activation+0.019
Top resid features:
#
Token #
Feature activation+0.041
Top resid features:
15
Token15
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.045
Top resid features:
Peter
Token Peter
Feature activation+0.032
Top resid features:
"
Token "
Feature activation+0.040
Top resid features:
Spider
TokenSpider
Feature activation+0.890
Top resid features:
-
Token-
Feature activation+0.041
Top resid features:
Man
TokenMan
Feature activation+0.044
Top resid features:
"
Token"
Feature activation+0.075
Top resid features:
Parker
Token Parker
Feature activation+0.079
Top resid features:
's
Token's
Feature activation+0.099
Top resid features:
currently
Token currently
Feature activation+0.008
Top resid features:
active
Token active
Feature activation+0.003
Top resid features:
filter
Token filter
Feature activation+0.007
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
WordPress
Token WordPress
Feature activation+1.381
Top resid features:
filter
Token filter
Feature activation+0.008
Top resid features:
âĢ
Token âĢ
Feature activation+0.015
Top resid features:
ĺ
Tokenĺ
Feature activation+0.013
Top resid features:
the
Tokenthe
Feature activation-0.002
Top resid features:
_
Token_
Feature activation+0.010
Top resid features:
of
Tokenof
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.039
Top resid features:
writer
Token writer
Feature activation+0.022
Top resid features:
of
Token of
Feature activation+0.033
Top resid features:
Star
Token Star
Feature activation+0.039
Top resid features:
Trek
Token Trek
Feature activation+1.301
Top resid features:
Into
Token Into
Feature activation+0.546
Top resid features:
Darkness
Token Darkness
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
and
Tokenand
Feature activation+0.000
Top resid features:
co
Token co
Feature activation+0.000
Top resid features:
hey
Token hey
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
one
Token one
Feature activation+0.022
Top resid features:
thing
Token thing
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
Marvel
Token Marvel
Feature activation+0.955
Top resid features:
Cinem
Token Cinem
Feature activation+0.066
Top resid features:
atic
Tokenatic
Feature activation-0.001
Top resid features:
Universe
Token Universe
Feature activation+0.022
Top resid features:
does
Token does
Feature activation+0.014
Top resid features:
well
Token well
Feature activation+0.025
Top resid features:
,
Token,
Feature activation+0.047
Top resid features:
recent
Token recent
Feature activation+0.025
Top resid features:
statements
Token statements
Feature activation+0.024
Top resid features:
made
Token made
Feature activation+0.020
Top resid features:
by
Token by
Feature activation+0.061
Top resid features:
UFC
Token UFC
Feature activation+1.200
Top resid features:
President
Token President
Feature activation+0.026
Top resid features:
Dana
Token Dana
Feature activation+0.504
Top resid features:
White
Token White
Feature activation+0.000
Top resid features:
reminded
Token reminded
Feature activation+0.000
Top resid features:
New
Token New
Feature activation+0.000
Top resid features:
Norman
Token Norman
Feature activation+0.012
Top resid features:
Foster
Token Foster
Feature activation+0.037
Top resid features:
started
Token started
Feature activation+0.033
Top resid features:
designing
Token designing
Feature activation+0.029
Top resid features:
for
Token for
Feature activation+0.031
Top resid features:
Apple
Token Apple
Feature activation+0.782
Top resid features:
in
Token in
Feature activation+0.051
Top resid features:
2009
Token 2009
Feature activation+0.042
Top resid features:
,
Token,
Feature activation+0.075
Top resid features:
when
Token when
Feature activation+0.061
Top resid features:
Steve
Token Steve
Feature activation+0.435
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
more
Token more
Feature activation+0.015
Top resid features:
epic
Token epic
Feature activation+0.032
Top resid features:
stories
Token stories
Feature activation+0.011
Top resid features:
in
Token in
Feature activation+0.018
Top resid features:
Bitcoin
Token Bitcoin
Feature activation+0.785
Top resid features:
âĢ
TokenâĢ
Feature activation+0.017
Top resid features:
Ļ
TokenĻ
Feature activation+0.011
Top resid features:
s
Tokens
Feature activation+0.024
Top resid features:
evolution
Token evolution
Feature activation+0.026
Top resid features:
.
Token.
Feature activation+0.026
Top resid features:
have
Token have
Feature activation+0.045
Top resid features:
teamed
Token teamed
Feature activation+0.025
Top resid features:
up
Token up
Feature activation+0.042
Top resid features:
to
Token to
Feature activation+0.051
Top resid features:
bring
Token bring
Feature activation+0.063
Top resid features:
downloadable
Token downloadable
Feature activation+0.597
Top resid features:
content
Token content
Feature activation+0.000
Top resid features:
packs
Token packs
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Minecraft
Token Minecraft
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
manufacturing
Token manufacturing
Feature activation+0.013
Top resid features:
facility
Token facility
Feature activation+0.040
Top resid features:
.
Token.
Feature activation+0.049
Top resid features:
Ċ
TokenĊ
Feature activation+0.052
Top resid features:
Ċ
TokenĊ
Feature activation+0.055
Top resid features:
Samsung
TokenSamsung
Feature activation+0.823
Top resid features:
announced
Token announced
Feature activation+0.048
Top resid features:
the
Token the
Feature activation+0.079
Top resid features:
Gear
Token Gear
Feature activation+0.538
Top resid features:
VR
Token VR
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
legacy
Token legacy
Feature activation+0.017
Top resid features:
of
Token of
Feature activation+0.026
Top resid features:
Star
Token Star
Feature activation+0.080
Top resid features:
Trek
Token Trek
Feature activation+1.122
Top resid features:
,
Token,
Feature activation+0.042
Top resid features:
so
Token so
Feature activation+0.033
Top resid features:
are
Token are
Feature activation+0.024
Top resid features:
the
Token the
Feature activation+0.048
Top resid features:
two
Token two
Feature activation+0.032
Top resid features:
60
Token 60
Feature activation+0.029
Top resid features:
,
Token,
Feature activation+0.050
Top resid features:
432
Token 432
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.068
Top resid features:
Ċ
TokenĊ
Feature activation+0.074
Top resid features:
Chelsea
TokenChelsea
Feature activation+1.010
Top resid features:
-
Token -
Feature activation+0.063
Top resid features:
New
Token New
Feature activation+0.057
Top resid features:
Stamford
Token Stamford
Feature activation+0.370
Top resid features:
Bridge
Token Bridge
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
when
Token when
Feature activation+0.050
Top resid features:
it
Token it
Feature activation+0.033
Top resid features:
partnered
Token partnered
Feature activation-0.062
Top resid features:
with
Token with
Feature activation+0.070
Top resid features:
the
Token the
Feature activation+0.086
Top resid features:
UFC
Token UFC
Feature activation+1.527
Top resid features:
for
Token for
Feature activation+0.078
Top resid features:
The
Token The
Feature activation+0.205
Top resid features:
Ultimate
Token Ultimate
Feature activation+0.224
Top resid features:
Fighter
Token Fighter
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.039
Top resid features:
Ċ
TokenĊ
Feature activation+0.043
Top resid features:
Stay
TokenStay
Feature activation+0.040
Top resid features:
tuned
Token tuned
Feature activation+0.030
Top resid features:
to
Token to
Feature activation+0.052
Top resid features:
MMA
Token MMA
Feature activation+0.860
Top resid features:
Week
TokenWeek
Feature activation-0.004
Top resid features:
ly
Tokenly
Feature activation+0.027
Top resid features:
.
Token.
Feature activation+0.077
Top resid features:
com
Tokencom
Feature activation+0.055
Top resid features:
for
Token for
Feature activation+0.074
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.13

Head 2: 0.29

Head 3: 0.12

Head 4: 0.04

Head 5: 0.04

Head 6: 0.04

Head 7: 0.04

Head 8: 0.07

Head 9: 0.08

Head 10: 0.07

Head 11: 0.04

Positive logits

contrace5.17

corrid5.10

resil4.64

sacrific4.64

gobl4.61

satell4.52

���4.41

advoc4.35

opio4.33

��極4.31

upgr4.26

helicop4.21

citiz4.18

mosqu4.05

cryst3.96

cumbers3.94

skelet3.89

agre3.80

torches3.78

metic3.78

Negative logits

RANT-3.85

tumblr-3.85

Fairfax-3.75

Dartmouth-3.68

enance-3.59

finding-3.48

Sheep-3.42

Portsmouth-3.40

Superintendent-3.38

ISC-3.35

Vermont-3.34

Borough-3.31

udic-3.31

FACE-3.30

anwhile-3.29

Upper-3.28

Hutchinson-3.28

Buckingham-3.27

Else-3.26

Seas-3.25

INTERVAL 1.089 - 1.210
CONTAINS 0.000%

str
Token str
Feature activation+0.000
_
Token_
Feature activation+0.000
replace
Tokenreplace
Feature activation+0.000
(
Token(
Feature activation+0.000
'
Token '
Feature activation+0.000
Word
TokenWord
Feature activation+1.098
press
Tokenpress
Feature activation+0.000
',
Token',
Feature activation+0.000
'
Token '
Feature activation+0.000
Word
TokenWord
Feature activation+1.007
Press
TokenPress
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
design
Token design
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
Cu
Token Cu
Feature activation+1.210
pert
Tokenpert
Feature activation+0.000
ino
Tokenino
Feature activation+0.000
headquarters
Token headquarters
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
#
Token#
Feature activation+0.000
4
Token4
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
The
Token The
Feature activation+0.000
Hal
Token Hal
Feature activation+0.000
Fin
Token Fin
Feature activation+1.142
ney
Tokenney
Feature activation+0.000
Story
Token Story
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hal
TokenHal
Feature activation+0.000

INTERVAL 0.968 - 1.089
CONTAINS 0.001%

-
Token-
Feature activation+0.000
Man
TokenMan
Feature activation+0.000
"
Token"
Feature activation+0.000
Parker
Token Parker
Feature activation+0.000
's
Token's
Feature activation+0.000
Aunt
Token Aunt
Feature activation+1.013
May
Token May
Feature activation+0.000
has
Token has
Feature activation+0.000
played
Token played
Feature activation+0.000
a
Token a
Feature activation+0.000
huge
Token huge
Feature activation+0.000
true
Token true
Feature activation+0.000
potential
Token potential
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
(
Token (
Feature activation+0.000
Form
TokenForm
Feature activation+1.071
ula
Tokenula
Feature activation+0.000
One
Token One
Feature activation+0.000
racing
Token racing
Feature activation+0.000
)
Token)
Feature activation+0.000
track
Token track
Feature activation+0.000
'
Token '
Feature activation+0.000
Word
TokenWord
Feature activation+1.098
press
Tokenpress
Feature activation+0.000
',
Token',
Feature activation+0.000
'
Token '
Feature activation+0.000
Word
TokenWord
Feature activation+1.007
Press
TokenPress
Feature activation+0.000
',
Token',
Feature activation+0.000
$
Token $
Feature activation+0.000
text
Tokentext
Feature activation+0.000
);
Token );
Feature activation+0.000
time
Tokentime
Feature activation+0.000
ride
Token ride
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
NASCAR
Token NASCAR
Feature activation+0.000
Sprint
Token Sprint
Feature activation+1.068
Cup
Token Cup
Feature activation+0.492
Series
Token Series
Feature activation+0.000
in
Token in
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
and
Token and
Feature activation+0.000
-
Token-
Feature activation+0.000
1
Token1
Feature activation+0.000
SF
Token SF
Feature activation+0.000
)
Token)
Feature activation+0.000
at
Token at
Feature activation+0.000
Strike
Token Strike
Feature activation+1.077
force
Tokenforce
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
final
Token final
Feature activation+0.000

INTERVAL 0.847 - 0.968
CONTAINS 0.001%

ney
Tokenney
Feature activation+0.000
Story
Token Story
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hal
TokenHal
Feature activation+0.000
Fin
Token Fin
Feature activation+0.912
ney
Tokenney
Feature activation+0.000
,
Token,
Feature activation+0.000
perhaps
Token perhaps
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
in
Token in
Feature activation+0.000
2009
Token 2009
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
Steve
Token Steve
Feature activation+0.940
Jobs
Token Jobs
Feature activation+0.798
tapped
Token tapped
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
design
Token design
Feature activation+0.000
it
Token it
Feature activation+0.000
with
Token with
Feature activation+0.000
another
Token another
Feature activation+0.000
convention
Token convention
Feature activation+0.000
.
Token.
Feature activation+0.000
Captain
Token Captain
Feature activation+0.948
America
Token America
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
period
Token period
Feature activation+0.000
piece
Token piece
Feature activation+0.000
statements
Token statements
Feature activation+0.000
made
Token made
Feature activation+0.000
by
Token by
Feature activation+0.000
UFC
Token UFC
Feature activation+0.000
President
Token President
Feature activation+0.000
Dana
Token Dana
Feature activation+0.940
White
Token White
Feature activation+0.000
reminded
Token reminded
Feature activation+0.000
New
Token New
Feature activation+0.000
ell
Tokenell
Feature activation+0.000
there
Token there
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
has
Token has
Feature activation+0.000
already
Token already
Feature activation+0.000
overt
Token overt
Feature activation+0.000
aken
Tokenaken
Feature activation+0.000
DS
Token DS
Feature activation+0.858
9
Token9
Feature activation+0.000
as
Token as
Feature activation+0.000
The
Token The
Feature activation+0.000
Future
Token Future
Feature activation+0.000
goes
Token goes
Feature activation+0.000

INTERVAL 0.726 - 0.847
CONTAINS 0.003%

Disney
Token Disney
Feature activation+0.000
,
Token,
Feature activation+0.000
Lucas
Token Lucas
Feature activation+0.401
film
Tokenfilm
Feature activation+0.051
and
Token and
Feature activation+0.000
Microsoft
Token Microsoft
Feature activation+0.780
have
Token have
Feature activation+0.000
teamed
Token teamed
Feature activation+0.015
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
yet
Token yet
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
crew
Token crew
Feature activation+0.773
chief
Token chief
Feature activation+0.000
in
Token in
Feature activation+0.000
place
Token place
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
in
Token in
Feature activation+0.000
2009
Token 2009
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
Steve
Token Steve
Feature activation+0.940
Jobs
Token Jobs
Feature activation+0.798
tapped
Token tapped
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
design
Token design
Feature activation+0.000
the
Token the
Feature activation+0.000
Back
Token Back
Feature activation+0.000
,
Token,
Feature activation+0.000
Star
Token Star
Feature activation+0.609
Wars
Token Wars
Feature activation+0.000
:
Token:
Feature activation+0.000
Return
Token Return
Feature activation+0.727
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Jedi
Token Jedi
Feature activation+0.115
;
Token;
Feature activation+0.000
Star
Token Star
Feature activation+0.540
ring
Token ring
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
Pokémon
Token Pokémon
Feature activation+0.000
.
Token.
Feature activation+0.000
Tap
Token Tap
Feature activation+0.809
and
Token and
Feature activation+0.000
hold
Token hold
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
Poké
Token Poké
Feature activation+0.000

INTERVAL 0.605 - 0.726
CONTAINS 0.004%

Android
Token Android
Feature activation+0.030
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
vehicle
Token vehicle
Feature activation+0.000
.
Token.
Feature activation+0.000
Google
Token Google
Feature activation+0.643
announced
Token announced
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
show
Token show
Feature activation+0.000
that
Token that
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
asset
Token asset
Feature activation+0.486
class
Token class
Feature activation+0.000
for
Token for
Feature activation+0.000
institutional
Token institutional
Feature activation+0.704
investors
Token investors
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
ch
Tokench
Feature activation+0.000
image
Token image
Feature activation+0.000
via
Token via
Feature activation+0.000
Coin
Token Coin
Feature activation+0.194
Desk
TokenDesk
Feature activation+0.675
archives
Token archives
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
hosting
Token hosting
Feature activation+0.000
the
Token the
Feature activation+0.000
Tom
TokenTom
Feature activation+0.000
Under
TokenUnder
Feature activation+0.000
Sea
TokenSea
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Offline
TokenOffline
Feature activation+0.721
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Activity
TokenActivity
Feature activation+0.000
:
Token:
Feature activation+0.000
126
Token 126
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Enterprise
Token Enterprise
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
deflect
Token deflect
Feature activation+0.718
or
Tokenor
Feature activation+0.000
array
Token array
Feature activation+0.000
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
these
Token these
Feature activation+0.000

INTERVAL 0.484 - 0.605
CONTAINS 0.004%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
fight
Token fight
Feature activation+0.323
with
Token with
Feature activation+0.000
Floyd
Token Floyd
Feature activation+0.491
Mayweather
Token Mayweather
Feature activation+0.000
and
Token and
Feature activation+0.000
Floyd
Token Floyd
Feature activation+0.604
wore
Token wore
Feature activation+0.000
him
Token him
Feature activation+0.000
Warren
TokenWarren
Feature activation+0.000
Buffett
Token Buffett
Feature activation+0.000
,
Token,
Feature activation+0.000
CEO
Token CEO
Feature activation+0.000
of
Token of
Feature activation+0.000
Berkshire
Token Berkshire
Feature activation+0.594
Hath
Token Hath
Feature activation+0.317
away
Tokenaway
Feature activation+0.000
,
Token,
Feature activation+0.000
addresses
Token addresses
Feature activation+0.000
The
Token The
Feature activation+0.000
comic
Token comic
Feature activation+0.532
giant
Token giant
Feature activation+0.074
-
Token -
Feature activation+0.000
means
Token means
Feature activation+0.000
that
Token that
Feature activation+0.000
Agents
Token Agents
Feature activation+0.528
of
Token of
Feature activation+0.000
SH
Token SH
Feature activation+0.000
IELD
TokenIELD
Feature activation+0.090
is
Token is
Feature activation+0.000
guaranteed
Token guaranteed
Feature activation+0.000
second
Token second
Feature activation+0.000
half
Token half
Feature activation+0.000
.
Token.
Feature activation+0.000
Indianapolis
Token Indianapolis
Feature activation+0.000
Colts
Token Colts
Feature activation+0.000
owner
Token owner
Feature activation+0.527
Jim
Token Jim
Feature activation+0.000
I
Token I
Feature activation+0.000
rs
Tokenrs
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
fore
Token fore
Feature activation+0.000
check
Tokencheck
Feature activation+0.000
er
Tokener
Feature activation+0.000
to
Token to
Feature activation+0.000
Brooks
Token Brooks
Feature activation+0.491
Or
Token Or
Feature activation+0.000
p
Tokenp
Feature activation+0.000
ik
Tokenik
Feature activation+0.000
in
Token in
Feature activation+0.000
front
Token front
Feature activation+0.000

INTERVAL 0.363 - 0.484
CONTAINS 0.011%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
very
Token very
Feature activation+0.000
own
Token own
Feature activation+0.000
iTunes
Token iTunes
Feature activation+0.478
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
to
Token to
Feature activation+0.000
continue
Token continue
Feature activation+0.000
working
Token working
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
crew
Token crew
Feature activation+0.415
chief
Token chief
Feature activation+0.000
role
Token role
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
crew
Token crew
Feature activation+0.000
chiefs
Token chiefs
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
NASCAR
Token NASCAR
Feature activation+0.000
Sprint
Token Sprint
Feature activation+0.430
Cup
Token Cup
Feature activation+0.000
garage
Token garage
Feature activation+0.000
,
Token,
Feature activation+0.000
F
Token F
Feature activation+0.000
enn
Tokenenn
Feature activation+0.000
the
Token the
Feature activation+0.000
short
Token short
Feature activation+0.000
-
Token-
Feature activation+0.000
lived
Tokenlived
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
Bout
Token Bout
Feature activation+0.390
ique
Tokenique
Feature activation+0.000
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
corner
Token corner
Feature activation+0.062
released
Token released
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
counselor
Token counselor
Feature activation+0.000
to
Token to
Feature activation+0.000
Bishop
Token Bishop
Feature activation+0.467
Part
Token Part
Feature activation+0.000
ridge
Tokenridge
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
called
Token called
Feature activation+0.000

INTERVAL 0.242 - 0.363
CONTAINS 0.018%

20
Token20
Feature activation+0.000
88
Token88
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Object
TokenObject
Feature activation+0.000
Class
Token Class
Feature activation+0.259
:
Token:
Feature activation+0.000
Safe
Token Safe
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Special
TokenSpecial
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
Las
Token Las
Feature activation+0.000
Vegas
Token Vegas
Feature activation+0.000
and
Token and
Feature activation+0.000
Clark
Token Clark
Feature activation+0.330
County
Token County
Feature activation+0.000
departments
Token departments
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
have
Token have
Feature activation+0.000
called
Token called
Feature activation+0.000
it
Token it
Feature activation+0.000
the
Token the
Feature activation+0.000
Samsung
Token Samsung
Feature activation+0.000
Galaxy
Token Galaxy
Feature activation+0.267
Shield
Token Shield
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
iPhone
TokeniPhone
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
enough
Token enough
Feature activation+0.000
that
Token that
Feature activation+0.000
Qu
Token Qu
Feature activation+0.299
ir
Tokenir
Feature activation+0.000
rell
Tokenrell
Feature activation+0.000
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
want
Token want
Feature activation+0.000
part
Token part
Feature activation+0.000
.
Token.
Feature activation+0.000
Brown
Token Brown
Feature activation+0.000
helped
Token helped
Feature activation+0.000
turn
Token turn
Feature activation+0.000
Lex
Token Lex
Feature activation+0.331
Luthor
Token Luthor
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
sill
Token sill
Feature activation+0.000
ier
Tokenier
Feature activation+0.000

INTERVAL 0.121 - 0.242
CONTAINS 0.033%

them
Token them
Feature activation+0.000
by
Token by
Feature activation+0.000
hand
Token hand
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Big
TokenBig
Feature activation+0.140
Pharma
Token Pharma
Feature activation+0.000
has
Token has
Feature activation+0.000
rem
Token rem
Feature activation+0.000
ade
Tokenade
Feature activation+0.000
their
Token their
Feature activation+0.000
experience
Token experience
Feature activation+0.000
for
Token for
Feature activation+0.000
mobile
Token mobile
Feature activation+0.000
browsers
Token browsers
Feature activation+0.000
on
Token on
Feature activation+0.000
Android
Token Android
Feature activation+0.155
and
Token and
Feature activation+0.000
iOS
Token iOS
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
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Meanwhile
TokenMeanwhile
Feature activation+0.000
,
Token,
Feature activation+0.000
environmental
Token environmental
Feature activation+0.208
and
Token and
Feature activation+0.000
animal
Token animal
Feature activation+0.726
rights
Token rights
Feature activation+0.000
organizations
Token organizations
Feature activation+0.000
such
Token such
Feature activation+0.000
run
Token run
Feature activation+0.000
the
Token the
Feature activation+0.000
expanding
Token expanding
Feature activation+0.000
bicycle
Token bicycle
Feature activation+0.000
-
Token-
Feature activation+0.000
sharing
Tokensharing
Feature activation+0.144
system
Token system
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
looking
Tokenlooking
Feature activation+0.000
,
Token,
Feature activation+0.000
muscle
Token muscle
Feature activation+0.000
-
Token-
Feature activation+0.000
bound
Tokenbound
Feature activation+0.000
superst
Token superst
Feature activation+0.179
ars
Tokenars
Feature activation+0.000
could
Token could
Feature activation+0.000
hold
Token hold
Feature activation+0.000
the
Token the
Feature activation+0.000
title
Token title
Feature activation+0.000

INTERVAL 0.000 - 0.121
CONTAINS 99.926%

his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
and
Token and
Feature activation+0.000
shot
Token shot
Feature activation+0.000
himself
Token himself
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Fake
TokenFake
Feature activation+0.000
news
Token news
Feature activation+0.000
has
Token has
Feature activation+0.000
she
Token she
Feature activation+0.000
had
Token had
Feature activation+0.000
an
Token an
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
exper
Tokenexper
Feature activation+0.000
ience
Tokenience
Feature activation+0.000
with
Token with
Feature activation+0.000
God
Token God
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
PC
Token PC
Feature activation+0.000
flight
Token flight
Feature activation+0.000
sim
Token sim
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
Ċ
TokenĊ
Feature activation+0.000
92
Token92
Feature activation+0.000
As
Token As
Feature activation+0.000
long
Token long
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.000
control
Token control
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
body
Token body
Feature activation+0.000
,
Token,
Feature activation+0.000
establishes
Token establishes
Feature activation+0.000
an
Token an
Feature activation+0.000
identification
Token identification
Feature activation+0.000
card
Token card
Feature activation+0.000
without
Token without
Feature activation+0.000
the
Token the
Feature activation+0.000
consent
Token consent
Feature activation+0.000
of
Token of
Feature activation+0.000
her
Token her
Feature activation+0.000
guardian
Token guardian
Feature activation+0.000
.
Token.
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 6 in H0.2: (feature 10165)

TOP ACTIVATIONS
MAX = 1.615

s
Tokens
Feature activation+0.000
classic
Token classic
Feature activation+0.075
origin
Token origin
Feature activation+0.287
story
Token story
Feature activation+0.000
with
Token with
Feature activation+0.000
Bruce
Token Bruce
Feature activation+1.615
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
parents
Token parents
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
The
Token The
Feature activation+0.000
Back
Token Back
Feature activation+0.123
,
Token,
Feature activation+0.000
Star
Token Star
Feature activation+0.978
Wars
Token Wars
Feature activation+0.031
:
Token:
Feature activation+0.000
Return
Token Return
Feature activation+1.536
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Jedi
Token Jedi
Feature activation+0.611
;
Token;
Feature activation+0.000
Star
Token Star
Feature activation+1.117
Star
Token Star
Feature activation+0.973
Wars
Token Wars
Feature activation+0.006
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.469
Empire
Token Empire
Feature activation+1.146
Strikes
Token Strikes
Feature activation+1.476
Back
Token Back
Feature activation+0.123
,
Token,
Feature activation+0.000
Star
Token Star
Feature activation+0.978
Wars
Token Wars
Feature activation+0.031
:
Token:
Feature activation+0.000
to
Token to
Feature activation+0.000
Harry
Token Harry
Feature activation+0.000
Potter
Token Potter
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Death
Token Death
Feature activation+1.472
ly
Tokenly
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
ows
Tokenows
Feature activation+0.000
part
Token part
Feature activation+0.000
I
Token I
Feature activation+0.000
gang
Token gang
Feature activation+0.000
wars
Token wars
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
Bat
Token Bat
Feature activation+1.444
girl
Tokengirl
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
complete
Token complete
Feature activation+0.000
isolation
Token isolation
Feature activation+0.000
ones
Tokenones
Feature activation+0.000
;
Token;
Feature activation+0.000
Star
Token Star
Feature activation+0.939
Wars
Token Wars
Feature activation+0.000
:
Token:
Feature activation+0.000
Revenge
Token Revenge
Feature activation+1.405
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Sith
Token Sith
Feature activation+0.306
,
Token,
Feature activation+0.000
Star
Token Star
Feature activation+0.973
âĢĵ
Token âĢĵ
Feature activation+0.000
to
Token to
Feature activation+0.000
deliver
Token deliver
Feature activation+0.369
what
Token what
Feature activation+0.000
M
Token M
Feature activation+0.000
ugg
Tokenugg
Feature activation+1.388
les
Tokenles
Feature activation+0.000
have
Token have
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
:
Token:
Feature activation+0.000
More
Token More
Feature activation+0.000
Part
Token Part
Feature activation+0.000
1
Token 1
Feature activation+0.000
and
Token and
Feature activation+0.000
Avengers
Token Avengers
Feature activation+0.260
:
Token:
Feature activation+0.000
Infinity
Token Infinity
Feature activation+1.371
War
Token War
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
Part
Token Part
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Star
TokenStar
Feature activation+0.552
Wars
Token Wars
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.164
Phantom
Token Phantom
Feature activation+1.362
Men
Token Men
Feature activation+0.000
ace
Tokenace
Feature activation+0.174
;
Token;
Feature activation+0.000
Star
Token Star
Feature activation+0.795
Wars
Token Wars
Feature activation+0.000
2018
Token 2018
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
Avengers
Token Avengers
Feature activation+0.000
:
Token:
Feature activation+0.000
Infinity
Token Infinity
Feature activation+1.230
War
Token War
Feature activation+0.000
Part
Token Part
Feature activation+0.000
II
Token II
Feature activation+0.000
opening
Token opening
Feature activation+0.000
in
Token in
Feature activation+0.000
two
Token two
Feature activation+0.000
things
Token things
Feature activation+0.000
missing
Token missing
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
DS
Token DS
Feature activation+1.224
9
Token9
Feature activation+0.000
universe
Token universe
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
one
Token one
Feature activation+0.000
that
Token that
Feature activation+0.000
Files
TokenFiles
Feature activation+0.000
,
Token,
Feature activation+0.000
end
Token end
Feature activation+0.000
up
Token up
Feature activation+0.000
with
Token with
Feature activation+0.000
Captain
Token Captain
Feature activation+1.193
Marvel
Token Marvel
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Our
TokenOur
Feature activation+0.000
es
Tokenes
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
apply
Token apply
Feature activation+0.000
.
Token.
Feature activation+0.000
Peter
Token Peter
Feature activation+1.165
Parker
Token Parker
Feature activation+0.326
's
Token's
Feature activation+0.000
presence
Token presence
Feature activation+0.000
in
Token in
Feature activation+0.000
Infinity
Token Infinity
Feature activation+0.713
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
upcoming
Token upcoming
Feature activation+0.000
Avengers
Token Avengers
Feature activation+0.000
:
Token:
Feature activation+0.000
Infinity
Token Infinity
Feature activation+1.164
War
Token War
Feature activation+0.000
films
Token films
Feature activation+0.000
once
Token once
Feature activation+0.000
more
Token more
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
Star
Token Star
Feature activation+0.973
Wars
Token Wars
Feature activation+0.006
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.469
Empire
Token Empire
Feature activation+1.146
Strikes
Token Strikes
Feature activation+1.476
Back
Token Back
Feature activation+0.123
,
Token,
Feature activation+0.000
Star
Token Star
Feature activation+0.978
Wars
Token Wars
Feature activation+0.031
ace
Tokenace
Feature activation+0.174
;
Token;
Feature activation+0.000
Star
Token Star
Feature activation+0.795
Wars
Token Wars
Feature activation+0.000
:
Token:
Feature activation+0.000
Attack
Token Attack
Feature activation+1.145
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Cl
Token Cl
Feature activation+0.000
ones
Tokenones
Feature activation+0.000
;
Token;
Feature activation+0.000
Star
Token Star
Feature activation+1.117
Wars
Token Wars
Feature activation+0.059
Rebels
Token Rebels
Feature activation+1.074
)
Token)
Feature activation+0.000
Ray
Token Ray
Feature activation+1.064
Park
Token Park
Feature activation+1.144
:
Token:
Feature activation+0.000
Darth
Token Darth
Feature activation+1.020
Maul
Token Maul
Feature activation+0.533
(
Token (
Feature activation+0.000
Star
TokenStar
Feature activation+1.035
are
Token are
Feature activation+0.000
hel
Token hel
Feature activation+0.109
ming
Tokenming
Feature activation+0.000
Avengers
Token Avengers
Feature activation+0.041
:
Token:
Feature activation+0.000
Infinity
Token Infinity
Feature activation+1.132
War
Token War
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
Part
Token Part
Feature activation+0.000
1
Token 1
Feature activation+0.000
and
Token and
Feature activation+0.000
Return
Token Return
Feature activation+1.536
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Jedi
Token Jedi
Feature activation+0.611
;
Token;
Feature activation+0.000
Star
Token Star
Feature activation+1.117
Wars
Token Wars
Feature activation+0.059
Rebels
Token Rebels
Feature activation+1.074
)
Token)
Feature activation+0.000
Ray
Token Ray
Feature activation+1.064
Park
Token Park
Feature activation+1.144
Scores
Token Scores
Feature activation+0.000
Arcade
Token Arcade
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Legend
Token Legend
Feature activation+1.115
of
Token of
Feature activation+0.000
Zelda
Token Zelda
Feature activation+0.000
isn
Token isn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

Top DFA by src position
MAX = 1.405

was
Token was
Feature activation+0.026
Top resid features:
even
Token even
Feature activation+0.018
Top resid features:
alluded
Token alluded
Feature activation+0.018
Top resid features:
to
Token to
Feature activation+0.018
Top resid features:
in
Token in
Feature activation+0.018
Top resid features:
Batman
Token Batman
Feature activation+0.838
Top resid features:
âĢ
TokenâĢ
Feature activation+0.034
Top resid features:
Ļ
TokenĻ
Feature activation+0.017
Top resid features:
s
Tokens
Feature activation+0.017
Top resid features:
classic
Token classic
Feature activation+0.034
Top resid features:
origin
Token origin
Feature activation+0.031
Top resid features:
Back
Token Back
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
Star
Token Star
Feature activation+0.050
Top resid features:
Wars
Token Wars
Feature activation+0.254
Top resid features:
:
Token:
Feature activation+0.080
Top resid features:
Return
Token Return
Feature activation+0.447
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Jedi
Token Jedi
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.000
Top resid features:
Star
Token Star
Feature activation+0.000
Top resid features:
Star
Token Star
Feature activation+0.046
Top resid features:
Wars
Token Wars
Feature activation+0.247
Top resid features:
:
Token:
Feature activation+0.033
Top resid features:
The
Token The
Feature activation+0.049
Top resid features:
Empire
Token Empire
Feature activation+0.216
Top resid features:
Strikes
Token Strikes
Feature activation+0.415
Top resid features:
Back
Token Back
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Star
Token Star
Feature activation+0.000
Top resid features:
Wars
Token Wars
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
wanted
Token wanted
Feature activation+0.017
Top resid features:
something
Token something
Feature activation+0.017
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
attach
Token attach
Feature activation+0.028
Top resid features:
to
Token to
Feature activation+0.025
Top resid features:
Harry
Token Harry
Feature activation+1.236
Top resid features:
Potter
Token Potter
Feature activation+0.656
Top resid features:
and
Token and
Feature activation+0.048
Top resid features:
the
Token the
Feature activation+0.051
Top resid features:
Death
Token Death
Feature activation+0.228
Top resid features:
ly
Tokenly
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.017
Top resid features:
hundred
Token hundred
Feature activation+0.018
Top resid features:
days
Token days
Feature activation+0.016
Top resid features:
without
Token without
Feature activation+0.016
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
Batman
Token Batman
Feature activation+0.860
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
police
Token police
Feature activation+0.046
Top resid features:
starting
Token starting
Feature activation+0.021
Top resid features:
gang
Token gang
Feature activation+0.059
Top resid features:
wars
Token wars
Feature activation+0.055
Top resid features:
ones
Tokenones
Feature activation+0.020
Top resid features:
;
Token;
Feature activation+0.047
Top resid features:
Star
Token Star
Feature activation+0.075
Top resid features:
Wars
Token Wars
Feature activation+0.220
Top resid features:
:
Token:
Feature activation+0.069
Top resid features:
Revenge
Token Revenge
Feature activation+0.409
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Sith
Token Sith
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Star
Token Star
Feature activation+0.000
Top resid features:
Twitter
Token Twitter
Feature activation+0.013
Top resid features:
asking
Token asking
Feature activation+0.006
Top resid features:
questions
Token questions
Feature activation+0.005
Top resid features:
like
Token like
Feature activation+0.008
Top resid features:
how
Token how
Feature activation+0.007
Top resid features:
Hogwarts
Token Hogwarts
Feature activation+0.528
Top resid features:
students
Token students
Feature activation+0.015
Top resid features:
deal
Token deal
Feature activation+0.007
Top resid features:
with
Token with
Feature activation+0.011
Top resid features:
their
Token their
Feature activation+0.007
Top resid features:
period
Token period
Feature activation+0.010
Top resid features:
War
Token War
Feature activation+0.030
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.034
Top resid features:
Part
Token Part
Feature activation+0.012
Top resid features:
1
Token 1
Feature activation+0.033
Top resid features:
and
Token and
Feature activation+0.030
Top resid features:
Avengers
Token Avengers
Feature activation+0.887
Top resid features:
:
Token:
Feature activation+0.040
Top resid features:
Infinity
Token Infinity
Feature activation+0.247
Top resid features:
War
Token War
Feature activation+0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
Part
Token Part
Feature activation+0.000
Top resid features:
Wars
Token Wars
Feature activation+0.194
Top resid features:
:
Token:
Feature activation+0.026
Top resid features:
Return
Token Return
Feature activation+0.017
Top resid features:
of
Token of
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
Jedi
Token Jedi
Feature activation+0.440
Top resid features:
;
Token;
Feature activation+0.026
Top resid features:
Star
Token Star
Feature activation+0.032
Top resid features:
Wars
Token Wars
Feature activation+0.234
Top resid features:
Rebels
Token Rebels
Feature activation+0.095
Top resid features:
)
Token)
Feature activation+0.016
Top resid features:
4
Token 4
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
2018
Token 2018
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
with
Token with
Feature activation+0.031
Top resid features:
Avengers
Token Avengers
Feature activation+0.985
Top resid features:
:
Token:
Feature activation+0.044
Top resid features:
Infinity
Token Infinity
Feature activation+0.244
Top resid features:
War
Token War
Feature activation+0.000
Top resid features:
Part
Token Part
Feature activation+0.000
Top resid features:
II
Token II
Feature activation+0.000
Top resid features:
zoom
Token zoom
Feature activation+0.027
Top resid features:
ed
Tokened
Feature activation+0.011
Top resid features:
right
Token right
Feature activation+0.010
Top resid features:
past
Token past
Feature activation+0.015
Top resid features:
Star
Token Star
Feature activation+0.028
Top resid features:
Trek
Token Trek
Feature activation+1.405
Top resid features:
's
Token's
Feature activation+0.015
Top resid features:
version
Token version
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
24
Token 24
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
best
Token best
Feature activation+0.010
Top resid features:
blend
Token blend
Feature activation+0.015
Top resid features:
with
Token with
Feature activation+0.011
Top resid features:
Captain
Token Captain
Feature activation+0.108
Top resid features:
Marvel
Token Marvel
Feature activation+1.005
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+0.008
Top resid features:
story
Token story
Feature activation+0.023
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.026
Top resid features:
and
Token and
Feature activation+0.018
Top resid features:
others
Token others
Feature activation+0.005
Top resid features:
from
Token from
Feature activation+0.012
Top resid features:
appearing
Token appearing
Feature activation+0.016
Top resid features:
in
Token in
Feature activation+0.008
Top resid features:
Marvel
Token Marvel
Feature activation+0.588
Top resid features:
's
Token's
Feature activation+0.016
Top resid features:
well
Token well
Feature activation+0.007
Top resid features:
-
Token-
Feature activation+0.016
Top resid features:
received
Tokenreceived
Feature activation+0.011
Top resid features:
silver
Token silver
Feature activation+0.020
Top resid features:
happening
Token happening
Feature activation+0.017
Top resid features:
in
Token in
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
two
Token two
Feature activation+0.008
Top resid features:
upcoming
Token upcoming
Feature activation+0.034
Top resid features:
Avengers
Token Avengers
Feature activation+1.134
Top resid features:
:
Token:
Feature activation+0.044
Top resid features:
Infinity
Token Infinity
Feature activation+0.333
Top resid features:
War
Token War
Feature activation+0.000
Top resid features:
films
Token films
Feature activation+0.000
Top resid features:
once
Token once
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
Sith
Token Sith
Feature activation+0.111
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
Star
Token Star
Feature activation+0.034
Top resid features:
Wars
Token Wars
Feature activation+0.256
Top resid features:
:
Token:
Feature activation+0.045
Top resid features:
The
Token The
Feature activation+0.077
Top resid features:
Empire
Token Empire
Feature activation+0.189
Top resid features:
Strikes
Token Strikes
Feature activation+0.000
Top resid features:
Back
Token Back
Feature activation+0.000
Top resid features:
Phantom
Token Phantom
Feature activation+0.041
Top resid features:
Men
Token Men
Feature activation+0.062
Top resid features:
ace
Tokenace
Feature activation+0.009
Top resid features:
;
Token;
Feature activation+0.036
Top resid features:
Star
Token Star
Feature activation+0.070
Top resid features:
Wars
Token Wars
Feature activation+0.307
Top resid features:
:
Token:
Feature activation+0.059
Top resid features:
Attack
Token Attack
Feature activation+0.112
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Cl
Token Cl
Feature activation+0.000
Top resid features:
Wars
Token Wars
Feature activation+0.120
Top resid features:
:
Token:
Feature activation+0.020
Top resid features:
Return
Token Return
Feature activation+0.020
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
Jedi
Token Jedi
Feature activation+0.387
Top resid features:
;
Token;
Feature activation+0.024
Top resid features:
Star
Token Star
Feature activation+0.071
Top resid features:
Wars
Token Wars
Feature activation+0.165
Top resid features:
Rebels
Token Rebels
Feature activation+0.074
Top resid features:
)
Token)
Feature activation+0.017
Top resid features:
Ļ
TokenĻ
Feature activation+0.019
Top resid features:
s
Tokens
Feature activation+0.017
Top resid features:
are
Token are
Feature activation+0.028
Top resid features:
hel
Token hel
Feature activation+0.056
Top resid features:
ming
Tokenming
Feature activation+0.017
Top resid features:
Avengers
Token Avengers
Feature activation+1.272
Top resid features:
:
Token:
Feature activation+0.049
Top resid features:
Infinity
Token Infinity
Feature activation+0.332
Top resid features:
War
Token War
Feature activation+0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
Part
Token Part
Feature activation+0.000
Top resid features:
Wars
Token Wars
Feature activation+0.231
Top resid features:
:
Token:
Feature activation+0.027
Top resid features:
Return
Token Return
Feature activation+0.039
Top resid features:
of
Token of
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
Jedi
Token Jedi
Feature activation+0.373
Top resid features:
;
Token;
Feature activation+0.061
Top resid features:
Star
Token Star
Feature activation+0.132
Top resid features:
Wars
Token Wars
Feature activation+0.000
Top resid features:
Rebels
Token Rebels
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
classic
Token classic
Feature activation+0.015
Top resid features:
drawings
Token drawings
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
Link
Token Link
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
Zelda
Token Zelda
Feature activation+0.517
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
and
Token and
Feature activation+0.012
Top resid features:
Gan
Token Gan
Feature activation+0.020
Top resid features:
on
Tokenon
Feature activation+0.005
Top resid features:
around
Token around
Feature activation+0.008
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.12

Head 2: 0.28

Head 3: 0.11

Head 4: 0.05

Head 5: 0.04

Head 6: 0.07

Head 7: 0.04

Head 8: 0.05

Head 9: 0.10

Head 10: 0.06

Head 11: 0.05

Positive logits

isphere4.13

3.85

corrid3.72

3.68

metic3.58

costumes3.52

���3.46

querque3.42

sequels3.39

staples3.35

3.30

upgr3.28

entreprene3.24

nodd3.23

iHUD3.21

adaptations3.21

conduc3.20

3.14

ファ3.10

manga3.06

Negative logits

doors-3.49

between-3.48

Drug-3.46

laus-3.38

enance-3.31

SPONSORED-3.23

nown-3.21

DEP-3.20

imity-3.17

ebin-3.10

yrinth-3.08

Dartmouth-3.07

Population-3.06

Fairfax-3.05

INESS-3.05

trak-3.05

riott-3.04

EStreamFrame-3.01

rg-3.00

erred-2.96

INTERVAL 1.454 - 1.615
CONTAINS 0.000%

to
Token to
Feature activation+0.000
Harry
Token Harry
Feature activation+0.000
Potter
Token Potter
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Death
Token Death
Feature activation+1.472
ly
Tokenly
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
ows
Tokenows
Feature activation+0.000
part
Token part
Feature activation+0.000
I
Token I
Feature activation+0.000
Star
Token Star
Feature activation+0.973
Wars
Token Wars
Feature activation+0.006
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.469
Empire
Token Empire
Feature activation+1.146
Strikes
Token Strikes
Feature activation+1.476
Back
Token Back
Feature activation+0.123
,
Token,
Feature activation+0.000
Star
Token Star
Feature activation+0.978
Wars
Token Wars
Feature activation+0.031
:
Token:
Feature activation+0.000
Back
Token Back
Feature activation+0.123
,
Token,
Feature activation+0.000
Star
Token Star
Feature activation+0.978
Wars
Token Wars
Feature activation+0.031
:
Token:
Feature activation+0.000
Return
Token Return
Feature activation+1.536
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Jedi
Token Jedi
Feature activation+0.611
;
Token;
Feature activation+0.000
Star
Token Star
Feature activation+1.117
s
Tokens
Feature activation+0.000
classic
Token classic
Feature activation+0.075
origin
Token origin
Feature activation+0.287
story
Token story
Feature activation+0.000
with
Token with
Feature activation+0.000
Bruce
Token Bruce
Feature activation+1.615
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
parents
Token parents
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
The
Token The
Feature activation+0.000

INTERVAL 1.292 - 1.454
CONTAINS 0.001%

âĢĵ
Token âĢĵ
Feature activation+0.000
to
Token to
Feature activation+0.000
deliver
Token deliver
Feature activation+0.369
what
Token what
Feature activation+0.000
M
Token M
Feature activation+0.000
ugg
Tokenugg
Feature activation+1.388
les
Tokenles
Feature activation+0.000
have
Token have
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
:
Token:
Feature activation+0.000
More
Token More
Feature activation+0.000
(
Token (
Feature activation+0.000
Star
TokenStar
Feature activation+0.552
Wars
Token Wars
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.164
Phantom
Token Phantom
Feature activation+1.362
Men
Token Men
Feature activation+0.000
ace
Tokenace
Feature activation+0.174
;
Token;
Feature activation+0.000
Star
Token Star
Feature activation+0.795
Wars
Token Wars
Feature activation+0.000
ones
Tokenones
Feature activation+0.000
;
Token;
Feature activation+0.000
Star
Token Star
Feature activation+0.939
Wars
Token Wars
Feature activation+0.000
:
Token:
Feature activation+0.000
Revenge
Token Revenge
Feature activation+1.405
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Sith
Token Sith
Feature activation+0.306
,
Token,
Feature activation+0.000
Star
Token Star
Feature activation+0.973
gang
Token gang
Feature activation+0.000
wars
Token wars
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
Bat
Token Bat
Feature activation+1.444
girl
Tokengirl
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
complete
Token complete
Feature activation+0.000
isolation
Token isolation
Feature activation+0.000
Part
Token Part
Feature activation+0.000
1
Token 1
Feature activation+0.000
and
Token and
Feature activation+0.000
Avengers
Token Avengers
Feature activation+0.260
:
Token:
Feature activation+0.000
Infinity
Token Infinity
Feature activation+1.371
War
Token War
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
Part
Token Part
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.131 - 1.292
CONTAINS 0.001%

Files
TokenFiles
Feature activation+0.000
,
Token,
Feature activation+0.000
end
Token end
Feature activation+0.000
up
Token up
Feature activation+0.000
with
Token with
Feature activation+0.000
Captain
Token Captain
Feature activation+1.193
Marvel
Token Marvel
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Our
TokenOur
Feature activation+0.000
2018
Token 2018
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
Avengers
Token Avengers
Feature activation+0.000
:
Token:
Feature activation+0.000
Infinity
Token Infinity
Feature activation+1.230
War
Token War
Feature activation+0.000
Part
Token Part
Feature activation+0.000
II
Token II
Feature activation+0.000
opening
Token opening
Feature activation+0.000
in
Token in
Feature activation+0.000
ace
Tokenace
Feature activation+0.174
;
Token;
Feature activation+0.000
Star
Token Star
Feature activation+0.795
Wars
Token Wars
Feature activation+0.000
:
Token:
Feature activation+0.000
Attack
Token Attack
Feature activation+1.145
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Cl
Token Cl
Feature activation+0.000
ones
Tokenones
Feature activation+0.000
;
Token;
Feature activation+0.000
es
Tokenes
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
apply
Token apply
Feature activation+0.000
.
Token.
Feature activation+0.000
Peter
Token Peter
Feature activation+1.165
Parker
Token Parker
Feature activation+0.326
's
Token's
Feature activation+0.000
presence
Token presence
Feature activation+0.000
in
Token in
Feature activation+0.000
Infinity
Token Infinity
Feature activation+0.713
Star
Token Star
Feature activation+1.117
Wars
Token Wars
Feature activation+0.059
Rebels
Token Rebels
Feature activation+1.074
)
Token)
Feature activation+0.000
Ray
Token Ray
Feature activation+1.064
Park
Token Park
Feature activation+1.144
:
Token:
Feature activation+0.000
Darth
Token Darth
Feature activation+1.020
Maul
Token Maul
Feature activation+0.533
(
Token (
Feature activation+0.000
Star
TokenStar
Feature activation+1.035

INTERVAL 0.969 - 1.131
CONTAINS 0.001%

far
Token far
Feature activation+0.000
more
Token more
Feature activation+0.000
to
Token to
Feature activation+0.000
offer
Token offer
Feature activation+0.000
the
Token the
Feature activation+0.000
Peter
Token Peter
Feature activation+1.097
Jackson
Token Jackson
Feature activation+0.000
and
Token and
Feature activation+0.000
J
Token J
Feature activation+0.369
.
Token.
Feature activation+0.000
R
TokenR
Feature activation+0.000
Scores
Token Scores
Feature activation+0.000
Arcade
Token Arcade
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Legend
Token Legend
Feature activation+1.115
of
Token of
Feature activation+0.000
Zelda
Token Zelda
Feature activation+0.000
isn
Token isn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
raise
Token raise
Feature activation+0.000
money
Token money
Feature activation+0.000
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
keep
Token keep
Feature activation+0.000
Aunt
Token Aunt
Feature activation+1.054
May
Token May
Feature activation+0.000
from
Token from
Feature activation+0.000
being
Token being
Feature activation+0.000
ev
Token ev
Feature activation+0.000
icted
Tokenicted
Feature activation+0.000
Return
Token Return
Feature activation+1.536
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Jedi
Token Jedi
Feature activation+0.611
;
Token;
Feature activation+0.000
Star
Token Star
Feature activation+1.117
Wars
Token Wars
Feature activation+0.059
Rebels
Token Rebels
Feature activation+1.074
)
Token)
Feature activation+0.000
Ray
Token Ray
Feature activation+1.064
Park
Token Park
Feature activation+1.144
;
Token;
Feature activation+0.000
Star
Token Star
Feature activation+1.117
Wars
Token Wars
Feature activation+0.059
Rebels
Token Rebels
Feature activation+1.074
)
Token)
Feature activation+0.000
Ray
Token Ray
Feature activation+1.064
Park
Token Park
Feature activation+1.144
:
Token:
Feature activation+0.000
Darth
Token Darth
Feature activation+1.020
Maul
Token Maul
Feature activation+0.533
(
Token (
Feature activation+0.000

INTERVAL 0.808 - 0.969
CONTAINS 0.001%

land
Token land
Feature activation+0.000
of
Token of
Feature activation+0.000
Wak
Token Wak
Feature activation+0.699
anda
Tokenanda
Feature activation+0.521
.
Token.
Feature activation+0.000
Captain
Token Captain
Feature activation+0.853
Britain
Token Britain
Feature activation+0.000
could
Token could
Feature activation+0.000
take
Token take
Feature activation+0.000
movie
Token movie
Feature activation+0.000
goers
Tokengoers
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
parents
Token parents
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
The
Token The
Feature activation+0.000
Mask
Token Mask
Feature activation+0.867
of
Token of
Feature activation+0.000
Z
Token Z
Feature activation+0.000
or
Tokenor
Feature activation+0.000
ro
Tokenro
Feature activation+0.026
on
Token on
Feature activation+0.000
Man
TokenMan
Feature activation+0.000
appeared
Token appeared
Feature activation+0.023
briefly
Token briefly
Feature activation+0.000
.
Token.
Feature activation+0.000
Disney
Token Disney
Feature activation+0.173
Infinity
Token Infinity
Feature activation+0.813
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
film
Token film
Feature activation+0.084
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Cl
Token Cl
Feature activation+0.000
ones
Tokenones
Feature activation+0.000
;
Token;
Feature activation+0.000
Star
Token Star
Feature activation+0.939
Wars
Token Wars
Feature activation+0.000
:
Token:
Feature activation+0.000
Revenge
Token Revenge
Feature activation+1.405
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
for
Token for
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Sm
Token Sm
Feature activation+0.953
ack
Tokenack
Feature activation+0.000
Down
TokenDown
Feature activation+0.000
,
Token,
Feature activation+0.000
setting
Token setting
Feature activation+0.000
up
Token up
Feature activation+0.000

INTERVAL 0.646 - 0.808
CONTAINS 0.003%

Sp
Token Sp
Feature activation+0.576
ide
Tokenide
Feature activation+0.000
y
Tokeny
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
X
Token X
Feature activation+0.783
-
Token-
Feature activation+0.000
Men
TokenMen
Feature activation+0.000
and
Token and
Feature activation+0.000
others
Token others
Feature activation+0.000
from
Token from
Feature activation+0.000
Ultron
Token Ultron
Feature activation+0.000
?
Token?
Feature activation+0.000
Email
Token Email
Feature activation+0.000
arts
Token arts
Feature activation+0.000
correspondent
Token correspondent
Feature activation+0.000
Emma
Token Emma
Feature activation+0.708
Knights
Token Knights
Feature activation+0.000
at
Token at
Feature activation+0.000
em
Token em
Feature activation+0.000
ma
Tokenma
Feature activation+0.000
.
Token.
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
rest
Token rest
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
DC
Token DC
Feature activation+0.696
pant
Token pant
Feature activation+0.374
heon
Tokenheon
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
re
Token re
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
ocean
Token ocean
Feature activation+0.000
planet
Token planet
Feature activation+0.000
of
Token of
Feature activation+0.000
Ah
Token Ah
Feature activation+0.683
ch
Tokench
Feature activation+0.000
-
Token-
Feature activation+0.000
To
TokenTo
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
person
Token person
Feature activation+0.000
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
Aunt
Token Aunt
Feature activation+0.662
May
Token May
Feature activation+0.000
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
husband
Token husband
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.485 - 0.646
CONTAINS 0.005%

:
Token:
Feature activation+0.000
Spider
Token Spider
Feature activation+0.000
-
Token-
Feature activation+0.000
Man
TokenMan
Feature activation+0.000
.
Token.
Feature activation+0.000
Peter
Token Peter
Feature activation+0.528
P
Token P
Feature activation+0.000
aker
Tokenaker
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Return
Token Return
Feature activation+0.768
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Jedi
Token Jedi
Feature activation+0.000
;
Token;
Feature activation+0.000
Star
Token Star
Feature activation+0.501
Wars
Token Wars
Feature activation+0.000
Rebels
Token Rebels
Feature activation+0.588
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ent
Token ent
Feature activation+0.000
hr
Tokenhr
Feature activation+0.000
alling
Tokenalling
Feature activation+0.000
return
Token return
Feature activation+0.000
to
Token to
Feature activation+0.000
Middle
Token Middle
Feature activation+0.555
-
Token-
Feature activation+0.000
Earth
TokenEarth
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
,
Token,
Feature activation+0.000
destroy
Token destroy
Feature activation+0.000
humanity
Token humanity
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
only
Token only
Feature activation+0.000
Captain
Token Captain
Feature activation+0.524
Marvel
Token Marvel
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
help
Token help
Feature activation+0.000
of
Token of
Feature activation+0.000
Comics
Token Comics
Feature activation+0.000
#
Token #
Feature activation+0.000
260
Token260
Feature activation+0.000
J
Token J
Feature activation+0.000
AN
TokenAN
Feature activation+0.000
Super
TokenSuper
Feature activation+0.526
girl
Tokengirl
Feature activation+0.000
becomes
Token becomes
Feature activation+0.000
Super
Token Super
Feature activation+0.000
-
Token-
Feature activation+0.000
baby
Tokenbaby
Feature activation+0.000

INTERVAL 0.323 - 0.485
CONTAINS 0.006%

.
Token.
Feature activation+0.000
Could
Token Could
Feature activation+0.000
there
Token there
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
Snow
Token Snow
Feature activation+0.402
White
Token White
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
cake
Tokencake
Feature activation+0.000
coming
Token coming
Feature activation+0.000
some
Token some
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.000
fight
Token fight
Feature activation+0.000
over
Token over
Feature activation+0.000
Confederate
Token Confederate
Feature activation+0.000
statues
Token statues
Feature activation+0.342
could
Token could
Feature activation+0.000
make
Token make
Feature activation+0.000
or
Token or
Feature activation+0.000
break
Token break
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
integrate
Token integrate
Feature activation+0.000
its
Token its
Feature activation+0.000
Wild
Token Wild
Feature activation+0.000
Storm
TokenStorm
Feature activation+0.000
and
Token and
Feature activation+0.000
Vert
Token Vert
Feature activation+0.475
igo
Tokenigo
Feature activation+0.000
superhero
Token superhero
Feature activation+0.000
properties
Token properties
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
read
Token read
Feature activation+0.000
Scientology
Token Scientology
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
founding
Token founding
Feature activation+0.451
text
Token text
Feature activation+0.000
cover
Token cover
Feature activation+0.000
to
Token to
Feature activation+0.000
cover
Token cover
Feature activation+0.000
with
Token with
Feature activation+0.000
allows
Token allows
Feature activation+0.000
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
development
Token development
Feature activation+0.397
tools
Token tools
Feature activation+0.000
Bethesda
Token Bethesda
Feature activation+0.165
used
Token used
Feature activation+0.000
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000

INTERVAL 0.162 - 0.323
CONTAINS 0.013%

Wars
Token Wars
Feature activation+0.000
after
Token after
Feature activation+0.000
befriend
Token befriend
Feature activation+0.000
ing
Tokening
Feature activation+0.000
Princess
Token Princess
Feature activation+0.245
Leia
Token Leia
Feature activation+0.203
and
Token and
Feature activation+0.000
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
impression
Token impression
Feature activation+0.000
that
Token that
Feature activation+0.000
Luke
Token Luke
Feature activation+0.111
Skywalker
Token Skywalker
Feature activation+0.248
,
Token,
Feature activation+0.000
sc
Token sc
Feature activation+0.000
ound
Tokenound
Feature activation+0.000
rel
Tokenrel
Feature activation+0.257
Han
Token Han
Feature activation+0.466
Solo
Token Solo
Feature activation+0.323
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
brave
Token brave
Feature activation+0.065
,
Token,
Feature activation+0.000
sc
Token sc
Feature activation+0.000
ound
Tokenound
Feature activation+0.000
rel
Tokenrel
Feature activation+0.257
Han
Token Han
Feature activation+0.466
Solo
Token Solo
Feature activation+0.323
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
brave
Token brave
Feature activation+0.065
and
Token and
Feature activation+0.000
l
Token l
Feature activation+0.000
successful
Token successful
Feature activation+0.000
opening
Token opening
Feature activation+0.000
weekend
Token weekend
Feature activation+0.000
,
Token,
Feature activation+0.000
writers
Token writers
Feature activation+0.000
Christopher
Token Christopher
Feature activation+0.277
Markus
Token Markus
Feature activation+0.326
and
Token and
Feature activation+0.000
Stephen
Token Stephen
Feature activation+0.228
McF
Token McF
Feature activation+0.626
eely
Tokeneely
Feature activation+0.000
Agent
Token Agent
Feature activation+0.000
00
Token 00
Feature activation+0.341
7
Token7
Feature activation+0.000
in
Token in
Feature activation+0.000
Her
Token Her
Feature activation+0.000
Majesty
Token Majesty
Feature activation+0.185
's
Token's
Feature activation+0.000
Secret
Token Secret
Feature activation+0.000
Service
Token Service
Feature activation+0.000
used
Token used
Feature activation+0.000
these
Token these
Feature activation+0.000

INTERVAL 0.000 - 0.162
CONTAINS 99.969%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
electric
Token electric
Feature activation+0.000
citrus
Token citrus
Feature activation+0.000
ju
Token ju
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
first
Token first
Feature activation+0.000
one
Token one
Feature activation+0.000
is
Token is
Feature activation+0.000
H
Token H
Feature activation+0.000
aster
Tokenaster
Feature activation+0.000
t
Tokent
Feature activation+0.000
spoke
Token spoke
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
man
Token man
Feature activation+0.000
,
Token,
Feature activation+0.000
previously
Token previously
Feature activation+0.000
Weekly
Token Weekly
Feature activation+0.000
that
Token that
Feature activation+0.000
his
Token his
Feature activation+0.000
workload
Token workload
Feature activation+0.000
,
Token,
Feature activation+0.000
stress
Token stress
Feature activation+0.000
over
Token over
Feature activation+0.000
wife
Token wife
Feature activation+0.000
Kim
Token Kim
Feature activation+0.000
Kardashian
Token Kardashian
Feature activation+0.000
's
Token's
Feature activation+0.000
as
Token as
Feature activation+0.000
illustrated
Token illustrated
Feature activation+0.000
by
Token by
Feature activation+0.000
her
Token her
Feature activation+0.000
report
Token report
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
local
Token local
Feature activation+0.000
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.000
global
Token global
Feature activation+0.000
cyber
Token cyber
Feature activation+0.000
bull
Tokenbull
Feature activation+0.000
ying
Tokenying
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
comes
Token comes
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
wake
Token wake
Feature activation+0.000
of
Token of
Feature activation+0.000
federal
Token federal
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 H0.2: (feature 1378)

TOP ACTIVATIONS
MAX = 1.494

will
Token will
Feature activation+0.000
have
Token have
Feature activation+0.000
more
Token more
Feature activation+0.000
Christians
Token Christians
Feature activation+0.000
than
Token than
Feature activation+0.000
Communist
Token Communist
Feature activation+1.494
Party
Token Party
Feature activation+0.776
members
Token members
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
stood
Token stood
Feature activation+0.000
by
Token by
Feature activation+0.000
Seoul
Token Seoul
Feature activation+0.376
's
Token's
Feature activation+0.000
poor
Token poor
Feature activation+0.000
and
Token and
Feature activation+0.000
isolated
Token isolated
Feature activation+1.464
neighbour
Token neighbour
Feature activation+0.203
."
Token."
Feature activation+0.000
I
TokenI
Feature activation+0.000
am
Token am
Feature activation+0.000
asking
Token asking
Feature activation+0.000
our
Token our
Feature activation+0.000
nation
Token nation
Feature activation+0.000
's
Token's
Feature activation+0.000
monitoring
Token monitoring
Feature activation+0.000
of
Token of
Feature activation+0.000
Communist
Token Communist
Feature activation+1.435
Chinese
Token Chinese
Feature activation+0.000
commercial
Token commercial
Feature activation+0.000
fronts
Token fronts
Feature activation+0.000
operating
Token operating
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
state
Token state
Feature activation+0.180
dinner
Token dinner
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Forbidden
Token Forbidden
Feature activation+1.424
City
Token City
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
elaborate
Token elaborate
Feature activation+0.000
palace
Token palace
Feature activation+0.000
games
Token games
Feature activation+0.000
nearby
Token nearby
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Py
TokenPy
Feature activation+1.314
ongyang
Tokenongyang
Feature activation+0.000
's
Token's
Feature activation+0.000
official
Token official
Feature activation+0.160
Korean
Token Korean
Feature activation+0.373
Central
Token Central
Feature activation+0.247
hostility
Token hostility
Feature activation+0.285
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
KC
Token KC
Feature activation+1.224
NA
TokenNA
Feature activation+0.000
reportedly
Token reportedly
Feature activation+0.000
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
much
Token much
Feature activation+0.000
less
Token less
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
reun
Token reun
Feature activation+1.179
ify
Tokenify
Feature activation+0.062
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Image
TokenImage
Feature activation+0.000
state
Token state
Feature activation+0.029
of
Token of
Feature activation+0.000
war
Token war
Feature activation+0.000
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
1950
Token 1950
Feature activation+1.174
-
Token-
Feature activation+0.000
53
Token53
Feature activation+0.000
Korean
Token Korean
Feature activation+0.164
War
Token War
Feature activation+0.000
ended
Token ended
Feature activation+0.000
"
Token"
Feature activation+0.000
for
Token for
Feature activation+0.000
Pyongyang
Token Pyongyang
Feature activation+0.287
,
Token,
Feature activation+0.000
should
Token should
Feature activation+0.000
Kim
Token Kim
Feature activation+1.146
Jong
Token Jong
Feature activation+0.197
Un
Token Un
Feature activation+0.366
engage
Token engage
Feature activation+0.000
in
Token in
Feature activation+0.000
further
Token further
Feature activation+0.000
Jong
Token Jong
Feature activation+0.197
Un
Token Un
Feature activation+0.366
engage
Token engage
Feature activation+0.000
in
Token in
Feature activation+0.000
further
Token further
Feature activation+0.000
prov
Token prov
Feature activation+1.098
ocations
Tokenocations
Feature activation+0.644
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
China
Token China
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
aggressive
Token aggressive
Feature activation+0.081
economic
Token economic
Feature activation+1.070
posture
Token posture
Feature activation+0.000
poses
Token poses
Feature activation+0.000
to
Token to
Feature activation+0.000
American
Token American
Feature activation+0.000
national
Token national
Feature activation+0.000
not
Token not
Feature activation+0.000
it
Token it
Feature activation+0.000
grants
Token grants
Feature activation+0.000
Hong
Token Hong
Feature activation+0.172
Kong
Token Kong
Feature activation+0.000
democracy
Token democracy
Feature activation+1.057
will
Token will
Feature activation+0.000
directly
Token directly
Feature activation+0.000
affect
Token affect
Feature activation+0.000
whether
Token whether
Feature activation+0.000
the
Token the
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
Kim
Token Kim
Feature activation+1.028
believes
Token believes
Feature activation+0.000
that
Token that
Feature activation+0.000
will
Token will
Feature activation+0.000
give
Token give
Feature activation+0.000
him
Token him
Feature activation+0.000
territory
Token territory
Feature activation+0.254
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
close
Token close
Feature activation+0.000
US
Token US
Feature activation+0.000
ally
Token ally
Feature activation+1.020
sends
Token sends
Feature activation+0.000
a
Token a
Feature activation+0.000
clear
Token clear
Feature activation+0.000
message
Token message
Feature activation+0.000
of
Token of
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
Japan
Token Japan
Feature activation+0.000
's
Token's
Feature activation+0.000
Nik
Token Nik
Feature activation+1.014
ke
Tokenke
Feature activation+0.000
i
Tokeni
Feature activation+0.000
share
Token share
Feature activation+0.000
average
Token average
Feature activation+0.000
.
Token .
Feature activation+0.000
the
Token the
Feature activation+0.000
North
Token North
Feature activation+0.054
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Korean
Token Korean
Feature activation+0.081
Peninsula
Token Peninsula
Feature activation+1.004
remains
Token remains
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
technical
Token technical
Feature activation+0.000
state
Token state
Feature activation+0.029
stronger
Token stronger
Feature activation+0.000
vigilance
Token vigilance
Feature activation+0.237
because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
continuing
Token continuing
Feature activation+0.000
provocation
Token provocation
Feature activation+0.925
by
Token by
Feature activation+0.000
Seoul
Token Seoul
Feature activation+0.376
's
Token's
Feature activation+0.000
poor
Token poor
Feature activation+0.000
and
Token and
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
nearest
Token nearest
Feature activation+0.000
Japanese
Token Japanese
Feature activation+0.000
island
Token island
Feature activation+0.915
,
Token,
Feature activation+0.000
O
Token O
Feature activation+0.000
ki
Tokenki
Feature activation+0.000
Islands
Token Islands
Feature activation+0.267
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
firing
Token firing
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
-
Token-
Feature activation+0.000
range
Tokenrange
Feature activation+0.883
missile
Token missile
Feature activation+0.425
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
US
Token US
Feature activation+0.000
think
Token think
Feature activation+0.000
why
Token why
Feature activation+0.000
defence
Token defence
Feature activation+0.000
analysts
Token analysts
Feature activation+0.000
think
Token think
Feature activation+0.000
that
Token that
Feature activation+0.000
Kim
Token Kim
Feature activation+0.880
Jong
Token Jong
Feature activation+0.198
-
Token-
Feature activation+0.000
un
Tokenun
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000

Top DFA by src position
MAX = 1.859

that
Token that
Feature activation+0.002
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
a
Token a
Feature activation+0.013
Top resid features:
few
Token few
Feature activation+0.003
Top resid features:
years
Token years
Feature activation-0.017
Top resid features:
China
Token China
Feature activation+1.526
Top resid features:
will
Token will
Feature activation+0.012
Top resid features:
have
Token have
Feature activation+0.007
Top resid features:
more
Token more
Feature activation+0.028
Top resid features:
Christians
Token Christians
Feature activation-0.021
Top resid features:
than
Token than
Feature activation+0.010
Top resid features:
10
Token 10
Feature activation+0.002
Top resid features:
days
Token days
Feature activation+0.002
Top resid features:
later
Token later
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
South
TokenSouth
Feature activation+0.001
Top resid features:
Korea
Token Korea
Feature activation+0.955
Top resid features:
's
Token's
Feature activation+0.007
Top resid features:
acting
Token acting
Feature activation+0.006
Top resid features:
president
Token president
Feature activation+0.007
Top resid features:
H
Token H
Feature activation+0.003
Top resid features:
wang
Tokenwang
Feature activation+0.012
Top resid features:
for
Token for
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
brutal
Token brutal
Feature activation+0.002
Top resid features:
regime
Token regime
Feature activation+0.004
Top resid features:
in
Token in
Feature activation+0.011
Top resid features:
China
Token China
Feature activation+1.859
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
voted
Token voted
Feature activation+0.010
Top resid features:
against
Token against
Feature activation+0.016
Top resid features:
our
Token our
Feature activation+0.016
Top resid features:
royal
Token royal
Feature activation+0.014
Top resid features:
during
Token during
Feature activation+0.003
Top resid features:
his
Token his
Feature activation+0.006
Top resid features:
visit
Token visit
Feature activation-0.003
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
China
Token China
Feature activation+0.721
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
He
TokenHe
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ļ
TokenĻ
Feature activation+0.009
Top resid features:
s
Tokens
Feature activation+0.002
Top resid features:
as
Token as
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
US
Token US
Feature activation+0.019
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
South
Token South
Feature activation-0.003
Top resid features:
Korea
Token Korea
Feature activation+1.123
Top resid features:
conduct
Token conduct
Feature activation-0.000
Top resid features:
war
Token war
Feature activation+0.016
Top resid features:
games
Token games
Feature activation+0.001
Top resid features:
nearby
Token nearby
Feature activation-0.012
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
hostility
Token hostility
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
The
TokenThe
Feature activation+0.046
Top resid features:
KC
Token KC
Feature activation+0.646
Top resid features:
NA
TokenNA
Feature activation+0.000
Top resid features:
reportedly
Token reportedly
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.015
Top resid features:
directly
Token directly
Feature activation+0.009
Top resid features:
affect
Token affect
Feature activation+0.008
Top resid features:
whether
Token whether
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
Taiwanese
Token Taiwanese
Feature activation+0.698
Top resid features:
trust
Token trust
Feature activation+0.004
Top resid features:
China
Token China
Feature activation+0.275
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
much
Token much
Feature activation+0.013
Top resid features:
less
Token less
Feature activation+0.018
Top resid features:
state
Token state
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
war
Token war
Feature activation+0.018
Top resid features:
because
Token because
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.070
Top resid features:
1950
Token 1950
Feature activation+0.802
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
53
Token53
Feature activation+0.000
Top resid features:
Korean
Token Korean
Feature activation+0.000
Top resid features:
War
Token War
Feature activation+0.000
Top resid features:
ended
Token ended
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.004
Top resid features:
for
Token for
Feature activation+0.013
Top resid features:
Pyongyang
Token Pyongyang
Feature activation+0.757
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
should
Token should
Feature activation+0.003
Top resid features:
Kim
Token Kim
Feature activation+0.783
Top resid features:
Jong
Token Jong
Feature activation+0.000
Top resid features:
Un
Token Un
Feature activation+0.000
Top resid features:
engage
Token engage
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
further
Token further
Feature activation+0.000
Top resid features:
Jong
Token Jong
Feature activation+0.398
Top resid features:
Un
Token Un
Feature activation+0.009
Top resid features:
engage
Token engage
Feature activation-0.002
Top resid features:
in
Token in
Feature activation+0.018
Top resid features:
further
Token further
Feature activation+0.038
Top resid features:
prov
Token prov
Feature activation+0.826
Top resid features:
ocations
Tokenocations
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
recognized
Token recognized
Feature activation-0.014
Top resid features:
repeatedly
Token repeatedly
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
threat
Token threat
Feature activation-0.009
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
China
Token China
Feature activation+0.905
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
s
Tokens
Feature activation+0.018
Top resid features:
aggressive
Token aggressive
Feature activation+0.044
Top resid features:
economic
Token economic
Feature activation+0.643
Top resid features:
not
Token not
Feature activation+0.009
Top resid features:
it
Token it
Feature activation+0.019
Top resid features:
grants
Token grants
Feature activation+0.007
Top resid features:
Hong
Token Hong
Feature activation+0.276
Top resid features:
Kong
Token Kong
Feature activation+0.131
Top resid features:
democracy
Token democracy
Feature activation+0.668
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
directly
Token directly
Feature activation+0.000
Top resid features:
affect
Token affect
Feature activation+0.000
Top resid features:
whether
Token whether
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
against
Token against
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
US
Token US
Feature activation+0.029
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
because
Token because
Feature activation-0.014
Top resid features:
Kim
Token Kim
Feature activation+0.723
Top resid features:
believes
Token believes
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
give
Token give
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
longest
Token longest
Feature activation+0.004
Top resid features:
ever
Token ever
Feature activation+0.007
Top resid features:
from
Token from
Feature activation+0.016
Top resid features:
North
Token North
Feature activation+0.011
Top resid features:
Korea
Token Korea
Feature activation+0.970
Top resid features:
-
Token -
Feature activation+0.005
Top resid features:
over
Token over
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
territory
Token territory
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
K
Token K
Feature activation+0.002
Top resid features:
ato
Tokenato
Feature activation+0.035
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
After
TokenAfter
Feature activation+0.001
Top resid features:
Japan
Token Japan
Feature activation+0.933
Top resid features:
's
Token's
Feature activation+0.032
Top resid features:
Nik
Token Nik
Feature activation+0.685
Top resid features:
ke
Tokenke
Feature activation+0.000
Top resid features:
i
Tokeni
Feature activation+0.000
Top resid features:
share
Token share
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
North
Token North
Feature activation+0.022
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
The
Token The
Feature activation+0.003
Top resid features:
Korean
Token Korean
Feature activation+0.769
Top resid features:
Peninsula
Token Peninsula
Feature activation+0.544
Top resid features:
remains
Token remains
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
technical
Token technical
Feature activation+0.000
Top resid features:
stronger
Token stronger
Feature activation+0.014
Top resid features:
vigilance
Token vigilance
Feature activation-0.006
Top resid features:
because
Token because
Feature activation-0.007
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
continuing
Token continuing
Feature activation-0.011
Top resid features:
provocation
Token provocation
Feature activation+1.085
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
Seoul
Token Seoul
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
poor
Token poor
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
n
Token n
Feature activation-0.004
Top resid features:
mi
Tokenmi
Feature activation+0.013
Top resid features:
)
Token)
Feature activation-0.007
Top resid features:
from
Token from
Feature activation+0.010
Top resid features:
mainland
Token mainland
Feature activation+0.080
Top resid features:
Korea
Token Korea
Feature activation+0.710
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
The
Token The
Feature activation+0.019
Top resid features:
nearest
Token nearest
Feature activation-0.007
Top resid features:
Japanese
Token Japanese
Feature activation+0.400
Top resid features:
island
Token island
Feature activation+0.598
Top resid features:
latest
Token latest
Feature activation-0.005
Top resid features:
nuclear
Token nuclear
Feature activation+0.051
Top resid features:
test
Token test
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
North
Token North
Feature activation+0.010
Top resid features:
Korea
Token Korea
Feature activation+1.231
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.006
Top resid features:
making
Token making
Feature activation-0.005
Top resid features:
preparations
Token preparations
Feature activation+0.003
Top resid features:
at
Token at
Feature activation+0.003
Top resid features:
why
Token why
Feature activation+0.005
Top resid features:
defence
Token defence
Feature activation+0.030
Top resid features:
analysts
Token analysts
Feature activation+0.029
Top resid features:
think
Token think
Feature activation+0.012
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
Kim
Token Kim
Feature activation+0.573
Top resid features:
Jong
Token Jong
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
un
Tokenun
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.12

Head 2: 0.26

Head 3: 0.11

Head 4: 0.06

Head 5: 0.05

Head 6: 0.05

Head 7: 0.05

Head 8: 0.05

Head 9: 0.08

Head 10: 0.06

Head 11: 0.06

Positive logits

warr4.43

citiz4.29

dismant4.10

istani3.95

ikuman3.83

rul3.76

achev3.70

fortun3.70

uprising3.64

shenan3.62

Jinping3.59

equival3.56

dictatorship3.56

consulate3.55

satell3.53

corrid3.51

unemploy3.46

rall3.41

igon3.40

Lumpur3.40

Negative logits

Interstitial-4.60

bleacher-4.17

Merit-3.63

Scotland-3.61

Magicka-3.61

ACTED-3.59

ONS-3.56

FORMATION-3.54

Fairfax-3.50

══-3.49

Weaver-3.49

Hurricanes-3.48

ACC-3.43

PUBLIC-3.40

Virginia-3.38

Private-3.37

Pwr-3.36

++++++++++++++++-3.31

nder-3.30

WARN-3.25

INTERVAL 1.344 - 1.494
CONTAINS 0.001%

a
Token a
Feature activation+0.000
state
Token state
Feature activation+0.180
dinner
Token dinner
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Forbidden
Token Forbidden
Feature activation+1.424
City
Token City
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
elaborate
Token elaborate
Feature activation+0.000
palace
Token palace
Feature activation+0.000
will
Token will
Feature activation+0.000
have
Token have
Feature activation+0.000
more
Token more
Feature activation+0.000
Christians
Token Christians
Feature activation+0.000
than
Token than
Feature activation+0.000
Communist
Token Communist
Feature activation+1.494
Party
Token Party
Feature activation+0.776
members
Token members
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
stood
Token stood
Feature activation+0.000
by
Token by
Feature activation+0.000
Seoul
Token Seoul
Feature activation+0.376
's
Token's
Feature activation+0.000
poor
Token poor
Feature activation+0.000
and
Token and
Feature activation+0.000
isolated
Token isolated
Feature activation+1.464
neighbour
Token neighbour
Feature activation+0.203
."
Token."
Feature activation+0.000
I
TokenI
Feature activation+0.000
am
Token am
Feature activation+0.000
asking
Token asking
Feature activation+0.000
our
Token our
Feature activation+0.000
nation
Token nation
Feature activation+0.000
's
Token's
Feature activation+0.000
monitoring
Token monitoring
Feature activation+0.000
of
Token of
Feature activation+0.000
Communist
Token Communist
Feature activation+1.435
Chinese
Token Chinese
Feature activation+0.000
commercial
Token commercial
Feature activation+0.000
fronts
Token fronts
Feature activation+0.000
operating
Token operating
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 1.195 - 1.344
CONTAINS 0.000%

games
Token games
Feature activation+0.000
nearby
Token nearby
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Py
TokenPy
Feature activation+1.314
ongyang
Tokenongyang
Feature activation+0.000
's
Token's
Feature activation+0.000
official
Token official
Feature activation+0.160
Korean
Token Korean
Feature activation+0.373
Central
Token Central
Feature activation+0.247
hostility
Token hostility
Feature activation+0.285
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
KC
Token KC
Feature activation+1.224
NA
TokenNA
Feature activation+0.000
reportedly
Token reportedly
Feature activation+0.000
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.046 - 1.195
CONTAINS 0.001%

state
Token state
Feature activation+0.029
of
Token of
Feature activation+0.000
war
Token war
Feature activation+0.000
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
1950
Token 1950
Feature activation+1.174
-
Token-
Feature activation+0.000
53
Token53
Feature activation+0.000
Korean
Token Korean
Feature activation+0.164
War
Token War
Feature activation+0.000
ended
Token ended
Feature activation+0.000
China
Token China
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
aggressive
Token aggressive
Feature activation+0.081
economic
Token economic
Feature activation+1.070
posture
Token posture
Feature activation+0.000
poses
Token poses
Feature activation+0.000
to
Token to
Feature activation+0.000
American
Token American
Feature activation+0.000
national
Token national
Feature activation+0.000
,
Token,
Feature activation+0.000
much
Token much
Feature activation+0.000
less
Token less
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
reun
Token reun
Feature activation+1.179
ify
Tokenify
Feature activation+0.062
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Image
TokenImage
Feature activation+0.000
"
Token"
Feature activation+0.000
for
Token for
Feature activation+0.000
Pyongyang
Token Pyongyang
Feature activation+0.287
,
Token,
Feature activation+0.000
should
Token should
Feature activation+0.000
Kim
Token Kim
Feature activation+1.146
Jong
Token Jong
Feature activation+0.197
Un
Token Un
Feature activation+0.366
engage
Token engage
Feature activation+0.000
in
Token in
Feature activation+0.000
further
Token further
Feature activation+0.000
not
Token not
Feature activation+0.000
it
Token it
Feature activation+0.000
grants
Token grants
Feature activation+0.000
Hong
Token Hong
Feature activation+0.172
Kong
Token Kong
Feature activation+0.000
democracy
Token democracy
Feature activation+1.057
will
Token will
Feature activation+0.000
directly
Token directly
Feature activation+0.000
affect
Token affect
Feature activation+0.000
whether
Token whether
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.896 - 1.046
CONTAINS 0.001%

against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
Kim
Token Kim
Feature activation+1.028
believes
Token believes
Feature activation+0.000
that
Token that
Feature activation+0.000
will
Token will
Feature activation+0.000
give
Token give
Feature activation+0.000
him
Token him
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
Japan
Token Japan
Feature activation+0.000
's
Token's
Feature activation+0.000
Nik
Token Nik
Feature activation+1.014
ke
Tokenke
Feature activation+0.000
i
Tokeni
Feature activation+0.000
share
Token share
Feature activation+0.000
average
Token average
Feature activation+0.000
.
Token .
Feature activation+0.000
territory
Token territory
Feature activation+0.254
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
close
Token close
Feature activation+0.000
US
Token US
Feature activation+0.000
ally
Token ally
Feature activation+1.020
sends
Token sends
Feature activation+0.000
a
Token a
Feature activation+0.000
clear
Token clear
Feature activation+0.000
message
Token message
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
North
Token North
Feature activation+0.054
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Korean
Token Korean
Feature activation+0.081
Peninsula
Token Peninsula
Feature activation+1.004
remains
Token remains
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
technical
Token technical
Feature activation+0.000
state
Token state
Feature activation+0.029
stronger
Token stronger
Feature activation+0.000
vigilance
Token vigilance
Feature activation+0.237
because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
continuing
Token continuing
Feature activation+0.000
provocation
Token provocation
Feature activation+0.925
by
Token by
Feature activation+0.000
Seoul
Token Seoul
Feature activation+0.376
's
Token's
Feature activation+0.000
poor
Token poor
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.747 - 0.896
CONTAINS 0.002%

in
Token in
Feature activation+0.000
Hong
Token Hong
Feature activation+0.171
Kong
Token Kong
Feature activation+0.000
and
Token and
Feature activation+0.000
an
Token an
Feature activation+0.000
Occupy
Token Occupy
Feature activation+0.844
Parliament
Token Parliament
Feature activation+0.003
movement
Token movement
Feature activation+0.000
in
Token in
Feature activation+0.000
Tai
Token Tai
Feature activation+0.542
pei
Tokenpei
Feature activation+0.000
for
Token for
Feature activation+0.000
firing
Token firing
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
-
Token-
Feature activation+0.000
range
Tokenrange
Feature activation+0.883
missile
Token missile
Feature activation+0.425
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
US
Token US
Feature activation+0.000
think
Token think
Feature activation+0.000
.
Token.
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
believed
Token believed
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Republic
Token Republic
Feature activation+0.768
of
Token of
Feature activation+0.000
China
Token China
Feature activation+0.000
also
Token also
Feature activation+0.000
had
Token had
Feature activation+0.000
designed
Token designed
Feature activation+0.000
States
Token States
Feature activation+0.000
has
Token has
Feature activation+0.000
concluded
Token concluded
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
People
Token People
Feature activation+0.768
's
Token's
Feature activation+0.000
Republic
Token Republic
Feature activation+0.000
of
Token of
Feature activation+0.000
China
Token China
Feature activation+0.000
conducted
Token conducted
Feature activation+0.000
the
Token the
Feature activation+0.000
North
Token North
Feature activation+0.224
's
Token's
Feature activation+0.000
frequent
Token frequent
Feature activation+0.000
weapons
Token weapons
Feature activation+0.357
tests
Token tests
Feature activation+0.763
are
Token are
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
steps
Token steps
Feature activation+0.000
in
Token in
Feature activation+0.000
acquiring
Token acquiring
Feature activation+0.000

INTERVAL 0.597 - 0.747
CONTAINS 0.002%

box
Token box
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
in
Token in
Feature activation+0.000
H
Token H
Feature activation+0.235
ano
Tokenano
Feature activation+0.718
i
Tokeni
Feature activation+0.000
.
Token .
Feature activation+0.000
My
Token My
Feature activation+0.000
North
Token North
Feature activation+0.000
Vietnamese
Token Vietnamese
Feature activation+0.000
officials
Token officials
Feature activation+0.000
,
Token,
Feature activation+0.000
North
Token North
Feature activation+0.000
Korean
Token Korean
Feature activation+0.000
leader
Token leader
Feature activation+0.250
Kim
Token Kim
Feature activation+0.706
Jong
Token Jong
Feature activation+0.000
-
Token-
Feature activation+0.000
un
Tokenun
Feature activation+0.000
continues
Token continues
Feature activation+0.000
to
Token to
Feature activation+0.000
two
Token two
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
intensified
Token intensified
Feature activation+0.000
after
Token after
Feature activation+0.000
Pyongyang
Token Pyongyang
Feature activation+0.000
tested
Token tested
Feature activation+0.602
two
Token two
Feature activation+0.000
inter
Token inter
Feature activation+0.311
continental
Tokencontinental
Feature activation+0.000
ballistic
Token ballistic
Feature activation+0.329
missiles
Token missiles
Feature activation+0.000
about
Token about
Feature activation+0.000
Pyongyang
Token Pyongyang
Feature activation+0.004
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
missile
Token missile
Feature activation+0.703
and
Token and
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.109
programs
Token programs
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
war
Token war
Feature activation+0.000
head
Tokenhead
Feature activation+0.000
,
Token,
Feature activation+0.000
allowing
Token allowing
Feature activation+0.000
the
Token the
Feature activation+0.000
missile
Token missile
Feature activation+0.696
to
Token to
Feature activation+0.000
achieve
Token achieve
Feature activation+0.000
a
Token a
Feature activation+0.000
much
Token much
Feature activation+0.000
higher
Token higher
Feature activation+0.000

INTERVAL 0.448 - 0.597
CONTAINS 0.003%

unusual
Token unusual
Feature activation+0.000
tr
Token tr
Feature activation+0.000
ilateral
Tokenilateral
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
with
Token with
Feature activation+0.000
Abe
Token Abe
Feature activation+0.462
and
Token and
Feature activation+0.000
South
Token South
Feature activation+0.000
Korean
Token Korean
Feature activation+0.000
President
Token President
Feature activation+0.000
Park
Token Park
Feature activation+0.720
the
Token the
Feature activation+0.000
matter
Token matter
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Indust
TokenIndust
Feature activation+0.539
ry
Tokenry
Feature activation+0.000
groups
Token groups
Feature activation+0.000
said
Token said
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
People
Token People
Feature activation+0.474
's
Token's
Feature activation+0.000
Daily
Token Daily
Feature activation+0.000
newspaper
Token newspaper
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
are
Token are
Feature activation+0.000
meant
Token meant
Feature activation+0.000
to
Token to
Feature activation+0.000
protect
Token protect
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.592
from
Token from
Feature activation+0.000
US
Token US
Feature activation+0.000
hostility
Token hostility
Feature activation+0.285
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
recognize
Token recognize
Feature activation+0.000
China
Token China
Feature activation+0.000
following
Token following
Feature activation+0.000
its
Token its
Feature activation+0.000
Communist
Token Communist
Feature activation+0.471
revolution
Token revolution
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
while
Token while
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 0.299 - 0.448
CONTAINS 0.006%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
confront
Token confront
Feature activation+0.000
a
Token a
Feature activation+0.000
strategic
Token strategic
Feature activation+0.310
dilemma
Token dilemma
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
have
Token have
Feature activation+0.000
close
Token close
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
independence
Token independence
Feature activation+0.158
from
Token from
Feature activation+0.000
Japanese
Token Japanese
Feature activation+0.000
colonial
Token colonial
Feature activation+0.312
rule
Token rule
Feature activation+0.000
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+0.000
swim
Token swim
Feature activation+0.000
follows
Token follows
Feature activation+0.000
being
Token being
Feature activation+0.000
a
Token a
Feature activation+0.000
local
Token local
Feature activation+0.000
organizer
Token organizer
Feature activation+0.000
of
Token of
Feature activation+0.000
Ik
Token Ik
Feature activation+0.384
esh
Tokenesh
Feature activation+0.000
ita
Tokenita
Feature activation+0.000
-
Token-
Feature activation+0.000
g
Tokeng
Feature activation+0.000
umi
Tokenumi
Feature activation+0.000
afternoon
Token afternoon
Feature activation+0.000
at
Token at
Feature activation+0.000
Tan
Token Tan
Feature activation+0.000
Son
Token Son
Feature activation+0.054
N
Token N
Feature activation+0.000
h
Tokenh
Feature activation+0.393
ut
Tokenut
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
waiting
Token waiting
Feature activation+0.000
for
Token for
Feature activation+0.000
which
Token which
Feature activation+0.000
followed
Token followed
Feature activation+0.000
a
Token a
Feature activation+0.000
major
Token major
Feature activation+0.000
Asian
Token Asian
Feature activation+0.442
regional
Token regional
Feature activation+0.398
summit
Token summit
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

INTERVAL 0.149 - 0.299
CONTAINS 0.009%

will
Token will
Feature activation+0.000
directly
Token directly
Feature activation+0.000
affect
Token affect
Feature activation+0.000
whether
Token whether
Feature activation+0.000
the
Token the
Feature activation+0.000
Taiwanese
Token Taiwanese
Feature activation+0.251
trust
Token trust
Feature activation+0.000
China
Token China
Feature activation+0.344
,
Token,
Feature activation+0.000
much
Token much
Feature activation+0.000
less
Token less
Feature activation+0.000
the
Token the
Feature activation+0.000
self
Token self
Feature activation+0.000
-
Token-
Feature activation+0.000
proclaimed
Tokenproclaimed
Feature activation+0.000
Donetsk
Token Donetsk
Feature activation+0.000
People
Token People
Feature activation+0.244
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Republic
Token Republic
Feature activation+0.115
âĢ
TokenâĢ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pro
TokenPro
Feature activation+0.000
-
Token-
Feature activation+0.000
independence
Tokenindependence
Feature activation+0.164
protesters
Token protesters
Feature activation+0.000
carry
Token carry
Feature activation+0.000
plac
Token plac
Feature activation+0.000
ard
Tokenard
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
seats
Token seats
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Communist
Token Communist
Feature activation+0.338
Party
Token Party
Feature activation+0.297
's
Token's
Feature activation+0.000
Central
Token Central
Feature activation+0.000
Committee
Token Committee
Feature activation+0.000
and
Token and
Feature activation+0.000
Polit
Token Polit
Feature activation+0.289
North
Token North
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
-
Token -
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
territory
Token territory
Feature activation+0.254
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
close
Token close
Feature activation+0.000
US
Token US
Feature activation+0.000
ally
Token ally
Feature activation+1.020

INTERVAL 0.000 - 0.149
CONTAINS 99.977%

released
Token released
Feature activation+0.000
on
Token on
Feature activation+0.000
social
Token social
Feature activation+0.000
media
Token media
Feature activation+0.000
by
Token by
Feature activation+0.000
Saudi
Token Saudi
Feature activation+0.000
officials
Token officials
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
too
Token too
Feature activation+0.000
much
Token much
Feature activation+0.000
let
Token let
Feature activation+0.000
me
Token me
Feature activation+0.000
know
Token know
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
move
Token move
Feature activation+0.000
the
Token the
Feature activation+0.000
O
Token O
Feature activation+0.000
psy
Token psy
Feature activation+0.000
b
Tokenb
Feature activation+0.000
ient
Tokenient
Feature activation+0.000
,
Token,
Feature activation+0.000
psy
Token psy
Feature activation+0.000
bass
Tokenbass
Feature activation+0.000
and
Token and
Feature activation+0.000
psy
Token psy
Feature activation+0.000
d
Tokend
Feature activation+0.000
ub
Tokenub
Feature activation+0.000
.
Token.
Feature activation+0.000
ick
Tokenick
Feature activation+0.000
Ã
TokenÃ
Feature activation+0.000
½
Token½
Feature activation+0.000
mi
Tokenmi
Feature activation+0.000
se
Token se
Feature activation+0.000
ty
Token ty
Feature activation+0.000
to
Tokento
Feature activation+0.000
p
Token p
Feature activation+0.000
Å
TokenÅ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ÃŃ
TokenÃŃ
Feature activation+0.000
and
Token and
Feature activation+0.000
also
Token also
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
local
Token local
Feature activation+0.000
First
Token First
Feature activation+0.000
Nation
Token Nation
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

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 H0.2: (feature 21829)

TOP ACTIVATIONS
MAX = 1.489

Ped
Token Ped
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
ud
Tokenud
Feature activation+0.000
u
Tokenu
Feature activation+0.000
starring
Token starring
Feature activation+1.489
Moh
Token Moh
Feature activation+0.000
an
Tokenan
Feature activation+0.000
Bab
Token Bab
Feature activation+0.000
u
Tokenu
Feature activation+0.000
,
Token,
Feature activation+0.000
B
Token B
Feature activation+0.000
ollywood
Tokenollywood
Feature activation+0.154
as
Token as
Feature activation+0.000
Bul
Token Bul
Feature activation+0.000
andi
Tokenandi
Feature activation+0.000
starring
Token starring
Feature activation+1.324
An
Token An
Feature activation+0.000
il
Tokenil
Feature activation+0.000
Kap
Token Kap
Feature activation+0.372
oor
Tokenoor
Feature activation+0.044
,
Token,
Feature activation+0.000
w
Tokenw
Feature activation+0.000
illing
Tokenilling
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
other
Token other
Feature activation+0.000
directing
Token directing
Feature activation+1.322
projects
Token projects
Feature activation+0.163
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
filled
Token filled
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
of
Token of
Feature activation+0.000
studios
Token studios
Feature activation+1.297
looking
Token looking
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
in
Token in
Feature activation+0.000
on
Token on
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.000
's
Token's
Feature activation+0.000
box
Token box
Feature activation+1.273
office
Token office
Feature activation+0.000
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
suffer
Token suffer
Feature activation+0.000
,
Token,
Feature activation+0.000
K
Token K
Feature activation+0.000
ami
Tokenami
Feature activation+0.000
y
Tokeny
Feature activation+0.000
ama
Tokenama
Feature activation+0.000
has
Token has
Feature activation+0.000
hel
Token hel
Feature activation+1.245
med
Tokenmed
Feature activation+0.000
in
Token in
Feature activation+0.000
five
Token five
Feature activation+0.000
years
Token years
Feature activation+0.000
since
Token since
Feature activation+0.000
Gift
Token Gift
Feature activation+0.000
Shop
Token Shop
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
prestigious
Token prestigious
Feature activation+0.000
festival
Token festival
Feature activation+1.225
has
Token has
Feature activation+0.000
,
Token,
Feature activation+0.000
typically
Token typically
Feature activation+0.000
for
Token for
Feature activation+0.000
Banks
Token Banks
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
tons
Token tons
Feature activation+0.000
of
Token of
Feature activation+0.000
feature
Token feature
Feature activation+1.143
ttes
Tokenttes
Feature activation+0.000
,
Token,
Feature activation+0.000
interviews
Token interviews
Feature activation+0.000
,
Token,
Feature activation+0.000
commentary
Token commentary
Feature activation+0.195
and
Token and
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
turned
Token turned
Feature activation+0.000
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
feature
Token feature
Feature activation+1.116
film
Token film
Feature activation+0.000
called
Token called
Feature activation+0.000
Trailer
Token Trailer
Feature activation+0.258
Park
Token Park
Feature activation+0.000
Boys
Token Boys
Feature activation+0.000
script
Token script
Feature activation+0.565
,
Token,
Feature activation+0.000
director
Token director
Feature activation+0.577
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
studio
Token studio
Feature activation+1.111
all
Token all
Feature activation+0.000
set
Token set
Feature activation+0.000
to
Token to
Feature activation+0.000
go
Token go
Feature activation+0.000
.
Token.
Feature activation+0.000
Never
TokenNever
Feature activation+0.000
having
Token having
Feature activation+0.000
made
Token made
Feature activation+0.000
a
Token a
Feature activation+0.000
studio
Token studio
Feature activation+1.045
feature
Token feature
Feature activation+1.108
before
Token before
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
assumed
Token assumed
Feature activation+0.000
this
Token this
Feature activation+0.000
local
Token local
Feature activation+0.000
film
Token film
Feature activation+0.000
school
Token school
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Rogue
Token Rogue
Feature activation+1.093
Film
Token Film
Feature activation+0.000
School
Token School
Feature activation+0.000
is
Token is
Feature activation+0.000
about
Token about
Feature activation+0.000
a
Token a
Feature activation+0.000
privilege
Token privilege
Feature activation+0.000
.
Token.
Feature activation+0.000
Its
Token Its
Feature activation+0.000
first
Token first
Feature activation+0.000
four
Token four
Feature activation+0.000
scripts
Token scripts
Feature activation+1.060
are
Token are
Feature activation+0.000
finely
Token finely
Feature activation+0.000
wrought
Token wrought
Feature activation+0.000
and
Token and
Feature activation+0.000
intellectually
Token intellectually
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Never
TokenNever
Feature activation+0.000
having
Token having
Feature activation+0.000
made
Token made
Feature activation+0.000
a
Token a
Feature activation+0.000
studio
Token studio
Feature activation+1.045
feature
Token feature
Feature activation+1.108
before
Token before
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
assumed
Token assumed
Feature activation+0.000
a
Token a
Feature activation+0.000
seemingly
Token seemingly
Feature activation+0.000
endless
Token endless
Feature activation+0.000
appetite
Token appetite
Feature activation+0.000
for
Token for
Feature activation+0.000
adaptations
Token adaptations
Feature activation+1.043
of
Token of
Feature activation+0.000
Wu
Token Wu
Feature activation+0.000
Chen
Token Chen
Feature activation+0.000
-
Token-
Feature activation+0.000
en
Tokenen
Feature activation+0.000
topping
Token topping
Feature activation+0.026
the
Token the
Feature activation+0.000
list
Token list
Feature activation+0.000
of
Token of
Feature activation+0.000
films
Token films
Feature activation+0.004
produced
Token produced
Feature activation+1.015
.
Token.
Feature activation+0.000
Considering
TokenConsidering
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
long
Token long
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
festival
Token festival
Feature activation+0.974
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Spotlight
Token Spotlight
Feature activation+0.021
Surprise
Token Surprise
Feature activation+0.000
dialect
Token dialect
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Attack
Token Attack
Feature activation+0.947
on
Token on
Feature activation+0.000
Titan
Token Titan
Feature activation+0.000
Exhibition
Token Exhibition
Feature activation+0.000
will
Token will
Feature activation+0.000
move
Token move
Feature activation+0.000
Although
TokenAlthough
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.000
had
Token had
Feature activation+0.000
mixed
Token mixed
Feature activation+0.000
reviews
Token reviews
Feature activation+0.933
,
Token,
Feature activation+0.000
Pop
Token Pop
Feature activation+0.000
eye
Tokeneye
Feature activation+0.000
Village
Token Village
Feature activation+0.461
remains
Token remains
Feature activation+0.000
the
Token the
Feature activation+0.000
coveted
Token coveted
Feature activation+0.000
best
Token best
Feature activation+0.242
national
Token national
Feature activation+0.000
film
Token film
Feature activation+0.000
award
Token award
Feature activation+0.909
had
Token had
Feature activation+0.000
el
Token el
Feature activation+0.000
uded
Tokenuded
Feature activation+0.000
the
Token the
Feature activation+0.000
Tel
Token Tel
Feature activation+0.000

Top DFA by src position
MAX = 1.388

Ped
Token Ped
Feature activation+0.029
Top resid features:
ar
Tokenar
Feature activation+0.012
Top resid features:
ay
Tokenay
Feature activation+0.013
Top resid features:
ud
Tokenud
Feature activation+0.015
Top resid features:
u
Tokenu
Feature activation+0.015
Top resid features:
starring
Token starring
Feature activation+0.807
Top resid features:
Moh
Token Moh
Feature activation+0.000
Top resid features:
an
Tokenan
Feature activation+0.000
Top resid features:
Bab
Token Bab
Feature activation+0.000
Top resid features:
u
Tokenu
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
B
Token B
Feature activation+0.014
Top resid features:
ollywood
Tokenollywood
Feature activation+0.212
Top resid features:
as
Token as
Feature activation+0.018
Top resid features:
Bul
Token Bul
Feature activation+0.033
Top resid features:
andi
Tokenandi
Feature activation+0.014
Top resid features:
starring
Token starring
Feature activation+0.666
Top resid features:
An
Token An
Feature activation+0.000
Top resid features:
il
Tokenil
Feature activation+0.000
Top resid features:
Kap
Token Kap
Feature activation+0.000
Top resid features:
oor
Tokenoor
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
closing
Token closing
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
curtain
Token curtain
Feature activation+0.035
Top resid features:
on
Token on
Feature activation+0.009
Top resid features:
theatrical
Token theatrical
Feature activation+0.174
Top resid features:
films
Token films
Feature activation+1.047
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
he
Token he
Feature activation+0.021
Top resid features:
is
Token is
Feature activation+0.023
Top resid features:
âĢ
Token âĢ
Feature activation+0.013
Top resid features:
ľ
Tokenľ
Feature activation+0.018
Top resid features:
potential
Token potential
Feature activation+0.012
Top resid features:
opportunity
Token opportunity
Feature activation+0.012
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
presents
Token presents
Feature activation+0.021
Top resid features:
for
Token for
Feature activation+0.008
Top resid features:
filmmakers
Token filmmakers
Feature activation+1.016
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
At
Token At
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
recent
Token recent
Feature activation+0.016
Top resid features:
Virtual
Token Virtual
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
While
TokenWhile
Feature activation+0.033
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
film
Token film
Feature activation+1.388
Top resid features:
's
Token's
Feature activation+0.048
Top resid features:
box
Token box
Feature activation+0.687
Top resid features:
office
Token office
Feature activation+0.000
Top resid features:
didn
Token didn
Feature activation+0.000
Top resid features:
't
Token't
Feature activation+0.000
Top resid features:
project
Token project
Feature activation+0.035
Top resid features:
will
Token will
Feature activation+0.017
Top resid features:
be
Token be
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
first
Token first
Feature activation+0.026
Top resid features:
film
Token film
Feature activation+0.778
Top resid features:
that
Token that
Feature activation+0.021
Top resid features:
K
Token K
Feature activation+0.036
Top resid features:
ami
Tokenami
Feature activation+0.022
Top resid features:
y
Tokeny
Feature activation+0.024
Top resid features:
ama
Tokenama
Feature activation+0.036
Top resid features:
finally
Token finally
Feature activation+0.020
Top resid features:
show
Token show
Feature activation+0.035
Top resid features:
his
Token his
Feature activation+0.012
Top resid features:
face
Token face
Feature activation+0.021
Top resid features:
on
Token on
Feature activation+0.011
Top resid features:
film
Token film
Feature activation+1.335
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
The
TokenThe
Feature activation+0.032
Top resid features:
inclusion
Token inclusion
Feature activation+0.031
Top resid features:
1956
Token 1956
Feature activation+0.029
Top resid features:
American
Token American
Feature activation+0.027
Top resid features:
adaptation
Token adaptation
Feature activation+0.060
Top resid features:
of
Token of
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
film
Token film
Feature activation+1.221
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
Godzilla
Token Godzilla
Feature activation+0.120
Top resid features:
:
Token:
Feature activation+0.019
Top resid features:
King
Token King
Feature activation+0.026
Top resid features:
of
Token of
Feature activation+0.017
Top resid features:
trailer
Token trailer
Feature activation+0.103
Top resid features:
park
Token park
Feature activation+0.042
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
The
Token The
Feature activation+0.018
Top resid features:
original
Token original
Feature activation+0.025
Top resid features:
film
Token film
Feature activation+0.814
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
called
Token called
Feature activation+0.014
Top resid features:
One
Token One
Feature activation+0.021
Top resid features:
Last
Token Last
Feature activation+0.012
Top resid features:
Shot
Token Shot
Feature activation+0.037
Top resid features:
original
Token original
Feature activation+0.025
Top resid features:
two
Token two
Feature activation+0.019
Top resid features:
movies
Token movies
Feature activation+0.743
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
film
Token film
Feature activation+0.955
Top resid features:
is
Token is
Feature activation+0.018
Top resid features:
now
Token now
Feature activation+0.012
Top resid features:
in
Token in
Feature activation+0.012
Top resid features:
pre
Token pre
Feature activation+0.020
Top resid features:
-
Token-
Feature activation+0.024
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
film
Token film
Feature activation+0.737
Top resid features:
(
Token (
Feature activation+0.011
Top resid features:
a
Tokena
Feature activation+0.006
Top resid features:
film
Token film
Feature activation+0.776
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
mind
Token mind
Feature activation+0.017
Top resid features:
you
Token you
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
called
Token called
Feature activation+0.011
Top resid features:
local
Token local
Feature activation+0.026
Top resid features:
film
Token film
Feature activation+0.645
Top resid features:
school
Token school
Feature activation+0.036
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
The
Token The
Feature activation+0.049
Top resid features:
Rogue
Token Rogue
Feature activation+0.853
Top resid features:
Film
Token Film
Feature activation+0.000
Top resid features:
School
Token School
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
privilege
Token privilege
Feature activation+0.030
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
Its
Token Its
Feature activation+0.028
Top resid features:
first
Token first
Feature activation+0.035
Top resid features:
four
Token four
Feature activation+0.021
Top resid features:
scripts
Token scripts
Feature activation+0.889
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
finely
Token finely
Feature activation+0.000
Top resid features:
wrought
Token wrought
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
intellectually
Token intellectually
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
film
Token film
Feature activation+0.792
Top resid features:
(
Token (
Feature activation+0.011
Top resid features:
a
Tokena
Feature activation+0.007
Top resid features:
film
Token film
Feature activation+0.816
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
mind
Token mind
Feature activation+0.011
Top resid features:
you
Token you
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
called
Token called
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.019
Top resid features:
seemingly
Token seemingly
Feature activation+0.036
Top resid features:
endless
Token endless
Feature activation+0.065
Top resid features:
appetite
Token appetite
Feature activation+0.056
Top resid features:
for
Token for
Feature activation+0.022
Top resid features:
adaptations
Token adaptations
Feature activation+0.743
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Wu
Token Wu
Feature activation+0.000
Top resid features:
Chen
Token Chen
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
en
Tokenen
Feature activation+0.000
Top resid features:
topping
Token topping
Feature activation+0.067
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
list
Token list
Feature activation+0.064
Top resid features:
of
Token of
Feature activation+0.019
Top resid features:
films
Token films
Feature activation+0.537
Top resid features:
produced
Token produced
Feature activation+0.673
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Considering
TokenConsidering
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
long
Token long
Feature activation+0.000
Top resid features:
finally
Token finally
Feature activation+0.008
Top resid features:
show
Token show
Feature activation+0.023
Top resid features:
his
Token his
Feature activation+0.004
Top resid features:
face
Token face
Feature activation+0.009
Top resid features:
on
Token on
Feature activation+0.005
Top resid features:
film
Token film
Feature activation+0.983
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
The
TokenThe
Feature activation+0.010
Top resid features:
inclusion
Token inclusion
Feature activation+0.011
Top resid features:
ime
Tokenime
Feature activation+0.015
Top resid features:
Is
Token Is
Feature activation+0.014
Top resid features:
ay
Tokenay
Feature activation+0.008
Top resid features:
ama
Tokenama
Feature activation+0.014
Top resid features:
's
Token's
Feature activation+0.018
Top resid features:
manga
Token manga
Feature activation+0.896
Top resid features:
replaces
Token replaces
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
dialogue
Token dialogue
Feature activation+0.048
Top resid features:
with
Token with
Feature activation+0.007
Top resid features:
Hok
Token Hok
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Although
TokenAlthough
Feature activation+0.051
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
film
Token film
Feature activation+0.878
Top resid features:
had
Token had
Feature activation+0.031
Top resid features:
mixed
Token mixed
Feature activation+0.054
Top resid features:
reviews
Token reviews
Feature activation+0.821
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Pop
Token Pop
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
coveted
Token coveted
Feature activation+0.073
Top resid features:
best
Token best
Feature activation+0.031
Top resid features:
national
Token national
Feature activation+0.014
Top resid features:
film
Token film
Feature activation+0.349
Top resid features:
award
Token award
Feature activation+0.893
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
el
Token el
Feature activation+0.000
Top resid features:
uded
Tokenuded
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Tel
Token Tel
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.13

Head 2: 0.26

Head 3: 0.12

Head 4: 0.05

Head 5: 0.05

Head 6: 0.05

Head 7: 0.05

Head 8: 0.05

Head 9: 0.09

Head 10: 0.07

Head 11: 0.05

Positive logits

sequels4.58

4.52

4.38

films4.37

4.35

4.29

isphere4.29

ゼウス4.24

staples3.95

screenings3.89

cinema3.83

3.81

DVDs3.80

premiered3.80

ファ3.78

movies3.73

ynski3.73

stars3.73

classics3.70

productions3.65

Negative logits

laus-4.26

ptoms-3.96

DEP-3.82

apa-3.58

etheless-3.52

maxwell-3.44

staking-3.36

forgiving-3.30

ift-3.24

minecraft-3.24

fect-3.18

FORMATION-3.16

ced-3.16

bia-3.15

Recon-3.14

ARR-3.14

hap-3.12

arta-3.10

distant-3.08

owship-3.08

INTERVAL 1.340 - 1.489
CONTAINS 0.000%

Ped
Token Ped
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
ud
Tokenud
Feature activation+0.000
u
Tokenu
Feature activation+0.000
starring
Token starring
Feature activation+1.489
Moh
Token Moh
Feature activation+0.000
an
Tokenan
Feature activation+0.000
Bab
Token Bab
Feature activation+0.000
u
Tokenu
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.191 - 1.340
CONTAINS 0.001%

K
Token K
Feature activation+0.000
ami
Tokenami
Feature activation+0.000
y
Tokeny
Feature activation+0.000
ama
Tokenama
Feature activation+0.000
has
Token has
Feature activation+0.000
hel
Token hel
Feature activation+1.245
med
Tokenmed
Feature activation+0.000
in
Token in
Feature activation+0.000
five
Token five
Feature activation+0.000
years
Token years
Feature activation+0.000
since
Token since
Feature activation+0.000
filled
Token filled
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
of
Token of
Feature activation+0.000
studios
Token studios
Feature activation+1.297
looking
Token looking
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
in
Token in
Feature activation+0.000
on
Token on
Feature activation+0.000
Gift
Token Gift
Feature activation+0.000
Shop
Token Shop
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
prestigious
Token prestigious
Feature activation+0.000
festival
Token festival
Feature activation+1.225
has
Token has
Feature activation+0.000
,
Token,
Feature activation+0.000
typically
Token typically
Feature activation+0.000
for
Token for
Feature activation+0.000
Banks
Token Banks
Feature activation+0.000
w
Tokenw
Feature activation+0.000
illing
Tokenilling
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
other
Token other
Feature activation+0.000
directing
Token directing
Feature activation+1.322
projects
Token projects
Feature activation+0.163
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.000
's
Token's
Feature activation+0.000
box
Token box
Feature activation+1.273
office
Token office
Feature activation+0.000
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
suffer
Token suffer
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.042 - 1.191
CONTAINS 0.001%

privilege
Token privilege
Feature activation+0.000
.
Token.
Feature activation+0.000
Its
Token Its
Feature activation+0.000
first
Token first
Feature activation+0.000
four
Token four
Feature activation+0.000
scripts
Token scripts
Feature activation+1.060
are
Token are
Feature activation+0.000
finely
Token finely
Feature activation+0.000
wrought
Token wrought
Feature activation+0.000
and
Token and
Feature activation+0.000
intellectually
Token intellectually
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Never
TokenNever
Feature activation+0.000
having
Token having
Feature activation+0.000
made
Token made
Feature activation+0.000
a
Token a
Feature activation+0.000
studio
Token studio
Feature activation+1.045
feature
Token feature
Feature activation+1.108
before
Token before
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
assumed
Token assumed
Feature activation+0.000
a
Token a
Feature activation+0.000
seemingly
Token seemingly
Feature activation+0.000
endless
Token endless
Feature activation+0.000
appetite
Token appetite
Feature activation+0.000
for
Token for
Feature activation+0.000
adaptations
Token adaptations
Feature activation+1.043
of
Token of
Feature activation+0.000
Wu
Token Wu
Feature activation+0.000
Chen
Token Chen
Feature activation+0.000
-
Token-
Feature activation+0.000
en
Tokenen
Feature activation+0.000
Never
TokenNever
Feature activation+0.000
having
Token having
Feature activation+0.000
made
Token made
Feature activation+0.000
a
Token a
Feature activation+0.000
studio
Token studio
Feature activation+1.045
feature
Token feature
Feature activation+1.108
before
Token before
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
assumed
Token assumed
Feature activation+0.000
this
Token this
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
tons
Token tons
Feature activation+0.000
of
Token of
Feature activation+0.000
feature
Token feature
Feature activation+1.143
ttes
Tokenttes
Feature activation+0.000
,
Token,
Feature activation+0.000
interviews
Token interviews
Feature activation+0.000
,
Token,
Feature activation+0.000
commentary
Token commentary
Feature activation+0.195

INTERVAL 0.893 - 1.042
CONTAINS 0.001%

that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
festival
Token festival
Feature activation+0.974
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Spotlight
Token Spotlight
Feature activation+0.021
Surprise
Token Surprise
Feature activation+0.000
Russo
Token Russo
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
are
Token are
Feature activation+0.000
hel
Token hel
Feature activation+0.896
ming
Tokenming
Feature activation+0.000
Avengers
Token Avengers
Feature activation+0.000
:
Token:
Feature activation+0.000
Infinity
Token Infinity
Feature activation+0.000
War
Token War
Feature activation+0.000
makes
Token makes
Feature activation+0.000
me
Token me
Feature activation+0.000
wonder
Token wonder
Feature activation+0.000
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
directors
Token directors
Feature activation+0.898
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Lincoln
Token Lincoln
Feature activation+0.028
Park
Token Park
Feature activation+0.000
Zoo
Token Zoo
Feature activation+0.000
Although
TokenAlthough
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.000
had
Token had
Feature activation+0.000
mixed
Token mixed
Feature activation+0.000
reviews
Token reviews
Feature activation+0.933
,
Token,
Feature activation+0.000
Pop
Token Pop
Feature activation+0.000
eye
Tokeneye
Feature activation+0.000
Village
Token Village
Feature activation+0.461
remains
Token remains
Feature activation+0.000
dialect
Token dialect
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Attack
Token Attack
Feature activation+0.947
on
Token on
Feature activation+0.000
Titan
Token Titan
Feature activation+0.000
Exhibition
Token Exhibition
Feature activation+0.000
will
Token will
Feature activation+0.000
move
Token move
Feature activation+0.000

INTERVAL 0.744 - 0.893
CONTAINS 0.001%

in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
speech
Token speech
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
scripted
Token scripted
Feature activation+0.868
and
Token and
Feature activation+0.000
delivered
Token delivered
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
help
Token help
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
anime
Token anime
Feature activation+0.000
adaptation
Token adaptation
Feature activation+0.767
of
Token of
Feature activation+0.000
Jun
Token Jun
Feature activation+0.000
Sak
Token Sak
Feature activation+0.000
yo
Tokenyo
Feature activation+0.146
's
Token's
Feature activation+0.000
The
TokenThe
Feature activation+0.000
movie
Token movie
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
latest
Token latest
Feature activation+0.000
installment
Token installment
Feature activation+0.831
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
God
Token God
Feature activation+0.000
of
Token of
Feature activation+0.000
Gam
Token Gam
Feature activation+0.000
Paul
Token Paul
Feature activation+0.001
ine
Tokenine
Feature activation+0.000
K
Token K
Feature activation+0.000
ael
Tokenael
Feature activation+0.000
and
Token and
Feature activation+0.000
Roger
Token Roger
Feature activation+0.750
E
Token E
Feature activation+0.000
bert
Tokenbert
Feature activation+0.000
.)
Token.)
Feature activation+0.000
Age
Token Age
Feature activation+0.000
e
Tokene
Feature activation+0.000
an
Token an
Feature activation+0.000
underdog
Token underdog
Feature activation+0.000
sci
Token sci
Feature activation+0.232
-
Token-
Feature activation+0.000
fi
Tokenfi
Feature activation+0.000
series
Token series
Feature activation+0.785
before
Token before
Feature activation+0.000
-
Token -
Feature activation+0.000
just
Token just
Feature activation+0.000
think
Token think
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.596 - 0.744
CONTAINS 0.003%

the
Token the
Feature activation+0.000
recent
Token recent
Feature activation+0.000
Virtual
Token Virtual
Feature activation+0.000
Reality
Token Reality
Feature activation+0.000
Film
Token Film
Feature activation+0.000
Fest
Token Fest
Feature activation+0.670
in
Token in
Feature activation+0.000
Los
Token Los
Feature activation+0.000
Angeles
Token Angeles
Feature activation+0.000
,
Token,
Feature activation+0.000
Rift
Token Rift
Feature activation+0.000
great
Token great
Feature activation+0.000
conclusion
Token conclusion
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
season
Token season
Feature activation+0.661
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
acting
Token acting
Feature activation+0.000
was
Token was
Feature activation+0.000
really
Token really
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
first
Token first
Feature activation+0.000
hour
Token hour
Feature activation+0.695
was
Token was
Feature activation+0.000
actually
Token actually
Feature activation+0.000
slightly
Token slightly
Feature activation+0.000
down
Token down
Feature activation+0.000
from
Token from
Feature activation+0.000
Fer
Token Fer
Feature activation+0.000
rell
Tokenrell
Feature activation+0.000
in
Token in
Feature activation+0.000
such
Token such
Feature activation+0.000
comedy
Token comedy
Feature activation+0.000
classics
Token classics
Feature activation+0.606
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
An
TokenAn
Feature activation+0.000
ch
Tokench
Feature activation+0.000
quite
Token quite
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
box
Token box
Feature activation+0.667
office
Token office
Feature activation+0.000
as
Token as
Feature activation+0.000
its
Token its
Feature activation+0.000
producers
Token producers
Feature activation+0.000
hoped
Token hoped
Feature activation+0.000

INTERVAL 0.447 - 0.596
CONTAINS 0.004%

Park
Token Park
Feature activation+0.000
Boys
Token Boys
Feature activation+0.000
the
Token the
Feature activation+0.000
series
Token series
Feature activation+0.481
is
Token is
Feature activation+0.000
based
Token based
Feature activation+0.514
on
Token on
Feature activation+0.000
Ricky
Token Ricky
Feature activation+0.000
,
Token,
Feature activation+0.000
Julian
Token Julian
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
television
Token television
Feature activation+0.000
news
Token news
Feature activation+0.000
channels
Token channels
Feature activation+0.525
began
Token began
Feature activation+0.000
spl
Token spl
Feature activation+0.000
ashing
Tokenashing
Feature activation+0.000
the
Token the
Feature activation+0.000
news
Token news
Feature activation+0.000
was
Token was
Feature activation+0.000
ton
Token ton
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
off
Token off
Feature activation+0.000
.
Token.
Feature activation+0.000
Guardians
Token Guardians
Feature activation+0.468
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Galaxy
Token Galaxy
Feature activation+0.000
was
Token was
Feature activation+0.000
heavily
Token heavily
Feature activation+0.000
med
Tokenmed
Feature activation+0.000
in
Token in
Feature activation+0.000
five
Token five
Feature activation+0.000
years
Token years
Feature activation+0.000
since
Token since
Feature activation+0.000
00
Token 00
Feature activation+0.545
9
Token9
Feature activation+0.000
Re
Token Re
Feature activation+0.000
:
Token:
Feature activation+0.000
Cy
TokenCy
Feature activation+0.000
borg
Tokenborg
Feature activation+0.000
Since
Token Since
Feature activation+0.000
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
McKay
Token McKay
Feature activation+0.000
has
Token has
Feature activation+0.000
directed
Token directed
Feature activation+0.590
Fer
Token Fer
Feature activation+0.000
rell
Tokenrell
Feature activation+0.000
in
Token in
Feature activation+0.000
such
Token such
Feature activation+0.000
comedy
Token comedy
Feature activation+0.000

INTERVAL 0.298 - 0.447
CONTAINS 0.006%

).
Token).
Feature activation+0.000
First
Token First
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
independent
Token independent
Feature activation+0.360
report
Token report
Feature activation+0.000
conducted
Token conducted
Feature activation+0.000
by
Token by
Feature activation+0.000
former
Token former
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
20
Token 20
Feature activation+0.038
minutes
Token minutes
Feature activation+0.000
leading
Token leading
Feature activation+0.000
into
Token into
Feature activation+0.000
his
Token his
Feature activation+0.000
unt
Token unt
Feature activation+0.425
ime
Tokenime
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
demise
Token demise
Feature activation+0.000
hoping
Token hoping
Feature activation+0.000
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
Fun
Token Fun
Feature activation+0.333
imation
Tokenimation
Feature activation+0.802
Entertainment
Token Entertainment
Feature activation+0.000
has
Token has
Feature activation+0.000
licensed
Token licensed
Feature activation+0.407
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.000
television
Token television
Feature activation+0.000
series
Token series
Feature activation+0.378
and
Token and
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
key
Token key
Feature activation+0.000
feature
Token feature
Feature activation+0.405
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
novel
Token novel
Feature activation+0.000
.
Token.
Feature activation+0.000
Jane
Token Jane
Feature activation+0.000
had
Token had
Feature activation+0.000
its
Token its
Feature activation+0.000
hugely
Token hugely
Feature activation+0.000
successful
Token successful
Feature activation+0.107
opening
Token opening
Feature activation+0.396
weekend
Token weekend
Feature activation+0.383
,
Token,
Feature activation+0.000
writers
Token writers
Feature activation+0.520
Christopher
Token Christopher
Feature activation+0.402
Markus
Token Markus
Feature activation+0.667
and
Token and
Feature activation+0.000

INTERVAL 0.149 - 0.298
CONTAINS 0.012%

do
Token do
Feature activation+0.000
is
Token is
Feature activation+0.000
dive
Token dive
Feature activation+0.073
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
impact
Token impact
Feature activation+0.213
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Guardians
Token Guardians
Feature activation+0.485
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Fog
Token Fog
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
features
Token features
Feature activation+0.200
a
Token a
Feature activation+0.000
loss
Token loss
Feature activation+0.000
less
Tokenless
Feature activation+0.000
5
Token 5
Feature activation+0.000
.
Token.
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
total
Token total
Feature activation+0.000
of
Token of
Feature activation+0.000
1966
Token 1966
Feature activation+0.223
films
Token films
Feature activation+0.000
were
Token were
Feature activation+0.000
made
Token made
Feature activation+0.581
in
Token in
Feature activation+0.000
India
Token India
Feature activation+0.000
horror
Token horror
Feature activation+0.000
series
Token series
Feature activation+0.000
is
Token is
Feature activation+0.000
directed
Token directed
Feature activation+0.546
and
Token and
Feature activation+0.000
produced
Token produced
Feature activation+0.154
by
Token by
Feature activation+0.000
Band
Token Band
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
will
Token will
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Last
TokenLast
Feature activation+0.000
year
Token year
Feature activation+0.000
local
Token local
Feature activation+0.000
Feature
Token Feature
Feature activation+0.304
production
Token production
Feature activation+0.154
hit
Token hit
Feature activation+0.000
a
Token a
Feature activation+0.000
seven
Token seven
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000

INTERVAL 0.000 - 0.149
CONTAINS 99.971%

and
Token and
Feature activation+0.000
will
Token will
Feature activation+0.000
finance
Token finance
Feature activation+0.000
countries
Token countries
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Co
Token Co
Feature activation+0.000
ene
Tokenene
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
handful
Token handful
Feature activation+0.000
of
Token of
Feature activation+0.000
states
Token states
Feature activation+0.000
where
Token where
Feature activation+0.000
Amazon
Token Amazon
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
't
Token't
Feature activation+0.000
have
Token have
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
pledge
Token pledge
Feature activation+0.000
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
with
Token with
Feature activation+0.000
global
Token global
Feature activation+0.000
oil
Token oil
Feature activation+0.000
producers
Token producers
Feature activation+0.000
in
Token in
Feature activation+0.000
out
Token out
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
a
Token a
Feature activation+0.000
result
Token result
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
lucky
Token lucky
Feature activation+0.000
circles
Token circles
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
were
Token were
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
just
Token just
Feature activation+0.000
client
Token client
Feature activation+0.000
and
Token and
Feature activation+0.000
attorney
Token attorney
Feature activation+0.000
.
Token.
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H0.2: (feature 18285)

TOP ACTIVATIONS
MAX = 1.399

of
Token of
Feature activation+0.000
England
Token England
Feature activation+0.244
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.190
s
Tokens
Feature activation+0.000
exit
Token exit
Feature activation+1.399
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+0.112
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
UK
Token UK
Feature activation+0.000
and
Token and
Feature activation+0.000
EU
Token EU
Feature activation+0.012
on
Token on
Feature activation+0.000
divorce
Token divorce
Feature activation+1.382
issues
Token issues
Feature activation+0.000
including
Token including
Feature activation+0.000
the
Token the
Feature activation+0.000
Irish
Token Irish
Feature activation+0.112
border
Token border
Feature activation+0.037
resigned
Token resigned
Feature activation+0.121
(
Token (
Feature activation+0.000
David
TokenDavid
Feature activation+1.075
Davis
Token Davis
Feature activation+0.248
and
Token and
Feature activation+0.000
Dominic
Token Dominic
Feature activation+1.347
Ra
Token Ra
Feature activation+0.019
ab
Tokenab
Feature activation+0.000
respectively
Token respectively
Feature activation+0.000
),
Token),
Feature activation+0.000
Stephen
Token Stephen
Feature activation+0.270
which
Token which
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
referendum
Token referendum
Feature activation+0.801
on
Token on
Feature activation+0.000
independence
Token independence
Feature activation+1.239
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
rest
Token rest
Feature activation+0.148
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
democratically
Token democratically
Feature activation+0.000
elected
Token elected
Feature activation+0.000
governments
Token governments
Feature activation+0.000
of
Token of
Feature activation+0.000
EU
Token EU
Feature activation+0.000
member
Token member
Feature activation+1.192
states
Token states
Feature activation+0.000
are
Token are
Feature activation+0.000
making
Token making
Feature activation+0.000
it
Token it
Feature activation+0.000
harder
Token harder
Feature activation+0.000
has
Token has
Feature activation+0.000
developed
Token developed
Feature activation+0.000
differently
Token differently
Feature activation+0.000
since
Token since
Feature activation+0.000
Old
Token Old
Feature activation+0.038
Sax
Token Sax
Feature activation+1.183
on
Tokenon
Feature activation+0.000
times
Token times
Feature activation+0.000
and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.000
lost
Token lost
Feature activation+0.000
MEP
Token MEP
Feature activation+0.276
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
EU
Token EU
Feature activation+0.266
member
Token member
Feature activation+1.178
states
Token states
Feature activation+0.000
and
Token and
Feature activation+0.000
Scotland
Token Scotland
Feature activation+0.194
rat
Token rat
Feature activation+0.000
ify
Tokenify
Feature activation+0.000
The
TokenThe
Feature activation+0.000
best
Token best
Feature activation+0.000
time
Token time
Feature activation+0.000
for
Token for
Feature activation+0.000
another
Token another
Feature activation+0.000
independence
Token independence
Feature activation+1.156
referendum
Token referendum
Feature activation+0.526
is
Token is
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
access
Token access
Feature activation+1.092
the
Token the
Feature activation+0.000
European
Token European
Feature activation+0.055
Court
Token Court
Feature activation+0.446
of
Token of
Feature activation+0.000
Justice
Token Justice
Feature activation+0.760
border
Token border
Feature activation+0.027
management
Token management
Feature activation+0.000
system
Token system
Feature activation+0.000
with
Token with
Feature activation+0.000
tougher
Token tougher
Feature activation+0.000
migration
Token migration
Feature activation+1.090
control
Token control
Feature activation+0.000
the
Token the
Feature activation+0.000
core
Token core
Feature activation+0.000
aim
Token aim
Feature activation+0.000
.
Token.
Feature activation+0.000
he
Token he
Feature activation+0.000
added
Token added
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Liberal
TokenLiberal
Feature activation+1.087
Democrat
Token Democrat
Feature activation+0.000
leader
Token leader
Feature activation+0.263
Tim
Token Tim
Feature activation+0.216
Far
Token Far
Feature activation+0.386
ron
Tokenron
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
want
Token want
Feature activation+0.000
another
Token another
Feature activation+0.000
independence
Token independence
Feature activation+1.087
referendum
Token referendum
Feature activation+0.513
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Will
TokenWill
Feature activation+0.000
Scotland
Token Scotland
Feature activation+0.000
still
Token still
Feature activation+0.000
use
Token use
Feature activation+0.000
sterling
Token sterling
Feature activation+1.081
?
Token?
Feature activation+0.000
And
Token And
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+0.000
do
Token do
Feature activation+0.000
appointed
Token appointed
Feature activation+0.000
Brexit
Token Brexit
Feature activation+0.225
secretaries
Token secretaries
Feature activation+0.000
resigned
Token resigned
Feature activation+0.121
(
Token (
Feature activation+0.000
David
TokenDavid
Feature activation+1.075
Davis
Token Davis
Feature activation+0.248
and
Token and
Feature activation+0.000
Dominic
Token Dominic
Feature activation+1.347
Ra
Token Ra
Feature activation+0.019
ab
Tokenab
Feature activation+0.000
CD
TokenCD
Feature activation+0.972
U
TokenU
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
its
Token its
Feature activation+0.000
Bav
Token Bav
Feature activation+1.065
arian
Tokenarian
Feature activation+0.000
sister
Token sister
Feature activation+0.265
party
Token party
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
REUTERS
Token REUTERS
Feature activation+0.000
/
Token/
Feature activation+0.000
Y
TokenY
Feature activation+0.000
ves
Tokenves
Feature activation+0.052
Herman
Token Herman
Feature activation+1.062
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
her
Token her
Feature activation+0.000
attempts
Token attempts
Feature activation+0.000
attacked
Token attacked
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
repeatedly
Token repeatedly
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
Falk
Token Falk
Feature activation+1.054
lands
Tokenlands
Feature activation+0.000
since
Token since
Feature activation+0.000
taking
Token taking
Feature activation+0.000
over
Token over
Feature activation+0.000
power
Token power
Feature activation+0.000
arian
Tokenarian
Feature activation+0.000
sister
Token sister
Feature activation+0.265
party
Token party
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Christian
Token Christian
Feature activation+1.052
Social
Token Social
Feature activation+0.612
Union
Token Union
Feature activation+0.000
(
Token (
Feature activation+0.000
CS
TokenCS
Feature activation+0.336
U
TokenU
Feature activation+0.000
be
Token be
Feature activation+0.000
solved
Token solved
Feature activation+0.000
by
Token by
Feature activation+0.000
Theresa
Token Theresa
Feature activation+0.713
May
Token May
Feature activation+0.843
triggering
Token triggering
Feature activation+1.043
article
Token article
Feature activation+1.011
50
Token 50
Feature activation+0.000
as
Token as
Feature activation+0.000
soon
Token soon
Feature activation+0.000
as
Token as
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
integrated
Token integrated
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
commission
Token commission
Feature activation+1.032
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
rule
Token rule
Feature activation+0.000
book
Tokenbook
Feature activation+0.000

Top DFA by src position
MAX = 1.455

Independence
Token Independence
Feature activation+0.025
Top resid features:
Party
Token Party
Feature activation+0.041
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
and
Token and
Feature activation+0.019
Top resid features:
#
Token #
Feature activation+0.016
Top resid features:
Brexit
TokenBrexit
Feature activation+1.171
Top resid features:
advocate
Token advocate
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
in
Token in
Feature activation+0.029
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
wake
Token wake
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.047
Top resid features:
UK
Token UK
Feature activation+0.727
Top resid features:
and
Token and
Feature activation+0.059
Top resid features:
EU
Token EU
Feature activation+0.450
Top resid features:
on
Token on
Feature activation+0.066
Top resid features:
divorce
Token divorce
Feature activation+0.794
Top resid features:
issues
Token issues
Feature activation+0.000
Top resid features:
including
Token including
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Irish
Token Irish
Feature activation+0.000
Top resid features:
border
Token border
Feature activation+0.000
Top resid features:
resigned
Token resigned
Feature activation+0.019
Top resid features:
(
Token (
Feature activation+0.050
Top resid features:
David
TokenDavid
Feature activation+0.016
Top resid features:
Davis
Token Davis
Feature activation+0.047
Top resid features:
and
Token and
Feature activation+0.091
Top resid features:
Dominic
Token Dominic
Feature activation+0.926
Top resid features:
Ra
Token Ra
Feature activation+0.000
Top resid features:
ab
Tokenab
Feature activation+0.000
Top resid features:
respectively
Token respectively
Feature activation+0.000
Top resid features:
),
Token),
Feature activation+0.000
Top resid features:
Stephen
Token Stephen
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.016
Top resid features:
j
Tokenj
Feature activation+0.007
Top resid features:
ealous
Tokenealous
Feature activation+0.026
Top resid features:
"
Token"
Feature activation+0.019
Top resid features:
of
Token of
Feature activation+0.024
Top resid features:
Scotland
Token Scotland
Feature activation+1.265
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
which
Token which
Feature activation+0.032
Top resid features:
has
Token has
Feature activation+0.028
Top resid features:
a
Token a
Feature activation+0.047
Top resid features:
referendum
Token referendum
Feature activation+0.044
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
democratically
Token democratically
Feature activation+0.066
Top resid features:
elected
Token elected
Feature activation+0.019
Top resid features:
governments
Token governments
Feature activation+0.052
Top resid features:
of
Token of
Feature activation+0.041
Top resid features:
EU
Token EU
Feature activation+1.455
Top resid features:
member
Token member
Feature activation+0.658
Top resid features:
states
Token states
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
making
Token making
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
German
Token German
Feature activation+0.756
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
The
Token The
Feature activation+0.029
Top resid features:
related
Token related
Feature activation+0.016
Top resid features:
Low
Token Low
Feature activation+0.029
Top resid features:
German
Token German
Feature activation+0.812
Top resid features:
has
Token has
Feature activation+0.019
Top resid features:
developed
Token developed
Feature activation+0.033
Top resid features:
differently
Token differently
Feature activation+0.018
Top resid features:
since
Token since
Feature activation+0.025
Top resid features:
Old
Token Old
Feature activation+0.224
Top resid features:
of
Token of
Feature activation+0.031
Top resid features:
MEP
Token MEP
Feature activation+0.191
Top resid features:
s
Tokens
Feature activation+0.032
Top resid features:
,
Token,
Feature activation+0.045
Top resid features:
all
Token all
Feature activation+0.053
Top resid features:
EU
Token EU
Feature activation+0.963
Top resid features:
member
Token member
Feature activation+0.594
Top resid features:
states
Token states
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Scotland
Token Scotland
Feature activation+0.000
Top resid features:
rat
Token rat
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.022
Top resid features:
proof
Tokenproof
Feature activation+0.010
Top resid features:
âĢ
TokenâĢ
Feature activation+0.020
Top resid features:
Ŀ
TokenĿ
Feature activation+0.020
Top resid features:
that
Token that
Feature activation+0.013
Top resid features:
Scotland
Token Scotland
Feature activation+1.224
Top resid features:
doesn
Token doesn
Feature activation+0.010
Top resid features:
âĢ
TokenâĢ
Feature activation+0.023
Top resid features:
Ļ
TokenĻ
Feature activation+0.022
Top resid features:
t
Tokent
Feature activation+0.009
Top resid features:
want
Token want
Feature activation+0.014
Top resid features:
Britain
Token Britain
Feature activation+0.171
Top resid features:
would
Token would
Feature activation+0.039
Top resid features:
be
Token be
Feature activation+0.019
Top resid features:
able
Token able
Feature activation+0.049
Top resid features:
to
Token to
Feature activation+0.080
Top resid features:
access
Token access
Feature activation+0.702
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
European
Token European
Feature activation+0.000
Top resid features:
Court
Token Court
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Justice
Token Justice
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.024
Top resid features:
IPS
TokenIPS
Feature activation+0.022
Top resid features:
)
Token)
Feature activation+0.019
Top resid features:
-
Token -
Feature activation+0.021
Top resid features:
The
Token The
Feature activation+0.032
Top resid features:
European
Token European
Feature activation+0.825
Top resid features:
Union
Token Union
Feature activation+0.026
Top resid features:
is
Token is
Feature activation+0.017
Top resid features:
implementing
Token implementing
Feature activation+0.017
Top resid features:
a
Token a
Feature activation+0.036
Top resid features:
new
Token new
Feature activation+0.017
Top resid features:
deliver
Token deliver
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
same
Token same
Feature activation+0.013
Top resid features:
deal
Token deal
Feature activation+0.014
Top resid features:
for
Token for
Feature activation+0.020
Top resid features:
UK
Token UK
Feature activation+0.553
Top resid features:
nationals
Token nationals
Feature activation+0.065
Top resid features:
living
Token living
Feature activation+0.025
Top resid features:
in
Token in
Feature activation+0.026
Top resid features:
the
Token the
Feature activation+0.029
Top resid features:
EU
Token EU
Feature activation+0.145
Top resid features:
ľ
Tokenľ
Feature activation+0.030
Top resid features:
proof
Tokenproof
Feature activation+0.013
Top resid features:
âĢ
TokenâĢ
Feature activation+0.028
Top resid features:
Ŀ
TokenĿ
Feature activation+0.029
Top resid features:
that
Token that
Feature activation+0.023
Top resid features:
Scotland
Token Scotland
Feature activation+1.307
Top resid features:
doesn
Token doesn
Feature activation+0.017
Top resid features:
âĢ
TokenâĢ
Feature activation+0.037
Top resid features:
Ļ
TokenĻ
Feature activation+0.045
Top resid features:
t
Tokent
Feature activation+0.017
Top resid features:
want
Token want
Feature activation+0.031
Top resid features:
Ċ
TokenĊ
Feature activation+0.037
Top resid features:
Will
TokenWill
Feature activation+0.005
Top resid features:
Scotland
Token Scotland
Feature activation+0.739
Top resid features:
still
Token still
Feature activation+0.045
Top resid features:
use
Token use
Feature activation+0.020
Top resid features:
sterling
Token sterling
Feature activation+0.858
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
And
Token And
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
first
Token first
Feature activation+0.016
Top resid features:
and
Token and
Feature activation+0.032
Top resid features:
second
Token second
Feature activation+0.017
Top resid features:
appointed
Token appointed
Feature activation+0.017
Top resid features:
Brexit
Token Brexit
Feature activation+0.699
Top resid features:
secretaries
Token secretaries
Feature activation+0.018
Top resid features:
resigned
Token resigned
Feature activation+0.017
Top resid features:
(
Token (
Feature activation+0.096
Top resid features:
David
TokenDavid
Feature activation+0.612
Top resid features:
Davis
Token Davis
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
The
Token The
Feature activation+0.025
Top resid features:
ministers
Token ministers
Feature activation+0.017
Top resid features:
belonging
Token belonging
Feature activation+0.013
Top resid features:
to
Token to
Feature activation+0.023
Top resid features:
Merkel
Token Merkel
Feature activation+0.920
Top resid features:
's
Token's
Feature activation+0.030
Top resid features:
center
Token center
Feature activation+0.003
Top resid features:
-
Token-
Feature activation+0.024
Top resid features:
right
Tokenright
Feature activation+0.019
Top resid features:
Christian
Token Christian
Feature activation+0.013
Top resid features:
Minister
Token Minister
Feature activation+0.023
Top resid features:
Theresa
Token Theresa
Feature activation+0.043
Top resid features:
May
Token May
Feature activation+0.016
Top resid features:
attends
Token attends
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
European
Token European
Feature activation+0.762
Top resid features:
Union
Token Union
Feature activation+0.039
Top resid features:
leaders
Token leaders
Feature activation+0.026
Top resid features:
summit
Token summit
Feature activation+0.019
Top resid features:
in
Token in
Feature activation+0.022
Top resid features:
Val
Token Val
Feature activation+0.017
Top resid features:
attacked
Token attacked
Feature activation+0.020
Top resid features:
Britain
Token Britain
Feature activation+0.645
Top resid features:
repeatedly
Token repeatedly
Feature activation+0.027
Top resid features:
over
Token over
Feature activation+0.069
Top resid features:
the
Token the
Feature activation+0.140
Top resid features:
Falk
Token Falk
Feature activation+0.679
Top resid features:
lands
Tokenlands
Feature activation+0.000
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
taking
Token taking
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
power
Token power
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
The
Token The
Feature activation+0.024
Top resid features:
ministers
Token ministers
Feature activation+0.061
Top resid features:
belonging
Token belonging
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.018
Top resid features:
Merkel
Token Merkel
Feature activation+1.197
Top resid features:
's
Token's
Feature activation+0.019
Top resid features:
center
Token center
Feature activation-0.002
Top resid features:
-
Token-
Feature activation+0.013
Top resid features:
right
Tokenright
Feature activation+0.016
Top resid features:
Christian
Token Christian
Feature activation-0.031
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
British
Token British
Feature activation+0.118
Top resid features:
public
Token public
Feature activation+0.008
Top resid features:
to
Token to
Feature activation+0.018
Top resid features:
back
Token back
Feature activation+0.016
Top resid features:
Brexit
Token Brexit
Feature activation+0.829
Top resid features:
as
Token as
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
cause
Token cause
Feature activation+0.006
Top resid features:
of
Token of
Feature activation+0.027
Top resid features:
uncertainty
Token uncertainty
Feature activation+0.021
Top resid features:
âĢ
TokenâĢ
Feature activation+0.007
Top resid features:
Ŀ
TokenĿ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
The
TokenThe
Feature activation+0.018
Top resid features:
EU
Token EU
Feature activation+1.371
Top resid features:
o
Token o
Feature activation+0.011
Top resid features:
mbudsman
Tokenmbudsman
Feature activation+0.004
Top resid features:
Emily
Token Emily
Feature activation+0.013
Top resid features:
O
Token O
Feature activation+0.011
Top resid features:
'
Token'
Feature activation+0.010
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.13

Head 2: 0.26

Head 3: 0.12

Head 4: 0.05

Head 5: 0.05

Head 6: 0.05

Head 7: 0.04

Head 8: 0.04

Head 9: 0.09

Head 10: 0.05

Head 11: 0.06

Positive logits

querque3.83

unemploy3.79

anthem3.78

corrid3.71

wedd3.66

ーティ3.63

guiActiveUn3.60

3.57

ファ3.51

3.47

isphere3.44

upgr3.39

appoint3.37

ageing3.36

ンジ3.32

citiz3.28

redes3.28

conduc3.27

franc3.27

shenan3.25

Negative logits

YES-3.76

Private-3.68

ARR-3.67

AAAA-3.46

esters-3.44

reads-3.42

shows-3.34

Drug-3.28

Information-3.27

Intent-3.27

Phys-3.26

Interstitial-3.24

Known-3.24

Explain-3.23

Merit-3.20

Resource-3.18

Dog-3.14

Sensor-3.14

Jackets-3.13

Recon-3.12

INTERVAL 1.259 - 1.399
CONTAINS 0.000%

resigned
Token resigned
Feature activation+0.121
(
Token (
Feature activation+0.000
David
TokenDavid
Feature activation+1.075
Davis
Token Davis
Feature activation+0.248
and
Token and
Feature activation+0.000
Dominic
Token Dominic
Feature activation+1.347
Ra
Token Ra
Feature activation+0.019
ab
Tokenab
Feature activation+0.000
respectively
Token respectively
Feature activation+0.000
),
Token),
Feature activation+0.000
Stephen
Token Stephen
Feature activation+0.270
the
Token the
Feature activation+0.000
UK
Token UK
Feature activation+0.000
and
Token and
Feature activation+0.000
EU
Token EU
Feature activation+0.012
on
Token on
Feature activation+0.000
divorce
Token divorce
Feature activation+1.382
issues
Token issues
Feature activation+0.000
including
Token including
Feature activation+0.000
the
Token the
Feature activation+0.000
Irish
Token Irish
Feature activation+0.112
border
Token border
Feature activation+0.037
of
Token of
Feature activation+0.000
England
Token England
Feature activation+0.244
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.190
s
Tokens
Feature activation+0.000
exit
Token exit
Feature activation+1.399
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+0.112
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 1.120 - 1.259
CONTAINS 0.001%

MEP
Token MEP
Feature activation+0.276
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
EU
Token EU
Feature activation+0.266
member
Token member
Feature activation+1.178
states
Token states
Feature activation+0.000
and
Token and
Feature activation+0.000
Scotland
Token Scotland
Feature activation+0.194
rat
Token rat
Feature activation+0.000
ify
Tokenify
Feature activation+0.000
The
TokenThe
Feature activation+0.000
best
Token best
Feature activation+0.000
time
Token time
Feature activation+0.000
for
Token for
Feature activation+0.000
another
Token another
Feature activation+0.000
independence
Token independence
Feature activation+1.156
referendum
Token referendum
Feature activation+0.526
is
Token is
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
has
Token has
Feature activation+0.000
developed
Token developed
Feature activation+0.000
differently
Token differently
Feature activation+0.000
since
Token since
Feature activation+0.000
Old
Token Old
Feature activation+0.038
Sax
Token Sax
Feature activation+1.183
on
Tokenon
Feature activation+0.000
times
Token times
Feature activation+0.000
and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.000
lost
Token lost
Feature activation+0.000
which
Token which
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
referendum
Token referendum
Feature activation+0.801
on
Token on
Feature activation+0.000
independence
Token independence
Feature activation+1.239
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
rest
Token rest
Feature activation+0.148
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
democratically
Token democratically
Feature activation+0.000
elected
Token elected
Feature activation+0.000
governments
Token governments
Feature activation+0.000
of
Token of
Feature activation+0.000
EU
Token EU
Feature activation+0.000
member
Token member
Feature activation+1.192
states
Token states
Feature activation+0.000
are
Token are
Feature activation+0.000
making
Token making
Feature activation+0.000
it
Token it
Feature activation+0.000
harder
Token harder
Feature activation+0.000

INTERVAL 0.980 - 1.120
CONTAINS 0.002%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
want
Token want
Feature activation+0.000
another
Token another
Feature activation+0.000
independence
Token independence
Feature activation+1.087
referendum
Token referendum
Feature activation+0.513
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
solved
Token solved
Feature activation+0.000
by
Token by
Feature activation+0.000
Theresa
Token Theresa
Feature activation+0.713
May
Token May
Feature activation+0.843
triggering
Token triggering
Feature activation+1.043
article
Token article
Feature activation+1.011
50
Token 50
Feature activation+0.000
as
Token as
Feature activation+0.000
soon
Token soon
Feature activation+0.000
as
Token as
Feature activation+0.000
possible
Token possible
Feature activation+0.000
.
Token.
Feature activation+0.000
REUTERS
Token REUTERS
Feature activation+0.000
/
Token/
Feature activation+0.000
Y
TokenY
Feature activation+0.000
ves
Tokenves
Feature activation+0.052
Herman
Token Herman
Feature activation+1.062
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
her
Token her
Feature activation+0.000
attempts
Token attempts
Feature activation+0.000
even
Token even
Feature activation+0.000
better
Token better
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
full
Token full
Feature activation+0.000
member
Token member
Feature activation+0.984
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
lament
Token lament
Feature activation+0.000
ing
Tokening
Feature activation+0.000
the
Token the
Feature activation+0.000
consequences
Token consequences
Feature activation+0.219
of
Token of
Feature activation+0.000
migration
Token migration
Feature activation+0.981
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
continent
Token continent
Feature activation+0.784
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.840 - 0.980
CONTAINS 0.002%

border
Token border
Feature activation+0.000
control
Token control
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000
of
Token of
Feature activation+0.000
EU
Token EU
Feature activation+0.000
member
Token member
Feature activation+0.951
states
Token states
Feature activation+0.000
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
promote
Token promote
Feature activation+0.000
surveillance
Token surveillance
Feature activation+0.000
and
Token and
Feature activation+0.000
Scotland
Token Scotland
Feature activation+0.194
rat
Token rat
Feature activation+0.000
ify
Tokenify
Feature activation+0.000
the
Token the
Feature activation+0.000
treaty
Token treaty
Feature activation+0.840
of
Token of
Feature activation+0.000
asc
Token asc
Feature activation+0.222
ension
Tokenension
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
political
Token political
Feature activation+0.000
amalg
Token amalg
Feature activation+0.000
amation
Tokenamation
Feature activation+0.000
EU
Token EU
Feature activation+0.000
membership
Token membership
Feature activation+0.897
now
Token now
Feature activation+0.000
involves
Token involves
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ra
Token Ra
Feature activation+0.019
ab
Tokenab
Feature activation+0.000
respectively
Token respectively
Feature activation+0.000
),
Token),
Feature activation+0.000
Stephen
Token Stephen
Feature activation+0.270
Barcl
Token Barcl
Feature activation+0.926
ay
Tokenay
Feature activation+0.000
is
Token is
Feature activation+0.000
currently
Token currently
Feature activation+0.026
heading
Token heading
Feature activation+0.129
up
Token up
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
view
Token view
Feature activation+0.000
of
Token of
Feature activation+0.000
controlling
Token controlling
Feature activation+0.000
migration
Token migration
Feature activation+0.941
to
Token to
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.700 - 0.840
CONTAINS 0.002%

Scotland
Token Scotland
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
referendum
Token referendum
Feature activation+0.801
on
Token on
Feature activation+0.000
independence
Token independence
Feature activation+1.239
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
rest
Token rest
Feature activation+0.148
2
Token2
Feature activation+0.000
LO
TokenLO
Feature activation+0.000
In
Token In
Feature activation+0.000
14
Token 14
Feature activation+0.000
November
Token November
Feature activation+0.000
1922
Token 1922
Feature activation+0.776
.[
Token.[
Feature activation+0.000
8
Token8
Feature activation+0.000
]
Token]
Feature activation+0.000
W
Token W
Feature activation+0.000
ishing
Tokenishing
Feature activation+0.000
b
Tokenb
Feature activation+0.000
,
Token,
Feature activation+0.000
2009
Token 2009
Feature activation+0.000
)
Token)
Feature activation+0.000
in
Token in
Feature activation+0.000
Sard
Token Sard
Feature activation+0.708
inia
Tokeninia
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
,
Token,
Feature activation+0.000
Finland
Token Finland
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Fin
TokenFin
Feature activation+0.811
land
Tokenland
Feature activation+0.000
was
Token was
Feature activation+0.000
selected
Token selected
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
June
Token June
Feature activation+0.074
to
Token to
Feature activation+0.000
increase
Token increase
Feature activation+0.000
the
Token the
Feature activation+0.000
euro
Token euro
Feature activation+0.392
rescue
Token rescue
Feature activation+0.720
fund
Token fund
Feature activation+0.000
(
Token (
Feature activation+0.000
E
TokenE
Feature activation+0.000
FS
TokenFS
Feature activation+0.380
F
TokenF
Feature activation+0.000

INTERVAL 0.560 - 0.700
CONTAINS 0.005%

cannot
Token cannot
Feature activation+0.000
enc
Token enc
Feature activation+0.000
roach
Tokenroach
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
compet
Token compet
Feature activation+0.585
ences
Tokenences
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+0.028
".
Token".
Feature activation+0.000
member
Token member
Feature activation+0.894
states
Token states
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
European
Token European
Feature activation+0.000
Commission
Token Commission
Feature activation+0.623
will
Token will
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
consider
Token consider
Feature activation+0.000
enact
Token enact
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
never
Token never
Feature activation+0.000
signed
Token signed
Feature activation+0.000
the
Token the
Feature activation+0.000
Ma
Token Ma
Feature activation+0.628
ast
Tokenast
Feature activation+0.000
rich
Tokenrich
Feature activation+0.194
t
Tokent
Feature activation+0.000
Treaty
Token Treaty
Feature activation+1.010
either
Token either
Feature activation+0.000
late
Token late
Feature activation+0.000
draw
Token draw
Feature activation+0.000
at
Token at
Feature activation+0.000
TS
Token TS
Feature activation+0.234
G
TokenG
Feature activation+0.000
1899
Token 1899
Feature activation+0.667
Hoff
Token Hoff
Feature activation+0.000
en
Tokenen
Feature activation+0.000
heim
Tokenheim
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
there
Token there
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
vote
Token vote
Feature activation+0.000
for
Token for
Feature activation+0.000
independence
Token independence
Feature activation+0.665
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
has
Token has
Feature activation+0.000

INTERVAL 0.420 - 0.560
CONTAINS 0.008%

give
Token give
Feature activation+0.000
the
Token the
Feature activation+0.000
green
Token green
Feature activation+0.000
light
Token light
Feature activation+0.000
and
Token and
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.433
begin
Token begin
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
20
Token20
Feature activation+0.000
23
Token23
Feature activation+0.000
early
Token early
Feature activation+0.000
deal
Token deal
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Ang
TokenAng
Feature activation+0.451
ela
Tokenela
Feature activation+0.000
Merkel
Token Merkel
Feature activation+0.000
is
Token is
Feature activation+0.000
wrong
Token wrong
Feature activation+0.000
to
Token to
Feature activation+0.000
oking
Tokenoking
Feature activation+0.000
anx
Token anx
Feature activation+0.000
ieties
Tokenieties
Feature activation+0.000
over
Token over
Feature activation+0.000
absorbing
Token absorbing
Feature activation+0.000
refugees
Token refugees
Feature activation+0.441
across
Token across
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
their
Token their
Feature activation+0.000
response
Token response
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Dutch
Token Dutch
Feature activation+0.006
referendum
Token referendum
Feature activation+0.559
today
Token today
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
IG
TokenIG
Feature activation+0.479
Donald
Token Donald
Feature activation+0.015
France
Token France
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+0.263
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.551
s
Tokens
Feature activation+0.000
leading
Token leading
Feature activation+0.412
military
Token military
Feature activation+0.000
powers
Token powers
Feature activation+0.252
with
Token with
Feature activation+0.000

INTERVAL 0.280 - 0.420
CONTAINS 0.012%

Day
Token Day
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Thousands
TokenThousands
Feature activation+0.000
of
Token of
Feature activation+0.000
Catal
Token Catal
Feature activation+0.372
ans
Tokenans
Feature activation+0.000
have
Token have
Feature activation+0.000
rallied
Token rallied
Feature activation+0.000
in
Token in
Feature activation+0.000
Barcelona
Token Barcelona
Feature activation+0.000
difficulty
Token difficulty
Feature activation+0.000
recruiting
Token recruiting
Feature activation+0.000
volunteers
Token volunteers
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
riding
Token riding
Feature activation+0.344
level
Token level
Feature activation+0.000
.
Token.
Feature activation+0.000
Even
Token Even
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
stal
Token stal
Feature activation+0.000
in
Token in
Feature activation+0.000
great
Token great
Feature activation+0.000
secret
Token secret
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
NK
Token NK
Feature activation+0.407
VD
TokenVD
Feature activation+0.000
and
Token and
Feature activation+0.000
reb
Token reb
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
ied
Tokenied
Feature activation+0.000
Greek
Token Greek
Feature activation+0.000
β
Token β
Feature activation+0.000
Î
TokenÎ
Feature activation+0.000
®
Token®
Feature activation+0.000
Ïģ
TokenÏģ
Feature activation+0.000
Ï
TokenÏ
Feature activation+0.342
ħ
Tokenħ
Feature activation+0.000
λ
Tokenλ
Feature activation+0.135
λ
Tokenλ
Feature activation+0.138
ο
Tokenο
Feature activation+0.000
ÏĤ
TokenÏĤ
Feature activation+0.000
reaction
Token reaction
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
cry
Token cry
Feature activation+0.000
Lib
Token Lib
Feature activation+0.599
Lab
TokenLab
Feature activation+0.316
Con
TokenCon
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
allege
Token allege
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 0.140 - 0.280
CONTAINS 0.019%

allowance
Token allowance
Feature activation+0.000
.
Token.
Feature activation+0.000
Sir
Token Sir
Feature activation+0.137
Christopher
Token Christopher
Feature activation+0.066
's
Token's
Feature activation+0.000
inquiry
Token inquiry
Feature activation+0.240
,
Token,
Feature activation+0.000
set
Token set
Feature activation+0.000
up
Token up
Feature activation+0.000
by
Token by
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
College
Token College
Feature activation+0.000
of
Token of
Feature activation+0.000
Nursing
Token Nursing
Feature activation+0.000
and
Token and
Feature activation+0.000
NHS
Token NHS
Feature activation+0.000
England
Token England
Feature activation+0.158
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
said
Token said
Feature activation+0.000
of
Token of
Feature activation+0.000
Brexit
Token Brexit
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.777
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
EU
TokenEU
Feature activation+0.249
researchers
Token researchers
Feature activation+0.000
working
Token working
Feature activation+0.000
and
Token and
Feature activation+0.000
studying
Token studying
Feature activation+0.000
in
Token in
Feature activation+0.000
ca
Token ca
Feature activation+0.000
ust
Tokenust
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
Anglo
Token Anglo
Feature activation+0.000
-
Token-
Feature activation+0.000
Sax
TokenSax
Feature activation+0.177
on
Tokenon
Feature activation+0.000
wit
Token wit
Feature activation+0.000
st
Token st
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
.
Token.
Feature activation+0.000
water
Token water
Feature activation+0.000
charges
Token charges
Feature activation+0.000
.
Token.
Feature activation+0.000
Under
Token Under
Feature activation+0.000
D
Token D
Feature activation+0.000
á
Tokená
Feature activation+0.271
il
Tokenil
Feature activation+0.000
rules
Token rules
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Water
Token Water
Feature activation+0.000

INTERVAL 0.000 - 0.140
CONTAINS 99.950%

powerful
Token powerful
Feature activation+0.000
use
Token use
Feature activation+0.000
their
Token their
Feature activation+0.000
position
Token position
Feature activation+0.000
to
Token to
Feature activation+0.000
bully
Token bully
Feature activation+0.000
others
Token others
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
all
Token all
Feature activation+0.000
lose
Token lose
Feature activation+0.000
is
Token is
Feature activation+0.000
based
Token based
Feature activation+0.000
in
Token in
Feature activation+0.000
Lithuania
Token Lithuania
Feature activation+0.000
,
Token,
Feature activation+0.000
51
Token 51
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
Belarus
Token Belarus
Feature activation+0.000
ians
Tokenians
Feature activation+0.000
believe
Token believe
Feature activation+0.000
Arizona
Token Arizona
Feature activation+0.000
Football
Token Football
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
feed
Token feed
Feature activation+0.000
recently
Token recently
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
announcement
Token announcement
Feature activation+0.000
by
Token by
Feature activation+0.000
USC
Token USC
Feature activation+0.000
defensive
Token defensive
Feature activation+0.000
Gardens
Token Gardens
Feature activation+0.000
in
Token in
Feature activation+0.000
K
Token K
Feature activation+0.000
ew
Tokenew
Feature activation+0.000
,
Token,
Feature activation+0.000
Tony
Token Tony
Feature activation+0.000
Kirk
Token Kirk
Feature activation+0.000
ham
Tokenham
Feature activation+0.000
,
Token,
Feature activation+0.000
head
Token head
Feature activation+0.000
of
Token of
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
I
Token I
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
this
Token this
Feature activation+0.000
frog
Token frog
Feature activation+0.000
resting
Token resting
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
log
Token log
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