H11.10 top features

Top feature 0 in H11.10: (feature 4557)

TOP ACTIVATIONS
MAX = 8.559

at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
peak
Token peak
Feature activation+1.569
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
tenure
Token tenure
Feature activation+8.559
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
up
Token up
Feature activation+0.000
of
Token of
Feature activation+0.000
Germans
Token Germans
Feature activation+0.000
are
Token are
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
war
Token war
Feature activation+7.764
is
Token is
Feature activation+0.316
hardly
Token hardly
Feature activation+0.000
surprising
Token surprising
Feature activation+0.000
.
Token.
Feature activation+0.000
Who
Token Who
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
up
Token up
Feature activation+0.000
public
Token public
Feature activation+0.000
service
Token service
Feature activation+7.197
speaks
Token speaks
Feature activation+0.000
volumes
Token volumes
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
one
Tokenone
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
front
Token front
Feature activation+6.931
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
decimal
Token decimal
Feature activation+0.000
point
Token point
Feature activation+6.897
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
front
Token front
Feature activation+6.931
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
decimal
Token decimal
Feature activation+0.000
point
Token point
Feature activation+6.897
and
Token and
Feature activation+0.000
having
Token having
Feature activation+0.000
a
Token a
Feature activation+0.000
n
Token n
Feature activation+0.000
ought
Tokenought
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
locate
Token locate
Feature activation+0.000
in
Token in
Feature activation+0.000
our
Token our
Feature activation+0.000
community
Token community
Feature activation+6.720
speaks
Token speaks
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
strong
Token strong
Feature activation+0.000
work
Token work
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
hide
Token hide
Feature activation+0.000
it
Token it
Feature activation+6.309
soft
Token soft
Feature activation+0.000
ens
Tokenens
Feature activation+0.000
the
Token the
Feature activation+0.000
blow
Token blow
Feature activation+0.000
.
Token.
Feature activation+0.000
governments
Token governments
Feature activation+0.000
stay
Token stay
Feature activation+0.000
out
Token out
Feature activation+1.404
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
industry
Token industry
Feature activation+6.281
shows
Token shows
Feature activation+0.000
a
Token a
Feature activation+0.000
concerning
Token concerning
Feature activation+0.000
attitude
Token attitude
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
period
Token period
Feature activation+0.000
of
Token of
Feature activation+0.000
falling
Token falling
Feature activation+0.000
oil
Token oil
Feature activation+0.000
prices
Token prices
Feature activation+6.158
proves
Token proves
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
government
Token government
Feature activation+0.000
was
Token was
Feature activation+0.000
and
Token and
Feature activation+0.000
having
Token having
Feature activation+0.000
a
Token a
Feature activation+0.000
n
Token n
Feature activation+0.000
ought
Tokenought
Feature activation+0.000
instead
Token instead
Feature activation+6.013
may
Token may
Feature activation+0.400
weigh
Token weigh
Feature activation+0.000
with
Token with
Feature activation+0.000
some
Token some
Feature activation+0.000
people
Token people
Feature activation+0.000
the
Token the
Feature activation+0.000
Windows
Token Windows
Feature activation+0.000
Store
Token Store
Feature activation+5.638
in
Token in
Feature activation+0.000
late
Token late
Feature activation+0.000
October
Token October
Feature activation+5.979
2012
Token 2012
Feature activation+5.682
does
Token does
Feature activation+0.251
not
Token not
Feature activation+0.000
mean
Token mean
Feature activation+0.000
that
Token that
Feature activation+0.000
Windows
Token Windows
Feature activation+0.000
Store
Token Store
Feature activation+5.638
in
Token in
Feature activation+0.000
late
Token late
Feature activation+0.000
October
Token October
Feature activation+5.979
2012
Token 2012
Feature activation+5.682
does
Token does
Feature activation+0.251
not
Token not
Feature activation+0.000
mean
Token mean
Feature activation+0.000
that
Token that
Feature activation+0.000
Microsoft
Token Microsoft
Feature activation+0.000
be
Token be
Feature activation+0.000
available
Token available
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Windows
Token Windows
Feature activation+0.000
Store
Token Store
Feature activation+5.638
in
Token in
Feature activation+0.000
late
Token late
Feature activation+0.000
October
Token October
Feature activation+5.979
2012
Token 2012
Feature activation+5.682
does
Token does
Feature activation+0.251
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
Harry
Token Harry
Feature activation+0.000
was
Token was
Feature activation+0.000
still
Token still
Feature activation+0.000
there
Token there
Feature activation+5.502
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+0.000
anything
Token anything
Feature activation+0.000
during
Token during
Feature activation+0.000
a
Token a
Feature activation+0.000
given
Token given
Feature activation+0.000
build
Token build
Feature activation+0.773
phase
Token phase
Feature activation+5.120
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
playing
Token playing
Feature activation+0.000
Ireland
Token Ireland
Feature activation+1.185
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
group
Token group
Feature activation+0.000
stage
Token stage
Feature activation+4.112
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
it
Token it
Feature activation+0.000
week
Token week
Feature activation+0.212
to
Token to
Feature activation+0.000
watch
Token watch
Feature activation+0.000
the
Token the
Feature activation+0.000
candidates
Token candidates
Feature activation+0.000
perform
Token perform
Feature activation+4.032
shows
Token shows
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
support
Token support
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
is
Token is
Feature activation+0.000
critical
Token critical
Feature activation+2.594
for
Token for
Feature activation+0.000
survival
Token survival
Feature activation+4.030
suggests
Token suggests
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
this
Token this
Feature activation+0.000
music
Token music
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
goddamn
Token goddamn
Feature activation+0.000
good
Token good
Feature activation+3.778
makes
Token makes
Feature activation+0.000
watching
Token watching
Feature activation+0.000
this
Token this
Feature activation+0.000
band
Token band
Feature activation+0.000
an
Token an
Feature activation+0.000
the
Token the
Feature activation+0.000
province
Token province
Feature activation+0.000
recorded
Token recorded
Feature activation+0.000
a
Token a
Feature activation+0.000
hefty
Token hefty
Feature activation+0.000
surplus
Token surplus
Feature activation+3.740
during
Token during
Feature activation+0.000
a
Token a
Feature activation+0.000
period
Token period
Feature activation+0.000
of
Token of
Feature activation+0.000
falling
Token falling
Feature activation+0.000

Top DFA by src position
MAX = 9.950

to
Token to
Feature activation+0.008
Top resid features:
wider
Token wider
Feature activation+0.000
Top resid features:
society
Token society
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
The
Token The
Feature activation+0.024
Top resid features:
fact
Token fact
Feature activation+9.950
Top resid features:
that
Token that
Feature activation+0.034
Top resid features:
he
Token he
Feature activation+0.103
Top resid features:
âĢ
TokenâĢ
Feature activation-0.032
Top resid features:
Ļ
TokenĻ
Feature activation+0.023
Top resid features:
s
Tokens
Feature activation+0.063
Top resid features:
wrong
Token wrong
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
Ċ
TokenĊ
Feature activation+0.120
Top resid features:
Ċ
TokenĊ
Feature activation+0.034
Top resid features:
The
TokenThe
Feature activation+0.036
Top resid features:
fact
Token fact
Feature activation+8.919
Top resid features:
that
Token that
Feature activation+0.037
Top resid features:
a
Token a
Feature activation+0.013
Top resid features:
majority
Token majority
Feature activation-0.029
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
Germans
Token Germans
Feature activation+0.045
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
wider
Token wider
Feature activation-0.002
Top resid features:
society
Token society
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
The
Token The
Feature activation+0.011
Top resid features:
fact
Token fact
Feature activation+8.690
Top resid features:
that
Token that
Feature activation+0.030
Top resid features:
he
Token he
Feature activation+0.042
Top resid features:
âĢ
TokenâĢ
Feature activation+0.003
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
s
Tokens
Feature activation+0.055
Top resid features:
Ċ
TokenĊ
Feature activation+0.121
Top resid features:
Ċ
TokenĊ
Feature activation-0.025
Top resid features:
âĢ
TokenâĢ
Feature activation-0.006
Top resid features:
ĺ
Tokenĺ
Feature activation+0.021
Top resid features:
The
TokenThe
Feature activation+0.027
Top resid features:
fact
Token fact
Feature activation+8.316
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
longer
Token longer
Feature activation+0.021
Top resid features:
having
Token having
Feature activation+0.008
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.103
Top resid features:
Ċ
TokenĊ
Feature activation-0.017
Top resid features:
âĢ
TokenâĢ
Feature activation-0.016
Top resid features:
ĺ
Tokenĺ
Feature activation-0.002
Top resid features:
The
TokenThe
Feature activation+0.034
Top resid features:
fact
Token fact
Feature activation+8.595
Top resid features:
of
Token of
Feature activation+0.015
Top resid features:
no
Token no
Feature activation+0.001
Top resid features:
longer
Token longer
Feature activation+0.043
Top resid features:
having
Token having
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
am
Tokenam
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.063
Top resid features:
âĢ
Token âĢ
Feature activation-0.061
Top resid features:
ľ
Tokenľ
Feature activation+0.005
Top resid features:
The
TokenThe
Feature activation+0.122
Top resid features:
fact
Token fact
Feature activation+8.174
Top resid features:
that
Token that
Feature activation+0.141
Top resid features:
this
Token this
Feature activation+0.077
Top resid features:
international
Token international
Feature activation+0.028
Top resid features:
company
Token company
Feature activation+0.074
Top resid features:
has
Token has
Feature activation+0.155
Top resid features:
was
Token was
Feature activation+0.026
Top resid features:
a
Token a
Feature activation+0.007
Top resid features:
bad
Token bad
Feature activation-0.000
Top resid features:
person
Token person
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.068
Top resid features:
fact
Token fact
Feature activation+7.859
Top resid features:
that
Token that
Feature activation+0.030
Top resid features:
he
Token he
Feature activation+0.071
Top resid features:
doesn
Token doesn
Feature activation+0.032
Top resid features:
âĢ
TokenâĢ
Feature activation-0.082
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
We
Token We
Feature activation-0.003
Top resid features:
Medicine
Token Medicine
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.088
Top resid features:
says
Token says
Feature activation+0.087
Top resid features:
the
Token the
Feature activation+0.048
Top resid features:
fact
Token fact
Feature activation+7.605
Top resid features:
that
Token that
Feature activation+0.062
Top resid features:
some
Token some
Feature activation+0.009
Top resid features:
surrog
Token surrog
Feature activation+0.002
Top resid features:
acy
Tokenacy
Feature activation+0.010
Top resid features:
clients
Token clients
Feature activation+0.092
Top resid features:
Mc
Token Mc
Feature activation-0.001
Top resid features:
I
TokenI
Feature activation+0.001
Top resid features:
ver
Tokenver
Feature activation-0.003
Top resid features:
said
Token said
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
fact
Token fact
Feature activation+7.844
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
province
Token province
Feature activation+0.024
Top resid features:
recorded
Token recorded
Feature activation+0.024
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
hefty
Token hefty
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.080
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
ĺ
Tokenĺ
Feature activation+0.026
Top resid features:
The
TokenThe
Feature activation+0.022
Top resid features:
fact
Token fact
Feature activation+7.374
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
no
Token no
Feature activation-0.002
Top resid features:
longer
Token longer
Feature activation+0.021
Top resid features:
having
Token having
Feature activation+0.006
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
one
Token one
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.050
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
The
TokenThe
Feature activation+0.016
Top resid features:
fact
Token fact
Feature activation+7.547
Top resid features:
that
Token that
Feature activation+0.018
Top resid features:
this
Token this
Feature activation+0.020
Top resid features:
new
Token new
Feature activation+0.002
Top resid features:
Lyn
Token Lyn
Feature activation-0.001
Top resid features:
c
Tokenc
Feature activation+0.008
Top resid features:
one
Token one
Feature activation+0.006
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.051
Top resid features:
Ċ
TokenĊ
Feature activation-0.013
Top resid features:
The
TokenThe
Feature activation+0.016
Top resid features:
fact
Token fact
Feature activation+7.268
Top resid features:
that
Token that
Feature activation+0.018
Top resid features:
this
Token this
Feature activation+0.022
Top resid features:
new
Token new
Feature activation+0.004
Top resid features:
Lyn
Token Lyn
Feature activation-0.006
Top resid features:
c
Tokenc
Feature activation+0.005
Top resid features:
one
Token one
Feature activation-0.013
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.037
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
The
TokenThe
Feature activation+0.031
Top resid features:
fact
Token fact
Feature activation+7.262
Top resid features:
that
Token that
Feature activation+0.024
Top resid features:
this
Token this
Feature activation+0.027
Top resid features:
new
Token new
Feature activation+0.006
Top resid features:
Lyn
Token Lyn
Feature activation-0.010
Top resid features:
c
Tokenc
Feature activation+0.008
Top resid features:
prepared
Token prepared
Feature activation-0.004
Top resid features:
.)
Token.)
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.098
Top resid features:
Ċ
TokenĊ
Feature activation+0.076
Top resid features:
The
TokenThe
Feature activation+0.106
Top resid features:
fact
Token fact
Feature activation+6.838
Top resid features:
that
Token that
Feature activation+0.081
Top resid features:
Harry
Token Harry
Feature activation+0.029
Top resid features:
was
Token was
Feature activation+0.378
Top resid features:
still
Token still
Feature activation+0.106
Top resid features:
there
Token there
Feature activation+0.137
Top resid features:
moving
Token moving
Feature activation-0.016
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
However
Token However
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.069
Top resid features:
the
Token the
Feature activation+0.044
Top resid features:
fact
Token fact
Feature activation+6.910
Top resid features:
that
Token that
Feature activation+0.049
Top resid features:
only
Token only
Feature activation+0.016
Top resid features:
one
Token one
Feature activation+0.001
Top resid features:
(
Token (
Feature activation+0.009
Top resid features:
or
Tokenor
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.229
Top resid features:
The
TokenThe
Feature activation+0.159
Top resid features:
fact
Token fact
Feature activation+5.383
Top resid features:
we
Token we
Feature activation+0.098
Top resid features:
're
Token're
Feature activation+0.168
Top resid features:
playing
Token playing
Feature activation+0.110
Top resid features:
Ireland
Token Ireland
Feature activation+0.191
Top resid features:
in
Token in
Feature activation+0.122
Top resid features:
oz
Tokenoz
Feature activation+0.003
Top resid features:
in
Tokenin
Feature activation+0.003
Top resid features:
off
Tokenoff
Feature activation+0.013
Top resid features:
said
Token said
Feature activation+0.035
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
fact
Token fact
Feature activation+5.498
Top resid features:
that
Token that
Feature activation+0.042
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
many
Token many
Feature activation+0.005
Top resid features:
electors
Token electors
Feature activation+0.038
Top resid features:
are
Token are
Feature activation+0.087
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
influence
Token influence
Feature activation-0.009
Top resid features:
decisions
Token decisions
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.054
Top resid features:
The
Token The
Feature activation+0.019
Top resid features:
fact
Token fact
Feature activation+5.904
Top resid features:
that
Token that
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
âĢ
Token âĢ
Feature activation-0.038
Top resid features:
ľ
Tokenľ
Feature activation+0.003
Top resid features:
cour
Tokencour
Feature activation+0.006
Top resid features:
playing
Token playing
Feature activation+0.014
Top resid features:
music
Token music
Feature activation+0.012
Top resid features:
together
Token together
Feature activation+0.028
Top resid features:
and
Token and
Feature activation+0.123
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
fact
Token fact
Feature activation+5.438
Top resid features:
this
Token this
Feature activation+0.053
Top resid features:
music
Token music
Feature activation+0.021
Top resid features:
is
Token is
Feature activation+0.074
Top resid features:
so
Token so
Feature activation+0.005
Top resid features:
goddamn
Token goddamn
Feature activation+0.005
Top resid features:
Mc
Token Mc
Feature activation-0.001
Top resid features:
I
TokenI
Feature activation+0.001
Top resid features:
ver
Tokenver
Feature activation-0.001
Top resid features:
said
Token said
Feature activation-0.008
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
fact
Token fact
Feature activation+5.335
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
province
Token province
Feature activation+0.107
Top resid features:
recorded
Token recorded
Feature activation+0.081
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
hefty
Token hefty
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.03

Head 2: 0.03

Head 3: 0.04

Head 4: 0.04

Head 5: 0.03

Head 6: 0.02

Head 7: 0.04

Head 8: 0.12

Head 9: 0.02

Head 10: 0.48

Head 11: 0.09

Positive logits

shows3.40

mart3.29

indicates3.13

rings3.05

tells2.89

shows2.89

speaks2.85

suggests2.75

casts2.69

signaling2.65

ring2.64

2.60

milit2.56

Bars2.56

demonstrates2.55

Mund2.51

Ring2.50

warn2.50

proves2.49

lends2.47

Negative logits

Hobby-3.05

senal-2.90

hovah-2.71

Goals-2.71

Goal-2.64

-2.59

HER-2.50

ortality-2.45

Hatch-2.39

HAL-2.38

Hercules-2.38

Hera-2.38

Objective-2.38

ho-2.38

Theodore-2.37

ouk-2.36

Goal-2.36

Toby-2.35

Includes-2.35

eas-2.33

INTERVAL 7.703 - 8.559
CONTAINS 0.000%

of
Token of
Feature activation+0.000
Germans
Token Germans
Feature activation+0.000
are
Token are
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
war
Token war
Feature activation+7.764
is
Token is
Feature activation+0.316
hardly
Token hardly
Feature activation+0.000
surprising
Token surprising
Feature activation+0.000
.
Token.
Feature activation+0.000
Who
Token Who
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
peak
Token peak
Feature activation+1.569
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
tenure
Token tenure
Feature activation+8.559
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
up
Token up
Feature activation+0.000

INTERVAL 6.847 - 7.703
CONTAINS 0.000%

ľ
Tokenľ
Feature activation+0.000
one
Tokenone
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
front
Token front
Feature activation+6.931
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
decimal
Token decimal
Feature activation+0.000
point
Token point
Feature activation+6.897
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
front
Token front
Feature activation+6.931
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
decimal
Token decimal
Feature activation+0.000
point
Token point
Feature activation+6.897
and
Token and
Feature activation+0.000
having
Token having
Feature activation+0.000
a
Token a
Feature activation+0.000
n
Token n
Feature activation+0.000
ought
Tokenought
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
up
Token up
Feature activation+0.000
public
Token public
Feature activation+0.000
service
Token service
Feature activation+7.197
speaks
Token speaks
Feature activation+0.000
volumes
Token volumes
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 5.991 - 6.847
CONTAINS 0.001%

and
Token and
Feature activation+0.000
having
Token having
Feature activation+0.000
a
Token a
Feature activation+0.000
n
Token n
Feature activation+0.000
ought
Tokenought
Feature activation+0.000
instead
Token instead
Feature activation+6.013
may
Token may
Feature activation+0.400
weigh
Token weigh
Feature activation+0.000
with
Token with
Feature activation+0.000
some
Token some
Feature activation+0.000
people
Token people
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
hide
Token hide
Feature activation+0.000
it
Token it
Feature activation+6.309
soft
Token soft
Feature activation+0.000
ens
Tokenens
Feature activation+0.000
the
Token the
Feature activation+0.000
blow
Token blow
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
period
Token period
Feature activation+0.000
of
Token of
Feature activation+0.000
falling
Token falling
Feature activation+0.000
oil
Token oil
Feature activation+0.000
prices
Token prices
Feature activation+6.158
proves
Token proves
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
government
Token government
Feature activation+0.000
was
Token was
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
locate
Token locate
Feature activation+0.000
in
Token in
Feature activation+0.000
our
Token our
Feature activation+0.000
community
Token community
Feature activation+6.720
speaks
Token speaks
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
strong
Token strong
Feature activation+0.000
work
Token work
Feature activation+0.000
governments
Token governments
Feature activation+0.000
stay
Token stay
Feature activation+0.000
out
Token out
Feature activation+1.404
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
industry
Token industry
Feature activation+6.281
shows
Token shows
Feature activation+0.000
a
Token a
Feature activation+0.000
concerning
Token concerning
Feature activation+0.000
attitude
Token attitude
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 5.135 - 5.991
CONTAINS 0.000%

be
Token be
Feature activation+0.000
available
Token available
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Windows
Token Windows
Feature activation+0.000
Store
Token Store
Feature activation+5.638
in
Token in
Feature activation+0.000
late
Token late
Feature activation+0.000
October
Token October
Feature activation+5.979
2012
Token 2012
Feature activation+5.682
does
Token does
Feature activation+0.251
the
Token the
Feature activation+0.000
Windows
Token Windows
Feature activation+0.000
Store
Token Store
Feature activation+5.638
in
Token in
Feature activation+0.000
late
Token late
Feature activation+0.000
October
Token October
Feature activation+5.979
2012
Token 2012
Feature activation+5.682
does
Token does
Feature activation+0.251
not
Token not
Feature activation+0.000
mean
Token mean
Feature activation+0.000
that
Token that
Feature activation+0.000
Windows
Token Windows
Feature activation+0.000
Store
Token Store
Feature activation+5.638
in
Token in
Feature activation+0.000
late
Token late
Feature activation+0.000
October
Token October
Feature activation+5.979
2012
Token 2012
Feature activation+5.682
does
Token does
Feature activation+0.251
not
Token not
Feature activation+0.000
mean
Token mean
Feature activation+0.000
that
Token that
Feature activation+0.000
Microsoft
Token Microsoft
Feature activation+0.000
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000
Harry
Token Harry
Feature activation+0.000
was
Token was
Feature activation+0.000
still
Token still
Feature activation+0.000
there
Token there
Feature activation+5.502
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+0.000

INTERVAL 4.279 - 5.135
CONTAINS 0.000%

anything
Token anything
Feature activation+0.000
during
Token during
Feature activation+0.000
a
Token a
Feature activation+0.000
given
Token given
Feature activation+0.000
build
Token build
Feature activation+0.773
phase
Token phase
Feature activation+5.120
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000

INTERVAL 3.423 - 4.279
CONTAINS 0.001%

planning
Token planning
Feature activation+0.000
to
Token to
Feature activation+0.000
vote
Token vote
Feature activation+2.223
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
NDP
Token NDP
Feature activation+3.602
after
Token after
Feature activation+0.000
having
Token having
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
week
Token week
Feature activation+0.212
child
Token child
Feature activation+0.000
and
Token and
Feature activation+0.000
understands
Token understands
Feature activation+0.000
like
Token like
Feature activation+0.000
a
Token a
Feature activation+0.018
child
Token child
Feature activation+3.446
is
Token is
Feature activation+0.000
perfectly
Token perfectly
Feature activation+0.000
appropriate
Token appropriate
Feature activation+0.000
âĢ¦.
TokenâĢ¦.
Feature activation+0.000
To
Token To
Feature activation+0.000
this
Token this
Feature activation+0.000
music
Token music
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
goddamn
Token goddamn
Feature activation+0.000
good
Token good
Feature activation+3.778
makes
Token makes
Feature activation+0.000
watching
Token watching
Feature activation+0.000
this
Token this
Feature activation+0.000
band
Token band
Feature activation+0.000
an
Token an
Feature activation+0.000
week
Token week
Feature activation+0.212
to
Token to
Feature activation+0.000
watch
Token watch
Feature activation+0.000
the
Token the
Feature activation+0.000
candidates
Token candidates
Feature activation+0.000
perform
Token perform
Feature activation+4.032
shows
Token shows
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
NDP
Token NDP
Feature activation+0.000
support
Token support
Feature activation+0.000
the
Token the
Feature activation+0.000
province
Token province
Feature activation+0.000
recorded
Token recorded
Feature activation+0.000
a
Token a
Feature activation+0.000
hefty
Token hefty
Feature activation+0.000
surplus
Token surplus
Feature activation+3.740
during
Token during
Feature activation+0.000
a
Token a
Feature activation+0.000
period
Token period
Feature activation+0.000
of
Token of
Feature activation+0.000
falling
Token falling
Feature activation+0.000

INTERVAL 2.568 - 3.423
CONTAINS 0.000%

hip
Tokenhip
Feature activation+0.000
circuit
Token circuit
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
is
Token is
Feature activation+0.000
critical
Token critical
Feature activation+2.594
for
Token for
Feature activation+0.000
survival
Token survival
Feature activation+4.030
suggests
Token suggests
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
fact
Token fact
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.631
matter
Token matter
Feature activation+2.753
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
no
Token no
Feature activation+0.000
other
Token other
Feature activation+0.000
worker
Token worker
Feature activation+0.000
timing
Token timing
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
mountain
Token mountain
Feature activation+0.000
lion
Token lion
Feature activation+0.000
sighting
Token sighting
Feature activation+2.648
presents
Token presents
Feature activation+0.000
an
Token an
Feature activation+0.000
intriguing
Token intriguing
Feature activation+0.000
coincidence
Token coincidence
Feature activation+0.000
given
Token given
Feature activation+0.000

INTERVAL 1.712 - 2.568
CONTAINS 0.001%

electors
Token electors
Feature activation+0.000
are
Token are
Feature activation+0.000
still
Token still
Feature activation+0.000
planning
Token planning
Feature activation+0.000
to
Token to
Feature activation+0.000
vote
Token vote
Feature activation+2.223
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
NDP
Token NDP
Feature activation+3.602
after
Token after
Feature activation+0.000
having
Token having
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
cover
Token cover
Feature activation+0.000
fact
Token fact
Feature activation+0.000
-
Token-
Feature activation+1.729
checking
Tokenchecking
Feature activation+0.000
4
Token 4
Feature activation+0.000
million
Token million
Feature activation+0.000
articles
Token articles
Feature activation+0.000
.
Token.
Feature activation+0.000
next
Token next
Feature activation+0.000
29
Token 29
Feature activation+0.000
games
Token games
Feature activation+1.104
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
road
Token road
Feature activation+2.313
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
a
Token a
Feature activation+0.000
nine
Token nine
Feature activation+0.000
-
Token-
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
were
Token were
Feature activation+0.000
directly
Token directly
Feature activation+0.000
involved
Token involved
Feature activation+2.068
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
war
Tokenwar
Feature activation+0.724
details
Token details
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
March
Token March
Feature activation+0.000
4
Token 4
Feature activation+0.000
incident
Token incident
Feature activation+1.945
emerged
Token emerged
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
from
Token from
Feature activation+0.000
interviews
Token interviews
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.856 - 1.712
CONTAINS 0.003%

s
Tokens
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
BT
Token BT
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
peak
Token peak
Feature activation+1.569
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
tenure
Token tenure
Feature activation+8.559
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
they
Token they
Feature activation+0.000
believe
Token believe
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
truth
Token truth
Feature activation+0.000
will
Token will
Feature activation+1.542
win
Token win
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
Manafort
Token Manafort
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
work
Token work
Feature activation+1.076
in
Token in
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+1.698
appeared
Token appeared
Feature activation+0.000
to
Token to
Feature activation+0.054
concern
Token concern
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
either
Token either
Feature activation+0.000
straight
Token straight
Feature activation+0.000
or
Token or
Feature activation+0.000
gay
Token gay
Feature activation+0.874
is
Token is
Feature activation+0.000
pervasive
Token pervasive
Feature activation+0.000
and
Token and
Feature activation+0.000
persistent
Token persistent
Feature activation+0.000
,
Token,
Feature activation+0.000
ably
Tokenably
Feature activation+0.000
linked
Token linked
Feature activation+0.000
to
Token to
Feature activation+0.000
fossil
Token fossil
Feature activation+0.000
fuels
Token fuels
Feature activation+0.938
alone
Token alone
Feature activation+1.095
is
Token is
Feature activation+0.000
simply
Token simply
Feature activation+0.000
rubbish
Token rubbish
Feature activation+0.000
.
Token.
Feature activation+0.000
Period
Token Period
Feature activation+0.000

INTERVAL 0.000 - 0.856
CONTAINS 99.994%

The
Token The
Feature activation+0.000
Jerusalem
Token Jerusalem
Feature activation+0.000
Post
Token Post
Feature activation+0.000
than
Token than
Feature activation+0.000
ever
Token ever
Feature activation+0.000
before
Token before
Feature activation+0.000
.
Token.
Feature activation+0.000
Nevertheless
Token Nevertheless
Feature activation+0.000
,
Token,
Feature activation+0.000
traditional
Token traditional
Feature activation+0.000
business
Token business
Feature activation+0.000
beta
Token beta
Feature activation+0.000
and
Token and
Feature activation+0.000
release
Token release
Feature activation+0.000
combined
Token combined
Feature activation+0.000
.
Token.
Feature activation+0.000
During
Token During
Feature activation+0.000
all
Token all
Feature activation+0.000
this
Token this
Feature activation+0.000
time
Token time
Feature activation+0.000
playing
Token playing
Feature activation+0.000
the
Token the
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
a
Token a
Feature activation+0.000
reference
Token reference
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
victory
Token victory
Feature activation+0.000
over
Token over
Feature activation+0.000
Mexican
Token Mexican
Feature activation+0.000
troops
Token troops
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
map
Token map
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
you
Token you
Feature activation+0.000
use
Token use
Feature activation+0.000
a
Token a
Feature activation+0.000
throttle
Token throttle
Feature activation+0.000
to
Token to
Feature activation+0.000
set
Token set
Feature activation+0.000
your
Token your
Feature activation+0.000
has
Token has
Feature activation+0.000
also
Token also
Feature activation+0.000
incorporated
Token incorporated
Feature activation+0.000
recycled
Token recycled
Feature activation+0.000
plastics
Token plastics
Feature activation+0.000
,
Token,
Feature activation+0.000
renewable
Token renewable
Feature activation+0.000
raw
Token raw
Feature activation+0.000
materials
Token materials
Feature activation+0.000
,
Token,
Feature activation+0.000
natural
Token natural
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H11.10: (feature 8117)

TOP ACTIVATIONS
MAX = 5.813

at
Token at
Feature activation+0.000
NSA
Token NSA
Feature activation+0.000
reform
Token reform
Feature activation+5.480
on
Token on
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+5.813
this
Token this
Feature activation+0.000
year
Token year
Feature activation+5.322
have
Token have
Feature activation+3.430
been
Token been
Feature activation+0.000
slow
Token slow
Feature activation+0.000
enforcement
Token enforcement
Feature activation+0.000
staff
Token staff
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+5.496
obviously
Token obviously
Feature activation+3.884
reveals
Token reveals
Feature activation+0.000
that
Token that
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
lacks
Token lacks
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
attempts
Token attempts
Feature activation+0.000
at
Token at
Feature activation+0.000
NSA
Token NSA
Feature activation+0.000
reform
Token reform
Feature activation+5.480
on
Token on
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+5.813
this
Token this
Feature activation+0.000
year
Token year
Feature activation+5.322
reform
Token reform
Feature activation+5.480
on
Token on
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+5.813
this
Token this
Feature activation+0.000
year
Token year
Feature activation+5.322
have
Token have
Feature activation+3.430
been
Token been
Feature activation+0.000
slow
Token slow
Feature activation+0.000
going
Token going
Feature activation+0.000
.
Token.
Feature activation+0.000
serious
Token serious
Feature activation+0.000
efforts
Token efforts
Feature activation+0.285
to
Token to
Feature activation+0.000
regulate
Token regulate
Feature activation+0.000
disruptive
Token disruptive
Feature activation+0.000
technologies
Token technologies
Feature activation+4.763
have
Token have
Feature activation+2.648
traditionally
Token traditionally
Feature activation+2.575
been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.000
function
Token function
Feature activation+0.000
near
Token near
Feature activation+0.000
an
Token an
Feature activation+0.000
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
Qaeda
TokenQaeda
Feature activation+0.000
compound
Token compound
Feature activation+4.265
were
Token were
Feature activation+0.000
handled
Token handled
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
CIA
Token CIA
Feature activation+0.000
to
Token to
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
stakes
Token stakes
Feature activation+2.405
in
Token in
Feature activation+0.000
talks
Token talks
Feature activation+4.156
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+1.346
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
Daily
Token Daily
Feature activation+0.000
Dot
Token Dot
Feature activation+2.595
to
Token to
Feature activation+0.000
contact
Token contact
Feature activation+0.000
the
Token the
Feature activation+0.000
foundation
Token foundation
Feature activation+4.143
went
Token went
Feature activation+0.000
unanswered
Token unanswered
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
received
Token received
Feature activation+2.271
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
police
Token police
Feature activation+0.000
control
Token control
Feature activation+0.000
room
Token room
Feature activation+4.065
had
Token had
Feature activation+1.336
not
Token not
Feature activation+0.966
been
Token been
Feature activation+0.000
logged
Token logged
Feature activation+0.000
correctly
Token correctly
Feature activation+0.002
staff
Token staff
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+5.496
obviously
Token obviously
Feature activation+3.884
reveals
Token reveals
Feature activation+0.000
that
Token that
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
lacks
Token lacks
Feature activation+0.000
sincerity
Token sincerity
Feature activation+0.000
fallen
Token fallen
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
soldier
Token soldier
Feature activation+3.690
whose
Token whose
Feature activation+0.000
father
Token father
Feature activation+0.000
spoke
Token spoke
Feature activation+0.000
out
Token out
Feature activation+0.481
against
Token against
Feature activation+0.000
ments
Tokenments
Feature activation+0.000
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+0.000
calls
Token calls
Feature activation+0.224
for
Token for
Feature activation+0.000
certainty
Token certainty
Feature activation+3.682
have
Token have
Feature activation+2.200
grown
Token grown
Feature activation+0.000
increasingly
Token increasingly
Feature activation+0.000
urgent
Token urgent
Feature activation+0.000
as
Token as
Feature activation+0.000
whose
Token whose
Feature activation+0.000
father
Token father
Feature activation+0.000
spoke
Token spoke
Feature activation+0.000
out
Token out
Feature activation+0.481
against
Token against
Feature activation+0.000
him
Token him
Feature activation+3.663
at
Token at
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
's
Token's
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
calls
Token calls
Feature activation+0.332
for
Token for
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
president
Token president
Feature activation+3.657
are
Token are
Feature activation+0.529
nothing
Token nothing
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
an
Token an
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
's
Token's
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
National
Token National
Feature activation+0.000
Convention
Token Convention
Feature activation+3.601
were
Token were
Feature activation+0.000
"
Token "
Feature activation+0.000
blown
Tokenblown
Feature activation+0.000
hugely
Token hugely
Feature activation+0.000
out
Token out
Feature activation+0.000
on
Token on
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+5.813
this
Token this
Feature activation+0.000
year
Token year
Feature activation+5.322
have
Token have
Feature activation+3.430
been
Token been
Feature activation+0.000
slow
Token slow
Feature activation+0.000
going
Token going
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
spokesman
Token spokesman
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Interior
Token Interior
Feature activation+0.000
Ministry
Token Ministry
Feature activation+0.000
,
Token,
Feature activation+3.429
were
Token were
Feature activation+0.000
met
Token met
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
busy
Token busy
Feature activation+0.000
comments
Token comments
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
Gold
Token Gold
Feature activation+0.000
Star
Token Star
Feature activation+0.000
family
Token family
Feature activation+3.372
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
fallen
Token fallen
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
Police
TokenPolice
Feature activation+0.000
said
Token said
Feature activation+0.000
protests
Token protests
Feature activation+0.096
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
plaza
Token plaza
Feature activation+3.365
were
Token were
Feature activation+0.000
mostly
Token mostly
Feature activation+0.000
peaceful
Token peaceful
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.899
encounter
Token encounter
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
barrier
Token barrier
Feature activation+0.000
described
Token described
Feature activation+0.000
above
Token above
Feature activation+3.338
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
objects
Token objects
Feature activation+0.000
typically
Token typically
Feature activation+0.000
possess
Token possess
Feature activation+0.000

Top DFA by src position
MAX = 6.914

âĢ
TokenâĢ
Feature activation+0.064
Top resid features:
Ŀ
TokenĿ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.079
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
But
TokenBut
Feature activation+0.083
Top resid features:
attempts
Token attempts
Feature activation+6.657
Top resid features:
at
Token at
Feature activation+0.029
Top resid features:
NSA
Token NSA
Feature activation+0.009
Top resid features:
reform
Token reform
Feature activation+0.349
Top resid features:
on
Token on
Feature activation+0.048
Top resid features:
Capitol
Token Capitol
Feature activation+0.004
Top resid features:
news
Token news
Feature activation-0.007
Top resid features:
wire
Token wire
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
said
Token said
Feature activation-0.003
Top resid features:
US
Token US
Feature activation+0.002
Top resid features:
attempts
Token attempts
Feature activation+6.914
Top resid features:
âĢ
Token âĢ
Feature activation+0.109
Top resid features:
ľ
Tokenľ
Feature activation+0.042
Top resid features:
to
Tokento
Feature activation+0.022
Top resid features:
force
Token force
Feature activation+0.005
Top resid features:
China
Token China
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.052
Top resid features:
Ŀ
TokenĿ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.131
Top resid features:
Ċ
TokenĊ
Feature activation+0.071
Top resid features:
But
TokenBut
Feature activation+0.085
Top resid features:
attempts
Token attempts
Feature activation+6.625
Top resid features:
at
Token at
Feature activation+0.047
Top resid features:
NSA
Token NSA
Feature activation+0.027
Top resid features:
reform
Token reform
Feature activation+0.278
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Capitol
Token Capitol
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.041
Top resid features:
Ŀ
TokenĿ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.063
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
But
TokenBut
Feature activation+0.054
Top resid features:
attempts
Token attempts
Feature activation+5.952
Top resid features:
at
Token at
Feature activation+0.033
Top resid features:
NSA
Token NSA
Feature activation+0.013
Top resid features:
reform
Token reform
Feature activation+0.412
Top resid features:
on
Token on
Feature activation+0.032
Top resid features:
Capitol
Token Capitol
Feature activation+0.004
Top resid features:
ľ
Tokenľ
Feature activation+0.080
Top resid features:
In
TokenIn
Feature activation+0.068
Top resid features:
fact
Token fact
Feature activation+0.038
Top resid features:
,
Token,
Feature activation+0.100
Top resid features:
serious
Token serious
Feature activation+0.059
Top resid features:
efforts
Token efforts
Feature activation+5.965
Top resid features:
to
Token to
Feature activation+0.127
Top resid features:
regulate
Token regulate
Feature activation+0.142
Top resid features:
disruptive
Token disruptive
Feature activation+0.076
Top resid features:
technologies
Token technologies
Feature activation+0.391
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
based
Token based
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
âĢ¦
Token âĢ¦
Feature activation+0.034
Top resid features:
Surveillance
Token Surveillance
Feature activation+0.140
Top resid features:
operations
Token operations
Feature activation+5.180
Top resid features:
that
Token that
Feature activation+0.404
Top resid features:
required
Token required
Feature activation+0.023
Top resid features:
placing
Token placing
Feature activation+0.019
Top resid features:
a
Token a
Feature activation+0.010
Top resid features:
device
Token device
Feature activation+0.136
Top resid features:
Herman
Token Herman
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
But
TokenBut
Feature activation+0.096
Top resid features:
her
Token her
Feature activation+0.013
Top resid features:
attempts
Token attempts
Feature activation+5.045
Top resid features:
to
Token to
Feature activation+0.030
Top resid features:
up
Token up
Feature activation-0.031
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
stakes
Token stakes
Feature activation+0.306
Top resid features:
in
Token in
Feature activation+0.033
Top resid features:
on
Token on
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
site
Token site
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Multiple
Token Multiple
Feature activation+0.015
Top resid features:
attempts
Token attempts
Feature activation+5.518
Top resid features:
by
Token by
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.038
Top resid features:
Daily
Token Daily
Feature activation+0.006
Top resid features:
Dot
Token Dot
Feature activation+0.076
Top resid features:
to
Token to
Feature activation+0.041
Top resid features:
rett
Tokenrett
Feature activation+0.002
Top resid features:
ably
Tokenably
Feature activation+0.009
Top resid features:
âĢ
TokenâĢ
Feature activation+0.076
Top resid features:
Ŀ
TokenĿ
Feature activation+0.028
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
calls
Token calls
Feature activation+4.116
Top resid features:
received
Token received
Feature activation+1.059
Top resid features:
at
Token at
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
police
Token police
Feature activation+0.001
Top resid features:
control
Token control
Feature activation-0.004
Top resid features:
news
Token news
Feature activation+0.001
Top resid features:
wire
Token wire
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
said
Token said
Feature activation+0.017
Top resid features:
US
Token US
Feature activation+0.006
Top resid features:
attempts
Token attempts
Feature activation+4.859
Top resid features:
âĢ
Token âĢ
Feature activation+0.164
Top resid features:
ľ
Tokenľ
Feature activation+0.039
Top resid features:
to
Tokento
Feature activation+0.029
Top resid features:
force
Token force
Feature activation+0.002
Top resid features:
China
Token China
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.172
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Donald
TokenDonald
Feature activation-0.007
Top resid features:
Trump
Token Trump
Feature activation-0.011
Top resid features:
's
Token's
Feature activation+0.008
Top resid features:
comments
Token comments
Feature activation+5.071
Top resid features:
about
Token about
Feature activation+0.090
Top resid features:
the
Token the
Feature activation+0.047
Top resid features:
Gold
Token Gold
Feature activation-0.007
Top resid features:
Star
Token Star
Feature activation+0.006
Top resid features:
family
Token family
Feature activation+0.331
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
pay
Tokenpay
Feature activation+0.015
Top resid features:
ments
Tokenments
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.108
Top resid features:
Their
Token Their
Feature activation+0.022
Top resid features:
calls
Token calls
Feature activation+5.239
Top resid features:
for
Token for
Feature activation+0.009
Top resid features:
certainty
Token certainty
Feature activation+0.418
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
grown
Token grown
Feature activation+0.000
Top resid features:
increasingly
Token increasingly
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.126
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Donald
TokenDonald
Feature activation-0.000
Top resid features:
Trump
Token Trump
Feature activation-0.026
Top resid features:
's
Token's
Feature activation+0.016
Top resid features:
comments
Token comments
Feature activation+5.260
Top resid features:
about
Token about
Feature activation+0.036
Top resid features:
the
Token the
Feature activation+0.028
Top resid features:
Gold
Token Gold
Feature activation-0.007
Top resid features:
Star
Token Star
Feature activation+0.001
Top resid features:
family
Token family
Feature activation+0.220
Top resid features:
Ċ
TokenĊ
Feature activation+0.057
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ren
TokenRen
Feature activation+0.001
Top resid features:
ew
Tokenew
Feature activation+0.004
Top resid features:
ed
Tokened
Feature activation+0.042
Top resid features:
calls
Token calls
Feature activation+5.089
Top resid features:
for
Token for
Feature activation+0.041
Top resid features:
Clinton
Token Clinton
Feature activation+0.036
Top resid features:
to
Token to
Feature activation+0.021
Top resid features:
be
Token be
Feature activation-0.002
Top resid features:
president
Token president
Feature activation+0.061
Top resid features:
Ċ
TokenĊ
Feature activation+0.058
Top resid features:
Ċ
TokenĊ
Feature activation-0.018
Top resid features:
Donald
TokenDonald
Feature activation-0.014
Top resid features:
Trump
Token Trump
Feature activation-0.025
Top resid features:
's
Token's
Feature activation+0.008
Top resid features:
comments
Token comments
Feature activation+5.066
Top resid features:
about
Token about
Feature activation+0.035
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
Gold
Token Gold
Feature activation-0.004
Top resid features:
Star
Token Star
Feature activation+0.002
Top resid features:
family
Token family
Feature activation+0.264
Top resid features:
âĢ
TokenâĢ
Feature activation+0.017
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.034
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
But
TokenBut
Feature activation+0.053
Top resid features:
attempts
Token attempts
Feature activation+3.423
Top resid features:
at
Token at
Feature activation+0.050
Top resid features:
NSA
Token NSA
Feature activation+0.014
Top resid features:
reform
Token reform
Feature activation+0.213
Top resid features:
on
Token on
Feature activation+0.036
Top resid features:
Capitol
Token Capitol
Feature activation+0.006
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.025
Top resid features:
comment
Token comment
Feature activation+0.099
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
Telephone
Token Telephone
Feature activation+0.187
Top resid features:
attempts
Token attempts
Feature activation+3.807
Top resid features:
to
Token to
Feature activation+0.143
Top resid features:
reach
Token reach
Feature activation+0.133
Top resid features:
Ali
Token Ali
Feature activation+0.088
Top resid features:
Oz
Token Oz
Feature activation-0.003
Top resid features:
tur
Tokentur
Feature activation+0.033
Top resid features:
Ċ
TokenĊ
Feature activation+0.154
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Donald
TokenDonald
Feature activation+0.009
Top resid features:
Trump
Token Trump
Feature activation-0.007
Top resid features:
's
Token's
Feature activation+0.015
Top resid features:
comments
Token comments
Feature activation+4.924
Top resid features:
about
Token about
Feature activation+0.062
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
Gold
Token Gold
Feature activation-0.029
Top resid features:
Star
Token Star
Feature activation-0.014
Top resid features:
family
Token family
Feature activation+0.057
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.060
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Police
TokenPolice
Feature activation+0.039
Top resid features:
said
Token said
Feature activation+0.024
Top resid features:
protests
Token protests
Feature activation+4.948
Top resid features:
at
Token at
Feature activation+0.033
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
plaza
Token plaza
Feature activation+0.188
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
mostly
Token mostly
Feature activation+0.000
Top resid features:
ubes
Tokenubes
Feature activation-0.015
Top resid features:
cent
Tokencent
Feature activation-0.002
Top resid features:
individual
Token individual
Feature activation+0.028
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
although
Token although
Feature activation+0.063
Top resid features:
attempts
Token attempts
Feature activation+4.897
Top resid features:
by
Token by
Feature activation+0.064
Top resid features:
pub
Token pub
Feature activation+0.000
Top resid features:
escent
Tokenescent
Feature activation-0.005
Top resid features:
or
Token or
Feature activation+0.004
Top resid features:
post
Token post
Feature activation+0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.03

Head 2: 0.04

Head 3: 0.05

Head 4: 0.04

Head 5: 0.04

Head 6: 0.03

Head 7: 0.04

Head 8: 0.11

Head 9: 0.03

Head 10: 0.40

Head 11: 0.10

Positive logits

failed2.52

fail2.48

Zup2.39

ADRA2.31

were2.28

paralle2.26

Mecca2.24

Brach2.21

have2.21

Fenrir2.18

ric2.15

have2.14

weren2.11

Parenthood2.09

originate2.07

Dynamo2.07

haven2.06

dracon2.06

Cro2.04

include2.04

Negative logits

Flavoring-3.17

quickShipAvailable-2.78

vote-2.73

adjusts-2.58

watches-2.50

reacts-2.43

SHARE-2.30

develops-2.30

objects-2.26

behaves-2.26

advert-2.25

expression-2.25

Reviewer-2.24

performs-2.21

negoti-2.21

expression-2.18

predicts-2.16

interacts-2.15

remembers-2.13

Motion-2.13

INTERVAL 5.232 - 5.813
CONTAINS 0.000%

enforcement
Token enforcement
Feature activation+0.000
staff
Token staff
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+5.496
obviously
Token obviously
Feature activation+3.884
reveals
Token reveals
Feature activation+0.000
that
Token that
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
lacks
Token lacks
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
attempts
Token attempts
Feature activation+0.000
at
Token at
Feature activation+0.000
NSA
Token NSA
Feature activation+0.000
reform
Token reform
Feature activation+5.480
on
Token on
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+5.813
this
Token this
Feature activation+0.000
year
Token year
Feature activation+5.322
at
Token at
Feature activation+0.000
NSA
Token NSA
Feature activation+0.000
reform
Token reform
Feature activation+5.480
on
Token on
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+5.813
this
Token this
Feature activation+0.000
year
Token year
Feature activation+5.322
have
Token have
Feature activation+3.430
been
Token been
Feature activation+0.000
slow
Token slow
Feature activation+0.000
reform
Token reform
Feature activation+5.480
on
Token on
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+5.813
this
Token this
Feature activation+0.000
year
Token year
Feature activation+5.322
have
Token have
Feature activation+3.430
been
Token been
Feature activation+0.000
slow
Token slow
Feature activation+0.000
going
Token going
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 4.650 - 5.232
CONTAINS 0.000%

serious
Token serious
Feature activation+0.000
efforts
Token efforts
Feature activation+0.285
to
Token to
Feature activation+0.000
regulate
Token regulate
Feature activation+0.000
disruptive
Token disruptive
Feature activation+0.000
technologies
Token technologies
Feature activation+4.763
have
Token have
Feature activation+2.648
traditionally
Token traditionally
Feature activation+2.575
been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.000
function
Token function
Feature activation+0.000

INTERVAL 4.069 - 4.650
CONTAINS 0.000%

to
Token to
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
stakes
Token stakes
Feature activation+2.405
in
Token in
Feature activation+0.000
talks
Token talks
Feature activation+4.156
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+1.346
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
near
Token near
Feature activation+0.000
an
Token an
Feature activation+0.000
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
Qaeda
TokenQaeda
Feature activation+0.000
compound
Token compound
Feature activation+4.265
were
Token were
Feature activation+0.000
handled
Token handled
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
CIA
Token CIA
Feature activation+0.000
Daily
Token Daily
Feature activation+0.000
Dot
Token Dot
Feature activation+2.595
to
Token to
Feature activation+0.000
contact
Token contact
Feature activation+0.000
the
Token the
Feature activation+0.000
foundation
Token foundation
Feature activation+4.143
went
Token went
Feature activation+0.000
unanswered
Token unanswered
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.488 - 4.069
CONTAINS 0.001%

ments
Tokenments
Feature activation+0.000
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+0.000
calls
Token calls
Feature activation+0.224
for
Token for
Feature activation+0.000
certainty
Token certainty
Feature activation+3.682
have
Token have
Feature activation+2.200
grown
Token grown
Feature activation+0.000
increasingly
Token increasingly
Feature activation+0.000
urgent
Token urgent
Feature activation+0.000
as
Token as
Feature activation+0.000
received
Token received
Feature activation+2.271
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
police
Token police
Feature activation+0.000
control
Token control
Feature activation+0.000
room
Token room
Feature activation+4.065
had
Token had
Feature activation+1.336
not
Token not
Feature activation+0.966
been
Token been
Feature activation+0.000
logged
Token logged
Feature activation+0.000
correctly
Token correctly
Feature activation+0.002
whose
Token whose
Feature activation+0.000
father
Token father
Feature activation+0.000
spoke
Token spoke
Feature activation+0.000
out
Token out
Feature activation+0.481
against
Token against
Feature activation+0.000
him
Token him
Feature activation+3.663
at
Token at
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
's
Token's
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
staff
Token staff
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+5.496
obviously
Token obviously
Feature activation+3.884
reveals
Token reveals
Feature activation+0.000
that
Token that
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
lacks
Token lacks
Feature activation+0.000
sincerity
Token sincerity
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
's
Token's
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
National
Token National
Feature activation+0.000
Convention
Token Convention
Feature activation+3.601
were
Token were
Feature activation+0.000
"
Token "
Feature activation+0.000
blown
Tokenblown
Feature activation+0.000
hugely
Token hugely
Feature activation+0.000
out
Token out
Feature activation+0.000

INTERVAL 2.907 - 3.488
CONTAINS 0.001%

encounter
Token encounter
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
barrier
Token barrier
Feature activation+0.000
described
Token described
Feature activation+0.000
above
Token above
Feature activation+3.338
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
objects
Token objects
Feature activation+0.000
typically
Token typically
Feature activation+0.000
possess
Token possess
Feature activation+0.000
on
Token on
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+5.813
this
Token this
Feature activation+0.000
year
Token year
Feature activation+5.322
have
Token have
Feature activation+3.430
been
Token been
Feature activation+0.000
slow
Token slow
Feature activation+0.000
going
Token going
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
spokesman
Token spokesman
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Interior
Token Interior
Feature activation+0.000
Ministry
Token Ministry
Feature activation+0.000
,
Token,
Feature activation+3.429
were
Token were
Feature activation+0.000
met
Token met
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
busy
Token busy
Feature activation+0.000
Police
TokenPolice
Feature activation+0.000
said
Token said
Feature activation+0.000
protests
Token protests
Feature activation+0.096
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
plaza
Token plaza
Feature activation+3.365
were
Token were
Feature activation+0.000
mostly
Token mostly
Feature activation+0.000
peaceful
Token peaceful
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.899
negotiations
Token negotiations
Feature activation+0.902
taking
Token taking
Feature activation+0.000
place
Token place
Feature activation+2.088
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
issue
Token issue
Feature activation+3.286
between
Token between
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+0.938

INTERVAL 2.325 - 2.907
CONTAINS 0.003%

to
Token to
Feature activation+0.000
regulate
Token regulate
Feature activation+0.000
disruptive
Token disruptive
Feature activation+0.000
technologies
Token technologies
Feature activation+4.763
have
Token have
Feature activation+2.648
traditionally
Token traditionally
Feature activation+2.575
been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.000
function
Token function
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
specifically
Token specifically
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
defense
Token defense
Feature activation+0.000
industry
Token industry
Feature activation+2.825
suggest
Token suggest
Feature activation+0.000
the
Token the
Feature activation+0.000
group
Token group
Feature activation+0.000
is
Token is
Feature activation+0.000
working
Token working
Feature activation+0.000
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
one
Token one
Feature activation+0.000
against
Token against
Feature activation+0.000
North
Token North
Feature activation+0.000
Korea
Token Korea
Feature activation+2.364
were
Token were
Feature activation+0.000
the
Token the
Feature activation+0.000
norm
Token norm
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
name
Token name
Feature activation+0.000
of
Token of
Feature activation+0.000
religious
Token religious
Feature activation+0.000
liberty
Token liberty
Feature activation+2.746
are
Token are
Feature activation+0.000
very
Token very
Feature activation+0.000
much
Token much
Feature activation+0.000
alive
Token alive
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
attempts
Token attempts
Feature activation+0.000
to
Token to
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
stakes
Token stakes
Feature activation+2.405
in
Token in
Feature activation+0.000
talks
Token talks
Feature activation+4.156
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+1.346

INTERVAL 1.744 - 2.325
CONTAINS 0.006%

r
Tokenr
Feature activation+0.000
ze
Tokenze
Feature activation+0.000
jc
Tokenjc
Feature activation+0.000
zyk
Tokenzyk
Feature activation+1.679
Saturday
Token Saturday
Feature activation+1.942
afternoon
Token afternoon
Feature activation+1.871
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
clock
Token clock
Feature activation+0.000
ticking
Token ticking
Feature activation+0.000
down
Token down
Feature activation+0.994
attempts
Token attempts
Feature activation+0.000
to
Token to
Feature activation+0.000
enforce
Token enforce
Feature activation+0.000
this
Token this
Feature activation+0.000
unconstitutional
Token unconstitutional
Feature activation+0.000
ban
Token ban
Feature activation+1.987
have
Token have
Feature activation+0.122
taken
Token taken
Feature activation+0.000
a
Token a
Feature activation+0.000
tremendous
Token tremendous
Feature activation+0.000
toll
Token toll
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Police
TokenPolice
Feature activation+0.000
investigations
Token investigations
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
matter
Token matter
Feature activation+2.016
are
Token are
Feature activation+0.000
continuing
Token continuing
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
officers
Token officers
Feature activation+0.000
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+0.000
calls
Token calls
Feature activation+0.224
for
Token for
Feature activation+0.000
certainty
Token certainty
Feature activation+3.682
have
Token have
Feature activation+2.200
grown
Token grown
Feature activation+0.000
increasingly
Token increasingly
Feature activation+0.000
urgent
Token urgent
Feature activation+0.000
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
tools
Token tools
Feature activation+0.000
available
Token available
Feature activation+0.000
to
Token to
Feature activation+0.000
them
Token them
Feature activation+2.044
are
Token are
Feature activation+0.000
limited
Token limited
Feature activation+0.000
.
Token.
Feature activation+0.000
Though
Token Though
Feature activation+0.000
there
Token there
Feature activation+0.000

INTERVAL 1.163 - 1.744
CONTAINS 0.013%

made
Token made
Feature activation+0.000
by
Token by
Feature activation+0.000
everyone
Token everyone
Feature activation+0.889
during
Token during
Feature activation+0.000
this
Token this
Feature activation+0.000
time
Token time
Feature activation+1.260
have
Token have
Feature activation+2.061
been
Token been
Feature activation+0.491
answered
Token answered
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
questions
Token questions
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
the
Token the
Feature activation+0.000
attack
Token attack
Feature activation+1.274
on
Token on
Feature activation+0.000
Benghazi
Token Benghazi
Feature activation+1.281
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
failure
Token failure
Feature activation+0.000
attacks
Token attacks
Feature activation+0.037
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
shootings
Token shootings
Feature activation+0.335
by
Token by
Feature activation+0.000
Palestinians
Token Palestinians
Feature activation+1.191
targeting
Token targeting
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
civilians
Token civilians
Feature activation+1.356
âĢĵ
Token âĢĵ
Feature activation+0.000
all
Token all
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
at
Token at
Feature activation+0.000
its
Token its
Feature activation+0.000
own
Token own
Feature activation+0.000
mobile
Token mobile
Feature activation+0.000
wallet
Token wallet
Feature activation+1.220
application
Token application
Feature activation+1.145
,
Token,
Feature activation+0.000
designed
Token designed
Feature activation+0.000
for
Token for
Feature activation+0.000
use
Token use
Feature activation+0.000
started
Token started
Feature activation+0.181
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Sydney
Token Sydney
Feature activation+0.000
Harbour
Token Harbour
Feature activation+0.000
Bridge
Token Bridge
Feature activation+1.456
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
general
Token general
Feature activation+0.000

INTERVAL 0.581 - 1.163
CONTAINS 0.025%

push
Token push
Feature activation+0.000
ups
Tokenups
Feature activation+0.049
or
Token or
Feature activation+0.000
triangle
Token triangle
Feature activation+0.000
push
Token push
Feature activation+0.000
ups
Tokenups
Feature activation+0.679
will
Token will
Feature activation+0.000
work
Token work
Feature activation+0.000
primarily
Token primarily
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
unimaginable
Token unimaginable
Feature activation+0.000
.
Token.
Feature activation+0.000
Though
Token Though
Feature activation+0.000
the
Token the
Feature activation+0.000
comments
Token comments
Feature activation+0.559
have
Token have
Feature activation+0.598
been
Token been
Feature activation+0.000
taken
Token taken
Feature activation+0.000
down
Token down
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
Payne
Token Payne
Feature activation+0.000
and
Token and
Feature activation+0.000
Lt
Token Lt
Feature activation+0.000
.
Token.
Feature activation+0.000
James
Token James
Feature activation+0.000
Tracy
Token Tracy
Feature activation+0.872
following
Token following
Feature activation+0.000
Payne
Token Payne
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
meantime
Token meantime
Feature activation+0.000
,
Token,
Feature activation+0.000
talks
Token talks
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
stranger
Token stranger
Feature activation+0.753
who
Token who
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
devil
Token devil
Feature activation+0.000
.
Token.
Feature activation+0.000
Sc
Token Sc
Feature activation+0.000
uff
Tokenuff
Feature activation+0.000
les
Tokenles
Feature activation+0.000
between
Token between
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.778
forced
Token forced
Feature activation+0.000
a
Token a
Feature activation+0.000
brief
Token brief
Feature activation+0.000
suspension
Token suspension
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.000 - 0.581
CONTAINS 99.950%

.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
million
Token million
Feature activation+0.000
are
Token are
Feature activation+0.000
"
Token "
Feature activation+0.000
marg
Tokenmarg
Feature activation+0.000
inally
Tokeninally
Feature activation+0.000
attached
Token attached
Feature activation+0.000
"
Token"
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
October
Token October
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
s
Tokens
Feature activation+0.000
inaugural
Token inaugural
Feature activation+0.000
AFL
Token AFL
Feature activation+0.000
W
TokenW
Feature activation+0.000
season
Token season
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
Many
TokenMany
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
particularly
Token particularly
Feature activation+0.000
relevant
Token relevant
Feature activation+0.000
to
Token to
Feature activation+0.000
mobile
Token mobile
Feature activation+0.000
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
size
Token size
Feature activation+0.000
restrictions
Token restrictions
Feature activation+0.000
placed
Token placed
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
TV
Token TV
Feature activation+0.000
show
Token show
Feature activation+0.000
in
Token in
Feature activation+0.000
1995
Token 1995
Feature activation+0.000
and
Token and
Feature activation+0.000
gaining
Token gaining
Feature activation+0.000
popularity
Token popularity
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H11.10: (feature 4637)

TOP ACTIVATIONS
MAX = 3.904

iv
Tokeniv
Feature activation+0.000
Gandhi
Token Gandhi
Feature activation+0.000
's
Token's
Feature activation+0.000
trip
Token trip
Feature activation+0.074
in
Token in
Feature activation+0.000
1986
Token 1986
Feature activation+3.617
.
Token.
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
sure
Token sure
Feature activation+0.000
Coleman
Token Coleman
Feature activation+0.000
's
Token's
Feature activation+0.000
photo
Token photo
Feature activation+0.000
shoots
Token shoots
Feature activation+1.228
with
Token with
Feature activation+0.000
Schwarzenegger
Token Schwarzenegger
Feature activation+3.517
featured
Token featured
Feature activation+0.000
that
Token that
Feature activation+0.000
year
Token year
Feature activation+0.000
in
Token in
Feature activation+0.000
Joe
Token Joe
Feature activation+0.000
The
Token The
Feature activation+0.000
actual
Token actual
Feature activation+0.000
production
Token production
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
,
Token,
Feature activation+3.374
takes
Token takes
Feature activation+0.000
place
Token place
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
dist
Token dist
Feature activation+0.000
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
-
Token-
Feature activation+0.000
bed
Tokenbed
Feature activation+0.000
jail
Token jail
Feature activation+3.265
began
Token began
Feature activation+0.000
in
Token in
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
under
Token under
Feature activation+0.000
County
Token County
Feature activation+0.000
previous
Token previous
Feature activation+0.000
faith
Token faith
Feature activation+1.986
/
Token/
Feature activation+0.000
bel
Tokenbel
Feature activation+0.000
ief
Tokenief
Feature activation+1.549
system
Token system
Feature activation+3.257
(
Token (
Feature activation+0.000
because
Tokenbecause
Feature activation+0.000
face
Token face
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
travel
Token travel
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
journey
Token journey
Feature activation+0.000
that
Token that
Feature activation+1.646
now
Token now
Feature activation+3.078
takes
Token takes
Feature activation+0.000
hours
Token hours
Feature activation+0.073
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
royal
Token royal
Feature activation+0.000
Khan
Token Khan
Feature activation+0.000
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.000
rescue
Token rescue
Feature activation+0.000
operation
Token operation
Feature activation+0.129
has
Token has
Feature activation+2.983
been
Token been
Feature activation+0.000
called
Token called
Feature activation+0.000
off
Token off
Feature activation+0.000
as
Token as
Feature activation+0.000
nobody
Token nobody
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
when
Token when
Feature activation+0.000
production
Token production
Feature activation+0.000
would
Token would
Feature activation+1.174
actually
Token actually
Feature activation+2.982
begin
Token begin
Feature activation+1.735
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
marks
Token marks
Feature activation+0.000
a
Token a
Feature activation+0.000
seemed
Token seemed
Feature activation+0.000
so
Token so
Feature activation+0.000
determined
Token determined
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+2.208
permanently
Token permanently
Feature activation+2.912
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
summer
Token summer
Feature activation+1.085
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
believe
Token believe
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
God
Token God
Feature activation+0.000
)
Token)
Feature activation+2.912
is
Token is
Feature activation+0.000
daunting
Token daunting
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
K
Token K
Feature activation+0.000
ets
Tokenets
Feature activation+0.000
ui
Tokenui
Feature activation+1.331
Shim
Token Shim
Feature activation+0.000
ash
Tokenash
Feature activation+0.000
ita
Tokenita
Feature activation+2.873
(
Token (
Feature activation+0.000
Yu
TokenYu
Feature activation+0.000
-
Token-
Feature activation+0.000
S
TokenS
Feature activation+0.000
ibu
Tokenibu
Feature activation+0.000
The
TokenThe
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
of
Token of
Feature activation+0.000
Ber
Token Ber
Feature activation+0.000
gd
Tokengd
Feature activation+0.000
ahl
Tokenahl
Feature activation+2.850
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.306
s
Tokens
Feature activation+0.000
disappearance
Token disappearance
Feature activation+2.809
was
Token was
Feature activation+0.000
gd
Tokengd
Feature activation+0.000
ahl
Tokenahl
Feature activation+2.850
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.306
s
Tokens
Feature activation+0.000
disappearance
Token disappearance
Feature activation+2.809
was
Token was
Feature activation+0.000
launched
Token launched
Feature activation+0.000
last
Token last
Feature activation+0.000
June
Token June
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
of
Token of
Feature activation+0.000
Saudi
Token Saudi
Feature activation+0.000
clerics
Token clerics
Feature activation+2.802
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000
approve
Token approve
Feature activation+0.000
and
Token and
Feature activation+0.000
issue
Token issue
Feature activation+0.000
near
Token near
Feature activation+0.000
an
Token an
Feature activation+0.000
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
Qaeda
TokenQaeda
Feature activation+0.000
compound
Token compound
Feature activation+2.749
were
Token were
Feature activation+0.000
handled
Token handled
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
CIA
Token CIA
Feature activation+0.000
party
Token party
Feature activation+0.000
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000
same
Token same
Feature activation+0.000
elite
Token elite
Feature activation+0.000
neighborhoods
Token neighborhoods
Feature activation+2.678
consists
Token consists
Feature activation+0.000
almost
Token almost
Feature activation+0.000
wholly
Token wholly
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
The
TokenThe
Feature activation+0.000
battle
Token battle
Feature activation+0.000
for
Token for
Feature activation+0.000
Man
Token Man
Feature activation+0.000
b
Tokenb
Feature activation+0.000
ij
Tokenij
Feature activation+2.664
--
Token --
Feature activation+0.000
a
Token a
Feature activation+0.000
key
Token key
Feature activation+0.000
supply
Token supply
Feature activation+0.000
route
Token route
Feature activation+0.000
and
Token and
Feature activation+0.000
design
Token design
Feature activation+0.193
work
Token work
Feature activation+0.000
I
Token I
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.942
previously
Token previously
Feature activation+2.629
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
first
Token first
Feature activation+0.000
step
Token step
Feature activation+0.000
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
illicit
Token illicit
Feature activation+0.000
sale
Token sale
Feature activation+0.000
of
Token of
Feature activation+0.000
guns
Token guns
Feature activation+2.628
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
violation
Token violation
Feature activation+0.000
of
Token of
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
Israel
Token Israel
Feature activation+2.314
to
Token to
Feature activation+0.000
meet
Token meet
Feature activation+0.000
the
Token the
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+2.606
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
2015
Token 2015
Feature activation+2.222

Top DFA by src position
MAX = 4.977

PM
Token PM
Feature activation+0.049
Top resid features:
Raj
Token Raj
Feature activation+0.008
Top resid features:
iv
Tokeniv
Feature activation+0.007
Top resid features:
Gandhi
Token Gandhi
Feature activation+0.193
Top resid features:
's
Token's
Feature activation+0.087
Top resid features:
trip
Token trip
Feature activation+4.557
Top resid features:
in
Token in
Feature activation+0.064
Top resid features:
1986
Token 1986
Feature activation+0.132
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
And
TokenAnd
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
One
Token One
Feature activation+0.050
Top resid features:
of
Token of
Feature activation+0.048
Top resid features:
Coleman
Token Coleman
Feature activation+0.004
Top resid features:
's
Token's
Feature activation+0.044
Top resid features:
photo
Token photo
Feature activation+0.060
Top resid features:
shoots
Token shoots
Feature activation+4.977
Top resid features:
with
Token with
Feature activation+0.035
Top resid features:
Schwarzenegger
Token Schwarzenegger
Feature activation+0.081
Top resid features:
featured
Token featured
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
secret
Token secret
Feature activation+0.013
Top resid features:
recipe
Token recipe
Feature activation+0.070
Top resid features:
.
Token.
Feature activation+0.044
Top resid features:
The
Token The
Feature activation+0.041
Top resid features:
actual
Token actual
Feature activation+0.018
Top resid features:
production
Token production
Feature activation+4.727
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
though
Token though
Feature activation+0.068
Top resid features:
,
Token,
Feature activation+0.112
Top resid features:
takes
Token takes
Feature activation+0.000
Top resid features:
place
Token place
Feature activation+0.000
Top resid features:
R
Token R
Feature activation-0.006
Top resid features:
FP
TokenFP
Feature activation+0.000
Top resid features:
."
Token."
Feature activation+0.032
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.025
Top resid features:
Construction
TokenConstruction
Feature activation+4.638
Top resid features:
of
Token of
Feature activation+0.053
Top resid features:
the
Token the
Feature activation+0.046
Top resid features:
$
Token $
Feature activation-0.000
Top resid features:
200
Token200
Feature activation+0.017
Top resid features:
million
Token million
Feature activation+0.008
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.181
Top resid features:
female
Token female
Feature activation+0.079
Top resid features:
converts
Token converts
Feature activation+0.048
Top resid features:
.
Token.
Feature activation+0.133
Top resid features:
The
Token The
Feature activation+0.072
Top resid features:
process
Token process
Feature activation+4.533
Top resid features:
of
Token of
Feature activation+0.076
Top resid features:
transitioning
Token transitioning
Feature activation+0.135
Top resid features:
into
Token into
Feature activation+0.058
Top resid features:
Islam
Token Islam
Feature activation+0.115
Top resid features:
from
Token from
Feature activation+0.064
Top resid features:
of
Token of
Feature activation+0.041
Top resid features:
travel
Token travel
Feature activation+0.236
Top resid features:
for
Token for
Feature activation+0.028
Top resid features:
a
Token a
Feature activation+0.042
Top resid features:
journey
Token journey
Feature activation+1.440
Top resid features:
that
Token that
Feature activation+2.189
Top resid features:
now
Token now
Feature activation+0.562
Top resid features:
takes
Token takes
Feature activation+0.000
Top resid features:
hours
Token hours
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
Mr
TokenMr
Feature activation+0.010
Top resid features:
Khan
Token Khan
Feature activation+0.016
Top resid features:
says
Token says
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.047
Top resid features:
rescue
Token rescue
Feature activation+0.476
Top resid features:
operation
Token operation
Feature activation+3.399
Top resid features:
has
Token has
Feature activation+0.796
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
called
Token called
Feature activation+0.000
Top resid features:
off
Token off
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
producers
Token producers
Feature activation+0.019
Top resid features:
declined
Token declined
Feature activation+0.007
Top resid features:
to
Token to
Feature activation-0.008
Top resid features:
say
Token say
Feature activation+0.011
Top resid features:
when
Token when
Feature activation+0.019
Top resid features:
production
Token production
Feature activation+1.900
Top resid features:
would
Token would
Feature activation+0.329
Top resid features:
actually
Token actually
Feature activation+0.075
Top resid features:
begin
Token begin
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
That
Token That
Feature activation+0.000
Top resid features:
on
Token on
Feature activation-0.000
Top resid features:
Sunday
Token Sunday
Feature activation+0.024
Top resid features:
afternoon
Token afternoon
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
a
Token a
Feature activation+0.038
Top resid features:
journey
Token journey
Feature activation+3.046
Top resid features:
S
Token S
Feature activation+0.002
Top resid features:
án
Tokenán
Feature activation+0.002
Top resid features:
che
Tokenche
Feature activation+0.006
Top resid features:
z
Tokenz
Feature activation+0.062
Top resid features:
seemed
Token seemed
Feature activation+0.043
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.144
Top resid features:
female
Token female
Feature activation+0.025
Top resid features:
converts
Token converts
Feature activation+0.031
Top resid features:
.
Token.
Feature activation+0.166
Top resid features:
The
Token The
Feature activation+0.079
Top resid features:
process
Token process
Feature activation+3.683
Top resid features:
of
Token of
Feature activation+0.042
Top resid features:
transitioning
Token transitioning
Feature activation+0.052
Top resid features:
into
Token into
Feature activation+0.027
Top resid features:
Islam
Token Islam
Feature activation+0.071
Top resid features:
from
Token from
Feature activation+0.025
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
The
TokenThe
Feature activation+0.026
Top resid features:
anime
Token anime
Feature activation+0.592
Top resid features:
adaptation
Token adaptation
Feature activation+3.110
Top resid features:
of
Token of
Feature activation-0.019
Top resid features:
Jun
Token Jun
Feature activation+0.005
Top resid features:
Sak
Token Sak
Feature activation+0.001
Top resid features:
yo
Tokenyo
Feature activation+0.095
Top resid features:
's
Token's
Feature activation+0.014
Top resid features:
midst
Token midst
Feature activation+0.009
Top resid features:
]
Token]
Feature activation+0.035
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.047
Top resid features:
The
TokenThe
Feature activation+0.042
Top resid features:
investigation
Token investigation
Feature activation+4.114
Top resid features:
of
Token of
Feature activation+0.020
Top resid features:
Ber
Token Ber
Feature activation+0.002
Top resid features:
gd
Tokengd
Feature activation+0.004
Top resid features:
ahl
Tokenahl
Feature activation+0.058
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
midst
Token midst
Feature activation+0.009
Top resid features:
]
Token]
Feature activation+0.054
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.035
Top resid features:
The
TokenThe
Feature activation+0.036
Top resid features:
investigation
Token investigation
Feature activation+3.756
Top resid features:
of
Token of
Feature activation+0.015
Top resid features:
Ber
Token Ber
Feature activation+0.002
Top resid features:
gd
Tokengd
Feature activation+0.003
Top resid features:
ahl
Tokenahl
Feature activation+0.072
Top resid features:
âĢ
TokenâĢ
Feature activation+0.226
Top resid features:
said
Token said
Feature activation+0.038
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
adding
Token adding
Feature activation+0.016
Top resid features:
that
Token that
Feature activation+0.085
Top resid features:
the
Token the
Feature activation+0.089
Top resid features:
meeting
Token meeting
Feature activation+4.245
Top resid features:
of
Token of
Feature activation+0.082
Top resid features:
Saudi
Token Saudi
Feature activation+0.024
Top resid features:
clerics
Token clerics
Feature activation+0.036
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.014
Top resid features:
based
Token based
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.075
Top resid features:
âĢ¦
Token âĢ¦
Feature activation+0.022
Top resid features:
Surveillance
Token Surveillance
Feature activation+0.206
Top resid features:
operations
Token operations
Feature activation+3.548
Top resid features:
that
Token that
Feature activation+0.361
Top resid features:
required
Token required
Feature activation+0.020
Top resid features:
placing
Token placing
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.020
Top resid features:
device
Token device
Feature activation-0.004
Top resid features:
In
Token In
Feature activation+0.041
Top resid features:
2016
Token 2016
Feature activation+0.067
Top resid features:
,
Token,
Feature activation+0.034
Top resid features:
a
Token a
Feature activation+0.055
Top resid features:
dinner
Token dinner
Feature activation+0.284
Top resid features:
party
Token party
Feature activation+3.872
Top resid features:
in
Token in
Feature activation+0.068
Top resid features:
those
Token those
Feature activation+0.035
Top resid features:
same
Token same
Feature activation+0.022
Top resid features:
elite
Token elite
Feature activation+0.003
Top resid features:
neighborhoods
Token neighborhoods
Feature activation+0.099
Top resid features:
terrorists
Token terrorists
Feature activation+0.000
Top resid features:
".
Token".
Feature activation+0.054
Top resid features:
Ċ
TokenĊ
Feature activation+0.091
Top resid features:
Ċ
TokenĊ
Feature activation+0.042
Top resid features:
The
TokenThe
Feature activation+0.022
Top resid features:
battle
Token battle
Feature activation+3.976
Top resid features:
for
Token for
Feature activation+0.008
Top resid features:
Man
Token Man
Feature activation-0.002
Top resid features:
b
Tokenb
Feature activation+0.001
Top resid features:
ij
Tokenij
Feature activation+0.042
Top resid features:
--
Token --
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.365
Top resid features:
The
Token The
Feature activation+0.175
Top resid features:
planning
Token planning
Feature activation+0.240
Top resid features:
and
Token and
Feature activation+0.070
Top resid features:
design
Token design
Feature activation+0.677
Top resid features:
work
Token work
Feature activation+2.641
Top resid features:
I
Token I
Feature activation+0.110
Top resid features:
mentioned
Token mentioned
Feature activation+0.090
Top resid features:
previously
Token previously
Feature activation+0.419
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.035
Top resid features:
The
TokenThe
Feature activation+0.055
Top resid features:
illicit
Token illicit
Feature activation+0.012
Top resid features:
sale
Token sale
Feature activation+2.671
Top resid features:
of
Token of
Feature activation+0.017
Top resid features:
guns
Token guns
Feature activation+0.022
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
violation
Token violation
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.027
Top resid features:
Netanyahu
Token Netanyahu
Feature activation+0.024
Top resid features:
.
Token.
Feature activation-0.038
Top resid features:
A
Token A
Feature activation+0.047
Top resid features:
planned
Token planned
Feature activation+0.037
Top resid features:
trip
Token trip
Feature activation+4.182
Top resid features:
to
Token to
Feature activation+0.025
Top resid features:
Israel
Token Israel
Feature activation+0.007
Top resid features:
to
Token to
Feature activation+0.085
Top resid features:
meet
Token meet
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.04

Head 2: 0.02

Head 3: 0.06

Head 4: 0.04

Head 5: 0.04

Head 6: 0.02

Head 7: 0.03

Head 8: 0.09

Head 9: 0.03

Head 10: 0.39

Head 11: 0.15

Positive logits

culmin3.12

culminated2.88

netted2.64

lasted2.62

involves2.57

began2.56

ended2.55

climax2.51

centered2.50

spans2.36

commenced2.34

ens2.33

begins2.32

unfolded2.31

revolves2.31

ends2.30

took2.20

ensued2.20

Nickel2.19

consisted2.18

Negative logits

SHARE-2.91

-2.66

piracy-2.49

defect-2.47

-2.34

ilo-2.33

Statement-2.31

casting-2.31

training-2.25

abuse-2.24

playback-2.16

rection-2.14

vote-2.13

lecture-2.13

shop-2.11

selling-2.09

dispute-2.08

lishing-2.08

repairs-2.07

debate-2.06

INTERVAL 3.513 - 3.904
CONTAINS 0.000%

Coleman
Token Coleman
Feature activation+0.000
's
Token's
Feature activation+0.000
photo
Token photo
Feature activation+0.000
shoots
Token shoots
Feature activation+1.228
with
Token with
Feature activation+0.000
Schwarzenegger
Token Schwarzenegger
Feature activation+3.517
featured
Token featured
Feature activation+0.000
that
Token that
Feature activation+0.000
year
Token year
Feature activation+0.000
in
Token in
Feature activation+0.000
Joe
Token Joe
Feature activation+0.000
iv
Tokeniv
Feature activation+0.000
Gandhi
Token Gandhi
Feature activation+0.000
's
Token's
Feature activation+0.000
trip
Token trip
Feature activation+0.074
in
Token in
Feature activation+0.000
1986
Token 1986
Feature activation+3.617
.
Token.
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
sure
Token sure
Feature activation+0.000

INTERVAL 3.123 - 3.513
CONTAINS 0.000%

The
Token The
Feature activation+0.000
actual
Token actual
Feature activation+0.000
production
Token production
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
,
Token,
Feature activation+3.374
takes
Token takes
Feature activation+0.000
place
Token place
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
dist
Token dist
Feature activation+0.000
previous
Token previous
Feature activation+0.000
faith
Token faith
Feature activation+1.986
/
Token/
Feature activation+0.000
bel
Tokenbel
Feature activation+0.000
ief
Tokenief
Feature activation+1.549
system
Token system
Feature activation+3.257
(
Token (
Feature activation+0.000
because
Tokenbecause
Feature activation+0.000
face
Token face
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
-
Token-
Feature activation+0.000
bed
Tokenbed
Feature activation+0.000
jail
Token jail
Feature activation+3.265
began
Token began
Feature activation+0.000
in
Token in
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
under
Token under
Feature activation+0.000
County
Token County
Feature activation+0.000

INTERVAL 2.733 - 3.123
CONTAINS 0.001%

Khan
Token Khan
Feature activation+0.000
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.000
rescue
Token rescue
Feature activation+0.000
operation
Token operation
Feature activation+0.129
has
Token has
Feature activation+2.983
been
Token been
Feature activation+0.000
called
Token called
Feature activation+0.000
off
Token off
Feature activation+0.000
as
Token as
Feature activation+0.000
nobody
Token nobody
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
of
Token of
Feature activation+0.000
Saudi
Token Saudi
Feature activation+0.000
clerics
Token clerics
Feature activation+2.802
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000
approve
Token approve
Feature activation+0.000
and
Token and
Feature activation+0.000
issue
Token issue
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
when
Token when
Feature activation+0.000
production
Token production
Feature activation+0.000
would
Token would
Feature activation+1.174
actually
Token actually
Feature activation+2.982
begin
Token begin
Feature activation+1.735
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
marks
Token marks
Feature activation+0.000
a
Token a
Feature activation+0.000
The
TokenThe
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
of
Token of
Feature activation+0.000
Ber
Token Ber
Feature activation+0.000
gd
Tokengd
Feature activation+0.000
ahl
Tokenahl
Feature activation+2.850
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.306
s
Tokens
Feature activation+0.000
disappearance
Token disappearance
Feature activation+2.809
was
Token was
Feature activation+0.000
gd
Tokengd
Feature activation+0.000
ahl
Tokenahl
Feature activation+2.850
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.306
s
Tokens
Feature activation+0.000
disappearance
Token disappearance
Feature activation+2.809
was
Token was
Feature activation+0.000
launched
Token launched
Feature activation+0.000
last
Token last
Feature activation+0.000
June
Token June
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.342 - 2.733
CONTAINS 0.002%

Israel
Token Israel
Feature activation+2.314
to
Token to
Feature activation+0.000
meet
Token meet
Feature activation+0.000
the
Token the
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+2.606
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
2015
Token 2015
Feature activation+2.222
Whe
Token Whe
Feature activation+0.000
eling
Tokeneling
Feature activation+0.000
Park
Token Park
Feature activation+0.000
's
Token's
Feature activation+0.000
swimming
Token swimming
Feature activation+0.000
pool
Token pool
Feature activation+2.372
turned
Token turned
Feature activation+0.000
tragic
Token tragic
Feature activation+0.000
when
Token when
Feature activation+0.000
a
Token a
Feature activation+0.000
student
Token student
Feature activation+0.000
.
Token.
Feature activation+0.000
Par
Token Par
Feature activation+0.000
ades
Tokenades
Feature activation+0.000
outside
Token outside
Feature activation+0.000
of
Token of
Feature activation+0.000
Ireland
Token Ireland
Feature activation+2.402
started
Token started
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
18
Token 18
Feature activation+0.000
th
Tokenth
Feature activation+0.000
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
conservative
Token conservative
Feature activation+0.000
southern
Token southern
Feature activation+0.000
states
Token states
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+2.420
is
Token is
Feature activation+0.000
designed
Token designed
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
und
Token und
Feature activation+0.000
banking
Token banking
Feature activation+0.000
,
Token,
Feature activation+0.000
insurance
Token insurance
Feature activation+0.000
and
Token and
Feature activation+0.000
finance
Token finance
Feature activation+0.000
sector
Token sector
Feature activation+2.559
is
Token is
Feature activation+0.000
open
Token open
Feature activation+0.000
and
Token and
Feature activation+0.000
shut
Token shut
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.952 - 2.342
CONTAINS 0.003%

two
Token two
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
international
Token international
Feature activation+0.000
operation
Token operation
Feature activation+0.000
had
Token had
Feature activation+2.057
resulted
Token resulted
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
arrest
Token arrest
Feature activation+0.000
of
Token of
Feature activation+0.000
into
Token into
Feature activation+0.000
Islam
Token Islam
Feature activation+1.885
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
previous
Token previous
Feature activation+0.000
faith
Token faith
Feature activation+1.986
/
Token/
Feature activation+0.000
bel
Tokenbel
Feature activation+0.000
ief
Tokenief
Feature activation+1.549
system
Token system
Feature activation+3.257
(
Token (
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
planned
Token planned
Feature activation+0.000
trip
Token trip
Feature activation+0.000
to
Token to
Feature activation+0.000
Israel
Token Israel
Feature activation+2.314
to
Token to
Feature activation+0.000
meet
Token meet
Feature activation+0.000
the
Token the
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+2.606
His
Token His
Feature activation+0.000
senior
Token senior
Feature activation+0.000
year
Token year
Feature activation+0.000
of
Token of
Feature activation+0.000
high
Token high
Feature activation+0.000
school
Token school
Feature activation+2.064
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
9
Token 9
Feature activation+0.000
th
Tokenth
Feature activation+0.000
in
Token in
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.758
,
Token,
Feature activation+2.068
are
Token are
Feature activation+0.000
a
Token a
Feature activation+0.000
hopeful
Token hopeful
Feature activation+0.000
sign
Token sign
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 1.561 - 1.952
CONTAINS 0.005%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
football
Token football
Feature activation+0.000
career
Token career
Feature activation+0.432
really
Token really
Feature activation+1.897
took
Token took
Feature activation+0.000
off
Token off
Feature activation+0.000
in
Token in
Feature activation+0.000
high
Token high
Feature activation+0.000
school
Token school
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
cam
Token cam
Feature activation+0.000
ap
Tokenap
Feature activation+0.000
aign
Tokenaign
Feature activation+0.000
gets
Token gets
Feature activation+0.000
underway
Token underway
Feature activation+1.860
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Wisconsin
Token Wisconsin
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
internal
Token internal
Feature activation+0.000
affairs
Token affairs
Feature activation+0.000
investigation
Token investigation
Feature activation+0.674
âĢĶ
Token âĢĶ
Feature activation+1.652
concluded
Token concluded
Feature activation+0.000
that
Token that
Feature activation+0.000
Tracy
Token Tracy
Feature activation+0.000
violated
Token violated
Feature activation+0.000
five
Token five
Feature activation+0.000
support
Token support
Feature activation+0.000
for
Token for
Feature activation+0.000
US
Token US
Feature activation+0.000
and
Token and
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
policy
Token policy
Feature activation+1.608
and
Token and
Feature activation+0.000
actions
Token actions
Feature activation+1.501
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Middle
Token Middle
Feature activation+0.000
Mid
Token Mid
Feature activation+0.000
town
Tokentown
Feature activation+0.066
and
Token and
Feature activation+0.000
pretty
Token pretty
Feature activation+0.000
much
Token much
Feature activation+0.000
everywhere
Token everywhere
Feature activation+1.764
else
Token else
Feature activation+2.472
was
Token was
Feature activation+0.923
grinding
Token grinding
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 1.171 - 1.561
CONTAINS 0.011%

.
Token.
Feature activation+0.000
Warfare
Token Warfare
Feature activation+0.000
in
Token in
Feature activation+0.000
Greece
Token Greece
Feature activation+0.721
had
Token had
Feature activation+0.104
always
Token always
Feature activation+1.240
been
Token been
Feature activation+0.000
dictated
Token dictated
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
terrain
Token terrain
Feature activation+0.000
after
Token after
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
's
Token's
Feature activation+0.000
offensive
Token offensive
Feature activation+0.000
in
Token in
Feature activation+0.000
Gaza
Token Gaza
Feature activation+1.184
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
announced
Token announced
Feature activation+0.000
this
Token this
Feature activation+0.000
the
Token the
Feature activation+0.000
murderous
Token murderous
Feature activation+0.000
attack
Token attack
Feature activation+0.000
by
Token by
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
radicals
Token radicals
Feature activation+1.302
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
fact
Token fact
Feature activation+0.000
a
Token a
Feature activation+0.000
spontaneous
Token spontaneous
Feature activation+0.000
where
Token where
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000
train
Token train
Feature activation+0.000
,
Token,
Feature activation+1.381
saw
Token saw
Feature activation+0.000
large
Token large
Feature activation+0.000
-
Token-
Feature activation+0.000
scale
Tokenscale
Feature activation+0.000
participation
Token participation
Feature activation+0.000
reactions
Token reactions
Feature activation+0.000
or
Token or
Feature activation+0.000
pur
Token pur
Feature activation+0.000
ifications
Tokenifications
Feature activation+1.586
of
Token of
Feature activation+0.000
compounds
Token compounds
Feature activation+1.246
occur
Token occur
Feature activation+0.000
in
Token in
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
p
Tokenp
Feature activation+0.000

INTERVAL 0.781 - 1.171
CONTAINS 0.021%

to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
the
Token the
Feature activation+0.000
proposals
Token proposals
Feature activation+0.000
into
Token into
Feature activation+0.000
law
Token law
Feature activation+0.859
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.923
hit
Token hit
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
h
Tokenh
Feature activation+0.000
anger
Tokenanger
Feature activation+0.621
season
Token season
Feature activation+0.000
finale
Token finale
Feature activation+0.385
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.978
saw
Token saw
Feature activation+0.000
the
Token the
Feature activation+0.000
Mayor
Token Mayor
Feature activation+0.000
admitting
Token admitting
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
development
Token development
Feature activation+0.000
cycle
Token cycle
Feature activation+0.000
for
Token for
Feature activation+0.000
Kol
Token Kol
Feature activation+0.000
ab
Tokenab
Feature activation+0.921
3
Token 3
Feature activation+1.885
.
Token.
Feature activation+0.000
1
Token1
Feature activation+1.857
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
implementation
Token implementation
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
directive
Token directive
Feature activation+0.902
led
Token led
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
ordering
Token ordering
Feature activation+0.000
of
Token of
Feature activation+0.000
controls
Token controls
Feature activation+0.000
activities
Token activities
Feature activation+0.000
within
Token within
Feature activation+0.000
the
Token the
Feature activation+0.000
mitochond
Token mitochond
Feature activation+0.000
ria
Tokenria
Feature activation+1.117
shows
Token shows
Feature activation+0.000
how
Token how
Feature activation+0.000
energy
Token energy
Feature activation+0.000
generation
Token generation
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 0.390 - 0.781
CONTAINS 0.045%

and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
massive
Token massive
Feature activation+0.000
recruiting
Token recruiting
Feature activation+0.000
war
Token war
Feature activation+0.004
began
Token began
Feature activation+0.778
for
Token for
Feature activation+0.000
anybody
Token anybody
Feature activation+0.000
with
Token with
Feature activation+0.000
relevant
Token relevant
Feature activation+0.000
skills
Token skills
Feature activation+0.000
open
Token open
Feature activation+0.000
-
Token-
Feature activation+0.000
en
Tokenen
Feature activation+0.000
rollment
Tokenrollment
Feature activation+0.000
period
Token period
Feature activation+0.000
had
Token had
Feature activation+0.672
exceeded
Token exceeded
Feature activation+0.000
its
Token its
Feature activation+0.000
goals
Token goals
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
hardest
Token hardest
Feature activation+0.000
route
Token route
Feature activation+0.000
in
Token in
Feature activation+0.000
Italy
Token Italy
Feature activation+0.767
until
Token until
Feature activation+0.000
now
Token now
Feature activation+0.486
likely
Token likely
Feature activation+0.078
was
Token was
Feature activation+0.000
Adam
Token Adam
Feature activation+0.000
O
Token O
Feature activation+0.000
ndra
Tokenndra
Feature activation+0.000
first
Token first
Feature activation+0.000
solo
Token solo
Feature activation+0.000
show
Token show
Feature activation+0.000
there
Token there
Feature activation+0.000
that
Token that
Feature activation+0.000
year
Token year
Feature activation+0.471
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
spent
Token spent
Feature activation+0.000
summers
Token summers
Feature activation+0.000
visiting
Token visiting
Feature activation+0.000
of
Token of
Feature activation+0.000
voting
Token voting
Feature activation+0.214
on
Token on
Feature activation+0.000
Aug
Token Aug
Feature activation+0.000
.
Token.
Feature activation+0.000
15
Token 15
Feature activation+0.494
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
Moore
Token Moore
Feature activation+0.000
finished
Token finished
Feature activation+0.000
ahead
Token ahead
Feature activation+0.000

INTERVAL 0.000 - 0.390
CONTAINS 99.911%

increased
Token increased
Feature activation+0.000
ratings
Token ratings
Feature activation+0.000
of
Token of
Feature activation+0.000
alert
Token alert
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
findings
Token findings
Feature activation+0.000
suggest
Token suggest
Feature activation+0.000
that
Token that
Feature activation+0.000
mac
Token mac
Feature activation+0.000
sentenced
Token sentenced
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
months
Token months
Feature activation+0.000
later
Token later
Feature activation+0.000
to
Token to
Feature activation+0.000
two
Token two
Feature activation+0.000
years
Token years
Feature activation+0.000
in
Token in
Feature activation+0.000
prison
Token prison
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
bone
Token bone
Feature activation+0.000
head
Tokenhead
Feature activation+0.000
,
Token,
Feature activation+0.000
bull
Token bull
Feature activation+0.000
,
Token,
Feature activation+0.000
blue
Token blue
Feature activation+0.000
,
Token,
Feature activation+0.000
nurse
Token nurse
Feature activation+0.000
ocean
Token ocean
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
applied
Token applied
Feature activation+0.000
to
Token to
Feature activation+0.000
biological
Token biological
Feature activation+0.000
compounds
Token compounds
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
nucle
Token nucle
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
who
Token who
Feature activation+0.000
ate
Token ate
Feature activation+0.000
eight
Token eight
Feature activation+0.000
j
Token j
Feature activation+0.000
al
Tokenal
Feature activation+0.000
ape
Tokenape
Feature activation+0.000
ñ
Tokenñ
Feature activation+0.000
os
Tokenos
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
minute
Token minute
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 3 in H11.10: (feature 218)

TOP ACTIVATIONS
MAX = 6.407

from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Illinois
Token Illinois
Feature activation+0.000
Department
Token Department
Feature activation+0.000
of
Token of
Feature activation+0.000
Corrections
Token Corrections
Feature activation+6.407
show
Token show
Feature activation+0.000
Perez
Token Perez
Feature activation+0.000
was
Token was
Feature activation+0.000
released
Token released
Feature activation+0.000
from
Token from
Feature activation+0.000
box
Token box
Feature activation+0.000
-
Token-
Feature activation+0.000
office
Tokenoffice
Feature activation+0.000
data
Token data
Feature activation+0.222
for
Token for
Feature activation+0.000
2013
Token 2013
Feature activation+6.191
showed
Token showed
Feature activation+0.000
sales
Token sales
Feature activation+0.000
of
Token of
Feature activation+0.000
$
Token $
Feature activation+0.000
3
Token3
Feature activation+0.000
Official
TokenOfficial
Feature activation+0.000
figures
Token figures
Feature activation+0.061
released
Token released
Feature activation+0.000
earlier
Token earlier
Feature activation+3.108
this
Token this
Feature activation+0.000
month
Token month
Feature activation+6.023
showed
Token showed
Feature activation+0.000
more
Token more
Feature activation+0.000
people
Token people
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
.
Token.
Feature activation+0.000
Documents
Token Documents
Feature activation+0.000
released
Token released
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
bureau
Token bureau
Feature activation+5.544
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
samples
Token samples
Feature activation+0.472
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.104
data
Token data
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
anten
Token anten
Feature activation+0.000
atal
Tokenatal
Feature activation+0.000
environment
Token environment
Feature activation+5.383
suggests
Token suggests
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
to
Token to
Feature activation+0.000
taking
Token taking
Feature activation+0.000
iodine
Token iodine
Feature activation+0.000
Non
Token Non
Feature activation+0.000
-
Token-
Feature activation+0.000
Pro
TokenPro
Feature activation+0.000
fit
Tokenfit
Feature activation+0.000
Housing
Token Housing
Feature activation+0.000
Association
Token Association
Feature activation+5.205
(
Token (
Feature activation+0.000
BC
TokenBC
Feature activation+0.000
NP
TokenNP
Feature activation+0.000
HA
TokenHA
Feature activation+0.000
)
Token)
Feature activation+4.384
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Oakland
Token Oakland
Feature activation+0.000
Privacy
Token Privacy
Feature activation+0.000
Working
Token Working
Feature activation+0.000
Group
Token Group
Feature activation+5.025
,
Token,
Feature activation+1.574
a
Token a
Feature activation+0.000
coalition
Token coalition
Feature activation+0.000
opposed
Token opposed
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
SF
Token SF
Feature activation+0.000
U
TokenU
Feature activation+0.000
City
Token City
Feature activation+0.000
Program
Token Program
Feature activation+0.433
,
Token,
Feature activation+5.015
shows
Token shows
Feature activation+0.000
varying
Token varying
Feature activation+0.000
levels
Token levels
Feature activation+0.000
of
Token of
Feature activation+0.000
renters
Token renters
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
statistics
Token statistics
Feature activation+0.163
on
Token on
Feature activation+0.000
imprisonment
Token imprisonment
Feature activation+4.074
further
Token further
Feature activation+4.844
demonstrate
Token demonstrate
Feature activation+0.000
the
Token the
Feature activation+0.000
extremes
Token extremes
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
videos
Token videos
Feature activation+0.896
allegedly
Token allegedly
Feature activation+3.703
showing
Token showing
Feature activation+0.000
the
Token the
Feature activation+0.000
bombed
Token bombed
Feature activation+0.000
headquarters
Token headquarters
Feature activation+4.722
quickly
Token quickly
Feature activation+3.570
emerged
Token emerged
Feature activation+0.000
online
Token online
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
figures
Token figures
Feature activation+0.396
cited
Token cited
Feature activation+1.144
below
Token below
Feature activation+4.497
come
Token come
Feature activation+0.000
from
Token from
Feature activation+0.000
surveys
Token surveys
Feature activation+0.000
conducted
Token conducted
Feature activation+0.000
by
Token by
Feature activation+0.000
Association
Token Association
Feature activation+5.205
(
Token (
Feature activation+0.000
BC
TokenBC
Feature activation+0.000
NP
TokenNP
Feature activation+0.000
HA
TokenHA
Feature activation+0.000
)
Token)
Feature activation+4.384
shows
Token shows
Feature activation+0.000
that
Token that
Feature activation+0.000
22
Token 22
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
underestimate
Token underestimate
Feature activation+0.000
some
Token some
Feature activation+0.000
types
Token types
Feature activation+0.000
of
Token of
Feature activation+0.000
crime
Token crime
Feature activation+0.000
)
Token)
Feature activation+4.368
and
Token and
Feature activation+0.274
surveys
Token surveys
Feature activation+1.564
of
Token of
Feature activation+0.000
victims
Token victims
Feature activation+4.014
(
Token (
Feature activation+0.807
taken
Token taken
Feature activation+0.000
by
Token by
Feature activation+0.000
fans
Token fans
Feature activation+4.015
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
crowd
Token crowd
Feature activation+4.227
appears
Token appears
Feature activation+0.025
to
Token to
Feature activation+2.877
show
Token show
Feature activation+0.000
the
Token the
Feature activation+0.000
flash
Token flash
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
strong
Token strong
Feature activation+0.000
opposition
Token opposition
Feature activation+0.000
to
Token to
Feature activation+0.000
legalization
Token legalization
Feature activation+4.216
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
private
Token private
Feature activation+0.000
appearance
Token appearance
Feature activation+0.613
,
Token,
Feature activation+2.260
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
small
Token small
Feature activation+0.000
investig
Token investig
Feature activation+0.000
ational
Tokenational
Feature activation+0.000
study
Token study
Feature activation+4.207
indicate
Token indicate
Feature activation+0.000
that
Token that
Feature activation+0.000
additional
Token additional
Feature activation+0.000
study
Token study
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.000
Data
Token Data
Feature activation+0.000
returned
Token returned
Feature activation+1.737
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
mission
Token mission
Feature activation+4.185
will
Token will
Feature activation+0.856
help
Token help
Feature activation+0.000
Nasa
Token Nasa
Feature activation+0.000
identify
Token identify
Feature activation+0.000
safe
Token safe
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Images
TokenImages
Feature activation+0.000
taken
Token taken
Feature activation+0.318
on
Token on
Feature activation+0.000
Thursday
Token Thursday
Feature activation+4.150
shows
Token shows
Feature activation+0.000
all
Token all
Feature activation+0.000
-
Token-
Feature activation+0.000
male
Tokenmale
Feature activation+0.000
groups
Token groups
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
footage
Token footage
Feature activation+0.222
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
incident
Token incident
Feature activation+4.109
was
Token was
Feature activation+0.127
shared
Token shared
Feature activation+0.000
online
Token online
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
details
Token details
Feature activation+0.222
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
March
Token March
Feature activation+0.000
4
Token 4
Feature activation+0.000
incident
Token incident
Feature activation+4.093
emerged
Token emerged
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.022
from
Token from
Feature activation+0.000
interviews
Token interviews
Feature activation+0.000
and
Token and
Feature activation+0.000

Top DFA by src position
MAX = 7.569

Monday
Token Monday
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.130
Top resid features:
Ċ
TokenĊ
Feature activation+0.052
Top resid features:
Ċ
TokenĊ
Feature activation+0.041
Top resid features:
Rec
TokenRec
Feature activation+0.006
Top resid features:
ords
Tokenords
Feature activation+7.569
Top resid features:
from
Token from
Feature activation+0.267
Top resid features:
the
Token the
Feature activation+0.074
Top resid features:
Illinois
Token Illinois
Feature activation+0.037
Top resid features:
Department
Token Department
Feature activation+0.036
Top resid features:
of
Token of
Feature activation+0.028
Top resid features:
Ċ
TokenĊ
Feature activation+0.101
Top resid features:
Official
TokenOfficial
Feature activation+0.033
Top resid features:
box
Token box
Feature activation+0.040
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
office
Tokenoffice
Feature activation+0.049
Top resid features:
data
Token data
Feature activation+5.147
Top resid features:
for
Token for
Feature activation+0.087
Top resid features:
2013
Token 2013
Feature activation+0.190
Top resid features:
showed
Token showed
Feature activation+0.000
Top resid features:
sales
Token sales
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
laundry
Token laundry
Feature activation-0.006
Top resid features:
'
Token'
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.062
Top resid features:
Ċ
TokenĊ
Feature activation+0.061
Top resid features:
Official
TokenOfficial
Feature activation+0.028
Top resid features:
figures
Token figures
Feature activation+6.713
Top resid features:
released
Token released
Feature activation+0.886
Top resid features:
earlier
Token earlier
Feature activation+0.110
Top resid features:
this
Token this
Feature activation+0.013
Top resid features:
month
Token month
Feature activation+0.372
Top resid features:
showed
Token showed
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+0.037
Top resid features:
in
Token in
Feature activation+0.057
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
letters
Token letters
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.091
Top resid features:
Documents
Token Documents
Feature activation+3.706
Top resid features:
released
Token released
Feature activation+3.001
Top resid features:
by
Token by
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
bureau
Token bureau
Feature activation+0.787
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
term
Token term
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.045
Top resid features:
(
Token (
Feature activation+0.049
Top resid features:
However
TokenHowever
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
data
Token data
Feature activation+7.261
Top resid features:
on
Token on
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
anten
Token anten
Feature activation+0.004
Top resid features:
atal
Tokenatal
Feature activation-0.003
Top resid features:
environment
Token environment
Feature activation+0.169
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
live
Token live
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.036
Top resid features:
Ċ
TokenĊ
Feature activation+0.046
Top resid features:
Ċ
TokenĊ
Feature activation+0.041
Top resid features:
Data
TokenData
Feature activation+6.080
Top resid features:
cr
Token cr
Feature activation+0.031
Top resid features:
un
Tokenun
Feature activation+0.006
Top resid features:
ched
Tokenched
Feature activation+0.728
Top resid features:
by
Token by
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.057
Top resid features:
Ċ
TokenĊ
Feature activation+0.042
Top resid features:
Internal
TokenInternal
Feature activation+0.027
Top resid features:
city
Token city
Feature activation-0.001
Top resid features:
emails
Token emails
Feature activation+3.385
Top resid features:
obtained
Token obtained
Feature activation+1.384
Top resid features:
by
Token by
Feature activation+0.055
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
Oakland
Token Oakland
Feature activation+0.020
Top resid features:
Privacy
Token Privacy
Feature activation+0.005
Top resid features:
crisis
Token crisis
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.077
Top resid features:
C
TokenC
Feature activation+0.023
Top resid features:
ensus
Tokenensus
Feature activation+0.166
Top resid features:
data
Token data
Feature activation+4.868
Top resid features:
compiled
Token compiled
Feature activation+1.096
Top resid features:
by
Token by
Feature activation+0.062
Top resid features:
Andy
Token Andy
Feature activation-0.002
Top resid features:
Yan
Token Yan
Feature activation+0.050
Top resid features:
,
Token,
Feature activation+0.095
Top resid features:
Life
TokenLife
Feature activation+0.022
Top resid features:
sentences
Token sentences
Feature activation+0.042
Top resid features:
Ċ
TokenĊ
Feature activation+0.053
Top resid features:
Ċ
TokenĊ
Feature activation+0.122
Top resid features:
The
TokenThe
Feature activation+0.069
Top resid features:
statistics
Token statistics
Feature activation+5.874
Top resid features:
on
Token on
Feature activation+0.062
Top resid features:
imprisonment
Token imprisonment
Feature activation+0.092
Top resid features:
further
Token further
Feature activation+0.577
Top resid features:
demonstrate
Token demonstrate
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.082
Top resid features:
Syria
Token Syria
Feature activation-0.013
Top resid features:
.
Token.
Feature activation+0.121
Top resid features:
Photos
Token Photos
Feature activation+1.903
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
videos
Token videos
Feature activation+4.035
Top resid features:
allegedly
Token allegedly
Feature activation+0.694
Top resid features:
showing
Token showing
Feature activation+0.120
Top resid features:
the
Token the
Feature activation+0.065
Top resid features:
bombed
Token bombed
Feature activation+0.060
Top resid features:
headquarters
Token headquarters
Feature activation+0.274
Top resid features:
accountable
Token accountable
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.055
Top resid features:
The
TokenThe
Feature activation+0.018
Top resid features:
figures
Token figures
Feature activation+4.731
Top resid features:
cited
Token cited
Feature activation+0.937
Top resid features:
below
Token below
Feature activation+0.955
Top resid features:
come
Token come
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
surveys
Token surveys
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
live
Token live
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.052
Top resid features:
Ċ
TokenĊ
Feature activation+0.037
Top resid features:
Ċ
TokenĊ
Feature activation+0.074
Top resid features:
Data
TokenData
Feature activation+4.343
Top resid features:
cr
Token cr
Feature activation+0.033
Top resid features:
un
Tokenun
Feature activation+0.006
Top resid features:
ched
Tokenched
Feature activation+0.850
Top resid features:
by
Token by
Feature activation+0.031
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.068
Top resid features:
Ċ
TokenĊ
Feature activation+0.136
Top resid features:
Both
TokenBoth
Feature activation+0.106
Top resid features:
police
Token police
Feature activation+0.139
Top resid features:
records
Token records
Feature activation+4.482
Top resid features:
(
Token (
Feature activation+0.167
Top resid features:
which
Tokenwhich
Feature activation+0.576
Top resid features:
underestimate
Token underestimate
Feature activation+0.030
Top resid features:
some
Token some
Feature activation+0.071
Top resid features:
types
Token types
Feature activation+0.091
Top resid features:
time
Token time
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.085
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Foot
TokenFoot
Feature activation-0.001
Top resid features:
age
Tokenage
Feature activation+5.510
Top resid features:
taken
Token taken
Feature activation+0.314
Top resid features:
by
Token by
Feature activation+0.016
Top resid features:
fans
Token fans
Feature activation+0.445
Top resid features:
in
Token in
Feature activation+0.043
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
The
TokenThe
Feature activation+0.015
Top resid features:
newly
Token newly
Feature activation+0.003
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
le
Tokenle
Feature activation+0.002
Top resid features:
aked
Tokenaked
Feature activation+0.035
Top resid features:
documents
Token documents
Feature activation+6.118
Top resid features:
showing
Token showing
Feature activation+0.060
Top resid features:
Clinton
Token Clinton
Feature activation+0.086
Top resid features:
âĢ
TokenâĢ
Feature activation+0.157
Top resid features:
Ļ
TokenĻ
Feature activation+0.076
Top resid features:
s
Tokens
Feature activation+0.017
Top resid features:
participants
Token participants
Feature activation+0.123
Top resid features:
were
Token were
Feature activation+0.155
Top resid features:
striking
Token striking
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.090
Top resid features:
The
Token The
Feature activation+0.023
Top resid features:
results
Token results
Feature activation+3.337
Top resid features:
of
Token of
Feature activation+0.029
Top resid features:
this
Token this
Feature activation+0.018
Top resid features:
small
Token small
Feature activation-0.016
Top resid features:
investig
Token investig
Feature activation+0.017
Top resid features:
ational
Tokenational
Feature activation+0.007
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
Moon
Token Moon
Feature activation-0.006
Top resid features:
."
Token."
Feature activation+0.066
Top resid features:
Although
Token Although
Feature activation+0.039
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
pictures
Token pictures
Feature activation+2.838
Top resid features:
provide
Token provide
Feature activation+0.061
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
reminder
Token reminder
Feature activation-0.004
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
past
Token past
Feature activation+0.005
Top resid features:
scene
Token scene
Feature activation-0.002
Top resid features:
!'
Token!'
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.063
Top resid features:
Ċ
TokenĊ
Feature activation+0.112
Top resid features:
Images
TokenImages
Feature activation+2.385
Top resid features:
taken
Token taken
Feature activation+3.488
Top resid features:
on
Token on
Feature activation+0.070
Top resid features:
Thursday
Token Thursday
Feature activation+0.536
Top resid features:
shows
Token shows
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.139
Top resid features:
At
Token At
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
time
Token time
Feature activation+0.035
Top resid features:
,
Token,
Feature activation+0.055
Top resid features:
footage
Token footage
Feature activation+5.529
Top resid features:
of
Token of
Feature activation+0.073
Top resid features:
the
Token the
Feature activation+0.074
Top resid features:
incident
Token incident
Feature activation+0.287
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
shared
Token shared
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
These
TokenThese
Feature activation+0.025
Top resid features:
and
Token and
Feature activation+0.023
Top resid features:
other
Token other
Feature activation+0.022
Top resid features:
new
Token new
Feature activation-0.010
Top resid features:
details
Token details
Feature activation+5.667
Top resid features:
about
Token about
Feature activation+0.034
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
March
Token March
Feature activation+0.042
Top resid features:
4
Token 4
Feature activation+0.016
Top resid features:
incident
Token incident
Feature activation+0.322
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.04

Head 2: 0.02

Head 3: 0.11

Head 4: 0.04

Head 5: 0.03

Head 6: 0.02

Head 7: 0.04

Head 8: 0.12

Head 9: 0.03

Head 10: 0.38

Head 11: 0.11

Positive logits

show4.00

indicate3.34

showed3.31

shows3.15

reveal3.10

shows3.07

SHOW3.03

Show3.01

showing3.00

demonstrate2.98

confirm2.95

show2.92

suggest2.90

Shows2.82

corrobor2.71

depict2.69

Show2.54

reve2.51

indicated2.51

confirming2.47

Negative logits

goal-2.46

itect-2.32

fixme-2.30

unconscious-2.28

impulse-2.23

Goal-2.22

SOFTWARE-2.20

vir-2.19

RNA-2.16

odor-2.15

iHUD-2.10

utical-2.10

olicy-2.05

vector-2.00

ictionary-2.00

conom-2.00

alg-1.99

HER-1.99

Hyper-1.97

Instruction-1.97

INTERVAL 5.766 - 6.407
CONTAINS 0.000%

from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Illinois
Token Illinois
Feature activation+0.000
Department
Token Department
Feature activation+0.000
of
Token of
Feature activation+0.000
Corrections
Token Corrections
Feature activation+6.407
show
Token show
Feature activation+0.000
Perez
Token Perez
Feature activation+0.000
was
Token was
Feature activation+0.000
released
Token released
Feature activation+0.000
from
Token from
Feature activation+0.000
Official
TokenOfficial
Feature activation+0.000
figures
Token figures
Feature activation+0.061
released
Token released
Feature activation+0.000
earlier
Token earlier
Feature activation+3.108
this
Token this
Feature activation+0.000
month
Token month
Feature activation+6.023
showed
Token showed
Feature activation+0.000
more
Token more
Feature activation+0.000
people
Token people
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
box
Token box
Feature activation+0.000
-
Token-
Feature activation+0.000
office
Tokenoffice
Feature activation+0.000
data
Token data
Feature activation+0.222
for
Token for
Feature activation+0.000
2013
Token 2013
Feature activation+6.191
showed
Token showed
Feature activation+0.000
sales
Token sales
Feature activation+0.000
of
Token of
Feature activation+0.000
$
Token $
Feature activation+0.000
3
Token3
Feature activation+0.000

INTERVAL 5.125 - 5.766
CONTAINS 0.000%

data
Token data
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
anten
Token anten
Feature activation+0.000
atal
Tokenatal
Feature activation+0.000
environment
Token environment
Feature activation+5.383
suggests
Token suggests
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
to
Token to
Feature activation+0.000
taking
Token taking
Feature activation+0.000
iodine
Token iodine
Feature activation+0.000
.
Token.
Feature activation+0.000
Documents
Token Documents
Feature activation+0.000
released
Token released
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
bureau
Token bureau
Feature activation+5.544
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
samples
Token samples
Feature activation+0.472
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.104
Non
Token Non
Feature activation+0.000
-
Token-
Feature activation+0.000
Pro
TokenPro
Feature activation+0.000
fit
Tokenfit
Feature activation+0.000
Housing
Token Housing
Feature activation+0.000
Association
Token Association
Feature activation+5.205
(
Token (
Feature activation+0.000
BC
TokenBC
Feature activation+0.000
NP
TokenNP
Feature activation+0.000
HA
TokenHA
Feature activation+0.000
)
Token)
Feature activation+4.384

INTERVAL 4.485 - 5.125
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
figures
Token figures
Feature activation+0.396
cited
Token cited
Feature activation+1.144
below
Token below
Feature activation+4.497
come
Token come
Feature activation+0.000
from
Token from
Feature activation+0.000
surveys
Token surveys
Feature activation+0.000
conducted
Token conducted
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
SF
Token SF
Feature activation+0.000
U
TokenU
Feature activation+0.000
City
Token City
Feature activation+0.000
Program
Token Program
Feature activation+0.433
,
Token,
Feature activation+5.015
shows
Token shows
Feature activation+0.000
varying
Token varying
Feature activation+0.000
levels
Token levels
Feature activation+0.000
of
Token of
Feature activation+0.000
renters
Token renters
Feature activation+0.000
videos
Token videos
Feature activation+0.896
allegedly
Token allegedly
Feature activation+3.703
showing
Token showing
Feature activation+0.000
the
Token the
Feature activation+0.000
bombed
Token bombed
Feature activation+0.000
headquarters
Token headquarters
Feature activation+4.722
quickly
Token quickly
Feature activation+3.570
emerged
Token emerged
Feature activation+0.000
online
Token online
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
statistics
Token statistics
Feature activation+0.163
on
Token on
Feature activation+0.000
imprisonment
Token imprisonment
Feature activation+4.074
further
Token further
Feature activation+4.844
demonstrate
Token demonstrate
Feature activation+0.000
the
Token the
Feature activation+0.000
extremes
Token extremes
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Oakland
Token Oakland
Feature activation+0.000
Privacy
Token Privacy
Feature activation+0.000
Working
Token Working
Feature activation+0.000
Group
Token Group
Feature activation+5.025
,
Token,
Feature activation+1.574
a
Token a
Feature activation+0.000
coalition
Token coalition
Feature activation+0.000
opposed
Token opposed
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 3.844 - 4.485
CONTAINS 0.002%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Images
TokenImages
Feature activation+0.000
taken
Token taken
Feature activation+0.318
on
Token on
Feature activation+0.000
Thursday
Token Thursday
Feature activation+4.150
shows
Token shows
Feature activation+0.000
all
Token all
Feature activation+0.000
-
Token-
Feature activation+0.000
male
Tokenmale
Feature activation+0.000
groups
Token groups
Feature activation+0.000
details
Token details
Feature activation+0.222
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
March
Token March
Feature activation+0.000
4
Token 4
Feature activation+0.000
incident
Token incident
Feature activation+4.093
emerged
Token emerged
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.022
from
Token from
Feature activation+0.000
interviews
Token interviews
Feature activation+0.000
and
Token and
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
strong
Token strong
Feature activation+0.000
opposition
Token opposition
Feature activation+0.000
to
Token to
Feature activation+0.000
legalization
Token legalization
Feature activation+4.216
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
private
Token private
Feature activation+0.000
appearance
Token appearance
Feature activation+0.613
,
Token,
Feature activation+2.260
.
Token.
Feature activation+0.000
Data
Token Data
Feature activation+0.000
returned
Token returned
Feature activation+1.737
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
mission
Token mission
Feature activation+4.185
will
Token will
Feature activation+0.856
help
Token help
Feature activation+0.000
Nasa
Token Nasa
Feature activation+0.000
identify
Token identify
Feature activation+0.000
safe
Token safe
Feature activation+0.000
emails
Token emails
Feature activation+0.897
,
Token,
Feature activation+0.165
reviewed
Token reviewed
Feature activation+0.000
by
Token by
Feature activation+0.000
Reuters
Token Reuters
Feature activation+1.720
,
Token,
Feature activation+4.042
were
Token were
Feature activation+0.457
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
batch
Token batch
Feature activation+0.191

INTERVAL 3.203 - 3.844
CONTAINS 0.002%

wall
Token wall
Feature activation+2.632
and
Token and
Feature activation+0.000
desk
Token desk
Feature activation+2.492
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
office
Token office
Feature activation+3.371
belong
Token belong
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
previous
Token previous
Feature activation+0.000
occupant
Token occupant
Feature activation+0.000
yet
Token yet
Feature activation+0.000
backing
Token backing
Feature activation+0.000
al
Token al
Feature activation+0.000
Assad
Token Assad
Feature activation+1.763
for
Token for
Feature activation+0.000
president
Token president
Feature activation+3.390
did
Token did
Feature activation+0.038
not
Token not
Feature activation+0.000
support
Token support
Feature activation+0.000
the
Token the
Feature activation+0.000
carefully
Token carefully
Feature activation+0.000
which
Token which
Feature activation+0.000
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
released
Token released
Feature activation+0.000
,
Token,
Feature activation+3.236
might
Token might
Feature activation+1.040
have
Token have
Feature activation+2.424
revealed
Token revealed
Feature activation+0.000
whether
Token whether
Feature activation+0.000
he
Token he
Feature activation+0.000
The
TokenThe
Feature activation+0.000
election
Token election
Feature activation+0.000
results
Token results
Feature activation+0.011
earlier
Token earlier
Feature activation+0.650
this
Token this
Feature activation+0.000
month
Token month
Feature activation+3.235
surprised
Token surprised
Feature activation+0.000
almost
Token almost
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
available
Token available
Feature activation+0.108
a
Token a
Feature activation+0.000
source
Token source
Feature activation+0.000
of
Token of
Feature activation+0.000
data
Token data
Feature activation+0.237
)
Token)
Feature activation+3.748
show
Token show
Feature activation+0.000
crime
Token crime
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
person
Token person
Feature activation+0.000

INTERVAL 2.563 - 3.203
CONTAINS 0.002%

TR
TokenTR
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
between
Token between
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
and
Token and
Feature activation+0.000
2014
Token 2014
Feature activation+2.619
practically
Token practically
Feature activation+1.401
doubled
Token doubled
Feature activation+0.000
,
Token,
Feature activation+0.000
recently
Token recently
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Second
Token Second
Feature activation+0.000
Bo
Token Bo
Feature activation+0.000
er
Tokener
Feature activation+0.000
War
Token War
Feature activation+2.909
that
Token that
Feature activation+1.035
show
Token show
Feature activation+0.000
battle
Token battle
Feature activation+0.000
scenes
Token scenes
Feature activation+1.142
from
Token from
Feature activation+0.000
The
Token The
Feature activation+0.000
extraordinary
Token extraordinary
Feature activation+0.000
debt
Token debt
Feature activation+0.000
figures
Token figures
Feature activation+1.605
of
Token of
Feature activation+0.000
Cyprus
Token Cyprus
Feature activation+2.701
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
results
Token results
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
lawyer
Token lawyer
Feature activation+2.019
and
Token and
Feature activation+0.000
public
Token public
Feature activation+0.000
servant
Token servant
Feature activation+2.632
demonstrates
Token demonstrates
Feature activation+0.000
a
Token a
Feature activation+0.000
fidelity
Token fidelity
Feature activation+0.000
to
Token to
Feature activation+0.000
law
Token law
Feature activation+0.000
fans
Token fans
Feature activation+4.015
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
crowd
Token crowd
Feature activation+4.227
appears
Token appears
Feature activation+0.025
to
Token to
Feature activation+2.877
show
Token show
Feature activation+0.000
the
Token the
Feature activation+0.000
flash
Token flash
Feature activation+0.000
point
Tokenpoint
Feature activation+0.000
regarding
Token regarding
Feature activation+0.000

INTERVAL 1.922 - 2.563
CONTAINS 0.005%

raft
Token raft
Feature activation+0.000
of
Token of
Feature activation+0.000
economic
Token economic
Feature activation+0.000
data
Token data
Feature activation+0.000
this
Token this
Feature activation+0.000
week
Token week
Feature activation+2.520
won
Token won
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.765
tell
Token tell
Feature activation+0.000
involvement
Token involvement
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000
justice
Token justice
Feature activation+0.000
system
Token system
Feature activation+1.933
are
Token are
Feature activation+0.000
well
Token well
Feature activation+0.000
known
Token known
Feature activation+0.000
among
Token among
Feature activation+0.000
policy
Token policy
Feature activation+0.000
-
Token-
Feature activation+0.000
14
Token14
Feature activation+0.000
aud
Token aud
Feature activation+0.000
ited
Tokenited
Feature activation+0.000
financial
Token financial
Feature activation+0.000
reports
Token reports
Feature activation+2.191
were
Token were
Feature activation+0.047
not
Token not
Feature activation+0.277
signed
Token signed
Feature activation+0.000
off
Token off
Feature activation+0.000
until
Token until
Feature activation+0.451
by
Token by
Feature activation+0.000
Al
Token Al
Feature activation+0.000
Jazeera
Token Jazeera
Feature activation+2.173
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
hospital
Token hospital
Feature activation+1.924
showed
Token showed
Feature activation+0.000
patients
Token patients
Feature activation+0.000
and
Token and
Feature activation+0.000
staff
Token staff
Feature activation+0.000
struggling
Token struggling
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
were
Token were
Feature activation+0.000
directly
Token directly
Feature activation+0.000
involved
Token involved
Feature activation+2.250
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
war
Tokenwar
Feature activation+0.565

INTERVAL 1.281 - 1.922
CONTAINS 0.012%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
findings
Token findings
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+1.485
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
useful
Token useful
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
records
Token records
Feature activation+0.566
obtained
Token obtained
Feature activation+0.699
by
Token by
Feature activation+0.000
The
Token The
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Post
Token Post
Feature activation+1.749
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
revelations
Token revelations
Feature activation+0.822
types
Token types
Feature activation+0.000
of
Token of
Feature activation+0.000
crime
Token crime
Feature activation+0.000
)
Token)
Feature activation+4.368
and
Token and
Feature activation+0.274
surveys
Token surveys
Feature activation+1.564
of
Token of
Feature activation+0.000
victims
Token victims
Feature activation+4.014
(
Token (
Feature activation+0.807
which
Tokenwhich
Feature activation+1.383
should
Token should
Feature activation+0.967
building
Token building
Feature activation+0.000
April
Token April
Feature activation+0.000
15
Token 15
Feature activation+0.000
.
Token.
Feature activation+0.000
Plans
Token Plans
Feature activation+0.182
also
Token also
Feature activation+1.332
include
Token include
Feature activation+0.000
a
Token a
Feature activation+0.000
two
Token two
Feature activation+0.000
-
Token-
Feature activation+0.000
story
Tokenstory
Feature activation+0.000
(
Token (
Feature activation+0.000
est
Tokenest
Feature activation+0.000
imates
Tokenimates
Feature activation+0.000
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
course
Token course
Feature activation+1.837
)
Token)
Feature activation+0.000
which
Token which
Feature activation+0.000
isn
Token isn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 0.641 - 1.281
CONTAINS 0.026%

the
Token the
Feature activation+0.000
documents
Token documents
Feature activation+0.000
obtained
Token obtained
Feature activation+0.000
by
Token by
Feature activation+0.000
The
Token The
Feature activation+0.000
Intercept
Token Intercept
Feature activation+1.050
and
Token and
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.582
showed
Token showed
Feature activation+0.000
from
Token from
Feature activation+0.000
Daniel
Token Daniel
Feature activation+0.000
Ther
Token Ther
Feature activation+0.000
rien
Tokenrien
Feature activation+0.392
's
Token's
Feature activation+0.000
office
Token office
Feature activation+0.709
found
Token found
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
Sw
TokenSw
Feature activation+0.000
art
Tokenart
Feature activation+0.000
mod
Tokenmod
Feature activation+0.000
der
Tokender
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.898
.
Token.
Feature activation+0.000
Mast
Token Mast
Feature activation+0.000
cam
Tokencam
Feature activation+0.000
will
Token will
Feature activation+0.000
document
Token document
Feature activation+0.000
and
Token and
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
debt
Token debt
Feature activation+1.177
are
Token are
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
election
Token election
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
polls
Token polls
Feature activation+0.000
did
Token did
Feature activation+0.142
not
Token not
Feature activation+0.712
cover
Token cover
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
with
Token with
Feature activation+0.000
glory
Token glory
Feature activation+0.000
during
Token during
Feature activation+0.000

INTERVAL 0.000 - 0.641
CONTAINS 99.950%

O
Token O
Feature activation+0.000
GE
TokenGE
Feature activation+0.000
will
Token will
Feature activation+0.000
promul
Token promul
Feature activation+0.000
gate
Tokengate
Feature activation+0.000
rules
Token rules
Feature activation+0.000
and
Token and
Feature activation+0.000
procedures
Token procedures
Feature activation+0.000
to
Token to
Feature activation+0.000
record
Token record
Feature activation+0.000
all
Token all
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
even
Token even
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
him
Token him
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
G
TokenG
Feature activation+0.000
areth
Tokenareth
Feature activation+0.000
Brick
Token Brick
Feature activation+0.000
man
Tokenman
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
analyst
Token analyst
Feature activation+0.000
at
Token at
Feature activation+0.000
help
Token help
Feature activation+0.000
.
Token.
Feature activation+0.000
Help
Token Help
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
taking
Token taking
Feature activation+0.000
advantage
Token advantage
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
vulnerable
Token vulnerable
Feature activation+0.000
and
Token and
Feature activation+0.000
driven
Token driven
Feature activation+0.000
by
Token by
Feature activation+0.000
opportun
Token opportun
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
and
Token and
Feature activation+0.000
proximity
Token proximity
Feature activation+0.000
;
Token;
Feature activation+0.000
If
Token If
Feature activation+0.000
African
Token African
Feature activation+0.000
-
Token-
Feature activation+0.000
Americans
TokenAmericans
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H11.10: (feature 16773)

TOP ACTIVATIONS
MAX = 5.571

better
Token better
Feature activation+0.000
now
Token now
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.000
used
Token used
Feature activation+0.000
to
Token to
Feature activation+5.571
be
Token be
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
certainly
Token certainly
Feature activation+0.000
better
Token better
Feature activation+0.000
verdict
Token verdict
Feature activation+1.771
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
George
Token George
Feature activation+0.000
Zimmerman
Token Zimmerman
Feature activation+0.000
case
Token case
Feature activation+4.637
end
Token end
Feature activation+0.000
differently
Token differently
Feature activation+0.000
than
Token than
Feature activation+0.016
expected
Token expected
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
imperfect
Token imperfect
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
may
Token may
Feature activation+3.898
be
Token be
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
democracy
Token democracy
Feature activation+0.000
relative
Token relative
Feature activation+0.000
impact
Token impact
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
problem
Token problem
Feature activation+0.004
would
Token would
Feature activation+3.890
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.000
short
Token short
Feature activation+0.000
goal
Token goal
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
beginning
Token beginning
Feature activation+1.171
has
Token has
Feature activation+1.705
always
Token always
Feature activation+3.842
been
Token been
Feature activation+0.000
Formula
Token Formula
Feature activation+0.000
1
Token 1
Feature activation+0.000
for
Token for
Feature activation+0.000
me
Token me
Feature activation+0.000
everybody
Token everybody
Feature activation+0.000
's
Token's
Feature activation+0.000
ultimate
Token ultimate
Feature activation+0.000
goal
Token goal
Feature activation+0.000
has
Token has
Feature activation+1.269
always
Token always
Feature activation+3.789
been
Token been
Feature activation+0.000
F
Token F
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.000
illy
Tokenilly
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
may
Token may
Feature activation+3.776
sound
Token sound
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
still
Token still
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
popular
Token popular
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+3.541
been
Token been
Feature activation+0.000
since
Token since
Feature activation+0.000
1976
Token 1976
Feature activation+0.000
.
Token.
Feature activation+0.000
Conservatives
Token Conservatives
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
into
Token into
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.000
actually
Token actually
Feature activation+3.464
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.000
Really
Token Really
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
citizen
Token citizen
Feature activation+0.000
.
Token.
Feature activation+0.000
Charges
Token Charges
Feature activation+0.000
have
Token have
Feature activation+1.925
not
Token not
Feature activation+2.612
yet
Token yet
Feature activation+3.357
been
Token been
Feature activation+0.000
filed
Token filed
Feature activation+0.300
against
Token against
Feature activation+0.000
D
Token D
Feature activation+0.000
zh
Tokenzh
Feature activation+0.000
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
decision
Token decision
Feature activation+0.000
has
Token has
Feature activation+1.405
not
Token not
Feature activation+2.447
yet
Token yet
Feature activation+3.351
been
Token been
Feature activation+0.000
made
Token made
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
terrorist
Token terrorist
Feature activation+0.000
as
Token as
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
challenges
Token challenges
Feature activation+0.734
may
Token may
Feature activation+3.293
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.000
countries
Token countries
Feature activation+0.000
have
Token have
Feature activation+0.000
less
Token less
Feature activation+0.000
compassionate
Token compassionate
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.586
have
Token have
Feature activation+3.204
been
Token been
Feature activation+0.000
with
Token with
Feature activation+0.000
you
Token you
Feature activation+0.000
guiding
Token guiding
Feature activation+0.000
it
Token it
Feature activation+0.000
problem
Token problem
Feature activation+0.000
and
Token and
Feature activation+0.000
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
solution
Token solution
Feature activation+0.684
might
Token might
Feature activation+3.094
be
Token be
Feature activation+0.659
?
Token?
Feature activation+0.000
Is
Token Is
Feature activation+0.000
this
Token this
Feature activation+0.000
a
Token a
Feature activation+0.000
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
potential
Token potential
Feature activation+0.000
for
Token for
Feature activation+0.000
there
Token there
Feature activation+0.000
to
Token to
Feature activation+3.022
be
Token be
Feature activation+0.000
information
Token information
Feature activation+0.000
of
Token of
Feature activation+0.000
screening
Token screening
Feature activation+0.000
value
Token value
Feature activation+0.000
policy
Token policy
Feature activation+0.000
,
Token,
Feature activation+0.000
terms
Token terms
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
contract
Token contract
Feature activation+3.006
were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.000
disclosed
Token disclosed
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
deal
Token deal
Feature activation+0.000
more
Token more
Feature activation+0.000
divided
Token divided
Feature activation+0.000
than
Token than
Feature activation+0.000
they
Token they
Feature activation+0.000
already
Token already
Feature activation+2.956
are
Token are
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
No
TokenNo
Feature activation+0.000
arrest
Token arrest
Feature activation+0.000
has
Token has
Feature activation+2.898
been
Token been
Feature activation+0.083
made
Token made
Feature activation+0.000
.
Token.
Feature activation+0.000
Crime
Token Crime
Feature activation+0.000
St
Token St
Feature activation+0.000
chaotic
Token chaotic
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.000
ever
Token ever
Feature activation+1.953
needed
Token needed
Feature activation+0.082
to
Token to
Feature activation+2.826
be
Token be
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
strike
Token strike
Feature activation+0.000
one
Token one
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
,
Token,
Feature activation+0.000
notices
Token notices
Feature activation+0.000
and
Token and
Feature activation+0.000
banners
Token banners
Feature activation+1.106
will
Token will
Feature activation+2.794
be
Token be
Feature activation+0.000
displayed
Token displayed
Feature activation+0.344
at
Token at
Feature activation+0.000
different
Token different
Feature activation+0.000
locations
Token locations
Feature activation+0.520

Top DFA by src position
MAX = 5.252

C
TokenC
Feature activation+0.011
Top resid features:
is
Token is
Feature activation+0.016
Top resid features:
better
Token better
Feature activation-0.070
Top resid features:
now
Token now
Feature activation+0.112
Top resid features:
than
Token than
Feature activation+0.071
Top resid features:
it
Token it
Feature activation+4.792
Top resid features:
used
Token used
Feature activation+0.499
Top resid features:
to
Token to
Feature activation+1.103
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
possible
Token possible
Feature activation+0.029
Top resid features:
violent
Token violent
Feature activation+0.028
Top resid features:
reaction
Token reaction
Feature activation+0.026
Top resid features:
should
Token should
Feature activation+0.032
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
verdict
Token verdict
Feature activation+5.252
Top resid features:
in
Token in
Feature activation+0.007
Top resid features:
the
Token the
Feature activation-0.019
Top resid features:
George
Token George
Feature activation+0.003
Top resid features:
Zimmerman
Token Zimmerman
Feature activation-0.031
Top resid features:
case
Token case
Feature activation+0.423
Top resid features:
country
Token country
Feature activation-0.007
Top resid features:
that
Token that
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.057
Top resid features:
imperfect
Token imperfect
Feature activation-0.067
Top resid features:
as
Token as
Feature activation+0.192
Top resid features:
it
Token it
Feature activation+3.505
Top resid features:
may
Token may
Feature activation+1.033
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
relative
Token relative
Feature activation+0.053
Top resid features:
impact
Token impact
Feature activation+0.495
Top resid features:
on
Token on
Feature activation+0.039
Top resid features:
the
Token the
Feature activation+0.037
Top resid features:
problem
Token problem
Feature activation+0.558
Top resid features:
would
Token would
Feature activation+3.525
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
both
Token both
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
short
Token short
Feature activation+0.000
Top resid features:
original
Token original
Feature activation+0.061
Top resid features:
goal
Token goal
Feature activation+1.329
Top resid features:
from
Token from
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
beginning
Token beginning
Feature activation+0.172
Top resid features:
has
Token has
Feature activation+2.379
Top resid features:
always
Token always
Feature activation+0.552
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
Formula
Token Formula
Feature activation+0.000
Top resid features:
1
Token 1
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
but
Token but
Feature activation+0.090
Top resid features:
everybody
Token everybody
Feature activation-0.013
Top resid features:
's
Token's
Feature activation-0.052
Top resid features:
ultimate
Token ultimate
Feature activation+0.029
Top resid features:
goal
Token goal
Feature activation+1.695
Top resid features:
has
Token has
Feature activation+1.285
Top resid features:
always
Token always
Feature activation+0.503
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
F
Token F
Feature activation+0.000
Top resid features:
1
Token1
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.105
Top resid features:
S
TokenS
Feature activation+0.013
Top resid features:
illy
Tokenilly
Feature activation-0.091
Top resid features:
as
Token as
Feature activation+0.057
Top resid features:
it
Token it
Feature activation+3.578
Top resid features:
may
Token may
Feature activation+1.053
Top resid features:
sound
Token sound
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
am
Token am
Feature activation+0.000
Top resid features:
word
Token word
Feature activation-0.053
Top resid features:
is
Token is
Feature activation+0.018
Top resid features:
more
Token more
Feature activation+0.016
Top resid features:
popular
Token popular
Feature activation+0.055
Top resid features:
than
Token than
Feature activation+0.069
Top resid features:
it
Token it
Feature activation+4.413
Top resid features:
has
Token has
Feature activation+0.562
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
1976
Token 1976
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
harder
Token harder
Feature activation+0.058
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
get
Token get
Feature activation+0.009
Top resid features:
into
Token into
Feature activation-0.069
Top resid features:
than
Token than
Feature activation+0.021
Top resid features:
it
Token it
Feature activation+3.490
Top resid features:
actually
Token actually
Feature activation+1.292
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Really
Token Really
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
S
TokenS
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
citizen
Token citizen
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
Charges
Token Charges
Feature activation+0.938
Top resid features:
have
Token have
Feature activation+1.291
Top resid features:
not
Token not
Feature activation+1.121
Top resid features:
yet
Token yet
Feature activation+0.658
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
filed
Token filed
Feature activation+0.000
Top resid features:
against
Token against
Feature activation+0.000
Top resid features:
ye
Tokenye
Feature activation+0.000
Top resid features:
h
Tokenh
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
final
Token final
Feature activation+0.019
Top resid features:
decision
Token decision
Feature activation+2.191
Top resid features:
has
Token has
Feature activation+0.755
Top resid features:
not
Token not
Feature activation+0.721
Top resid features:
yet
Token yet
Feature activation+0.381
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
made
Token made
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
as
Token as
Feature activation+0.134
Top resid features:
difficult
Token difficult
Feature activation+0.092
Top resid features:
as
Token as
Feature activation+0.152
Top resid features:
the
Token the
Feature activation+0.077
Top resid features:
challenges
Token challenges
Feature activation+2.843
Top resid features:
may
Token may
Feature activation+0.833
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Both
Token Both
Feature activation+0.000
Top resid features:
countries
Token countries
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
less
Token less
Feature activation-0.007
Top resid features:
compassionate
Token compassionate
Feature activation+0.035
Top resid features:
than
Token than
Feature activation-0.083
Top resid features:
it
Token it
Feature activation+1.310
Top resid features:
would
Token would
Feature activation+3.059
Top resid features:
have
Token have
Feature activation+0.192
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
guiding
Token guiding
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.023
Top resid features:
problem
Token problem
Feature activation+0.116
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
what
Token what
Feature activation+0.036
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
solution
Token solution
Feature activation+3.501
Top resid features:
might
Token might
Feature activation+0.661
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Is
Token Is
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.121
Top resid features:
a
Token a
Feature activation+0.086
Top resid features:
potential
Token potential
Feature activation+0.014
Top resid features:
for
Token for
Feature activation+0.075
Top resid features:
there
Token there
Feature activation+0.931
Top resid features:
to
Token to
Feature activation+1.565
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
information
Token information
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
screening
Token screening
Feature activation+0.000
Top resid features:
value
Token value
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.115
Top resid features:
Per
Token Per
Feature activation+0.174
Top resid features:
club
Token club
Feature activation+0.009
Top resid features:
policy
Token policy
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.059
Top resid features:
terms
Token terms
Feature activation+4.189
Top resid features:
of
Token of
Feature activation-0.016
Top resid features:
the
Token the
Feature activation-0.071
Top resid features:
contract
Token contract
Feature activation+0.124
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
great
Token great
Feature activation+0.003
Top resid features:
deal
Token deal
Feature activation+0.002
Top resid features:
more
Token more
Feature activation+0.025
Top resid features:
divided
Token divided
Feature activation+0.060
Top resid features:
than
Token than
Feature activation+0.105
Top resid features:
they
Token they
Feature activation+3.219
Top resid features:
already
Token already
Feature activation+0.726
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
All
Token All
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
scene
Token scene
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.035
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
No
TokenNo
Feature activation+0.112
Top resid features:
arrest
Token arrest
Feature activation+2.711
Top resid features:
has
Token has
Feature activation+1.045
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
made
Token made
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Crime
Token Crime
Feature activation+0.000
Top resid features:
far
Token far
Feature activation+0.118
Top resid features:
more
Token more
Feature activation+0.179
Top resid features:
chaotic
Token chaotic
Feature activation+0.043
Top resid features:
than
Token than
Feature activation+0.065
Top resid features:
it
Token it
Feature activation+1.041
Top resid features:
ever
Token ever
Feature activation+1.327
Top resid features:
needed
Token needed
Feature activation+0.604
Top resid features:
to
Token to
Feature activation+0.810
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
awareness
Token awareness
Feature activation+0.028
Top resid features:
campaign
Token campaign
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
notices
Token notices
Feature activation+1.520
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
banners
Token banners
Feature activation+1.591
Top resid features:
will
Token will
Feature activation+0.459
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
displayed
Token displayed
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
different
Token different
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.04

Head 2: 0.03

Head 3: 0.04

Head 4: 0.04

Head 5: 0.04

Head 6: 0.02

Head 7: 0.05

Head 8: 0.11

Head 9: 0.03

Head 10: 0.38

Head 11: 0.13

Positive logits

be3.07

Bey3.05

Be2.73

actionDate2.72

displayText2.65

Beet2.63

ÃÂ2.57

be2.48

Disney2.48

★★2.43

Be2.41

been2.40

BE2.38

BE2.36

bee2.36

2.32

Beetle2.30

Cubs2.29

Been2.26

ividual2.26

Negative logits

Moran-2.80

sends-2.40

translates-2.37

pauses-2.35

wastes-2.32

rejects-2.26

buys-2.25

splits-2.21

partitions-2.20

paints-2.20

mining-2.19

destroys-2.18

compares-2.14

locks-2.13

investigates-2.13

invests-2.13

slices-2.13

lishes-2.12

wills-2.12

defends-2.11

INTERVAL 5.014 - 5.571
CONTAINS 0.000%

better
Token better
Feature activation+0.000
now
Token now
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.000
used
Token used
Feature activation+0.000
to
Token to
Feature activation+5.571
be
Token be
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
certainly
Token certainly
Feature activation+0.000
better
Token better
Feature activation+0.000

INTERVAL 4.457 - 5.014
CONTAINS 0.000%

verdict
Token verdict
Feature activation+1.771
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
George
Token George
Feature activation+0.000
Zimmerman
Token Zimmerman
Feature activation+0.000
case
Token case
Feature activation+4.637
end
Token end
Feature activation+0.000
differently
Token differently
Feature activation+0.000
than
Token than
Feature activation+0.016
expected
Token expected
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.900 - 4.457
CONTAINS 0.000%

INTERVAL 3.343 - 3.900
CONTAINS 0.001%

relative
Token relative
Feature activation+0.000
impact
Token impact
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
problem
Token problem
Feature activation+0.004
would
Token would
Feature activation+3.890
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.000
short
Token short
Feature activation+0.000
goal
Token goal
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
beginning
Token beginning
Feature activation+1.171
has
Token has
Feature activation+1.705
always
Token always
Feature activation+3.842
been
Token been
Feature activation+0.000
Formula
Token Formula
Feature activation+0.000
1
Token 1
Feature activation+0.000
for
Token for
Feature activation+0.000
me
Token me
Feature activation+0.000
citizen
Token citizen
Feature activation+0.000
.
Token.
Feature activation+0.000
Charges
Token Charges
Feature activation+0.000
have
Token have
Feature activation+1.925
not
Token not
Feature activation+2.612
yet
Token yet
Feature activation+3.357
been
Token been
Feature activation+0.000
filed
Token filed
Feature activation+0.300
against
Token against
Feature activation+0.000
D
Token D
Feature activation+0.000
zh
Tokenzh
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
popular
Token popular
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+3.541
been
Token been
Feature activation+0.000
since
Token since
Feature activation+0.000
1976
Token 1976
Feature activation+0.000
.
Token.
Feature activation+0.000
Conservatives
Token Conservatives
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
into
Token into
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.000
actually
Token actually
Feature activation+3.464
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.000
Really
Token Really
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 2.786 - 3.343
CONTAINS 0.001%

's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
potential
Token potential
Feature activation+0.000
for
Token for
Feature activation+0.000
there
Token there
Feature activation+0.000
to
Token to
Feature activation+3.022
be
Token be
Feature activation+0.000
information
Token information
Feature activation+0.000
of
Token of
Feature activation+0.000
screening
Token screening
Feature activation+0.000
value
Token value
Feature activation+0.000
chaotic
Token chaotic
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.000
ever
Token ever
Feature activation+1.953
needed
Token needed
Feature activation+0.082
to
Token to
Feature activation+2.826
be
Token be
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
strike
Token strike
Feature activation+0.000
one
Token one
Feature activation+0.000
deal
Token deal
Feature activation+0.000
more
Token more
Feature activation+0.000
divided
Token divided
Feature activation+0.000
than
Token than
Feature activation+0.000
they
Token they
Feature activation+0.000
already
Token already
Feature activation+2.956
are
Token are
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
tomorrow
Token tomorrow
Feature activation+0.000
night
Token night
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
would
Token would
Feature activation+0.052
've
Token've
Feature activation+2.789
been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.000
celebr
Token celebr
Feature activation+0.000
atory
Tokenatory
Feature activation+0.000
riot
Token riot
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
No
TokenNo
Feature activation+0.000
arrest
Token arrest
Feature activation+0.000
has
Token has
Feature activation+2.898
been
Token been
Feature activation+0.083
made
Token made
Feature activation+0.000
.
Token.
Feature activation+0.000
Crime
Token Crime
Feature activation+0.000
St
Token St
Feature activation+0.000

INTERVAL 2.228 - 2.786
CONTAINS 0.002%

.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
Specifically
TokenSpecifically
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
have
Token have
Feature activation+2.394
been
Token been
Feature activation+0.000
more
Token more
Feature activation+0.000
discipline
Token discipline
Feature activation+0.000
referrals
Token referrals
Feature activation+0.000
for
Token for
Feature activation+0.000
less
Token less
Feature activation+0.000
valuable
Token valuable
Feature activation+0.000
than
Token than
Feature activation+0.000
they
Token they
Feature activation+0.000
used
Token used
Feature activation+0.000
to
Token to
Feature activation+2.458
be
Token be
Feature activation+0.000
for
Token for
Feature activation+0.000
players
Token players
Feature activation+0.000
and
Token and
Feature activation+0.000
guild
Token guild
Feature activation+0.000
express
Token express
Feature activation+0.000
apology
Token apology
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
will
Token will
Feature activation+0.319
likely
Token likely
Feature activation+2.319
be
Token be
Feature activation+0.000
moral
Token moral
Feature activation+0.000
equival
Token equival
Feature activation+0.000
ence
Tokenence
Feature activation+0.000
like
Token like
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
will
Token will
Feature activation+0.414
also
Token also
Feature activation+2.237
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
limited
Token limited
Feature activation+0.000
Nickel
Token Nickel
Feature activation+0.000
Creek
Token Creek
Feature activation+0.000
the
Token the
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
.
Token.
Feature activation+0.000
Tomorrow
Token Tomorrow
Feature activation+0.000
it
Token it
Feature activation+0.181
could
Token could
Feature activation+2.539
be
Token be
Feature activation+0.000
us
Token us
Feature activation+0.000
."
Token."
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Some
TokenSome
Feature activation+0.000

INTERVAL 1.671 - 2.228
CONTAINS 0.007%

This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
worst
Token worst
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+1.728
ever
Token ever
Feature activation+1.834
been
Token been
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
simple
Token simple
Feature activation+0.000
ton
Tokenton
Feature activation+0.000
warrior
Token warrior
Feature activation+0.000
he
Token he
Feature activation+0.000
appears
Token appears
Feature activation+0.000
to
Token to
Feature activation+2.023
be
Token be
Feature activation+0.000
at
Token at
Feature activation+0.000
first
Token first
Feature activation+0.000
glance
Token glance
Feature activation+0.000
.
Token.
Feature activation+0.000
are
Token are
Feature activation+0.000
(
Token (
Feature activation+0.000
or
Tokenor
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
should
Token should
Feature activation+1.683
be
Token be
Feature activation+0.000
)
Token)
Feature activation+0.000
deeply
Token deeply
Feature activation+0.000
interconnected
Token interconnected
Feature activation+0.000
,
Token,
Feature activation+0.000
mess
Token mess
Feature activation+0.000
of
Token of
Feature activation+0.000
things
Token things
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
ever
Token ever
Feature activation+1.866
was
Token was
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Contact
TokenContact
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
said
Token said
Feature activation+0.000
more
Token more
Feature activation+0.000
steps
Token steps
Feature activation+0.000
may
Token may
Feature activation+1.679
follow
Token follow
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
If
TokenIf
Feature activation+0.000

INTERVAL 1.114 - 1.671
CONTAINS 0.010%

forced
Token forced
Feature activation+0.000
entry
Token entry
Feature activation+0.000
and
Token and
Feature activation+0.000
keys
Token keys
Feature activation+0.000
may
Token may
Feature activation+0.000
have
Token have
Feature activation+1.248
been
Token been
Feature activation+0.000
used
Token used
Feature activation+0.000
,
Token,
Feature activation+0.000
allowing
Token allowing
Feature activation+0.000
an
Token an
Feature activation+0.000
the
Token the
Feature activation+0.000
comfort
Token comfort
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
believed
Token believed
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+1.578
be
Token be
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
plaintiffs
Token plaintiffs
Feature activation+0.000
'
Token'
Feature activation+0.000
claims
Token claims
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
conce
Token conce
Feature activation+0.000
ivably
Tokenivably
Feature activation+1.260
be
Token be
Feature activation+0.000
typical
Token typical
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
claims
Token claims
Feature activation+0.000
In
TokenIn
Feature activation+0.000
recent
Token recent
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+1.397
been
Token been
Feature activation+0.000
shocking
Token shocking
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
reports
Token reports
Feature activation+0.000
disturbing
Token disturbing
Feature activation+0.000
message
Token message
Feature activation+0.000
that
Token that
Feature activation+0.000
their
Token their
Feature activation+0.000
lives
Token lives
Feature activation+0.000
have
Token have
Feature activation+1.219
little
Token little
Feature activation+0.137
to
Token to
Feature activation+0.294
no
Token no
Feature activation+0.000
value
Token value
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.557 - 1.114
CONTAINS 0.030%

the
Token the
Feature activation+0.000
Crimean
Token Crimean
Feature activation+0.000
annexation
Token annexation
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
have
Token have
Feature activation+0.815
been
Token been
Feature activation+0.000
about
Token about
Feature activation+0.000
22
Token 22
Feature activation+0.000
people
Token people
Feature activation+0.000
missing
Token missing
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
law
Token law
Feature activation+0.000
can
Token can
Feature activation+0.000
or
Token or
Feature activation+0.000
should
Token should
Feature activation+0.859
be
Token be
Feature activation+0.000
used
Token used
Feature activation+0.000
to
Token to
Feature activation+0.000
facilitate
Token facilitate
Feature activation+0.000
the
Token the
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
expect
Token expect
Feature activation+0.000
there
Token there
Feature activation+0.000
to
Token to
Feature activation+1.030
be
Token be
Feature activation+0.000
better
Token better
Feature activation+0.000
reception
Token reception
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
get
Token get
Feature activation+0.000
more
Token more
Feature activation+0.000
deadly
Token deadly
Feature activation+0.000
serious
Token serious
Feature activation+0.000
than
Token than
Feature activation+0.000
it
Token it
Feature activation+1.066
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
is
Token is
Feature activation+0.000
where
Token where
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.755
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
division
Token division
Feature activation+0.000
within
Token within
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.557
CONTAINS 99.949%

gender
Token gender
Feature activation+0.000
.'"
Token.'"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
finally
Token finally
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
asked
Token asked
Feature activation+0.000
if
Token if
Feature activation+0.000
a
Token a
Feature activation+0.000
coffee
Token coffee
Feature activation+0.000
,
Token,
Feature activation+0.000
wool
Token wool
Feature activation+0.000
,
Token,
Feature activation+0.000
pepper
Token pepper
Feature activation+0.000
,
Token,
Feature activation+0.000
ginger
Token ginger
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
and
Token and
Feature activation+0.000
opium
Token opium
Feature activation+0.000
,
Token,
Feature activation+0.000
August
Token August
Feature activation+0.000
2003
Token 2003
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
People
TokenPeople
Feature activation+0.000
's
Token's
Feature activation+0.000
memories
Token memories
Feature activation+0.000
are
Token are
Feature activation+0.000
short
Token short
Feature activation+0.000
,"
Token,"
Feature activation+0.000
says
Token says
Feature activation+0.000
civil
Token civil
Feature activation+0.000
war
Token war
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
IDF
Token IDF
Feature activation+0.000
has
Token has
Feature activation+0.000
set
Token set
Feature activation+0.000
up
Token up
Feature activation+0.000
a
Token a
Feature activation+0.000
field
Token field
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
-
Token-
Feature activation+0.000
time
Tokentime
Feature activation+0.000
player
Token player
Feature activation+0.000
of
Token of
Feature activation+0.000
Marvel
Token Marvel
Feature activation+0.000
Avengers
Token Avengers
Feature activation+0.000
Alliance
Token Alliance
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H11.10: (feature 11587)

TOP ACTIVATIONS
MAX = 4.353

house
Token house
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+4.353
been
Token been
Feature activation+0.000
much
Token much
Feature activation+0.000
worse
Token worse
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
me
Token me
Feature activation+0.000
it
Token it
Feature activation+0.000
could
Token could
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.793
ve
Tokenve
Feature activation+3.929
been
Token been
Feature activation+0.000
avoided
Token avoided
Feature activation+0.000
.
Token.
Feature activation+0.000
Or
Token Or
Feature activation+0.000
if
Token if
Feature activation+0.000
forward
Token forward
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
fish
Token fish
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+3.106
likely
Token likely
Feature activation+2.586
never
Token never
Feature activation+1.519
fed
Token fed
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
her
Token her
Feature activation+0.000
way
Token way
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
it
Token it
Feature activation+0.735
had
Token had
Feature activation+2.963
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
separate
Token separate
Feature activation+0.000
dining
Token dining
Feature activation+0.000
room
Token room
Feature activation+0.000
been
Token been
Feature activation+0.000
killed
Token killed
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
would
Token would
Feature activation+0.079
have
Token have
Feature activation+2.953
"
Token "
Feature activation+1.957
t
Tokent
Feature activation+0.000
aken
Tokenaken
Feature activation+0.000
steps
Token steps
Feature activation+0.000
to
Token to
Feature activation+0.000
speculate
Token speculate
Feature activation+0.000
how
Token how
Feature activation+0.000
Seth
Token Seth
Feature activation+0.000
Rich
Token Rich
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+2.802
become
Token become
Feature activation+0.000
disgruntled
Token disgruntled
Feature activation+0.000
after
Token after
Feature activation+0.000
witnessing
Token witnessing
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
things
Token things
Feature activation+0.000
haven
Token haven
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.177
t
Tokent
Feature activation+2.780
gone
Token gone
Feature activation+0.000
smoothly
Token smoothly
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
shortly
Token shortly
Feature activation+0.000
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
absolutely
Token absolutely
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+2.728
been
Token been
Feature activation+0.000
not
Token not
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
car
Token car
Feature activation+0.000
icycle
Tokenicycle
Feature activation+0.000
wouldn
Token wouldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.557
have
Token have
Feature activation+2.681
stood
Token stood
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
way
Token way
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
conservative
Token conservative
Feature activation+0.000
and
Token and
Feature activation+0.000
libertarian
Token libertarian
Feature activation+0.000
movement
Token movement
Feature activation+2.641
has
Token has
Feature activation+1.543
grown
Token grown
Feature activation+0.000
exponentially
Token exponentially
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
living
Token living
Feature activation+0.000
room
Token room
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
it
Token it
Feature activation+0.000
had
Token had
Feature activation+2.609
had
Token had
Feature activation+0.000
more
Token more
Feature activation+0.000
storage
Token storage
Feature activation+0.000
space
Token space
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
fish
Token fish
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+3.106
likely
Token likely
Feature activation+2.586
never
Token never
Feature activation+1.519
fed
Token fed
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
academ
Token academ
Feature activation+0.000
e
Tokene
Feature activation+2.568
have
Token have
Feature activation+1.657
been
Token been
Feature activation+0.146
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
forefront
Token forefront
Feature activation+0.000
the
Token the
Feature activation+0.000
violation
Token violation
Feature activation+0.000
,
Token,
Feature activation+0.000
Milwaukee
Token Milwaukee
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+2.520
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
chance
Token chance
Feature activation+0.000
to
Token to
Feature activation+0.000
tie
Token tie
Feature activation+0.000
and
Token and
Feature activation+0.000
travelling
Token travelling
Feature activation+0.000
by
Token by
Feature activation+0.000
horse
Token horse
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+2.499
meant
Token meant
Feature activation+0.000
days
Token days
Feature activation+0.000
of
Token of
Feature activation+0.000
travel
Token travel
Feature activation+0.000
for
Token for
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
better
Token better
Feature activation+0.000
,
Token,
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+2.443
been
Token been
Feature activation+0.000
if
Token if
Feature activation+0.000
there
Token there
Feature activation+0.000
had
Token had
Feature activation+0.912
been
Token been
Feature activation+0.000
Mark
Token Mark
Feature activation+0.000
had
Token had
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+2.429
easily
Token easily
Feature activation+2.110
found
Token found
Feature activation+0.000
out
Token out
Feature activation+0.000
about
Token about
Feature activation+0.000
these
Token these
Feature activation+0.000
bit
Token bit
Feature activation+0.000
later
Token later
Feature activation+0.000
the
Token the
Feature activation+0.000
riders
Token riders
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+2.354
peeled
Token peeled
Feature activation+0.000
out
Token out
Feature activation+0.000
from
Token from
Feature activation+0.000
behind
Token behind
Feature activation+0.000
each
Token each
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
They
TokenThey
Feature activation+0.000
would
Token would
Feature activation+0.000
also
Token also
Feature activation+2.103
have
Token have
Feature activation+2.306
assumed
Token assumed
Feature activation+0.000
that
Token that
Feature activation+0.000
one
Token one
Feature activation+0.000
loss
Token loss
Feature activation+0.000
so
Token so
Feature activation+0.000
my
Token my
Feature activation+0.000
seat
Token seat
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+2.224
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
even
Token even
Feature activation+0.000
at
Token at
Feature activation+0.000
my
Token my
Feature activation+0.000

Top DFA by src position
MAX = 4.577

the
Token the
Feature activation+0.099
Top resid features:
house
Token house
Feature activation+0.029
Top resid features:
earlier
Token earlier
Feature activation+0.029
Top resid features:
,
Token,
Feature activation+0.073
Top resid features:
it
Token it
Feature activation+0.338
Top resid features:
could
Token could
Feature activation+3.653
Top resid features:
have
Token have
Feature activation+0.788
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
much
Token much
Feature activation+0.000
Top resid features:
worse
Token worse
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
broken
Token broken
Feature activation-0.013
Top resid features:
up
Token up
Feature activation+0.014
Top resid features:
with
Token with
Feature activation+0.024
Top resid features:
me
Token me
Feature activation+0.033
Top resid features:
it
Token it
Feature activation+0.449
Top resid features:
could
Token could
Feature activation+4.577
Top resid features:
âĢ
TokenâĢ
Feature activation-0.012
Top resid features:
Ļ
TokenĻ
Feature activation+0.029
Top resid features:
ve
Tokenve
Feature activation+0.292
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
avoided
Token avoided
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.024
Top resid features:
forward
Token forward
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.030
Top resid features:
the
Token the
Feature activation+0.096
Top resid features:
fish
Token fish
Feature activation+0.132
Top resid features:
would
Token would
Feature activation+2.950
Top resid features:
have
Token have
Feature activation+0.460
Top resid features:
likely
Token likely
Feature activation+0.000
Top resid features:
never
Token never
Feature activation+0.000
Top resid features:
fed
Token fed
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.055
Top resid features:
living
Token living
Feature activation+0.005
Top resid features:
room
Token room
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
If
Token If
Feature activation+0.026
Top resid features:
it
Token it
Feature activation+1.189
Top resid features:
had
Token had
Feature activation+0.162
Top resid features:
had
Token had
Feature activation+0.077
Top resid features:
more
Token more
Feature activation+0.007
Top resid features:
storage
Token storage
Feature activation+0.014
Top resid features:
space
Token space
Feature activation+0.014
Top resid features:
have
Token have
Feature activation+0.078
Top resid features:
been
Token been
Feature activation+0.038
Top resid features:
killed
Token killed
Feature activation+0.089
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
and
Token and
Feature activation+0.040
Top resid features:
would
Token would
Feature activation+2.264
Top resid features:
have
Token have
Feature activation+0.143
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
aken
Tokenaken
Feature activation+0.000
Top resid features:
steps
Token steps
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
speculate
Token speculate
Feature activation-0.000
Top resid features:
how
Token how
Feature activation+0.064
Top resid features:
Seth
Token Seth
Feature activation+0.024
Top resid features:
Rich
Token Rich
Feature activation+0.074
Top resid features:
could
Token could
Feature activation+3.004
Top resid features:
have
Token have
Feature activation+0.229
Top resid features:
become
Token become
Feature activation+0.000
Top resid features:
disgruntled
Token disgruntled
Feature activation+0.000
Top resid features:
after
Token after
Feature activation+0.000
Top resid features:
witnessing
Token witnessing
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.100
Top resid features:
But
TokenBut
Feature activation+0.050
Top resid features:
since
Token since
Feature activation+0.059
Top resid features:
that
Token that
Feature activation+0.055
Top resid features:
time
Token time
Feature activation+0.114
Top resid features:
things
Token things
Feature activation+3.684
Top resid features:
haven
Token haven
Feature activation+0.150
Top resid features:
âĢ
TokenâĢ
Feature activation+0.040
Top resid features:
Ļ
TokenĻ
Feature activation+0.145
Top resid features:
t
Tokent
Feature activation+0.392
Top resid features:
gone
Token gone
Feature activation+0.000
Top resid features:
here
Token here
Feature activation+0.024
Top resid features:
shortly
Token shortly
Feature activation+0.058
Top resid features:
,
Token,
Feature activation+0.046
Top resid features:
this
Token this
Feature activation+0.124
Top resid features:
absolutely
Token absolutely
Feature activation+0.054
Top resid features:
could
Token could
Feature activation+3.066
Top resid features:
have
Token have
Feature activation+0.387
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
tr
Token tr
Feature activation+0.004
Top resid features:
icycle
Tokenicycle
Feature activation+0.059
Top resid features:
wouldn
Token wouldn
Feature activation+0.204
Top resid features:
âĢ
TokenâĢ
Feature activation+0.176
Top resid features:
Ļ
TokenĻ
Feature activation+0.104
Top resid features:
t
Tokent
Feature activation+1.495
Top resid features:
have
Token have
Feature activation+0.508
Top resid features:
stood
Token stood
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
way
Token way
Feature activation+0.000
Top resid features:
1980
Token 1980
Feature activation+0.004
Top resid features:
s
Tokens
Feature activation+0.069
Top resid features:
,
Token,
Feature activation+0.101
Top resid features:
the
Token the
Feature activation+0.074
Top resid features:
institutional
Token institutional
Feature activation+0.019
Top resid features:
infrastructure
Token infrastructure
Feature activation+3.744
Top resid features:
of
Token of
Feature activation+0.038
Top resid features:
the
Token the
Feature activation+0.041
Top resid features:
conservative
Token conservative
Feature activation+0.051
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
libertarian
Token libertarian
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.102
Top resid features:
living
Token living
Feature activation+0.015
Top resid features:
room
Token room
Feature activation+0.028
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
If
Token If
Feature activation+0.042
Top resid features:
it
Token it
Feature activation+2.591
Top resid features:
had
Token had
Feature activation+0.244
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
storage
Token storage
Feature activation+0.000
Top resid features:
space
Token space
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.015
Top resid features:
forward
Token forward
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.061
Top resid features:
fish
Token fish
Feature activation+0.121
Top resid features:
would
Token would
Feature activation+2.177
Top resid features:
have
Token have
Feature activation+0.627
Top resid features:
likely
Token likely
Feature activation+0.453
Top resid features:
never
Token never
Feature activation+0.000
Top resid features:
fed
Token fed
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.028
Top resid features:
Ļ
TokenĻ
Feature activation+0.093
Top resid features:
s
Tokens
Feature activation+0.065
Top resid features:
very
Token very
Feature activation+0.048
Top resid features:
influential
Token influential
Feature activation+0.026
Top resid features:
members
Token members
Feature activation+3.287
Top resid features:
in
Token in
Feature activation+0.059
Top resid features:
government
Token government
Feature activation+0.180
Top resid features:
,
Token,
Feature activation+0.036
Top resid features:
the
Token the
Feature activation+0.041
Top resid features:
media
Token media
Feature activation-0.051
Top resid features:
for
Token for
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.134
Top resid features:
violation
Token violation
Feature activation+0.040
Top resid features:
,
Token,
Feature activation+0.043
Top resid features:
Milwaukee
Token Milwaukee
Feature activation+0.013
Top resid features:
would
Token would
Feature activation+3.919
Top resid features:
have
Token have
Feature activation+0.283
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
chance
Token chance
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
then
Token then
Feature activation+0.046
Top resid features:
and
Token and
Feature activation+0.059
Top resid features:
travelling
Token travelling
Feature activation+0.061
Top resid features:
by
Token by
Feature activation+0.039
Top resid features:
horse
Token horse
Feature activation+0.025
Top resid features:
would
Token would
Feature activation+3.002
Top resid features:
have
Token have
Feature activation+0.791
Top resid features:
meant
Token meant
Feature activation+0.000
Top resid features:
days
Token days
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
travel
Token travel
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.413
Top resid features:
have
Token have
Feature activation+0.047
Top resid features:
been
Token been
Feature activation+0.128
Top resid features:
better
Token better
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.085
Top resid features:
would
Token would
Feature activation+2.963
Top resid features:
have
Token have
Feature activation+0.467
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
If
Token If
Feature activation+0.125
Top resid features:
Mark
Token Mark
Feature activation+0.085
Top resid features:
had
Token had
Feature activation+0.263
Top resid features:
,
Token,
Feature activation+0.156
Top resid features:
he
Token he
Feature activation+0.342
Top resid features:
would
Token would
Feature activation+2.873
Top resid features:
have
Token have
Feature activation+0.290
Top resid features:
easily
Token easily
Feature activation+0.000
Top resid features:
found
Token found
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
little
Token little
Feature activation+0.027
Top resid features:
bit
Token bit
Feature activation+0.042
Top resid features:
later
Token later
Feature activation+0.037
Top resid features:
the
Token the
Feature activation+0.102
Top resid features:
riders
Token riders
Feature activation+0.071
Top resid features:
would
Token would
Feature activation+3.220
Top resid features:
have
Token have
Feature activation+0.208
Top resid features:
peeled
Token peeled
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
behind
Token behind
Feature activation+0.000
Top resid features:
start
Token start
Feature activation+0.065
Top resid features:
.
Token.
Feature activation+0.033
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
They
TokenThey
Feature activation+0.299
Top resid features:
would
Token would
Feature activation+1.904
Top resid features:
also
Token also
Feature activation+0.762
Top resid features:
have
Token have
Feature activation+0.195
Top resid features:
assumed
Token assumed
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
up
Token up
Feature activation-0.000
Top resid features:
my
Token my
Feature activation+0.021
Top resid features:
seat
Token seat
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
I
Token I
Feature activation+0.353
Top resid features:
would
Token would
Feature activation+3.067
Top resid features:
have
Token have
Feature activation+0.406
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
But
Token But
Feature activation+0.000
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.03

Head 2: 0.04

Head 3: 0.04

Head 4: 0.06

Head 5: 0.04

Head 6: 0.02

Head 7: 0.05

Head 8: 0.12

Head 9: 0.04

Head 10: 0.38

Head 11: 0.09

Positive logits

have3.45

have2.92

've2.91

olla2.71

ğ2.71

��2.62

2.46

ouched2.46

olkien2.43

HAVE2.41

zech2.37

haven2.37

endant2.36

emonium2.36

Have2.36

hovah2.35

cry2.35

DRAGON2.33

etti2.32

has2.31

Negative logits

Tor-2.76

RM-2.57

Marg-2.52

FontSize-2.38

EMP-2.30

lishes-2.27

directs-2.27

channelAvailability-2.27

restores-2.26

prepares-2.24

Lee-2.15

Min-2.15

urges-2.13

Gat-2.12

tor-2.12

searches-2.11

Region-2.11

Torres-2.08

Augusta-2.08

Marg-2.05

INTERVAL 3.918 - 4.353
CONTAINS 0.000%

house
Token house
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+4.353
been
Token been
Feature activation+0.000
much
Token much
Feature activation+0.000
worse
Token worse
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
me
Token me
Feature activation+0.000
it
Token it
Feature activation+0.000
could
Token could
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.793
ve
Tokenve
Feature activation+3.929
been
Token been
Feature activation+0.000
avoided
Token avoided
Feature activation+0.000
.
Token.
Feature activation+0.000
Or
Token Or
Feature activation+0.000
if
Token if
Feature activation+0.000

INTERVAL 3.482 - 3.918
CONTAINS 0.000%

INTERVAL 3.047 - 3.482
CONTAINS 0.000%

forward
Token forward
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
fish
Token fish
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+3.106
likely
Token likely
Feature activation+2.586
never
Token never
Feature activation+1.519
fed
Token fed
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 2.612 - 3.047
CONTAINS 0.001%

time
Token time
Feature activation+0.000
things
Token things
Feature activation+0.000
haven
Token haven
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+2.177
t
Tokent
Feature activation+2.780
gone
Token gone
Feature activation+0.000
smoothly
Token smoothly
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
icycle
Tokenicycle
Feature activation+0.000
wouldn
Token wouldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.557
have
Token have
Feature activation+2.681
stood
Token stood
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
way
Token way
Feature activation+0.000
.
Token.
Feature activation+0.000
her
Token her
Feature activation+0.000
way
Token way
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
it
Token it
Feature activation+0.735
had
Token had
Feature activation+2.963
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
separate
Token separate
Feature activation+0.000
dining
Token dining
Feature activation+0.000
room
Token room
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
conservative
Token conservative
Feature activation+0.000
and
Token and
Feature activation+0.000
libertarian
Token libertarian
Feature activation+0.000
movement
Token movement
Feature activation+2.641
has
Token has
Feature activation+1.543
grown
Token grown
Feature activation+0.000
exponentially
Token exponentially
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
been
Token been
Feature activation+0.000
killed
Token killed
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
would
Token would
Feature activation+0.079
have
Token have
Feature activation+2.953
"
Token "
Feature activation+1.957
t
Tokent
Feature activation+0.000
aken
Tokenaken
Feature activation+0.000
steps
Token steps
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 2.176 - 2.612
CONTAINS 0.001%

bit
Token bit
Feature activation+0.000
later
Token later
Feature activation+0.000
the
Token the
Feature activation+0.000
riders
Token riders
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+2.354
peeled
Token peeled
Feature activation+0.000
out
Token out
Feature activation+0.000
from
Token from
Feature activation+0.000
behind
Token behind
Feature activation+0.000
each
Token each
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
fish
Token fish
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+3.106
likely
Token likely
Feature activation+2.586
never
Token never
Feature activation+1.519
fed
Token fed
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
violation
Token violation
Feature activation+0.000
,
Token,
Feature activation+0.000
Milwaukee
Token Milwaukee
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+2.520
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
chance
Token chance
Feature activation+0.000
to
Token to
Feature activation+0.000
tie
Token tie
Feature activation+0.000
my
Token my
Feature activation+0.000
seat
Token seat
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+2.224
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
even
Token even
Feature activation+0.000
at
Token at
Feature activation+0.000
my
Token my
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
They
TokenThey
Feature activation+0.000
would
Token would
Feature activation+0.000
also
Token also
Feature activation+2.103
have
Token have
Feature activation+2.306
assumed
Token assumed
Feature activation+0.000
that
Token that
Feature activation+0.000
one
Token one
Feature activation+0.000
loss
Token loss
Feature activation+0.000
so
Token so
Feature activation+0.000

INTERVAL 1.741 - 2.176
CONTAINS 0.002%

had
Token had
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+2.429
easily
Token easily
Feature activation+2.110
found
Token found
Feature activation+0.000
out
Token out
Feature activation+0.000
about
Token about
Feature activation+0.000
these
Token these
Feature activation+0.000
crimes
Token crimes
Feature activation+0.000
Libre
Token Libre
Feature activation+0.000
Office
TokenOffice
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+1.909
been
Token been
Feature activation+0.000
better
Token better
Feature activation+0.000
,
Token,
Feature activation+0.000
specially
Token specially
Feature activation+0.000
considering
Token considering
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.722
ve
Tokenve
Feature activation+1.764
voted
Token voted
Feature activation+0.000
for
Token for
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
other
Token other
Feature activation+0.000
so
Token so
Feature activation+0.000
they
Token they
Feature activation+0.000
wouldn
Token wouldn
Feature activation+0.000
't
Token't
Feature activation+1.308
have
Token have
Feature activation+1.842
been
Token been
Feature activation+0.000
bun
Token bun
Feature activation+0.000
ched
Tokenched
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
parties
Token parties
Feature activation+1.774
is
Token is
Feature activation+0.000
wider
Token wider
Feature activation+0.000
than
Token than
Feature activation+0.000
at
Token at
Feature activation+0.000
any
Token any
Feature activation+0.000

INTERVAL 1.306 - 1.741
CONTAINS 0.004%

Every
Token Every
Feature activation+0.000
single
Token single
Feature activation+0.000
threat
Token threat
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+1.309
overcome
Token overcome
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.867
ve
Tokenve
Feature activation+1.518
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
time
Token time
Feature activation+0.000
the
Token the
Feature activation+0.000
intervening
Token intervening
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
has
Token has
Feature activation+1.346
evolved
Token evolved
Feature activation+0.000
to
Token to
Feature activation+0.000
ever
Token ever
Feature activation+0.000
-
Token-
Feature activation+0.000
more
Tokenmore
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
None
TokenNone
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+1.649
happened
Token happened
Feature activation+0.000
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
wouldn
Token wouldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
test
Token test
Feature activation+0.000
may
Token may
Feature activation+0.000
have
Token have
Feature activation+1.516
been
Token been
Feature activation+0.000
considerably
Token considerably
Feature activation+0.000
lighter
Token lighter
Feature activation+0.000
than
Token than
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 0.871 - 1.306
CONTAINS 0.008%

carrots
Token carrots
Feature activation+0.000
there
Token there
Feature activation+0.000
no
Token no
Feature activation+0.000
one
Token one
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+1.053
given
Token given
Feature activation+0.000
a
Token a
Feature activation+0.000
damn
Token damn
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
bathroom
Token bathroom
Feature activation+0.000
might
Token might
Feature activation+0.000
have
Token have
Feature activation+1.022
been
Token been
Feature activation+0.000
killed
Token killed
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
would
Token would
Feature activation+0.079
mother
Token mother
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
mission
Token mission
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+1.145
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.709
ab
Tokenab
Feature activation+0.000
andon
Tokenandon
Feature activation+0.000
ed
Tokened
Feature activation+0.000
,
Token,
Feature activation+0.000
cases
Token cases
Feature activation+0.000
of
Token of
Feature activation+0.000
complete
Token complete
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000
failure
Token failure
Feature activation+1.305
have
Token have
Feature activation+1.186
been
Token been
Feature activation+0.000
reported
Token reported
Feature activation+0.000
in
Token in
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
time
Token time
Feature activation+0.000
has
Token has
Feature activation+1.201
passed
Token passed
Feature activation+0.000
since
Token since
Feature activation+0.000
then
Token then
Feature activation+0.000
and
Token and
Feature activation+0.000
lots
Token lots
Feature activation+0.000

INTERVAL 0.435 - 0.871
CONTAINS 0.016%

.
Token.
Feature activation+0.000
None
Token None
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.502
happened
Token happened
Feature activation+0.000
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
weren
Token weren
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
from
Token from
Feature activation+0.000
all
Token all
Feature activation+0.000
across
Token across
Feature activation+0.000
France
Token France
Feature activation+0.433
and
Token and
Feature activation+0.000
Europe
Token Europe
Feature activation+0.550
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
later
Token later
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
here
Token here
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Brew
Token Brew
Feature activation+0.000
Review
Token Review
Feature activation+0.000
Crew
Token Crew
Feature activation+0.633
have
Token have
Feature activation+0.244
been
Token been
Feature activation+0.000
spreading
Token spreading
Feature activation+0.000
the
Token the
Feature activation+0.000
good
Token good
Feature activation+0.000
it
Token it
Feature activation+0.000
than
Token than
Feature activation+0.000
I
Token I
Feature activation+0.000
ever
Token ever
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.738
imagined
Token imagined
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
've
Token've
Feature activation+0.000
achieved
Token achieved
Feature activation+0.000
anything
Token anything
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+1.191
ever
Token ever
Feature activation+0.869
experienced
Token experienced
Feature activation+0.000
.
Token.
Feature activation+0.000
Not
Token Not
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000

INTERVAL 0.000 - 0.435
CONTAINS 99.969%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Perhaps
TokenPerhaps
Feature activation+0.000
now
Token now
Feature activation+0.000
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
've
Token've
Feature activation+0.000
seen
Token seen
Feature activation+0.000
the
Token the
Feature activation+0.000
enemy
Token enemy
Feature activation+0.000
,
Token,
Feature activation+0.000
club
Token club
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
plans
Token plans
Feature activation+0.000
altogether
Token altogether
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.000
reached
Token reached
Feature activation+0.000
for
Token for
Feature activation+0.000
comment
Token comment
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
clear
Token clear
Feature activation+0.000
from
Token from
Feature activation+0.000
has
Token has
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000
a
Token a
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
growing
Token growing
Feature activation+0.000
shared
Token shared
Feature activation+0.000
economy
Token economy
Feature activation+0.000
and
Token and
Feature activation+0.000
what
Token what
Feature activation+0.000
broader
Token broader
Feature activation+0.000
battle
Token battle
Feature activation+0.000
against
Token against
Feature activation+0.000
McConnell
Token McConnell
Feature activation+0.000
that
Token that
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
play
Token play
Feature activation+0.000
out
Token out
Feature activation+0.000
in
Token in
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H11.10: (feature 16615)

TOP ACTIVATIONS
MAX = 6.939

decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
secret
Token secret
Feature activation+6.939
is
Token is
Feature activation+0.031
just
Token just
Feature activation+0.000
one
Token one
Feature activation+0.127
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Stock
Token Stock
Feature activation+0.000
Exchange
Token Exchange
Feature activation+6.069
was
Token was
Feature activation+0.085
a
Token a
Feature activation+0.000
cost
Token cost
Feature activation+0.000
savings
Token savings
Feature activation+0.000
measure
Token measure
Feature activation+0.000
decision
Token decision
Feature activation+0.000
the
Token the
Feature activation+0.000
commission
Token commission
Feature activation+0.000
had
Token had
Feature activation+1.124
to
Token to
Feature activation+0.000
make
Token make
Feature activation+4.963
was
Token was
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
we
Token we
Feature activation+0.000
going
Token going
Feature activation+0.000
of
Token of
Feature activation+0.000
Steven
Token Steven
Feature activation+0.000
Sin
Token Sin
Feature activation+0.000
of
Tokenof
Feature activation+0.000
sky
Tokensky
Feature activation+0.000
,
Token,
Feature activation+4.887
comes
Token comes
Feature activation+0.000
as
Token as
Feature activation+0.000
Microsoft
Token Microsoft
Feature activation+0.000
faces
Token faces
Feature activation+0.000
increasing
Token increasing
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
highest
Token highest
Feature activation+0.000
court
Token court
Feature activation+4.480
was
Token was
Feature activation+0.000
released
Token released
Feature activation+0.000
after
Token after
Feature activation+0.000
a
Token a
Feature activation+0.000
seven
Token seven
Feature activation+0.000
territory
Token territory
Feature activation+0.000
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+4.326
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
announcement
Token announcement
Feature activation+0.000
by
Token by
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+0.000
Benjamin
Token Benjamin
Feature activation+0.000
Netanyahu
Token Netanyahu
Feature activation+4.312
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
security
Token security
Feature activation+0.000
cabinet
Token cabinet
Feature activation+0.626
meeting
Token meeting
Feature activation+3.266
s
Tokens
Feature activation+0.000
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
back
Token back
Feature activation+0.000
Roy
Token Roy
Feature activation+0.000
Moore
Token Moore
Feature activation+4.271
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
negative
Token negative
Feature activation+0.000
impact
Token impact
Feature activation+0.000
code
Token code
Feature activation+0.000
the
Token the
Feature activation+0.000
decision
Token decision
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
judge
Token judge
Feature activation+4.200
author
Token author
Feature activation+0.000
ising
Tokenising
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.000
marriage
Token marriage
Feature activation+4.097
broken
Token broken
Feature activation+0.000
and
Token and
Feature activation+0.000
deficient
Token deficient
Feature activation+0.000
military
Token military
Feature activation+0.000
commissions
Token commissions
Feature activation+0.000
system
Token system
Feature activation+4.152
to
Token to
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Kevin
TokenKevin
Feature activation+0.000
Space
Token Space
Feature activation+0.000
y
Tokeny
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
security
Token security
Feature activation+0.000
cabinet
Token cabinet
Feature activation+0.626
meeting
Token meeting
Feature activation+3.266
Tuesday
Token Tuesday
Feature activation+4.076
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
blockade
Token blockade
Feature activation+0.000
of
Token of
Feature activation+0.000
Gaza
Token Gaza
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
National
Token National
Feature activation+0.000
Labor
Token Labor
Feature activation+0.000
Relations
Token Relations
Feature activation+0.000
Board
Token Board
Feature activation+3.774
reversed
Token reversed
Feature activation+0.000
the
Token the
Feature activation+0.000
standard
Token standard
Feature activation+0.000
it
Token it
Feature activation+0.000
had
Token had
Feature activation+0.000
of
Token of
Feature activation+0.000
Broad
Token Broad
Feature activation+0.000
band
Tokenband
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
Access
Token Access
Feature activation+0.000
Act
Token Act
Feature activation+3.649
was
Token was
Feature activation+0.000
29
Token 29
Feature activation+0.000
to
Token to
Feature activation+0.000
19
Token 19
Feature activation+0.000
,
Token,
Feature activation+0.000
ato
Tokenato
Feature activation+0.000
's
Token's
Feature activation+0.000
surprise
Token surprise
Feature activation+0.000
departure
Token departure
Feature activation+0.262
on
Token on
Feature activation+0.000
Monday
Token Monday
Feature activation+3.637
was
Token was
Feature activation+0.000
seen
Token seen
Feature activation+0.000
as
Token as
Feature activation+0.000
proof
Token proof
Feature activation+0.000
that
Token that
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
on
Token on
Feature activation+0.000
using
Token using
Feature activation+0.000
force
Token force
Feature activation+3.515
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
ships
Token ships
Feature activation+0.000
from
Token from
Feature activation+0.000
entering
Token entering
Feature activation+0.000
rein
Token rein
Feature activation+0.000
state
Tokenstate
Feature activation+0.000
its
Token its
Feature activation+0.000
support
Token support
Feature activation+0.000
for
Token for
Feature activation+0.000
Moore
Token Moore
Feature activation+3.478
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
thing
Token thing
Feature activation+0.000
to
Token to
Feature activation+0.000
The
TokenThe
Feature activation+0.000
request
Token request
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
mist
Token mist
Feature activation+0.000
rial
Tokenrial
Feature activation+3.398
comes
Token comes
Feature activation+0.000
seven
Token seven
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+2.482
in
Token in
Feature activation+0.000
2009
Token 2009
Feature activation+3.303
to
Token to
Feature activation+0.000
down
Token down
Feature activation+0.000
play
Tokenplay
Feature activation+0.000
climate
Token climate
Feature activation+0.000
change
Token change
Feature activation+1.684
Netanyahu
Token Netanyahu
Feature activation+4.312
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
security
Token security
Feature activation+0.000
cabinet
Token cabinet
Feature activation+0.626
meeting
Token meeting
Feature activation+3.266
Tuesday
Token Tuesday
Feature activation+4.076
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
blockade
Token blockade
Feature activation+0.000
of
Token of
Feature activation+0.000
ennial
Tokenennial
Feature activation+0.000
General
Token General
Feature activation+0.000
Convention
Token Convention
Feature activation+0.000
in
Token in
Feature activation+0.000
Indianapolis
Token Indianapolis
Feature activation+0.045
,
Token,
Feature activation+3.224
means
Token means
Feature activation+0.000
that
Token that
Feature activation+0.000
priests
Token priests
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000

Top DFA by src position
MAX = 7.611

Thursday
Token Thursday
Feature activation+0.107
Top resid features:
.
Token.
Feature activation+0.470
Top resid features:
Ċ
TokenĊ
Feature activation+0.265
Top resid features:
Ċ
TokenĊ
Feature activation+0.156
Top resid features:
The
TokenThe
Feature activation+0.099
Top resid features:
decision
Token decision
Feature activation+7.611
Top resid features:
to
Token to
Feature activation+0.148
Top resid features:
keep
Token keep
Feature activation+0.140
Top resid features:
the
Token the
Feature activation+0.070
Top resid features:
numbers
Token numbers
Feature activation+0.468
Top resid features:
secret
Token secret
Feature activation+0.483
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
Konami
Token Konami
Feature activation+0.085
Top resid features:
officials
Token officials
Feature activation+0.056
Top resid features:
said
Token said
Feature activation+0.034
Top resid features:
the
Token the
Feature activation+0.044
Top resid features:
decision
Token decision
Feature activation+7.192
Top resid features:
to
Token to
Feature activation+0.117
Top resid features:
del
Token del
Feature activation+0.016
Top resid features:
ist
Tokenist
Feature activation+0.130
Top resid features:
the
Token the
Feature activation+0.058
Top resid features:
company
Token company
Feature activation+0.233
Top resid features:
:
Token:
Feature activation+0.031
Top resid features:
Ċ
TokenĊ
Feature activation+0.164
Top resid features:
Ċ
TokenĊ
Feature activation+0.055
Top resid features:
"
Token"
Feature activation+0.143
Top resid features:
The
TokenThe
Feature activation+0.078
Top resid features:
decision
Token decision
Feature activation+6.136
Top resid features:
the
Token the
Feature activation+0.102
Top resid features:
commission
Token commission
Feature activation+0.061
Top resid features:
had
Token had
Feature activation+0.172
Top resid features:
to
Token to
Feature activation+0.046
Top resid features:
make
Token make
Feature activation+0.350
Top resid features:
2009
Token 2009
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.054
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.046
Top resid features:
The
TokenThe
Feature activation+0.044
Top resid features:
announcement
Token announcement
Feature activation+6.332
Top resid features:
by
Token by
Feature activation+0.024
Top resid features:
T
Token T
Feature activation-0.006
Top resid features:
ami
Tokenami
Feature activation-0.002
Top resid features:
R
Token R
Feature activation+0.001
Top resid features:
eller
Tokeneller
Feature activation+0.053
Top resid features:
The
TokenThe
Feature activation+0.067
Top resid features:
32
Token 32
Feature activation+0.008
Top resid features:
-
Token-
Feature activation+0.007
Top resid features:
page
Tokenpage
Feature activation+0.071
Top resid features:
unanimous
Token unanimous
Feature activation+0.036
Top resid features:
decision
Token decision
Feature activation+5.554
Top resid features:
by
Token by
Feature activation+0.060
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
state
Token state
Feature activation+0.034
Top resid features:
âĢ
TokenâĢ
Feature activation+0.118
Top resid features:
Ļ
TokenĻ
Feature activation+0.117
Top resid features:
Ċ
TokenĊ
Feature activation+0.049
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Tuesday
TokenTuesday
Feature activation+0.063
Top resid features:
's
Token's
Feature activation+0.083
Top resid features:
missile
Token missile
Feature activation+0.069
Top resid features:
launch
Token launch
Feature activation+3.256
Top resid features:
-
Token -
Feature activation+0.108
Top resid features:
likely
Token likely
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
longest
Token longest
Feature activation-0.036
Top resid features:
ever
Token ever
Feature activation+0.036
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
Gaza
Token Gaza
Feature activation+0.004
Top resid features:
Strip
Token Strip
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.033
Top resid features:
The
Token The
Feature activation+0.036
Top resid features:
announcement
Token announcement
Feature activation+6.338
Top resid features:
by
Token by
Feature activation+0.041
Top resid features:
Prime
Token Prime
Feature activation+0.033
Top resid features:
Minister
Token Minister
Feature activation+0.025
Top resid features:
Benjamin
Token Benjamin
Feature activation-0.012
Top resid features:
Netanyahu
Token Netanyahu
Feature activation+0.064
Top resid features:
The
TokenThe
Feature activation+0.035
Top resid features:
RNC
Token RNC
Feature activation+0.044
Top resid features:
âĢ
TokenâĢ
Feature activation+0.071
Top resid features:
Ļ
TokenĻ
Feature activation+0.040
Top resid features:
s
Tokens
Feature activation+0.032
Top resid features:
decision
Token decision
Feature activation+4.400
Top resid features:
to
Token to
Feature activation+0.037
Top resid features:
back
Token back
Feature activation-0.007
Top resid features:
Roy
Token Roy
Feature activation+0.035
Top resid features:
Moore
Token Moore
Feature activation+0.065
Top resid features:
could
Token could
Feature activation+0.000
Top resid features:
under
Token under
Feature activation+0.016
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
family
Token family
Feature activation+0.021
Top resid features:
code
Token code
Feature activation-0.028
Top resid features:
the
Token the
Feature activation+0.057
Top resid features:
decision
Token decision
Feature activation+6.018
Top resid features:
of
Token of
Feature activation+0.042
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
judge
Token judge
Feature activation+0.210
Top resid features:
author
Token author
Feature activation+0.000
Top resid features:
ising
Tokenising
Feature activation+0.000
Top resid features:
Obama
Token Obama
Feature activation+0.006
Top resid features:
administration
Token administration
Feature activation+0.067
Top resid features:
âĢ
TokenâĢ
Feature activation+0.064
Top resid features:
Ļ
TokenĻ
Feature activation+0.048
Top resid features:
s
Tokens
Feature activation+0.013
Top resid features:
decision
Token decision
Feature activation+5.630
Top resid features:
to
Token to
Feature activation+0.039
Top resid features:
use
Token use
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
broken
Token broken
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
Gaza
Token Gaza
Feature activation+0.020
Top resid features:
Strip
Token Strip
Feature activation+0.032
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
The
Token The
Feature activation+0.049
Top resid features:
announcement
Token announcement
Feature activation+6.088
Top resid features:
by
Token by
Feature activation+0.026
Top resid features:
Prime
Token Prime
Feature activation+0.006
Top resid features:
Minister
Token Minister
Feature activation+0.003
Top resid features:
Benjamin
Token Benjamin
Feature activation-0.002
Top resid features:
Netanyahu
Token Netanyahu
Feature activation+0.098
Top resid features:
Ċ
TokenĊ
Feature activation+0.067
Top resid features:
The
TokenThe
Feature activation+0.078
Top resid features:
3
Token 3
Feature activation+0.046
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
2
Token2
Feature activation+0.036
Top resid features:
decision
Token decision
Feature activation+5.297
Top resid features:
by
Token by
Feature activation+0.106
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
National
Token National
Feature activation+0.006
Top resid features:
Labor
Token Labor
Feature activation-0.056
Top resid features:
Relations
Token Relations
Feature activation+0.054
Top resid features:
Commerce
Token Commerce
Feature activation+0.008
Top resid features:
Committee
Token Committee
Feature activation+0.132
Top resid features:
âĢ
TokenâĢ
Feature activation+0.163
Top resid features:
Ļ
TokenĻ
Feature activation+0.180
Top resid features:
s
Tokens
Feature activation+0.237
Top resid features:
vote
Token vote
Feature activation+5.102
Top resid features:
on
Token on
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.065
Top resid features:
No
Token No
Feature activation-0.002
Top resid features:
Rate
Token Rate
Feature activation+0.032
Top resid features:
Regulation
Token Regulation
Feature activation+0.139
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
R
TokenR
Feature activation+0.000
Top resid features:
ato
Tokenato
Feature activation+0.150
Top resid features:
's
Token's
Feature activation+0.038
Top resid features:
surprise
Token surprise
Feature activation+0.107
Top resid features:
departure
Token departure
Feature activation+4.856
Top resid features:
on
Token on
Feature activation+0.071
Top resid features:
Monday
Token Monday
Feature activation+0.506
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
seen
Token seen
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
Gaza
Token Gaza
Feature activation+0.013
Top resid features:
Strip
Token Strip
Feature activation+0.027
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
The
Token The
Feature activation+0.041
Top resid features:
announcement
Token announcement
Feature activation+5.068
Top resid features:
by
Token by
Feature activation+0.016
Top resid features:
Prime
Token Prime
Feature activation+0.001
Top resid features:
Minister
Token Minister
Feature activation+0.003
Top resid features:
Benjamin
Token Benjamin
Feature activation-0.002
Top resid features:
Netanyahu
Token Netanyahu
Feature activation+0.034
Top resid features:
National
Token National
Feature activation-0.001
Top resid features:
Committee
Token Committee
Feature activation+0.027
Top resid features:
âĢ
TokenâĢ
Feature activation+0.245
Top resid features:
Ļ
TokenĻ
Feature activation+0.068
Top resid features:
s
Tokens
Feature activation+0.015
Top resid features:
decision
Token decision
Feature activation+4.851
Top resid features:
to
Token to
Feature activation+0.066
Top resid features:
rein
Token rein
Feature activation+0.003
Top resid features:
state
Tokenstate
Feature activation+0.044
Top resid features:
its
Token its
Feature activation+0.016
Top resid features:
support
Token support
Feature activation+0.467
Top resid features:
judge
Token judge
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.179
Top resid features:
Ċ
TokenĊ
Feature activation+0.251
Top resid features:
Ċ
TokenĊ
Feature activation+0.130
Top resid features:
The
TokenThe
Feature activation+0.074
Top resid features:
request
Token request
Feature activation+5.226
Top resid features:
for
Token for
Feature activation+0.059
Top resid features:
a
Token a
Feature activation+0.032
Top resid features:
mist
Token mist
Feature activation+0.002
Top resid features:
rial
Tokenrial
Feature activation+0.352
Top resid features:
comes
Token comes
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.127
Top resid features:
Ċ
TokenĊ
Feature activation+0.072
Top resid features:
But
TokenBut
Feature activation+0.132
Top resid features:
a
Token a
Feature activation+0.094
Top resid features:
strategic
Token strategic
Feature activation-0.016
Top resid features:
decision
Token decision
Feature activation+4.871
Top resid features:
by
Token by
Feature activation+0.074
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
White
Token White
Feature activation-0.001
Top resid features:
House
Token House
Feature activation+0.176
Top resid features:
in
Token in
Feature activation+0.068
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
Gaza
Token Gaza
Feature activation+0.013
Top resid features:
Strip
Token Strip
Feature activation+0.041
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
The
Token The
Feature activation+0.054
Top resid features:
announcement
Token announcement
Feature activation+5.062
Top resid features:
by
Token by
Feature activation+0.027
Top resid features:
Prime
Token Prime
Feature activation+0.006
Top resid features:
Minister
Token Minister
Feature activation+0.003
Top resid features:
Benjamin
Token Benjamin
Feature activation-0.002
Top resid features:
Netanyahu
Token Netanyahu
Feature activation+0.128
Top resid features:
.
Token.
Feature activation+0.081
Top resid features:
Ċ
TokenĊ
Feature activation+0.039
Top resid features:
Ċ
TokenĊ
Feature activation+0.045
Top resid features:
The
TokenThe
Feature activation+0.071
Top resid features:
monumental
Token monumental
Feature activation+0.076
Top resid features:
decision
Token decision
Feature activation+3.824
Top resid features:
,
Token,
Feature activation+0.152
Top resid features:
approved
Token approved
Feature activation+0.201
Top resid features:
by
Token by
Feature activation+0.034
Top resid features:
a
Token a
Feature activation+0.029
Top resid features:
thick
Token thick
Feature activation+0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.03

Head 2: 0.02

Head 3: 0.06

Head 4: 0.05

Head 5: 0.03

Head 6: 0.02

Head 7: 0.04

Head 8: 0.16

Head 9: 0.03

Head 10: 0.38

Head 11: 0.10

Positive logits

underscores2.79

comes2.67

arag2.64

undersc2.62

sadd2.53

came2.46

infuri2.39

stunned2.34

reverber2.31

ric2.31

Hait2.29

etheless2.28

stems2.27

reinforces2.25

angered2.24

STL2.24

reson2.23

stadt2.22

rings2.22

sylv2.20

Negative logits

ITNESS-2.85

Tsukuyomi-2.48

Know-2.43

Switch-2.31

Vote-2.25

Obj-2.18

Win-2.16

hate-2.15

prise-2.15

Improve-2.15

Secrets-2.11

Try-2.07

Boo-2.06

Beta-2.05

beta-2.05

Transfer-2.04

Braun-2.04

Command-2.03

Order-2.03

Changing-2.02

INTERVAL 6.245 - 6.939
CONTAINS 0.000%

decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
secret
Token secret
Feature activation+6.939
is
Token is
Feature activation+0.031
just
Token just
Feature activation+0.000
one
Token one
Feature activation+0.127
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 5.551 - 6.245
CONTAINS 0.000%

from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Stock
Token Stock
Feature activation+0.000
Exchange
Token Exchange
Feature activation+6.069
was
Token was
Feature activation+0.085
a
Token a
Feature activation+0.000
cost
Token cost
Feature activation+0.000
savings
Token savings
Feature activation+0.000
measure
Token measure
Feature activation+0.000

INTERVAL 4.857 - 5.551
CONTAINS 0.000%

of
Token of
Feature activation+0.000
Steven
Token Steven
Feature activation+0.000
Sin
Token Sin
Feature activation+0.000
of
Tokenof
Feature activation+0.000
sky
Tokensky
Feature activation+0.000
,
Token,
Feature activation+4.887
comes
Token comes
Feature activation+0.000
as
Token as
Feature activation+0.000
Microsoft
Token Microsoft
Feature activation+0.000
faces
Token faces
Feature activation+0.000
increasing
Token increasing
Feature activation+0.000
decision
Token decision
Feature activation+0.000
the
Token the
Feature activation+0.000
commission
Token commission
Feature activation+0.000
had
Token had
Feature activation+1.124
to
Token to
Feature activation+0.000
make
Token make
Feature activation+4.963
was
Token was
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
we
Token we
Feature activation+0.000
going
Token going
Feature activation+0.000

INTERVAL 4.164 - 4.857
CONTAINS 0.001%

announcement
Token announcement
Feature activation+0.000
by
Token by
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+0.000
Benjamin
Token Benjamin
Feature activation+0.000
Netanyahu
Token Netanyahu
Feature activation+4.312
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
security
Token security
Feature activation+0.000
cabinet
Token cabinet
Feature activation+0.626
meeting
Token meeting
Feature activation+3.266
territory
Token territory
Feature activation+0.000
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+4.326
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
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
highest
Token highest
Feature activation+0.000
court
Token court
Feature activation+4.480
was
Token was
Feature activation+0.000
released
Token released
Feature activation+0.000
after
Token after
Feature activation+0.000
a
Token a
Feature activation+0.000
seven
Token seven
Feature activation+0.000
code
Token code
Feature activation+0.000
the
Token the
Feature activation+0.000
decision
Token decision
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
judge
Token judge
Feature activation+4.200
author
Token author
Feature activation+0.000
ising
Tokenising
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.000
marriage
Token marriage
Feature activation+4.097
s
Tokens
Feature activation+0.000
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
back
Token back
Feature activation+0.000
Roy
Token Roy
Feature activation+0.000
Moore
Token Moore
Feature activation+4.271
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
negative
Token negative
Feature activation+0.000
impact
Token impact
Feature activation+0.000

INTERVAL 3.470 - 4.164
CONTAINS 0.001%

of
Token of
Feature activation+0.000
Broad
Token Broad
Feature activation+0.000
band
Tokenband
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
Access
Token Access
Feature activation+0.000
Act
Token Act
Feature activation+3.649
was
Token was
Feature activation+0.000
29
Token 29
Feature activation+0.000
to
Token to
Feature activation+0.000
19
Token 19
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
security
Token security
Feature activation+0.000
cabinet
Token cabinet
Feature activation+0.626
meeting
Token meeting
Feature activation+3.266
Tuesday
Token Tuesday
Feature activation+4.076
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
blockade
Token blockade
Feature activation+0.000
of
Token of
Feature activation+0.000
Gaza
Token Gaza
Feature activation+0.000
ato
Tokenato
Feature activation+0.000
's
Token's
Feature activation+0.000
surprise
Token surprise
Feature activation+0.000
departure
Token departure
Feature activation+0.262
on
Token on
Feature activation+0.000
Monday
Token Monday
Feature activation+3.637
was
Token was
Feature activation+0.000
seen
Token seen
Feature activation+0.000
as
Token as
Feature activation+0.000
proof
Token proof
Feature activation+0.000
that
Token that
Feature activation+0.000
broken
Token broken
Feature activation+0.000
and
Token and
Feature activation+0.000
deficient
Token deficient
Feature activation+0.000
military
Token military
Feature activation+0.000
commissions
Token commissions
Feature activation+0.000
system
Token system
Feature activation+4.152
to
Token to
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Kevin
TokenKevin
Feature activation+0.000
Space
Token Space
Feature activation+0.000
y
Tokeny
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
on
Token on
Feature activation+0.000
using
Token using
Feature activation+0.000
force
Token force
Feature activation+3.515
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
ships
Token ships
Feature activation+0.000
from
Token from
Feature activation+0.000
entering
Token entering
Feature activation+0.000

INTERVAL 2.776 - 3.470
CONTAINS 0.002%

by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+2.482
in
Token in
Feature activation+0.000
2009
Token 2009
Feature activation+3.303
to
Token to
Feature activation+0.000
down
Token down
Feature activation+0.000
play
Tokenplay
Feature activation+0.000
climate
Token climate
Feature activation+0.000
change
Token change
Feature activation+1.684
be
Token be
Feature activation+0.000
officially
Token officially
Feature activation+0.000
announced
Token announced
Feature activation+0.000
later
Token later
Feature activation+0.000
today
Token today
Feature activation+0.000
,
Token,
Feature activation+2.886
brings
Token brings
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
close
Token close
Feature activation+0.000
months
Token months
Feature activation+0.000
ennial
Tokenennial
Feature activation+0.000
General
Token General
Feature activation+0.000
Convention
Token Convention
Feature activation+0.000
in
Token in
Feature activation+0.000
Indianapolis
Token Indianapolis
Feature activation+0.045
,
Token,
Feature activation+3.224
means
Token means
Feature activation+0.000
that
Token that
Feature activation+0.000
priests
Token priests
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
heated
Token heated
Feature activation+0.000
rhetoric
Token rhetoric
Feature activation+0.446
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
leaders
Token leaders
Feature activation+2.975
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+0.000
two
Token two
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
ruling
Token ruling
Feature activation+0.493
on
Token on
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+3.180
will
Token will
Feature activation+0.000
hold
Token hold
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
law
Token law
Feature activation+0.000

INTERVAL 2.082 - 2.776
CONTAINS 0.003%

British
Token British
Feature activation+0.000
engineer
Token engineer
Feature activation+0.000
Chris
Token Chris
Feature activation+0.000
P
Token P
Feature activation+0.000
ree
Tokenree
Feature activation+0.000
ce
Tokence
Feature activation+2.163
,
Token,
Feature activation+0.000
54
Token 54
Feature activation+0.000
,
Token,
Feature activation+2.158
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
handgun
Token handgun
Feature activation+1.385
for
Token for
Feature activation+0.000
self
Token self
Feature activation+0.000
-
Token-
Feature activation+0.000
protection
Tokenprotection
Feature activation+2.226
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
home
Token home
Feature activation+1.933
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
finding
Token finding
Feature activation+0.877
of
Token of
Feature activation+0.000
liability
Token liability
Feature activation+2.373
establishes
Token establishes
Feature activation+0.000
that
Token that
Feature activation+0.000
Haz
Token Haz
Feature activation+0.000
le
Tokenle
Feature activation+0.000
suffered
Token suffered
Feature activation+0.000
$
Token $
Feature activation+0.000
500
Token500
Feature activation+0.000
fine
Token fine
Feature activation+0.000
for
Token for
Feature activation+0.000
offensive
Token offensive
Feature activation+0.000
conduct
Token conduct
Feature activation+2.470
was
Token was
Feature activation+0.000
increased
Token increased
Feature activation+0.000
from
Token from
Feature activation+0.000
$
Token $
Feature activation+0.000
200
Token200
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
negotiators
Token negotiators
Feature activation+0.000
working
Token working
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
bill
Token bill
Feature activation+2.266
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.789
,
Token,
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.388 - 2.082
CONTAINS 0.007%

Hen
Token Hen
Feature activation+0.000
ao
Tokenao
Feature activation+1.253
and
Token and
Feature activation+0.000
Richie
Token Richie
Feature activation+0.000
Port
Token Port
Feature activation+0.000
e
Tokene
Feature activation+1.794
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
far
Token far
Feature activation+0.000
more
Token more
Feature activation+0.000
devastating
Token devastating
Feature activation+0.000
Adams
TokenAdams
Feature activation+0.000
application
Token application
Feature activation+0.000
for
Token for
Feature activation+0.000
that
Token that
Feature activation+0.000
first
Token first
Feature activation+0.000
settlement
Token settlement
Feature activation+1.478
was
Token was
Feature activation+0.000
denied
Token denied
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
A
TokenA
Feature activation+0.000
q
Tokenq
Feature activation+0.000
sa
Tokensa
Feature activation+0.000
Mosque
Token Mosque
Feature activation+0.856
in
Token in
Feature activation+0.000
Jerusalem
Token Jerusalem
Feature activation+1.532
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
seen
Token seen
Feature activation+0.000
in
Token in
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
visit
Token visit
Feature activation+0.000
to
Token to
Feature activation+0.000
Ireland
Token Ireland
Feature activation+1.543
will
Token will
Feature activation+0.007
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
her
Token her
Feature activation+0.000
periodic
Token periodic
Feature activation+0.000
renew
Token renew
Feature activation+0.000
als
Tokenals
Feature activation+1.777
in
Token in
Feature activation+0.000
Europe
Token Europe
Feature activation+2.036
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
consistent
Token consistent
Feature activation+0.000
with
Token with
Feature activation+0.000
someone
Token someone
Feature activation+0.000

INTERVAL 0.694 - 1.388
CONTAINS 0.017%

the
Token the
Feature activation+0.000
median
Token median
Feature activation+0.000
estimate
Token estimate
Feature activation+0.000
from
Token from
Feature activation+0.000
Fed
Token Fed
Feature activation+0.000
officials
Token officials
Feature activation+1.128
was
Token was
Feature activation+0.000
for
Token for
Feature activation+0.000
four
Token four
Feature activation+0.000
rate
Token rate
Feature activation+0.000
hikes
Token hikes
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
They
TokenThey
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
decision
Token decision
Feature activation+1.110
was
Token was
Feature activation+0.000
taken
Token taken
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
high
Token high
Feature activation+0.000
The
TokenThe
Feature activation+0.000
election
Token election
Feature activation+0.000
results
Token results
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
this
Token this
Feature activation+0.000
month
Token month
Feature activation+0.932
surprised
Token surprised
Feature activation+0.000
almost
Token almost
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
law
Token law
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
ruling
Token ruling
Feature activation+1.027
is
Token is
Feature activation+0.000
set
Token set
Feature activation+0.000
to
Token to
Feature activation+1.246
take
Token take
Feature activation+0.000
effect
Token effect
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
year
Token year
Feature activation+0.458
or
Token or
Feature activation+0.000
two
Token two
Feature activation+0.744
is
Token is
Feature activation+0.000
actually
Token actually
Feature activation+0.000
lower
Token lower
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.000 - 0.694
CONTAINS 99.969%

week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Daily
Token Daily
Feature activation+0.000
Star
Token Star
Feature activation+0.000
Lebanon
Token Lebanon
Feature activation+0.000
reported
Token reported
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
changed
Token changed
Feature activation+0.000
the
Token the
Feature activation+0.000
and
Token and
Feature activation+0.000
their
Token their
Feature activation+0.000
native
Token native
Feature activation+0.000
neighbors
Token neighbors
Feature activation+0.000
at
Token at
Feature activation+0.000
this
Token this
Feature activation+0.000
time
Token time
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
occasions
Token occasions
Feature activation+0.000
with
Token with
Feature activation+0.000
loaded
Token loaded
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
(
Token (
Feature activation+0.000
https
Token https
Feature activation+0.000
://
Token://
Feature activation+0.000
www
Tokenwww
Feature activation+0.000
.
Token.
Feature activation+0.000
natural
Tokennatural
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
20
Token 20
Feature activation+0.000
-
Token-
Feature activation+0.000
city
Tokencity
Feature activation+0.000
index
Token index
Feature activation+0.000
released
Token released
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
FX
Token FX
Feature activation+0.000
background
Token background
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
made
Token made
Feature activation+0.000
the
Token the
Feature activation+0.000
short
Token short
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
sho
Token sho
Feature activation+0.000
est
Tokenest
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 7 in H11.10: (feature 3370)

TOP ACTIVATIONS
MAX = 0.886

factor
Token factor
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.886
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
is
Token is
Feature activation+0.000
ant
Tokenant
Feature activation+0.000
orum
Tokenorum
Feature activation+0.000
got
Token got
Feature activation+0.000
a
Token a
Feature activation+0.000
prime
Token prime
Feature activation+0.000
-
Token-
Feature activation+0.722
time
Tokentime
Feature activation+0.000
speaking
Token speaking
Feature activation+0.000
spot
Token spot
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
proved
Token proved
Feature activation+0.000
itself
Token itself
Feature activation+0.000
ready
Token ready
Feature activation+0.000
for
Token for
Feature activation+0.000
prime
Token prime
Feature activation+0.000
-
Token-
Feature activation+0.518
time
Tokentime
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
M
TokenM
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
<|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
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
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
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
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
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
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

Top DFA by src position
MAX = 15.582

Factor
Token Factor
Feature activation-1.791
Top resid features:
ization
Tokenization
Feature activation-0.139
Top resid features:
Ċ
TokenĊ
Feature activation-0.032
Top resid features:
Ċ
TokenĊ
Feature activation+0.220
Top resid features:
Let
TokenLet
Feature activation-0.052
Top resid features:
Prime
Token Prime
Feature activation+9.456
Top resid features:
Division
Token Division
Feature activation-0.035
Top resid features:
teach
Token teach
Feature activation-0.279
Top resid features:
you
Token you
Feature activation-0.120
Top resid features:
the
Token the
Feature activation-0.085
Top resid features:
fun
Token fun
Feature activation-0.178
Top resid features:
S
TokenS
Feature activation+0.010
Top resid features:
ant
Tokenant
Feature activation-0.088
Top resid features:
orum
Tokenorum
Feature activation-0.033
Top resid features:
got
Token got
Feature activation-0.096
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
prime
Token prime
Feature activation+15.582
Top resid features:
-
Token-
Feature activation+0.090
Top resid features:
time
Tokentime
Feature activation+0.000
Top resid features:
speaking
Token speaking
Feature activation+0.000
Top resid features:
spot
Token spot
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.026
Top resid features:
proved
Token proved
Feature activation+0.002
Top resid features:
itself
Token itself
Feature activation+0.012
Top resid features:
ready
Token ready
Feature activation-0.010
Top resid features:
for
Token for
Feature activation-0.051
Top resid features:
prime
Token prime
Feature activation+14.333
Top resid features:
-
Token-
Feature activation+0.286
Top resid features:
time
Tokentime
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.173
Top resid features:
Ċ
TokenĊ
Feature activation+0.063
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
The
TokenThe
Feature activation+0.238
Top resid features:
defence
Token defence
Feature activation+0.067
Top resid features:
ministry
Token ministry
Feature activation+0.552
Top resid features:
committee
Token committee
Feature activation-0.086
Top resid features:
headed
Token headed
Feature activation-0.173
Top resid features:
by
Token by
Feature activation-1.190
Top resid features:
V
Token V
Feature activation-0.034
Top resid features:
.
Token.
Feature activation-0.096
Top resid features:
rik
Tokenrik
Feature activation-1.581
Top resid features:
ar
Tokenar
Feature activation-0.127
Top resid features:
said
Token said
Feature activation-0.552
Top resid features:
Saturday
Token Saturday
Feature activation-1.146
Top resid features:
.
Token.
Feature activation-0.849
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.304
Top resid features:
Ċ
TokenĊ
Feature activation-0.180
Top resid features:
Ċ
TokenĊ
Feature activation-0.036
Top resid features:
The
TokenThe
Feature activation-0.126
Top resid features:
defence
Token defence
Feature activation-0.145
Top resid features:
ministry
Token ministry
Feature activation+0.833
Top resid features:
committee
Token committee
Feature activation+0.490
Top resid features:
headed
Token headed
Feature activation-0.262
Top resid features:
by
Token by
Feature activation-0.923
Top resid features:
V
Token V
Feature activation-0.368
Top resid features:
.
Token.
Feature activation-0.093
Top resid features:
by
Token by
Feature activation-0.142
Top resid features:
V
Token V
Feature activation-0.057
Top resid features:
.
Token.
Feature activation-0.036
Top resid features:
K
TokenK
Feature activation-0.213
Top resid features:
.
Token.
Feature activation+0.051
Top resid features:
A
Token A
Feature activation+0.372
Top resid features:
atre
Tokenatre
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
former
Token former
Feature activation+0.000
Top resid features:
boss
Token boss
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.394
Top resid features:
V
Token V
Feature activation-0.157
Top resid features:
.
Token.
Feature activation-0.031
Top resid features:
K
TokenK
Feature activation-0.072
Top resid features:
.
Token.
Feature activation-0.077
Top resid features:
A
Token A
Feature activation+0.430
Top resid features:
atre
Tokenatre
Feature activation+0.075
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
former
Token former
Feature activation+0.000
Top resid features:
boss
Token boss
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.066
Top resid features:
Ċ
TokenĊ
Feature activation-0.032
Top resid features:
Ċ
TokenĊ
Feature activation-0.071
Top resid features:
The
TokenThe
Feature activation-0.131
Top resid features:
defence
Token defence
Feature activation-0.189
Top resid features:
ministry
Token ministry
Feature activation+0.043
Top resid features:
committee
Token committee
Feature activation+0.007
Top resid features:
headed
Token headed
Feature activation-0.045
Top resid features:
by
Token by
Feature activation-1.018
Top resid features:
V
Token V
Feature activation-0.673
Top resid features:
.
Token.
Feature activation-0.242
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-8.403
Top resid features:
rik
Tokenrik
Feature activation-0.085
Top resid features:
ar
Tokenar
Feature activation+0.015
Top resid features:
said
Token said
Feature activation+0.078
Top resid features:
Saturday
Token Saturday
Feature activation-0.009
Top resid features:
.
Token.
Feature activation-0.055
Top resid features:
Ċ
TokenĊ
Feature activation-0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.073
Top resid features:
The
TokenThe
Feature activation+0.042
Top resid features:
.
Token.
Feature activation-0.117
Top resid features:
Ċ
TokenĊ
Feature activation-0.021
Top resid features:
Ċ
TokenĊ
Feature activation-1.985
Top resid features:
The
TokenThe
Feature activation-0.192
Top resid features:
defence
Token defence
Feature activation-0.038
Top resid features:
ministry
Token ministry
Feature activation+0.066
Top resid features:
committee
Token committee
Feature activation-0.015
Top resid features:
headed
Token headed
Feature activation-0.096
Top resid features:
by
Token by
Feature activation-0.619
Top resid features:
V
Token V
Feature activation-0.512
Top resid features:
.
Token.
Feature activation-0.096
Top resid features:
.
Token.
Feature activation-0.554
Top resid features:
Ċ
TokenĊ
Feature activation-0.471
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
The
TokenThe
Feature activation-0.262
Top resid features:
defence
Token defence
Feature activation-0.109
Top resid features:
ministry
Token ministry
Feature activation+0.576
Top resid features:
committee
Token committee
Feature activation+0.410
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-7.844
Top resid features:
rik
Tokenrik
Feature activation-0.107
Top resid features:
ar
Tokenar
Feature activation+0.076
Top resid features:
said
Token said
Feature activation-0.018
Top resid features:
Saturday
Token Saturday
Feature activation-0.052
Top resid features:
.
Token.
Feature activation-0.135
Top resid features:
Ċ
TokenĊ
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.103
Top resid features:
said
Token said
Feature activation-0.388
Top resid features:
Saturday
Token Saturday
Feature activation-0.457
Top resid features:
.
Token.
Feature activation-0.494
Top resid features:
Ċ
TokenĊ
Feature activation-0.125
Top resid features:
Ċ
TokenĊ
Feature activation+0.035
Top resid features:
The
TokenThe
Feature activation+0.102
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-8.547
Top resid features:
rik
Tokenrik
Feature activation-0.014
Top resid features:
ar
Tokenar
Feature activation+0.153
Top resid features:
said
Token said
Feature activation+0.339
Top resid features:
Saturday
Token Saturday
Feature activation-0.051
Top resid features:
.
Token.
Feature activation-0.127
Top resid features:
Ċ
TokenĊ
Feature activation-2.327
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
rik
Tokenrik
Feature activation-4.541
Top resid features:
ar
Tokenar
Feature activation-0.155
Top resid features:
said
Token said
Feature activation-0.746
Top resid features:
Saturday
Token Saturday
Feature activation-0.663
Top resid features:
.
Token.
Feature activation-1.334
Top resid features:
Ċ
TokenĊ
Feature activation+0.144
Top resid features:
Ċ
TokenĊ
Feature activation+0.114
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.582
Top resid features:
Ċ
TokenĊ
Feature activation-0.043
Top resid features:
Ċ
TokenĊ
Feature activation-0.071
Top resid features:
The
TokenThe
Feature activation-0.016
Top resid features:
defence
Token defence
Feature activation-0.483
Top resid features:
ministry
Token ministry
Feature activation+0.891
Top resid features:
committee
Token committee
Feature activation+0.164
Top resid features:
headed
Token headed
Feature activation-0.132
Top resid features:
by
Token by
Feature activation-1.958
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.629
Top resid features:
Ċ
TokenĊ
Feature activation-0.768
Top resid features:
Ċ
TokenĊ
Feature activation-2.992
Top resid features:
The
TokenThe
Feature activation-0.573
Top resid features:
defence
Token defence
Feature activation-0.035
Top resid features:
ministry
Token ministry
Feature activation+0.674
Top resid features:
committee
Token committee
Feature activation+0.286
Top resid features:
headed
Token headed
Feature activation-0.578
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.907
Top resid features:
Ċ
TokenĊ
Feature activation-0.332
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
The
TokenThe
Feature activation-0.510
Top resid features:
defence
Token defence
Feature activation-0.065
Top resid features:
ministry
Token ministry
Feature activation+0.527
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
said
Token said
Feature activation-0.090
Top resid features:
Saturday
Token Saturday
Feature activation-0.116
Top resid features:
.
Token.
Feature activation-0.095
Top resid features:
Ċ
TokenĊ
Feature activation-0.076
Top resid features:
Ċ
TokenĊ
Feature activation+0.130
Top resid features:
The
TokenThe
Feature activation+0.806
Top resid features:
defence
Token defence
Feature activation+0.053
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.03

Head 2: 0.03

Head 3: 0.09

Head 4: 0.04

Head 5: 0.02

Head 6: 0.02

Head 7: 0.02

Head 8: 0.08

Head 9: 0.02

Head 10: 0.38

Head 11: 0.19

Positive logits

govtrack3.02

thro2.86

time2.64

nih2.51

widget2.41

html2.36

aez2.36

3072.34

ucha2.32

cursing2.32

ct2.32

socket2.31

TIME2.31

cmp2.26

cus2.26

loc2.22

1092.21

Tenn2.18

ees2.18

2.16

Negative logits

Renaissance-2.85

Prime-2.49

Raspberry-2.45

Bin-2.45

ogn-2.44

rez-2.38

proportional-2.38

Orion-2.36

abal-2.36

PRO-2.35

Pal-2.35

Mono-2.35

Paladin-2.34

Rarity-2.32

REST-2.31

rise-2.29

Pixel-2.28

Pall-2.26

Recon-2.26

PG-2.26

INTERVAL 0.797 - 0.886
CONTAINS 0.000%

factor
Token factor
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.886
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 0.708 - 0.797
CONTAINS 0.000%

ant
Tokenant
Feature activation+0.000
orum
Tokenorum
Feature activation+0.000
got
Token got
Feature activation+0.000
a
Token a
Feature activation+0.000
prime
Token prime
Feature activation+0.000
-
Token-
Feature activation+0.722
time
Tokentime
Feature activation+0.000
speaking
Token speaking
Feature activation+0.000
spot
Token spot
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.620 - 0.708
CONTAINS 0.000%

INTERVAL 0.531 - 0.620
CONTAINS 0.000%

INTERVAL 0.443 - 0.531
CONTAINS 0.000%

proved
Token proved
Feature activation+0.000
itself
Token itself
Feature activation+0.000
ready
Token ready
Feature activation+0.000
for
Token for
Feature activation+0.000
prime
Token prime
Feature activation+0.000
-
Token-
Feature activation+0.518
time
Tokentime
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
M
TokenM
Feature activation+0.000

INTERVAL 0.354 - 0.443
CONTAINS 0.000%

INTERVAL 0.266 - 0.354
CONTAINS 0.000%

INTERVAL 0.177 - 0.266
CONTAINS 0.000%

INTERVAL 0.089 - 0.177
CONTAINS 0.000%

INTERVAL 0.000 - 0.089
CONTAINS 100.000%

member
Token member
Feature activation+0.000
Andrew
Token Andrew
Feature activation+0.000
Roberts
Token Roberts
Feature activation+0.000
described
Token described
Feature activation+0.000
the
Token the
Feature activation+0.000
Union
Token Union
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
genesis
Token genesis
Feature activation+0.000
:
Token:
Feature activation+0.000
decide
Token decide
Feature activation+0.000
the
Token the
Feature activation+0.000
fate
Token fate
Feature activation+0.000
of
Token of
Feature activation+0.000
t
Token t
Feature activation+0.000
asers
Tokenasers
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mal
TokenMal
Feature activation+0.000
ika
Tokenika
Feature activation+0.000
bands
Token bands
Feature activation+0.000
",
Token",
Feature activation+0.000
playing
Token playing
Feature activation+0.000
music
Token music
Feature activation+0.000
by
Token by
Feature activation+0.000
Black
Token Black
Feature activation+0.000
Sabbath
Token Sabbath
Feature activation+0.000
,
Token,
Feature activation+0.000
O
Token O
Feature activation+0.000
zzy
Tokenzzy
Feature activation+0.000
,
Token,
Feature activation+0.000
Gl
TokenGl
Feature activation+0.000
obe
Tokenobe
Feature activation+0.000
activates
Token activates
Feature activation+0.000
First
Token First
Feature activation+0.000
Look
TokenLook
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
used
Token used
Feature activation+0.000
by
Token by
Feature activation+0.000
emergency
Token emergency
Feature activation+0.000
-
Token-
Feature activation+0.000
response
Tokenresponse
Feature activation+0.000
has
Token has
Feature activation+0.000
signed
Token signed
Feature activation+0.000
a
Token a
Feature activation+0.000
defence
Token defence
Feature activation+0.000
cooperation
Token cooperation
Feature activation+0.000
agreement
Token agreement
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
specific
Token specific
Feature activation+0.000
country
Token country
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 8 in H11.10: (feature 6156)

TOP ACTIVATIONS
MAX = 5.398

to
Token to
Feature activation+0.000
predict
Token predict
Feature activation+0.000
or
Token or
Feature activation+0.000
observe
Token observe
Feature activation+0.000
an
Token an
Feature activation+0.000
eruption
Token eruption
Feature activation+5.398
is
Token is
Feature activation+0.000
through
Token through
Feature activation+0.000
remote
Token remote
Feature activation+0.000
sensing
Token sensing
Feature activation+0.000
.
Token.
Feature activation+0.000
variations
Token variations
Feature activation+2.447
and
Token and
Feature activation+0.000
keep
Token keep
Feature activation+0.000
on
Token on
Feature activation+0.000
with
Token with
Feature activation+0.000
them
Token them
Feature activation+4.793
will
Token will
Feature activation+0.972
be
Token be
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
one
Token one
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
reach
Token reach
Feature activation+0.000
these
Token these
Feature activation+0.000
targets
Token targets
Feature activation+4.588
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
cut
Token cut
Feature activation+0.000
down
Token down
Feature activation+0.000
on
Token on
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
way
Token way
Feature activation+0.000
out
Token out
Feature activation+3.733
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
crisis
Token crisis
Feature activation+2.889
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
compl
Tokencompl
Feature activation+0.000
iant
Tokeniant
Feature activation+0.000
device
Token device
Feature activation+3.678
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
market
Token market
Feature activation+3.460
include
Token include
Feature activation+0.000
competitors
Token competitors
Feature activation+0.000
great
Token great
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
document
Token document
Feature activation+0.000
our
Token our
Feature activation+0.000
tasks
Token tasks
Feature activation+3.612
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
5
Token5
Feature activation+0.000
)
Token)
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+0.000
referendum
Token referendum
Feature activation+3.598
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
that
Token that
Feature activation+0.000
compl
Tokencompl
Feature activation+0.000
iant
Tokeniant
Feature activation+0.000
device
Token device
Feature activation+3.678
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
market
Token market
Feature activation+3.460
include
Token include
Feature activation+0.000
competitors
Token competitors
Feature activation+0.000
not
Token not
Feature activation+0.000
ifying
Tokenifying
Feature activation+0.000
authorities
Token authorities
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
read
Token read
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
lyrics
Token lyrics
Feature activation+3.352
is
Token is
Feature activation+0.000
by
Token by
Feature activation+0.000
playing
Token playing
Feature activation+0.000
the
Token the
Feature activation+0.000
instrumental
Token instrumental
Feature activation+0.000
and
Token and
Feature activation+0.000
language
Token language
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
from
Token from
Feature activation+0.000
other
Token other
Feature activation+0.000
sources
Token sources
Feature activation+3.222
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
install
Token install
Feature activation+0.000
the
Token the
Feature activation+0.000
browser
Token browser
Feature activation+0.000
to
Token to
Feature activation+0.000
compare
Token compare
Feature activation+0.000
how
Token how
Feature activation+0.000
well
Token well
Feature activation+0.000
predictions
Token predictions
Feature activation+0.000
worked
Token worked
Feature activation+2.942
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
rank
Token rank
Feature activation+0.000
all
Token all
Feature activation+0.000
players
Token players
Feature activation+0.000
only
Token only
Feature activation+0.000
way
Token way
Feature activation+0.000
out
Token out
Feature activation+3.733
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
crisis
Token crisis
Feature activation+2.889
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
implement
Token implement
Feature activation+0.000
an
Token an
Feature activation+0.000
EU
Token EU
Feature activation+0.000
This
TokenThis
Feature activation+0.000
easiest
Token easiest
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
this
Token this
Feature activation+2.485
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
an
Token an
Feature activation+0.000
Amazon
Token Amazon
Feature activation+0.000
ultimate
Token ultimate
Feature activation+0.000
way
Token way
Feature activation+1.471
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
these
Token these
Feature activation+0.000
variations
Token variations
Feature activation+2.447
and
Token and
Feature activation+0.000
keep
Token keep
Feature activation+0.000
on
Token on
Feature activation+0.000
with
Token with
Feature activation+0.000
them
Token them
Feature activation+4.793
first
Token first
Feature activation+0.000
act
Token act
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
gate
Token gate
Feature activation+1.907
âĢĶ
Token âĢĶ
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
just
Token just
Feature activation+0.000
complete
Token complete
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
fight
Token fight
Feature activation+0.000
the
Token the
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
administration
Token administration
Feature activation+1.786
now
Token now
Feature activation+1.769
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
galvan
Token galvan
Feature activation+0.000
ize
Tokenize
Feature activation+0.000
way
Token way
Feature activation+0.000
I
Token I
Feature activation+0.000
see
Token see
Feature activation+0.000
him
Token him
Feature activation+0.000
not
Token not
Feature activation+0.000
starting
Token starting
Feature activation+1.771
in
Token in
Feature activation+0.000
Week
Token Week
Feature activation+0.000
1
Token 1
Feature activation+1.586
is
Token is
Feature activation+0.000
if
Token if
Feature activation+0.000
to
Token to
Feature activation+0.000
fight
Token fight
Feature activation+0.000
the
Token the
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
administration
Token administration
Feature activation+1.786
now
Token now
Feature activation+1.769
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
galvan
Token galvan
Feature activation+0.000
ize
Tokenize
Feature activation+0.000
volunteers
Token volunteers
Feature activation+0.000
reducing
Token reducing
Feature activation+0.000
the
Token the
Feature activation+0.000
cost
Token cost
Feature activation+0.000
of
Token of
Feature activation+0.000
garbage
Token garbage
Feature activation+0.000
collection
Token collection
Feature activation+1.719
in
Token in
Feature activation+0.000
Er
Token Er
Feature activation+0.000
lang
Tokenlang
Feature activation+0.066
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
happy
Token happy
Feature activation+0.000
-
Token-
Feature activation+0.000
go
Tokengo
Feature activation+0.000
-
Token-
Feature activation+1.679
l
Tokenl
Feature activation+0.558
ucky
Tokenucky
Feature activation+0.000
albeit
Token albeit
Feature activation+0.000
death
Token death
Feature activation+0.000
-
Token-
Feature activation+0.000

Top DFA by src position
MAX = 7.341

island
Token island
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.093
Top resid features:
so
Token so
Feature activation+0.048
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
only
Token only
Feature activation+0.029
Top resid features:
way
Token way
Feature activation+7.341
Top resid features:
to
Token to
Feature activation+0.097
Top resid features:
predict
Token predict
Feature activation-0.049
Top resid features:
or
Token or
Feature activation+0.045
Top resid features:
observe
Token observe
Feature activation+0.021
Top resid features:
an
Token an
Feature activation+0.004
Top resid features:
sluggish
Token sluggish
Feature activation+0.009
Top resid features:
modifications
Token modifications
Feature activation-0.027
Top resid features:
.
Token.
Feature activation+0.131
Top resid features:
The
Token The
Feature activation+0.060
Top resid features:
ultimate
Token ultimate
Feature activation+0.121
Top resid features:
way
Token way
Feature activation+4.234
Top resid features:
to
Token to
Feature activation+0.098
Top resid features:
make
Token make
Feature activation+0.075
Top resid features:
these
Token these
Feature activation+0.013
Top resid features:
variations
Token variations
Feature activation+0.018
Top resid features:
and
Token and
Feature activation+0.070
Top resid features:
certain
Token certain
Feature activation-0.024
Top resid features:
targets
Token targets
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.070
Top resid features:
and
Token and
Feature activation+0.364
Top resid features:
one
Token one
Feature activation+0.165
Top resid features:
way
Token way
Feature activation+5.799
Top resid features:
to
Token to
Feature activation+0.073
Top resid features:
reach
Token reach
Feature activation+0.075
Top resid features:
these
Token these
Feature activation+0.005
Top resid features:
targets
Token targets
Feature activation+0.020
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
And
TokenAnd
Feature activation+0.017
Top resid features:
he
Token he
Feature activation-0.023
Top resid features:
said
Token said
Feature activation-0.115
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
only
Token only
Feature activation+0.047
Top resid features:
way
Token way
Feature activation+5.848
Top resid features:
out
Token out
Feature activation+0.460
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
crisis
Token crisis
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.194
Top resid features:
Ċ
TokenĊ
Feature activation+0.236
Top resid features:
The
TokenThe
Feature activation+0.024
Top resid features:
most
Token most
Feature activation+0.029
Top resid features:
likely
Token likely
Feature activation-0.034
Top resid features:
ways
Token ways
Feature activation+5.718
Top resid features:
to
Token to
Feature activation+0.063
Top resid features:
be
Token be
Feature activation+0.014
Top resid features:
caught
Token caught
Feature activation-0.215
Top resid features:
with
Token with
Feature activation-0.016
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
to
Token to
Feature activation+0.082
Top resid features:
run
Token run
Feature activation+0.035
Top resid features:
.
Token.
Feature activation+0.171
Top resid features:
A
Token A
Feature activation+0.034
Top resid features:
great
Token great
Feature activation+0.016
Top resid features:
way
Token way
Feature activation+5.193
Top resid features:
to
Token to
Feature activation+0.153
Top resid features:
document
Token document
Feature activation+0.096
Top resid features:
our
Token our
Feature activation+0.064
Top resid features:
tasks
Token tasks
Feature activation+0.060
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
Ċ
TokenĊ
Feature activation+0.110
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
The
TokenThe
Feature activation+0.035
Top resid features:
best
Token best
Feature activation+0.215
Top resid features:
time
Token time
Feature activation+5.227
Top resid features:
for
Token for
Feature activation+0.069
Top resid features:
another
Token another
Feature activation+0.054
Top resid features:
independence
Token independence
Feature activation+0.014
Top resid features:
referendum
Token referendum
Feature activation+0.038
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.188
Top resid features:
Ċ
TokenĊ
Feature activation+0.168
Top resid features:
The
TokenThe
Feature activation+0.037
Top resid features:
most
Token most
Feature activation+0.042
Top resid features:
likely
Token likely
Feature activation-0.017
Top resid features:
ways
Token ways
Feature activation+5.359
Top resid features:
to
Token to
Feature activation+0.040
Top resid features:
be
Token be
Feature activation+0.012
Top resid features:
caught
Token caught
Feature activation-0.082
Top resid features:
with
Token with
Feature activation-0.002
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
".
Token".
Feature activation+0.026
Top resid features:
I
Token I
Feature activation-0.020
Top resid features:
suggest
Token suggest
Feature activation+0.107
Top resid features:
the
Token the
Feature activation+0.037
Top resid features:
best
Token best
Feature activation+0.041
Top resid features:
way
Token way
Feature activation+4.806
Top resid features:
to
Token to
Feature activation+0.099
Top resid features:
read
Token read
Feature activation+0.436
Top resid features:
through
Token through
Feature activation+0.203
Top resid features:
the
Token the
Feature activation+0.095
Top resid features:
lyrics
Token lyrics
Feature activation+0.073
Top resid features:
.
Token.
Feature activation+0.119
Top resid features:
Ċ
TokenĊ
Feature activation+0.141
Top resid features:
Ċ
TokenĊ
Feature activation+0.064
Top resid features:
The
TokenThe
Feature activation+0.040
Top resid features:
best
Token best
Feature activation+0.051
Top resid features:
way
Token way
Feature activation+5.171
Top resid features:
to
Token to
Feature activation+0.112
Top resid features:
detect
Token detect
Feature activation+0.021
Top resid features:
influence
Token influence
Feature activation-0.218
Top resid features:
and
Token and
Feature activation+0.042
Top resid features:
language
Token language
Feature activation-0.064
Top resid features:
I
TokenI
Feature activation-0.031
Top resid features:
found
Token found
Feature activation+0.083
Top resid features:
that
Token that
Feature activation+0.073
Top resid features:
another
Token another
Feature activation+0.036
Top resid features:
good
Token good
Feature activation+0.002
Top resid features:
way
Token way
Feature activation+4.411
Top resid features:
to
Token to
Feature activation+0.054
Top resid features:
compare
Token compare
Feature activation+0.078
Top resid features:
how
Token how
Feature activation+0.172
Top resid features:
well
Token well
Feature activation+0.066
Top resid features:
predictions
Token predictions
Feature activation-0.055
Top resid features:
And
TokenAnd
Feature activation-0.003
Top resid features:
he
Token he
Feature activation-0.019
Top resid features:
said
Token said
Feature activation-0.104
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
only
Token only
Feature activation+0.054
Top resid features:
way
Token way
Feature activation+4.653
Top resid features:
out
Token out
Feature activation+0.537
Top resid features:
of
Token of
Feature activation+0.113
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
crisis
Token crisis
Feature activation+0.161
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
Read
Token Read
Feature activation+0.028
Top resid features:
Ċ
TokenĊ
Feature activation+0.070
Top resid features:
Ċ
TokenĊ
Feature activation+0.061
Top resid features:
This
TokenThis
Feature activation+0.023
Top resid features:
easiest
Token easiest
Feature activation+0.148
Top resid features:
way
Token way
Feature activation+3.700
Top resid features:
to
Token to
Feature activation+0.121
Top resid features:
do
Token do
Feature activation+0.253
Top resid features:
this
Token this
Feature activation+0.194
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
sluggish
Token sluggish
Feature activation-0.029
Top resid features:
modifications
Token modifications
Feature activation+0.081
Top resid features:
.
Token.
Feature activation+0.051
Top resid features:
The
Token The
Feature activation+0.067
Top resid features:
ultimate
Token ultimate
Feature activation+0.118
Top resid features:
way
Token way
Feature activation+2.461
Top resid features:
to
Token to
Feature activation+0.186
Top resid features:
make
Token make
Feature activation+0.138
Top resid features:
these
Token these
Feature activation+0.028
Top resid features:
variations
Token variations
Feature activation+0.097
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
power
Token power
Feature activation-0.119
Top resid features:
,
Token,
Feature activation-0.018
Top resid features:
and
Token and
Feature activation+0.126
Top resid features:
their
Token their
Feature activation+0.038
Top resid features:
first
Token first
Feature activation+0.109
Top resid features:
act
Token act
Feature activation+3.454
Top resid features:
out
Token out
Feature activation+0.168
Top resid features:
of
Token of
Feature activation+0.055
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
gate
Token gate
Feature activation+0.070
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
they
Token they
Feature activation-0.009
Top resid features:
are
Token are
Feature activation-0.002
Top resid features:
certain
Token certain
Feature activation+0.062
Top resid features:
the
Token the
Feature activation+0.058
Top resid features:
only
Token only
Feature activation+0.145
Top resid features:
way
Token way
Feature activation+3.015
Top resid features:
to
Token to
Feature activation+0.089
Top resid features:
fight
Token fight
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
Trump
Token Trump
Feature activation-0.001
Top resid features:
administration
Token administration
Feature activation+0.072
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
spot
Token spot
Feature activation-0.019
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.168
Top resid features:
only
Token only
Feature activation+0.137
Top resid features:
way
Token way
Feature activation+2.985
Top resid features:
I
Token I
Feature activation+0.038
Top resid features:
see
Token see
Feature activation+0.162
Top resid features:
him
Token him
Feature activation+0.122
Top resid features:
not
Token not
Feature activation+0.070
Top resid features:
starting
Token starting
Feature activation+0.331
Top resid features:
they
Token they
Feature activation-0.010
Top resid features:
are
Token are
Feature activation+0.001
Top resid features:
certain
Token certain
Feature activation+0.040
Top resid features:
the
Token the
Feature activation+0.048
Top resid features:
only
Token only
Feature activation+0.074
Top resid features:
way
Token way
Feature activation+3.136
Top resid features:
to
Token to
Feature activation+0.067
Top resid features:
fight
Token fight
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
Trump
Token Trump
Feature activation+0.004
Top resid features:
administration
Token administration
Feature activation+0.205
Top resid features:
Ċ
TokenĊ
Feature activation+0.195
Top resid features:
Ċ
TokenĊ
Feature activation+0.183
Top resid features:
The
TokenThe
Feature activation+0.027
Top resid features:
other
Token other
Feature activation+0.019
Top resid features:
pragmatic
Token pragmatic
Feature activation+0.007
Top resid features:
approach
Token approach
Feature activation+2.961
Top resid features:
to
Token to
Feature activation+0.160
Top resid features:
reducing
Token reducing
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
cost
Token cost
Feature activation+0.386
Top resid features:
of
Token of
Feature activation+0.074
Top resid features:
pursuit
Token pursuit
Feature activation+0.039
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
this
Token this
Feature activation+0.002
Top resid features:
happy
Token happy
Feature activation+0.017
Top resid features:
-
Token-
Feature activation-0.022
Top resid features:
go
Tokengo
Feature activation+3.874
Top resid features:
-
Token-
Feature activation+0.065
Top resid features:
l
Tokenl
Feature activation+0.000
Top resid features:
ucky
Tokenucky
Feature activation+0.000
Top resid features:
albeit
Token albeit
Feature activation+0.000
Top resid features:
death
Token death
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.03

Head 2: 0.03

Head 3: 0.04

Head 4: 0.05

Head 5: 0.05

Head 6: 0.02

Head 7: 0.06

Head 8: 0.15

Head 9: 0.03

Head 10: 0.37

Head 11: 0.09

Positive logits

Fab2.97

Faust2.87

MAT2.63

Lind2.61

fab2.55

Bern2.48

Lyn2.48

Madd2.48

Matrix2.45

Benn2.44

Lind2.43

Corn2.42

Corn2.40

Lal2.38

Columb2.37

Matte2.34

Belarus2.34

Ill2.33

Marqu2.33

Mall2.33

Negative logits

��-3.06

OTE-2.74

ogle-2.65

hoe-2.58

��-2.57

guyen-2.56

tesy-2.54

eus-2.53

aurus-2.53

agos-2.51

ote-2.49

Roads-2.45

Services-2.44

este-2.43

arrison-2.37

nyder-2.37

anchez-2.36

ッド-2.35

�士-2.34

aples-2.33

INTERVAL 4.858 - 5.398
CONTAINS 0.000%

to
Token to
Feature activation+0.000
predict
Token predict
Feature activation+0.000
or
Token or
Feature activation+0.000
observe
Token observe
Feature activation+0.000
an
Token an
Feature activation+0.000
eruption
Token eruption
Feature activation+5.398
is
Token is
Feature activation+0.000
through
Token through
Feature activation+0.000
remote
Token remote
Feature activation+0.000
sensing
Token sensing
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 4.318 - 4.858
CONTAINS 0.000%

variations
Token variations
Feature activation+2.447
and
Token and
Feature activation+0.000
keep
Token keep
Feature activation+0.000
on
Token on
Feature activation+0.000
with
Token with
Feature activation+0.000
them
Token them
Feature activation+4.793
will
Token will
Feature activation+0.972
be
Token be
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
one
Token one
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
reach
Token reach
Feature activation+0.000
these
Token these
Feature activation+0.000
targets
Token targets
Feature activation+4.588
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
cut
Token cut
Feature activation+0.000
down
Token down
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 3.779 - 4.318
CONTAINS 0.000%

INTERVAL 3.239 - 3.779
CONTAINS 0.001%

a
Token a
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
compl
Tokencompl
Feature activation+0.000
iant
Tokeniant
Feature activation+0.000
device
Token device
Feature activation+3.678
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
market
Token market
Feature activation+3.460
include
Token include
Feature activation+0.000
competitors
Token competitors
Feature activation+0.000
compl
Tokencompl
Feature activation+0.000
iant
Tokeniant
Feature activation+0.000
device
Token device
Feature activation+3.678
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
market
Token market
Feature activation+3.460
include
Token include
Feature activation+0.000
competitors
Token competitors
Feature activation+0.000
not
Token not
Feature activation+0.000
ifying
Tokenifying
Feature activation+0.000
authorities
Token authorities
Feature activation+0.000
great
Token great
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
document
Token document
Feature activation+0.000
our
Token our
Feature activation+0.000
tasks
Token tasks
Feature activation+3.612
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
5
Token5
Feature activation+0.000
)
Token)
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+0.000
referendum
Token referendum
Feature activation+3.598
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
that
Token that
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
read
Token read
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
lyrics
Token lyrics
Feature activation+3.352
is
Token is
Feature activation+0.000
by
Token by
Feature activation+0.000
playing
Token playing
Feature activation+0.000
the
Token the
Feature activation+0.000
instrumental
Token instrumental
Feature activation+0.000

INTERVAL 2.699 - 3.239
CONTAINS 0.000%

only
Token only
Feature activation+0.000
way
Token way
Feature activation+0.000
out
Token out
Feature activation+3.733
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
crisis
Token crisis
Feature activation+2.889
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
implement
Token implement
Feature activation+0.000
an
Token an
Feature activation+0.000
EU
Token EU
Feature activation+0.000
and
Token and
Feature activation+0.000
language
Token language
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
from
Token from
Feature activation+0.000
other
Token other
Feature activation+0.000
sources
Token sources
Feature activation+3.222
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
install
Token install
Feature activation+0.000
the
Token the
Feature activation+0.000
browser
Token browser
Feature activation+0.000
to
Token to
Feature activation+0.000
compare
Token compare
Feature activation+0.000
how
Token how
Feature activation+0.000
well
Token well
Feature activation+0.000
predictions
Token predictions
Feature activation+0.000
worked
Token worked
Feature activation+2.942
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
rank
Token rank
Feature activation+0.000
all
Token all
Feature activation+0.000
players
Token players
Feature activation+0.000

INTERVAL 2.159 - 2.699
CONTAINS 0.000%

ultimate
Token ultimate
Feature activation+0.000
way
Token way
Feature activation+1.471
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
these
Token these
Feature activation+0.000
variations
Token variations
Feature activation+2.447
and
Token and
Feature activation+0.000
keep
Token keep
Feature activation+0.000
on
Token on
Feature activation+0.000
with
Token with
Feature activation+0.000
them
Token them
Feature activation+4.793
This
TokenThis
Feature activation+0.000
easiest
Token easiest
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
this
Token this
Feature activation+2.485
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
an
Token an
Feature activation+0.000
Amazon
Token Amazon
Feature activation+0.000

INTERVAL 1.619 - 2.159
CONTAINS 0.001%

reducing
Token reducing
Feature activation+0.000
the
Token the
Feature activation+0.000
cost
Token cost
Feature activation+0.000
of
Token of
Feature activation+0.000
garbage
Token garbage
Feature activation+0.000
collection
Token collection
Feature activation+1.719
in
Token in
Feature activation+0.000
Er
Token Er
Feature activation+0.000
lang
Tokenlang
Feature activation+0.066
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
happy
Token happy
Feature activation+0.000
-
Token-
Feature activation+0.000
go
Tokengo
Feature activation+0.000
-
Token-
Feature activation+1.679
l
Tokenl
Feature activation+0.558
ucky
Tokenucky
Feature activation+0.000
albeit
Token albeit
Feature activation+0.000
death
Token death
Feature activation+0.000
-
Token-
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
fight
Token fight
Feature activation+0.000
the
Token the
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
administration
Token administration
Feature activation+1.786
now
Token now
Feature activation+1.769
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
galvan
Token galvan
Feature activation+0.000
ize
Tokenize
Feature activation+0.000
way
Token way
Feature activation+0.000
I
Token I
Feature activation+0.000
see
Token see
Feature activation+0.000
him
Token him
Feature activation+0.000
not
Token not
Feature activation+0.000
starting
Token starting
Feature activation+1.771
in
Token in
Feature activation+0.000
Week
Token Week
Feature activation+0.000
1
Token 1
Feature activation+1.586
is
Token is
Feature activation+0.000
if
Token if
Feature activation+0.000
to
Token to
Feature activation+0.000
fight
Token fight
Feature activation+0.000
the
Token the
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
administration
Token administration
Feature activation+1.786
now
Token now
Feature activation+1.769
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
galvan
Token galvan
Feature activation+0.000
ize
Tokenize
Feature activation+0.000
volunteers
Token volunteers
Feature activation+0.000

INTERVAL 1.080 - 1.619
CONTAINS 0.002%

the
Token the
Feature activation+0.000
app
Token app
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
impact
Token impact
Feature activation+1.360
is
Token is
Feature activation+0.000
anecd
Token anecd
Feature activation+0.000
otally
Tokenotally
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Another
TokenAnother
Feature activation+0.000
common
Token common
Feature activation+0.000
reason
Token reason
Feature activation+0.000
for
Token for
Feature activation+0.000
this
Token this
Feature activation+0.000
trend
Token trend
Feature activation+1.404
of
Token of
Feature activation+0.000
car
Token car
Feature activation+0.000
-
Token-
Feature activation+0.000
less
Tokenless
Feature activation+0.000
Millennials
Token Millennials
Feature activation+1.409
apparatus
Token apparatus
Feature activation+0.193
to
Token to
Feature activation+0.000
invest
Token invest
Feature activation+0.000
and
Token and
Feature activation+0.000
create
Token create
Feature activation+0.000
jobs
Token jobs
Feature activation+1.344
are
Token are
Feature activation+0.000
large
Token large
Feature activation+0.000
institutions
Token institutions
Feature activation+0.000
,
Token,
Feature activation+0.000
banks
Token banks
Feature activation+0.000
the
Token the
Feature activation+0.000
firmware
Token firmware
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
home
Token home
Feature activation+0.000
router
Token router
Feature activation+1.334
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
throw
Token throw
Feature activation+0.000
it
Token it
Feature activation+0.000
away
Token away
Feature activation+0.000
trend
Token trend
Feature activation+1.404
of
Token of
Feature activation+0.000
car
Token car
Feature activation+0.000
-
Token-
Feature activation+0.000
less
Tokenless
Feature activation+0.000
Millennials
Token Millennials
Feature activation+1.409
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
fact
Token fact
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 0.540 - 1.080
CONTAINS 0.004%

Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
security
Token security
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
computers
Token computers
Feature activation+0.702
and
Token and
Feature activation+0.000
phones
Token phones
Feature activation+0.892
also
Token also
Feature activation+0.000
comes
Token comes
Feature activation+0.000
from
Token from
Feature activation+0.000
My
TokenMy
Feature activation+0.000
best
Token best
Feature activation+0.000
guess
Token guess
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
moment
Token moment
Feature activation+0.561
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
this
Token this
Feature activation+0.000
was
Token was
Feature activation+0.000
an
Token an
Feature activation+0.000
1944
Token 1944
Feature activation+0.000
,
Token,
Feature activation+0.000
had
Token had
Feature activation+0.000
gone
Token gone
Feature activation+0.000
almost
Token almost
Feature activation+0.000
too
Token too
Feature activation+0.740
well
Token well
Feature activation+0.000
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
a
Token a
Feature activation+0.000
fierce
Token fierce
Feature activation+0.000
The
Token The
Feature activation+0.000
sure
Token sure
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
increase
Token increase
Feature activation+0.000
productivity
Token productivity
Feature activation+0.922
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
better
Token better
Feature activation+0.000
administ
Token administ
Feature activation+0.000
rate
Tokenrate
Feature activation+0.000
generally
Token generally
Feature activation+0.000
favored
Token favored
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000
door
Tokendoor
Feature activation+0.000
-
Token-
Feature activation+0.847
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.000
door
Tokendoor
Feature activation+0.000
"
Token"
Feature activation+0.000
approach
Token approach
Feature activation+0.000

INTERVAL 0.000 - 0.540
CONTAINS 99.993%

of
Token of
Feature activation+0.000
museum
Token museum
Feature activation+0.000
retrospect
Token retrospect
Feature activation+0.000
ives
Tokenives
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Whitney
Token Whitney
Feature activation+0.000
(
Token (
Feature activation+0.000
1982
Token1982
Feature activation+0.000
),
Token),
Feature activation+0.000
the
Token the
Feature activation+0.000
I
Token I
Feature activation+0.000
let
Token let
Feature activation+0.000
it
Token it
Feature activation+0.000
ring
Token ring
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
then
Token then
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
sitting
Token sitting
Feature activation+0.000
in
Token in
Feature activation+0.000
are
Token are
Feature activation+0.000
heat
Token heat
Feature activation+0.000
vision
Token vision
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Cy
TokenCy
Feature activation+0.000
cl
Tokencl
Feature activation+0.000
ops
Tokenops
Feature activation+0.000
is
Token is
Feature activation+0.000
one
Token one
Feature activation+0.000
profitable
Token profitable
Feature activation+0.000
for
Token for
Feature activation+0.000
pharmaceutical
Token pharmaceutical
Feature activation+0.000
companies
Token companies
Feature activation+0.000
to
Token to
Feature activation+0.000
research
Token research
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
pick
Token pick
Feature activation+0.000
for
Token for
Feature activation+0.000
secretary
Token secretary
Feature activation+0.000
of
Token of
Feature activation+0.000
state
Token state
Feature activation+0.000
,
Token,
Feature activation+0.000
Exxon
Token Exxon
Feature activation+0.000
Mobil
Token Mobil
Feature activation+0.000
CEO
Token CEO
Feature activation+0.000
Rex
Token Rex
Feature activation+0.000
Tillerson
Token Tillerson
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H11.10: (feature 4353)

TOP ACTIVATIONS
MAX = 10.445

ck
Tokenck
Feature activation+0.000
,
Token,
Feature activation+0.000
founder
Token founder
Feature activation+0.000
and
Token and
Feature activation+0.000
chief
Token chief
Feature activation+0.000
technology
Token technology
Feature activation+10.445
officer
Token officer
Feature activation+0.000
of
Token of
Feature activation+0.000
Cloud
Token Cloud
Feature activation+0.000
Shield
TokenShield
Feature activation+0.000
,
Token,
Feature activation+0.000
H
Token H
Feature activation+0.000
irsch
Tokenirsch
Feature activation+0.000
horn
Tokenhorn
Feature activation+0.000
,
Token,
Feature activation+0.000
chief
Token chief
Feature activation+0.000
operating
Token operating
Feature activation+10.260
officer
Token officer
Feature activation+0.000
of
Token of
Feature activation+0.000
mall
Token mall
Feature activation+0.000
owner
Token owner
Feature activation+0.000
RD
Token RD
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+1.684
Chief
Token Chief
Feature activation+0.000
Technology
Token Technology
Feature activation+10.184
Officer
Token Officer
Feature activation+0.097
Todd
Token Todd
Feature activation+0.000
Park
Token Park
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Greg
Token Greg
Feature activation+0.000
Mc
Token Mc
Feature activation+0.000
Bride
TokenBride
Feature activation+0.000
,
Token,
Feature activation+0.000
chief
Token chief
Feature activation+0.000
financial
Token financial
Feature activation+10.127
analyst
Token analyst
Feature activation+0.745
for
Token for
Feature activation+0.000
Bank
Token Bank
Feature activation+0.000
rate
Tokenrate
Feature activation+0.000
.
Token.
Feature activation+0.000
McC
Token McC
Feature activation+0.000
all
Tokenall
Feature activation+0.000
um
Tokenum
Feature activation+0.000
,
Token,
Feature activation+0.000
chief
Token chief
Feature activation+0.000
technology
Token technology
Feature activation+9.773
officer
Token officer
Feature activation+0.000
at
Token at
Feature activation+0.000
Orange
Token Orange
Feature activation+0.000
Business
Token Business
Feature activation+0.000
Services
Token Services
Feature activation+0.000
also
Token also
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.000
and
Token and
Feature activation+0.000
chief
Token chief
Feature activation+0.000
executive
Token executive
Feature activation+8.502
officer
Token officer
Feature activation+2.643
of
Token of
Feature activation+0.000
United
Token United
Feature activation+0.000
Way
Token Way
Feature activation+0.000
of
Token of
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
chief
Token chief
Feature activation+0.000
technology
Token technology
Feature activation+8.454
officer
Token officer
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
D
TokenD
Feature activation+0.000
erek
Tokenerek
Feature activation+0.000
White
Token White
Feature activation+0.000
,
Token,
Feature activation+0.000
chief
Token chief
Feature activation+0.000
design
Token design
Feature activation+8.360
and
Token and
Feature activation+0.000
digital
Token digital
Feature activation+5.441
officer
Token officer
Feature activation+0.362
,
Token,
Feature activation+0.000
Barclays
Token Barclays
Feature activation+0.000
Statement
TokenStatement
Feature activation+0.000
by
Token by
Feature activation+0.000
FC
Token FC
Feature activation+0.000
Barcelona
Token Barcelona
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
Revenue
Token Revenue
Feature activation+7.951
Officer
Token Officer
Feature activation+0.000
,
Token,
Feature activation+0.000
Frances
Token Frances
Feature activation+0.000
co
Tokenco
Feature activation+0.000
Cal
Token Cal
Feature activation+0.000
-
Token-
Feature activation+0.000
Found
TokenFound
Feature activation+0.000
er
Tokener
Feature activation+0.000
and
Token and
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
Research
Token Research
Feature activation+7.762
Officer
Token Officer
Feature activation+0.000
Kyle
Token Kyle
Feature activation+0.000
Dro
Token Dro
Feature activation+0.000
pp
Tokenpp
Feature activation+0.000
.
Token.
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
James
Token James
Feature activation+0.000
Hughes
Token Hughes
Feature activation+0.000
,
Token,
Feature activation+0.000
chief
Token chief
Feature activation+0.000
market
Token market
Feature activation+7.511
analyst
Token analyst
Feature activation+0.000
at
Token at
Feature activation+0.000
FX
Token FX
Feature activation+0.000
broker
Token broker
Feature activation+0.000
Ax
Token Ax
Feature activation+0.000
shares
Token shares
Feature activation+0.000
an
Token an
Feature activation+0.000
address
Token address
Feature activation+0.000
and
Token and
Feature activation+0.000
chief
Token chief
Feature activation+0.000
financial
Token financial
Feature activation+7.374
officer
Token officer
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
church
Token church
Feature activation+0.000
,
Token,
Feature activation+0.000
city
Token city
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
chief
Token chief
Feature activation+0.427
financial
Token financial
Feature activation+7.220
officer
Token officer
Feature activation+0.000
,
Token,
Feature activation+0.000
Ben
Token Ben
Feature activation+0.000
Gor
Token Gor
Feature activation+0.000
z
Tokenz
Feature activation+0.000
8
Token8
Feature activation+0.000
European
Token European
Feature activation+0.000
Union
Token Union
Feature activation+0.000
's
Token's
Feature activation+0.000
chief
Token chief
Feature activation+0.110
Brexit
Token Brexit
Feature activation+7.157
negotiator
Token negotiator
Feature activation+1.202
,
Token,
Feature activation+0.035
Michel
Token Michel
Feature activation+0.000
Barn
Token Barn
Feature activation+0.000
ier
Tokenier
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
's
Token's
Feature activation+0.000
chief
Token chief
Feature activation+0.000
of
Token of
Feature activation+0.000
security
Token security
Feature activation+4.679
operations
Token operations
Feature activation+7.047
was
Token was
Feature activation+0.000
forced
Token forced
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
chief
Token chief
Feature activation+0.000
law
Token law
Feature activation+0.819
-
Token-
Feature activation+0.000
enforcement
Tokenenforcement
Feature activation+6.793
officer
Token officer
Feature activation+0.000
.
Token.
Feature activation+0.000
Sessions
Token Sessions
Feature activation+0.000
announced
Token announced
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
Hat
Token Hat
Feature activation+0.000
's
Token's
Feature activation+0.000
president
Token president
Feature activation+0.000
and
Token and
Feature activation+0.000
chief
Token chief
Feature activation+0.000
executive
Token executive
Feature activation+6.417
officer
Token officer
Feature activation+0.068
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
93
Token 93
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
of
Token of
Feature activation+0.000
chief
Token chief
Feature activation+0.000
executive
Token executive
Feature activation+6.089
officer
Token officer
Feature activation+3.125
positions
Token positions
Feature activation+0.000
in
Token in
Feature activation+0.000
Australian
Token Australian
Feature activation+0.000
corporations
Token corporations
Feature activation+0.000
The
Token The
Feature activation+0.000
European
Token European
Feature activation+0.000
Parliament
Token Parliament
Feature activation+0.000
's
Token's
Feature activation+0.000
chief
Token chief
Feature activation+0.000
Brexit
Token Brexit
Feature activation+5.567
negotiator
Token negotiator
Feature activation+0.000
Guy
Token Guy
Feature activation+0.000
Ver
Token Ver
Feature activation+0.000
hof
Tokenhof
Feature activation+0.000
stadt
Tokenstadt
Feature activation+0.000
er
Tokener
Feature activation+0.000
,
Token,
Feature activation+0.000
chief
Token chief
Feature activation+0.000
designer
Token designer
Feature activation+0.000
and
Token and
Feature activation+0.000
technical
Token technical
Feature activation+5.545
director
Token director
Feature activation+0.000
at
Token at
Feature activation+0.000
Hein
Token Hein
Feature activation+0.000
kel
Tokenkel
Feature activation+0.000
.
Token.
Feature activation+0.000

Top DFA by src position
MAX = 11.983

Jung
Token Jung
Feature activation-0.002
Top resid features:
ck
Tokenck
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
founder
Token founder
Feature activation+0.041
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
chief
Token chief
Feature activation+11.983
Top resid features:
technology
Token technology
Feature activation+0.041
Top resid features:
officer
Token officer
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Cloud
Token Cloud
Feature activation+0.000
Top resid features:
Shield
TokenShield
Feature activation+0.000
Top resid features:
Roger
Token Roger
Feature activation-0.003
Top resid features:
H
Token H
Feature activation-0.011
Top resid features:
irsch
Tokenirsch
Feature activation-0.021
Top resid features:
horn
Tokenhorn
Feature activation-0.030
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
chief
Token chief
Feature activation+11.282
Top resid features:
operating
Token operating
Feature activation+0.315
Top resid features:
officer
Token officer
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
mall
Token mall
Feature activation+0.000
Top resid features:
owner
Token owner
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.005
Top resid features:
U
Token U
Feature activation-0.004
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
S
TokenS
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
Chief
Token Chief
Feature activation+6.455
Top resid features:
Information
Token Information
Feature activation+0.071
Top resid features:
Officer
Token Officer
Feature activation+0.158
Top resid features:
Steve
Token Steve
Feature activation+0.017
Top resid features:
Van
Token Van
Feature activation-0.001
Top resid features:
R
TokenR
Feature activation-0.004
Top resid features:
says
Token says
Feature activation+0.004
Top resid features:
Greg
Token Greg
Feature activation-0.011
Top resid features:
Mc
Token Mc
Feature activation-0.023
Top resid features:
Bride
TokenBride
Feature activation-0.015
Top resid features:
,
Token,
Feature activation+0.051
Top resid features:
chief
Token chief
Feature activation+11.381
Top resid features:
financial
Token financial
Feature activation+0.039
Top resid features:
analyst
Token analyst
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Bank
Token Bank
Feature activation+0.000
Top resid features:
rate
Tokenrate
Feature activation+0.000
Top resid features:
Mark
Token Mark
Feature activation-0.007
Top resid features:
McC
Token McC
Feature activation-0.021
Top resid features:
all
Tokenall
Feature activation-0.004
Top resid features:
um
Tokenum
Feature activation-0.017
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
chief
Token chief
Feature activation+11.319
Top resid features:
technology
Token technology
Feature activation+0.011
Top resid features:
officer
Token officer
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
Orange
Token Orange
Feature activation+0.000
Top resid features:
Business
Token Business
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.020
Top resid features:
also
Token also
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.041
Top resid features:
president
Token president
Feature activation+0.169
Top resid features:
and
Token and
Feature activation+0.041
Top resid features:
chief
Token chief
Feature activation+9.278
Top resid features:
executive
Token executive
Feature activation+0.221
Top resid features:
officer
Token officer
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
United
Token United
Feature activation+0.000
Top resid features:
Way
Token Way
Feature activation+0.000
Top resid features:
Chop
Token Chop
Feature activation-0.010
Top resid features:
ra
Tokenra
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
first
Token first
Feature activation+0.006
Top resid features:
chief
Token chief
Feature activation+9.635
Top resid features:
technology
Token technology
Feature activation+0.003
Top resid features:
officer
Token officer
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:
White
Token White
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
D
TokenD
Feature activation-0.012
Top resid features:
erek
Tokenerek
Feature activation+0.001
Top resid features:
White
Token White
Feature activation-0.042
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
chief
Token chief
Feature activation+9.735
Top resid features:
design
Token design
Feature activation-0.023
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
digital
Token digital
Feature activation+0.000
Top resid features:
officer
Token officer
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Statement
TokenStatement
Feature activation+0.025
Top resid features:
by
Token by
Feature activation-0.000
Top resid features:
FC
Token FC
Feature activation-0.023
Top resid features:
Barcelona
Token Barcelona
Feature activation+0.015
Top resid features:
Chief
Token Chief
Feature activation+9.073
Top resid features:
Revenue
Token Revenue
Feature activation+0.152
Top resid features:
Officer
Token Officer
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Frances
Token Frances
Feature activation+0.000
Top resid features:
co
Tokenco
Feature activation+0.000
Top resid features:
Co
Token Co
Feature activation+0.058
Top resid features:
-
Token-
Feature activation+0.019
Top resid features:
Found
TokenFound
Feature activation+0.051
Top resid features:
er
Tokener
Feature activation+0.033
Top resid features:
and
Token and
Feature activation-0.034
Top resid features:
Chief
Token Chief
Feature activation+8.757
Top resid features:
Research
Token Research
Feature activation+0.106
Top resid features:
Officer
Token Officer
Feature activation+0.000
Top resid features:
Kyle
Token Kyle
Feature activation+0.000
Top resid features:
Dro
Token Dro
Feature activation+0.000
Top resid features:
pp
Tokenpp
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.009
Top resid features:
Ŀ
TokenĿ
Feature activation-0.007
Top resid features:
James
Token James
Feature activation+0.002
Top resid features:
Hughes
Token Hughes
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
chief
Token chief
Feature activation+8.739
Top resid features:
market
Token market
Feature activation+0.037
Top resid features:
analyst
Token analyst
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
FX
Token FX
Feature activation+0.000
Top resid features:
broker
Token broker
Feature activation+0.000
Top resid features:
PAC
Token PAC
Feature activation-0.033
Top resid features:
shares
Token shares
Feature activation-0.146
Top resid features:
an
Token an
Feature activation-0.064
Top resid features:
address
Token address
Feature activation-0.117
Top resid features:
and
Token and
Feature activation-0.054
Top resid features:
chief
Token chief
Feature activation+8.969
Top resid features:
financial
Token financial
Feature activation+0.000
Top resid features:
officer
Token officer
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
church
Token church
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation-0.012
Top resid features:
city
Token city
Feature activation-0.027
Top resid features:
âĢ
TokenâĢ
Feature activation+0.015
Top resid features:
Ļ
TokenĻ
Feature activation-0.015
Top resid features:
s
Tokens
Feature activation-0.002
Top resid features:
chief
Token chief
Feature activation+8.584
Top resid features:
financial
Token financial
Feature activation+0.054
Top resid features:
officer
Token officer
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ben
Token Ben
Feature activation+0.000
Top resid features:
Gor
Token Gor
Feature activation+0.000
Top resid features:
/
Token/
Feature activation-0.023
Top resid features:
8
Token8
Feature activation-0.003
Top resid features:
European
Token European
Feature activation+0.016
Top resid features:
Union
Token Union
Feature activation-0.030
Top resid features:
's
Token's
Feature activation-0.056
Top resid features:
chief
Token chief
Feature activation+8.316
Top resid features:
Brexit
Token Brexit
Feature activation-0.003
Top resid features:
negotiator
Token negotiator
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Michel
Token Michel
Feature activation+0.000
Top resid features:
Barn
Token Barn
Feature activation+0.000
Top resid features:
ated
Tokenated
Feature activation-0.015
Top resid features:
policemen
Token policemen
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.018
Top resid features:
Apple
Token Apple
Feature activation+0.018
Top resid features:
's
Token's
Feature activation-0.088
Top resid features:
chief
Token chief
Feature activation+7.891
Top resid features:
of
Token of
Feature activation+0.224
Top resid features:
security
Token security
Feature activation+0.156
Top resid features:
operations
Token operations
Feature activation+0.124
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
forced
Token forced
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.084
Top resid features:
nation
Token nation
Feature activation-0.088
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ļ
TokenĻ
Feature activation-0.009
Top resid features:
s
Tokens
Feature activation-0.095
Top resid features:
chief
Token chief
Feature activation+9.132
Top resid features:
law
Token law
Feature activation-0.132
Top resid features:
-
Token-
Feature activation-0.057
Top resid features:
enforcement
Tokenenforcement
Feature activation+0.022
Top resid features:
officer
Token officer
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Red
Token Red
Feature activation-0.037
Top resid features:
Hat
Token Hat
Feature activation-0.081
Top resid features:
's
Token's
Feature activation-0.048
Top resid features:
president
Token president
Feature activation+0.116
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
chief
Token chief
Feature activation+7.602
Top resid features:
executive
Token executive
Feature activation+0.203
Top resid features:
officer
Token officer
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.029
Top resid features:
93
Token 93
Feature activation-0.033
Top resid features:
per
Token per
Feature activation-0.012
Top resid features:
cent
Token cent
Feature activation-0.040
Top resid features:
of
Token of
Feature activation-0.092
Top resid features:
chief
Token chief
Feature activation+7.404
Top resid features:
executive
Token executive
Feature activation+0.379
Top resid features:
officer
Token officer
Feature activation+0.000
Top resid features:
positions
Token positions
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Australian
Token Australian
Feature activation+0.000
Top resid features:
8
Token8
Feature activation+0.003
Top resid features:
The
Token The
Feature activation+0.047
Top resid features:
European
Token European
Feature activation+0.019
Top resid features:
Parliament
Token Parliament
Feature activation-0.014
Top resid features:
's
Token's
Feature activation-0.030
Top resid features:
chief
Token chief
Feature activation+5.838
Top resid features:
Brexit
Token Brexit
Feature activation-0.012
Top resid features:
negotiator
Token negotiator
Feature activation+0.000
Top resid features:
Guy
Token Guy
Feature activation+0.000
Top resid features:
Ver
Token Ver
Feature activation+0.000
Top resid features:
hof
Tokenhof
Feature activation+0.000
Top resid features:
Robert
Token Robert
Feature activation-0.023
Top resid features:
L
Token L
Feature activation-0.020
Top resid features:
uss
Tokenuss
Feature activation-0.025
Top resid features:
er
Tokener
Feature activation-0.029
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
chief
Token chief
Feature activation+6.765
Top resid features:
designer
Token designer
Feature activation+0.169
Top resid features:
and
Token and
Feature activation+0.078
Top resid features:
technical
Token technical
Feature activation+0.022
Top resid features:
director
Token director
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.04

Head 2: 0.02

Head 3: 0.05

Head 4: 0.03

Head 5: 0.02

Head 6: 0.02

Head 7: 0.03

Head 8: 0.24

Head 9: 0.02

Head 10: 0.37

Head 11: 0.08

Positive logits

NetMessage3.41

ascript2.89

natureconservancy2.83

Downloadha2.70

vir2.61

buquerque2.59

ocol2.58

usalem2.57

mosqu2.54

Flavoring2.52

2.49

vironment2.49

enezuel2.49

visual2.48

imil2.41

mosp2.39

2.35

ouston2.35

vironments2.34

ooting2.34

Negative logits

Prime-2.69

Laz-2.61

cores-2.60

Boehner-2.56

LS-2.54

Kings-2.52

prime-2.50

King-2.48

Mega-2.48

giants-2.46

Cluster-2.46

clusters-2.45

Rack-2.45

cluster-2.45

Lifetime-2.45

LD-2.41

Premiership-2.38

prime-2.37

gang-2.36

Stanley-2.36

INTERVAL 9.400 - 10.445
CONTAINS 0.001%

U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+1.684
Chief
Token Chief
Feature activation+0.000
Technology
Token Technology
Feature activation+10.184
Officer
Token Officer
Feature activation+0.097
Todd
Token Todd
Feature activation+0.000
Park
Token Park
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
H
Token H
Feature activation+0.000
irsch
Tokenirsch
Feature activation+0.000
horn
Tokenhorn
Feature activation+0.000
,
Token,
Feature activation+0.000
chief
Token chief
Feature activation+0.000
operating
Token operating
Feature activation+10.260
officer
Token officer
Feature activation+0.000
of
Token of
Feature activation+0.000
mall
Token mall
Feature activation+0.000
owner
Token owner
Feature activation+0.000
RD
Token RD
Feature activation+0.000
Greg
Token Greg
Feature activation+0.000
Mc
Token Mc
Feature activation+0.000
Bride
TokenBride
Feature activation+0.000
,
Token,
Feature activation+0.000
chief
Token chief
Feature activation+0.000
financial
Token financial
Feature activation+10.127
analyst
Token analyst
Feature activation+0.745
for
Token for
Feature activation+0.000
Bank
Token Bank
Feature activation+0.000
rate
Tokenrate
Feature activation+0.000
.
Token.
Feature activation+0.000
ck
Tokenck
Feature activation+0.000
,
Token,
Feature activation+0.000
founder
Token founder
Feature activation+0.000
and
Token and
Feature activation+0.000
chief
Token chief
Feature activation+0.000
technology
Token technology
Feature activation+10.445
officer
Token officer
Feature activation+0.000
of
Token of
Feature activation+0.000
Cloud
Token Cloud
Feature activation+0.000
Shield
TokenShield
Feature activation+0.000
,
Token,
Feature activation+0.000
McC
Token McC
Feature activation+0.000
all
Tokenall
Feature activation+0.000
um
Tokenum
Feature activation+0.000
,
Token,
Feature activation+0.000
chief
Token chief
Feature activation+0.000
technology
Token technology
Feature activation+9.773
officer
Token officer
Feature activation+0.000
at
Token at
Feature activation+0.000
Orange
Token Orange
Feature activation+0.000
Business
Token Business
Feature activation+0.000
Services
Token Services
Feature activation+0.000

INTERVAL 8.356 - 9.400
CONTAINS 0.000%

also
Token also
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.000
and
Token and
Feature activation+0.000
chief
Token chief
Feature activation+0.000
executive
Token executive
Feature activation+8.502
officer
Token officer
Feature activation+2.643
of
Token of
Feature activation+0.000
United
Token United
Feature activation+0.000
Way
Token Way
Feature activation+0.000
of
Token of
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
chief
Token chief
Feature activation+0.000
technology
Token technology
Feature activation+8.454
officer
Token officer
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
D
TokenD
Feature activation+0.000
erek
Tokenerek
Feature activation+0.000
White
Token White
Feature activation+0.000
,
Token,
Feature activation+0.000
chief
Token chief
Feature activation+0.000
design
Token design
Feature activation+8.360
and
Token and
Feature activation+0.000
digital
Token digital
Feature activation+5.441
officer
Token officer
Feature activation+0.362
,
Token,
Feature activation+0.000
Barclays
Token Barclays
Feature activation+0.000

INTERVAL 7.311 - 8.356
CONTAINS 0.000%

Ŀ
TokenĿ
Feature activation+0.000
James
Token James
Feature activation+0.000
Hughes
Token Hughes
Feature activation+0.000
,
Token,
Feature activation+0.000
chief
Token chief
Feature activation+0.000
market
Token market
Feature activation+7.511
analyst
Token analyst
Feature activation+0.000
at
Token at
Feature activation+0.000
FX
Token FX
Feature activation+0.000
broker
Token broker
Feature activation+0.000
Ax
Token Ax
Feature activation+0.000
Statement
TokenStatement
Feature activation+0.000
by
Token by
Feature activation+0.000
FC
Token FC
Feature activation+0.000
Barcelona
Token Barcelona
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
Revenue
Token Revenue
Feature activation+7.951
Officer
Token Officer
Feature activation+0.000
,
Token,
Feature activation+0.000
Frances
Token Frances
Feature activation+0.000
co
Tokenco
Feature activation+0.000
Cal
Token Cal
Feature activation+0.000
shares
Token shares
Feature activation+0.000
an
Token an
Feature activation+0.000
address
Token address
Feature activation+0.000
and
Token and
Feature activation+0.000
chief
Token chief
Feature activation+0.000
financial
Token financial
Feature activation+7.374
officer
Token officer
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
church
Token church
Feature activation+0.000
,
Token,
Feature activation+0.000
-
Token-
Feature activation+0.000
Found
TokenFound
Feature activation+0.000
er
Tokener
Feature activation+0.000
and
Token and
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
Research
Token Research
Feature activation+7.762
Officer
Token Officer
Feature activation+0.000
Kyle
Token Kyle
Feature activation+0.000
Dro
Token Dro
Feature activation+0.000
pp
Tokenpp
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 6.267 - 7.311
CONTAINS 0.001%

8
Token8
Feature activation+0.000
European
Token European
Feature activation+0.000
Union
Token Union
Feature activation+0.000
's
Token's
Feature activation+0.000
chief
Token chief
Feature activation+0.110
Brexit
Token Brexit
Feature activation+7.157
negotiator
Token negotiator
Feature activation+1.202
,
Token,
Feature activation+0.035
Michel
Token Michel
Feature activation+0.000
Barn
Token Barn
Feature activation+0.000
ier
Tokenier
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
chief
Token chief
Feature activation+0.000
law
Token law
Feature activation+0.819
-
Token-
Feature activation+0.000
enforcement
Tokenenforcement
Feature activation+6.793
officer
Token officer
Feature activation+0.000
.
Token.
Feature activation+0.000
Sessions
Token Sessions
Feature activation+0.000
announced
Token announced
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
Hat
Token Hat
Feature activation+0.000
's
Token's
Feature activation+0.000
president
Token president
Feature activation+0.000
and
Token and
Feature activation+0.000
chief
Token chief
Feature activation+0.000
executive
Token executive
Feature activation+6.417
officer
Token officer
Feature activation+0.068
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
chief
Token chief
Feature activation+0.427
financial
Token financial
Feature activation+7.220
officer
Token officer
Feature activation+0.000
,
Token,
Feature activation+0.000
Ben
Token Ben
Feature activation+0.000
Gor
Token Gor
Feature activation+0.000
z
Tokenz
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
's
Token's
Feature activation+0.000
chief
Token chief
Feature activation+0.000
of
Token of
Feature activation+0.000
security
Token security
Feature activation+4.679
operations
Token operations
Feature activation+7.047
was
Token was
Feature activation+0.000
forced
Token forced
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000

INTERVAL 5.222 - 6.267
CONTAINS 0.001%

93
Token 93
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
of
Token of
Feature activation+0.000
chief
Token chief
Feature activation+0.000
executive
Token executive
Feature activation+6.089
officer
Token officer
Feature activation+3.125
positions
Token positions
Feature activation+0.000
in
Token in
Feature activation+0.000
Australian
Token Australian
Feature activation+0.000
corporations
Token corporations
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
appointed
Token appointed
Feature activation+0.000
his
Token his
Feature activation+0.000
chief
Token chief
Feature activation+0.000
legal
Token legal
Feature activation+5.394
counsel
Token counsel
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
a
Token a
Feature activation+0.000
vacancy
Token vacancy
Feature activation+0.000
White
Token White
Feature activation+0.000
,
Token,
Feature activation+0.000
chief
Token chief
Feature activation+0.000
design
Token design
Feature activation+8.360
and
Token and
Feature activation+0.000
digital
Token digital
Feature activation+5.441
officer
Token officer
Feature activation+0.362
,
Token,
Feature activation+0.000
Barclays
Token Barclays
Feature activation+0.000
,
Token,
Feature activation+0.000
says
Token says
Feature activation+0.000
er
Tokener
Feature activation+0.000
,
Token,
Feature activation+0.000
chief
Token chief
Feature activation+0.000
designer
Token designer
Feature activation+0.000
and
Token and
Feature activation+0.000
technical
Token technical
Feature activation+5.545
director
Token director
Feature activation+0.000
at
Token at
Feature activation+0.000
Hein
Token Hein
Feature activation+0.000
kel
Tokenkel
Feature activation+0.000
.
Token.
Feature activation+0.000
Q
Token Q
Feature activation+0.000
N
TokenN
Feature activation+0.000
X
TokenX
Feature activation+0.000
as
Token as
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
Operating
Token Operating
Feature activation+5.485
Officer
Token Officer
Feature activation+0.000
,
Token,
Feature activation+0.000
will
Token will
Feature activation+0.000
transition
Token transition
Feature activation+0.000
into
Token into
Feature activation+0.000

INTERVAL 4.178 - 5.222
CONTAINS 0.000%

As
TokenAs
Feature activation+0.000
the
Token the
Feature activation+0.000
chief
Token chief
Feature activation+0.000
law
Token law
Feature activation+1.689
-
Token-
Feature activation+0.000
enforcement
Tokenenforcement
Feature activation+4.261
officer
Token officer
Feature activation+0.000
for
Token for
Feature activation+0.000
Mar
Token Mar
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
opa
Tokenopa
Feature activation+0.000
att
Tokenatt
Feature activation+0.000
ock
Tokenock
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
chief
Token chief
Feature activation+0.000
executive
Token executive
Feature activation+4.252
of
Token of
Feature activation+0.000
Beam
Token Beam
Feature activation+0.000
,
Token,
Feature activation+0.000
cr
Token cr
Feature activation+0.000
inged
Tokeninged
Feature activation+0.000
,
Token,
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
's
Token's
Feature activation+0.000
chief
Token chief
Feature activation+0.000
of
Token of
Feature activation+0.000
security
Token security
Feature activation+4.679
operations
Token operations
Feature activation+7.047
was
Token was
Feature activation+0.000
forced
Token forced
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
by
Token by
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+5.205
District
Token District
Feature activation+1.677
Judge
Token Judge
Feature activation+0.000
W
Token W
Feature activation+0.000
.
Token.
Feature activation+0.000
Keith
Token Keith
Feature activation+0.000

INTERVAL 3.133 - 4.178
CONTAINS 0.001%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
king
Token king
Feature activation+0.000
-
Token-
Feature activation+3.804
hell
Tokenhell
Feature activation+0.000
bastard
Token bastard
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
line
Token line
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Kyle
TokenKyle
Feature activation+0.000
Terry
Token Terry
Feature activation+0.000
,
Token,
Feature activation+0.000
Senior
Token Senior
Feature activation+0.000
Systems
Token Systems
Feature activation+3.142
and
Token and
Feature activation+0.000
Software
Token Software
Feature activation+2.460
Engineer
Token Engineer
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Kan
Token Kan
Feature activation+0.000
as
Tokenas
Feature activation+0.000
ugi
Tokenugi
Feature activation+0.000
.
Token.
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
animation
Token animation
Feature activation+3.864
director
Token director
Feature activation+0.000
Hi
Token Hi
Feature activation+0.000
roy
Tokenroy
Feature activation+0.000
uki
Tokenuki
Feature activation+0.000
Said
Token Said
Feature activation+0.000
Pro
Token Pro
Feature activation+0.000
ctor
Tokenctor
Feature activation+0.000
,
Token,
Feature activation+0.000
deputy
Token deputy
Feature activation+0.000
chief
Token chief
Feature activation+0.000
executive
Token executive
Feature activation+3.497
of
Token of
Feature activation+0.000
York
Token York
Feature activation+0.000
Teaching
Token Teaching
Feature activation+0.000
Hospital
Token Hospital
Feature activation+0.000
NHS
Token NHS
Feature activation+0.000
G
Token G
Feature activation+0.000
oss
Tokenoss
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
Lead
Token Lead
Feature activation+0.000
Game
Token Game
Feature activation+3.494
Designer
Token Designer
Feature activation+0.000
on
Token on
Feature activation+0.000
World
Token World
Feature activation+0.000
of
Token of
Feature activation+0.000
Warcraft
Token Warcraft
Feature activation+0.000

INTERVAL 2.089 - 3.133
CONTAINS 0.001%

is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
depressing
Token depressing
Feature activation+0.000
,
Token,
Feature activation+0.000
heart
Token heart
Feature activation+0.000
-
Token-
Feature activation+2.099
breaking
Tokenbreaking
Feature activation+0.000
journey
Token journey
Feature activation+0.000
through
Token through
Feature activation+0.000
one
Token one
Feature activation+0.000
woman
Token woman
Feature activation+0.000
no
Token no
Feature activation+0.000
mention
Token mention
Feature activation+0.000
of
Token of
Feature activation+0.000
any
Token any
Feature activation+0.000
other
Token other
Feature activation+0.000
former
Token former
Feature activation+2.776
officials
Token officials
Feature activation+0.000
being
Token being
Feature activation+0.000
held
Token held
Feature activation+0.000
accountable
Token accountable
Feature activation+0.000
for
Token for
Feature activation+0.000
Terry
Token Terry
Feature activation+0.000
,
Token,
Feature activation+0.000
Senior
Token Senior
Feature activation+0.000
Systems
Token Systems
Feature activation+3.142
and
Token and
Feature activation+0.000
Software
Token Software
Feature activation+2.460
Engineer
Token Engineer
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
How
TokenHow
Feature activation+0.000
would
Token would
Feature activation+0.000
2007
Token 2007
Feature activation+0.000
,
Token,
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
's
Token's
Feature activation+0.000
chief
Token chief
Feature activation+0.000
executive
Token executive
Feature activation+3.114
was
Token was
Feature activation+0.000
former
Token former
Feature activation+0.000
Beatles
Token Beatles
Feature activation+1.560
road
Token road
Feature activation+0.000
manager
Token manager
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.000
and
Token and
Feature activation+0.000
chief
Token chief
Feature activation+0.000
executive
Token executive
Feature activation+8.502
officer
Token officer
Feature activation+2.643
of
Token of
Feature activation+0.000
United
Token United
Feature activation+0.000
Way
Token Way
Feature activation+0.000
of
Token of
Feature activation+0.000
America
Token America
Feature activation+0.000

INTERVAL 1.044 - 2.089
CONTAINS 0.004%

:
Token:
Feature activation+0.000
Royal
Token Royal
Feature activation+0.224
College
Token College
Feature activation+0.000
of
Token of
Feature activation+0.833
Nursing
Token Nursing
Feature activation+0.000
and
Token and
Feature activation+1.128
NHS
Token NHS
Feature activation+0.054
England
Token England
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
Gold
Token Gold
Feature activation+0.000
we
Tokenwe
Feature activation+0.000
in
Tokenin
Feature activation+0.000
,
Token,
Feature activation+0.000
senior
Token senior
Feature activation+0.000
policy
Token policy
Feature activation+1.193
director
Token director
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Committee
Token Committee
Feature activation+0.000
for
Token for
Feature activation+0.000
company
Token company
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
chief
Token chief
Feature activation+0.000
information
Token information
Feature activation+1.698
officer
Token officer
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
station
Token station
Feature activation+0.000
's
Token's
Feature activation+0.000
"
Token "
Feature activation+0.000
most
Tokenmost
Feature activation+0.000
senior
Token senior
Feature activation+0.000
police
Token police
Feature activation+1.252
officer
Token officer
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
there
Token there
Feature activation+0.000
right
Token right
Feature activation+0.000
county
Token county
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
chief
Token chief
Feature activation+0.000
public
Token public
Feature activation+1.464
defender
Token defender
Feature activation+0.000
,
Token,
Feature activation+0.000
Mary
Token Mary
Feature activation+0.000
Mori
Token Mori
Feature activation+0.000
arty
Tokenarty
Feature activation+0.000

INTERVAL 0.000 - 1.044
CONTAINS 99.991%

lack
Token lack
Feature activation+0.000
of
Token of
Feature activation+0.000
government
Token government
Feature activation+0.000
investment
Token investment
Feature activation+0.000
in
Token in
Feature activation+0.000
infrastructure
Token infrastructure
Feature activation+0.000
has
Token has
Feature activation+0.000
hurt
Token hurt
Feature activation+0.000
production
Token production
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
63
Token 63
Feature activation+0.000
%
Token%
Feature activation+0.000
from
Token from
Feature activation+0.000
2004
Token 2004
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
relationship
Token relationship
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
were
Token were
Feature activation+0.000
also
Token also
Feature activation+0.000
not
Token not
Feature activation+0.000
regularly
Token regularly
Feature activation+0.000
checked
Token checked
Feature activation+0.000
for
Token for
Feature activation+0.000
up
Token up
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.000
date
Tokendate
Feature activation+0.000
provides
Token provides
Feature activation+0.000
transitional
Token transitional
Feature activation+0.000
and
Token and
Feature activation+0.000
permanent
Token permanent
Feature activation+0.000
housing
Token housing
Feature activation+0.000
for
Token for
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
military
Token military
Feature activation+0.000
friend
Token friend
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
none
Token none
Feature activation+0.000
of
Token of
Feature activation+0.000
us
Token us
Feature activation+0.000
understands
Token understands
Feature activation+0.000
why
Token why
Feature activation+0.000
he
Token he
Feature activation+0.000
did
Token did
Feature activation+0.000
this
Token this
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