H3.2 top features

Top feature 0 in H3.2: (feature 18855)

TOP ACTIVATIONS
MAX = 4.772

blood
Token blood
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
wound
Token wound
Feature activation+0.000
so
Token so
Feature activation+0.063
bad
Token bad
Feature activation+4.772
that
Token that
Feature activation+1.719
it
Token it
Feature activation+0.000
prompted
Token prompted
Feature activation+0.000
a
Token a
Feature activation+0.000
captain
Token captain
Feature activation+0.000
a
Token a
Feature activation+0.000
term
Token term
Feature activation+0.000
so
Token so
Feature activation+0.000
am
Token am
Feature activation+3.270
orph
Tokenorph
Feature activation+0.000
ous
Tokenous
Feature activation+4.686
that
Token that
Feature activation+1.153
it
Token it
Feature activation+0.000
can
Token can
Feature activation+0.000
cover
Token cover
Feature activation+0.000
any
Token any
Feature activation+0.000
a
Tokena
Feature activation+0.000
vow
Token vow
Feature activation+0.000
so
Token so
Feature activation+0.000
sw
Token sw
Feature activation+2.968
agger
Tokenagger
Feature activation+2.157
ing
Tokening
Feature activation+4.615
that
Token that
Feature activation+0.402
it
Token it
Feature activation+0.000
seemed
Token seemed
Feature activation+0.000
com
Token com
Feature activation+0.000
ical
Tokenical
Feature activation+0.000
,
Token,
Feature activation+2.584
the
Token the
Feature activation+0.000
paperwork
Token paperwork
Feature activation+0.000
so
Token so
Feature activation+1.707
ardu
Token ardu
Feature activation+3.311
ous
Tokenous
Feature activation+4.595
for
Token for
Feature activation+1.748
often
Token often
Feature activation+0.000
-
Token-
Feature activation+0.000
over
Tokenover
Feature activation+0.000
worked
Tokenworked
Feature activation+0.000
entire
Token entire
Feature activation+0.000
dog
Token dog
Feature activation+0.000
meat
Token meat
Feature activation+0.000
trade
Token trade
Feature activation+0.000
so
Token so
Feature activation+0.000
grotesque
Token grotesque
Feature activation+4.591
is
Token is
Feature activation+2.817
that
Token that
Feature activation+0.000
dogs
Token dogs
Feature activation+0.000
are
Token are
Feature activation+0.000
purposely
Token purposely
Feature activation+0.000
Who
Token Who
Feature activation+0.000
âĦ¢
TokenâĦ¢
Feature activation+0.000
was
Token was
Feature activation+0.000
greeted
Token greeted
Feature activation+0.000
so
Token so
Feature activation+0.000
rapt
Token rapt
Feature activation+4.585
ur
Tokenur
Feature activation+1.389
ously
Tokenously
Feature activation+4.426
,
Token,
Feature activation+2.741
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
serving
Token serving
Feature activation+0.000
her
Token her
Feature activation+0.000
interests
Token interests
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+2.865
as
Token as
Feature activation+4.523
those
Token those
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
mon
Token mon
Feature activation+0.000
ied
Tokenied
Feature activation+0.000
and
Token and
Feature activation+0.000
Mah
Token Mah
Feature activation+0.000
ali
Tokenali
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
so
Token so
Feature activation+0.000
agitated
Token agitated
Feature activation+4.448
that
Token that
Feature activation+0.178
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
charged
Token charged
Feature activation+0.000
was
Token was
Feature activation+0.000
greeted
Token greeted
Feature activation+0.000
so
Token so
Feature activation+0.000
rapt
Token rapt
Feature activation+4.585
ur
Tokenur
Feature activation+1.389
ously
Tokenously
Feature activation+4.426
,
Token,
Feature activation+2.741
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
that
Token that
Feature activation+0.000
left
Token left
Feature activation+0.000
me
Token me
Feature activation+0.000
so
Token so
Feature activation+0.000
sed
Token sed
Feature activation+1.589
ated
Tokenated
Feature activation+4.406
,
Token,
Feature activation+2.066
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
step
Token step
Feature activation+0.000
was
Token was
Feature activation+0.000
sensitive
Token sensitive
Feature activation+0.000
topic
Token topic
Feature activation+0.000
put
Token put
Feature activation+0.000
together
Token together
Feature activation+0.000
so
Token so
Feature activation+0.000
quickly
Token quickly
Feature activation+4.317
,
Token,
Feature activation+1.926
there
Token there
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
some
Token some
Feature activation+0.000
officers
Token officers
Feature activation+0.000
beat
Token beat
Feature activation+0.000
plaintiff
Token plaintiff
Feature activation+0.000
so
Token so
Feature activation+0.000
vicious
Token vicious
Feature activation+3.914
ly
Tokenly
Feature activation+4.210
that
Token that
Feature activation+0.638
they
Token they
Feature activation+0.000
rupt
Token rupt
Feature activation+0.000
ured
Tokenured
Feature activation+0.000
his
Token his
Feature activation+0.000
Goddard
Token Goddard
Feature activation+0.000
kept
Token kept
Feature activation+0.000
this
Token this
Feature activation+0.000
thing
Token thing
Feature activation+0.000
so
Token so
Feature activation+0.000
close
Token close
Feature activation+4.196
to
Token to
Feature activation+3.409
the
Token the
Feature activation+0.000
vest
Token vest
Feature activation+0.000
that
Token that
Feature activation+0.000
when
Token when
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
preparation
Token preparation
Feature activation+0.000
time
Token time
Feature activation+0.000
so
Token so
Feature activation+0.000
short
Token short
Feature activation+4.194
and
Token and
Feature activation+1.513
with
Token with
Feature activation+0.182
no
Token no
Feature activation+0.000
mid
Token mid
Feature activation+0.000
week
Tokenweek
Feature activation+0.000
172
Token172
Feature activation+0.000
,
Token,
Feature activation+0.000
went
Token went
Feature activation+0.000
so
Token so
Feature activation+0.000
far
Token far
Feature activation+1.964
above
Token above
Feature activation+4.119
and
Token and
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
that
Token that
Feature activation+0.000
my
Token my
Feature activation+0.000
mind
Token mind
Feature activation+0.000
"
Token "
Feature activation+0.000
strike
Tokenstrike
Feature activation+0.000
"
Token"
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+2.655
as
Token as
Feature activation+4.082
taking
Token taking
Feature activation+0.000
an
Token an
Feature activation+0.000
hour
Token hour
Feature activation+0.000
so
Token so
Feature activation+0.000
that
Token that
Feature activation+0.977
would
Token would
Feature activation+0.400
be
Token be
Feature activation+0.000
an
Token an
Feature activation+0.121
abuse
Token abuse
Feature activation+0.000
so
Token so
Feature activation+0.782
great
Token great
Feature activation+4.031
that
Token that
Feature activation+2.358
one
Token one
Feature activation+0.000
one
Token one
Feature activation+0.000
could
Token could
Feature activation+0.000
call
Token call
Feature activation+0.000
that
Token that
Feature activation+0.000
makes
Token makes
Feature activation+0.000
this
Token this
Feature activation+0.000
salad
Token salad
Feature activation+0.000
so
Token so
Feature activation+0.000
sensational
Token sensational
Feature activation+4.023
.
Token.
Feature activation+0.501
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
it
Token it
Feature activation+0.000
on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
terms
Token terms
Feature activation+0.000
so
Token so
Feature activation+0.858
badly
Token badly
Feature activation+4.023
,
Token,
Feature activation+3.231
is
Token is
Feature activation+1.103
just
Token just
Feature activation+0.000
pure
Token pure
Feature activation+0.000
Sch
Token Sch
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
sick
Token sick
Feature activation+0.000
so
Token so
Feature activation+0.000
violently
Token violently
Feature activation+4.008
it
Token it
Feature activation+1.143
was
Token was
Feature activation+0.381
a
Token a
Feature activation+0.372
lake
Token lake
Feature activation+0.051
of
Token of
Feature activation+0.000

Top DFA by src position
MAX = 5.547

with
Token with
Feature activation-0.003
Top resid features:
blood
Token blood
Feature activation-0.020
Top resid features:
,
Token,
Feature activation-0.014
Top resid features:
a
Token a
Feature activation+0.028
Top resid features:
wound
Token wound
Feature activation-0.129
Top resid features:
so
Token so
Feature activation+5.547
Top resid features:
bad
Token bad
Feature activation+0.040
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
prompted
Token prompted
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.005
Top resid features:
have
Token have
Feature activation-0.020
Top resid features:
a
Token a
Feature activation+0.031
Top resid features:
term
Token term
Feature activation-0.031
Top resid features:
so
Token so
Feature activation+5.293
Top resid features:
am
Token am
Feature activation+0.075
Top resid features:
orph
Tokenorph
Feature activation-0.015
Top resid features:
ous
Tokenous
Feature activation-0.081
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
fish
Token fish
Feature activation-0.019
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation-0.120
Top resid features:
a
Tokena
Feature activation+0.074
Top resid features:
vow
Token vow
Feature activation-0.188
Top resid features:
so
Token so
Feature activation+5.337
Top resid features:
sw
Token sw
Feature activation-0.087
Top resid features:
agger
Tokenagger
Feature activation+0.145
Top resid features:
ing
Tokening
Feature activation+0.114
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.077
Top resid features:
confusing
Token confusing
Feature activation+0.045
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.014
Top resid features:
paperwork
Token paperwork
Feature activation-0.406
Top resid features:
so
Token so
Feature activation+5.459
Top resid features:
ardu
Token ardu
Feature activation+0.081
Top resid features:
ous
Tokenous
Feature activation+0.008
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
often
Token often
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
entire
Token entire
Feature activation-0.008
Top resid features:
dog
Token dog
Feature activation-0.035
Top resid features:
meat
Token meat
Feature activation-0.069
Top resid features:
trade
Token trade
Feature activation-0.191
Top resid features:
so
Token so
Feature activation+5.510
Top resid features:
grotesque
Token grotesque
Feature activation+0.009
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
dogs
Token dogs
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
Doctor
Token Doctor
Feature activation-0.008
Top resid features:
Who
Token Who
Feature activation-0.004
Top resid features:
âĦ¢
TokenâĦ¢
Feature activation-0.028
Top resid features:
was
Token was
Feature activation-0.087
Top resid features:
greeted
Token greeted
Feature activation-0.193
Top resid features:
so
Token so
Feature activation+5.536
Top resid features:
rapt
Token rapt
Feature activation+0.074
Top resid features:
ur
Tokenur
Feature activation+0.000
Top resid features:
ously
Tokenously
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
t
Tokent
Feature activation+0.009
Top resid features:
serving
Token serving
Feature activation-0.027
Top resid features:
her
Token her
Feature activation-0.072
Top resid features:
interests
Token interests
Feature activation-0.034
Top resid features:
so
Token so
Feature activation+5.207
Top resid features:
much
Token much
Feature activation-0.013
Top resid features:
as
Token as
Feature activation+0.045
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
u
Tokenu
Feature activation+0.004
Top resid features:
and
Token and
Feature activation-0.022
Top resid features:
Mah
Token Mah
Feature activation-0.021
Top resid features:
ali
Tokenali
Feature activation-0.008
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.380
Top resid features:
so
Token so
Feature activation+5.422
Top resid features:
agitated
Token agitated
Feature activation-0.028
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
them
Token them
Feature activation+0.000
Top resid features:
Doctor
Token Doctor
Feature activation-0.005
Top resid features:
Who
Token Who
Feature activation+0.003
Top resid features:
âĦ¢
TokenâĦ¢
Feature activation-0.039
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
greeted
Token greeted
Feature activation-0.154
Top resid features:
so
Token so
Feature activation+4.921
Top resid features:
rapt
Token rapt
Feature activation+0.284
Top resid features:
ur
Tokenur
Feature activation-0.003
Top resid features:
ously
Tokenously
Feature activation+0.043
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.024
Top resid features:
All
TokenAll
Feature activation+0.019
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
left
Token left
Feature activation-0.138
Top resid features:
me
Token me
Feature activation-0.113
Top resid features:
so
Token so
Feature activation+5.476
Top resid features:
sed
Token sed
Feature activation-0.181
Top resid features:
ated
Tokenated
Feature activation+0.076
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
sensitive
Token sensitive
Feature activation-0.006
Top resid features:
topic
Token topic
Feature activation-0.007
Top resid features:
put
Token put
Feature activation-0.157
Top resid features:
together
Token together
Feature activation-0.103
Top resid features:
so
Token so
Feature activation+5.026
Top resid features:
quickly
Token quickly
Feature activation+0.095
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.007
Top resid features:
other
Token other
Feature activation-0.005
Top resid features:
officers
Token officers
Feature activation-0.015
Top resid features:
beat
Token beat
Feature activation-0.033
Top resid features:
plaintiff
Token plaintiff
Feature activation-0.203
Top resid features:
so
Token so
Feature activation+4.798
Top resid features:
vicious
Token vicious
Feature activation+0.233
Top resid features:
ly
Tokenly
Feature activation+0.056
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
rupt
Token rupt
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
Goddard
Token Goddard
Feature activation-0.030
Top resid features:
kept
Token kept
Feature activation+0.005
Top resid features:
this
Token this
Feature activation-0.084
Top resid features:
thing
Token thing
Feature activation-0.026
Top resid features:
so
Token so
Feature activation+4.957
Top resid features:
close
Token close
Feature activation+0.102
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
vest
Token vest
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
games
Token games
Feature activation-0.022
Top resid features:
.
Token.
Feature activation-0.027
Top resid features:
With
Token With
Feature activation+0.092
Top resid features:
preparation
Token preparation
Feature activation-0.041
Top resid features:
time
Token time
Feature activation-0.157
Top resid features:
so
Token so
Feature activation+4.948
Top resid features:
short
Token short
Feature activation+0.054
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
mid
Token mid
Feature activation+0.000
Top resid features:
inside
Token inside
Feature activation+0.010
Top resid features:
out
Tokenout
Feature activation+0.007
Top resid features:
172
Token172
Feature activation-0.014
Top resid features:
,
Token,
Feature activation-0.037
Top resid features:
went
Token went
Feature activation-0.149
Top resid features:
so
Token so
Feature activation+4.988
Top resid features:
far
Token far
Feature activation-0.097
Top resid features:
above
Token above
Feature activation+0.012
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
beyond
Token beyond
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
really
Token really
Feature activation+0.012
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
"
Token "
Feature activation-0.033
Top resid features:
strike
Tokenstrike
Feature activation-0.013
Top resid features:
"
Token"
Feature activation-0.048
Top resid features:
so
Token so
Feature activation+4.926
Top resid features:
much
Token much
Feature activation+0.017
Top resid features:
as
Token as
Feature activation-0.072
Top resid features:
taking
Token taking
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
hour
Token hour
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.016
Top resid features:
would
Token would
Feature activation-0.001
Top resid features:
be
Token be
Feature activation+0.018
Top resid features:
an
Token an
Feature activation-0.032
Top resid features:
abuse
Token abuse
Feature activation-0.288
Top resid features:
so
Token so
Feature activation+4.887
Top resid features:
great
Token great
Feature activation-0.005
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
could
Token could
Feature activation+0.000
Top resid features:
dressing
Token dressing
Feature activation-0.011
Top resid features:
that
Token that
Feature activation+0.013
Top resid features:
makes
Token makes
Feature activation-0.045
Top resid features:
this
Token this
Feature activation-0.049
Top resid features:
salad
Token salad
Feature activation-0.159
Top resid features:
so
Token so
Feature activation+4.963
Top resid features:
sensational
Token sensational
Feature activation-0.044
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:
When
TokenWhen
Feature activation+0.000
Top resid features:
lose
Token lose
Feature activation-0.086
Top resid features:
on
Token on
Feature activation+0.006
Top resid features:
their
Token their
Feature activation-0.041
Top resid features:
own
Token own
Feature activation-0.043
Top resid features:
terms
Token terms
Feature activation-0.097
Top resid features:
so
Token so
Feature activation+4.650
Top resid features:
badly
Token badly
Feature activation+0.086
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
pure
Token pure
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.030
Top resid features:
everyone
Token everyone
Feature activation-0.004
Top resid features:
had
Token had
Feature activation-0.029
Top resid features:
been
Token been
Feature activation-0.014
Top resid features:
sick
Token sick
Feature activation-0.196
Top resid features:
so
Token so
Feature activation+4.777
Top resid features:
violently
Token violently
Feature activation+0.032
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
lake
Token lake
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.05

Head 2: 0.49

Head 3: 0.03

Head 4: 0.01

Head 5: 0.03

Head 6: 0.06

Head 7: 0.06

Head 8: 0.06

Head 9: 0.04

Head 10: 0.07

Head 11: 0.07

Positive logits

ymm1.45

atically1.21

insofar1.19

lately1.18

hetic1.18

ás1.14

tomat1.14

ocating1.10

gripped1.09

exceeds1.08

ially1.06

igor1.05

unfairly1.05

worldly1.03

ointed1.02

eg1.01

rocked1.00

javascript0.99

ingly0.99

odynam0.98

Negative logits

wick-1.20

hower-1.11

VA-1.05

PA-1.02

Pope-1.02

Pa-1.00

burg-1.00

IDF-0.99

())-0.97

IL-0.96

Pa-0.95

baum-0.95

Pump-0.95

silhouette-0.94

vised-0.91

pill-0.91

nonex-0.91

iler-0.91

population-0.91

column-0.90

INTERVAL 4.294 - 4.772
CONTAINS 0.001%

and
Token and
Feature activation+0.000
Mah
Token Mah
Feature activation+0.000
ali
Tokenali
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
so
Token so
Feature activation+0.000
agitated
Token agitated
Feature activation+4.448
that
Token that
Feature activation+0.178
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
charged
Token charged
Feature activation+0.000
entire
Token entire
Feature activation+0.000
dog
Token dog
Feature activation+0.000
meat
Token meat
Feature activation+0.000
trade
Token trade
Feature activation+0.000
so
Token so
Feature activation+0.000
grotesque
Token grotesque
Feature activation+4.591
is
Token is
Feature activation+2.817
that
Token that
Feature activation+0.000
dogs
Token dogs
Feature activation+0.000
are
Token are
Feature activation+0.000
purposely
Token purposely
Feature activation+0.000
blood
Token blood
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
wound
Token wound
Feature activation+0.000
so
Token so
Feature activation+0.063
bad
Token bad
Feature activation+4.772
that
Token that
Feature activation+1.719
it
Token it
Feature activation+0.000
prompted
Token prompted
Feature activation+0.000
a
Token a
Feature activation+0.000
captain
Token captain
Feature activation+0.000
sensitive
Token sensitive
Feature activation+0.000
topic
Token topic
Feature activation+0.000
put
Token put
Feature activation+0.000
together
Token together
Feature activation+0.000
so
Token so
Feature activation+0.000
quickly
Token quickly
Feature activation+4.317
,
Token,
Feature activation+1.926
there
Token there
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
some
Token some
Feature activation+0.000
a
Token a
Feature activation+0.000
term
Token term
Feature activation+0.000
so
Token so
Feature activation+0.000
am
Token am
Feature activation+3.270
orph
Tokenorph
Feature activation+0.000
ous
Tokenous
Feature activation+4.686
that
Token that
Feature activation+1.153
it
Token it
Feature activation+0.000
can
Token can
Feature activation+0.000
cover
Token cover
Feature activation+0.000
any
Token any
Feature activation+0.000

INTERVAL 3.817 - 4.294
CONTAINS 0.002%

are
Token are
Feature activation+0.000
right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
so
Token so
Feature activation+0.000
disenfranch
Token disenfranch
Feature activation+2.398
ised
Tokenised
Feature activation+3.890
,
Token,
Feature activation+2.875
and
Token and
Feature activation+0.415
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
being
Token being
Feature activation+0.000
never
Token never
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
so
Token so
Feature activation+0.000
wide
Token wide
Feature activation+3.834
a
Token a
Feature activation+3.900
lead
Token lead
Feature activation+0.000
vis
Token vis
Feature activation+0.000
-
Token-
Feature activation+0.000
a
Tokena
Feature activation+0.000
-
Token-
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
sick
Token sick
Feature activation+0.000
so
Token so
Feature activation+0.000
violently
Token violently
Feature activation+4.008
it
Token it
Feature activation+1.143
was
Token was
Feature activation+0.381
a
Token a
Feature activation+0.372
lake
Token lake
Feature activation+0.051
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
makes
Token makes
Feature activation+0.000
this
Token this
Feature activation+0.000
salad
Token salad
Feature activation+0.000
so
Token so
Feature activation+0.000
sensational
Token sensational
Feature activation+4.023
.
Token.
Feature activation+0.501
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
it
Token it
Feature activation+0.000
172
Token172
Feature activation+0.000
,
Token,
Feature activation+0.000
went
Token went
Feature activation+0.000
so
Token so
Feature activation+0.000
far
Token far
Feature activation+1.964
above
Token above
Feature activation+4.119
and
Token and
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
that
Token that
Feature activation+0.000
my
Token my
Feature activation+0.000
mind
Token mind
Feature activation+0.000

INTERVAL 3.340 - 3.817
CONTAINS 0.006%

,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
so
Token so
Feature activation+0.000
focused
Token focused
Feature activation+3.431
on
Token on
Feature activation+0.528
the
Token the
Feature activation+0.000
extraction
Token extraction
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
choice
Token choice
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
with
Token with
Feature activation+0.000
so
Token so
Feature activation+0.000
many
Token many
Feature activation+3.612
enchant
Token enchant
Feature activation+1.436
ments
Tokenments
Feature activation+1.119
,
Token,
Feature activation+0.569
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
pol
Token pol
Feature activation+0.000
ishes
Tokenishes
Feature activation+0.000
are
Token are
Feature activation+0.000
both
Token both
Feature activation+0.000
so
Token so
Feature activation+0.000
intense
Token intense
Feature activation+3.574
and
Token and
Feature activation+1.806
complex
Token complex
Feature activation+2.164
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Jim
Token Jim
Feature activation+0.000
's
Token's
Feature activation+0.000
life
Token life
Feature activation+0.000
represents
Token represents
Feature activation+0.000
so
Token so
Feature activation+0.000
well
Token well
Feature activation+3.503
:
Token:
Feature activation+0.000
America
Token America
Feature activation+0.000
's
Token's
Feature activation+0.000
un
Token un
Feature activation+0.000
break
Tokenbreak
Feature activation+0.000
the
Token the
Feature activation+0.000
Rudd
Token Rudd
Feature activation+0.000
cabinet
Token cabinet
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
sub
Token sub
Feature activation+3.473
missive
Tokenmissive
Feature activation+3.891
to
Token to
Feature activation+0.577
Mr
Token Mr
Feature activation+0.000
Rudd
Token Rudd
Feature activation+0.000
's
Token's
Feature activation+0.000

INTERVAL 2.863 - 3.340
CONTAINS 0.009%

"
Token"
Feature activation+0.000
These
TokenThese
Feature activation+0.000
teachers
Token teachers
Feature activation+0.000
were
Token were
Feature activation+0.000
so
Token so
Feature activation+0.000
accustomed
Token accustomed
Feature activation+2.949
to
Token to
Feature activation+1.873
Windows
Token Windows
Feature activation+0.000
that
Token that
Feature activation+0.000
any
Token any
Feature activation+0.000
change
Token change
Feature activation+0.000
confusing
Token confusing
Feature activation+3.164
,
Token,
Feature activation+2.584
the
Token the
Feature activation+0.000
paperwork
Token paperwork
Feature activation+0.000
so
Token so
Feature activation+1.707
ardu
Token ardu
Feature activation+3.311
ous
Tokenous
Feature activation+4.595
for
Token for
Feature activation+1.748
often
Token often
Feature activation+0.000
-
Token-
Feature activation+0.000
over
Tokenover
Feature activation+0.000
The
Token The
Feature activation+0.000
passing
Token passing
Feature activation+0.000
term
Token term
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
problematic
Token problematic
Feature activation+3.054
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
painfully
Token painfully
Feature activation+2.964
obvious
Token obvious
Feature activation+3.189
that
Token that
Feature activation+0.098
these
Token these
Feature activation+0.000
two
Token two
Feature activation+0.000
men
Token men
Feature activation+0.000
even
Token even
Feature activation+0.000
after
Token after
Feature activation+0.000
executing
Token executing
Feature activation+0.000
everything
Token everything
Feature activation+0.000
so
Token so
Feature activation+0.000
perfectly
Token perfectly
Feature activation+3.106
,
Token,
Feature activation+2.377
Detroit
Token Detroit
Feature activation+0.000
had
Token had
Feature activation+0.000
only
Token only
Feature activation+0.000
2
Token 2
Feature activation+0.000

INTERVAL 2.386 - 2.863
CONTAINS 0.012%

operation
Token operation
Feature activation+0.000
was
Token was
Feature activation+0.000
running
Token running
Feature activation+0.000
so
Token so
Feature activation+0.000
poorly
Token poorly
Feature activation+3.717
,
Token,
Feature activation+2.658
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
all
Tokenall
Feature activation+0.000
hands
Token hands
Feature activation+0.000
on
Token on
Feature activation+0.000
each
Token each
Feature activation+0.000
section
Token section
Feature activation+0.000
to
Token to
Feature activation+0.000
memory
Token memory
Feature activation+0.000
so
Token so
Feature activation+0.000
virtual
Token virtual
Feature activation+2.499
addresses
Token addresses
Feature activation+0.000
in
Token in
Feature activation+0.343
the
Token the
Feature activation+0.000
binary
Token binary
Feature activation+0.000
match
Token match
Feature activation+0.000
but
Token but
Feature activation+0.000
poison
Token poison
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+1.325
more
Token more
Feature activation+2.408
civilized
Token civilized
Feature activation+0.313
.
Token.
Feature activation+0.131
I
Token I
Feature activation+0.000
know
Token know
Feature activation+0.000
Gand
Token Gand
Feature activation+0.000
been
Token been
Feature activation+0.000
so
Token so
Feature activation+0.000
brazen
Token brazen
Feature activation+2.751
and
Token and
Feature activation+1.322
so
Token so
Feature activation+0.525
un
Token un
Feature activation+2.737
mind
Tokenmind
Feature activation+0.918
ful
Tokenful
Feature activation+3.171
of
Token of
Feature activation+1.663
the
Token the
Feature activation+0.000
constitutional
Token constitutional
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+1.528
better
Token better
Feature activation+2.545
that
Token that
Feature activation+0.000
people
Token people
Feature activation+0.000
have
Token have
Feature activation+0.000
meaningful
Token meaningful
Feature activation+0.000
access
Token access
Feature activation+0.000

INTERVAL 1.909 - 2.386
CONTAINS 0.013%

.
Token.
Feature activation+0.000
My
Token My
Feature activation+0.000
dad
Token dad
Feature activation+0.000
was
Token was
Feature activation+0.000
so
Token so
Feature activation+0.000
capt
Token capt
Feature activation+2.374
ivated
Tokenivated
Feature activation+3.431
that
Token that
Feature activation+0.849
he
Token he
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Stoke
Token Stoke
Feature activation+0.000
City
Token City
Feature activation+0.000
and
Token and
Feature activation+0.000
did
Token did
Feature activation+0.000
so
Token so
Feature activation+0.000
markedly
Token markedly
Feature activation+1.988
at
Token at
Feature activation+0.079
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
last
Token last
Feature activation+0.000
ed
Tokened
Feature activation+0.000
group
Token group
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
so
Token so
Feature activation+0.000
are
Token are
Feature activation+2.239
the
Token the
Feature activation+0.000
female
Token female
Feature activation+0.000
medieval
Token medieval
Feature activation+0.000
cos
Token cos
Feature activation+0.000
m
Tokenm
Feature activation+0.000
are
Token are
Feature activation+0.000
both
Token both
Feature activation+0.000
so
Token so
Feature activation+0.000
intense
Token intense
Feature activation+3.574
and
Token and
Feature activation+1.806
complex
Token complex
Feature activation+2.164
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Gir
Token Gir
Feature activation+0.000
speakers
Token speakers
Feature activation+0.000
talk
Token talk
Feature activation+0.000
politics
Token politics
Feature activation+0.000
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
,
Token,
Feature activation+2.208
with
Token with
Feature activation+0.000
economist
Token economist
Feature activation+0.000
Glenn
Token Glenn
Feature activation+0.000
Hubbard
Token Hubbard
Feature activation+0.000
at
Token at
Feature activation+0.000

INTERVAL 1.431 - 1.909
CONTAINS 0.014%

be
Token be
Feature activation+0.000
exceptionally
Token exceptionally
Feature activation+0.000
boring
Token boring
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
imagine
Token imagine
Feature activation+1.616
my
Token my
Feature activation+0.000
excitement
Token excitement
Feature activation+0.000
when
Token when
Feature activation+0.000
I
Token I
Feature activation+0.000
get
Token get
Feature activation+0.000
that
Token that
Feature activation+0.000
appears
Token appears
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
so
Token so
Feature activation+0.000
start
Token start
Feature activation+1.557
the
Token the
Feature activation+0.000
conversation
Token conversation
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
positive
Token positive
Feature activation+0.000
because
Token because
Feature activation+0.000
bananas
Token bananas
Feature activation+0.000
spoiled
Token spoiled
Feature activation+0.000
so
Token so
Feature activation+0.000
quickly
Token quickly
Feature activation+3.081
,
Token,
Feature activation+1.677
trans
Token trans
Feature activation+0.000
por
Tokenpor
Feature activation+0.000
ters
Tokenters
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
piv
Token piv
Feature activation+0.000
oted
Tokenoted
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
so
Token so
Feature activation+0.000
it
Token it
Feature activation+1.679
will
Token will
Feature activation+0.196
be
Token be
Feature activation+0.000
interesting
Token interesting
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
-
Token-
Feature activation+0.000
tested
Tokentested
Feature activation+0.000
welfare
Token welfare
Feature activation+0.000
programs
Token programs
Feature activation+0.000
so
Token so
Feature activation+0.000
as
Token as
Feature activation+1.598
to
Token to
Feature activation+0.000
ass
Token ass
Feature activation+0.000
u
Tokenu
Feature activation+0.000
age
Tokenage
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000

INTERVAL 0.954 - 1.431
CONTAINS 0.018%

:
Token:
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
having
Token having
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+1.411
goddamn
Token goddamn
Feature activation+0.000
fun
Token fun
Feature activation+0.552
,
Token,
Feature activation+0.312
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Token and
Feature activation+0.000
so
Token so
Feature activation+0.000
ot
Tokenot
Feature activation+0.418
-
Token-
Feature activation+0.163
forming
Tokenforming
Feature activation+1.099
pollution
Token pollution
Feature activation+0.000
.
Token.
Feature activation+0.000
Still
Token Still
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
-
Token-
Feature activation+0.000
received
Tokenreceived
Feature activation+0.000
silver
Token silver
Feature activation+0.000
screen
Token screen
Feature activation+0.000
so
Token so
Feature activation+0.000
ire
Tokenire
Feature activation+1.348
es
Tokenes
Feature activation+1.023
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
apply
Token apply
Feature activation+0.000
.
Token.
Feature activation+0.000
Oy
Token Oy
Feature activation+0.000
ster
Tokenster
Feature activation+0.000
cards
Token cards
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+2.062
,
Token,
Feature activation+1.341
he
Token he
Feature activation+0.000
showed
Token showed
Feature activation+0.000
a
Token a
Feature activation+0.000
couple
Token couple
Feature activation+0.000
of
Token of
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
toe
Token toe
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
the
Token the
Feature activation+1.191
talent
Token talent
Feature activation+0.000
is
Token is
Feature activation+0.000
certainly
Token certainly
Feature activation+0.000
in
Token in
Feature activation+0.000
place
Token place
Feature activation+0.000

INTERVAL 0.477 - 0.954
CONTAINS 0.026%

nuclear
Token nuclear
Feature activation+0.000
imaging
Token imaging
Feature activation+0.000
technology
Token technology
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
so
Tokenso
Feature activation+0.000
-
Token-
Feature activation+0.828
called
Tokencalled
Feature activation+1.017
SP
Token SP
Feature activation+0.000
ECT
TokenECT
Feature activation+0.000
scans
Token scans
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+1.558
Ċ
TokenĊ
Feature activation+0.000
Imp
TokenImp
Feature activation+0.000
ressed
Tokenressed
Feature activation+0.000
?
Token?
Feature activation+0.000
So
Token So
Feature activation+0.000
how
Token how
Feature activation+0.504
about
Token about
Feature activation+0.000
staying
Token staying
Feature activation+0.000
behind
Token behind
Feature activation+0.000
such
Token such
Feature activation+0.000
tech
Token tech
Feature activation+0.037
dealing
Token dealing
Feature activation+0.000
with
Token with
Feature activation+0.000
supermarkets
Token supermarkets
Feature activation+0.000
for
Token for
Feature activation+0.000
so
Token so
Feature activation+0.000
long
Token long
Feature activation+0.887
I
Token I
Feature activation+0.000
kept
Token kept
Feature activation+0.000
waiting
Token waiting
Feature activation+0.000
for
Token for
Feature activation+0.000
them
Token them
Feature activation+0.000
also
Token also
Feature activation+0.000
a
Token a
Feature activation+0.000
not
Token not
Feature activation+0.000
-
Token-
Feature activation+0.000
so
Tokenso
Feature activation+0.000
-
Token-
Feature activation+0.801
sub
Tokensub
Feature activation+1.510
tle
Tokentle
Feature activation+0.000
way
Token way
Feature activation+0.000
of
Token of
Feature activation+0.000
MJ
Token MJ
Feature activation+0.000
its
Token its
Feature activation+0.000
regulatory
Token regulatory
Feature activation+0.000
oversight
Token oversight
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
does
Token does
Feature activation+0.901
that
Token that
Feature activation+0.000
make
Token make
Feature activation+0.000
me
Token me
Feature activation+0.000
a
Token a
Feature activation+0.000
controlled
Token controlled
Feature activation+0.000

INTERVAL 0.000 - 0.477
CONTAINS 99.899%

Ċ
TokenĊ
Feature activation+0.000
Person
TokenPerson
Feature activation+0.000
ality
Tokenality
Feature activation+0.000
:
Token:
Feature activation+0.000
Lord
Token Lord
Feature activation+0.000
worked
Token worked
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
Y
Token Y
Feature activation+0.000
M
TokenM
Feature activation+0.000
CA
TokenCA
Feature activation+0.000
tyranny
Token tyranny
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
dollar
Token dollar
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
trade
Token trade
Feature activation+0.000
and
Token and
Feature activation+0.000
finance
Token finance
Feature activation+0.000
JSON
Token JSON
Feature activation+0.000
Sche
Token Sche
Feature activation+0.000
ma
Tokenma
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Overview
TokenOverview
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Features
TokenFeatures
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
os
Tokenos
Feature activation+0.000
30
Token 30
Feature activation+0.000
D
Token D
Feature activation+0.000
C
Token C
Feature activation+0.000
,
Token,
Feature activation+0.000
DM
Token DM
Feature activation+0.000
BRA
Token BRA
Feature activation+0.000
0
Token 0
Feature activation+0.000
As
Token As
Feature activation+0.000
at
Tokenat
Feature activation+0.000
iani
Tokeniani
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
child
Token child
Feature activation+0.000
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000
carry
Token carry
Feature activation+0.000
buckets
Token buckets
Feature activation+0.000
of
Token of
Feature activation+0.000
water
Token water
Feature activation+0.000
to
Token to
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 1 in H3.2: (feature 883)

TOP ACTIVATIONS
MAX = 3.136

Kay
Token Kay
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
One
TokenOne
Feature activation+0.000
of
Token of
Feature activation+0.000
Spain
Token Spain
Feature activation+0.000
's
Token's
Feature activation+3.136
most
Token most
Feature activation+2.281
high
Token high
Feature activation+0.268
-
Token-
Feature activation+0.000
profile
Tokenprofile
Feature activation+0.932
finan
Token finan
Feature activation+1.255
VA
TokenVA
Feature activation+0.000
Street
Token Street
Feature activation+0.000
Art
Token Art
Feature activation+0.273
Fest
Token Fest
Feature activation+1.580
Organ
Token Organ
Feature activation+0.072
izers
Tokenizers
Feature activation+3.103
)
Token)
Feature activation+0.491
met
Token met
Feature activation+0.000
with
Token with
Feature activation+0.000
News
Token News
Feature activation+0.000
om
Tokenom
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
P
Token P
Feature activation+0.051
ORT
TokenORT
Feature activation+0.000
AL
TokenAL
Feature activation+0.000
's
Token's
Feature activation+2.878
creators
Token creators
Feature activation+2.400
,
Token,
Feature activation+1.200
says
Token says
Feature activation+0.000
they
Token they
Feature activation+0.000
've
Token've
Feature activation+0.000
high
Token high
Feature activation+0.268
-
Token-
Feature activation+0.000
profile
Tokenprofile
Feature activation+0.932
finan
Token finan
Feature activation+1.255
ci
Tokenci
Feature activation+0.313
ers
Tokeners
Feature activation+2.788
,
Token,
Feature activation+1.322
Rodrigo
Token Rodrigo
Feature activation+0.000
R
Token R
Feature activation+0.000
ato
Tokenato
Feature activation+0.000
,
Token,
Feature activation+0.000
accidentally
Token accidentally
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Slim
Token Slim
Feature activation+0.000
's
Token's
Feature activation+2.785
spiked
Token spiked
Feature activation+1.429
sod
Token sod
Feature activation+0.921
as
Tokenas
Feature activation+2.377
,
Token,
Feature activation+1.545
unwittingly
Token unwittingly
Feature activation+0.000
10
Token10
Feature activation+0.000
]
Token]
Feature activation+0.000
One
Token One
Feature activation+0.000
of
Token of
Feature activation+0.000
Coleman
Token Coleman
Feature activation+0.000
's
Token's
Feature activation+2.778
photo
Token photo
Feature activation+1.025
shoots
Token shoots
Feature activation+1.449
with
Token with
Feature activation+0.231
Schwarzenegger
Token Schwarzenegger
Feature activation+0.000
featured
Token featured
Feature activation+0.000
.),
Token.),
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
bill
Token bill
Feature activation+1.476
's
Token's
Feature activation+2.774
sponsors
Token sponsors
Feature activation+2.716
,
Token,
Feature activation+0.846
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
bill
Token bill
Feature activation+1.476
's
Token's
Feature activation+2.774
sponsors
Token sponsors
Feature activation+2.716
,
Token,
Feature activation+0.846
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
interview
Token interview
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Scottish
Token Scottish
Feature activation+0.188
National
Token National
Feature activation+0.128
party
Token party
Feature activation+0.751
's
Token's
Feature activation+2.552
core
Token core
Feature activation+1.621
areas
Token areas
Feature activation+1.184
of
Token of
Feature activation+0.000
support
Token support
Feature activation+0.000
is
Token is
Feature activation+0.000
Gl
Token Gl
Feature activation+0.000
itter
Tokenitter
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.526
organizers
Token organizers
Feature activation+2.468
,
Token,
Feature activation+0.000
told
Token told
Feature activation+0.000
press
Token press
Feature activation+0.000
assembled
Token assembled
Feature activation+0.000
outside
Token outside
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Airbus
Token Airbus
Feature activation+1.264
pilots
Token pilots
Feature activation+2.449
was
Token was
Feature activation+1.204
the
Token the
Feature activation+0.000
CEO
Token CEO
Feature activation+0.000
of
Token of
Feature activation+0.000
Airbus
Token Airbus
Feature activation+0.000
that
Token that
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.231
's
Token's
Feature activation+2.430
most
Token most
Feature activation+2.072
cherished
Token cherished
Feature activation+0.902
historic
Token historic
Feature activation+0.245
monuments
Token monuments
Feature activation+0.933
was
Token was
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
One
TokenOne
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
suspects
Token suspects
Feature activation+0.616
named
Token named
Feature activation+2.430
by
Token by
Feature activation+0.202
authorities
Token authorities
Feature activation+0.000
could
Token could
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.000
of
Token of
Feature activation+0.000
P
Token P
Feature activation+0.051
ORT
TokenORT
Feature activation+0.000
AL
TokenAL
Feature activation+0.000
's
Token's
Feature activation+2.878
creators
Token creators
Feature activation+2.400
,
Token,
Feature activation+1.200
says
Token says
Feature activation+0.000
they
Token they
Feature activation+0.000
've
Token've
Feature activation+0.000
carefully
Token carefully
Feature activation+0.000
of
Token of
Feature activation+0.000
Slim
Token Slim
Feature activation+0.000
's
Token's
Feature activation+2.785
spiked
Token spiked
Feature activation+1.429
sod
Token sod
Feature activation+0.921
as
Tokenas
Feature activation+2.377
,
Token,
Feature activation+1.545
unwittingly
Token unwittingly
Feature activation+0.000
ingest
Token ingest
Feature activation+0.000
ing
Tokening
Feature activation+0.000
his
Token his
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Ur
Token Ur
Feature activation+0.000
b
Tokenb
Feature activation+0.000
ana
Tokenana
Feature activation+0.050
's
Token's
Feature activation+2.367
23
Token 23
Feature activation+1.845
precincts
Token precincts
Feature activation+1.958
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
all
Token all
Feature activation+0.000
water
Token water
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
America
Token America
Feature activation+0.000
's
Token's
Feature activation+2.359
most
Token most
Feature activation+2.016
be
Token be
Feature activation+0.090
league
Tokenleague
Feature activation+0.000
red
Tokenred
Feature activation+0.571
cities
Token cities
Feature activation+0.785
seeing
Token seeing
Feature activation+0.000
that
Token that
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
my
Token my
Feature activation+0.000
favorite
Token favorite
Feature activation+2.340
childhood
Token childhood
Feature activation+0.823
idols
Token idols
Feature activation+1.727
quite
Token quite
Feature activation+0.000
possibly
Token possibly
Feature activation+0.000
used
Token used
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
One
TokenOne
Feature activation+0.000
of
Token of
Feature activation+0.000
Spain
Token Spain
Feature activation+0.000
's
Token's
Feature activation+3.136
most
Token most
Feature activation+2.281
high
Token high
Feature activation+0.268
-
Token-
Feature activation+0.000
profile
Tokenprofile
Feature activation+0.932
finan
Token finan
Feature activation+1.255
ci
Tokenci
Feature activation+0.313
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+2.267
most
Token most
Feature activation+1.862
str
Token str
Feature activation+0.025
ident
Tokenident
Feature activation+0.176
atheists
Token atheists
Feature activation+1.376
commun
Token commun
Feature activation+0.059

Top DFA by src position
MAX = 3.969

-
Token-
Feature activation-0.003
Top resid features:
Stanley
Token Stanley
Feature activation+0.000
Top resid features:
Kay
Token Kay
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.081
Top resid features:
One
TokenOne
Feature activation-0.184
Top resid features:
of
Token of
Feature activation+3.693
Top resid features:
Spain
Token Spain
Feature activation+0.144
Top resid features:
's
Token's
Feature activation+0.017
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
high
Token high
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
Ed
Token Ed
Feature activation+0.010
Top resid features:
Tr
Token Tr
Feature activation+0.000
Top resid features:
ask
Tokenask
Feature activation+0.005
Top resid features:
(
Token (
Feature activation+0.118
Top resid features:
one
Tokenone
Feature activation-0.096
Top resid features:
of
Token of
Feature activation+3.550
Top resid features:
R
Token R
Feature activation+0.000
Top resid features:
VA
TokenVA
Feature activation+0.041
Top resid features:
Street
Token Street
Feature activation+0.063
Top resid features:
Art
Token Art
Feature activation-0.040
Top resid features:
Fest
Token Fest
Feature activation-0.044
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
security
Token security
Feature activation-0.007
Top resid features:
consultant
Token consultant
Feature activation+0.021
Top resid features:
and
Token and
Feature activation+0.023
Top resid features:
one
Token one
Feature activation-0.210
Top resid features:
of
Token of
Feature activation+3.597
Top resid features:
P
Token P
Feature activation-0.087
Top resid features:
ORT
TokenORT
Feature activation-0.039
Top resid features:
AL
TokenAL
Feature activation+0.067
Top resid features:
's
Token's
Feature activation-0.015
Top resid features:
creators
Token creators
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
Stanley
Token Stanley
Feature activation-0.003
Top resid features:
Kay
Token Kay
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.048
Top resid features:
One
TokenOne
Feature activation-0.931
Top resid features:
of
Token of
Feature activation+3.877
Top resid features:
Spain
Token Spain
Feature activation+0.123
Top resid features:
's
Token's
Feature activation+0.102
Top resid features:
most
Token most
Feature activation-0.141
Top resid features:
high
Token high
Feature activation+0.028
Top resid features:
-
Token-
Feature activation-0.008
Top resid features:
I
Token I
Feature activation+0.029
Top resid features:
drank
Token drank
Feature activation-0.006
Top resid features:
accidentally
Token accidentally
Feature activation+0.022
Top resid features:
from
Token from
Feature activation+0.025
Top resid features:
one
Token one
Feature activation-0.203
Top resid features:
of
Token of
Feature activation+3.483
Top resid features:
Slim
Token Slim
Feature activation-0.090
Top resid features:
's
Token's
Feature activation-0.026
Top resid features:
spiked
Token spiked
Feature activation+0.000
Top resid features:
sod
Token sod
Feature activation+0.000
Top resid features:
as
Tokenas
Feature activation+0.000
Top resid features:
lbs
Token lbs
Feature activation+0.001
Top resid features:
).[
Token).[
Feature activation+0.010
Top resid features:
10
Token10
Feature activation-0.001
Top resid features:
]
Token]
Feature activation+0.022
Top resid features:
One
Token One
Feature activation-0.133
Top resid features:
of
Token of
Feature activation+3.412
Top resid features:
Coleman
Token Coleman
Feature activation-0.013
Top resid features:
's
Token's
Feature activation+0.011
Top resid features:
photo
Token photo
Feature activation+0.000
Top resid features:
shoots
Token shoots
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
D
TokenD
Feature activation+0.002
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
Va
TokenVa
Feature activation-0.001
Top resid features:
.),
Token.),
Feature activation+0.064
Top resid features:
one
Token one
Feature activation-0.179
Top resid features:
of
Token of
Feature activation+2.332
Top resid features:
the
Token the
Feature activation+0.851
Top resid features:
bill
Token bill
Feature activation+0.072
Top resid features:
's
Token's
Feature activation+0.017
Top resid features:
sponsors
Token sponsors
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
D
TokenD
Feature activation+0.008
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
Va
TokenVa
Feature activation-0.001
Top resid features:
.),
Token.),
Feature activation+0.092
Top resid features:
one
Token one
Feature activation-0.688
Top resid features:
of
Token of
Feature activation+2.948
Top resid features:
the
Token the
Feature activation+0.562
Top resid features:
bill
Token bill
Feature activation-0.001
Top resid features:
's
Token's
Feature activation+0.073
Top resid features:
sponsors
Token sponsors
Feature activation+0.034
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
carbon
Tokencarbon
Feature activation-0.000
Top resid features:
vehicles
Token vehicles
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.071
Top resid features:
One
Token One
Feature activation-0.169
Top resid features:
of
Token of
Feature activation+2.637
Top resid features:
the
Token the
Feature activation+0.529
Top resid features:
Scottish
Token Scottish
Feature activation+0.001
Top resid features:
National
Token National
Feature activation-0.024
Top resid features:
party
Token party
Feature activation-0.021
Top resid features:
's
Token's
Feature activation+0.020
Top resid features:
Sarah
Token Sarah
Feature activation+0.022
Top resid features:
Water
Token Water
Feature activation+0.002
Top resid features:
feld
Tokenfeld
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
one
Token one
Feature activation-0.176
Top resid features:
of
Token of
Feature activation+2.896
Top resid features:
Dust
Token Dust
Feature activation+0.016
Top resid features:
to
Token to
Feature activation+0.058
Top resid features:
Gl
Token Gl
Feature activation-0.029
Top resid features:
itter
Tokenitter
Feature activation+0.028
Top resid features:
âĢ
TokenâĢ
Feature activation+0.026
Top resid features:
Helic
Token Helic
Feature activation+0.003
Top resid features:
op
Tokenop
Feature activation-0.001
Top resid features:
ters
Tokenters
Feature activation-0.024
Top resid features:
.
Token.
Feature activation+0.040
Top resid features:
One
Token One
Feature activation-0.736
Top resid features:
of
Token of
Feature activation+2.694
Top resid features:
the
Token the
Feature activation+0.781
Top resid features:
Airbus
Token Airbus
Feature activation+0.126
Top resid features:
pilots
Token pilots
Feature activation+0.023
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
program
Token program
Feature activation-0.005
Top resid features:
's
Token's
Feature activation+0.006
Top resid features:
claims
Token claims
Feature activation+0.016
Top resid features:
that
Token that
Feature activation-0.057
Top resid features:
one
Token one
Feature activation-0.369
Top resid features:
of
Token of
Feature activation+2.595
Top resid features:
the
Token the
Feature activation+0.324
Top resid features:
country
Token country
Feature activation+0.261
Top resid features:
's
Token's
Feature activation+0.080
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
cherished
Token cherished
Feature activation+0.000
Top resid features:
substance
Token substance
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
One
TokenOne
Feature activation-0.346
Top resid features:
of
Token of
Feature activation+2.182
Top resid features:
the
Token the
Feature activation+0.722
Top resid features:
suspects
Token suspects
Feature activation+0.283
Top resid features:
named
Token named
Feature activation+0.001
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
authorities
Token authorities
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.023
Top resid features:
security
Token security
Feature activation+0.027
Top resid features:
consultant
Token consultant
Feature activation-0.012
Top resid features:
and
Token and
Feature activation-0.012
Top resid features:
one
Token one
Feature activation-1.014
Top resid features:
of
Token of
Feature activation+3.969
Top resid features:
P
Token P
Feature activation-0.037
Top resid features:
ORT
TokenORT
Feature activation+0.002
Top resid features:
AL
TokenAL
Feature activation+0.056
Top resid features:
's
Token's
Feature activation-0.052
Top resid features:
creators
Token creators
Feature activation-0.036
Top resid features:
I
Token I
Feature activation+0.016
Top resid features:
drank
Token drank
Feature activation+0.008
Top resid features:
accidentally
Token accidentally
Feature activation+0.013
Top resid features:
from
Token from
Feature activation+0.039
Top resid features:
one
Token one
Feature activation-0.234
Top resid features:
of
Token of
Feature activation+2.722
Top resid features:
Slim
Token Slim
Feature activation+0.026
Top resid features:
's
Token's
Feature activation+0.212
Top resid features:
spiked
Token spiked
Feature activation+0.020
Top resid features:
sod
Token sod
Feature activation-0.032
Top resid features:
as
Tokenas
Feature activation-0.002
Top resid features:
were
Token were
Feature activation-0.005
Top resid features:
drawn
Token drawn
Feature activation+0.007
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
every
Token every
Feature activation-0.110
Top resid features:
one
Token one
Feature activation+0.015
Top resid features:
of
Token of
Feature activation+2.899
Top resid features:
Ur
Token Ur
Feature activation+0.036
Top resid features:
b
Tokenb
Feature activation-0.005
Top resid features:
ana
Tokenana
Feature activation+0.046
Top resid features:
's
Token's
Feature activation-0.008
Top resid features:
23
Token 23
Feature activation+0.000
Top resid features:
toxic
Token toxic
Feature activation-0.012
Top resid features:
drinking
Token drinking
Feature activation+0.003
Top resid features:
water
Token water
Feature activation-0.011
Top resid features:
in
Token in
Feature activation-0.013
Top resid features:
one
Token one
Feature activation-0.572
Top resid features:
of
Token of
Feature activation+3.223
Top resid features:
America
Token America
Feature activation+0.175
Top resid features:
's
Token's
Feature activation-0.005
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
league
Tokenleague
Feature activation+0.000
Top resid features:
And
Token And
Feature activation+0.010
Top resid features:
now
Token now
Feature activation-0.006
Top resid features:
seeing
Token seeing
Feature activation+0.016
Top resid features:
that
Token that
Feature activation+0.006
Top resid features:
one
Token one
Feature activation-0.415
Top resid features:
of
Token of
Feature activation+2.732
Top resid features:
my
Token my
Feature activation+0.633
Top resid features:
favorite
Token favorite
Feature activation-0.141
Top resid features:
childhood
Token childhood
Feature activation+0.000
Top resid features:
idols
Token idols
Feature activation+0.000
Top resid features:
quite
Token quite
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
Stanley
Token Stanley
Feature activation-0.004
Top resid features:
Kay
Token Kay
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.017
Top resid features:
One
TokenOne
Feature activation-0.312
Top resid features:
of
Token of
Feature activation+2.651
Top resid features:
Spain
Token Spain
Feature activation+0.298
Top resid features:
's
Token's
Feature activation+0.208
Top resid features:
most
Token most
Feature activation-0.130
Top resid features:
high
Token high
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
light
Token light
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
Yes
Token Yes
Feature activation-0.017
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
one
Token one
Feature activation-0.211
Top resid features:
of
Token of
Feature activation+2.179
Top resid features:
the
Token the
Feature activation+0.702
Top resid features:
world
Token world
Feature activation+0.014
Top resid features:
's
Token's
Feature activation+0.011
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
str
Token str
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.04

Head 2: 0.48

Head 3: 0.02

Head 4: 0.02

Head 5: 0.05

Head 6: 0.07

Head 7: 0.05

Head 8: 0.07

Head 9: 0.04

Head 10: 0.05

Head 11: 0.09

Positive logits

emies1.53

agonists1.43

quir1.39

favourites1.38

favorites1.33

ipal1.27

embr1.25

gars1.24

arters1.21

finalists1.20

��1.20

posters1.19

unique1.18

farious1.17

axies1.16

pioneers1.15

holes1.15

izers1.14

isers1.12

iph1.12

Negative logits

-1.42

..."-1.29

Norn-1.23

ゼウス-1.15

osity-1.14

Tsukuyomi-1.13

Maiden-1.13

Babe-1.12

Hague-1.11

Aging-1.07

livion-1.07

Squirrel-1.07

Courier-1.05

Smy-1.05

"],-1.03

ptroller-1.03

Compass-1.03

Bahamas-1.03

leigh-1.03

Ibid-1.02

INTERVAL 2.822 - 3.136
CONTAINS 0.000%

one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
P
Token P
Feature activation+0.051
ORT
TokenORT
Feature activation+0.000
AL
TokenAL
Feature activation+0.000
's
Token's
Feature activation+2.878
creators
Token creators
Feature activation+2.400
,
Token,
Feature activation+1.200
says
Token says
Feature activation+0.000
they
Token they
Feature activation+0.000
've
Token've
Feature activation+0.000
Kay
Token Kay
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
One
TokenOne
Feature activation+0.000
of
Token of
Feature activation+0.000
Spain
Token Spain
Feature activation+0.000
's
Token's
Feature activation+3.136
most
Token most
Feature activation+2.281
high
Token high
Feature activation+0.268
-
Token-
Feature activation+0.000
profile
Tokenprofile
Feature activation+0.932
finan
Token finan
Feature activation+1.255
VA
TokenVA
Feature activation+0.000
Street
Token Street
Feature activation+0.000
Art
Token Art
Feature activation+0.273
Fest
Token Fest
Feature activation+1.580
Organ
Token Organ
Feature activation+0.072
izers
Tokenizers
Feature activation+3.103
)
Token)
Feature activation+0.491
met
Token met
Feature activation+0.000
with
Token with
Feature activation+0.000
News
Token News
Feature activation+0.000
om
Tokenom
Feature activation+0.000

INTERVAL 2.509 - 2.822
CONTAINS 0.001%

accidentally
Token accidentally
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Slim
Token Slim
Feature activation+0.000
's
Token's
Feature activation+2.785
spiked
Token spiked
Feature activation+1.429
sod
Token sod
Feature activation+0.921
as
Tokenas
Feature activation+2.377
,
Token,
Feature activation+1.545
unwittingly
Token unwittingly
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
bill
Token bill
Feature activation+1.476
's
Token's
Feature activation+2.774
sponsors
Token sponsors
Feature activation+2.716
,
Token,
Feature activation+0.846
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
interview
Token interview
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Scottish
Token Scottish
Feature activation+0.188
National
Token National
Feature activation+0.128
party
Token party
Feature activation+0.751
's
Token's
Feature activation+2.552
core
Token core
Feature activation+1.621
areas
Token areas
Feature activation+1.184
of
Token of
Feature activation+0.000
support
Token support
Feature activation+0.000
is
Token is
Feature activation+0.000
.),
Token.),
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
bill
Token bill
Feature activation+1.476
's
Token's
Feature activation+2.774
sponsors
Token sponsors
Feature activation+2.716
,
Token,
Feature activation+0.846
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
high
Token high
Feature activation+0.268
-
Token-
Feature activation+0.000
profile
Tokenprofile
Feature activation+0.932
finan
Token finan
Feature activation+1.255
ci
Tokenci
Feature activation+0.313
ers
Tokeners
Feature activation+2.788
,
Token,
Feature activation+1.322
Rodrigo
Token Rodrigo
Feature activation+0.000
R
Token R
Feature activation+0.000
ato
Tokenato
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.195 - 2.509
CONTAINS 0.002%

water
Token water
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
America
Token America
Feature activation+0.000
's
Token's
Feature activation+2.359
most
Token most
Feature activation+2.016
be
Token be
Feature activation+0.090
league
Tokenleague
Feature activation+0.000
red
Tokenred
Feature activation+0.571
cities
Token cities
Feature activation+0.785
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Ur
Token Ur
Feature activation+0.000
b
Tokenb
Feature activation+0.000
ana
Tokenana
Feature activation+0.050
's
Token's
Feature activation+2.367
23
Token 23
Feature activation+1.845
precincts
Token precincts
Feature activation+1.958
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
all
Token all
Feature activation+0.000
As
TokenAs
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
's
Token's
Feature activation+2.220
most
Token most
Feature activation+1.746
advanced
Token advanced
Feature activation+1.452
economies
Token economies
Feature activation+0.219
,
Token,
Feature activation+0.238
the
Token the
Feature activation+0.000
that
Token that
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.231
's
Token's
Feature activation+2.430
most
Token most
Feature activation+2.072
cherished
Token cherished
Feature activation+0.902
historic
Token historic
Feature activation+0.245
monuments
Token monuments
Feature activation+0.933
was
Token was
Feature activation+0.000
where
Token where
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
South
Token South
Feature activation+0.000
Africa
Token Africa
Feature activation+0.234
's
Token's
Feature activation+2.220
most
Token most
Feature activation+1.808
disturb
Token disturb
Feature activation+0.000
ingly
Tokeningly
Feature activation+0.000
brutal
Token brutal
Feature activation+0.393
crimes
Token crimes
Feature activation+0.965

INTERVAL 1.881 - 2.195
CONTAINS 0.002%

was
Token was
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
lucky
Token lucky
Feature activation+1.241
ones
Token ones
Feature activation+1.906
on
Token on
Feature activation+0.365
the
Token the
Feature activation+0.000
darkest
Token darkest
Feature activation+0.000
day
Token day
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
eight
Token eight
Feature activation+0.653
homegrown
Token homegrown
Feature activation+0.858
players
Token players
Feature activation+2.093
on
Token on
Feature activation+0.249
R
Token R
Feature activation+0.000
SL
TokenSL
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
point
Token point
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.055
top
Token top
Feature activation+1.895
priorities
Token priorities
Feature activation+1.085
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
a
Token a
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
field
Token field
Feature activation+1.074
's
Token's
Feature activation+2.118
leaders
Token leaders
Feature activation+1.178
,
Token,
Feature activation+0.246
of
Token of
Feature activation+0.000
joining
Token joining
Feature activation+0.000
"
Token "
Feature activation+0.000
ATM
Token ATM
Feature activation+0.270
Solutions
Token Solutions
Feature activation+0.806
âĢ
TokenâĢ
Feature activation+0.209
Ļ
TokenĻ
Feature activation+0.000
armored
Token armored
Feature activation+0.151
vans
Token vans
Feature activation+1.931
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Load
TokenLoad
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.568 - 1.881
CONTAINS 0.006%

(
Token (
Feature activation+0.000
one
Tokenone
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
crew
Token crew
Feature activation+0.772
members
Token members
Feature activation+1.841
)
Token)
Feature activation+0.000
underneath
Token underneath
Feature activation+0.000
a
Token a
Feature activation+0.000
bright
Token bright
Feature activation+0.000
-
Token-
Feature activation+0.000
active
Token active
Feature activation+0.443
"
Token"
Feature activation+0.149
Islamic
Token Islamic
Feature activation+0.618
State
Token State
Feature activation+0.550
execution
Token execution
Feature activation+1.517
ers
Tokeners
Feature activation+1.629
in
Token in
Feature activation+0.143
Syria
Token Syria
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Scottish
Token Scottish
Feature activation+0.188
National
Token National
Feature activation+0.128
party
Token party
Feature activation+0.751
's
Token's
Feature activation+2.552
core
Token core
Feature activation+1.621
areas
Token areas
Feature activation+1.184
of
Token of
Feature activation+0.000
support
Token support
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
IN
Token IN
Feature activation+0.899
A
TokenA
Feature activation+0.533
âĢ
TokenâĢ
Feature activation+0.668
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.493
exceptions
Token exceptions
Feature activation+1.756
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
but
Token but
Feature activation+0.115
better
Token better
Feature activation+0.000
Android
Token Android
Feature activation+0.000
Wear
Token Wear
Feature activation+0.000
watch
Token watch
Feature activation+0.313
faces
Token faces
Feature activation+1.805
.
Token.
Feature activation+0.000
DOWN
Token DOWN
Feature activation+0.000
LOAD
TokenLOAD
Feature activation+0.000
ON
Token ON
Feature activation+0.000
G
Token G
Feature activation+0.000

INTERVAL 1.254 - 1.568
CONTAINS 0.010%

Slim
Token Slim
Feature activation+0.000
's
Token's
Feature activation+2.785
spiked
Token spiked
Feature activation+1.429
sod
Token sod
Feature activation+0.921
as
Tokenas
Feature activation+2.377
,
Token,
Feature activation+1.545
unwittingly
Token unwittingly
Feature activation+0.000
ingest
Token ingest
Feature activation+0.000
ing
Tokening
Feature activation+0.000
his
Token his
Feature activation+0.000
drugs
Token drugs
Feature activation+0.000
-
Token-
Feature activation+0.000
profile
Tokenprofile
Feature activation+0.932
finan
Token finan
Feature activation+1.255
ci
Tokenci
Feature activation+0.313
ers
Tokeners
Feature activation+2.788
,
Token,
Feature activation+1.322
Rodrigo
Token Rodrigo
Feature activation+0.000
R
Token R
Feature activation+0.000
ato
Tokenato
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
is
Token is
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
curses
Token curses
Feature activation+0.893
which
Token which
Feature activation+1.361
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
boost
Token boost
Feature activation+0.000
was
Token was
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.747
's
Token's
Feature activation+1.529
outstanding
Token outstanding
Feature activation+0.470
's
Token's
Feature activation+1.514
moments
Token moments
Feature activation+0.715
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
Applic
Token Applic
Feature activation+0.145
ative
Tokenative
Feature activation+0.000
morph
Token morph
Feature activation+1.278
ism
Tokenism
Feature activation+1.047
laws
Token laws
Feature activation+0.435
(
Token (
Feature activation+0.049
which
Tokenwhich
Feature activation+0.000
I
Token I
Feature activation+0.000

INTERVAL 0.941 - 1.254
CONTAINS 0.016%

urry
Tokenurry
Feature activation+0.000
is
Token is
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
members
Token members
Feature activation+1.234
of
Token of
Feature activation+0.004
Home
Token Home
Feature activation+0.000
Sweet
Token Sweet
Feature activation+0.000
Home
Token Home
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
my
Token my
Feature activation+0.000
favourite
Token favourite
Feature activation+1.080
Australian
Token Australian
Feature activation+0.639
journalists
Token journalists
Feature activation+1.071
,
Token,
Feature activation+0.861
Craig
Token Craig
Feature activation+0.000
McGregor
Token McGregor
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
coolest
Token coolest
Feature activation+0.740
and
Token and
Feature activation+0.627
most
Token most
Feature activation+1.052
immediately
Token immediately
Feature activation+0.000
worthwhile
Token worthwhile
Feature activation+0.976
applications
Token applications
Feature activation+0.833
of
Token of
Feature activation+0.000
distributed
Token distributed
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
your
Token your
Feature activation+0.000
Lab
Token Lab
Feature activation+0.000
els
Tokenels
Feature activation+0.390
(
Token (
Feature activation+1.149
a
Tokena
Feature activation+0.000
stat
Token stat
Feature activation+0.000
that
Token that
Feature activation+0.000
describes
Token describes
Feature activation+0.000
your
Token your
Feature activation+0.000
pen
Token pen
Feature activation+0.000
of
Token of
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
my
Token my
Feature activation+0.000
favourite
Token favourite
Feature activation+1.080
Australian
Token Australian
Feature activation+0.639
journalists
Token journalists
Feature activation+1.071
,
Token,
Feature activation+0.861
Craig
Token Craig
Feature activation+0.000
McGregor
Token McGregor
Feature activation+0.000

INTERVAL 0.627 - 0.941
CONTAINS 0.032%

out
Token out
Feature activation+0.000
to
Token to
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
founders
Token founders
Feature activation+0.926
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Blockchain
Token Blockchain
Feature activation+0.235
Embassy
Token Embassy
Feature activation+0.583
(
Token (
Feature activation+0.735
you
Token you
Feature activation+0.000
pick
Token pick
Feature activation+0.000
3
Token 3
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.072
following
Token following
Feature activation+0.657
8
Token 8
Feature activation+0.410
themes
Token themes
Feature activation+0.086
(
Token (
Feature activation+0.094
we
Tokenwe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
of
Token of
Feature activation+0.000
my
Token my
Feature activation+0.000
favourite
Token favourite
Feature activation+1.080
Australian
Token Australian
Feature activation+0.639
journalists
Token journalists
Feature activation+1.071
,
Token,
Feature activation+0.861
Craig
Token Craig
Feature activation+0.000
McGregor
Token McGregor
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
had
Token had
Feature activation+0.000
the
Token the
Feature activation+0.000
main
Token main
Feature activation+1.093
goals
Token goals
Feature activation+0.864
core
Tokencore
Feature activation+0.752
rs
Tokenrs
Feature activation+1.272
is
Token is
Feature activation+0.669
Boulder
Token Boulder
Feature activation+0.000
native
Token native
Feature activation+0.000
Shane
Token Shane
Feature activation+0.000
Wheeler
Token Wheeler
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
reasons
Token reasons
Feature activation+0.515
I
Token I
Feature activation+0.643
like
Token like
Feature activation+0.000
it
Token it
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
racing
Token racing
Feature activation+0.000

INTERVAL 0.314 - 0.627
CONTAINS 0.047%

of
Token of
Feature activation+0.000
Bernie
Token Bernie
Feature activation+0.000
Sanders
Token Sanders
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
most
Token most
Feature activation+0.533
popular
Token popular
Feature activation+0.000
proposals
Token proposals
Feature activation+1.878
was
Token was
Feature activation+0.000
his
Token his
Feature activation+0.000
plan
Token plan
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.145
most
Token most
Feature activation+1.021
eminent
Token eminent
Feature activation+1.164
scientists
Token scientists
Feature activation+0.681
:
Token:
Feature activation+0.344
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
general
Token general
Feature activation+0.000
we
Token we
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.795
likes
Token likes
Feature activation+0.725
donated
Token donated
Feature activation+0.570
$
Token $
Feature activation+0.354
15
Token15
Feature activation+0.000
right
Token right
Feature activation+0.000
now
Token now
Feature activation+0.000
,
Token,
Feature activation+0.242
Battle
Token Battle
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
One
TokenOne
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.555
techniques
Token techniques
Feature activation+0.000
that
Token that
Feature activation+0.028
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
English
Token English
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
two
Token two
Feature activation+0.339
forwarded
Token forwarded
Feature activation+0.045
by
Token by
Feature activation+0.413
the
Token the
Feature activation+0.000
Spokane
Token Spokane
Feature activation+0.000
Tribal
Token Tribal
Feature activation+0.000

INTERVAL 0.000 - 0.314
CONTAINS 99.883%

about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
1945
Token 1945
Feature activation+0.000
atomic
Token atomic
Feature activation+0.000
bombing
Token bombing
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
home
Token home
Feature activation+0.000
city
Token city
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
f
Token f
Feature activation+0.000
attr
Tokenattr
Feature activation+0.000
(
Token(
Feature activation+0.000
:
Token:
Feature activation+0.000
role
Tokenrole
Feature activation+0.000
)
Token)
Feature activation+0.000
{
Token {
Feature activation+0.000
nil
Token nil
Feature activation+0.000
}
Token }
Feature activation+0.000
#
Token #
Feature activation+0.000
attribute
Token attribute
Feature activation+0.000
that
Token that
Feature activation+0.000
John
Token John
Feature activation+0.000
Scal
Token Scal
Feature activation+0.000
zi
Tokenzi
Feature activation+0.000
donated
Token donated
Feature activation+0.000
was
Token was
Feature activation+0.000
going
Token going
Feature activation+0.000
into
Token into
Feature activation+0.000
an
Token an
Feature activation+0.000
auction
Token auction
Feature activation+0.000
.
Token.
Feature activation+0.000
old
Token old
Feature activation+0.000
,
Token,
Feature activation+0.000
same
Token same
Feature activation+0.000
old
Token old
Feature activation+0.000
,
Token,
Feature activation+0.000
billions
Token billions
Feature activation+0.000
of
Token of
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
in
Token in
Feature activation+0.000
spending
Token spending
Feature activation+0.000
and
Token and
Feature activation+0.000
-
Token-
Feature activation+0.000
oak
Tokenoak
Feature activation+0.000
is
Token is
Feature activation+0.000
found
Token found
Feature activation+0.000
only
Token only
Feature activation+0.000
within
Token within
Feature activation+0.000
metropolitan
Token metropolitan
Feature activation+0.000
Sydney
Token Sydney
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
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 H3.2: (feature 15264)

TOP ACTIVATIONS
MAX = 4.728

order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
safely
Token safely
Feature activation+0.000
reach
Token reach
Feature activation+0.000
such
Token such
Feature activation+0.000
unprecedented
Token unprecedented
Feature activation+4.728
heights
Token heights
Feature activation+3.840
.
Token.
Feature activation+0.000
Struct
Token Struct
Feature activation+0.000
ural
Tokenural
Feature activation+0.000
steel
Token steel
Feature activation+0.000
state
Token state
Feature activation+0.000
to
Token to
Feature activation+0.000
pass
Token pass
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.674
bill
Token bill
Feature activation+4.726
in
Token in
Feature activation+0.343
2013
Token 2013
Feature activation+0.000
.
Token.
Feature activation+0.000
Typically
Token Typically
Feature activation+0.000
those
Token those
Feature activation+0.000
used
Token used
Feature activation+0.000
for
Token for
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.959
wide
Token wide
Feature activation+3.524
variety
Token variety
Feature activation+4.703
of
Token of
Feature activation+2.993
tasks
Token tasks
Feature activation+1.281
by
Token by
Feature activation+0.412
indigenous
Token indigenous
Feature activation+0.000
peoples
Token peoples
Feature activation+0.000
primed
Token primed
Feature activation+0.000
for
Token for
Feature activation+0.000
just
Token just
Feature activation+0.000
such
Token such
Feature activation+0.000
an
Token an
Feature activation+0.000
extraordinary
Token extraordinary
Feature activation+4.590
event
Token event
Feature activation+2.449
,
Token,
Feature activation+0.377
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
ge
Token ge
Feature activation+0.000
is
Token is
Feature activation+0.000
often
Token often
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.463
rare
Token rare
Feature activation+3.293
feat
Token feat
Feature activation+4.468
that
Token that
Feature activation+1.778
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
celebrated
Token celebrated
Feature activation+0.000
with
Token with
Feature activation+0.000
on
Token on
Feature activation+0.000
us
Token us
Feature activation+0.000
to
Token to
Feature activation+0.000
such
Token such
Feature activation+0.000
an
Token an
Feature activation+0.013
extent
Token extent
Feature activation+4.387
that
Token that
Feature activation+2.447
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
here
Token here
Feature activation+0.000
such
Token such
Feature activation+0.000
an
Token an
Feature activation+0.065
idea
Token idea
Feature activation+4.366
could
Token could
Feature activation+0.682
be
Token be
Feature activation+0.000
interesting
Token interesting
Feature activation+0.144
,
Token,
Feature activation+0.000
especially
Token especially
Feature activation+0.000
.
Token.
Feature activation+0.000
Such
Token Such
Feature activation+0.000
unsub
Token unsub
Feature activation+2.877
stant
Tokenstant
Feature activation+1.782
iated
Tokeniated
Feature activation+3.546
assertions
Token assertions
Feature activation+4.364
often
Token often
Feature activation+0.188
highlight
Token highlight
Feature activation+0.000
that
Token that
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.000
Fer
Token Fer
Feature activation+0.000
rell
Tokenrell
Feature activation+0.000
in
Token in
Feature activation+0.000
such
Token such
Feature activation+0.000
comedy
Token comedy
Feature activation+3.223
classics
Token classics
Feature activation+4.361
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
An
TokenAn
Feature activation+0.000
ch
Tokench
Feature activation+0.000
to
Token to
Feature activation+0.000
let
Token let
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.351
lucrative
Token lucrative
Feature activation+3.621
practice
Token practice
Feature activation+4.285
go
Token go
Feature activation+0.000
up
Token up
Feature activation+0.000
in
Token in
Feature activation+0.000
smoke
Token smoke
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
actually
Token actually
Feature activation+0.000
fund
Token fund
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.935
massive
Token massive
Feature activation+4.261
project
Token project
Feature activation+3.841
,
Token,
Feature activation+1.434
and
Token and
Feature activation+0.028
what
Token what
Feature activation+0.000
repercussions
Token repercussions
Feature activation+0.000
Aleppo
Token Aleppo
Feature activation+0.000
have
Token have
Feature activation+0.000
never
Token never
Feature activation+0.000
seen
Token seen
Feature activation+0.000
such
Token such
Feature activation+0.000
intense
Token intense
Feature activation+4.229
bombardment
Token bombardment
Feature activation+3.200
as
Token as
Feature activation+0.129
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
over
Token over
Feature activation+0.000
started
Token started
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
about
Token about
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+1.317
project
Token project
Feature activation+4.180
,
Token,
Feature activation+2.059
to
Token to
Feature activation+0.000
unb
Token unb
Feature activation+0.000
urden
Tokenurden
Feature activation+0.000
the
Token the
Feature activation+0.000
defend
Token defend
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
against
Token against
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.883
ludicrous
Token ludicrous
Feature activation+4.092
charge
Token charge
Feature activation+3.168
?
Token?
Feature activation+0.000
Who
Token Who
Feature activation+0.000
would
Token would
Feature activation+0.000
ever
Token ever
Feature activation+0.000
systems
Token systems
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
for
Token for
Feature activation+0.000
such
Token such
Feature activation+0.186
a
Token a
Feature activation+1.061
project
Token project
Feature activation+4.047
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
what
Token what
Feature activation+0.000
shred
Token shred
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+1.444
crossover
Token crossover
Feature activation+4.024
to
Token to
Feature activation+0.794
happen
Token happen
Feature activation+1.355
would
Token would
Feature activation+0.000
take
Token take
Feature activation+0.000
a
Token a
Feature activation+0.000
since
Token since
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.137
clear
Token clear
Feature activation+3.950
violation
Token violation
Feature activation+3.690
of
Token of
Feature activation+0.065
their
Token their
Feature activation+0.000
numerous
Token numerous
Feature activation+0.000
statements
Token statements
Feature activation+0.000
helping
Token helping
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.470
tent
Token tent
Feature activation+2.632
acular
Tokenacular
Feature activation+2.399
feat
Token feat
Feature activation+3.946
of
Token of
Feature activation+1.516
parallel
Token parallel
Feature activation+0.000
development
Token development
Feature activation+0.000
to
Token to
Feature activation+0.000
happen
Token happen
Feature activation+0.000
could
Token could
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
from
Token from
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.931
debate
Token debate
Feature activation+3.931
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
other
Token other
Feature activation+0.000
points
Token points
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
With
TokenWith
Feature activation+0.000
such
Token such
Feature activation+0.000
turbulent
Token turbulent
Feature activation+3.646
financial
Token financial
Feature activation+3.929
forecasts
Token forecasts
Feature activation+3.906
of
Token of
Feature activation+1.367
late
Token late
Feature activation+0.000
,
Token,
Feature activation+0.000
OMG
Token OMG
Feature activation+0.000

Top DFA by src position
MAX = 5.350

in
Token in
Feature activation+0.001
Top resid features:
order
Token order
Feature activation+0.021
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
safely
Token safely
Feature activation-0.026
Top resid features:
reach
Token reach
Feature activation+0.021
Top resid features:
such
Token such
Feature activation+5.210
Top resid features:
unprecedented
Token unprecedented
Feature activation+0.131
Top resid features:
heights
Token heights
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Struct
Token Struct
Feature activation+0.000
Top resid features:
ural
Tokenural
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
last
Token last
Feature activation+0.015
Top resid features:
state
Token state
Feature activation+0.036
Top resid features:
to
Token to
Feature activation+0.072
Top resid features:
pass
Token pass
Feature activation+0.328
Top resid features:
such
Token such
Feature activation+4.636
Top resid features:
a
Token a
Feature activation+0.181
Top resid features:
bill
Token bill
Feature activation+0.066
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
2013
Token 2013
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
amboo
Tokenamboo
Feature activation-0.013
Top resid features:
has
Token has
Feature activation+0.061
Top resid features:
been
Token been
Feature activation-0.006
Top resid features:
used
Token used
Feature activation-0.039
Top resid features:
for
Token for
Feature activation-0.072
Top resid features:
such
Token such
Feature activation+5.350
Top resid features:
a
Token a
Feature activation+0.132
Top resid features:
wide
Token wide
Feature activation-0.019
Top resid features:
variety
Token variety
Feature activation-0.032
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
tasks
Token tasks
Feature activation+0.000
Top resid features:
area
Token area
Feature activation-0.015
Top resid features:
was
Token was
Feature activation+0.010
Top resid features:
primed
Token primed
Feature activation-0.039
Top resid features:
for
Token for
Feature activation-0.101
Top resid features:
just
Token just
Feature activation+0.057
Top resid features:
such
Token such
Feature activation+5.019
Top resid features:
an
Token an
Feature activation+0.119
Top resid features:
extraordinary
Token extraordinary
Feature activation+0.116
Top resid features:
event
Token event
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
according
Token according
Feature activation+0.000
Top resid features:
soccer
Token soccer
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
It
Token It
Feature activation-0.011
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
often
Token often
Feature activation-0.058
Top resid features:
such
Token such
Feature activation+4.875
Top resid features:
a
Token a
Feature activation+0.153
Top resid features:
rare
Token rare
Feature activation+0.061
Top resid features:
feat
Token feat
Feature activation+0.116
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.030
Top resid features:
depend
Token depend
Feature activation+0.026
Top resid features:
on
Token on
Feature activation-0.004
Top resid features:
us
Token us
Feature activation-0.019
Top resid features:
to
Token to
Feature activation+0.080
Top resid features:
such
Token such
Feature activation+4.686
Top resid features:
an
Token an
Feature activation+0.140
Top resid features:
extent
Token extent
Feature activation+0.172
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
Switzerland
Token Switzerland
Feature activation+0.025
Top resid features:
,
Token,
Feature activation+0.039
Top resid features:
but
Token but
Feature activation+0.030
Top resid features:
also
Token also
Feature activation-0.017
Top resid features:
here
Token here
Feature activation-0.229
Top resid features:
such
Token such
Feature activation+4.776
Top resid features:
an
Token an
Feature activation+0.203
Top resid features:
idea
Token idea
Feature activation+0.069
Top resid features:
could
Token could
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
interesting
Token interesting
Feature activation+0.000
Top resid features:
White
Token White
Feature activation+0.000
Top resid features:
House
Token House
Feature activation+0.013
Top resid features:
in
Token in
Feature activation-0.007
Top resid features:
2008
Token 2008
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.091
Top resid features:
Such
Token Such
Feature activation+4.587
Top resid features:
unsub
Token unsub
Feature activation-0.033
Top resid features:
stant
Tokenstant
Feature activation+0.048
Top resid features:
iated
Tokeniated
Feature activation+0.042
Top resid features:
assertions
Token assertions
Feature activation+0.250
Top resid features:
often
Token often
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.099
Top resid features:
directed
Token directed
Feature activation+0.105
Top resid features:
Fer
Token Fer
Feature activation-0.017
Top resid features:
rell
Tokenrell
Feature activation+0.004
Top resid features:
in
Token in
Feature activation-0.036
Top resid features:
such
Token such
Feature activation+4.552
Top resid features:
comedy
Token comedy
Feature activation+0.166
Top resid features:
classics
Token classics
Feature activation+0.130
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
too
Token too
Feature activation+0.002
Top resid features:
much
Token much
Feature activation-0.005
Top resid features:
money
Token money
Feature activation-0.049
Top resid features:
to
Token to
Feature activation-0.026
Top resid features:
let
Token let
Feature activation-0.059
Top resid features:
such
Token such
Feature activation+4.727
Top resid features:
a
Token a
Feature activation+0.134
Top resid features:
lucrative
Token lucrative
Feature activation+0.005
Top resid features:
practice
Token practice
Feature activation+0.047
Top resid features:
go
Token go
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.014
Top resid features:
going
Token going
Feature activation+0.016
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
actually
Token actually
Feature activation+0.007
Top resid features:
fund
Token fund
Feature activation+0.021
Top resid features:
such
Token such
Feature activation+4.479
Top resid features:
a
Token a
Feature activation+0.177
Top resid features:
massive
Token massive
Feature activation+0.089
Top resid features:
project
Token project
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:
eastern
Token eastern
Feature activation-0.008
Top resid features:
Aleppo
Token Aleppo
Feature activation-0.007
Top resid features:
have
Token have
Feature activation+0.077
Top resid features:
never
Token never
Feature activation+0.085
Top resid features:
seen
Token seen
Feature activation+0.205
Top resid features:
such
Token such
Feature activation+4.415
Top resid features:
intense
Token intense
Feature activation+0.026
Top resid features:
bombardment
Token bombardment
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
ago
Token ago
Feature activation+0.008
Top resid features:
they
Token they
Feature activation-0.027
Top resid features:
started
Token started
Feature activation-0.002
Top resid features:
thinking
Token thinking
Feature activation+0.080
Top resid features:
about
Token about
Feature activation-0.072
Top resid features:
such
Token such
Feature activation+4.464
Top resid features:
a
Token a
Feature activation+0.234
Top resid features:
project
Token project
Feature activation+0.058
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
unb
Token unb
Feature activation+0.000
Top resid features:
need
Token need
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
defend
Token defend
Feature activation+0.031
Top resid features:
themselves
Token themselves
Feature activation+0.006
Top resid features:
against
Token against
Feature activation-0.050
Top resid features:
such
Token such
Feature activation+4.182
Top resid features:
a
Token a
Feature activation+0.327
Top resid features:
ludicrous
Token ludicrous
Feature activation+0.150
Top resid features:
charge
Token charge
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Who
Token Who
Feature activation+0.000
Top resid features:
water
Token water
Feature activation+0.004
Top resid features:
reuse
Token reuse
Feature activation-0.001
Top resid features:
systems
Token systems
Feature activation-0.012
Top resid features:
necessary
Token necessary
Feature activation+0.009
Top resid features:
for
Token for
Feature activation-0.049
Top resid features:
such
Token such
Feature activation+4.227
Top resid features:
a
Token a
Feature activation+0.352
Top resid features:
project
Token project
Feature activation+0.026
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+0.001
Top resid features:
A
Token A
Feature activation+0.009
Top resid features:
shred
Token shred
Feature activation+0.035
Top resid features:
.
Token.
Feature activation+0.041
Top resid features:
For
Token For
Feature activation-0.060
Top resid features:
such
Token such
Feature activation+4.324
Top resid features:
a
Token a
Feature activation+0.221
Top resid features:
crossover
Token crossover
Feature activation+0.041
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
happen
Token happen
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
act
Token act
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
since
Token since
Feature activation+0.018
Top resid features:
this
Token this
Feature activation-0.204
Top resid features:
is
Token is
Feature activation+0.114
Top resid features:
such
Token such
Feature activation+4.198
Top resid features:
a
Token a
Feature activation+0.274
Top resid features:
clear
Token clear
Feature activation+0.107
Top resid features:
violation
Token violation
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
editing
Token editing
Feature activation-0.007
Top resid features:
task
Token task
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
helping
Token helping
Feature activation+0.080
Top resid features:
such
Token such
Feature activation+4.345
Top resid features:
a
Token a
Feature activation+0.139
Top resid features:
tent
Token tent
Feature activation-0.044
Top resid features:
acular
Tokenacular
Feature activation-0.006
Top resid features:
feat
Token feat
Feature activation+0.074
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
ism
Tokenism
Feature activation+0.016
Top resid features:
certainly
Token certainly
Feature activation-0.017
Top resid features:
could
Token could
Feature activation+0.052
Top resid features:
benefit
Token benefit
Feature activation+0.069
Top resid features:
from
Token from
Feature activation-0.103
Top resid features:
such
Token such
Feature activation+4.115
Top resid features:
a
Token a
Feature activation+0.304
Top resid features:
debate
Token debate
Feature activation+0.073
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
There
Token There
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
2012
Token 2012
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.027
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
With
TokenWith
Feature activation+0.034
Top resid features:
such
Token such
Feature activation+4.349
Top resid features:
turbulent
Token turbulent
Feature activation+0.169
Top resid features:
financial
Token financial
Feature activation-0.012
Top resid features:
forecasts
Token forecasts
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
late
Token late
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.05

Head 2: 0.48

Head 3: 0.02

Head 4: 0.03

Head 5: 0.03

Head 6: 0.11

Head 7: 0.05

Head 8: 0.04

Head 9: 0.02

Head 10: 0.06

Head 11: 0.07

Positive logits

lems1.42

anes1.38

hetic1.36

hesis1.34

ionic1.34

atically1.32

aments1.28

alt1.23

imb1.23

asses1.23

roman1.22

arity1.22

enery1.21

azo1.20

unctions1.20

ials1.20

ult1.19

otic1.19

angles1.19

extends1.19

Negative logits

Nun-1.34

Poster-1.19

Patton-1.06

Murd-1.05

Died-1.05

Massacre-1.04

bestselling-1.00

twins-1.00

Tank-1.00

Pump-0.99

Books-0.99

Mail-0.99

Courier-0.97

_--0.96

Malf-0.95

Su-0.95

Pru-0.95

Sins-0.95

_>-0.95

Yose-0.95

INTERVAL 4.255 - 4.728
CONTAINS 0.001%

state
Token state
Feature activation+0.000
to
Token to
Feature activation+0.000
pass
Token pass
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.674
bill
Token bill
Feature activation+4.726
in
Token in
Feature activation+0.343
2013
Token 2013
Feature activation+0.000
.
Token.
Feature activation+0.000
Typically
Token Typically
Feature activation+0.000
those
Token those
Feature activation+0.000
primed
Token primed
Feature activation+0.000
for
Token for
Feature activation+0.000
just
Token just
Feature activation+0.000
such
Token such
Feature activation+0.000
an
Token an
Feature activation+0.000
extraordinary
Token extraordinary
Feature activation+4.590
event
Token event
Feature activation+2.449
,
Token,
Feature activation+0.377
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
ge
Token ge
Feature activation+0.000
used
Token used
Feature activation+0.000
for
Token for
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.959
wide
Token wide
Feature activation+3.524
variety
Token variety
Feature activation+4.703
of
Token of
Feature activation+2.993
tasks
Token tasks
Feature activation+1.281
by
Token by
Feature activation+0.412
indigenous
Token indigenous
Feature activation+0.000
peoples
Token peoples
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
safely
Token safely
Feature activation+0.000
reach
Token reach
Feature activation+0.000
such
Token such
Feature activation+0.000
unprecedented
Token unprecedented
Feature activation+4.728
heights
Token heights
Feature activation+3.840
.
Token.
Feature activation+0.000
Struct
Token Struct
Feature activation+0.000
ural
Tokenural
Feature activation+0.000
steel
Token steel
Feature activation+0.000
Fer
Token Fer
Feature activation+0.000
rell
Tokenrell
Feature activation+0.000
in
Token in
Feature activation+0.000
such
Token such
Feature activation+0.000
comedy
Token comedy
Feature activation+3.223
classics
Token classics
Feature activation+4.361
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
An
TokenAn
Feature activation+0.000
ch
Tokench
Feature activation+0.000

INTERVAL 3.782 - 4.255
CONTAINS 0.002%

to
Token to
Feature activation+0.000
carry
Token carry
Feature activation+0.000
it
Token it
Feature activation+0.000
:
Token:
Feature activation+0.000
such
Token such
Feature activation+0.000
changes
Token changes
Feature activation+3.809
are
Token are
Feature activation+2.506
made
Token made
Feature activation+0.000
nightly
Token nightly
Feature activation+0.000
by
Token by
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
attendance
Token attendance
Feature activation+0.000
ruled
Token ruled
Feature activation+0.000
out
Token out
Feature activation+0.000
such
Token such
Feature activation+0.000
risks
Token risks
Feature activation+3.838
from
Token from
Feature activation+1.427
the
Token the
Feature activation+0.000
start
Token start
Feature activation+0.000
,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.000
failed
Tokenfailed
Feature activation+0.000
to
Token to
Feature activation+0.000
timely
Token timely
Feature activation+0.000
cure
Token cure
Feature activation+0.000
such
Token such
Feature activation+0.000
defaults
Token defaults
Feature activation+3.801
and
Token and
Feature activation+1.821
accordingly
Token accordingly
Feature activation+0.000
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
or
Token or
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.410
conflict
Token conflict
Feature activation+3.862
.
Token.
Feature activation+0.000
Massive
Token Massive
Feature activation+0.000
industrialized
Token industrialized
Feature activation+0.000
powers
Token powers
Feature activation+0.000
with
Token with
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.000
transparent
Token transparent
Feature activation+3.317
ly
Tokenly
Feature activation+1.106
false
Token false
Feature activation+3.558
assertion
Token assertion
Feature activation+3.878
right
Token right
Feature activation+1.631
up
Token up
Feature activation+0.000
front
Token front
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 3.309 - 3.782
CONTAINS 0.006%

take
Token take
Feature activation+0.000
advantage
Token advantage
Feature activation+0.000
of
Token of
Feature activation+0.000
such
Token such
Feature activation+0.000
injust
Token injust
Feature activation+2.864
ices
Tokenices
Feature activation+3.323
,
Token,
Feature activation+1.471
which
Token which
Feature activation+0.814
typically
Token typically
Feature activation+0.000
target
Token target
Feature activation+0.000
vulnerable
Token vulnerable
Feature activation+0.000
of
Token of
Feature activation+0.000
threat
Token threat
Feature activation+0.000
.
Token.
Feature activation+0.000
Such
Token Such
Feature activation+0.000
cheap
Token cheap
Feature activation+2.768
threats
Token threats
Feature activation+3.361
and
Token and
Feature activation+0.564
intimidation
Token intimidation
Feature activation+0.000
give
Token give
Feature activation+0.000
people
Token people
Feature activation+0.000
even
Token even
Feature activation+0.000
2008
Token 2008
Feature activation+0.000
.
Token.
Feature activation+0.000
Such
Token Such
Feature activation+0.000
unsub
Token unsub
Feature activation+2.877
stant
Tokenstant
Feature activation+1.782
iated
Tokeniated
Feature activation+3.546
assertions
Token assertions
Feature activation+4.364
often
Token often
Feature activation+0.188
highlight
Token highlight
Feature activation+0.000
that
Token that
Feature activation+0.000
his
Token his
Feature activation+0.000
grateful
Token grateful
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.488
terrific
Token terrific
Feature activation+3.676
brand
Token brand
Feature activation+3.361
like
Token like
Feature activation+0.000
G
Token G
Feature activation+0.000
AT
TokenAT
Feature activation+0.000
sponsor
Token sponsor
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000
policymakers
Token policymakers
Feature activation+0.000
think
Token think
Feature activation+0.000
about
Token about
Feature activation+0.000
such
Token such
Feature activation+0.000
matters
Token matters
Feature activation+3.448
,
Token,
Feature activation+0.639
then
Token then
Feature activation+0.000
Murray
Token Murray
Feature activation+0.000
has
Token has
Feature activation+0.000
already
Token already
Feature activation+0.000

INTERVAL 2.837 - 3.309
CONTAINS 0.007%

The
Token The
Feature activation+0.000
FD
Token FD
Feature activation+0.000
IC
TokenIC
Feature activation+0.000
supports
Token supports
Feature activation+0.000
such
Token such
Feature activation+0.000
rules
Token rules
Feature activation+3.037
,
Token,
Feature activation+0.925
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
FD
Token FD
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
years
Token years
Feature activation+0.000
of
Token of
Feature activation+0.000
such
Token such
Feature activation+0.000
bathing
Token bathing
Feature activation+2.997
causes
Token causes
Feature activation+1.718
a
Token a
Feature activation+0.000
condition
Token condition
Feature activation+0.254
known
Token known
Feature activation+0.000
as
Token as
Feature activation+0.000
mercenaries
Token mercenaries
Feature activation+0.000
who
Token who
Feature activation+0.000
had
Token had
Feature activation+0.000
received
Token received
Feature activation+0.000
such
Token such
Feature activation+0.000
payments
Token payments
Feature activation+3.119
complained
Token complained
Feature activation+0.906
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
tax
Token tax
Feature activation+0.000
plan
Token plan
Feature activation+0.000
.
Token.
Feature activation+0.000
Yet
Token Yet
Feature activation+0.000
such
Token such
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+3.007
have
Token have
Feature activation+1.998
shown
Token shown
Feature activation+0.000
they
Token they
Feature activation+0.000
see
Token see
Feature activation+0.000
no
Token no
Feature activation+0.000
have
Token have
Feature activation+0.000
never
Token never
Feature activation+0.000
seen
Token seen
Feature activation+0.000
such
Token such
Feature activation+0.000
intense
Token intense
Feature activation+4.229
bombardment
Token bombardment
Feature activation+3.200
as
Token as
Feature activation+0.129
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.364 - 2.837
CONTAINS 0.007%

which
Token which
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
involve
Token involve
Feature activation+0.000
such
Token such
Feature activation+0.000
heavy
Token heavy
Feature activation+2.566
Libre
Token Libre
Feature activation+1.069
Office
TokenOffice
Feature activation+0.000
use
Token use
Feature activation+0.826
).
Token).
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
us
Token us
Feature activation+0.000
to
Token to
Feature activation+0.000
such
Token such
Feature activation+0.000
an
Token an
Feature activation+0.013
extent
Token extent
Feature activation+4.387
that
Token that
Feature activation+2.447
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
staff
Token staff
Feature activation+0.000
to
Token to
Feature activation+0.000
oversee
Token oversee
Feature activation+0.000
such
Token such
Feature activation+0.000
complex
Token complex
Feature activation+2.579
programs
Token programs
Feature activation+2.764
,
Token,
Feature activation+0.427
and
Token and
Feature activation+0.000
Foot
Token Foot
Feature activation+0.000
e
Tokene
Feature activation+0.000
announced
Token announced
Feature activation+0.000
of
Token of
Feature activation+0.000
sex
Token sex
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
such
Token such
Feature activation+0.000
facilities
Token facilities
Feature activation+2.681
provided
Token provided
Feature activation+1.803
for
Token for
Feature activation+0.000
students
Token students
Feature activation+0.000
of
Token of
Feature activation+0.000
one
Token one
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Such
TokenSuch
Feature activation+0.000
an
Token an
Feature activation+0.000
active
Token active
Feature activation+2.534
aerial
Token aerial
Feature activation+1.423
surveillance
Token surveillance
Feature activation+0.614
operation
Token operation
Feature activation+0.735
,
Token,
Feature activation+0.917
when
Token when
Feature activation+0.000

INTERVAL 1.891 - 2.364
CONTAINS 0.007%

by
Token by
Feature activation+0.000
being
Token being
Feature activation+0.000
in
Token in
Feature activation+0.000
such
Token such
Feature activation+0.000
close
Token close
Feature activation+0.584
proximity
Token proximity
Feature activation+2.250
to
Token to
Feature activation+0.671
teach
Token teach
Feature activation+0.000
other
Token other
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
to
Token to
Feature activation+0.000
school
Token school
Feature activation+0.000
and
Token and
Feature activation+0.000
face
Token face
Feature activation+0.000
such
Token such
Feature activation+0.000
abuse
Token abuse
Feature activation+2.245
.
Token.
Feature activation+0.000
The
TokenThe
Feature activation+0.000
mother
Token mother
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
such
Token such
Feature activation+0.000
acts
Token acts
Feature activation+3.539
should
Token should
Feature activation+2.285
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.000
outlawed
Token outlawed
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
dreams
Token dreams
Feature activation+0.000
at
Token at
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.077
prestigious
Token prestigious
Feature activation+3.301
University
Token University
Feature activation+2.033
.
Token.
Feature activation+0.099
I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
graduating
Token graduating
Feature activation+0.000
Current
Token Current
Feature activation+0.000
laws
Token laws
Feature activation+0.000
permit
Token permit
Feature activation+0.000
such
Token such
Feature activation+0.000
citizenship
Token citizenship
Feature activation+1.915
status
Token status
Feature activation+1.996
are
Token are
Feature activation+1.393
the
Token the
Feature activation+0.000
practice
Token practice
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000

INTERVAL 1.418 - 1.891
CONTAINS 0.007%

was
Token was
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.195
beautiful
Token beautiful
Feature activation+3.248
and
Token and
Feature activation+1.537
powerful
Token powerful
Feature activation+1.564
image
Token image
Feature activation+1.760
and
Token and
Feature activation+0.354
he
Token he
Feature activation+0.000
immediately
Token immediately
Feature activation+0.000
connected
Token connected
Feature activation+0.000
ions
Tokenions
Feature activation+0.000
work
Token work
Feature activation+0.000
in
Token in
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.620
way
Token way
Feature activation+1.587
that
Token that
Feature activation+1.164
the
Token the
Feature activation+0.000
particle
Token particle
Feature activation+0.000
rarely
Token rarely
Feature activation+0.000
interacts
Token interacts
Feature activation+0.000
made
Token made
Feature activation+0.000
such
Token such
Feature activation+0.000
an
Token an
Feature activation+0.000
aggressive
Token aggressive
Feature activation+3.162
push
Token push
Feature activation+2.334
,
Token,
Feature activation+1.878
Republican
Token Republican
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
here
Token here
Feature activation+0.000
have
Token have
Feature activation+0.000
yet
Token yet
Feature activation+0.000
to
Token to
Feature activation+0.000
timely
Token timely
Feature activation+0.000
cure
Token cure
Feature activation+0.000
such
Token such
Feature activation+0.000
defaults
Token defaults
Feature activation+3.801
and
Token and
Feature activation+1.821
accordingly
Token accordingly
Feature activation+0.000
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
or
Token or
Feature activation+0.000
about
Token about
Feature activation+0.000
solutions
Token solutions
Feature activation+0.000
.
Token.
Feature activation+0.000
Most
Token Most
Feature activation+0.000
of
Token of
Feature activation+0.000
such
Token such
Feature activation+0.000
solutions
Token solutions
Feature activation+1.435
are
Token are
Feature activation+0.000
simply
Token simply
Feature activation+0.000
not
Token not
Feature activation+0.000
available
Token available
Feature activation+0.000
as
Token as
Feature activation+0.000

INTERVAL 0.946 - 1.418
CONTAINS 0.009%

,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.000
conducting
Token conducting
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.852
launch
Token launch
Feature activation+1.025
over
Token over
Feature activation+0.334
Japan
Token Japan
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
of
Token of
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.517
large
Token large
Feature activation+3.675
crowd
Token crowd
Feature activation+2.342
and
Token and
Feature activation+1.137
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
vehicle
Token vehicle
Feature activation+0.000
in
Token in
Feature activation+0.000
places
Token places
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
luxurious
Token luxurious
Feature activation+1.092
Long
Token Long
Feature activation+0.000
Island
Token Island
Feature activation+0.000
homes
Token homes
Feature activation+1.029
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
influence
Token influence
Feature activation+0.000
the
Token the
Feature activation+0.000
outcome
Token outcome
Feature activation+0.000
of
Token of
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+1.136
competition
Token competition
Feature activation+2.334
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
assumed
Token assumed
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
such
Token such
Feature activation+0.000
fossil
Token fossil
Feature activation+1.502
ized
Tokenized
Feature activation+1.426
dinosaur
Token dinosaur
Feature activation+0.961
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
marine
Token marine
Feature activation+0.000
str
Token str
Feature activation+0.000
atum
Tokenatum
Feature activation+0.000

INTERVAL 0.473 - 0.946
CONTAINS 0.011%

t
Tokent
Feature activation+0.000
warrant
Token warrant
Feature activation+0.000
such
Token such
Feature activation+0.000
extended
Token extended
Feature activation+2.871
disruption
Token disruption
Feature activation+2.085
of
Token of
Feature activation+0.916
parliament
Token parliament
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
only
Token only
Feature activation+0.000
thing
Token thing
Feature activation+0.000
the
Token the
Feature activation+0.000
Assad
Token Assad
Feature activation+0.000
regime
Token regime
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.749
development
Token development
Feature activation+2.386
would
Token would
Feature activation+0.938
force
Token force
Feature activation+0.000
Israel
Token Israel
Feature activation+0.000
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Such
TokenSuch
Feature activation+0.000
people
Token people
Feature activation+1.877
are
Token are
Feature activation+0.631
very
Token very
Feature activation+0.000
expensive
Token expensive
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.000
feature
Token feature
Feature activation+3.627
doesn
Token doesn
Feature activation+0.838
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
really
Token really
Feature activation+0.000
count
Token count
Feature activation+0.000
.
Token.
Feature activation+0.000
Having
Token Having
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+1.128
one
Token one
Feature activation+1.643
-
Token-
Feature activation+0.698
sided
Tokensided
Feature activation+1.505
hearing
Token hearing
Feature activation+2.771
undermines
Token undermines
Feature activation+0.000
the
Token the
Feature activation+0.000
credibility
Token credibility
Feature activation+0.000

INTERVAL 0.000 - 0.473
CONTAINS 99.944%

fi
Tokenfi
Feature activation+0.000
found
Token found
Feature activation+0.000
-
Token-
Feature activation+0.000
foot
Tokenfoot
Feature activation+0.000
age
Tokenage
Feature activation+0.000
hit
Token hit
Feature activation+0.000
Chronicle
Token Chronicle
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
other
Token other
Feature activation+0.000
uncertainties
Token uncertainties
Feature activation+0.000
remain
Token remain
Feature activation+0.000
.
Token.
Feature activation+0.000
Why
Token Why
Feature activation+0.000
among
Token among
Feature activation+0.000
verte
Token verte
Feature activation+0.000
brates
Tokenbrates
Feature activation+0.000
the
Token the
Feature activation+0.000
boy
Token boy
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
operation
Token operation
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
mother
Token mother
Feature activation+0.000
to
Token to
Feature activation+0.000
read
Token read
Feature activation+0.000
just
Tokenjust
Feature activation+0.000
every
Token every
Feature activation+0.000
time
Token time
Feature activation+0.000
you
Token you
Feature activation+0.000
use
Token use
Feature activation+0.000
the
Token the
Feature activation+0.000
headphones
Token headphones
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token 3
Feature activation+0.000
see
Token see
Feature activation+0.000
infertility
Token infertility
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
curse
Token curse
Feature activation+0.000
alone
Token alone
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
reduce
Token reduce
Feature activation+0.000
fruit
Token fruit
Feature activation+0.000
fulness
Tokenfulness
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 H3.2: (feature 6994)

TOP ACTIVATIONS
MAX = 4.793

come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
realize
Token realize
Feature activation+0.000
how
Token how
Feature activation+0.000
morally
Token morally
Feature activation+3.346
bankrupt
Token bankrupt
Feature activation+4.793
the
Token the
Feature activation+0.000
Rebellion
Token Rebellion
Feature activation+0.000
really
Token really
Feature activation+0.000
is
Token is
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
notice
Token notice
Feature activation+0.000
how
Token how
Feature activation+0.000
devoid
Token devoid
Feature activation+4.761
of
Token of
Feature activation+1.138
trainers
Token trainers
Feature activation+0.000
Route
Token Route
Feature activation+0.000
8
Token 8
Feature activation+0.000
was
Token was
Feature activation+0.000
tell
Token tell
Feature activation+0.000
you
Token you
Feature activation+0.000
how
Token how
Feature activation+0.000
dis
Token dis
Feature activation+3.306
pir
Tokenpir
Feature activation+0.241
iting
Tokeniting
Feature activation+4.689
this
Token this
Feature activation+0.000
delay
Token delay
Feature activation+0.000
is
Token is
Feature activation+0.000
for
Token for
Feature activation+0.000
us
Token us
Feature activation+0.000
really
Token really
Feature activation+0.000
shows
Token shows
Feature activation+0.000
how
Token how
Feature activation+0.000
ideologically
Token ideologically
Feature activation+2.948
wedd
Token wedd
Feature activation+1.438
ed
Tokened
Feature activation+4.585
to
Token to
Feature activation+0.000
climate
Token climate
Feature activation+0.000
denial
Token denial
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
the
Token the
Feature activation+0.000
in
Token in
Feature activation+0.000
awe
Token awe
Feature activation+0.000
of
Token of
Feature activation+0.000
how
Token how
Feature activation+0.133
eloqu
Token eloqu
Feature activation+2.906
ently
Tokenently
Feature activation+4.574
you
Token you
Feature activation+0.894
write
Token write
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
only
Token only
Feature activation+0.000
imagine
Token imagine
Feature activation+0.000
how
Token how
Feature activation+0.000
voc
Token voc
Feature activation+2.024
ifer
Tokenifer
Feature activation+0.841
ous
Tokenous
Feature activation+4.557
they
Token they
Feature activation+0.130
are
Token are
Feature activation+0.000
in
Token in
Feature activation+0.000
private
Token private
Feature activation+0.000
.
Token.
Feature activation+0.000
note
Token note
Feature activation+0.000
how
Token how
Feature activation+0.000
e
Token e
Feature activation+2.258
er
Tokener
Feature activation+0.000
ily
Tokenily
Feature activation+3.303
similar
Token similar
Feature activation+4.406
the
Token the
Feature activation+0.000
charts
Token charts
Feature activation+0.000
for
Token for
Feature activation+0.000
China
Token China
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
of
Token of
Feature activation+0.000
racism
Token racism
Feature activation+0.000
?
Token?
Feature activation+0.000
Remember
Token Remember
Feature activation+0.000
how
Token how
Feature activation+0.000
stupid
Token stupid
Feature activation+4.272
that
Token that
Feature activation+0.479
was
Token was
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
home
Token home
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
just
Token just
Feature activation+0.000
how
Token how
Feature activation+0.000
persuasive
Token persuasive
Feature activation+4.229
and
Token and
Feature activation+1.994
compelling
Token compelling
Feature activation+4.137
that
Token that
Feature activation+2.487
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
me
Token me
Feature activation+0.000
just
Token just
Feature activation+0.000
how
Token how
Feature activation+0.000
persuasive
Token persuasive
Feature activation+4.229
and
Token and
Feature activation+1.994
compelling
Token compelling
Feature activation+4.137
that
Token that
Feature activation+2.487
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
a
Tokena
Feature activation+0.000
usterity
Tokenusterity
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
proved
Token proved
Feature activation+0.000
just
Token just
Feature activation+0.000
how
Token how
Feature activation+0.000
obst
Token obst
Feature activation+3.641
inate
Tokeninate
Feature activation+4.134
those
Token those
Feature activation+0.000
regimes
Token regimes
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
over
Token over
Feature activation+0.000
state
Tokenstate
Feature activation+0.000
just
Token just
Feature activation+0.000
how
Token how
Feature activation+0.000
unlikely
Token unlikely
Feature activation+4.118
a
Token a
Feature activation+0.000
candidate
Token candidate
Feature activation+0.000
Cage
Token Cage
Feature activation+0.000
seemed
Token seemed
Feature activation+0.000
at
Token at
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
incredible
Token incredible
Feature activation+0.000
how
Token how
Feature activation+0.000
easy
Token easy
Feature activation+4.041
it
Token it
Feature activation+2.471
becomes
Token becomes
Feature activation+0.000
to
Token to
Feature activation+0.000
flick
Token flick
Feature activation+0.000
a
Token a
Feature activation+0.000
-
Token-
Feature activation+0.000
quarter
Tokenquarter
Feature activation+0.000
rampage
Token rampage
Feature activation+0.000
showed
Token showed
Feature activation+0.000
how
Token how
Feature activation+0.040
deadly
Token deadly
Feature activation+4.017
he
Token he
Feature activation+0.069
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
front
Token front
Feature activation+0.000
the
Token the
Feature activation+0.000
awareness
Token awareness
Feature activation+0.000
out
Token out
Feature activation+0.000
there
Token there
Feature activation+0.000
how
Token how
Feature activation+0.218
unnecessary
Token unnecessary
Feature activation+4.000
these
Token these
Feature activation+0.000
bottles
Token bottles
Feature activation+0.000
are
Token are
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
no
Token no
Feature activation+0.000
words
Token words
Feature activation+0.000
to
Token to
Feature activation+0.000
describe
Token describe
Feature activation+0.000
how
Token how
Feature activation+0.000
devastating
Token devastating
Feature activation+3.989
and
Token and
Feature activation+0.044
--
Token --
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
completely
Token completely
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
surprised
Token surprised
Feature activation+0.000
how
Token how
Feature activation+0.000
quickly
Token quickly
Feature activation+3.976
it
Token it
Feature activation+1.121
happened
Token happened
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
appreciate
Token appreciate
Feature activation+0.000
just
Token just
Feature activation+0.000
how
Token how
Feature activation+0.000
painful
Token painful
Feature activation+3.588
and
Token and
Feature activation+1.068
frustrating
Token frustrating
Feature activation+3.917
these
Token these
Feature activation+0.000
m
Token m
Feature activation+0.000
add
Tokenadd
Feature activation+0.000
ening
Tokenening
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
-
Token -
Feature activation+0.000
how
Token how
Feature activation+0.000
compatible
Token compatible
Feature activation+3.876
they
Token they
Feature activation+0.061
were
Token were
Feature activation+0.000
with
Token with
Feature activation+0.000
other
Token other
Feature activation+0.000
parties
Token parties
Feature activation+0.000
made
Token made
Feature activation+0.000
a
Token a
Feature activation+0.000
note
Token note
Feature activation+0.000
of
Token of
Feature activation+0.000
how
Token how
Feature activation+0.000
ripe
Token ripe
Feature activation+3.864
for
Token for
Feature activation+0.000
CM
Token CM
Feature activation+0.000
player
Token player
Feature activation+0.000
housing
Token housing
Feature activation+0.000
content
Token content
Feature activation+0.000

Top DFA by src position
MAX = 5.571

,
Token,
Feature activation-0.042
Top resid features:
you
Token you
Feature activation-0.003
Top resid features:
come
Token come
Feature activation-0.040
Top resid features:
to
Token to
Feature activation+0.028
Top resid features:
realize
Token realize
Feature activation-0.050
Top resid features:
how
Token how
Feature activation+5.342
Top resid features:
morally
Token morally
Feature activation+0.152
Top resid features:
bankrupt
Token bankrupt
Feature activation+0.091
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Rebellion
Token Rebellion
Feature activation+0.000
Top resid features:
really
Token really
Feature activation+0.000
Top resid features:
didn
Token didn
Feature activation-0.030
Top resid features:
âĢ
TokenâĢ
Feature activation-0.030
Top resid features:
Ļ
TokenĻ
Feature activation-0.016
Top resid features:
t
Tokent
Feature activation-0.060
Top resid features:
notice
Token notice
Feature activation-0.111
Top resid features:
how
Token how
Feature activation+5.496
Top resid features:
devoid
Token devoid
Feature activation+0.204
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
trainers
Token trainers
Feature activation+0.000
Top resid features:
Route
Token Route
Feature activation+0.000
Top resid features:
8
Token 8
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.019
Top resid features:
Ļ
TokenĻ
Feature activation-0.012
Top resid features:
t
Tokent
Feature activation-0.025
Top resid features:
tell
Token tell
Feature activation-0.036
Top resid features:
you
Token you
Feature activation-0.090
Top resid features:
how
Token how
Feature activation+5.571
Top resid features:
dis
Token dis
Feature activation+0.315
Top resid features:
pir
Tokenpir
Feature activation-0.265
Top resid features:
iting
Tokeniting
Feature activation-0.057
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
delay
Token delay
Feature activation+0.000
Top resid features:
climate
Token climate
Feature activation-0.023
Top resid features:
agreement
Token agreement
Feature activation-0.030
Top resid features:
it
Token it
Feature activation-0.019
Top resid features:
really
Token really
Feature activation-0.007
Top resid features:
shows
Token shows
Feature activation-0.050
Top resid features:
how
Token how
Feature activation+5.150
Top resid features:
ideologically
Token ideologically
Feature activation+0.197
Top resid features:
wedd
Token wedd
Feature activation+0.056
Top resid features:
ed
Tokened
Feature activation-0.016
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
climate
Token climate
Feature activation+0.000
Top resid features:
come
Token come
Feature activation-0.025
Top resid features:
away
Token away
Feature activation-0.003
Top resid features:
in
Token in
Feature activation-0.036
Top resid features:
awe
Token awe
Feature activation-0.010
Top resid features:
of
Token of
Feature activation-0.075
Top resid features:
how
Token how
Feature activation+5.109
Top resid features:
eloqu
Token eloqu
Feature activation+0.271
Top resid features:
ently
Tokenently
Feature activation+0.036
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
write
Token write
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
you
Token you
Feature activation-0.013
Top resid features:
can
Token can
Feature activation-0.021
Top resid features:
only
Token only
Feature activation-0.003
Top resid features:
imagine
Token imagine
Feature activation-0.042
Top resid features:
how
Token how
Feature activation+5.315
Top resid features:
voc
Token voc
Feature activation+0.209
Top resid features:
ifer
Tokenifer
Feature activation-0.032
Top resid features:
ous
Tokenous
Feature activation-0.182
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
impl
Token impl
Feature activation-0.001
Top resid features:
oded
Tokenoded
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.029
Top resid features:
Also
Token Also
Feature activation+0.002
Top resid features:
note
Token note
Feature activation+0.003
Top resid features:
how
Token how
Feature activation+4.988
Top resid features:
e
Token e
Feature activation+0.074
Top resid features:
er
Tokener
Feature activation+0.041
Top resid features:
ily
Tokenily
Feature activation+0.081
Top resid features:
similar
Token similar
Feature activation-0.085
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
era
Token era
Feature activation-0.009
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
racism
Token racism
Feature activation-0.004
Top resid features:
?
Token?
Feature activation+0.039
Top resid features:
Remember
Token Remember
Feature activation+0.004
Top resid features:
how
Token how
Feature activation+5.015
Top resid features:
stupid
Token stupid
Feature activation-0.105
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.031
Top resid features:
home
Token home
Feature activation-0.006
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
me
Token me
Feature activation-0.038
Top resid features:
just
Token just
Feature activation-0.075
Top resid features:
how
Token how
Feature activation+5.307
Top resid features:
persuasive
Token persuasive
Feature activation-0.120
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
compelling
Token compelling
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
anti
Token anti
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.020
Top resid features:
home
Token home
Feature activation-0.023
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
me
Token me
Feature activation-0.038
Top resid features:
just
Token just
Feature activation-0.083
Top resid features:
how
Token how
Feature activation+5.169
Top resid features:
persuasive
Token persuasive
Feature activation-0.068
Top resid features:
and
Token and
Feature activation+0.095
Top resid features:
compelling
Token compelling
Feature activation-0.179
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
anti
Token anti
Feature activation+0.000
Top resid features:
up
Token up
Feature activation-0.003
Top resid features:
ris
Tokenris
Feature activation-0.001
Top resid features:
ings
Tokenings
Feature activation-0.007
Top resid features:
proved
Token proved
Feature activation-0.038
Top resid features:
just
Token just
Feature activation-0.021
Top resid features:
how
Token how
Feature activation+5.006
Top resid features:
obst
Token obst
Feature activation-0.105
Top resid features:
inate
Tokeninate
Feature activation+0.077
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
regimes
Token regimes
Feature activation+0.000
Top resid features:
could
Token could
Feature activation+0.000
Top resid features:
hard
Token hard
Feature activation-0.023
Top resid features:
to
Token to
Feature activation+0.022
Top resid features:
over
Token over
Feature activation+0.003
Top resid features:
state
Tokenstate
Feature activation-0.050
Top resid features:
just
Token just
Feature activation-0.064
Top resid features:
how
Token how
Feature activation+5.129
Top resid features:
unlikely
Token unlikely
Feature activation-0.028
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
candidate
Token candidate
Feature activation+0.000
Top resid features:
Cage
Token Cage
Feature activation+0.000
Top resid features:
seemed
Token seemed
Feature activation+0.000
Top resid features:
weight
Token weight
Feature activation-0.013
Top resid features:
.
Token.
Feature activation-0.060
Top resid features:
It
Token It
Feature activation-0.034
Top resid features:
's
Token's
Feature activation-0.013
Top resid features:
incredible
Token incredible
Feature activation-0.042
Top resid features:
how
Token how
Feature activation+5.269
Top resid features:
easy
Token easy
Feature activation-0.365
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
becomes
Token becomes
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
flick
Token flick
Feature activation+0.000
Top resid features:
fourth
Token fourth
Feature activation-0.020
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
quarter
Tokenquarter
Feature activation+0.014
Top resid features:
rampage
Token rampage
Feature activation-0.025
Top resid features:
showed
Token showed
Feature activation-0.133
Top resid features:
how
Token how
Feature activation+4.985
Top resid features:
deadly
Token deadly
Feature activation-0.180
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
getting
Token getting
Feature activation-0.022
Top resid features:
the
Token the
Feature activation-0.044
Top resid features:
awareness
Token awareness
Feature activation-0.050
Top resid features:
out
Token out
Feature activation-0.022
Top resid features:
there
Token there
Feature activation-0.028
Top resid features:
how
Token how
Feature activation+4.758
Top resid features:
unnecessary
Token unnecessary
Feature activation+0.032
Top resid features:
these
Token these
Feature activation+0.000
Top resid features:
bottles
Token bottles
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
really
Token really
Feature activation+0.003
Top resid features:
no
Token no
Feature activation-0.059
Top resid features:
words
Token words
Feature activation-0.054
Top resid features:
to
Token to
Feature activation+0.021
Top resid features:
describe
Token describe
Feature activation-0.095
Top resid features:
how
Token how
Feature activation+5.245
Top resid features:
devastating
Token devastating
Feature activation-0.401
Top resid features:
and
Token and
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:
'm
Token'm
Feature activation+0.000
Top resid features:
calls
Token calls
Feature activation-0.028
Top resid features:
.
Token.
Feature activation-0.034
Top resid features:
I
Token I
Feature activation+0.024
Top resid features:
was
Token was
Feature activation-0.060
Top resid features:
surprised
Token surprised
Feature activation-0.231
Top resid features:
how
Token how
Feature activation+5.240
Top resid features:
quickly
Token quickly
Feature activation-0.281
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
happened
Token happened
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:
headaches
Token headaches
Feature activation-0.034
Top resid features:
,
Token,
Feature activation-0.036
Top resid features:
most
Token most
Feature activation+0.033
Top resid features:
appreciate
Token appreciate
Feature activation+0.028
Top resid features:
just
Token just
Feature activation-0.080
Top resid features:
how
Token how
Feature activation+5.134
Top resid features:
painful
Token painful
Feature activation-0.394
Top resid features:
and
Token and
Feature activation+0.262
Top resid features:
frustrating
Token frustrating
Feature activation-0.301
Top resid features:
these
Token these
Feature activation+0.000
Top resid features:
m
Token m
Feature activation+0.000
Top resid features:
lines
Token lines
Feature activation+0.008
Top resid features:
,"
Token,"
Feature activation-0.061
Top resid features:
he
Token he
Feature activation-0.015
Top resid features:
said
Token said
Feature activation-0.065
Top resid features:
-
Token -
Feature activation+0.001
Top resid features:
how
Token how
Feature activation+4.711
Top resid features:
compatible
Token compatible
Feature activation-0.079
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.009
Top resid features:
made
Token made
Feature activation-0.071
Top resid features:
a
Token a
Feature activation-0.066
Top resid features:
note
Token note
Feature activation-0.139
Top resid features:
of
Token of
Feature activation-0.114
Top resid features:
how
Token how
Feature activation+4.953
Top resid features:
ripe
Token ripe
Feature activation-0.037
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
CM
Token CM
Feature activation+0.000
Top resid features:
player
Token player
Feature activation+0.000
Top resid features:
housing
Token housing
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.06

Head 2: 0.42

Head 3: 0.04

Head 4: 0.02

Head 5: 0.02

Head 6: 0.07

Head 7: 0.05

Head 8: 0.12

Head 9: 0.03

Head 10: 0.06

Head 11: 0.07

Positive logits

agric1.22

awaited1.12

assembled1.10

fodder1.08

seats1.05

aback1.05

invested1.01

stakes0.99

Dems0.99

wrought0.99

screwed0.98

prizes0.97

chairs0.97

wedd0.97

hoops0.95

guesses0.95

traded0.95

aped0.94

fired0.94

implied0.94

Negative logits

ICA-1.31

-1.18

tyard-1.18

tesy-1.17

FACE-1.11

illery-1.11

Ward-1.09

lance-1.08

INA-1.08

izzle-1.08

ixel-1.08

yi-1.07

unker-1.07

gob-1.06

ِ-1.06

insula-1.06

plane-1.05

vis-1.04

finding-1.04

ocaust-1.04

INTERVAL 4.314 - 4.793
CONTAINS 0.001%

really
Token really
Feature activation+0.000
shows
Token shows
Feature activation+0.000
how
Token how
Feature activation+0.000
ideologically
Token ideologically
Feature activation+2.948
wedd
Token wedd
Feature activation+1.438
ed
Tokened
Feature activation+4.585
to
Token to
Feature activation+0.000
climate
Token climate
Feature activation+0.000
denial
Token denial
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
the
Token the
Feature activation+0.000
note
Token note
Feature activation+0.000
how
Token how
Feature activation+0.000
e
Token e
Feature activation+2.258
er
Tokener
Feature activation+0.000
ily
Tokenily
Feature activation+3.303
similar
Token similar
Feature activation+4.406
the
Token the
Feature activation+0.000
charts
Token charts
Feature activation+0.000
for
Token for
Feature activation+0.000
China
Token China
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
notice
Token notice
Feature activation+0.000
how
Token how
Feature activation+0.000
devoid
Token devoid
Feature activation+4.761
of
Token of
Feature activation+1.138
trainers
Token trainers
Feature activation+0.000
Route
Token Route
Feature activation+0.000
8
Token 8
Feature activation+0.000
was
Token was
Feature activation+0.000
tell
Token tell
Feature activation+0.000
you
Token you
Feature activation+0.000
how
Token how
Feature activation+0.000
dis
Token dis
Feature activation+3.306
pir
Tokenpir
Feature activation+0.241
iting
Tokeniting
Feature activation+4.689
this
Token this
Feature activation+0.000
delay
Token delay
Feature activation+0.000
is
Token is
Feature activation+0.000
for
Token for
Feature activation+0.000
us
Token us
Feature activation+0.000
only
Token only
Feature activation+0.000
imagine
Token imagine
Feature activation+0.000
how
Token how
Feature activation+0.000
voc
Token voc
Feature activation+2.024
ifer
Tokenifer
Feature activation+0.841
ous
Tokenous
Feature activation+4.557
they
Token they
Feature activation+0.130
are
Token are
Feature activation+0.000
in
Token in
Feature activation+0.000
private
Token private
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 3.834 - 4.314
CONTAINS 0.001%

home
Token home
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
just
Token just
Feature activation+0.000
how
Token how
Feature activation+0.000
persuasive
Token persuasive
Feature activation+4.229
and
Token and
Feature activation+1.994
compelling
Token compelling
Feature activation+4.137
that
Token that
Feature activation+2.487
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
no
Token no
Feature activation+0.000
words
Token words
Feature activation+0.000
to
Token to
Feature activation+0.000
describe
Token describe
Feature activation+0.000
how
Token how
Feature activation+0.000
devastating
Token devastating
Feature activation+3.989
and
Token and
Feature activation+0.044
--
Token --
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
completely
Token completely
Feature activation+0.000
appreciate
Token appreciate
Feature activation+0.000
just
Token just
Feature activation+0.000
how
Token how
Feature activation+0.000
painful
Token painful
Feature activation+3.588
and
Token and
Feature activation+1.068
frustrating
Token frustrating
Feature activation+3.917
these
Token these
Feature activation+0.000
m
Token m
Feature activation+0.000
add
Tokenadd
Feature activation+0.000
ening
Tokenening
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
of
Token of
Feature activation+0.000
racism
Token racism
Feature activation+0.000
?
Token?
Feature activation+0.000
Remember
Token Remember
Feature activation+0.000
how
Token how
Feature activation+0.000
stupid
Token stupid
Feature activation+4.272
that
Token that
Feature activation+0.479
was
Token was
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
awareness
Token awareness
Feature activation+0.000
out
Token out
Feature activation+0.000
there
Token there
Feature activation+0.000
how
Token how
Feature activation+0.218
unnecessary
Token unnecessary
Feature activation+4.000
these
Token these
Feature activation+0.000
bottles
Token bottles
Feature activation+0.000
are
Token are
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 3.355 - 3.834
CONTAINS 0.003%

and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
shows
Token shows
Feature activation+0.000
us
Token us
Feature activation+0.000
how
Token how
Feature activation+0.000
little
Token little
Feature activation+3.577
Korra
Token Korra
Feature activation+0.334
deals
Token deals
Feature activation+0.000
with
Token with
Feature activation+0.000
being
Token being
Feature activation+0.000
the
Token the
Feature activation+0.000
ent
Token ent
Feature activation+0.000
hr
Tokenhr
Feature activation+0.000
alled
Tokenalled
Feature activation+0.000
with
Token with
Feature activation+0.000
how
Token how
Feature activation+0.000
dope
Token dope
Feature activation+3.495
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
product
Token product
Feature activation+0.000
is
Token is
Feature activation+0.000
sounding
Token sounding
Feature activation+0.000
open
Token open
Feature activation+0.000
.
Token.
Feature activation+0.000
Because
Token Because
Feature activation+0.000
of
Token of
Feature activation+0.000
how
Token how
Feature activation+0.000
divisive
Token divisive
Feature activation+3.492
his
Token his
Feature activation+0.000
art
Token art
Feature activation+0.000
was
Token was
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
clear
Token clear
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
guests
Token guests
Feature activation+0.000
how
Token how
Feature activation+0.166
aware
Token aware
Feature activation+3.357
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
was
Token was
Feature activation+0.000
of
Token of
Feature activation+0.000
shocked
Token shocked
Feature activation+0.000
and
Token and
Feature activation+0.000
grateful
Token grateful
Feature activation+0.000
for
Token for
Feature activation+0.000
how
Token how
Feature activation+0.000
well
Token well
Feature activation+3.587
the
Token the
Feature activation+1.081
show
Token show
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
received
Token received
Feature activation+0.000

INTERVAL 2.876 - 3.355
CONTAINS 0.004%

First
Token First
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
knows
Token knows
Feature activation+0.000
how
Token how
Feature activation+0.000
accurate
Token accurate
Feature activation+3.284
the
Token the
Feature activation+0.000
probabilities
Token probabilities
Feature activation+0.000
are
Token are
Feature activation+0.000
.
Token.
Feature activation+0.000
Second
Token Second
Feature activation+0.000
is
Token is
Feature activation+0.000
rather
Token rather
Feature activation+0.000
amazing
Token amazing
Feature activation+0.000
just
Token just
Feature activation+0.000
how
Token how
Feature activation+0.000
far
Token far
Feature activation+3.330
the
Token the
Feature activation+0.367
contents
Token contents
Feature activation+0.000
of
Token of
Feature activation+0.000
four
Token four
Feature activation+0.000
basic
Token basic
Feature activation+0.000
ideas
Token ideas
Feature activation+0.000
,
Token,
Feature activation+0.000
no
Token no
Feature activation+0.000
matter
Token matter
Feature activation+0.000
how
Token how
Feature activation+0.000
insane
Token insane
Feature activation+3.206
,
Token,
Feature activation+0.000
enter
Token enter
Feature activation+0.000
the
Token the
Feature activation+0.000
mainstream
Token mainstream
Feature activation+0.000
debate
Token debate
Feature activation+0.000
a
Token a
Feature activation+0.000
far
Token far
Feature activation+0.000
cry
Token cry
Feature activation+0.000
from
Token from
Feature activation+0.000
how
Token how
Feature activation+0.000
deep
Token deep
Feature activation+3.151
they
Token they
Feature activation+0.727
were
Token were
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
was
Token was
Feature activation+0.000
alarmed
Token alarmed
Feature activation+0.000
to
Token to
Feature activation+0.000
learn
Token learn
Feature activation+0.000
how
Token how
Feature activation+0.000
fundamentally
Token fundamentally
Feature activation+3.314
opposed
Token opposed
Feature activation+2.872
Su
Token Su
Feature activation+0.000
f
Tokenf
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 2.396 - 2.876
CONTAINS 0.003%

get
Token get
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
just
Token just
Feature activation+0.000
how
Token how
Feature activation+0.000
big
Token big
Feature activation+2.815
a
Token a
Feature activation+0.000
b
Token b
Feature activation+0.000
osh
Tokenosh
Feature activation+0.000
't
Token't
Feature activation+0.000
et
Tokenet
Feature activation+0.000
players
Token players
Feature activation+0.000
,
Token,
Feature activation+0.000
3
Token 3
Feature activation+0.000
)
Token)
Feature activation+0.000
How
Token How
Feature activation+0.000
religious
Token religious
Feature activation+2.759
and
Token and
Feature activation+1.080
sports
Token sports
Feature activation+0.189
are
Token are
Feature activation+0.155
so
Token so
Feature activation+0.000
often
Token often
Feature activation+0.000
test
Token test
Feature activation+0.000
your
Token your
Feature activation+0.000
patience
Token patience
Feature activation+0.000
for
Token for
Feature activation+0.000
how
Token how
Feature activation+0.000
little
Token little
Feature activation+2.858
action
Token action
Feature activation+0.000
constitutes
Token constitutes
Feature activation+0.000
a
Token a
Feature activation+0.000
"
Token "
Feature activation+0.000
motion
Tokenmotion
Feature activation+0.000
denomin
Token denomin
Feature activation+0.000
ator
Tokenator
Feature activation+0.000
.
Token.
Feature activation+0.000
How
Token How
Feature activation+0.000
ins
Token ins
Feature activation+2.444
ulating
Tokenulating
Feature activation+2.732
#
Token #
Feature activation+0.000
ABC
TokenABC
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Matt
Token Matt
Feature activation+0.000
Falk
Token Falk
Feature activation+0.000
R
Token R
Feature activation+0.000
enton
Tokenenton
Feature activation+0.000
talking
Token talking
Feature activation+0.000
about
Token about
Feature activation+0.000
how
Token how
Feature activation+0.000
good
Token good
Feature activation+2.425
the
Token the
Feature activation+0.319
drugs
Token drugs
Feature activation+0.000
make
Token make
Feature activation+0.000
him
Token him
Feature activation+0.000
feel
Token feel
Feature activation+0.000

INTERVAL 1.917 - 2.396
CONTAINS 0.004%

It
Token It
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
't
Token't
Feature activation+0.000
matter
Token matter
Feature activation+0.000
how
Token how
Feature activation+0.000
often
Token often
Feature activation+2.131
he
Token he
Feature activation+0.000
shot
Token shot
Feature activation+0.000
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.000
what
Token what
Feature activation+0.000
classrooms
Token classrooms
Feature activation+0.000
,
Token,
Feature activation+0.000
no
Token no
Feature activation+0.000
matter
Token matter
Feature activation+0.000
how
Token how
Feature activation+0.000
important
Token important
Feature activation+2.251
some
Token some
Feature activation+0.000
say
Token say
Feature activation+0.000
these
Token these
Feature activation+0.000
novels
Token novels
Feature activation+0.000
and
Token and
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
know
Token know
Feature activation+0.000
how
Token how
Feature activation+0.000
long
Token long
Feature activation+1.974
I
Token I
Feature activation+1.575
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
going
Token going
Feature activation+0.000
't
Token't
Feature activation+0.000
biting
Token biting
Feature activation+0.000
on
Token on
Feature activation+0.000
how
Token how
Feature activation+0.000
much
Token much
Feature activation+1.586
fun
Token fun
Feature activation+2.182
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
having
Token having
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
cat
Tokencat
Feature activation+0.000
has
Token has
Feature activation+0.000
published
Token published
Feature activation+0.000
several
Token several
Feature activation+0.000
how
Token how
Feature activation+0.000
-
Token-
Feature activation+2.308
to
Tokento
Feature activation+0.000
guides
Token guides
Feature activation+0.400
to
Token to
Feature activation+0.000
for
Token for
Feature activation+0.000
beginning
Token beginning
Feature activation+0.000

INTERVAL 1.438 - 1.917
CONTAINS 0.004%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
sure
Token sure
Feature activation+0.000
how
Token how
Feature activation+0.000
much
Token much
Feature activation+1.722
Christie
Token Christie
Feature activation+0.000
knew
Token knew
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
issues
Token issues
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
know
Token know
Feature activation+0.000
how
Token how
Feature activation+0.000
long
Token long
Feature activation+1.974
I
Token I
Feature activation+1.575
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
s
Tokens
Feature activation+0.000
that
Token that
Feature activation+0.000
know
Token know
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
how
Token how
Feature activation+0.000
long
Token long
Feature activation+1.892
to
Token to
Feature activation+0.000
cook
Token cook
Feature activation+0.000
your
Token your
Feature activation+0.000
food
Token food
Feature activation+0.000
:
Token:
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
Lord
TokenLord
Feature activation+0.000
,
Token,
Feature activation+0.000
how
Token how
Feature activation+0.000
oft
Token oft
Feature activation+1.484
shall
Token shall
Feature activation+0.000
my
Token my
Feature activation+0.000
brother
Token brother
Feature activation+0.000
sin
Token sin
Feature activation+0.000
against
Token against
Feature activation+0.000
scenes
Token scenes
Feature activation+0.000
together
Token together
Feature activation+0.000
that
Token that
Feature activation+0.000
showed
Token showed
Feature activation+0.000
how
Token how
Feature activation+0.000
much
Token much
Feature activation+1.445
they
Token they
Feature activation+0.388
cared
Token cared
Feature activation+0.000
for
Token for
Feature activation+0.000
each
Token each
Feature activation+0.000
other
Token other
Feature activation+0.000

INTERVAL 0.959 - 1.438
CONTAINS 0.008%

of
Tokenof
Feature activation+0.000
ors
Tokenors
Feature activation+0.000
how
Token how
Feature activation+0.000
itz
Tokenitz
Feature activation+1.163
ers
Tokeners
Feature activation+0.136
,
Token,
Feature activation+0.963
no
Token no
Feature activation+0.000
Ak
Token Ak
Feature activation+0.000
ash
Tokenash
Feature activation+0.000
surface
Token surface
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Token to
Feature activation+0.000
show
Token show
Feature activation+0.000
jurors
Token jurors
Feature activation+0.000
how
Token how
Feature activation+0.000
severely
Token severely
Feature activation+3.188
it
Token it
Feature activation+1.435
limited
Token limited
Feature activation+0.148
its
Token its
Feature activation+0.000
occupant
Token occupant
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
my
Token my
Feature activation+0.000
friends
Token friends
Feature activation+0.000
think
Token think
Feature activation+0.000
?
Token?
Feature activation+0.000
How
Token How
Feature activation+0.000
will
Token will
Feature activation+1.292
I
Token I
Feature activation+0.000
be
Token be
Feature activation+0.000
received
Token received
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
of
Token of
Feature activation+0.000
which
Token which
Feature activation+0.000
answer
Token answer
Feature activation+0.000
:
Token:
Feature activation+0.000
How
Token How
Feature activation+0.000
difficult
Token difficult
Feature activation+1.196
will
Token will
Feature activation+0.000
it
Token it
Feature activation+0.000
be
Token be
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
work
Token work
Feature activation+0.000
out
Token out
Feature activation+0.000
how
Token how
Feature activation+0.000
much
Token much
Feature activation+1.144
land
Token land
Feature activation+0.000
would
Token would
Feature activation+0.604
be
Token be
Feature activation+0.000
required
Token required
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.479 - 0.959
CONTAINS 0.015%

how
Token how
Feature activation+0.000
it
Token it
Feature activation+0.443
works
Token works
Feature activation+0.000
,
Token,
Feature activation+0.000
how
Token how
Feature activation+0.505
it
Token it
Feature activation+0.510
is
Token is
Feature activation+0.000
deployed
Token deployed
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
books
Token books
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
-
Token-
Feature activation+1.085
to
Tokento
Feature activation+0.000
videos
Token videos
Feature activation+0.521
and
Token and
Feature activation+0.000
DVDs
Token DVDs
Feature activation+0.450
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
tools
Token tools
Feature activation+0.000
to
Token to
Feature activation+0.000
figure
Token figure
Feature activation+0.000
out
Token out
Feature activation+0.000
--
Token --
Feature activation+0.000
how
Token how
Feature activation+0.000
can
Token can
Feature activation+0.938
something
Token something
Feature activation+0.000
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
90
Token 90
Feature activation+0.000
percent
Token percent
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
survive
Token survive
Feature activation+0.000
.
Token.
Feature activation+0.000
How
Token How
Feature activation+0.000
?
Token?
Feature activation+0.554
Ċ
TokenĊ
Feature activation+1.320
Ċ
TokenĊ
Feature activation+0.852
Road
TokenRoad
Feature activation+0.000
s
Tokens
Feature activation+0.000
and
Token and
Feature activation+0.000
awe
Token awe
Feature activation+0.000
of
Token of
Feature activation+0.000
how
Token how
Feature activation+0.133
eloqu
Token eloqu
Feature activation+2.906
ently
Tokenently
Feature activation+4.574
you
Token you
Feature activation+0.894
write
Token write
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
you
Token you
Feature activation+0.000

INTERVAL 0.000 - 0.479
CONTAINS 99.957%

reason
Token reason
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
crash
Token crash
Feature activation+0.000
?
Token?
Feature activation+0.000
A
Token A
Feature activation+0.000
17
Token 17
Feature activation+0.000
-
Token-
Feature activation+0.000
inch
Tokeninch
Feature activation+0.000
metal
Token metal
Feature activation+0.000
strip
Token strip
Feature activation+0.000
inter
Tokeninter
Feature activation+0.000
by
Token by
Feature activation+0.000
Berg
Token Berg
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Raspberry
Token Raspberry
Feature activation+0.000
Pi
Token Pi
Feature activation+0.000
computer
Token computer
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
go
Token go
Feature activation+0.000
be
Token be
Feature activation+0.000
OK
Token OK
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Sgt
Token Sgt
Feature activation+0.000
.
Token.
Feature activation+0.000
Anna
Token Anna
Feature activation+0.000
Rose
Token Rose
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
U
Token U
Feature activation+0.000
all
Token all
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
depending
Token depending
Feature activation+0.000
on
Token on
Feature activation+0.000
what
Token what
Feature activation+0.000
happens
Token happens
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
may
Token may
Feature activation+0.000
or
Token or
Feature activation+0.000
've
Token've
Feature activation+0.000
never
Token never
Feature activation+0.000
heard
Token heard
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
before
Token before
Feature activation+0.000
."
Token."
Feature activation+0.000
Let
Token Let
Feature activation+0.000
down
Token down
Feature activation+0.000
,
Token,
Feature activation+0.000
indeed
Token indeed
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 H3.2: (feature 15788)

TOP ACTIVATIONS
MAX = 2.939

International
Token International
Feature activation+0.000
Tournament
Token Tournament
Feature activation+0.000
from
Token from
Feature activation+0.000
Oct
Token Oct
Feature activation+1.631
.
Token.
Feature activation+1.657
1
Token 1
Feature activation+2.939
-
Token-
Feature activation+2.613
5
Token5
Feature activation+0.092
.
Token.
Feature activation+0.229
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
will
Token will
Feature activation+0.000
appear
Token appear
Feature activation+0.000
from
Token from
Feature activation+0.000
9
Token 9
Feature activation+1.028
âĢĵ
TokenâĢĵ
Feature activation+2.899
10
Token10
Feature activation+0.000
:
Token:
Feature activation+0.000
30
Token30
Feature activation+0.000
a
Token a
Feature activation+0.468
.
Token.
Feature activation+0.000
Finland
Token Finland
Feature activation+0.000
from
Token from
Feature activation+0.000
Dec
Token Dec
Feature activation+0.948
.
Token.
Feature activation+2.009
26
Token 26
Feature activation+2.694
,
Token,
Feature activation+2.705
2015
Token 2015
Feature activation+2.024
,
Token,
Feature activation+1.648
through
Token through
Feature activation+0.868
Jan
Token Jan
Feature activation+0.000
.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
Finland
Token Finland
Feature activation+0.000
from
Token from
Feature activation+0.000
Dec
Token Dec
Feature activation+0.948
.
Token.
Feature activation+2.009
26
Token 26
Feature activation+2.694
,
Token,
Feature activation+2.705
2015
Token 2015
Feature activation+2.024
,
Token,
Feature activation+1.648
through
Token through
Feature activation+0.868
Jan
Token Jan
Feature activation+0.000
will
Token will
Feature activation+0.000
throw
Token throw
Feature activation+0.000
anywhere
Token anywhere
Feature activation+0.000
from
Token from
Feature activation+0.000
92
Token 92
Feature activation+1.518
-
Token-
Feature activation+2.654
94
Token94
Feature activation+0.000
,
Token,
Feature activation+0.331
with
Token with
Feature activation+0.000
W
Token W
Feature activation+0.000
ahl
Tokenahl
Feature activation+0.000
ts
Tokents
Feature activation+0.000
were
Token were
Feature activation+0.000
made
Token made
Feature activation+0.000
from
Token from
Feature activation+0.000
18
Token 18
Feature activation+1.492
82
Token82
Feature activation+2.621
on
Token on
Feature activation+1.317
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
S
Token S
Feature activation+0.000
ared
Tokenared
Feature activation+0.000
Tournament
Token Tournament
Feature activation+0.000
from
Token from
Feature activation+0.000
Oct
Token Oct
Feature activation+1.631
.
Token.
Feature activation+1.657
1
Token 1
Feature activation+2.939
-
Token-
Feature activation+2.613
5
Token5
Feature activation+0.092
.
Token.
Feature activation+0.229
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Se
TokenSe
Feature activation+0.000
ager
Tokenager
Feature activation+0.000
from
Token from
Feature activation+0.000
2018
Token 2018
Feature activation+0.742
-
Token-
Feature activation+2.563
21
Token21
Feature activation+0.640
,
Token,
Feature activation+1.242
his
Token his
Feature activation+0.000
ages
Token ages
Feature activation+0.000
30
Token 30
Feature activation+0.000
reason
Token reason
Feature activation+0.000
Dallas
Token Dallas
Feature activation+0.000
slumped
Token slumped
Feature activation+0.000
from
Token from
Feature activation+0.000
12
Token 12
Feature activation+1.634
-
Token-
Feature activation+2.462
4
Token4
Feature activation+0.000
to
Token to
Feature activation+0.014
4
Token 4
Feature activation+0.000
-
Token-
Feature activation+0.000
12
Token12
Feature activation+0.000
with
Token with
Feature activation+0.000
five
Token five
Feature activation+0.000
fellow
Token fellow
Feature activation+0.000
migrants
Token migrants
Feature activation+0.000
from
Token from
Feature activation+0.000
Bangladesh
Token Bangladesh
Feature activation+2.385
,
Token,
Feature activation+1.237
India
Token India
Feature activation+0.264
and
Token and
Feature activation+0.000
Nepal
Token Nepal
Feature activation+0.000
.
Token.
Feature activation+0.000
shut
Token shut
Feature activation+0.000
down
Token down
Feature activation+0.000
from
Token from
Feature activation+0.000
Dec
Token Dec
Feature activation+0.732
.
Token.
Feature activation+0.763
1
Token 1
Feature activation+2.378
,
Token,
Feature activation+1.827
2015
Token 2015
Feature activation+1.431
,
Token,
Feature activation+1.014
to
Token to
Feature activation+0.884
Feb
Token Feb
Feature activation+0.000
drop
Token drop
Feature activation+0.000
from
Token from
Feature activation+0.000
39
Token 39
Feature activation+0.019
.
Token.
Feature activation+0.000
6
Token6
Feature activation+0.210
percent
Token percent
Feature activation+2.361
to
Token to
Feature activation+0.917
25
Token 25
Feature activation+0.000
percent
Token percent
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
a
Token a
Feature activation+0.000
talented
Token talented
Feature activation+0.000
RB
Token RB
Feature activation+0.000
from
Token from
Feature activation+0.000
Ohio
Token Ohio
Feature activation+1.055
State
Token State
Feature activation+2.336
.
Token.
Feature activation+0.000
Why
Token Why
Feature activation+0.000
Jones
Token Jones
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
tax
Token tax
Feature activation+0.000
on
Token on
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
from
Token from
Feature activation+0.000
10
Token 10
Feature activation+1.198
%
Token%
Feature activation+2.319
to
Token to
Feature activation+1.157
8
Token 8
Feature activation+0.000
%
Token%
Feature activation+0.000
beginning
Token beginning
Feature activation+0.000
July
Token July
Feature activation+0.000
months
Token months
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
$
Token $
Feature activation+1.204
91
Token91
Feature activation+0.507
million
Token million
Feature activation+2.316
in
Token in
Feature activation+1.323
January
Token January
Feature activation+0.449
to
Token to
Feature activation+0.544
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
up
Token up
Feature activation+0.000
from
Token from
Feature activation+0.000
58
Token 58
Feature activation+1.156
.
Token.
Feature activation+0.738
4
Token4
Feature activation+0.369
percent
Token percent
Feature activation+2.288
in
Token in
Feature activation+1.267
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
quarter
Token quarter
Feature activation+0.000
but
Token but
Feature activation+0.000
will
Token will
Feature activation+0.000
take
Token take
Feature activation+0.000
place
Token place
Feature activation+0.000
from
Token from
Feature activation+0.000
Nov
Token Nov
Feature activation+1.259
27
Token 27
Feature activation+2.281
to
Token to
Feature activation+1.110
30
Token 30
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
all
Token all
Feature activation+0.000
served
Token served
Feature activation+0.000
from
Token from
Feature activation+0.000
tap
Token tap
Feature activation+1.091
âĢĵ
Token âĢĵ
Feature activation+2.250
were
Token were
Feature activation+0.311
beautiful
Token beautiful
Feature activation+0.000
as
Token as
Feature activation+0.000
always
Token always
Feature activation+0.000
.
Token.
Feature activation+0.000
it
Token it
Feature activation+0.000
ran
Token ran
Feature activation+0.000
from
Token from
Feature activation+0.000
Feb
Token Feb
Feature activation+1.741
.
Token.
Feature activation+1.236
18
Token 18
Feature activation+2.241
to
Token to
Feature activation+1.443
22
Token 22
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
from
Token from
Feature activation+0.000
August
Token August
Feature activation+1.624
18
Token 18
Feature activation+1.963
71
Token71
Feature activation+2.217
,
Token,
Feature activation+1.598
he
Token he
Feature activation+0.000
told
Token told
Feature activation+0.000
her
Token her
Feature activation+0.000
of
Token of
Feature activation+0.000

Top DFA by src position
MAX = 3.280

U
Token U
Feature activation+0.014
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
17
Token17
Feature activation+0.016
Top resid features:
International
Token International
Feature activation+0.010
Top resid features:
Tournament
Token Tournament
Feature activation+0.050
Top resid features:
from
Token from
Feature activation+3.120
Top resid features:
Oct
Token Oct
Feature activation-0.035
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
1
Token 1
Feature activation+0.186
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
5
Token5
Feature activation+0.000
Top resid features:
orn
Tokenorn
Feature activation+0.004
Top resid features:
career
Token career
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
will
Token will
Feature activation+0.029
Top resid features:
appear
Token appear
Feature activation+0.017
Top resid features:
from
Token from
Feature activation+3.280
Top resid features:
9
Token 9
Feature activation+0.082
Top resid features:
âĢĵ
TokenâĢĵ
Feature activation-0.022
Top resid features:
10
Token10
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
30
Token30
Feature activation+0.000
Top resid features:
World
Token World
Feature activation+0.008
Top resid features:
Junior
Token Junior
Feature activation+0.036
Top resid features:
Championship
Token Championship
Feature activation+0.037
Top resid features:
in
Token in
Feature activation+0.013
Top resid features:
Finland
Token Finland
Feature activation+0.072
Top resid features:
from
Token from
Feature activation+2.963
Top resid features:
Dec
Token Dec
Feature activation+0.017
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
26
Token 26
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
2015
Token 2015
Feature activation+0.000
Top resid features:
World
Token World
Feature activation+0.008
Top resid features:
Junior
Token Junior
Feature activation+0.019
Top resid features:
Championship
Token Championship
Feature activation+0.029
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
Finland
Token Finland
Feature activation+0.032
Top resid features:
from
Token from
Feature activation+3.057
Top resid features:
Dec
Token Dec
Feature activation+0.015
Top resid features:
.
Token.
Feature activation-0.020
Top resid features:
26
Token 26
Feature activation+0.056
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
2015
Token 2015
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.000
Top resid features:
ers
Tokeners
Feature activation-0.000
Top resid features:
will
Token will
Feature activation+0.007
Top resid features:
throw
Token throw
Feature activation+0.002
Top resid features:
anywhere
Token anywhere
Feature activation+0.052
Top resid features:
from
Token from
Feature activation+2.869
Top resid features:
92
Token 92
Feature activation+0.280
Top resid features:
-
Token-
Feature activation-0.065
Top resid features:
94
Token94
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
man
Token man
Feature activation+0.013
Top resid features:
hun
Tokenhun
Feature activation+0.005
Top resid features:
ts
Tokents
Feature activation+0.008
Top resid features:
were
Token were
Feature activation-0.002
Top resid features:
made
Token made
Feature activation+0.006
Top resid features:
from
Token from
Feature activation+2.983
Top resid features:
18
Token 18
Feature activation-0.082
Top resid features:
82
Token82
Feature activation+0.184
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
U
Token U
Feature activation+0.012
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
17
Token17
Feature activation+0.012
Top resid features:
International
Token International
Feature activation+0.010
Top resid features:
Tournament
Token Tournament
Feature activation+0.033
Top resid features:
from
Token from
Feature activation+2.924
Top resid features:
Oct
Token Oct
Feature activation+0.120
Top resid features:
.
Token.
Feature activation-0.029
Top resid features:
1
Token 1
Feature activation+0.038
Top resid features:
-
Token-
Feature activation-0.075
Top resid features:
5
Token5
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Se
TokenSe
Feature activation+0.008
Top resid features:
ager
Tokenager
Feature activation+0.010
Top resid features:
from
Token from
Feature activation+3.037
Top resid features:
2018
Token 2018
Feature activation+0.025
Top resid features:
-
Token-
Feature activation-0.011
Top resid features:
21
Token21
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
primary
Token primary
Feature activation+0.006
Top resid features:
reason
Token reason
Feature activation+0.002
Top resid features:
Dallas
Token Dallas
Feature activation+0.025
Top resid features:
slumped
Token slumped
Feature activation-0.007
Top resid features:
from
Token from
Feature activation+2.953
Top resid features:
12
Token 12
Feature activation-0.060
Top resid features:
-
Token-
Feature activation+0.015
Top resid features:
4
Token4
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
4
Token 4
Feature activation+0.000
Top resid features:
afternoon
Token afternoon
Feature activation+0.031
Top resid features:
with
Token with
Feature activation-0.006
Top resid features:
five
Token five
Feature activation-0.008
Top resid features:
fellow
Token fellow
Feature activation+0.025
Top resid features:
migrants
Token migrants
Feature activation+0.044
Top resid features:
from
Token from
Feature activation+2.625
Top resid features:
Bangladesh
Token Bangladesh
Feature activation+0.250
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
India
Token India
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Nepal
Token Nepal
Feature activation+0.000
Top resid features:
show
Token show
Feature activation-0.003
Top resid features:
ultimately
Token ultimately
Feature activation+0.002
Top resid features:
was
Token was
Feature activation-0.003
Top resid features:
shut
Token shut
Feature activation-0.004
Top resid features:
down
Token down
Feature activation-0.008
Top resid features:
from
Token from
Feature activation+2.804
Top resid features:
Dec
Token Dec
Feature activation+0.053
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
1
Token 1
Feature activation+0.140
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
2015
Token 2015
Feature activation+0.000
Top resid features:
income
Token income
Feature activation-0.003
Top resid features:
tax
Token tax
Feature activation-0.002
Top resid features:
rate
Token rate
Feature activation-0.017
Top resid features:
would
Token would
Feature activation-0.012
Top resid features:
drop
Token drop
Feature activation-0.164
Top resid features:
from
Token from
Feature activation+3.059
Top resid features:
39
Token 39
Feature activation+0.154
Top resid features:
.
Token.
Feature activation-0.081
Top resid features:
6
Token6
Feature activation-0.021
Top resid features:
percent
Token percent
Feature activation-0.024
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Elliott
Token Elliott
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
a
Token a
Feature activation-0.010
Top resid features:
talented
Token talented
Feature activation+0.014
Top resid features:
RB
Token RB
Feature activation+0.029
Top resid features:
from
Token from
Feature activation+2.668
Top resid features:
Ohio
Token Ohio
Feature activation+0.102
Top resid features:
State
Token State
Feature activation-0.014
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Why
Token Why
Feature activation+0.000
Top resid features:
Jones
Token Jones
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.014
Top resid features:
sales
Token sales
Feature activation+0.001
Top resid features:
tax
Token tax
Feature activation-0.017
Top resid features:
on
Token on
Feature activation-0.043
Top resid features:
marijuana
Token marijuana
Feature activation+0.009
Top resid features:
from
Token from
Feature activation+3.053
Top resid features:
10
Token 10
Feature activation+0.008
Top resid features:
%
Token%
Feature activation+0.013
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
8
Token 8
Feature activation+0.000
Top resid features:
%
Token%
Feature activation+0.000
Top resid features:
less
Token less
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.015
Top resid features:
six
Token six
Feature activation-0.004
Top resid features:
months
Token months
Feature activation+0.034
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
from
Token from
Feature activation+2.802
Top resid features:
$
Token $
Feature activation+0.063
Top resid features:
91
Token91
Feature activation+0.001
Top resid features:
million
Token million
Feature activation-0.056
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
January
Token January
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.134
Top resid features:
ownership
Token ownership
Feature activation-0.001
Top resid features:
is
Token is
Feature activation+0.009
Top resid features:
up
Token up
Feature activation-0.244
Top resid features:
from
Token from
Feature activation+3.162
Top resid features:
58
Token 58
Feature activation+0.099
Top resid features:
.
Token.
Feature activation-0.156
Top resid features:
4
Token4
Feature activation-0.046
Top resid features:
percent
Token percent
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
it
Token it
Feature activation+0.009
Top resid features:
will
Token will
Feature activation+0.023
Top resid features:
take
Token take
Feature activation+0.001
Top resid features:
place
Token place
Feature activation-0.001
Top resid features:
from
Token from
Feature activation+2.575
Top resid features:
Nov
Token Nov
Feature activation+0.069
Top resid features:
27
Token 27
Feature activation+0.052
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
30
Token 30
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
illon
Tokenillon
Feature activation+0.002
Top resid features:
beers
Token beers
Feature activation+0.004
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.010
Top resid features:
all
Token all
Feature activation-0.034
Top resid features:
served
Token served
Feature activation+0.015
Top resid features:
from
Token from
Feature activation+2.683
Top resid features:
tap
Token tap
Feature activation+0.036
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.009
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
beautiful
Token beautiful
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.026
Top resid features:
this
Token this
Feature activation+0.013
Top resid features:
year
Token year
Feature activation+0.021
Top resid features:
it
Token it
Feature activation+0.004
Top resid features:
ran
Token ran
Feature activation-0.029
Top resid features:
from
Token from
Feature activation+2.651
Top resid features:
Feb
Token Feb
Feature activation+0.038
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
18
Token 18
Feature activation+0.012
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
22
Token 22
Feature activation+0.000
Top resid features:
surviving
Token surviving
Feature activation+0.007
Top resid features:
letter
Token letter
Feature activation+0.028
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
his
Token his
Feature activation+0.021
Top resid features:
wife
Token wife
Feature activation+0.091
Top resid features:
from
Token from
Feature activation+2.382
Top resid features:
August
Token August
Feature activation+0.114
Top resid features:
18
Token 18
Feature activation-0.085
Top resid features:
71
Token71
Feature activation+0.193
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.03

Head 2: 0.42

Head 3: 0.03

Head 4: 0.02

Head 5: 0.03

Head 6: 0.05

Head 7: 0.05

Head 8: 0.11

Head 9: 0.08

Head 10: 0.07

Head 11: 0.07

Positive logits

standpoint1.42

ratch1.42

onwards1.30

obscurity1.22

onward1.10

Tours1.10

confines1.07

bondage1.06

outset1.01

Mormonism1.01

sources1.00

breeding0.99

fulfillment0.98

heights0.97

uania0.97

unknown0.96

Qatar0.96

perspective0.95

taboola0.95

vantage0.94

Negative logits

upd-1.40

awa-1.15

Sov-1.13

effic-1.12

inn-1.12

-1.08

fram-1.08

acci-1.07

aper-1.06

herty-1.06

-1.06

ウス-1.04

-1.02

berra-1.01

natureconservancy-1.01

Polic-0.99

seys-0.99

IONS-0.99

Els-0.97

iour-0.97

INTERVAL 2.645 - 2.939
CONTAINS 0.001%

International
Token International
Feature activation+0.000
Tournament
Token Tournament
Feature activation+0.000
from
Token from
Feature activation+0.000
Oct
Token Oct
Feature activation+1.631
.
Token.
Feature activation+1.657
1
Token 1
Feature activation+2.939
-
Token-
Feature activation+2.613
5
Token5
Feature activation+0.092
.
Token.
Feature activation+0.229
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
will
Token will
Feature activation+0.000
appear
Token appear
Feature activation+0.000
from
Token from
Feature activation+0.000
9
Token 9
Feature activation+1.028
âĢĵ
TokenâĢĵ
Feature activation+2.899
10
Token10
Feature activation+0.000
:
Token:
Feature activation+0.000
30
Token30
Feature activation+0.000
a
Token a
Feature activation+0.468
.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
Finland
Token Finland
Feature activation+0.000
from
Token from
Feature activation+0.000
Dec
Token Dec
Feature activation+0.948
.
Token.
Feature activation+2.009
26
Token 26
Feature activation+2.694
,
Token,
Feature activation+2.705
2015
Token 2015
Feature activation+2.024
,
Token,
Feature activation+1.648
through
Token through
Feature activation+0.868
Jan
Token Jan
Feature activation+0.000
Finland
Token Finland
Feature activation+0.000
from
Token from
Feature activation+0.000
Dec
Token Dec
Feature activation+0.948
.
Token.
Feature activation+2.009
26
Token 26
Feature activation+2.694
,
Token,
Feature activation+2.705
2015
Token 2015
Feature activation+2.024
,
Token,
Feature activation+1.648
through
Token through
Feature activation+0.868
Jan
Token Jan
Feature activation+0.000
.
Token.
Feature activation+0.000
will
Token will
Feature activation+0.000
throw
Token throw
Feature activation+0.000
anywhere
Token anywhere
Feature activation+0.000
from
Token from
Feature activation+0.000
92
Token 92
Feature activation+1.518
-
Token-
Feature activation+2.654
94
Token94
Feature activation+0.000
,
Token,
Feature activation+0.331
with
Token with
Feature activation+0.000
W
Token W
Feature activation+0.000
ahl
Tokenahl
Feature activation+0.000

INTERVAL 2.351 - 2.645
CONTAINS 0.001%

reason
Token reason
Feature activation+0.000
Dallas
Token Dallas
Feature activation+0.000
slumped
Token slumped
Feature activation+0.000
from
Token from
Feature activation+0.000
12
Token 12
Feature activation+1.634
-
Token-
Feature activation+2.462
4
Token4
Feature activation+0.000
to
Token to
Feature activation+0.014
4
Token 4
Feature activation+0.000
-
Token-
Feature activation+0.000
12
Token12
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Se
TokenSe
Feature activation+0.000
ager
Tokenager
Feature activation+0.000
from
Token from
Feature activation+0.000
2018
Token 2018
Feature activation+0.742
-
Token-
Feature activation+2.563
21
Token21
Feature activation+0.640
,
Token,
Feature activation+1.242
his
Token his
Feature activation+0.000
ages
Token ages
Feature activation+0.000
30
Token 30
Feature activation+0.000
drop
Token drop
Feature activation+0.000
from
Token from
Feature activation+0.000
39
Token 39
Feature activation+0.019
.
Token.
Feature activation+0.000
6
Token6
Feature activation+0.210
percent
Token percent
Feature activation+2.361
to
Token to
Feature activation+0.917
25
Token 25
Feature activation+0.000
percent
Token percent
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
shut
Token shut
Feature activation+0.000
down
Token down
Feature activation+0.000
from
Token from
Feature activation+0.000
Dec
Token Dec
Feature activation+0.732
.
Token.
Feature activation+0.763
1
Token 1
Feature activation+2.378
,
Token,
Feature activation+1.827
2015
Token 2015
Feature activation+1.431
,
Token,
Feature activation+1.014
to
Token to
Feature activation+0.884
Feb
Token Feb
Feature activation+0.000
ts
Tokents
Feature activation+0.000
were
Token were
Feature activation+0.000
made
Token made
Feature activation+0.000
from
Token from
Feature activation+0.000
18
Token 18
Feature activation+1.492
82
Token82
Feature activation+2.621
on
Token on
Feature activation+1.317
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
S
Token S
Feature activation+0.000
ared
Tokenared
Feature activation+0.000

INTERVAL 2.057 - 2.351
CONTAINS 0.002%

his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
from
Token from
Feature activation+0.000
August
Token August
Feature activation+1.624
18
Token 18
Feature activation+1.963
71
Token71
Feature activation+2.217
,
Token,
Feature activation+1.598
he
Token he
Feature activation+0.000
told
Token told
Feature activation+0.000
her
Token her
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Korean
Token Korean
Feature activation+0.000
War
Token War
Feature activation+0.000
from
Token from
Feature activation+0.000
August
Token August
Feature activation+1.712
15
Token 15
Feature activation+2.209
to
Token to
Feature activation+1.923
September
Token September
Feature activation+0.000
19
Token 19
Feature activation+0.000
,
Token,
Feature activation+0.178
1950
Token 1950
Feature activation+0.000
was
Token was
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
from
Token from
Feature activation+0.000
2009
Token 2009
Feature activation+2.081
to
Token to
Feature activation+1.578
2013
Token 2013
Feature activation+0.000
,
Token,
Feature activation+0.000
starting
Token starting
Feature activation+0.000
with
Token with
Feature activation+0.000
Irish
TokenIrish
Feature activation+0.000
insurrection
Token insurrection
Feature activation+0.000
lasted
Token lasted
Feature activation+0.000
from
Token from
Feature activation+0.000
1915
Token 1915
Feature activation+1.901
until
Token until
Feature activation+2.182
1998
Token 1998
Feature activation+0.000
without
Token without
Feature activation+0.031
a
Token a
Feature activation+0.000
military
Token military
Feature activation+0.000
victory
Token victory
Feature activation+0.000
up
Token up
Feature activation+0.000
from
Token from
Feature activation+0.000
58
Token 58
Feature activation+1.156
.
Token.
Feature activation+0.738
4
Token4
Feature activation+0.369
percent
Token percent
Feature activation+2.288
in
Token in
Feature activation+1.267
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
quarter
Token quarter
Feature activation+0.000
but
Token but
Feature activation+0.000

INTERVAL 1.763 - 2.057
CONTAINS 0.006%

of
Token of
Feature activation+0.000
143
Token 143
Feature activation+0.000
flights
Token flights
Feature activation+0.000
from
Token from
Feature activation+0.000
September
Token September
Feature activation+1.457
1
Token 1
Feature activation+1.927
st
Tokenst
Feature activation+1.984
âĢĵ
Token âĢĵ
Feature activation+1.950
7
Token 7
Feature activation+0.000
th
Tokenth
Feature activation+0.000
.
Token.
Feature activation+0.000
on
Tokenon
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
1963
Token 1963
Feature activation+1.932
-
Token-
Feature activation+1.938
65
Token65
Feature activation+0.598
,
Token,
Feature activation+1.421
Col
Token Col
Feature activation+0.000
.
Token.
Feature activation+0.000
American
Token American
Feature activation+0.000
community
Token community
Feature activation+0.000
from
Token from
Feature activation+0.000
across
Token across
Feature activation+1.866
the
Token the
Feature activation+0.000
country
Token country
Feature activation+1.909
,
Token,
Feature activation+0.794
senior
Token senior
Feature activation+0.000
Indian
Token Indian
Feature activation+0.000
American
Token American
Feature activation+0.000
staffers
Token staffers
Feature activation+0.000
utilities
Token utilities
Feature activation+0.000
in
Token in
Feature activation+0.000
Puerto
Token Puerto
Feature activation+0.000
Rico
Token Rico
Feature activation+0.000
from
Token from
Feature activation+0.000
declaring
Token declaring
Feature activation+1.912
bankruptcy
Token bankruptcy
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
allowing
Token allowing
Feature activation+0.000
those
Token those
Feature activation+0.000
Panthers
Token Panthers
Feature activation+0.000
go
Token go
Feature activation+0.000
from
Token from
Feature activation+0.000
finishing
Token finishing
Feature activation+1.197
15
Token 15
Feature activation+0.367
-
Token-
Feature activation+1.941
1
Token1
Feature activation+0.000
to
Token to
Feature activation+0.000
winning
Token winning
Feature activation+0.000
Super
Token Super
Feature activation+0.000
Bowl
Token Bowl
Feature activation+0.000

INTERVAL 1.469 - 1.763
CONTAINS 0.013%

Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
today
Token today
Feature activation+1.303
,
Token,
Feature activation+1.585
and
Token and
Feature activation+0.045
via
Token via
Feature activation+0.000
De
Token De
Feature activation+0.000
ez
Tokenez
Feature activation+0.000
er
Tokener
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
from
Token from
Feature activation+0.000
1992
Token 1992
Feature activation+1.747
to
Token to
Feature activation+1.802
1996
Token 1996
Feature activation+0.000
,
Token,
Feature activation+0.000
turning
Token turning
Feature activation+0.000
around
Token around
Feature activation+0.000
games
Token games
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
early
Token early
Feature activation+0.060
1980
Token 1980
Feature activation+0.425
s
Tokens
Feature activation+1.647
,
Token,
Feature activation+0.099
there
Token there
Feature activation+0.000
's
Token's
Feature activation+0.000
no
Token no
Feature activation+0.000
hardware
Token hardware
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
will
Token will
Feature activation+0.000
throw
Token throw
Feature activation+0.000
anywhere
Token anywhere
Feature activation+0.000
from
Token from
Feature activation+0.000
92
Token 92
Feature activation+1.518
-
Token-
Feature activation+2.654
94
Token94
Feature activation+0.000
,
Token,
Feature activation+0.331
with
Token with
Feature activation+0.000
W
Token W
Feature activation+0.000
which
Token which
Feature activation+0.000
Ph
Token Ph
Feature activation+0.000
o
Tokeno
Feature activation+0.000
took
Token took
Feature activation+0.000
from
Token from
Feature activation+0.000
work
Token work
Feature activation+1.702
between
Token between
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
and
Token and
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.175 - 1.469
CONTAINS 0.025%

how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
trees
Token trees
Feature activation+0.000
grow
Token grow
Feature activation+0.000
from
Token from
Feature activation+0.000
seed
Token seed
Feature activation+1.348
,
Token,
Feature activation+0.807
to
Token to
Feature activation+0.242
sa
Token sa
Feature activation+0.000
pling
Tokenpling
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
2
Token 2
Feature activation+0.685
.
Token.
Feature activation+0.000
05
Token05
Feature activation+0.000
%
Token%
Feature activation+2.049
to
Token to
Feature activation+1.462
5
Token 5
Feature activation+0.000
.
Token.
Feature activation+0.000
89
Token89
Feature activation+0.000
%
Token%
Feature activation+0.000
this
Token this
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
junior
Token junior
Feature activation+0.000
senator
Token senator
Feature activation+0.000
from
Token from
Feature activation+0.000
South
Token South
Feature activation+1.409
Carolina
Token Carolina
Feature activation+1.994
,
Token,
Feature activation+1.071
but
Token but
Feature activation+0.000
here
Token here
Feature activation+0.000
we
Token we
Feature activation+0.000
Met
Token Met
Feature activation+0.000
z
Tokenz
Feature activation+0.000
's
Token's
Feature activation+0.000
escape
Token escape
Feature activation+0.000
from
Token from
Feature activation+0.000
relegation
Token relegation
Feature activation+1.197
from
Token from
Feature activation+0.000
L
Token L
Feature activation+0.000
igue
Tokenigue
Feature activation+0.000
1
Token 1
Feature activation+1.439
at
Token at
Feature activation+0.798
s
Tokens
Feature activation+0.000
composition
Token composition
Feature activation+0.000
was
Token was
Feature activation+0.000
from
Token from
Feature activation+0.000
year
Token year
Feature activation+0.769
to
Token to
Feature activation+1.452
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 0.882 - 1.175
CONTAINS 0.034%

email
Token email
Feature activation+0.000
newsletters
Token newsletters
Feature activation+0.000
or
Token or
Feature activation+0.000
alerts
Token alerts
Feature activation+0.000
from
Token from
Feature activation+0.000
POLITICO
Token POLITICO
Feature activation+0.915
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
unsub
Token unsub
Feature activation+0.000
scribe
Tokenscribe
Feature activation+0.000
Check
Token Check
Feature activation+0.000
out
Token out
Feature activation+0.000
this
Token this
Feature activation+0.000
documentary
Token documentary
Feature activation+0.000
from
Token from
Feature activation+0.000
when
Token when
Feature activation+1.005
she
Token she
Feature activation+0.000
created
Token created
Feature activation+0.000
her
Token her
Feature activation+0.000
famous
Token famous
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
once
Token once
Feature activation+0.000
every
Token every
Feature activation+0.000
hour
Token hour
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.874
total
Token total
Feature activation+1.001
of
Token of
Feature activation+0.265
15
Token 15
Feature activation+0.000
different
Token different
Feature activation+0.000
global
Token global
Feature activation+0.000
locations
Token locations
Feature activation+0.000
had
Token had
Feature activation+0.000
returned
Token returned
Feature activation+0.000
home
Token home
Feature activation+0.000
from
Token from
Feature activation+0.000
school
Token school
Feature activation+0.983
Feb
Token Feb
Feature activation+1.037
.
Token.
Feature activation+0.000
9
Token 9
Feature activation+0.429
,
Token,
Feature activation+0.645
the
Token the
Feature activation+0.000
Bos
Token Bos
Feature activation+0.000
requests
Token requests
Feature activation+0.000
or
Token or
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
Walker
Token Walker
Feature activation+0.000
from
Token from
Feature activation+0.000
being
Token being
Feature activation+1.158
held
Token held
Feature activation+0.099
accountable
Token accountable
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
death
Token death
Feature activation+0.000

INTERVAL 0.588 - 0.882
CONTAINS 0.054%

consumers
Token consumers
Feature activation+0.000
shifting
Token shifting
Feature activation+0.000
game
Token game
Feature activation+0.000
play
Token play
Feature activation+0.000
from
Token from
Feature activation+0.000
computers
Token computers
Feature activation+0.870
to
Token to
Feature activation+1.236
mobile
Token mobile
Feature activation+0.000
devices
Token devices
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.401
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
cross
Token cross
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.872
left
Token left
Feature activation+1.411
.
Token.
Feature activation+0.000
Just
Token Just
Feature activation+0.000
two
Token two
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
to
Token to
Feature activation+0.000
defend
Token defend
Feature activation+0.000
a
Token a
Feature activation+0.000
location
Token location
Feature activation+0.000
from
Token from
Feature activation+0.000
attack
Token attack
Feature activation+0.688
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
should
Token should
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.000
run
Token run
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.356
diversity
Token diversity
Feature activation+0.000
standpoint
Token standpoint
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.732
Ļ
TokenĻ
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
qualification
Token qualification
Feature activation+0.000
to
Token to
Feature activation+0.000
protect
Token protect
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
from
Token from
Feature activation+0.000
US
Token US
Feature activation+0.642
hostility
Token hostility
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

INTERVAL 0.294 - 0.588
CONTAINS 0.098%

10
Token 10
Feature activation+0.000
seconds
Token seconds
Feature activation+0.000
.
Token.
Feature activation+0.000
Boots
Token Boots
Feature activation+0.000
from
Token from
Feature activation+0.000
sleep
Token sleep
Feature activation+0.391
in
Token in
Feature activation+0.000
2
Token 2
Feature activation+0.000
seconds
Token seconds
Feature activation+0.000
.
Token.
Feature activation+0.000
Has
Token Has
Feature activation+0.000
the
Token the
Feature activation+0.000
North
Token North
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.479
Stadium
Token Stadium
Feature activation+0.455
District
Token District
Feature activation+0.301
building
Token building
Feature activation+0.315
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
Co
Token Co
Feature activation+0.000
oley
Tokenoley
Feature activation+0.000
face
Token face
Feature activation+0.000
of
Token of
Feature activation+0.000
staunch
Token staunch
Feature activation+0.000
opposition
Token opposition
Feature activation+0.000
from
Token from
Feature activation+0.000
US
Token US
Feature activation+0.353
social
Token social
Feature activation+0.054
media
Token media
Feature activation+0.000
companies
Token companies
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
and
Token and
Feature activation+0.000
spaghetti
Token spaghetti
Feature activation+0.000
(
Token (
Feature activation+0.000
from
Tokenfrom
Feature activation+0.000
$
Token $
Feature activation+1.608
16
Token16
Feature activation+0.332
.
Token.
Feature activation+0.000
99
Token99
Feature activation+0.559
)
Token)
Feature activation+0.826
as
Token as
Feature activation+0.154
bland
Token bland
Feature activation+0.000
Video
Token Video
Feature activation+0.000
/
Token/
Feature activation+0.000
Photo
TokenPhoto
Feature activation+0.000
from
Token from
Feature activation+0.000
Gallery
Token Gallery
Feature activation+0.388
Ċ
TokenĊ
Feature activation+0.405
Ċ
TokenĊ
Feature activation+0.051
As
TokenAs
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
tell
Token tell
Feature activation+0.000

INTERVAL 0.000 - 0.294
CONTAINS 99.767%

-
Token-
Feature activation+0.000
2
Token2
Feature activation+0.000
-
Token-
Feature activation+0.000
Version
TokenVersion
Feature activation+0.000
-
Token-
Feature activation+0.000
2
Token2
Feature activation+0.000
.
Token.
Feature activation+0.000
jpg
Tokenjpg
Feature activation+0.000
","
Token","
Feature activation+0.000
small
Tokensmall
Feature activation+0.000
Width
TokenWidth
Feature activation+0.000
bars
Token bars
Feature activation+0.000
people
Token people
Feature activation+0.000
or
Token or
Feature activation+0.000
businesses
Token businesses
Feature activation+0.000
for
Token for
Feature activation+0.000
operating
Token operating
Feature activation+0.000
a
Token a
Feature activation+0.000
drone
Token drone
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
or
Token or
Feature activation+0.000
as
Token as
Feature activation+0.000
from
Token from
Feature activation+0.000
deportation
Token deportation
Feature activation+1.385
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
the
Token the
Feature activation+0.000
conversations
Token conversations
Feature activation+0.000
were
Token were
Feature activation+0.000
a
Token a
Feature activation+0.000
clear
Token clear
Feature activation+0.000
given
Token given
Feature activation+0.000
from
Token from
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
have
Token have
Feature activation+0.209
caused
Token caused
Feature activation+0.000
schools
Token schools
Feature activation+0.000
to
Token to
Feature activation+0.000
focus
Token focus
Feature activation+0.000
entirely
Token entirely
Feature activation+0.000
on
Token on
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
article
Tokenarticle
Feature activation+0.000
/
Token/
Feature activation+0.000
blocks
Tokenblocks
Feature activation+0.000
/
Token/
Feature activation+0.000
block
Tokenblock
Feature activation+0.000
_
Token_
Feature activation+0.000
comm
Tokencomm
Feature activation+0.000
end
Tokenend
Feature activation+0.000
.
Token.
Feature activation+0.000
php
Tokenphp
Feature activation+0.000
on
Token on
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 H3.2: (feature 23976)

TOP ACTIVATIONS
MAX = 3.443

head
Token head
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Queen
Token Queen
Feature activation+0.000
as
Token as
Feature activation+0.018
engraved
Token engraved
Feature activation+3.443
by
Token by
Feature activation+1.319
William
Token William
Feature activation+0.147
Wy
Token Wy
Feature activation+0.000
on
Tokenon
Feature activation+0.000
for
Token for
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Crime
TokenCrime
Feature activation+0.000
-
Token-
Feature activation+0.000
as
Tokenas
Feature activation+0.334
-
Token-
Feature activation+3.372
a
Tokena
Feature activation+1.895
-
Token-
Feature activation+0.000
Service
TokenService
Feature activation+0.100
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
their
Token their
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
as
Token as
Feature activation+0.000
ins
Token ins
Feature activation+3.126
cr
Tokencr
Feature activation+0.000
utable
Tokenutable
Feature activation+2.507
and
Token and
Feature activation+1.097
fascinating
Token fascinating
Feature activation+1.741
as
Token as
Feature activation+0.031
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
come
Token come
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.587
surprise
Token surprise
Feature activation+3.101
as
Token as
Feature activation+0.291
nobody
Token nobody
Feature activation+0.000
knows
Token knows
Feature activation+0.000
the
Token the
Feature activation+0.000
character
Token character
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
Baldwin
Token Baldwin
Feature activation+0.000
-
Token-
Feature activation+0.000
as
Tokenas
Feature activation+0.705
-
Token-
Feature activation+3.004
Trump
TokenTrump
Feature activation+1.896
said
Token said
Feature activation+0.192
he
Token he
Feature activation+0.000
feels
Token feels
Feature activation+0.000
bad
Token bad
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
his
Token his
Feature activation+0.000
body
Token body
Feature activation+0.000
as
Token as
Feature activation+0.000
bait
Token bait
Feature activation+3.003
to
Token to
Feature activation+0.000
hook
Token hook
Feature activation+0.028
a
Token a
Feature activation+0.000
larger
Token larger
Feature activation+0.000
fish
Token fish
Feature activation+0.000
The
Token The
Feature activation+0.000
voyage
Token voyage
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
as
Token as
Feature activation+0.296
rough
Token rough
Feature activation+3.002
as
Token as
Feature activation+1.329
any
Token any
Feature activation+0.505
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
remember
Token remember
Feature activation+0.000
try
Token try
Feature activation+0.000
and
Token and
Feature activation+0.000
make
Token make
Feature activation+0.000
this
Token this
Feature activation+0.000
as
Token as
Feature activation+0.000
short
Token short
Feature activation+2.987
as
Token as
Feature activation+0.255
I
Token I
Feature activation+0.753
can
Token can
Feature activation+0.805
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
un
Token un
Feature activation+0.000
ruly
Tokenruly
Feature activation+0.000
dwarves
Token dwarves
Feature activation+0.000
as
Token as
Feature activation+0.000
nom
Token nom
Feature activation+2.195
ads
Tokenads
Feature activation+2.975
longing
Token longing
Feature activation+1.007
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
rightful
Token rightful
Feature activation+0.000
place
Token place
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
they
Token they
Feature activation+0.000
're
Token're
Feature activation+0.000
as
Token as
Feature activation+0.000
divided
Token divided
Feature activation+2.922
as
Token as
Feature activation+1.218
any
Token any
Feature activation+0.223
other
Token other
Feature activation+0.000
.
Token.
Feature activation+0.000
As
TokenAs
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
as
Token as
Feature activation+0.000
em
Token em
Feature activation+1.934
bl
Tokenbl
Feature activation+0.000
azon
Tokenazon
Feature activation+2.915
ed
Tokened
Feature activation+2.480
on
Token on
Feature activation+0.721
the
Token the
Feature activation+0.000
back
Token back
Feature activation+0.000
of
Token of
Feature activation+0.000
North
Token North
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
came
Token came
Feature activation+0.000
as
Token as
Feature activation+0.613
no
Token no
Feature activation+2.205
surprise
Token surprise
Feature activation+2.892
.
Token.
Feature activation+0.000
Ken
Token Ken
Feature activation+0.000
Ge
Token Ge
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
opponents
Token opponents
Feature activation+0.000
are
Token are
Feature activation+0.000
as
Token as
Feature activation+0.001
evil
Token evil
Feature activation+2.860
as
Token as
Feature activation+0.401
we
Token we
Feature activation+1.253
believe
Token believe
Feature activation+1.424
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
it
Token it
Feature activation+0.000
may
Token may
Feature activation+0.000
come
Token come
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.837
surprise
Token surprise
Feature activation+2.859
that
Token that
Feature activation+0.000
this
Token this
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Jill
Token Jill
Feature activation+0.000
Abram
Token Abram
Feature activation+0.000
son
Tokenson
Feature activation+0.000
as
Token as
Feature activation+0.000
op
Token op
Feature activation+1.595
ining
Tokenining
Feature activation+2.856
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
us
Token us
Feature activation+0.000
,
Token,
Feature activation+0.000
battling
Token battling
Feature activation+0.000
dangers
Token dangers
Feature activation+0.000
as
Token as
Feature activation+0.000
real
Token real
Feature activation+2.833
as
Token as
Feature activation+0.100
Sent
Token Sent
Feature activation+0.143
ry
Tokenry
Feature activation+0.000
robots
Token robots
Feature activation+0.930
and
Token and
Feature activation+0.289
likely
Token likely
Feature activation+0.000
been
Token been
Feature activation+0.000
asked
Token asked
Feature activation+0.000
for
Token for
Feature activation+0.000
as
Token as
Feature activation+0.000
long
Token long
Feature activation+2.832
as
Token as
Feature activation+0.267
there
Token there
Feature activation+0.113
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
humans
Token humans
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
hole
Token hole
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
healed
Token healed
Feature activation+2.825
as
Token as
Feature activation+0.994
it
Token it
Feature activation+0.328
is
Token is
Feature activation+0.409
going
Token going
Feature activation+0.136
to
Token to
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
development
Tokendevelopment
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
as
Token as
Feature activation+0.000
material
Token material
Feature activation+2.823
,
Token,
Feature activation+0.793
economic
Token economic
Feature activation+0.000
progress
Token progress
Feature activation+0.000
,
Token,
Feature activation+0.000
Sch
Token Sch
Feature activation+0.000
great
Token great
Feature activation+0.000
instincts
Token instincts
Feature activation+0.000
.
Token.
Feature activation+0.000
Being
Token Being
Feature activation+0.000
as
Token as
Feature activation+0.000
smart
Token smart
Feature activation+2.816
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.072
was
Token was
Feature activation+0.703
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000

Top DFA by src position
MAX = 3.896

the
Token the
Feature activation-0.000
Top resid features:
head
Token head
Feature activation+0.029
Top resid features:
of
Token of
Feature activation+0.034
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
Queen
Token Queen
Feature activation+0.056
Top resid features:
as
Token as
Feature activation+3.896
Top resid features:
engraved
Token engraved
Feature activation-0.081
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
William
Token William
Feature activation+0.000
Top resid features:
Wy
Token Wy
Feature activation+0.000
Top resid features:
on
Tokenon
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.011
Top resid features:
âĢ
Token âĢ
Feature activation-0.026
Top resid features:
ľ
Tokenľ
Feature activation+0.028
Top resid features:
Crime
TokenCrime
Feature activation+0.346
Top resid features:
-
Token-
Feature activation+0.029
Top resid features:
as
Tokenas
Feature activation+3.675
Top resid features:
-
Token-
Feature activation-0.061
Top resid features:
a
Tokena
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
Service
TokenService
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
their
Token their
Feature activation-0.008
Top resid features:
way
Token way
Feature activation+0.006
Top resid features:
to
Token to
Feature activation-0.018
Top resid features:
be
Token be
Feature activation+0.011
Top resid features:
as
Token as
Feature activation+3.581
Top resid features:
ins
Token ins
Feature activation+0.093
Top resid features:
cr
Tokencr
Feature activation+0.000
Top resid features:
utable
Tokenutable
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
fascinating
Token fascinating
Feature activation+0.000
Top resid features:
shouldn
Token shouldn
Feature activation+0.012
Top resid features:
âĢ
TokenâĢ
Feature activation-0.048
Top resid features:
Ļ
TokenĻ
Feature activation+0.017
Top resid features:
t
Tokent
Feature activation-0.001
Top resid features:
come
Token come
Feature activation+0.199
Top resid features:
as
Token as
Feature activation+3.576
Top resid features:
a
Token a
Feature activation-0.061
Top resid features:
surprise
Token surprise
Feature activation-0.053
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
nobody
Token nobody
Feature activation+0.000
Top resid features:
knows
Token knows
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.011
Top resid features:
When
TokenWhen
Feature activation-0.063
Top resid features:
Baldwin
Token Baldwin
Feature activation+0.109
Top resid features:
-
Token-
Feature activation+0.042
Top resid features:
as
Tokenas
Feature activation+3.645
Top resid features:
-
Token-
Feature activation-0.061
Top resid features:
Trump
TokenTrump
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
feels
Token feels
Feature activation+0.000
Top resid features:
planned
Token planned
Feature activation-0.026
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
use
Token use
Feature activation+0.013
Top resid features:
his
Token his
Feature activation+0.007
Top resid features:
body
Token body
Feature activation-0.022
Top resid features:
as
Token as
Feature activation+3.460
Top resid features:
bait
Token bait
Feature activation+0.156
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
hook
Token hook
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
larger
Token larger
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.016
Top resid features:
The
Token The
Feature activation-0.016
Top resid features:
voyage
Token voyage
Feature activation-0.012
Top resid features:
had
Token had
Feature activation-0.003
Top resid features:
been
Token been
Feature activation+0.093
Top resid features:
as
Token as
Feature activation+3.768
Top resid features:
rough
Token rough
Feature activation-0.279
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
try
Token try
Feature activation-0.008
Top resid features:
and
Token and
Feature activation+0.064
Top resid features:
make
Token make
Feature activation+0.002
Top resid features:
this
Token this
Feature activation-0.027
Top resid features:
as
Token as
Feature activation+3.598
Top resid features:
short
Token short
Feature activation-0.104
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
the
Token the
Feature activation-0.016
Top resid features:
un
Token un
Feature activation+0.016
Top resid features:
ruly
Tokenruly
Feature activation-0.064
Top resid features:
dwarves
Token dwarves
Feature activation+0.006
Top resid features:
as
Token as
Feature activation+3.347
Top resid features:
nom
Token nom
Feature activation+0.124
Top resid features:
ads
Tokenads
Feature activation+0.109
Top resid features:
longing
Token longing
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
problems
Token problems
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
And
Token And
Feature activation+0.006
Top resid features:
they
Token they
Feature activation+0.014
Top resid features:
're
Token're
Feature activation-0.009
Top resid features:
as
Token as
Feature activation+3.608
Top resid features:
divided
Token divided
Feature activation-0.126
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.018
Top resid features:
F
TokenF
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.036
Top resid features:
âĢ
TokenâĢ
Feature activation+0.020
Top resid features:
Ŀ
TokenĿ
Feature activation+0.084
Top resid features:
as
Token as
Feature activation+3.236
Top resid features:
em
Token em
Feature activation-0.003
Top resid features:
bl
Tokenbl
Feature activation+0.037
Top resid features:
azon
Tokenazon
Feature activation+0.006
Top resid features:
ed
Tokened
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
campaign
Token campaign
Feature activation+0.042
Top resid features:
against
Token against
Feature activation+0.013
Top resid features:
North
Token North
Feature activation+0.002
Top resid features:
Korea
Token Korea
Feature activation+0.010
Top resid features:
came
Token came
Feature activation+0.224
Top resid features:
as
Token as
Feature activation+3.239
Top resid features:
no
Token no
Feature activation-0.005
Top resid features:
surprise
Token surprise
Feature activation-0.061
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ken
Token Ken
Feature activation+0.000
Top resid features:
Ge
Token Ge
Feature activation+0.000
Top resid features:
none
Token none
Feature activation-0.011
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
our
Token our
Feature activation+0.001
Top resid features:
opponents
Token opponents
Feature activation+0.027
Top resid features:
are
Token are
Feature activation+0.035
Top resid features:
as
Token as
Feature activation+3.421
Top resid features:
evil
Token evil
Feature activation-0.098
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
believe
Token believe
Feature activation+0.000
Top resid features:
them
Token them
Feature activation+0.000
Top resid features:
To
Token To
Feature activation-0.101
Top resid features:
some
Token some
Feature activation+0.001
Top resid features:
it
Token it
Feature activation+0.051
Top resid features:
may
Token may
Feature activation-0.046
Top resid features:
come
Token come
Feature activation+0.102
Top resid features:
as
Token as
Feature activation+3.502
Top resid features:
a
Token a
Feature activation-0.058
Top resid features:
surprise
Token surprise
Feature activation-0.048
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
wasn
Token wasn
Feature activation+0.000
Top resid features:
managing
Token managing
Feature activation-0.013
Top resid features:
editor
Token editor
Feature activation-0.006
Top resid features:
Jill
Token Jill
Feature activation+0.019
Top resid features:
Abram
Token Abram
Feature activation+0.007
Top resid features:
son
Tokenson
Feature activation+0.009
Top resid features:
as
Token as
Feature activation+3.617
Top resid features:
op
Token op
Feature activation-0.020
Top resid features:
ining
Tokenining
Feature activation-0.200
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
This
TokenThis
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
among
Token among
Feature activation+0.011
Top resid features:
us
Token us
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
battling
Token battling
Feature activation-0.009
Top resid features:
dangers
Token dangers
Feature activation+0.042
Top resid features:
as
Token as
Feature activation+3.442
Top resid features:
real
Token real
Feature activation-0.116
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Sent
Token Sent
Feature activation+0.000
Top resid features:
ry
Tokenry
Feature activation+0.000
Top resid features:
robots
Token robots
Feature activation+0.000
Top resid features:
have
Token have
Feature activation-0.007
Top resid features:
likely
Token likely
Feature activation-0.010
Top resid features:
been
Token been
Feature activation+0.205
Top resid features:
asked
Token asked
Feature activation+0.023
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
as
Token as
Feature activation+3.428
Top resid features:
long
Token long
Feature activation-0.303
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
The
TokenThe
Feature activation-0.010
Top resid features:
hole
Token hole
Feature activation+0.038
Top resid features:
is
Token is
Feature activation+0.020
Top resid features:
as
Token as
Feature activation+3.556
Top resid features:
healed
Token healed
Feature activation-0.170
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
going
Token going
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation-0.001
Top resid features:
ľ
Tokenľ
Feature activation+0.052
Top resid features:
development
Tokendevelopment
Feature activation+0.026
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ŀ
TokenĿ
Feature activation+0.016
Top resid features:
as
Token as
Feature activation+3.218
Top resid features:
material
Token material
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
economic
Token economic
Feature activation+0.000
Top resid features:
progress
Token progress
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
had
Token had
Feature activation-0.019
Top resid features:
great
Token great
Feature activation-0.003
Top resid features:
instincts
Token instincts
Feature activation-0.013
Top resid features:
.
Token.
Feature activation-0.020
Top resid features:
Being
Token Being
Feature activation+0.060
Top resid features:
as
Token as
Feature activation+3.581
Top resid features:
smart
Token smart
Feature activation-0.188
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.01

Head 1: 0.05

Head 2: 0.42

Head 3: 0.07

Head 4: 0.01

Head 5: 0.02

Head 6: 0.06

Head 7: 0.04

Head 8: 0.14

Head 9: 0.05

Head 10: 0.06

Head 11: 0.06

Positive logits

standalone1.05

progresses0.99

unfolds0.95

Cub0.92

slightest0.92

eyes0.92

scales0.91

conduit0.91

iates0.91

identifiers0.90

predictor0.89

diver0.89

disparate0.89

possible0.89

practicable0.89

divid0.89

focal0.88

ansky0.87

harb0.87

tack0.86

Negative logits

istries-1.31

olas-1.22

nce-1.11

abases-1.08

Olympus-1.08

terness-1.07

ucket-1.06

=~-1.03

-1.02

partName-1.00

sites-0.99

tern-0.98

-0.98

roller-0.97

ogram-0.97

nep-0.95

idity-0.95

iland-0.95

wa-0.94

Pew-0.94

INTERVAL 3.098 - 3.443
CONTAINS 0.001%

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
come
Token come
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.587
surprise
Token surprise
Feature activation+3.101
as
Token as
Feature activation+0.291
nobody
Token nobody
Feature activation+0.000
knows
Token knows
Feature activation+0.000
the
Token the
Feature activation+0.000
character
Token character
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Crime
TokenCrime
Feature activation+0.000
-
Token-
Feature activation+0.000
as
Tokenas
Feature activation+0.334
-
Token-
Feature activation+3.372
a
Tokena
Feature activation+1.895
-
Token-
Feature activation+0.000
Service
TokenService
Feature activation+0.100
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
head
Token head
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Queen
Token Queen
Feature activation+0.000
as
Token as
Feature activation+0.018
engraved
Token engraved
Feature activation+3.443
by
Token by
Feature activation+1.319
William
Token William
Feature activation+0.147
Wy
Token Wy
Feature activation+0.000
on
Tokenon
Feature activation+0.000
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
as
Token as
Feature activation+0.000
ins
Token ins
Feature activation+3.126
cr
Tokencr
Feature activation+0.000
utable
Tokenutable
Feature activation+2.507
and
Token and
Feature activation+1.097
fascinating
Token fascinating
Feature activation+1.741
as
Token as
Feature activation+0.031

INTERVAL 2.754 - 3.098
CONTAINS 0.002%

ľ
Tokenľ
Feature activation+0.000
development
Tokendevelopment
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
as
Token as
Feature activation+0.000
material
Token material
Feature activation+2.823
,
Token,
Feature activation+0.793
economic
Token economic
Feature activation+0.000
progress
Token progress
Feature activation+0.000
,
Token,
Feature activation+0.000
Sch
Token Sch
Feature activation+0.000
Jill
Token Jill
Feature activation+0.000
Abram
Token Abram
Feature activation+0.000
son
Tokenson
Feature activation+0.000
as
Token as
Feature activation+0.000
op
Token op
Feature activation+1.595
ining
Tokenining
Feature activation+2.856
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
us
Token us
Feature activation+0.000
,
Token,
Feature activation+0.000
battling
Token battling
Feature activation+0.000
dangers
Token dangers
Feature activation+0.000
as
Token as
Feature activation+0.000
real
Token real
Feature activation+2.833
as
Token as
Feature activation+0.100
Sent
Token Sent
Feature activation+0.143
ry
Tokenry
Feature activation+0.000
robots
Token robots
Feature activation+0.930
and
Token and
Feature activation+0.289
try
Token try
Feature activation+0.000
and
Token and
Feature activation+0.000
make
Token make
Feature activation+0.000
this
Token this
Feature activation+0.000
as
Token as
Feature activation+0.000
short
Token short
Feature activation+2.987
as
Token as
Feature activation+0.255
I
Token I
Feature activation+0.753
can
Token can
Feature activation+0.805
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
hole
Token hole
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
healed
Token healed
Feature activation+2.825
as
Token as
Feature activation+0.994
it
Token it
Feature activation+0.328
is
Token is
Feature activation+0.409
going
Token going
Feature activation+0.136
to
Token to
Feature activation+0.000

INTERVAL 2.410 - 2.754
CONTAINS 0.004%

tried
Token tried
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
this
Token this
Feature activation+0.000
as
Token as
Feature activation+0.000
balanced
Token balanced
Feature activation+2.422
and
Token and
Feature activation+0.728
as
Token as
Feature activation+0.264
fun
Token fun
Feature activation+1.790
as
Token as
Feature activation+0.302
possible
Token possible
Feature activation+0.808
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
as
Token as
Feature activation+0.000
RN
TokenRN
Feature activation+2.617
As
TokenAs
Feature activation+0.000
is
Token is
Feature activation+1.318
exponentially
Token exponentially
Feature activation+0.000
dependent
Token dependent
Feature activation+0.000
on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
AS
Token AS
Feature activation+0.000
WE
Token WE
Feature activation+1.841
LL
TokenLL
Feature activation+1.103
as
Token as
Feature activation+0.000
learn
Token learn
Feature activation+2.414
myself
Token myself
Feature activation+0.000
more
Token more
Feature activation+0.000
about
Token about
Feature activation+0.000
God
Token God
Feature activation+0.000
and
Token and
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
horizon
Token horizon
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
crazy
Token crazy
Feature activation+2.590
as
Token as
Feature activation+0.014
it
Token it
Feature activation+0.000
gets
Token gets
Feature activation+0.116
,
Token,
Feature activation+0.701
but
Token but
Feature activation+0.000
His
TokenHis
Feature activation+0.000
crime
Token crime
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
baff
Token baff
Feature activation+1.298
ling
Tokenling
Feature activation+2.529
as
Token as
Feature activation+0.554
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.341
gruesome
Token gruesome
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 2.066 - 2.410
CONTAINS 0.009%

,
Token,
Feature activation+0.602
conservatives
Token conservatives
Feature activation+0.000
are
Token are
Feature activation+0.000
as
Token as
Feature activation+0.241
dep
Token dep
Feature activation+1.608
raved
Tokenraved
Feature activation+2.263
,
Token,
Feature activation+1.534
wicked
Token wicked
Feature activation+0.870
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
on
Token on
Feature activation+0.000
earth
Token earth
Feature activation+0.000
to
Token to
Feature activation+0.000
forgive
Token forgive
Feature activation+0.000
as
Token as
Feature activation+0.000
long
Token long
Feature activation+2.354
as
Token as
Feature activation+0.101
the
Token the
Feature activation+0.093
money
Token money
Feature activation+0.000
was
Token was
Feature activation+0.000
put
Token put
Feature activation+0.000
still
Token still
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
as
Token as
Feature activation+0.000
authentic
Token authentic
Feature activation+2.291
as
Token as
Feature activation+0.038
possible
Token possible
Feature activation+0.567
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
to
Token to
Feature activation+0.000
uphold
Token uphold
Feature activation+0.000
the
Token the
Feature activation+0.000
law
Token law
Feature activation+0.000
as
Token as
Feature activation+0.000
peacefully
Token peacefully
Feature activation+2.372
and
Token and
Feature activation+1.039
principled
Token principled
Feature activation+1.441
as
Token as
Feature activation+0.275
possible
Token possible
Feature activation+0.986
,
Token,
Feature activation+1.273
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
answer
Token answer
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
dark
Token dark
Feature activation+2.097
and
Token and
Feature activation+1.462
troubling
Token troubling
Feature activation+1.239
as
Token as
Feature activation+0.104
the
Token the
Feature activation+0.357
infamous
Token infamous
Feature activation+0.000

INTERVAL 1.721 - 2.066
CONTAINS 0.015%

the
Token the
Feature activation+0.000
Sun
Token Sun
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
chronic
Token chronic
Feature activation+0.919
led
Tokenled
Feature activation+1.897
in
Token in
Feature activation+0.758
an
Token an
Feature activation+0.000
accompanying
Token accompanying
Feature activation+0.000
documentary
Token documentary
Feature activation+0.000
(
Token (
Feature activation+0.000
con
Token con
Feature activation+0.000
se
Tokense
Feature activation+0.000
gu
Tokengu
Feature activation+0.000
iu
Tokeniu
Feature activation+0.000
as
Token as
Feature activation+0.000
du
Token du
Feature activation+1.803
as
Tokenas
Feature activation+0.000
prime
Token prime
Feature activation+0.000
ir
Tokenir
Feature activation+0.000
as
Tokenas
Feature activation+0.000
vend
Token vend
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
cellular
Token cellular
Feature activation+0.000
connection
Token connection
Feature activation+0.000
as
Token as
Feature activation+0.000
needed
Token needed
Feature activation+1.956
.
Token.
Feature activation+0.000
AT
Token AT
Feature activation+0.000
&
Token&
Feature activation+0.000
T
TokenT
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
as
Token as
Feature activation+0.000
big
Token big
Feature activation+1.809
a
Token a
Feature activation+0.000
problem
Token problem
Feature activation+0.414
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.568
age
Token age
Feature activation+0.000
when
Token when
Feature activation+0.000
freedom
Token freedom
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
as
Token as
Feature activation+0.000
in
Token in
Feature activation+1.888
the
Token the
Feature activation+0.317
old
Token old
Feature activation+0.000
-
Token-
Feature activation+0.000
fashioned
Tokenfashioned
Feature activation+0.000
sense
Token sense
Feature activation+0.000

INTERVAL 1.377 - 1.721
CONTAINS 0.029%

Y
TokenY
Feature activation+0.000
.,
Token.,
Feature activation+0.000
who
Token who
Feature activation+0.000
works
Token works
Feature activation+0.000
as
Token as
Feature activation+0.000
addiction
Token addiction
Feature activation+1.568
counselor
Token counselor
Feature activation+1.643
and
Token and
Feature activation+0.562
whose
Token whose
Feature activation+0.596
34
Token 34
Feature activation+0.000
-
Token-
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Which
Token Which
Feature activation+0.000
comes
Token comes
Feature activation+0.000
out
Token out
Feature activation+0.000
as
Token as
Feature activation+0.000
,
Token,
Feature activation+1.573
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
won
Token won
Feature activation+0.000
hipp
Token hipp
Feature activation+0.000
"
Token "
Feature activation+0.000
so
Tokenso
Feature activation+0.000
severely
Token severely
Feature activation+0.000
weakened
Token weakened
Feature activation+0.000
as
Token as
Feature activation+0.000
to
Token to
Feature activation+1.476
make
Token make
Feature activation+0.209
a
Token a
Feature activation+0.000
last
Token last
Feature activation+0.000
-
Token-
Feature activation+0.000
minute
Tokenminute
Feature activation+0.000
bypass
Token bypass
Feature activation+0.000
UN
Token UN
Feature activation+0.000
SC
TokenSC
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
did
Token did
Feature activation+1.406
in
Token in
Feature activation+0.154
2003
Token 2003
Feature activation+0.000
and
Token and
Feature activation+0.000
invaded
Token invaded
Feature activation+0.000
Iraq
Token Iraq
Feature activation+0.000
imper
Token imper
Feature activation+1.415
manent
Tokenmanent
Feature activation+2.103
and
Token and
Feature activation+0.776
inter
Token inter
Feature activation+0.000
dependent
Tokendependent
Feature activation+0.185
.
Token.
Feature activation+1.661
It
Token It
Feature activation+0.000
means
Token means
Feature activation+0.000
that
Token that
Feature activation+0.000
someone
Token someone
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000

INTERVAL 1.033 - 1.377
CONTAINS 0.046%

so
Token so
Feature activation+0.000
they
Token they
Feature activation+0.000
function
Token function
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
unit
Token unit
Feature activation+1.257
.
Token.
Feature activation+0.000
Other
Token Other
Feature activation+0.000
products
Token products
Feature activation+0.000
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+0.000
car
Token car
Feature activation+0.000
ne
Tokenne
Feature activation+0.000
as
Token as
Feature activation+0.000
ada
Tokenada
Feature activation+0.915
fries
Token fries
Feature activation+1.374
are
Token are
Feature activation+0.007
really
Token really
Feature activation+0.000
good
Token good
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.755
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
speech
Token speech
Feature activation+0.000
as
Token as
Feature activation+0.000
summarized
Token summarized
Feature activation+1.839
by
Token by
Feature activation+1.130
Ax
Token Ax
Feature activation+0.000
ios
Tokenios
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
exciting
Token exciting
Feature activation+0.000
things
Token things
Feature activation+0.000
with
Token with
Feature activation+0.000
Sonic
Token Sonic
Feature activation+0.000
as
Token as
Feature activation+0.032
a
Token a
Feature activation+1.100
brand
Token brand
Feature activation+1.791
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
near
Token near
Feature activation+0.000
future
Token future
Feature activation+0.000
still
Token still
Feature activation+0.000
use
Token use
Feature activation+0.000
it
Token it
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.313
moistur
Token moistur
Feature activation+1.141
izer
Tokenizer
Feature activation+0.442
every
Token every
Feature activation+0.000
time
Token time
Feature activation+0.000
you
Token you
Feature activation+0.000
wash
Token wash
Feature activation+0.000

INTERVAL 0.689 - 1.033
CONTAINS 0.077%

apology
Token apology
Feature activation+0.000
but
Token but
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
nation
Token nation
Feature activation+1.376
,
Token,
Feature activation+0.968
America
Token America
Feature activation+0.000
should
Token should
Feature activation+0.000
admit
Token admit
Feature activation+0.000
the
Token the
Feature activation+0.000
bombings
Token bombings
Feature activation+0.000
of
Token of
Feature activation+0.000
freedom
Token freedom
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
as
Token as
Feature activation+0.000
something
Token something
Feature activation+0.963
they
Token they
Feature activation+0.000
express
Token express
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
with
Token with
Feature activation+0.000
.
Token.
Feature activation+0.000
did
Token did
Feature activation+0.000
so
Token so
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.155
senator
Token senator
Feature activation+1.128
or
Token or
Feature activation+0.979
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.749
Trump
Token Trump
Feature activation+0.067
surrogate
Token surrogate
Feature activation+0.000
.
Token.
Feature activation+0.000
parliamentary
Token parliamentary
Feature activation+0.000
debate
Token debate
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
as
Token as
Feature activation+0.000
"
Token "
Feature activation+0.902
probably
Tokenprobably
Feature activation+0.302
the
Token the
Feature activation+0.000
one
Token one
Feature activation+0.000
person
Token person
Feature activation+0.000
in
Token in
Feature activation+0.000
Christians
Token Christians
Feature activation+0.000
rose
Token rose
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
share
Token share
Feature activation+1.996
of
Token of
Feature activation+0.750
the
Token the
Feature activation+0.000
population
Token population
Feature activation+0.000
from
Token from
Feature activation+0.000
19
Token 19
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.344 - 0.689
CONTAINS 0.119%

the
Token the
Feature activation+0.000
Carlton
Token Carlton
Feature activation+0.000
Ground
Token Ground
Feature activation+0.000
available
Token available
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.370
main
Token main
Feature activation+0.000
stadium
Token stadium
Feature activation+0.000
should
Token should
Feature activation+0.134
be
Token be
Feature activation+0.000
borne
Token borne
Feature activation+0.000
railroad
Token railroad
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.041
literal
Token literal
Feature activation+0.000
railroad
Token railroad
Feature activation+0.000
,
Token,
Feature activation+0.398
was
Token was
Feature activation+0.000
named
Token named
Feature activation+0.000
by
Token by
Feature activation+0.000
Barack
Token Barack
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
Las
Token Las
Feature activation+0.000
Vegas
Token Vegas
Feature activation+0.000
nightclub
Token nightclub
Feature activation+0.108
cocktail
Token cocktail
Feature activation+0.346
waitress
Token waitress
Feature activation+0.000
is
Token is
Feature activation+0.000
how
Token how
Feature activation+0.000
a
Token a
Feature activation+0.000
stranger
Token stranger
Feature activation+0.000
his
Token his
Feature activation+0.000
body
Token body
Feature activation+0.000
camera
Token camera
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
as
Token as
Feature activation+0.000
required
Token required
Feature activation+0.424
by
Token by
Feature activation+0.391
the
Token the
Feature activation+0.000
department
Token department
Feature activation+0.000
in
Token in
Feature activation+0.000
all
Token all
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
many
Token many
Feature activation+0.000
as
Token as
Feature activation+0.331
70
Token 70
Feature activation+0.000
%
Token%
Feature activation+0.520
of
Token of
Feature activation+0.000
participants
Token participants
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.000
study
Token study
Feature activation+0.000

INTERVAL 0.000 - 0.344
CONTAINS 99.699%

In
TokenIn
Feature activation+0.000
response
Token response
Feature activation+0.000
,
Token,
Feature activation+0.000
Rogers
Token Rogers
Feature activation+0.000
'
Token'
Feature activation+0.000
mother
Token mother
Feature activation+0.000
,
Token,
Feature activation+0.000
Lauren
Token Lauren
Feature activation+0.000
Rogers
Token Rogers
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
ordinary
Token ordinary
Feature activation+0.000
English
Token English
Feature activation+0.000
to
Token to
Feature activation+0.000
collectively
Token collectively
Feature activation+0.000
refer
Token refer
Feature activation+0.000
to
Token to
Feature activation+0.000
all
Token all
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.000
Euph
Token Euph
Feature activation+0.000
or
Tokenor
Feature activation+0.000
the
Token the
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
psyche
Token psyche
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
strength
Token strength
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
tradition
Token tradition
Feature activation+0.000
went
Token went
Feature activation+0.000
to
Token to
Feature activation+0.000
Signature
Token Signature
Feature activation+0.000
Theater
Token Theater
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
C
TokenC
Feature activation+0.000
level
Tokenlevel
Feature activation+0.000
and
Tokenand
Feature activation+0.000
Play
Token Play
Feature activation+0.000
tank
Tokentank
Feature activation+0.000
,
Token,
Feature activation+0.000
says
Token says
Feature activation+0.000
the
Token the
Feature activation+0.000
law
Token law
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
bl
Tokenbl
Feature activation+0.000
at
Tokenat
Feature activation+0.000
antly
Tokenantly
Feature activation+0.000
violates
Token violates
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 H3.2: (feature 13742)

TOP ACTIVATIONS
MAX = 2.960

the
Token the
Feature activation+0.000
conversation
Token conversation
Feature activation+0.000
at
Token at
Feature activation+0.000
that
Token that
Feature activation+0.000
dinner
Token dinner
Feature activation+2.100
party
Token party
Feature activation+2.960
is
Token is
Feature activation+0.090
likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
completely
Token completely
Feature activation+0.000
that
Token that
Feature activation+0.000
unlikely
Token unlikely
Feature activation+1.105
-
Token-
Feature activation+1.160
se
Tokense
Feature activation+1.027
eming
Tokeneming
Feature activation+1.454
victory
Token victory
Feature activation+2.792
.
Token.
Feature activation+0.000
How
Token How
Feature activation+0.000
could
Token could
Feature activation+0.000
the
Token the
Feature activation+0.000
all
Token all
Feature activation+0.000
PG
TokenPG
Feature activation+0.000
.
Token.
Feature activation+0.000
Watching
Token Watching
Feature activation+0.000
that
Token that
Feature activation+0.000
boss
Token boss
Feature activation+1.407
monster
Token monster
Feature activation+2.519
explode
Token explode
Feature activation+1.496
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
shower
Token shower
Feature activation+0.000
of
Token of
Feature activation+0.000
erase
Token erase
Feature activation+0.000
that
Token that
Feature activation+0.000
$
Token $
Feature activation+0.800
100
Token100
Feature activation+1.841
million
Token million
Feature activation+1.910
difference
Token difference
Feature activation+2.477
in
Token in
Feature activation+0.450
the
Token the
Feature activation+0.000
near
Token near
Feature activation+0.000
future
Token future
Feature activation+0.000
.
Token.
Feature activation+0.000
national
Token national
Feature activation+0.000
television
Token television
Feature activation+0.000
to
Token to
Feature activation+0.000
that
Token that
Feature activation+0.000
moment
Token moment
Feature activation+1.034
of
Token of
Feature activation+2.469
spont
Token spont
Feature activation+0.151
ane
Tokenane
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
on
Token on
Feature activation+0.135
the
Token the
Feature activation+0.000
players
Token players
Feature activation+0.000
on
Token on
Feature activation+0.000
that
Token that
Feature activation+0.000
kickoff
Token kickoff
Feature activation+1.001
coverage
Token coverage
Feature activation+1.909
unit
Token unit
Feature activation+2.452
who
Token who
Feature activation+0.151
graded
Token graded
Feature activation+0.000
out
Token out
Feature activation+0.000
positively
Token positively
Feature activation+0.000
.
Token.
Feature activation+0.000
o
Tokeno
Feature activation+0.000
iled
Tokeniled
Feature activation+0.000
from
Token from
Feature activation+0.000
that
Token that
Feature activation+0.000
aspect
Token aspect
Feature activation+0.952
of
Token of
Feature activation+2.428
Spider
Token Spider
Feature activation+0.200
-
Token-
Feature activation+0.000
Man
TokenMan
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
went
Token went
Feature activation+0.000
into
Token into
Feature activation+0.000
that
Token that
Feature activation+0.000
protective
Token protective
Feature activation+1.328
motorcycle
Token motorcycle
Feature activation+2.263
look
Token look
Feature activation+2.415
from
Token from
Feature activation+1.098
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
hung
Token hung
Feature activation+0.000
you
Token you
Feature activation+0.000
buy
Token buy
Feature activation+0.000
into
Token into
Feature activation+0.000
that
Token that
Feature activation+0.000
line
Token line
Feature activation+1.169
of
Token of
Feature activation+2.366
thinking
Token thinking
Feature activation+0.455
,
Token,
Feature activation+0.000
consider
Token consider
Feature activation+0.000
the
Token the
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Despite
TokenDespite
Feature activation+0.000
that
Token that
Feature activation+0.000
tiny
Token tiny
Feature activation+1.582
shred
Token shred
Feature activation+2.328
of
Token of
Feature activation+2.340
optimism
Token optimism
Feature activation+0.491
of
Token of
Feature activation+0.732
any
Token any
Feature activation+0.000
crossover
Token crossover
Feature activation+0.000
happening
Token happening
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Despite
TokenDespite
Feature activation+0.000
that
Token that
Feature activation+0.000
tiny
Token tiny
Feature activation+1.582
shred
Token shred
Feature activation+2.328
of
Token of
Feature activation+2.340
optimism
Token optimism
Feature activation+0.491
of
Token of
Feature activation+0.732
any
Token any
Feature activation+0.000
crossover
Token crossover
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
back
Token back
Feature activation+0.000
that
Token that
Feature activation+0.000
tradition
Token tradition
Feature activation+1.466
of
Token of
Feature activation+2.327
Chicago
Token Chicago
Feature activation+0.000
Bears
Token Bears
Feature activation+0.025
defense
Token defense
Feature activation+0.000
,
Token,
Feature activation+0.251
where
Token where
Feature activation+0.000
had
Token had
Feature activation+0.000
that
Token that
Feature activation+0.000
old
Token old
Feature activation+1.240
-
Token-
Feature activation+0.107
school
Tokenschool
Feature activation+1.029
grit
Token grit
Feature activation+2.305
âĢĵ
Token âĢĵ
Feature activation+0.875
very
Token very
Feature activation+0.000
determined
Token determined
Feature activation+0.000
and
Token and
Feature activation+0.000
mentally
Token mentally
Feature activation+0.000
just
Token just
Feature activation+0.000
gave
Token gave
Feature activation+0.000
you
Token you
Feature activation+0.000
that
Token that
Feature activation+0.000
eerie
Token eerie
Feature activation+1.402
feeling
Token feeling
Feature activation+2.286
of
Token of
Feature activation+2.247
-
Token -
Feature activation+0.000
what
Token what
Feature activation+0.000
?
Token?
Feature activation+0.000
-
Token -
Feature activation+0.000
to
Token to
Feature activation+0.000
rel
Token rel
Feature activation+0.000
ive
Tokenive
Feature activation+0.000
that
Token that
Feature activation+0.000
special
Token special
Feature activation+1.878
high
Token high
Feature activation+2.275
school
Token school
Feature activation+1.284
magic
Token magic
Feature activation+1.584
once
Token once
Feature activation+0.000
again
Token again
Feature activation+0.000
.
Token.
Feature activation+0.000
looks
Token looks
Feature activation+0.000
at
Token at
Feature activation+0.000
that
Token that
Feature activation+0.000
looming
Token looming
Feature activation+1.191
question
Token question
Feature activation+2.244
of
Token of
Feature activation+2.264
relevance
Token relevance
Feature activation+0.163
square
Token square
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
eye
Token eye
Feature activation+0.000
we
Token we
Feature activation+0.000
went
Token went
Feature activation+0.000
into
Token into
Feature activation+0.000
that
Token that
Feature activation+0.000
protective
Token protective
Feature activation+1.328
motorcycle
Token motorcycle
Feature activation+2.263
look
Token look
Feature activation+2.415
from
Token from
Feature activation+1.098
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
far
Token far
Feature activation+0.000
enough
Token enough
Feature activation+0.000
down
Token down
Feature activation+0.000
that
Token that
Feature activation+0.000
rabbit
Token rabbit
Feature activation+1.505
hole
Token hole
Feature activation+2.262
to
Token to
Feature activation+1.305
have
Token have
Feature activation+0.000
40
Token 40
Feature activation+0.000
+
Token+
Feature activation+0.000
tabs
Token tabs
Feature activation+0.000
gave
Token gave
Feature activation+0.000
you
Token you
Feature activation+0.000
that
Token that
Feature activation+0.000
eerie
Token eerie
Feature activation+1.402
feeling
Token feeling
Feature activation+2.286
of
Token of
Feature activation+2.247
-
Token -
Feature activation+0.000
what
Token what
Feature activation+0.000
?
Token?
Feature activation+0.000
-
Token -
Feature activation+0.000
like
Token like
Feature activation+0.000
that
Token that
Feature activation+0.000
South
Token South
Feature activation+1.490
Carolina
Token Carolina
Feature activation+0.485
GOP
Token GOP
Feature activation+1.033
presidential
Token presidential
Feature activation+0.201
debate
Token debate
Feature activation+2.245
and
Token and
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 3.179

Ċ
TokenĊ
Feature activation-0.026
Top resid features:
And
TokenAnd
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.106
Top resid features:
conversation
Token conversation
Feature activation-0.050
Top resid features:
at
Token at
Feature activation+0.033
Top resid features:
that
Token that
Feature activation+2.918
Top resid features:
dinner
Token dinner
Feature activation+0.233
Top resid features:
party
Token party
Feature activation+0.084
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
likely
Token likely
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
E
Token E
Feature activation+0.014
Top resid features:
w
Tokenw
Feature activation+0.009
Top resid features:
oks
Tokenoks
Feature activation-0.029
Top resid features:
stems
Token stems
Feature activation+0.005
Top resid features:
from
Token from
Feature activation-0.125
Top resid features:
that
Token that
Feature activation+3.179
Top resid features:
unlikely
Token unlikely
Feature activation-0.079
Top resid features:
-
Token-
Feature activation-0.022
Top resid features:
se
Tokense
Feature activation+0.035
Top resid features:
eming
Tokeneming
Feature activation+0.023
Top resid features:
victory
Token victory
Feature activation+0.016
Top resid features:
any
Token any
Feature activation-0.014
Top resid features:
AR
Token AR
Feature activation+0.000
Top resid features:
PG
TokenPG
Feature activation+0.014
Top resid features:
.
Token.
Feature activation-0.125
Top resid features:
Watching
Token Watching
Feature activation-0.050
Top resid features:
that
Token that
Feature activation+2.559
Top resid features:
boss
Token boss
Feature activation+0.299
Top resid features:
monster
Token monster
Feature activation+0.081
Top resid features:
explode
Token explode
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
have
Token have
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.025
Top resid features:
leverage
Token leverage
Feature activation-0.006
Top resid features:
to
Token to
Feature activation-0.005
Top resid features:
erase
Token erase
Feature activation-0.079
Top resid features:
that
Token that
Feature activation+2.814
Top resid features:
$
Token $
Feature activation+0.119
Top resid features:
100
Token100
Feature activation+0.017
Top resid features:
million
Token million
Feature activation-0.149
Top resid features:
difference
Token difference
Feature activation+0.048
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
tears
Token tears
Feature activation-0.019
Top resid features:
on
Token on
Feature activation-0.026
Top resid features:
national
Token national
Feature activation-0.030
Top resid features:
television
Token television
Feature activation-0.089
Top resid features:
to
Token to
Feature activation-0.133
Top resid features:
that
Token that
Feature activation+2.697
Top resid features:
moment
Token moment
Feature activation+0.059
Top resid features:
of
Token of
Feature activation+0.156
Top resid features:
spont
Token spont
Feature activation+0.000
Top resid features:
ane
Tokenane
Feature activation+0.000
Top resid features:
ity
Tokenity
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.013
Top resid features:
numerous
Token numerous
Feature activation-0.013
Top resid features:
other
Token other
Feature activation-0.004
Top resid features:
players
Token players
Feature activation-0.062
Top resid features:
on
Token on
Feature activation-0.051
Top resid features:
that
Token that
Feature activation+2.641
Top resid features:
kickoff
Token kickoff
Feature activation+0.114
Top resid features:
coverage
Token coverage
Feature activation-0.060
Top resid features:
unit
Token unit
Feature activation+0.044
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
graded
Token graded
Feature activation+0.000
Top resid features:
un
Tokenun
Feature activation+0.006
Top resid features:
rec
Token rec
Feature activation-0.042
Top resid features:
o
Tokeno
Feature activation+0.003
Top resid features:
iled
Tokeniled
Feature activation+0.009
Top resid features:
from
Token from
Feature activation-0.027
Top resid features:
that
Token that
Feature activation+2.755
Top resid features:
aspect
Token aspect
Feature activation-0.249
Top resid features:
of
Token of
Feature activation+0.177
Top resid features:
Spider
Token Spider
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
Man
TokenMan
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation-0.033
Top resid features:
So
TokenSo
Feature activation-0.016
Top resid features:
we
Token we
Feature activation+0.019
Top resid features:
went
Token went
Feature activation+0.052
Top resid features:
into
Token into
Feature activation-0.036
Top resid features:
that
Token that
Feature activation+2.656
Top resid features:
protective
Token protective
Feature activation+0.073
Top resid features:
motorcycle
Token motorcycle
Feature activation+0.029
Top resid features:
look
Token look
Feature activation+0.021
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.031
Top resid features:
If
Token If
Feature activation-0.031
Top resid features:
you
Token you
Feature activation-0.042
Top resid features:
buy
Token buy
Feature activation-0.021
Top resid features:
into
Token into
Feature activation-0.025
Top resid features:
that
Token that
Feature activation+2.793
Top resid features:
line
Token line
Feature activation-0.195
Top resid features:
of
Token of
Feature activation+0.161
Top resid features:
thinking
Token thinking
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
consider
Token consider
Feature activation+0.000
Top resid features:
possible
Token possible
Feature activation-0.005
Top resid features:
!
Token!
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Despite
TokenDespite
Feature activation+0.012
Top resid features:
that
Token that
Feature activation+2.473
Top resid features:
tiny
Token tiny
Feature activation-0.074
Top resid features:
shred
Token shred
Feature activation+0.012
Top resid features:
of
Token of
Feature activation+0.124
Top resid features:
optimism
Token optimism
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
possible
Token possible
Feature activation-0.009
Top resid features:
!
Token!
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.017
Top resid features:
Despite
TokenDespite
Feature activation-0.009
Top resid features:
that
Token that
Feature activation+2.711
Top resid features:
tiny
Token tiny
Feature activation-0.058
Top resid features:
shred
Token shred
Feature activation-0.005
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
optimism
Token optimism
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation-0.011
Top resid features:
Just
TokenJust
Feature activation-0.017
Top resid features:
to
Token to
Feature activation-0.019
Top resid features:
bring
Token bring
Feature activation-0.087
Top resid features:
back
Token back
Feature activation-0.000
Top resid features:
that
Token that
Feature activation+2.241
Top resid features:
tradition
Token tradition
Feature activation+0.312
Top resid features:
of
Token of
Feature activation+0.112
Top resid features:
Chicago
Token Chicago
Feature activation+0.000
Top resid features:
Bears
Token Bears
Feature activation+0.000
Top resid features:
defense
Token defense
Feature activation+0.000
Top resid features:
was
Token was
Feature activation-0.018
Top resid features:
perfect
Token perfect
Feature activation-0.014
Top resid features:
.
Token.
Feature activation-0.035
Top resid features:
She
Token She
Feature activation-0.042
Top resid features:
had
Token had
Feature activation-0.147
Top resid features:
that
Token that
Feature activation+2.790
Top resid features:
old
Token old
Feature activation+0.067
Top resid features:
-
Token-
Feature activation-0.010
Top resid features:
school
Tokenschool
Feature activation-0.006
Top resid features:
grit
Token grit
Feature activation-0.051
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.023
Top resid features:
It
Token It
Feature activation-0.006
Top resid features:
just
Token just
Feature activation-0.030
Top resid features:
gave
Token gave
Feature activation-0.031
Top resid features:
you
Token you
Feature activation-0.082
Top resid features:
that
Token that
Feature activation+2.700
Top resid features:
eerie
Token eerie
Feature activation+0.053
Top resid features:
feeling
Token feeling
Feature activation-0.046
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
back
Token back
Feature activation-0.004
Top resid features:
on
Token on
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
rel
Token rel
Feature activation-0.040
Top resid features:
ive
Tokenive
Feature activation-0.047
Top resid features:
that
Token that
Feature activation+2.378
Top resid features:
special
Token special
Feature activation+0.089
Top resid features:
high
Token high
Feature activation+0.164
Top resid features:
school
Token school
Feature activation+0.000
Top resid features:
magic
Token magic
Feature activation+0.000
Top resid features:
once
Token once
Feature activation+0.000
Top resid features:
good
Token good
Feature activation+0.006
Top resid features:
indie
Token indie
Feature activation+0.001
Top resid features:
rock
Token rock
Feature activation+0.004
Top resid features:
looks
Token looks
Feature activation-0.002
Top resid features:
at
Token at
Feature activation-0.061
Top resid features:
that
Token that
Feature activation+2.566
Top resid features:
looming
Token looming
Feature activation+0.009
Top resid features:
question
Token question
Feature activation-0.030
Top resid features:
of
Token of
Feature activation-0.024
Top resid features:
relevance
Token relevance
Feature activation+0.000
Top resid features:
square
Token square
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation-0.033
Top resid features:
So
TokenSo
Feature activation-0.001
Top resid features:
we
Token we
Feature activation+0.009
Top resid features:
went
Token went
Feature activation-0.005
Top resid features:
into
Token into
Feature activation-0.020
Top resid features:
that
Token that
Feature activation+2.482
Top resid features:
protective
Token protective
Feature activation+0.060
Top resid features:
motorcycle
Token motorcycle
Feature activation+0.071
Top resid features:
look
Token look
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
after
Token after
Feature activation-0.013
Top resid features:
going
Token going
Feature activation+0.029
Top resid features:
far
Token far
Feature activation-0.009
Top resid features:
enough
Token enough
Feature activation-0.043
Top resid features:
down
Token down
Feature activation+0.018
Top resid features:
that
Token that
Feature activation+2.258
Top resid features:
rabbit
Token rabbit
Feature activation+0.071
Top resid features:
hole
Token hole
Feature activation+0.232
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
40
Token 40
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.017
Top resid features:
It
Token It
Feature activation+0.003
Top resid features:
just
Token just
Feature activation-0.009
Top resid features:
gave
Token gave
Feature activation-0.011
Top resid features:
you
Token you
Feature activation-0.026
Top resid features:
that
Token that
Feature activation+2.545
Top resid features:
eerie
Token eerie
Feature activation+0.063
Top resid features:
feeling
Token feeling
Feature activation-0.200
Top resid features:
of
Token of
Feature activation+0.054
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
when
Token when
Feature activation-0.047
Top resid features:
you
Token you
Feature activation-0.018
Top resid features:
got
Token got
Feature activation-0.014
Top resid features:
up
Token up
Feature activation+0.001
Top resid features:
at
Token at
Feature activation+0.028
Top resid features:
that
Token that
Feature activation+2.643
Top resid features:
South
Token South
Feature activation+0.020
Top resid features:
Carolina
Token Carolina
Feature activation-0.027
Top resid features:
GOP
Token GOP
Feature activation-0.050
Top resid features:
presidential
Token presidential
Feature activation-0.048
Top resid features:
debate
Token debate
Feature activation-0.048
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.06

Head 2: 0.41

Head 3: 0.04

Head 4: 0.02

Head 5: 0.03

Head 6: 0.07

Head 7: 0.09

Head 8: 0.06

Head 9: 0.05

Head 10: 0.07

Head 11: 0.08

Positive logits

isphere1.47

ungle1.23

craw1.19

keleton1.18

AVG1.16

angle1.15

acid1.14

Lamar1.14

itch1.13

headache1.12

Asheville1.11

elight1.11

footed1.10

undrum1.09

ixture1.09

adle1.08

hetic1.08

ylum1.06

cca1.05

assian1.04

Negative logits

Tablet-1.35

orously-1.20

Entered-1.16

Platform-1.11

Guest-1.10

showc-1.10

condem-1.09

CLASSIFIED-1.09

Stand-1.07

Video-1.07

Recommend-1.07

Correspond-1.05

Bron-1.04

PT-1.04

Works-1.03

Platform-1.03

Marshal-1.02

catentry-1.02

emergencies-1.01

-0.98

INTERVAL 2.664 - 2.960
CONTAINS 0.000%

that
Token that
Feature activation+0.000
unlikely
Token unlikely
Feature activation+1.105
-
Token-
Feature activation+1.160
se
Tokense
Feature activation+1.027
eming
Tokeneming
Feature activation+1.454
victory
Token victory
Feature activation+2.792
.
Token.
Feature activation+0.000
How
Token How
Feature activation+0.000
could
Token could
Feature activation+0.000
the
Token the
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
conversation
Token conversation
Feature activation+0.000
at
Token at
Feature activation+0.000
that
Token that
Feature activation+0.000
dinner
Token dinner
Feature activation+2.100
party
Token party
Feature activation+2.960
is
Token is
Feature activation+0.090
likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
completely
Token completely
Feature activation+0.000

INTERVAL 2.368 - 2.664
CONTAINS 0.001%

national
Token national
Feature activation+0.000
television
Token television
Feature activation+0.000
to
Token to
Feature activation+0.000
that
Token that
Feature activation+0.000
moment
Token moment
Feature activation+1.034
of
Token of
Feature activation+2.469
spont
Token spont
Feature activation+0.151
ane
Tokenane
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
on
Token on
Feature activation+0.135
the
Token the
Feature activation+0.000
went
Token went
Feature activation+0.000
into
Token into
Feature activation+0.000
that
Token that
Feature activation+0.000
protective
Token protective
Feature activation+1.328
motorcycle
Token motorcycle
Feature activation+2.263
look
Token look
Feature activation+2.415
from
Token from
Feature activation+1.098
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
hung
Token hung
Feature activation+0.000
players
Token players
Feature activation+0.000
on
Token on
Feature activation+0.000
that
Token that
Feature activation+0.000
kickoff
Token kickoff
Feature activation+1.001
coverage
Token coverage
Feature activation+1.909
unit
Token unit
Feature activation+2.452
who
Token who
Feature activation+0.151
graded
Token graded
Feature activation+0.000
out
Token out
Feature activation+0.000
positively
Token positively
Feature activation+0.000
.
Token.
Feature activation+0.000
erase
Token erase
Feature activation+0.000
that
Token that
Feature activation+0.000
$
Token $
Feature activation+0.800
100
Token100
Feature activation+1.841
million
Token million
Feature activation+1.910
difference
Token difference
Feature activation+2.477
in
Token in
Feature activation+0.450
the
Token the
Feature activation+0.000
near
Token near
Feature activation+0.000
future
Token future
Feature activation+0.000
.
Token.
Feature activation+0.000
o
Tokeno
Feature activation+0.000
iled
Tokeniled
Feature activation+0.000
from
Token from
Feature activation+0.000
that
Token that
Feature activation+0.000
aspect
Token aspect
Feature activation+0.952
of
Token of
Feature activation+2.428
Spider
Token Spider
Feature activation+0.200
-
Token-
Feature activation+0.000
Man
TokenMan
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000

INTERVAL 2.072 - 2.368
CONTAINS 0.003%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Despite
TokenDespite
Feature activation+0.000
that
Token that
Feature activation+0.000
tiny
Token tiny
Feature activation+1.582
shred
Token shred
Feature activation+2.328
of
Token of
Feature activation+2.340
optimism
Token optimism
Feature activation+0.491
of
Token of
Feature activation+0.732
any
Token any
Feature activation+0.000
crossover
Token crossover
Feature activation+0.000
you
Token you
Feature activation+0.000
buy
Token buy
Feature activation+0.000
into
Token into
Feature activation+0.000
that
Token that
Feature activation+0.000
line
Token line
Feature activation+1.169
of
Token of
Feature activation+2.366
thinking
Token thinking
Feature activation+0.455
,
Token,
Feature activation+0.000
consider
Token consider
Feature activation+0.000
the
Token the
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
we
Token we
Feature activation+0.000
went
Token went
Feature activation+0.000
into
Token into
Feature activation+0.000
that
Token that
Feature activation+0.000
protective
Token protective
Feature activation+1.328
motorcycle
Token motorcycle
Feature activation+2.263
look
Token look
Feature activation+2.415
from
Token from
Feature activation+1.098
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
ros
Tokenros
Feature activation+0.000
via
Token via
Feature activation+0.000
that
Token that
Feature activation+0.000
trust
Token trust
Feature activation+1.240
y
Tokeny
Feature activation+0.745
red
Token red
Feature activation+2.179
square
Token square
Feature activation+0.432
freeze
Token freeze
Feature activation+0.784
button
Token button
Feature activation+1.116
and
Token and
Feature activation+0.069
my
Token my
Feature activation+0.000
inappropriate
Token inappropriate
Feature activation+0.000
reaction
Token reaction
Feature activation+0.000
to
Token to
Feature activation+0.000
that
Token that
Feature activation+0.000
bill
Token bill
Feature activation+1.774
to
Token to
Feature activation+2.189
call
Token call
Feature activation+0.454
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
boycott
Token boycott
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.776 - 2.072
CONTAINS 0.006%

-
Token-
Feature activation+0.000
u
Tokenu
Feature activation+0.000
pped
Tokenpped
Feature activation+0.000
that
Token that
Feature activation+0.000
conspiracy
Token conspiracy
Feature activation+1.473
theory
Token theory
Feature activation+2.070
,
Token,
Feature activation+1.034
saying
Token saying
Feature activation+0.000
that
Token that
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
culture
Token culture
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
that
Token that
Feature activation+0.000
mindset
Token mindset
Feature activation+1.955
,
Token,
Feature activation+1.865
keeps
Token keeps
Feature activation+0.000
reaff
Token reaff
Feature activation+0.000
irming
Tokenirming
Feature activation+0.000
that
Token that
Feature activation+0.000
there
Token there
Feature activation+0.000
s
Tokens
Feature activation+0.000
hold
Token hold
Feature activation+0.000
onto
Token onto
Feature activation+0.000
that
Token that
Feature activation+0.000
optimistic
Token optimistic
Feature activation+1.123
interpretation
Token interpretation
Feature activation+1.907
for
Token for
Feature activation+0.663
a
Token a
Feature activation+0.000
minute
Token minute
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
so
Token so
Feature activation+0.000
help
Token help
Feature activation+0.000
to
Token to
Feature activation+0.000
fulfill
Token fulfill
Feature activation+0.000
that
Token that
Feature activation+0.000
dream
Token dream
Feature activation+1.897
of
Token of
Feature activation+2.228
a
Token a
Feature activation+0.902
future
Token future
Feature activation+0.000
of
Token of
Feature activation+0.000
peace
Token peace
Feature activation+0.000
political
Token political
Feature activation+0.000
power
Token power
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
tiny
Token tiny
Feature activation+1.209
spot
Token spot
Feature activation+1.946
of
Token of
Feature activation+1.917
southeastern
Token southeastern
Feature activation+0.820
Kentucky
Token Kentucky
Feature activation+0.144
.
Token.
Feature activation+0.000
Everything
Token Everything
Feature activation+0.000

INTERVAL 1.480 - 1.776
CONTAINS 0.012%

.
Token.
Feature activation+0.000
Waiting
Token Waiting
Feature activation+0.000
until
Token until
Feature activation+0.000
that
Token that
Feature activation+0.000
ring
Token ring
Feature activation+1.462
shr
Token shr
Feature activation+1.651
inks
Tokeninks
Feature activation+0.159
to
Token to
Feature activation+0.000
its
Token its
Feature activation+0.000
smallest
Token smallest
Feature activation+0.000
size
Token size
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
always
Token always
Feature activation+0.000
love
Token love
Feature activation+0.000
that
Token that
Feature activation+0.000
fight
Token fight
Feature activation+1.627
again
Token again
Feature activation+0.667
but
Token but
Feature activation+0.206
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
it
Token it
Feature activation+0.000
can
Token can
Feature activation+0.000
use
Token use
Feature activation+0.000
that
Token that
Feature activation+0.000
information
Token information
Feature activation+0.672
to
Token to
Feature activation+1.533
match
Token match
Feature activation+0.000
potential
Token potential
Feature activation+0.000
advertisers
Token advertisers
Feature activation+0.000
program
Token program
Feature activation+0.000
matically
Tokenmatically
Feature activation+0.000
.
Token.
Feature activation+0.000
Watching
Token Watching
Feature activation+0.000
that
Token that
Feature activation+0.000
boss
Token boss
Feature activation+1.407
monster
Token monster
Feature activation+2.519
explode
Token explode
Feature activation+1.496
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
shower
Token shower
Feature activation+0.000
of
Token of
Feature activation+0.000
items
Token items
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
value
Token value
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
contract
Token contract
Feature activation+1.558
soared
Token soared
Feature activation+0.288
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
92
Token 92
Feature activation+0.000
percent
Token percent
Feature activation+0.000

INTERVAL 1.184 - 1.480
CONTAINS 0.020%

.
Token.
Feature activation+0.000
More
Token More
Feature activation+0.000
on
Token on
Feature activation+0.000
that
Token that
Feature activation+0.000
folly
Token folly
Feature activation+1.373
in
Token in
Feature activation+1.472
another
Token another
Feature activation+0.000
article
Token article
Feature activation+0.000
.]
Token.]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
how
Token how
Feature activation+0.000
being
Token being
Feature activation+0.000
around
Token around
Feature activation+0.000
for
Token for
Feature activation+0.000
that
Token that
Feature activation+0.000
amount
Token amount
Feature activation+1.367
of
Token of
Feature activation+1.890
time
Token time
Feature activation+1.148
comes
Token comes
Feature activation+0.000
with
Token with
Feature activation+0.000
its
Token its
Feature activation+0.000
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
u
Tokenu
Feature activation+0.000
pped
Tokenpped
Feature activation+0.000
that
Token that
Feature activation+0.000
conspiracy
Token conspiracy
Feature activation+1.473
theory
Token theory
Feature activation+2.070
,
Token,
Feature activation+1.034
saying
Token saying
Feature activation+0.000
that
Token that
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
and
Token and
Feature activation+0.000
who
Token who
Feature activation+0.000
can
Token can
Feature activation+0.000
forget
Token forget
Feature activation+0.000
that
Token that
Feature activation+0.000
deadly
Token deadly
Feature activation+1.327
no
Token no
Feature activation+0.000
-
Token-
Feature activation+0.000
look
Tokenlook
Feature activation+0.000
pass
Token pass
Feature activation+0.000
he
Token he
Feature activation+0.000
not
Token not
Feature activation+0.000
directly
Token directly
Feature activation+0.000
shaped
Token shaped
Feature activation+0.000
by
Token by
Feature activation+0.000
that
Token that
Feature activation+0.000
Internet
Token Internet
Feature activation+1.326
culture
Token culture
Feature activation+2.104
,
Token,
Feature activation+0.483
he
Token he
Feature activation+0.000
nonetheless
Token nonetheless
Feature activation+0.000
moved
Token moved
Feature activation+0.000

INTERVAL 0.888 - 1.184
CONTAINS 0.025%

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
like
Token like
Feature activation+0.000
that
Token that
Feature activation+0.000
thing
Token thing
Feature activation+0.865
,
Token,
Feature activation+0.990
which
Token which
Feature activation+0.338
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
our
Token our
Feature activation+0.000
job
Token job
Feature activation+0.000
't
Token't
Feature activation+0.000
listen
Token listen
Feature activation+0.000
to
Token to
Feature activation+0.000
all
Token all
Feature activation+0.000
that
Token that
Feature activation+0.000
negativity
Token negativity
Feature activation+0.991
out
Token out
Feature activation+0.682
there
Token there
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
free
Token free
Feature activation+0.000
up
Token up
Feature activation+0.000
capacity
Token capacity
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
corridor
Token corridor
Feature activation+1.138
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
Metro
Token Metro
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
watch
Token watch
Feature activation+0.000
that
Token that
Feature activation+0.000
jaw
Token jaw
Feature activation+1.205
-
Token-
Feature activation+0.959
dro
Tokendro
Feature activation+0.966
pped
Tokenpped
Feature activation+2.064
,
Token,
Feature activation+1.347
utterly
Token utterly
Feature activation+0.000
lost
Token lost
Feature activation+1.322
interact
Token interact
Feature activation+0.000
badly
Token badly
Feature activation+0.000
with
Token with
Feature activation+0.000
that
Token that
Feature activation+0.000
intervention
Token intervention
Feature activation+1.185
,
Token,
Feature activation+1.013
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
should
Token should
Feature activation+0.000
intervene
Token intervene
Feature activation+0.000

INTERVAL 0.592 - 0.888
CONTAINS 0.036%

just
Token just
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
that
Token that
Feature activation+0.000
physical
Token physical
Feature activation+0.704
writing
Token writing
Feature activation+0.814
there
Token there
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
permanently
Token permanently
Feature activation+0.000
remove
Token remove
Feature activation+0.000
that
Token that
Feature activation+0.000
authority
Token authority
Feature activation+0.736
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
watch
Token watch
Feature activation+0.000
.
Token.
Feature activation+0.000
Having
Token Having
Feature activation+0.000
that
Token that
Feature activation+0.000
kind
Token kind
Feature activation+0.377
of
Token of
Feature activation+0.758
control
Token control
Feature activation+0.567
over
Token over
Feature activation+1.042
a
Token a
Feature activation+0.150
crowd
Token crowd
Feature activation+0.000
is
Token is
Feature activation+0.000
election
Token election
Feature activation+0.000
.
Token.
Feature activation+0.000
Among
Token Among
Feature activation+0.000
just
Token just
Feature activation+0.000
that
Token that
Feature activation+0.000
group
Token group
Feature activation+0.794
,
Token,
Feature activation+0.681
Romney
Token Romney
Feature activation+0.000
tops
Token tops
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
by
Token by
Feature activation+0.000
int
Token int
Feature activation+0.000
ros
Tokenros
Feature activation+0.000
via
Token via
Feature activation+0.000
that
Token that
Feature activation+0.000
trust
Token trust
Feature activation+1.240
y
Tokeny
Feature activation+0.745
red
Token red
Feature activation+2.179
square
Token square
Feature activation+0.432
freeze
Token freeze
Feature activation+0.784
button
Token button
Feature activation+1.116
and
Token and
Feature activation+0.069

INTERVAL 0.296 - 0.592
CONTAINS 0.051%

about
Token about
Feature activation+0.000
that
Token that
Feature activation+0.000
day
Token day
Feature activation+0.982
,
Token,
Feature activation+1.277
that
Token that
Feature activation+0.000
fall
Token fall
Feature activation+0.313
and
Token and
Feature activation+0.460
getting
Token getting
Feature activation+0.000
straight
Token straight
Feature activation+0.000
back
Token back
Feature activation+0.000
out
Token out
Feature activation+0.000
wish
Token wish
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
that
Token that
Feature activation+0.000
thought
Token thought
Feature activation+0.245
out
Token out
Feature activation+0.425
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
no
Token no
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
and
Tokenand
Feature activation+0.000
for
Token for
Feature activation+0.000
that
Token that
Feature activation+0.000
matter
Token matter
Feature activation+1.087
,
Token,
Feature activation+0.734
ability
Token ability
Feature activation+0.450
)
Token)
Feature activation+0.000
to
Token to
Feature activation+0.000
invest
Token invest
Feature activation+0.000
money
Token money
Feature activation+0.000
where
Token where
Feature activation+0.000
remove
Token remove
Feature activation+0.000
that
Token that
Feature activation+0.000
piece
Token piece
Feature activation+1.546
of
Token of
Feature activation+2.224
metal
Token metal
Feature activation+0.416
when
Token when
Feature activation+0.432
they
Token they
Feature activation+0.000
go
Token go
Feature activation+0.000
through
Token through
Feature activation+0.000
security
Token security
Feature activation+0.000
.
Token.
Feature activation+0.000
shooting
Token shooting
Feature activation+0.000
percentage
Token percentage
Feature activation+0.000
on
Token on
Feature activation+0.000
those
Token those
Feature activation+0.000
252
Token 252
Feature activation+0.000
shots
Token shots
Feature activation+0.429
,
Token,
Feature activation+0.000
well
Token well
Feature activation+0.000
below
Token below
Feature activation+0.000
his
Token his
Feature activation+0.000
career
Token career
Feature activation+0.000

INTERVAL 0.000 - 0.296
CONTAINS 99.847%

in
Token in
Feature activation+0.000
9
Token 9
Feature activation+0.000
games
Token games
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
a
Token a
Feature activation+0.000
goal
Token goal
Feature activation+0.000
and
Token and
Feature activation+0.000
an
Token an
Feature activation+0.000
assist
Token assist
Feature activation+0.000
in
Token in
Feature activation+0.000
were
Token were
Feature activation+0.244
the
Token the
Feature activation+0.000
focus
Token focus
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
recent
Token recent
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
-
Token-
Feature activation+0.000
sponsored
Tokensponsored
Feature activation+0.000
conference
Token conference
Feature activation+0.000
Manchester
Token Manchester
Feature activation+0.000
attack
Token attack
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
authentic
Token authentic
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
all
Token all
Feature activation+0.000
guilty
Token guilty
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
let
Token let
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
put
Token put
Feature activation+0.000
it
Token it
Feature activation+0.000
behind
Token behind
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
bug
Token bug
Feature activation+0.000
was
Token was
Feature activation+0.000
being
Token being
Feature activation+0.000
frequently
Token frequently
Feature activation+0.000
rep
Token rep
Feature activation+0.000
rogram
Tokenrogram
Feature activation+0.000
med
Tokenmed
Feature activation+0.000
to
Token to
Feature activation+0.000
target
Token target
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 H3.2: (feature 21677)

TOP ACTIVATIONS
MAX = 4.226

I
Token I
Feature activation+0.000
believe
Token believe
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
too
Token too
Feature activation+0.000
consumed
Token consumed
Feature activation+4.226
by
Token by
Feature activation+1.586
me
Token me
Feature activation+0.000
gal
Tokengal
Feature activation+0.000
oman
Tokenoman
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000
Too
Token Too
Feature activation+0.000
fl
Token fl
Feature activation+2.857
irty
Tokenirty
Feature activation+3.858
at
Token at
Feature activation+0.343
work
Token work
Feature activation+0.000
mean
Token mean
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ride
Token ride
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
too
Token too
Feature activation+0.000
bump
Token bump
Feature activation+2.372
y
Tokeny
Feature activation+3.792
for
Token for
Feature activation+0.439
Bobby
Token Bobby
Feature activation+0.000
(
Token (
Feature activation+0.000
Mark
TokenMark
Feature activation+0.000
Boone
Token Boone
Feature activation+0.000
life
Token life
Feature activation+0.000
was
Token was
Feature activation+0.000
cut
Token cut
Feature activation+0.000
far
Token far
Feature activation+0.000
too
Token too
Feature activation+0.000
short
Token short
Feature activation+3.649
.
Token.
Feature activation+0.000
My
Token My
Feature activation+0.000
condolences
Token condolences
Feature activation+0.000
go
Token go
Feature activation+0.000
out
Token out
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
too
Token too
Feature activation+0.000
busy
Token busy
Feature activation+3.615
for
Token for
Feature activation+0.152
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.000
story
Token story
Feature activation+0.000
,
Token,
Feature activation+0.000
Step
Token Step
Feature activation+0.000
dad
Tokendad
Feature activation+0.000
who
Token who
Feature activation+0.000
tries
Token tries
Feature activation+0.000
too
Token too
Feature activation+0.000
hard
Token hard
Feature activation+3.588
to
Token to
Feature activation+2.411
be
Token be
Feature activation+0.099
called
Token called
Feature activation+0.000
dad
Token dad
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Changing
TokenChanging
Feature activation+0.000
too
Token too
Feature activation+0.000
slowly
Token slowly
Feature activation+3.447
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Will
TokenWill
Feature activation+0.000
these
Token these
Feature activation+0.000
physiological
Token physiological
Feature activation+0.000
t
Tokent
Feature activation+0.000
show
Token show
Feature activation+0.000
size
Token size
Feature activation+0.000
differences
Token differences
Feature activation+0.000
too
Token too
Feature activation+0.000
drastically
Token drastically
Feature activation+3.395
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
however
Token however
Feature activation+0.000
have
Token have
Feature activation+0.000
always
Token always
Feature activation+0.000
There
Token There
Feature activation+0.000
were
Token were
Feature activation+0.000
Ferr
Token Ferr
Feature activation+0.000
aris
Tokenaris
Feature activation+0.000
too
Token too
Feature activation+0.000
and
Token and
Feature activation+3.330
not
Token not
Feature activation+0.000
just
Token just
Feature activation+0.000
any
Token any
Feature activation+0.000
Ferr
Token Ferr
Feature activation+0.000
aris
Tokenaris
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
too
Token too
Feature activation+0.000
important
Token important
Feature activation+3.303
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
future
Token future
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
arrived
Token arrived
Feature activation+0.000
because
Token because
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
too
Token too
Feature activation+0.000
scared
Token scared
Feature activation+3.303
to
Token to
Feature activation+0.280
go
Token go
Feature activation+0.000
out
Token out
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Sn
Token Sn
Feature activation+0.000
team
Token team
Feature activation+0.000
has
Token has
Feature activation+0.000
committed
Token committed
Feature activation+0.000
too
Token too
Feature activation+0.000
much
Token much
Feature activation+2.272
time
Token time
Feature activation+3.296
to
Token to
Feature activation+0.000
Griffin
Token Griffin
Feature activation+0.000
for
Token for
Feature activation+0.000
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
he
Token he
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
't
Token't
Feature activation+0.000
trying
Token trying
Feature activation+0.000
too
Token too
Feature activation+0.000
hard
Token hard
Feature activation+3.294
,
Token,
Feature activation+0.909
I
Token I
Feature activation+0.000
'll
Token'll
Feature activation+0.000
tell
Token tell
Feature activation+0.000
you
Token you
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.000
also
Token also
Feature activation+0.000
strong
Token strong
Feature activation+0.000
too
Token too
Feature activation+0.000
and
Token and
Feature activation+3.113
will
Token will
Feature activation+0.404
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.249
very
Token very
Feature activation+0.000
good
Token good
Feature activation+0.000
people
Token people
Feature activation+0.000
out
Token out
Feature activation+0.000
there
Token there
Feature activation+0.000
trying
Token trying
Feature activation+0.000
too
Token too
Feature activation+0.000
hard
Token hard
Feature activation+3.106
to
Token to
Feature activation+1.477
spot
Token spot
Feature activation+0.000
them
Token them
Feature activation+0.000
or
Token or
Feature activation+0.000
interact
Token interact
Feature activation+0.000
tyre
Token tyre
Feature activation+0.000
compounds
Token compounds
Feature activation+0.000
are
Token are
Feature activation+0.000
far
Token far
Feature activation+0.000
too
Token too
Feature activation+0.000
hard
Token hard
Feature activation+3.081
this
Token this
Feature activation+0.811
year
Token year
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
Red
Token Red
Feature activation+0.000
each
Token each
Feature activation+0.000
others
Token others
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
,
Token,
Feature activation+0.000
too
Token too
Feature activation+0.000
afraid
Token afraid
Feature activation+3.080
to
Token to
Feature activation+0.116
talk
Token talk
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
love
Token love
Feature activation+0.000
proper
Token proper
Feature activation+0.000
book
Token book
Feature activation+0.000
proposal
Token proposal
Feature activation+0.000
as
Token as
Feature activation+0.000
too
Token too
Feature activation+0.000
risky
Token risky
Feature activation+3.023
.[
Token.[
Feature activation+0.000
10
Token10
Feature activation+0.000
]
Token]
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
too
Token too
Feature activation+0.000
dramatic
Token dramatic
Feature activation+2.333
a
Token a
Feature activation+3.015
change
Token change
Feature activation+0.000
for
Token for
Feature activation+0.000
them
Token them
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
reports
Token reports
Feature activation+0.000
as
Token as
Feature activation+0.000
too
Token too
Feature activation+0.000
expensive
Token expensive
Feature activation+3.014
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
using
Tokenusing
Feature activation+0.000

Top DFA by src position
MAX = 5.024

,
Token,
Feature activation+0.007
Top resid features:
I
Token I
Feature activation+0.003
Top resid features:
believe
Token believe
Feature activation+0.024
Top resid features:
he
Token he
Feature activation+0.103
Top resid features:
was
Token was
Feature activation-0.068
Top resid features:
too
Token too
Feature activation+4.634
Top resid features:
consumed
Token consumed
Feature activation+0.390
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
gal
Tokengal
Feature activation+0.000
Top resid features:
oman
Tokenoman
Feature activation+0.000
Top resid features:
re
Tokenre
Feature activation-0.008
Top resid features:
supposed
Token supposed
Feature activation+0.018
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
be
Token be
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.054
Top resid features:
Too
Token Too
Feature activation+4.455
Top resid features:
fl
Token fl
Feature activation+0.044
Top resid features:
irty
Tokenirty
Feature activation+0.161
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
work
Token work
Feature activation+0.000
Top resid features:
mean
Token mean
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation-0.006
Top resid features:
final
Token final
Feature activation-0.014
Top resid features:
ride
Token ride
Feature activation-0.016
Top resid features:
will
Token will
Feature activation+0.011
Top resid features:
be
Token be
Feature activation-0.059
Top resid features:
too
Token too
Feature activation+4.453
Top resid features:
bump
Token bump
Feature activation+0.261
Top resid features:
y
Tokeny
Feature activation+0.056
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Bobby
Token Bobby
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.008
Top resid features:
life
Token life
Feature activation-0.001
Top resid features:
was
Token was
Feature activation-0.038
Top resid features:
cut
Token cut
Feature activation+0.102
Top resid features:
far
Token far
Feature activation-0.043
Top resid features:
too
Token too
Feature activation+4.349
Top resid features:
short
Token short
Feature activation+0.091
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
My
Token My
Feature activation+0.000
Top resid features:
condolences
Token condolences
Feature activation+0.000
Top resid features:
go
Token go
Feature activation+0.000
Top resid features:
if
Token if
Feature activation-0.046
Top resid features:
you
Token you
Feature activation+0.109
Top resid features:
âĢ
TokenâĢ
Feature activation+0.050
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
re
Tokenre
Feature activation-0.115
Top resid features:
too
Token too
Feature activation+4.305
Top resid features:
busy
Token busy
Feature activation+0.233
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
whole
Token whole
Feature activation+0.000
Top resid features:
story
Token story
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.015
Top resid features:
Step
Token Step
Feature activation-0.001
Top resid features:
dad
Tokendad
Feature activation-0.002
Top resid features:
who
Token who
Feature activation-0.020
Top resid features:
tries
Token tries
Feature activation-0.621
Top resid features:
too
Token too
Feature activation+5.024
Top resid features:
hard
Token hard
Feature activation+0.136
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
called
Token called
Feature activation+0.000
Top resid features:
dad
Token dad
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.069
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.013
Top resid features:
Changing
TokenChanging
Feature activation-0.356
Top resid features:
too
Token too
Feature activation+4.401
Top resid features:
slowly
Token slowly
Feature activation+0.303
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Will
TokenWill
Feature activation+0.000
Top resid features:
these
Token these
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
t
Tokent
Feature activation+0.012
Top resid features:
show
Token show
Feature activation-0.101
Top resid features:
size
Token size
Feature activation-0.159
Top resid features:
differences
Token differences
Feature activation-0.040
Top resid features:
too
Token too
Feature activation+4.318
Top resid features:
drastically
Token drastically
Feature activation+0.198
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
however
Token however
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.053
Top resid features:
There
Token There
Feature activation-0.054
Top resid features:
were
Token were
Feature activation-0.003
Top resid features:
Ferr
Token Ferr
Feature activation-0.001
Top resid features:
aris
Tokenaris
Feature activation-0.051
Top resid features:
too
Token too
Feature activation+4.197
Top resid features:
and
Token and
Feature activation+0.058
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
Ferr
Token Ferr
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.080
Top resid features:
,
Token,
Feature activation-0.052
Top resid features:
it
Token it
Feature activation-0.110
Top resid features:
's
Token's
Feature activation-0.045
Top resid features:
too
Token too
Feature activation+4.353
Top resid features:
important
Token important
Feature activation+0.042
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
future
Token future
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.019
Top resid features:
arrived
Token arrived
Feature activation-0.090
Top resid features:
because
Token because
Feature activation+0.044
Top resid features:
he
Token he
Feature activation+0.166
Top resid features:
was
Token was
Feature activation+0.010
Top resid features:
too
Token too
Feature activation+3.839
Top resid features:
scared
Token scared
Feature activation+0.237
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
go
Token go
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
think
Token think
Feature activation-0.018
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
team
Token team
Feature activation+0.085
Top resid features:
has
Token has
Feature activation-0.107
Top resid features:
committed
Token committed
Feature activation-0.109
Top resid features:
too
Token too
Feature activation+4.233
Top resid features:
much
Token much
Feature activation+0.015
Top resid features:
time
Token time
Feature activation+0.072
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Griffin
Token Griffin
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.017
Top resid features:
he
Token he
Feature activation+0.082
Top resid features:
wasn
Token wasn
Feature activation+0.029
Top resid features:
't
Token't
Feature activation+0.270
Top resid features:
trying
Token trying
Feature activation-0.454
Top resid features:
too
Token too
Feature activation+4.050
Top resid features:
hard
Token hard
Feature activation+0.115
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
'll
Token'll
Feature activation+0.000
Top resid features:
tell
Token tell
Feature activation+0.000
Top resid features:
but
Token but
Feature activation-0.017
Top resid features:
he
Token he
Feature activation+0.018
Top resid features:
's
Token's
Feature activation-0.014
Top resid features:
also
Token also
Feature activation-0.051
Top resid features:
strong
Token strong
Feature activation-0.053
Top resid features:
too
Token too
Feature activation+4.093
Top resid features:
and
Token and
Feature activation+0.104
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
very
Token very
Feature activation+0.000
Top resid features:
want
Token want
Feature activation+0.024
Top resid features:
people
Token people
Feature activation-0.019
Top resid features:
out
Token out
Feature activation+0.070
Top resid features:
there
Token there
Feature activation-0.100
Top resid features:
trying
Token trying
Feature activation-0.567
Top resid features:
too
Token too
Feature activation+4.401
Top resid features:
hard
Token hard
Feature activation+0.120
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
spot
Token spot
Feature activation+0.000
Top resid features:
them
Token them
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
harder
Token harder
Feature activation-0.064
Top resid features:
tyre
Token tyre
Feature activation-0.026
Top resid features:
compounds
Token compounds
Feature activation-0.047
Top resid features:
are
Token are
Feature activation-0.089
Top resid features:
far
Token far
Feature activation+0.127
Top resid features:
too
Token too
Feature activation+3.768
Top resid features:
hard
Token hard
Feature activation+0.347
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
according
Token according
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
into
Token into
Feature activation-0.010
Top resid features:
each
Token each
Feature activation+0.002
Top resid features:
others
Token others
Feature activation-0.010
Top resid features:
eyes
Token eyes
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.039
Top resid features:
too
Token too
Feature activation+3.423
Top resid features:
afraid
Token afraid
Feature activation+0.354
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
talk
Token talk
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.010
Top resid features:
proper
Token proper
Feature activation-0.008
Top resid features:
book
Token book
Feature activation+0.011
Top resid features:
proposal
Token proposal
Feature activation+0.017
Top resid features:
as
Token as
Feature activation+0.077
Top resid features:
too
Token too
Feature activation+3.342
Top resid features:
risky
Token risky
Feature activation+0.411
Top resid features:
.[
Token.[
Feature activation+0.000
Top resid features:
10
Token10
Feature activation+0.000
Top resid features:
]
Token]
Feature activation+0.000
Top resid features:
However
Token However
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
but
Token but
Feature activation-0.026
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
can
Token can
Feature activation+0.042
Top resid features:
be
Token be
Feature activation-0.001
Top resid features:
too
Token too
Feature activation+3.627
Top resid features:
dramatic
Token dramatic
Feature activation+0.268
Top resid features:
a
Token a
Feature activation+0.028
Top resid features:
change
Token change
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
them
Token them
Feature activation+0.000
Top resid features:
dismissed
Token dismissed
Feature activation+0.118
Top resid features:
in
Token in
Feature activation-0.029
Top resid features:
the
Token the
Feature activation-0.013
Top resid features:
reports
Token reports
Feature activation+0.022
Top resid features:
as
Token as
Feature activation+0.086
Top resid features:
too
Token too
Feature activation+3.653
Top resid features:
expensive
Token expensive
Feature activation+0.125
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
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:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.03

Head 2: 0.41

Head 3: 0.04

Head 4: 0.02

Head 5: 0.03

Head 6: 0.05

Head 7: 0.05

Head 8: 0.07

Head 9: 0.03

Head 10: 0.08

Head 11: 0.17

Positive logits

acket1.22

too1.15

inventoryQuantity1.11

agric1.07

mus1.01

ugu1.01

athlet1.00

spoiled1.00

surely1.00

Territory0.99

comprom0.99

insofar0.98

reckoned0.98

sway0.97

atched0.97

Calories0.95

bounces0.95

oneliness0.94

sounding0.94

ointed0.93

Negative logits

mini-1.14

-1.13

ctions-1.08

umbn-1.06

TRANS-1.04

isks-1.03

USS-1.01

ief-0.99

statement-0.98

OPLE-0.98

design-0.98

idan-0.98

BEN-0.97

pillar-0.97

CTV-0.97

foundation-0.97

Wiki-0.96

ILS-0.96

tto-0.95

ELS-0.95

INTERVAL 3.803 - 4.226
CONTAINS 0.000%

to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000
Too
Token Too
Feature activation+0.000
fl
Token fl
Feature activation+2.857
irty
Tokenirty
Feature activation+3.858
at
Token at
Feature activation+0.343
work
Token work
Feature activation+0.000
mean
Token mean
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
I
Token I
Feature activation+0.000
believe
Token believe
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
too
Token too
Feature activation+0.000
consumed
Token consumed
Feature activation+4.226
by
Token by
Feature activation+1.586
me
Token me
Feature activation+0.000
gal
Tokengal
Feature activation+0.000
oman
Tokenoman
Feature activation+0.000
ia
Tokenia
Feature activation+0.000

INTERVAL 3.380 - 3.803
CONTAINS 0.001%

life
Token life
Feature activation+0.000
was
Token was
Feature activation+0.000
cut
Token cut
Feature activation+0.000
far
Token far
Feature activation+0.000
too
Token too
Feature activation+0.000
short
Token short
Feature activation+3.649
.
Token.
Feature activation+0.000
My
Token My
Feature activation+0.000
condolences
Token condolences
Feature activation+0.000
go
Token go
Feature activation+0.000
out
Token out
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
too
Token too
Feature activation+0.000
busy
Token busy
Feature activation+3.615
for
Token for
Feature activation+0.152
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.000
story
Token story
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Changing
TokenChanging
Feature activation+0.000
too
Token too
Feature activation+0.000
slowly
Token slowly
Feature activation+3.447
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Will
TokenWill
Feature activation+0.000
these
Token these
Feature activation+0.000
physiological
Token physiological
Feature activation+0.000
ride
Token ride
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
too
Token too
Feature activation+0.000
bump
Token bump
Feature activation+2.372
y
Tokeny
Feature activation+3.792
for
Token for
Feature activation+0.439
Bobby
Token Bobby
Feature activation+0.000
(
Token (
Feature activation+0.000
Mark
TokenMark
Feature activation+0.000
Boone
Token Boone
Feature activation+0.000
Step
Token Step
Feature activation+0.000
dad
Tokendad
Feature activation+0.000
who
Token who
Feature activation+0.000
tries
Token tries
Feature activation+0.000
too
Token too
Feature activation+0.000
hard
Token hard
Feature activation+3.588
to
Token to
Feature activation+2.411
be
Token be
Feature activation+0.099
called
Token called
Feature activation+0.000
dad
Token dad
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.958 - 3.380
CONTAINS 0.002%

of
Token of
Feature activation+0.000
reciprocal
Token reciprocal
Feature activation+0.000
rights
Token rights
Feature activation+0.000
was
Token was
Feature activation+0.000
too
Token too
Feature activation+0.000
important
Token important
Feature activation+2.974
to
Token to
Feature activation+0.223
wait
Token wait
Feature activation+0.000
until
Token until
Feature activation+0.000
article
Token article
Feature activation+0.000
50
Token 50
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
reports
Token reports
Feature activation+0.000
as
Token as
Feature activation+0.000
too
Token too
Feature activation+0.000
expensive
Token expensive
Feature activation+3.014
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
using
Tokenusing
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
too
Token too
Feature activation+0.000
important
Token important
Feature activation+3.303
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
future
Token future
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
team
Token team
Feature activation+0.000
has
Token has
Feature activation+0.000
committed
Token committed
Feature activation+0.000
too
Token too
Feature activation+0.000
much
Token much
Feature activation+2.272
time
Token time
Feature activation+3.296
to
Token to
Feature activation+0.000
Griffin
Token Griffin
Feature activation+0.000
for
Token for
Feature activation+0.000
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
There
Token There
Feature activation+0.000
were
Token were
Feature activation+0.000
Ferr
Token Ferr
Feature activation+0.000
aris
Tokenaris
Feature activation+0.000
too
Token too
Feature activation+0.000
and
Token and
Feature activation+3.330
not
Token not
Feature activation+0.000
just
Token just
Feature activation+0.000
any
Token any
Feature activation+0.000
Ferr
Token Ferr
Feature activation+0.000
aris
Tokenaris
Feature activation+0.000

INTERVAL 2.535 - 2.958
CONTAINS 0.002%

recognised
Token recognised
Feature activation+0.000
Fury
Token Fury
Feature activation+0.000
's
Token's
Feature activation+0.000
father
Token father
Feature activation+0.000
too
Token too
Feature activation+0.000
as
Token as
Feature activation+2.561
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
regular
Token regular
Feature activation+0.000
rings
Token rings
Feature activation+0.000
These
Token These
Feature activation+0.000
guesses
Token guesses
Feature activation+0.000
are
Token are
Feature activation+0.000
far
Token far
Feature activation+0.000
too
Token too
Feature activation+0.000
uncertain
Token uncertain
Feature activation+2.689
for
Token for
Feature activation+0.000
us
Token us
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
any
Token any
Feature activation+0.000
helpful
Token helpful
Feature activation+0.000
guide
Token guide
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
too
Token too
Feature activation+0.000
can
Token can
Feature activation+2.867
stop
Token stop
Feature activation+0.000
contributing
Token contributing
Feature activation+0.000
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
environment
Token environment
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
issue
Token issue
Feature activation+0.000
is
Token is
Feature activation+0.000
too
Token too
Feature activation+0.000
important
Token important
Feature activation+2.571
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
need
Token need
Feature activation+0.000
determined
Token determined
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
it
Token it
Feature activation+0.000
more
Token more
Feature activation+0.000
movie
Token movie
Feature activation+0.000
accurate
Token accurate
Feature activation+0.000
too
Token too
Feature activation+0.000
and
Token and
Feature activation+2.855
now
Token now
Feature activation+0.000
it
Token it
Feature activation+0.000
looks
Token looks
Feature activation+0.000
awesome
Token awesome
Feature activation+0.000
!
Token!
Feature activation+0.000

INTERVAL 2.113 - 2.535
CONTAINS 0.003%

complaints
Token complaints
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
too
Token too
Feature activation+0.000
bureaucratic
Token bureaucratic
Feature activation+2.514
and
Token and
Feature activation+0.557
"
Token "
Feature activation+0.000
anti
Tokenanti
Feature activation+1.666
-
Token-
Feature activation+0.000
family
Tokenfamily
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
taken
Token taken
Feature activation+0.000
too
Token too
Feature activation+0.000
seriously
Token seriously
Feature activation+2.182
.
Token.
Feature activation+0.000
Still
Token Still
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
represent
Token represent
Feature activation+0.000
?
Token?
Feature activation+0.000
Does
Token Does
Feature activation+0.000
he
Token he
Feature activation+0.000
seem
Token seem
Feature activation+0.000
too
Token too
Feature activation+0.000
defensive
Token defensive
Feature activation+2.168
?
Token?
Feature activation+0.000
Does
Token Does
Feature activation+0.000
he
Token he
Feature activation+0.000
seem
Token seem
Feature activation+0.000
too
Token too
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
too
Token too
Feature activation+0.000
funny
Token funny
Feature activation+2.373
to
Token to
Feature activation+0.902
hear
Token hear
Feature activation+0.000
you
Token you
Feature activation+0.000
admit
Token admit
Feature activation+0.000
it
Token it
Feature activation+0.000
?
Token?
Feature activation+0.000
Does
Token Does
Feature activation+0.000
he
Token he
Feature activation+0.000
seem
Token seem
Feature activation+0.000
too
Token too
Feature activation+0.000
hostile
Token hostile
Feature activation+2.341
to
Token to
Feature activation+1.588
the
Token the
Feature activation+0.000
apparent
Token apparent
Feature activation+0.000
conclusions
Token conclusions
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.690 - 2.113
CONTAINS 0.005%

there
Token there
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
too
Token too
Feature activation+0.000
much
Token much
Feature activation+1.928
money
Token money
Feature activation+1.457
to
Token to
Feature activation+0.000
let
Token let
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
rather
Token rather
Feature activation+0.000
bit
Token bit
Feature activation+0.000
too
Token too
Feature activation+0.000
eager
Token eager
Feature activation+2.045
to
Token to
Feature activation+1.292
tell
Token tell
Feature activation+0.000
you
Token you
Feature activation+0.000
about
Token about
Feature activation+0.000
it
Token it
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+0.000
had
Token had
Feature activation+0.000
gone
Token gone
Feature activation+0.000
too
Token too
Feature activation+0.000
far
Token far
Feature activation+1.971
in
Token in
Feature activation+1.411
regulation
Token regulation
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
startup
Token startup
Feature activation+0.000
place
Token place
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
too
Token too
Feature activation+0.000
many
Token many
Feature activation+2.031
laws
Token laws
Feature activation+0.000
and
Token and
Feature activation+0.000
regulations
Token regulations
Feature activation+0.000
.
Token.
Feature activation+0.000
Something
Token Something
Feature activation+0.000
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.000
Canadians
Token Canadians
Feature activation+0.000
are
Token are
Feature activation+0.000
too
Token too
Feature activation+0.000
polite
Token polite
Feature activation+1.890
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
felt
Token felt
Feature activation+0.000
an
Token an
Feature activation+0.000
overwhelming
Token overwhelming
Feature activation+0.000

INTERVAL 1.268 - 1.690
CONTAINS 0.005%

Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Far
TokenFar
Feature activation+0.000
too
Token too
Feature activation+0.000
often
Token often
Feature activation+1.282
when
Token when
Feature activation+0.000
Black
Token Black
Feature activation+0.000
gay
Token gay
Feature activation+0.000
men
Token men
Feature activation+0.000
and
Token and
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
too
Token too
Feature activation+0.000
much
Token much
Feature activation+1.928
money
Token money
Feature activation+1.457
to
Token to
Feature activation+0.000
let
Token let
Feature activation+0.000
such
Token such
Feature activation+0.000
a
Token a
Feature activation+0.000
lucrative
Token lucrative
Feature activation+0.000
int
Tokenint
Feature activation+0.000
flags
Token flags
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
too
Token too
Feature activation+0.000
important
Token important
Feature activation+1.390
for
Token for
Feature activation+0.000
now
Token now
Feature activation+0.000
because
Token because
Feature activation+0.000
most
Token most
Feature activation+0.000
of
Token of
Feature activation+0.000
nearest
Token nearest
Feature activation+0.000
secondary
Token secondary
Feature activation+0.000
school
Token school
Feature activation+0.000
is
Token is
Feature activation+0.000
too
Token too
Feature activation+0.000
far
Token far
Feature activation+1.525
to
Token to
Feature activation+0.232
commute
Token commute
Feature activation+0.000
to
Token to
Feature activation+0.000
by
Token by
Feature activation+0.000
foot
Token foot
Feature activation+0.000
but
Token but
Feature activation+0.000
this
Token this
Feature activation+0.000
one
Token one
Feature activation+0.000
is
Token is
Feature activation+0.000
too
Token too
Feature activation+0.000
small
Token small
Feature activation+1.538
to
Token to
Feature activation+0.304
worry
Token worry
Feature activation+0.000
about
Token about
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000

INTERVAL 0.845 - 1.268
CONTAINS 0.007%

would
Token would
Feature activation+0.000
consider
Token consider
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
too
Tokentoo
Feature activation+0.000
much
Token much
Feature activation+1.219
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.680
at
Token at
Feature activation+0.273
home
Token home
Feature activation+0.000
,
Token,
Feature activation+0.000
Coast
Token Coast
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
too
Token too
Feature activation+0.000
-
Token-
Feature activation+1.262
fast
Tokenfast
Feature activation+0.918
expansion
Token expansion
Feature activation+0.290
,
Token,
Feature activation+0.321
aggressive
Token aggressive
Feature activation+0.000
accounting
Token accounting
Feature activation+0.000
practices
Token practices
Feature activation+0.000
crosses
Token crosses
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
too
Token too
Feature activation+0.000
often
Token often
Feature activation+0.025
as
Token as
Feature activation+1.025
well
Token well
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
teams
Token teams
Feature activation+0.000
crossing
Token crossing
Feature activation+0.000
them
Token them
Feature activation+0.000
too
Token too
Feature activation+0.000
?
Token?
Feature activation+0.000
Are
Token Are
Feature activation+0.000
they
Token they
Feature activation+0.000
m
Token m
Feature activation+1.179
olly
Tokenolly
Feature activation+0.000
c
Tokenc
Feature activation+0.000
odd
Tokenodd
Feature activation+0.000
led
Tokenled
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
too
Token too
Feature activation+0.000
young
Token young
Feature activation+2.339
to
Token to
Feature activation+1.178
understand
Token understand
Feature activation+0.315
the
Token the
Feature activation+0.000
weight
Token weight
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.423 - 0.845
CONTAINS 0.009%

ness
Tokenness
Feature activation+0.000
of
Token of
Feature activation+0.000
it
Token it
Feature activation+0.000
--
Token --
Feature activation+0.000
too
Token too
Feature activation+0.000
many
Token many
Feature activation+0.626
tw
Token tw
Feature activation+0.000
its
Tokenits
Feature activation+0.000
might
Token might
Feature activation+0.629
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
unofficial
Token unofficial
Feature activation+0.000
bulbs
Token bulbs
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
too
Token too
Feature activation+0.000
quickly
Token quickly
Feature activation+0.763
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.000
users
Token users
Feature activation+0.000
were
Token were
Feature activation+0.000
using
Token using
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.000
the
Token the
Feature activation+0.000
cup
Token cup
Feature activation+0.000
too
Token too
Feature activation+0.000
much
Token much
Feature activation+0.443
for
Token for
Feature activation+0.000
you
Token you
Feature activation+0.000
(
Token (
Feature activation+0.000
You
TokenYou
Feature activation+0.000
can
Token can
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
affairs
Token affairs
Feature activation+0.000
too
Token too
Feature activation+0.000
often
Token often
Feature activation+0.771
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
know
Token know
Feature activation+0.000
the
Token the
Feature activation+0.000
little
Token little
Feature activation+0.000
W
TokenW
Feature activation+0.000
ickets
Tokenickets
Feature activation+0.000
stop
Token stop
Feature activation+0.000
scoring
Token scoring
Feature activation+0.000
too
Token too
Feature activation+0.000
,
Token,
Feature activation+0.499
so
Token so
Feature activation+0.000
let
Token let
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 0.000 - 0.423
CONTAINS 99.967%

not
Token not
Feature activation+0.000
coming
Token coming
Feature activation+0.000
from
Token from
Feature activation+0.000
half
Token half
Feature activation+0.000
-
Token-
Feature activation+0.000
n
Tokenn
Feature activation+0.000
aked
Tokenaked
Feature activation+0.000
anarchists
Token anarchists
Feature activation+0.000
man
Token man
Feature activation+0.000
ning
Tokenning
Feature activation+0.000
the
Token the
Feature activation+0.000
crossed
Token crossed
Feature activation+0.000
the
Token the
Feature activation+0.000
line
Token line
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
âĢĶ
Token âĢĶ
Feature activation+0.000
prisoners
Token prisoners
Feature activation+0.000
,
Token,
Feature activation+0.000
prison
Token prison
Feature activation+0.000
staff
Token staff
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ms
TokenMs
Feature activation+0.000
.
Token.
Feature activation+0.000
Re
Token Re
Feature activation+0.000
ibel
Tokenibel
Feature activation+0.000
cited
Token cited
Feature activation+0.000
one
Token one
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
multi
Token multi
Feature activation+0.000
-
Token-
Feature activation+0.000
.
Token .
Feature activation+0.000
.
Token .
Feature activation+0.000
.
Token .
Feature activation+0.000
is
Token is
Feature activation+0.000
being
Token being
Feature activation+0.000
very
Token very
Feature activation+0.000
aggressively
Token aggressively
Feature activation+0.000
pursued
Token pursued
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
fresh
Token fresh
Feature activation+0.000
meat
Tokenmeat
Feature activation+0.000
,
Token,
Feature activation+0.000
most
Token most
Feature activation+0.000
of
Token of
Feature activation+0.000
which
Token which
Feature activation+0.000
have
Token have
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
with
Token with
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 H3.2: (feature 7786)

TOP ACTIVATIONS
MAX = 1.957

team
Token team
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
'd
Token'd
Feature activation+0.000
be
Token be
Feature activation+0.097
frightened
Token frightened
Feature activation+1.957
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
likes
Token likes
Feature activation+0.000
of
Token of
Feature activation+0.000
Zach
Token Zach
Feature activation+0.000
skeptical
Token skeptical
Feature activation+0.000
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.924
to
Token to
Feature activation+1.176
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
successful
Token successful
Feature activation+0.000
and
Token and
Feature activation+0.000
comments
Token comments
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
'd
Token'd
Feature activation+0.000
be
Token be
Feature activation+0.068
happy
Token happy
Feature activation+1.861
to
Token to
Feature activation+0.600
give
Token give
Feature activation+0.000
additional
Token additional
Feature activation+0.000
explanations
Token explanations
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
we
Token we
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
really
Token really
Feature activation+1.771
worried
Token worried
Feature activation+0.793
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
scheme
Token scheme
Feature activation+0.000
is
Token is
Feature activation+0.000
Ireland
Token Ireland
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
astonished
Token astonished
Feature activation+1.764
to
Token to
Feature activation+0.743
see
Token see
Feature activation+0.000
a
Token a
Feature activation+0.000
beautiful
Token beautiful
Feature activation+0.000
arrangement
Token arrangement
Feature activation+0.000
printing
Token printing
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
'll
Token'll
Feature activation+0.000
be
Token be
Feature activation+0.000
sure
Token sure
Feature activation+1.723
to
Token to
Feature activation+0.171
walk
Token walk
Feature activation+0.000
you
Token you
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
all
Token all
Feature activation+0.000
this
Token this
Feature activation+0.000
she
Token she
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
satisfied
Token satisfied
Feature activation+1.696
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
no
Token no
Feature activation+0.000
.
Token.
Feature activation+0.000
Hel
Token Hel
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
we
Token we
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.675
to
Token to
Feature activation+0.870
use
Token use
Feature activation+0.000
more
Token more
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
out
Tokenout
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.644
to
Token to
Feature activation+0.642
figure
Token figure
Feature activation+0.000
out
Token out
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
are
Token are
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
'll
Token'll
Feature activation+0.000
be
Token be
Feature activation+0.000
honest
Token honest
Feature activation+1.642
with
Token with
Feature activation+0.153
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
's
Token's
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.607
to
Token to
Feature activation+0.847
afford
Token afford
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
it
Token it
Feature activation+0.000
him
Token him
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
sure
Token sure
Feature activation+1.600
he
Token he
Feature activation+0.000
'll
Token'll
Feature activation+0.000
say
Token say
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
shall
Token shall
Feature activation+0.000
be
Token be
Feature activation+0.000
grateful
Token grateful
Feature activation+1.600
if
Token if
Feature activation+0.166
the
Token the
Feature activation+0.000
above
Token above
Feature activation+0.000
aspects
Token aspects
Feature activation+0.000
receive
Token receive
Feature activation+0.000
Constitution
Token Constitution
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
willing
Token willing
Feature activation+1.594
to
Token to
Feature activation+0.579
depend
Token depend
Feature activation+0.000
on
Token on
Feature activation+0.000
that
Token that
Feature activation+0.000
alone
Token alone
Feature activation+0.000
but
Token but
Feature activation+0.000
hinted
Token hinted
Feature activation+0.000
he
Token he
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
prepared
Token prepared
Feature activation+1.582
to
Token to
Feature activation+0.573
withdraw
Token withdraw
Feature activation+0.000
support
Token support
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
we
Token we
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.576
to
Token to
Feature activation+0.616
contend
Token contend
Feature activation+0.000
;
Token;
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
living
Token living
Feature activation+0.000
in
Token in
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.560
to
Token to
Feature activation+0.219
access
Token access
Feature activation+0.000
the
Token the
Feature activation+0.000
European
Token European
Feature activation+0.000
Court
Token Court
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
would
Token would
Feature activation+0.000
never
Token never
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.556
to
Token to
Feature activation+0.640
find
Token find
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
this
Token this
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
completely
Token completely
Feature activation+1.536
stunned
Token stunned
Feature activation+1.496
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
completely
Token completely
Feature activation+1.536
stunned
Token stunned
Feature activation+1.496
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

Top DFA by src position
MAX = 2.461

opposing
Token opposing
Feature activation-0.014
Top resid features:
team
Token team
Feature activation-0.012
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
I
Token I
Feature activation+0.086
Top resid features:
'd
Token'd
Feature activation+0.154
Top resid features:
be
Token be
Feature activation+2.384
Top resid features:
frightened
Token frightened
Feature activation+0.047
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
likes
Token likes
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
was
Token was
Feature activation-0.021
Top resid features:
skeptical
Token skeptical
Feature activation-0.069
Top resid features:
that
Token that
Feature activation+0.058
Top resid features:
I
Token I
Feature activation+0.098
Top resid features:
would
Token would
Feature activation+0.189
Top resid features:
be
Token be
Feature activation+2.274
Top resid features:
able
Token able
Feature activation-0.023
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
successful
Token successful
Feature activation+0.000
Top resid features:
for
Token for
Feature activation-0.013
Top resid features:
comments
Token comments
Feature activation-0.015
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
I
Token I
Feature activation+0.082
Top resid features:
'd
Token'd
Feature activation-0.012
Top resid features:
be
Token be
Feature activation+2.461
Top resid features:
happy
Token happy
Feature activation-0.011
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
give
Token give
Feature activation+0.000
Top resid features:
additional
Token additional
Feature activation+0.000
Top resid features:
explanations
Token explanations
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
But
TokenBut
Feature activation+0.129
Top resid features:
we
Token we
Feature activation+0.102
Top resid features:
should
Token should
Feature activation+0.134
Top resid features:
be
Token be
Feature activation+2.029
Top resid features:
really
Token really
Feature activation+0.004
Top resid features:
worried
Token worried
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
This
Token This
Feature activation+0.000
Top resid features:
scheme
Token scheme
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
Ireland
Token Ireland
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
you
Token you
Feature activation+0.144
Top resid features:
may
Token may
Feature activation+0.202
Top resid features:
be
Token be
Feature activation+2.011
Top resid features:
astonished
Token astonished
Feature activation+0.061
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
see
Token see
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
beautiful
Token beautiful
Feature activation+0.000
Top resid features:
D
TokenD
Feature activation-0.011
Top resid features:
printing
Token printing
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.032
Top resid features:
we
Token we
Feature activation+0.057
Top resid features:
'll
Token'll
Feature activation+0.155
Top resid features:
be
Token be
Feature activation+2.076
Top resid features:
sure
Token sure
Feature activation+0.024
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
walk
Token walk
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
given
Token given
Feature activation-0.007
Top resid features:
all
Token all
Feature activation-0.001
Top resid features:
this
Token this
Feature activation-0.003
Top resid features:
she
Token she
Feature activation+0.162
Top resid features:
would
Token would
Feature activation+0.087
Top resid features:
be
Token be
Feature activation+2.124
Top resid features:
satisfied
Token satisfied
Feature activation-0.007
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
too
Token too
Feature activation-0.021
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
so
Token so
Feature activation+0.013
Top resid features:
we
Token we
Feature activation+0.096
Top resid features:
might
Token might
Feature activation+0.093
Top resid features:
be
Token be
Feature activation+2.131
Top resid features:
able
Token able
Feature activation-0.022
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
use
Token use
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
sn
Token sn
Feature activation-0.009
Top resid features:
out
Tokenout
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.048
Top resid features:
you
Token you
Feature activation+0.123
Top resid features:
should
Token should
Feature activation+0.197
Top resid features:
be
Token be
Feature activation+1.904
Top resid features:
able
Token able
Feature activation-0.059
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
figure
Token figure
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
city
Token city
Feature activation+0.000
Top resid features:
are
Token are
Feature activation-0.010
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
I
Token I
Feature activation+0.148
Top resid features:
'll
Token'll
Feature activation+0.218
Top resid features:
be
Token be
Feature activation+1.840
Top resid features:
honest
Token honest
Feature activation+0.074
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
impression
Token impression
Feature activation+0.002
Top resid features:
is
Token is
Feature activation-0.024
Top resid features:
that
Token that
Feature activation+0.098
Top resid features:
Australia
Token Australia
Feature activation+0.138
Top resid features:
might
Token might
Feature activation+0.109
Top resid features:
be
Token be
Feature activation+1.872
Top resid features:
able
Token able
Feature activation-0.008
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
afford
Token afford
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
takes
Token takes
Feature activation-0.006
Top resid features:
him
Token him
Feature activation-0.022
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
you
Token you
Feature activation+0.134
Top resid features:
can
Token can
Feature activation-0.052
Top resid features:
be
Token be
Feature activation+2.009
Top resid features:
sure
Token sure
Feature activation+0.006
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
'll
Token'll
Feature activation+0.000
Top resid features:
say
Token say
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
possible
Token possible
Feature activation-0.006
Top resid features:
time
Token time
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
I
Token I
Feature activation+0.056
Top resid features:
shall
Token shall
Feature activation+0.232
Top resid features:
be
Token be
Feature activation+1.906
Top resid features:
grateful
Token grateful
Feature activation+0.029
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
above
Token above
Feature activation+0.000
Top resid features:
aspects
Token aspects
Feature activation+0.000
Top resid features:
our
Token our
Feature activation-0.004
Top resid features:
Constitution
Token Constitution
Feature activation-0.004
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
I
Token I
Feature activation+0.100
Top resid features:
would
Token would
Feature activation+0.130
Top resid features:
be
Token be
Feature activation+1.936
Top resid features:
willing
Token willing
Feature activation+0.087
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
depend
Token depend
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
but
Token but
Feature activation+0.059
Top resid features:
hinted
Token hinted
Feature activation+0.002
Top resid features:
he
Token he
Feature activation+0.162
Top resid features:
could
Token could
Feature activation+0.130
Top resid features:
be
Token be
Feature activation+1.894
Top resid features:
prepared
Token prepared
Feature activation-0.032
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
withdraw
Token withdraw
Feature activation+0.000
Top resid features:
support
Token support
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
I
Token I
Feature activation+0.014
Top resid features:
think
Token think
Feature activation+0.034
Top resid features:
we
Token we
Feature activation+0.116
Top resid features:
will
Token will
Feature activation+0.181
Top resid features:
be
Token be
Feature activation+1.848
Top resid features:
able
Token able
Feature activation-0.034
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
contend
Token contend
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.000
Top resid features:
however
Token however
Feature activation+0.000
Top resid features:
nationals
Token nationals
Feature activation+0.036
Top resid features:
living
Token living
Feature activation-0.041
Top resid features:
in
Token in
Feature activation-0.024
Top resid features:
Britain
Token Britain
Feature activation+0.003
Top resid features:
would
Token would
Feature activation+0.092
Top resid features:
be
Token be
Feature activation+1.970
Top resid features:
able
Token able
Feature activation-0.020
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
access
Token access
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
European
Token European
Feature activation+0.000
Top resid features:
areas
Token areas
Feature activation-0.036
Top resid features:
that
Token that
Feature activation+0.029
Top resid features:
we
Token we
Feature activation+0.135
Top resid features:
would
Token would
Feature activation+0.130
Top resid features:
never
Token never
Feature activation+0.046
Top resid features:
be
Token be
Feature activation+1.897
Top resid features:
able
Token able
Feature activation-0.006
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
find
Token find
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
such
Token such
Feature activation+0.000
Top resid features:
on
Token on
Feature activation-0.019
Top resid features:
this
Token this
Feature activation-0.018
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
I
Token I
Feature activation+0.072
Top resid features:
would
Token would
Feature activation+0.123
Top resid features:
be
Token be
Feature activation+2.102
Top resid features:
completely
Token completely
Feature activation-0.009
Top resid features:
stunned
Token stunned
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
don
Token don
Feature activation+0.000
Top resid features:
on
Token on
Feature activation-0.018
Top resid features:
this
Token this
Feature activation-0.021
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
I
Token I
Feature activation+0.101
Top resid features:
would
Token would
Feature activation+0.095
Top resid features:
be
Token be
Feature activation+1.855
Top resid features:
completely
Token completely
Feature activation+0.086
Top resid features:
stunned
Token stunned
Feature activation+0.051
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
don
Token don
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.05

Head 2: 0.41

Head 3: 0.04

Head 4: 0.02

Head 5: 0.03

Head 6: 0.04

Head 7: 0.06

Head 8: 0.11

Head 9: 0.10

Head 10: 0.05

Head 11: 0.05

Positive logits

angered1.68

someday1.63

icent1.58

ワン1.57

icted1.55

stories1.52

itialized1.50

atre1.46

1.43

orthy1.42

aska1.42

izzy1.41

ASAP1.39

ardless1.39

atform1.38

��1.37

isconsin1.36

tomorrow1.36

Parenthood1.34

role1.33

Negative logits

Directive-1.19

plague-1.16

precaution-1.14

Lum-1.13

Internal-1.13

rarely-1.12

tradition-1.11

bount-1.10

selection-1.10

characteristic-1.09

flare-1.08

ugh-1.08

stem-1.08

scripting-1.07

contingency-1.07

hamstring-1.07

subsystem-1.06

seldom-1.06

stem-1.06

compound-1.06

INTERVAL 1.761 - 1.957
CONTAINS 0.001%

team
Token team
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
'd
Token'd
Feature activation+0.000
be
Token be
Feature activation+0.097
frightened
Token frightened
Feature activation+1.957
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
likes
Token likes
Feature activation+0.000
of
Token of
Feature activation+0.000
Zach
Token Zach
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
we
Token we
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
really
Token really
Feature activation+1.771
worried
Token worried
Feature activation+0.793
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
scheme
Token scheme
Feature activation+0.000
is
Token is
Feature activation+0.000
comments
Token comments
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
'd
Token'd
Feature activation+0.000
be
Token be
Feature activation+0.068
happy
Token happy
Feature activation+1.861
to
Token to
Feature activation+0.600
give
Token give
Feature activation+0.000
additional
Token additional
Feature activation+0.000
explanations
Token explanations
Feature activation+0.000
.
Token.
Feature activation+0.000
skeptical
Token skeptical
Feature activation+0.000
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.924
to
Token to
Feature activation+1.176
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
successful
Token successful
Feature activation+0.000
and
Token and
Feature activation+0.000
Ireland
Token Ireland
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
astonished
Token astonished
Feature activation+1.764
to
Token to
Feature activation+0.743
see
Token see
Feature activation+0.000
a
Token a
Feature activation+0.000
beautiful
Token beautiful
Feature activation+0.000
arrangement
Token arrangement
Feature activation+0.000

INTERVAL 1.565 - 1.761
CONTAINS 0.001%

I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
we
Token we
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.576
to
Token to
Feature activation+0.616
contend
Token contend
Feature activation+0.000
;
Token;
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
this
Token this
Feature activation+0.000
she
Token she
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
satisfied
Token satisfied
Feature activation+1.696
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
no
Token no
Feature activation+0.000
.
Token.
Feature activation+0.000
Hel
Token Hel
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.607
to
Token to
Feature activation+0.847
afford
Token afford
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
we
Token we
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.675
to
Token to
Feature activation+0.870
use
Token use
Feature activation+0.000
more
Token more
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
but
Token but
Feature activation+0.000
hinted
Token hinted
Feature activation+0.000
he
Token he
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
prepared
Token prepared
Feature activation+1.582
to
Token to
Feature activation+0.573
withdraw
Token withdraw
Feature activation+0.000
support
Token support
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.370 - 1.565
CONTAINS 0.001%

plugin
Token plugin
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
happy
Token happy
Feature activation+1.471
with
Token with
Feature activation+0.264
the
Token the
Feature activation+0.000
default
Token default
Feature activation+0.000
shadow
Token shadow
Feature activation+0.000
Jar
TokenJar
Feature activation+0.000
fix
Token fix
Feature activation+0.000
could
Token could
Feature activation+0.000
also
Token also
Feature activation+0.000
be
Token be
Feature activation+0.000
t
Token t
Feature activation+0.000
acked
Tokenacked
Feature activation+1.375
on
Token on
Feature activation+0.349
to
Token to
Feature activation+0.000
broader
Token broader
Feature activation+0.000
tax
Token tax
Feature activation+0.000
reform
Token reform
Feature activation+0.000
living
Token living
Feature activation+0.000
in
Token in
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.560
to
Token to
Feature activation+0.219
access
Token access
Feature activation+0.000
the
Token the
Feature activation+0.000
European
Token European
Feature activation+0.000
Court
Token Court
Feature activation+0.000
this
Token this
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
completely
Token completely
Feature activation+1.536
stunned
Token stunned
Feature activation+1.496
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.012
able
Token able
Feature activation+1.446
to
Token to
Feature activation+0.386
view
Token view
Feature activation+0.000
your
Token your
Feature activation+0.000
profile
Token profile
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.174 - 1.370
CONTAINS 0.003%

read
Token read
Feature activation+0.000
this
Token this
Feature activation+0.000
site
Token site
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.263
to
Token to
Feature activation+0.297
improve
Token improve
Feature activation+0.000
the
Token the
Feature activation+0.000
petition
Token petition
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
might
Token might
Feature activation+0.000
finally
Token finally
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.352
to
Token to
Feature activation+1.171
choose
Token choose
Feature activation+0.000
to
Token to
Feature activation+0.000
download
Token download
Feature activation+0.000
just
Token just
Feature activation+0.000
'
Token'
Feature activation+0.000
brass
Token brass
Feature activation+0.000
would
Token would
Feature activation+0.000
easily
Token easily
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.270
to
Token to
Feature activation+0.718
keep
Token keep
Feature activation+0.000
track
Token track
Feature activation+0.000
of
Token of
Feature activation+0.000
Cab
Token Cab
Feature activation+0.000
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.924
to
Token to
Feature activation+1.176
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
successful
Token successful
Feature activation+0.000
and
Token and
Feature activation+0.000
happy
Token happy
Feature activation+0.000
'd
Token'd
Feature activation+0.000
think
Token think
Feature activation+0.000
it
Token it
Feature activation+0.000
'd
Token'd
Feature activation+0.000
be
Token be
Feature activation+0.000
really
Token really
Feature activation+1.333
hard
Token hard
Feature activation+0.153
to
Token to
Feature activation+0.046
relate
Token relate
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.978 - 1.174
CONTAINS 0.004%

the
Token the
Feature activation+0.000
beer
Token beer
Feature activation+0.000
list
Token list
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
very
Token very
Feature activation+1.077
helpful
Token helpful
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Israel
TokenIsrael
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
highly
Token highly
Feature activation+1.100
unlikely
Token unlikely
Feature activation+0.952
to
Token to
Feature activation+0.520
co
Token co
Feature activation+0.013
-
Token-
Feature activation+0.000
oper
Tokenoper
Feature activation+0.000
which
Token which
Feature activation+0.000
candidate
Token candidate
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
more
Token more
Feature activation+0.332
likely
Token likely
Feature activation+0.994
to
Token to
Feature activation+0.281
use
Token use
Feature activation+0.000
drones
Token drones
Feature activation+0.000
,
Token,
Feature activation+0.000
more
Token more
Feature activation+0.000
doubts
Token doubts
Feature activation+0.000
that
Token that
Feature activation+0.000
technology
Token technology
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+1.080
to
Token to
Feature activation+0.168
revolution
Token revolution
Feature activation+0.000
ize
Tokenize
Feature activation+0.000
mineral
Token mineral
Feature activation+0.000
exploration
Token exploration
Feature activation+0.000
investors
Token investors
Feature activation+0.000
said
Token said
Feature activation+0.000
they
Token they
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
prepared
Token prepared
Feature activation+1.076
to
Token to
Feature activation+0.267
contemplate
Token contemplate
Feature activation+0.000
new
Token new
Feature activation+0.000
deals
Token deals
Feature activation+0.000
with
Token with
Feature activation+0.000

INTERVAL 0.783 - 0.978
CONTAINS 0.008%

stem
Token stem
Feature activation+0.000
cells
Token cells
Feature activation+0.000
could
Token could
Feature activation+0.000
be
Token be
Feature activation+0.000
coax
Token coax
Feature activation+0.109
ed
Tokened
Feature activation+0.796
to
Token to
Feature activation+0.000
become
Token become
Feature activation+0.000
muscle
Token muscle
Feature activation+0.000
cells
Token cells
Feature activation+0.000
,
Token,
Feature activation+0.000
."
Token."
Feature activation+0.000
I
Token I
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
't
Token't
Feature activation+0.000
be
Token be
Feature activation+0.000
more
Token more
Feature activation+0.954
wrong
Token wrong
Feature activation+0.189
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
"
Token "
Feature activation+0.000
re
Tokenre
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
should
Token should
Feature activation+0.000
also
Token also
Feature activation+0.000
be
Token be
Feature activation+0.000
rewarded
Token rewarded
Feature activation+0.929
10
Token 10
Feature activation+0.000
x
Tokenx
Feature activation+0.000
more
Token more
Feature activation+0.000
.
Token.
Feature activation+0.000
Indeed
Token Indeed
Feature activation+0.000
the
Token the
Feature activation+0.000
debt
Token debt
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
wiped
Token wiped
Feature activation+0.000
out
Token out
Feature activation+0.908
.
Token.
Feature activation+0.000
Canadians
Token Canadians
Feature activation+0.000
will
Token will
Feature activation+0.000
again
Token again
Feature activation+0.000
prosper
Token prosper
Feature activation+0.000
we
Token we
Feature activation+0.000
as
Token as
Feature activation+0.000
individuals
Token individuals
Feature activation+0.000
be
Token be
Feature activation+0.000
more
Token more
Feature activation+0.622
casual
Token casual
Feature activation+0.840
about
Token about
Feature activation+0.556
our
Token our
Feature activation+0.000
safety
Token safety
Feature activation+0.000
than
Token than
Feature activation+0.000
we
Token we
Feature activation+0.000

INTERVAL 0.587 - 0.783
CONTAINS 0.012%

belt
Token belt
Feature activation+0.000
"
Token"
Feature activation+0.000
MPs
Token MPs
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+0.747
to
Token to
Feature activation+0.000
claim
Token claim
Feature activation+0.000
for
Token for
Feature activation+0.000
hotels
Token hotels
Feature activation+0.000
or
Token or
Feature activation+0.000
DIY
Token DIY
Feature activation+0.000
approach
Token approach
Feature activation+0.000
you
Token you
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
interested
Token interested
Feature activation+0.615
in
Token in
Feature activation+0.000
our
Token our
Feature activation+0.000
brother
Token brother
Feature activation+0.000
company
Token company
Feature activation+0.000
,
Token,
Feature activation+0.000
clear
Token clear
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
forced
Token forced
Feature activation+0.608
to
Token to
Feature activation+0.404
resign
Token resign
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
could
Token could
Feature activation+0.000
finally
Token finally
Feature activation+0.000
be
Token be
Feature activation+0.000
properly
Token properly
Feature activation+0.729
polic
Token polic
Feature activation+0.000
ed
Tokened
Feature activation+0.639
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
licenses
Token licenses
Feature activation+0.000
withdrawn
Token withdrawn
Feature activation+0.000
for
Token for
Feature activation+0.000
paying
Tokenpaying
Feature activation+0.000
ill
Token ill
Feature activation+0.000
"
Token"
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+0.702
to
Token to
Feature activation+0.040
jump
Token jump
Feature activation+0.000
the
Token the
Feature activation+0.000
queue
Token queue
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.391 - 0.587
CONTAINS 0.025%

we
Token we
Feature activation+0.000
'd
Token'd
Feature activation+0.000
all
Token all
Feature activation+0.000
be
Token be
Feature activation+0.000
talking
Token talking
Feature activation+0.366
about
Token about
Feature activation+0.516
what
Token what
Feature activation+0.000
a
Token a
Feature activation+0.000
great
Token great
Feature activation+0.000
game
Token game
Feature activation+0.000
the
Token the
Feature activation+0.000
atheists
Token atheists
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
even
Token even
Feature activation+0.163
more
Token more
Feature activation+0.409
upset
Token upset
Feature activation+0.377
by
Token by
Feature activation+0.000
this
Token this
Feature activation+0.000
than
Token than
Feature activation+0.000
they
Token they
Feature activation+0.000
up
Token up
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
familiar
Token familiar
Feature activation+0.558
to
Token to
Feature activation+0.000
Oregon
Token Oregon
Feature activation+0.000
and
Token and
Feature activation+0.000
Eagles
Token Eagles
Feature activation+0.000
fans
Token fans
Feature activation+0.000
Jim
TokenJim
Feature activation+0.000
Love
Token Love
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
best
Token best
Feature activation+0.480
remembered
Token remembered
Feature activation+0.028
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
and
Token and
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
added
Token added
Feature activation+0.547
to
Token to
Feature activation+0.196
the
Token the
Feature activation+0.000
major
Token major
Feature activation+0.000
league
Token league
Feature activation+0.000
roster
Token roster
Feature activation+0.000

INTERVAL 0.196 - 0.391
CONTAINS 0.042%

stage
Token stage
Feature activation+0.000
those
Token those
Feature activation+0.000
won
Token won
Feature activation+0.000
't
Token't
Feature activation+0.000
be
Token be
Feature activation+0.000
considered
Token considered
Feature activation+0.364
.
Token.
Feature activation+0.000
Thanks
Token Thanks
Feature activation+0.000
for
Token for
Feature activation+0.000
your
Token your
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000
caus
Token caus
Feature activation+0.000
ality
Tokenality
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
interpreted
Token interpreted
Feature activation+0.000
as
Token as
Feature activation+0.228
running
Token running
Feature activation+0.000
(
Token (
Feature activation+0.000
mostly
Tokenmostly
Feature activation+0.000
)
Token)
Feature activation+0.000
from
Token from
Feature activation+0.000
so
Token so
Feature activation+0.000
they
Token they
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
readily
Token readily
Feature activation+1.282
used
Token used
Feature activation+0.316
as
Token as
Feature activation+0.301
pawn
Token pawn
Feature activation+0.000
s
Tokens
Feature activation+0.000
in
Token in
Feature activation+0.000
our
Token our
Feature activation+0.000
charge
Token charge
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
be
Token be
Feature activation+0.000
ske
Token ske
Feature activation+0.316
wered
Tokenwered
Feature activation+0.186
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
cross
Token cross
Feature activation+0.000
of
Token of
Feature activation+0.000
think
Token think
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
very
Token very
Feature activation+0.261
,
Token,
Feature activation+0.000
very
Token very
Feature activation+0.000
big
Token big
Feature activation+0.000
mistake
Token mistake
Feature activation+0.070
,"
Token,"
Feature activation+0.000

INTERVAL 0.000 - 0.196
CONTAINS 99.903%

since
Tokensince
Feature activation+0.000
debunked
Token debunked
Feature activation+0.000
story
Token story
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
outgoing
Token outgoing
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
istas
Tokenistas
Feature activation+0.000
in
Token in
Feature activation+0.000
2001
Token 2001
Feature activation+0.000
removed
Token removed
Feature activation+0.000
committed
Token committed
Feature activation+0.000
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
"
Token "
Feature activation+0.000
ide
Tokenide
Feature activation+0.000
ological
Tokenological
Feature activation+0.000
plan
Token plan
Feature activation+0.000
"
Token"
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
ensure
Token ensure
Feature activation+0.000
that
Token that
Feature activation+0.000
launches
Token launches
Feature activation+0.000
from
Token from
Feature activation+0.000
within
Token within
Feature activation+0.000
their
Token their
Feature activation+0.000
borders
Token borders
Feature activation+0.000
take
Token take
Feature activation+0.000
precaution
Token precaution
Feature activation+0.000
ary
Tokenary
Feature activation+0.000
measures
Token measures
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Y
Token Y
Feature activation+0.000
ousse
Tokenousse
Feature activation+0.000
f
Tokenf
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
case
Token case
Feature activation+0.000
has
Token has
Feature activation+0.000
made
Token made
Feature activation+0.000
The
Token The
Feature activation+0.000
Department
Token Department
Feature activation+0.000
of
Token of
Feature activation+0.000
Justice
Token Justice
Feature activation+0.000
launched
Token launched
Feature activation+0.000
179
Token 179
Feature activation+0.000
prosecutions
Token prosecutions
Feature activation+0.000
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
amended
Token amended
Feature activation+0.000
Act
Token Act
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 H3.2: (feature 22917)

TOP ACTIVATIONS
MAX = 2.754

or
Token or
Feature activation+0.000
batter
Token batter
Feature activation+0.000
by
Token by
Feature activation+0.000
kn
Token kn
Feature activation+0.754
ead
Tokenead
Feature activation+1.493
ing
Tokening
Feature activation+2.754
or
Token or
Feature activation+0.191
stirring
Token stirring
Feature activation+0.287
helps
Token helps
Feature activation+0.000
encourage
Token encourage
Feature activation+0.000
bonding
Token bonding
Feature activation+0.000
capital
Token capital
Feature activation+0.000
ships
Token ships
Feature activation+0.000
apart
Token apart
Feature activation+0.000
piece
Token piece
Feature activation+0.000
by
Token by
Feature activation+0.000
piece
Token piece
Feature activation+2.735
âĢĵ
Token âĢĵ
Feature activation+0.044
take
Token take
Feature activation+0.000
out
Token out
Feature activation+0.000
their
Token their
Feature activation+0.000
turrets
Token turrets
Feature activation+0.000
creativity
Token creativity
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
"
Token "
Feature activation+0.000
one
Tokenone
Feature activation+0.000
by
Token by
Feature activation+0.000
one
Token one
Feature activation+2.492
,"
Token,"
Feature activation+0.619
B
Token B
Feature activation+0.000
els
Tokenels
Feature activation+0.000
ky
Tokenky
Feature activation+0.000
says
Token says
Feature activation+0.000
capital
Token capital
Feature activation+0.000
ships
Token ships
Feature activation+0.000
apart
Token apart
Feature activation+0.000
piece
Token piece
Feature activation+0.000
by
Token by
Feature activation+0.000
piece
Token piece
Feature activation+2.478
âĢĵ
Token âĢĵ
Feature activation+0.062
take
Token take
Feature activation+0.000
out
Token out
Feature activation+0.000
their
Token their
Feature activation+0.000
turrets
Token turrets
Feature activation+0.000
battles
Token battles
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
case
Token case
Feature activation+0.000
by
Token by
Feature activation+0.000
case
Token case
Feature activation+2.302
basis
Token basis
Feature activation+0.275
with
Token with
Feature activation+0.000
more
Token more
Feature activation+0.000
research
Token research
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
brushes
Token brushes
Feature activation+0.000
,
Token,
Feature activation+0.000
step
Token step
Feature activation+0.000
by
Token by
Feature activation+0.000
step
Token step
Feature activation+2.252
,
Token,
Feature activation+0.794
explanatory
Token explanatory
Feature activation+0.000
diagram
Token diagram
Feature activation+0.000
)
Token)
Feature activation+0.000
on
Token on
Feature activation+0.000
far
Token far
Feature activation+0.000
to
Token to
Feature activation+0.000
commute
Token commute
Feature activation+0.000
to
Token to
Feature activation+0.000
by
Token by
Feature activation+0.000
foot
Token foot
Feature activation+2.191
.
Token.
Feature activation+0.000
Furthermore
Token Furthermore
Feature activation+0.000
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
long
Token long
Feature activation+0.000
property
Token property
Feature activation+0.000
tax
Token tax
Feature activation+0.000
bill
Token bill
Feature activation+0.000
by
Token by
Feature activation+0.000
95
Token 95
Feature activation+0.781
percent
Token percent
Feature activation+2.184
,
Token,
Feature activation+0.399
or
Token or
Feature activation+0.946
an
Token an
Feature activation+0.000
estimated
Token estimated
Feature activation+0.000
$
Token $
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
sort
Token sort
Feature activation+0.000
them
Token them
Feature activation+0.000
by
Token by
Feature activation+0.000
frequency
Token frequency
Feature activation+2.180
of
Token of
Feature activation+1.435
usage
Token usage
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
take
Token take
Feature activation+0.000
exclusive
Token exclusive
Feature activation+0.000
track
Token track
Feature activation+0.000
-
Token-
Feature activation+0.000
by
Tokenby
Feature activation+0.000
-
Token-
Feature activation+1.641
track
Tokentrack
Feature activation+2.158
interviews
Token interviews
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
band
Token band
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
quarter
Token quarter
Feature activation+0.000
-
Token-
Feature activation+0.000
by
Tokenby
Feature activation+0.000
-
Token-
Feature activation+1.480
quarter
Tokenquarter
Feature activation+2.155
basis
Token basis
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
-
Token-
Feature activation+0.000
by
Tokenby
Feature activation+0.000
-
Token-
Feature activation+1.329
p
Tokenp
Feature activation+0.338
itch
Tokenitch
Feature activation+2.148
,
Token,
Feature activation+0.497
Brad
Token Brad
Feature activation+0.000
De
Token De
Feature activation+0.000
bo
Tokenbo
Feature activation+0.000
tripled
Token tripled
Feature activation+0.000
sort
Token sort
Feature activation+0.000
words
Token words
Feature activation+0.000
by
Token by
Feature activation+0.000
alphabet
Token alphabet
Feature activation+1.740
ical
Tokenical
Feature activation+1.618
order
Token order
Feature activation+2.147
,
Token,
Feature activation+0.550
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
convenient
Token convenient
Feature activation+0.000
if
Token if
Feature activation+0.000
inding
Tokeninding
Feature activation+0.000
Hub
Token Hub
Feature activation+0.000
Tile
TokenTile
Feature activation+0.000
Step
Token Step
Feature activation+0.000
by
Token by
Feature activation+0.000
Step
Token Step
Feature activation+2.130
Ċ
TokenĊ
Feature activation+1.064
Ċ
TokenĊ
Feature activation+0.481
This
TokenThis
Feature activation+0.000
example
Token example
Feature activation+0.000
demonstrates
Token demonstrates
Feature activation+0.000
extend
Token extend
Feature activation+0.000
it
Token it
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.786
few
Token few
Feature activation+0.970
days
Token days
Feature activation+2.116
to
Token to
Feature activation+0.654
gather
Token gather
Feature activation+0.000
more
Token more
Feature activation+0.000
data
Token data
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
Received
Token Received
Feature activation+0.000
:
Token:
Feature activation+0.000
by
Token by
Feature activation+0.222
10
Token 10
Feature activation+2.090
.
Token.
Feature activation+1.132
25
Token25
Feature activation+1.245
.
Token.
Feature activation+0.000
24
Token24
Feature activation+0.040
.
Token.
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
without
Token without
Feature activation+0.000
step
Token step
Feature activation+0.000
-
Token-
Feature activation+0.000
by
Tokenby
Feature activation+0.000
-
Token-
Feature activation+2.061
step
Tokenstep
Feature activation+1.669
instructions
Token instructions
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
pattern
Token pattern
Feature activation+0.000
candidate
Token candidate
Feature activation+0.000
John
Token John
Feature activation+0.000
McCain
Token McCain
Feature activation+0.000
by
Token by
Feature activation+0.000
11
Token 11
Feature activation+0.860
percentage
Token percentage
Feature activation+2.037
points
Token points
Feature activation+1.799
and
Token and
Feature activation+1.080
close
Token close
Feature activation+0.187
to
Token to
Feature activation+0.000
1
Token 1
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
questions
Token questions
Feature activation+0.000
by
Token by
Feature activation+0.000
March
Token March
Feature activation+0.745
1
Token 1
Feature activation+0.946
,
Token,
Feature activation+2.035
as
Token as
Feature activation+0.429
her
Token her
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
ask
Token ask
Feature activation+0.000
t
Tokent
Feature activation+0.000
ucket
Tokenucket
Feature activation+0.000
by
Token by
Feature activation+0.000
May
Token May
Feature activation+0.360
1
Token 1
Feature activation+1.052
,
Token,
Feature activation+1.973
has
Token has
Feature activation+0.000
remained
Token remained
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000

Top DFA by src position
MAX = 3.303

Working
Token Working
Feature activation+0.011
Top resid features:
the
Token the
Feature activation-0.011
Top resid features:
dough
Token dough
Feature activation+0.014
Top resid features:
or
Token or
Feature activation+0.022
Top resid features:
batter
Token batter
Feature activation+0.011
Top resid features:
by
Token by
Feature activation+3.111
Top resid features:
kn
Token kn
Feature activation+0.171
Top resid features:
ead
Tokenead
Feature activation+0.144
Top resid features:
ing
Tokening
Feature activation-0.069
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
stirring
Token stirring
Feature activation+0.000
Top resid features:
take
Token take
Feature activation+0.001
Top resid features:
capital
Token capital
Feature activation+0.001
Top resid features:
ships
Token ships
Feature activation+0.020
Top resid features:
apart
Token apart
Feature activation+0.012
Top resid features:
piece
Token piece
Feature activation+0.062
Top resid features:
by
Token by
Feature activation+3.303
Top resid features:
piece
Token piece
Feature activation+0.089
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
take
Token take
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
enabled
Tokenenabled
Feature activation+0.005
Top resid features:
creativity
Token creativity
Feature activation-0.009
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.003
Top resid features:
"
Token "
Feature activation+0.096
Top resid features:
one
Tokenone
Feature activation+0.018
Top resid features:
by
Token by
Feature activation+2.967
Top resid features:
one
Token one
Feature activation+0.080
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
B
Token B
Feature activation+0.000
Top resid features:
els
Tokenels
Feature activation+0.000
Top resid features:
ky
Tokenky
Feature activation+0.000
Top resid features:
take
Tokentake
Feature activation+0.017
Top resid features:
capital
Token capital
Feature activation+0.002
Top resid features:
ships
Token ships
Feature activation+0.010
Top resid features:
apart
Token apart
Feature activation+0.004
Top resid features:
piece
Token piece
Feature activation+0.020
Top resid features:
by
Token by
Feature activation+3.003
Top resid features:
piece
Token piece
Feature activation+0.077
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
take
Token take
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
custody
Token custody
Feature activation-0.005
Top resid features:
battles
Token battles
Feature activation-0.038
Top resid features:
on
Token on
Feature activation-0.035
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
case
Token case
Feature activation-0.029
Top resid features:
by
Token by
Feature activation+2.928
Top resid features:
case
Token case
Feature activation+0.192
Top resid features:
basis
Token basis
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
research
Token research
Feature activation+0.000
Top resid features:
D
TokenD
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
brushes
Token brushes
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
step
Token step
Feature activation-0.024
Top resid features:
by
Token by
Feature activation+2.678
Top resid features:
step
Token step
Feature activation+0.246
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
explanatory
Token explanatory
Feature activation+0.000
Top resid features:
diagram
Token diagram
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
too
Token too
Feature activation-0.025
Top resid features:
far
Token far
Feature activation-0.015
Top resid features:
to
Token to
Feature activation+0.034
Top resid features:
commute
Token commute
Feature activation+0.048
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
by
Token by
Feature activation+2.673
Top resid features:
foot
Token foot
Feature activation+0.185
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Furthermore
Token Furthermore
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.036
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
property
Token property
Feature activation+0.017
Top resid features:
tax
Token tax
Feature activation-0.046
Top resid features:
bill
Token bill
Feature activation-0.009
Top resid features:
by
Token by
Feature activation+2.917
Top resid features:
95
Token 95
Feature activation+0.187
Top resid features:
percent
Token percent
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
way
Token way
Feature activation-0.019
Top resid features:
is
Token is
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
sort
Token sort
Feature activation+0.039
Top resid features:
them
Token them
Feature activation-0.013
Top resid features:
by
Token by
Feature activation+2.691
Top resid features:
frequency
Token frequency
Feature activation+0.200
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
usage
Token usage
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
You
Token You
Feature activation+0.000
Top resid features:
card
Token card
Feature activation+0.039
Top resid features:
containing
Token containing
Feature activation+0.028
Top resid features:
exclusive
Token exclusive
Feature activation-0.004
Top resid features:
track
Token track
Feature activation+0.053
Top resid features:
-
Token-
Feature activation-0.053
Top resid features:
by
Tokenby
Feature activation+2.785
Top resid features:
-
Token-
Feature activation-0.023
Top resid features:
track
Tokentrack
Feature activation+0.014
Top resid features:
interviews
Token interviews
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:
evaluate
Token evaluate
Feature activation-0.037
Top resid features:
on
Token on
Feature activation-0.189
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
quarter
Token quarter
Feature activation+0.200
Top resid features:
-
Token-
Feature activation-0.097
Top resid features:
by
Tokenby
Feature activation+2.993
Top resid features:
-
Token-
Feature activation-0.050
Top resid features:
quarter
Tokenquarter
Feature activation+0.096
Top resid features:
basis
Token basis
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.083
Top resid features:
-
Token-
Feature activation-0.012
Top resid features:
by
Tokenby
Feature activation+2.688
Top resid features:
-
Token-
Feature activation+0.012
Top resid features:
p
Tokenp
Feature activation+0.075
Top resid features:
itch
Tokenitch
Feature activation+0.074
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Brad
Token Brad
Feature activation+0.000
Top resid features:
D
TokenD
Feature activation+0.007
Top resid features:
iction
Tokeniction
Feature activation+0.003
Top resid features:
aries
Tokenaries
Feature activation+0.025
Top resid features:
sort
Token sort
Feature activation+0.057
Top resid features:
words
Token words
Feature activation-0.003
Top resid features:
by
Token by
Feature activation+2.437
Top resid features:
alphabet
Token alphabet
Feature activation+0.134
Top resid features:
ical
Tokenical
Feature activation+0.077
Top resid features:
order
Token order
Feature activation+0.080
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
ab
Tokenab
Feature activation+0.003
Top resid features:
inding
Tokeninding
Feature activation+0.002
Top resid features:
Hub
Token Hub
Feature activation+0.001
Top resid features:
Tile
TokenTile
Feature activation+0.003
Top resid features:
Step
Token Step
Feature activation+0.022
Top resid features:
by
Token by
Feature activation+2.547
Top resid features:
Step
Token Step
Feature activation+0.283
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
This
TokenThis
Feature activation+0.000
Top resid features:
example
Token example
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.009
Top resid features:
decided
Token decided
Feature activation-0.038
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
extend
Token extend
Feature activation-0.183
Top resid features:
it
Token it
Feature activation+0.029
Top resid features:
by
Token by
Feature activation+2.719
Top resid features:
a
Token a
Feature activation+0.036
Top resid features:
few
Token few
Feature activation+0.128
Top resid features:
days
Token days
Feature activation+0.120
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
gather
Token gather
Feature activation+0.000
Top resid features:
gmail
Tokengmail
Feature activation+0.015
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
com
Tokencom
Feature activation-0.002
Top resid features:
Received
Token Received
Feature activation+0.066
Top resid features:
:
Token:
Feature activation+0.058
Top resid features:
by
Token by
Feature activation+2.504
Top resid features:
10
Token 10
Feature activation+0.127
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
25
Token25
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
24
Token24
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Even
TokenEven
Feature activation-0.026
Top resid features:
without
Token without
Feature activation-0.148
Top resid features:
step
Token step
Feature activation+0.059
Top resid features:
-
Token-
Feature activation-0.087
Top resid features:
by
Tokenby
Feature activation+2.965
Top resid features:
-
Token-
Feature activation-0.030
Top resid features:
step
Tokenstep
Feature activation+0.000
Top resid features:
instructions
Token instructions
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Republican
Token Republican
Feature activation-0.008
Top resid features:
presidential
Token presidential
Feature activation-0.001
Top resid features:
candidate
Token candidate
Feature activation-0.006
Top resid features:
John
Token John
Feature activation-0.003
Top resid features:
McCain
Token McCain
Feature activation-0.008
Top resid features:
by
Token by
Feature activation+2.693
Top resid features:
11
Token 11
Feature activation+0.122
Top resid features:
percentage
Token percentage
Feature activation+0.049
Top resid features:
points
Token points
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
close
Token close
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.033
Top resid features:
questions
Token questions
Feature activation-0.020
Top resid features:
by
Token by
Feature activation+2.636
Top resid features:
March
Token March
Feature activation-0.121
Top resid features:
1
Token 1
Feature activation+0.191
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
him
Token him
Feature activation-0.005
Top resid features:
from
Token from
Feature activation+0.023
Top resid features:
Paw
Token Paw
Feature activation+0.019
Top resid features:
t
Tokent
Feature activation+0.006
Top resid features:
ucket
Tokenucket
Feature activation+0.019
Top resid features:
by
Token by
Feature activation+2.610
Top resid features:
May
Token May
Feature activation-0.066
Top resid features:
1
Token 1
Feature activation+0.076
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
remained
Token remained
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.04

Head 2: 0.40

Head 3: 0.05

Head 4: 0.02

Head 5: 0.03

Head 6: 0.06

Head 7: 0.05

Head 8: 0.13

Head 9: 0.05

Head 10: 0.06

Head 11: 0.07

Positive logits

mentioning1.05

fiat1.04

sprink1.03

dding1.03

infusion1.03

ixel1.02

leaping1.01

slapping1.00

obo0.98

manufacturer0.97

tapping0.97

eternity0.97

employing0.96

Bay0.95

feeding0.95

olding0.94

asuring0.94

3730.93

4200.93

rounding0.93

Negative logits

ibaba-1.47

neighb-1.34

Roose-1.17

vae-1.13

wcs-1.12

ums-1.09

endas-1.09

pherd-1.09

wors-1.08

ptoms-1.07

ntil-1.07

etsk-1.05

liga-1.02

marched-1.01

persisted-1.00

vind-1.00

ignty-1.00

ça-0.99

iries-0.98

igue-0.98

INTERVAL 2.478 - 2.754
CONTAINS 0.000%

creativity
Token creativity
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
"
Token "
Feature activation+0.000
one
Tokenone
Feature activation+0.000
by
Token by
Feature activation+0.000
one
Token one
Feature activation+2.492
,"
Token,"
Feature activation+0.619
B
Token B
Feature activation+0.000
els
Tokenels
Feature activation+0.000
ky
Tokenky
Feature activation+0.000
says
Token says
Feature activation+0.000
or
Token or
Feature activation+0.000
batter
Token batter
Feature activation+0.000
by
Token by
Feature activation+0.000
kn
Token kn
Feature activation+0.754
ead
Tokenead
Feature activation+1.493
ing
Tokening
Feature activation+2.754
or
Token or
Feature activation+0.191
stirring
Token stirring
Feature activation+0.287
helps
Token helps
Feature activation+0.000
encourage
Token encourage
Feature activation+0.000
bonding
Token bonding
Feature activation+0.000
capital
Token capital
Feature activation+0.000
ships
Token ships
Feature activation+0.000
apart
Token apart
Feature activation+0.000
piece
Token piece
Feature activation+0.000
by
Token by
Feature activation+0.000
piece
Token piece
Feature activation+2.735
âĢĵ
Token âĢĵ
Feature activation+0.044
take
Token take
Feature activation+0.000
out
Token out
Feature activation+0.000
their
Token their
Feature activation+0.000
turrets
Token turrets
Feature activation+0.000

INTERVAL 2.203 - 2.478
CONTAINS 0.000%

battles
Token battles
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
case
Token case
Feature activation+0.000
by
Token by
Feature activation+0.000
case
Token case
Feature activation+2.302
basis
Token basis
Feature activation+0.275
with
Token with
Feature activation+0.000
more
Token more
Feature activation+0.000
research
Token research
Feature activation+0.000
and
Token and
Feature activation+0.000
capital
Token capital
Feature activation+0.000
ships
Token ships
Feature activation+0.000
apart
Token apart
Feature activation+0.000
piece
Token piece
Feature activation+0.000
by
Token by
Feature activation+0.000
piece
Token piece
Feature activation+2.478
âĢĵ
Token âĢĵ
Feature activation+0.062
take
Token take
Feature activation+0.000
out
Token out
Feature activation+0.000
their
Token their
Feature activation+0.000
turrets
Token turrets
Feature activation+0.000
,
Token,
Feature activation+0.000
brushes
Token brushes
Feature activation+0.000
,
Token,
Feature activation+0.000
step
Token step
Feature activation+0.000
by
Token by
Feature activation+0.000
step
Token step
Feature activation+2.252
,
Token,
Feature activation+0.794
explanatory
Token explanatory
Feature activation+0.000
diagram
Token diagram
Feature activation+0.000
)
Token)
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 1.928 - 2.203
CONTAINS 0.002%

candidate
Token candidate
Feature activation+0.000
John
Token John
Feature activation+0.000
McCain
Token McCain
Feature activation+0.000
by
Token by
Feature activation+0.000
11
Token 11
Feature activation+0.860
percentage
Token percentage
Feature activation+2.037
points
Token points
Feature activation+1.799
and
Token and
Feature activation+1.080
close
Token close
Feature activation+0.187
to
Token to
Feature activation+0.000
1
Token 1
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
questions
Token questions
Feature activation+0.000
by
Token by
Feature activation+0.000
March
Token March
Feature activation+0.745
1
Token 1
Feature activation+0.946
,
Token,
Feature activation+2.035
as
Token as
Feature activation+0.429
her
Token her
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
ask
Token ask
Feature activation+0.000
drug
Token drug
Feature activation+0.000
by
Token by
Feature activation+0.000
5
Token 5
Feature activation+0.411
,
Token,
Feature activation+0.711
000
Token000
Feature activation+1.749
percent
Token percent
Feature activation+1.944
but
Token but
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
convicted
Token convicted
Feature activation+0.000
by
Token by
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
Received
Token Received
Feature activation+0.000
:
Token:
Feature activation+0.000
by
Token by
Feature activation+0.222
10
Token 10
Feature activation+2.090
.
Token.
Feature activation+1.132
25
Token25
Feature activation+1.245
.
Token.
Feature activation+0.000
24
Token24
Feature activation+0.040
.
Token.
Feature activation+0.000
inding
Tokeninding
Feature activation+0.000
Hub
Token Hub
Feature activation+0.000
Tile
TokenTile
Feature activation+0.000
Step
Token Step
Feature activation+0.000
by
Token by
Feature activation+0.000
Step
Token Step
Feature activation+2.130
Ċ
TokenĊ
Feature activation+1.064
Ċ
TokenĊ
Feature activation+0.481
This
TokenThis
Feature activation+0.000
example
Token example
Feature activation+0.000
demonstrates
Token demonstrates
Feature activation+0.000

INTERVAL 1.652 - 1.928
CONTAINS 0.007%

leaders
Token leaders
Feature activation+0.000
Sydney
Token Sydney
Feature activation+0.000
FC
Token FC
Feature activation+0.000
by
Token by
Feature activation+0.000
17
Token 17
Feature activation+1.172
points
Token points
Feature activation+1.815
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
President
TokenPresident
Feature activation+0.000
Barack
Token Barack
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
Sort
TokenSort
Feature activation+0.000
by
Token by
Feature activation+0.000
popularity
Token popularity
Feature activation+1.514
Sort
Token Sort
Feature activation+1.204
by
Token by
Feature activation+0.000
date
Token date
Feature activation+1.712
Ċ
TokenĊ
Feature activation+0.413
Ċ
TokenĊ
Feature activation+0.298
Top
TokenTop
Feature activation+0.000
contributor
Token contributor
Feature activation+0.000
ra
Token ra
Feature activation+0.000
without
Token without
Feature activation+0.000
step
Token step
Feature activation+0.000
-
Token-
Feature activation+0.000
by
Tokenby
Feature activation+0.000
-
Token-
Feature activation+2.061
step
Tokenstep
Feature activation+1.669
instructions
Token instructions
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
pattern
Token pattern
Feature activation+0.000
envelop
Token envelop
Feature activation+0.000
on
Tokenon
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token1
Feature activation+0.000
festival
Token festival
Feature activation+0.000
by
Token by
Feature activation+0.000
car
Token car
Feature activation+1.719
with
Token with
Feature activation+0.291
several
Token several
Feature activation+0.000
friends
Token friends
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
here
Token here
Feature activation+0.000
before
Token before
Feature activation+0.000
being
Token being
Feature activation+0.000
deported
Token deported
Feature activation+0.000
by
Token by
Feature activation+0.000
bus
Token bus
Feature activation+1.925
back
Token back
Feature activation+1.475
to
Token to
Feature activation+0.213
their
Token their
Feature activation+0.000
countries
Token countries
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.377 - 1.652
CONTAINS 0.010%

rivers
Token rivers
Feature activation+0.000
,
Token,
Feature activation+0.243
bl
Token bl
Feature activation+0.000
est
Tokenest
Feature activation+0.000
by
Token by
Feature activation+0.000
sun
Token sun
Feature activation+1.491
s
Tokens
Feature activation+0.828
of
Token of
Feature activation+0.904
home
Token home
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
survey
Token survey
Feature activation+0.000
conducted
Token conducted
Feature activation+0.000
by
Token by
Feature activation+0.000
personal
Token personal
Feature activation+0.371
finance
Token finance
Feature activation+0.302
site
Token site
Feature activation+1.412
Nerd
Token Nerd
Feature activation+0.000
Wallet
TokenWallet
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
student
Token student
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
by
Token by
Feature activation+0.000
28
Token 28
Feature activation+1.697
âĢ
TokenâĢ
Feature activation+1.826
Ŀ
TokenĿ
Feature activation+0.000
of
Token of
Feature activation+1.597
which
Token which
Feature activation+0.000
24
Token 24
Feature activation+0.000
inches
Token inches
Feature activation+0.000
is
Token is
Feature activation+0.000
reserved
Token reserved
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
many
Token many
Feature activation+0.000
efforts
Token efforts
Feature activation+0.000
by
Token by
Feature activation+0.000
neighborhood
Token neighborhood
Feature activation+1.429
partners
Token partners
Feature activation+0.486
to
Token to
Feature activation+0.171
increase
Token increase
Feature activation+0.000
opportunities
Token opportunities
Feature activation+0.000
for
Token for
Feature activation+0.000
to
Token to
Feature activation+0.000
sort
Token sort
Feature activation+0.000
the
Token the
Feature activation+0.000
table
Token table
Feature activation+0.000
by
Token by
Feature activation+0.000
newest
Token newest
Feature activation+1.625
to
Token to
Feature activation+0.573
oldest
Token oldest
Feature activation+0.015
releases
Token releases
Feature activation+0.000
.
Token.
Feature activation+0.000
Also
Token Also
Feature activation+0.000

INTERVAL 1.101 - 1.377
CONTAINS 0.018%

why
Token why
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
by
Tokenby
Feature activation+0.000
-
Token-
Feature activation+1.108
one
Tokenone
Feature activation+1.619
,
Token,
Feature activation+0.205
our
Token our
Feature activation+0.000
musical
Token musical
Feature activation+0.000
tastes
Token tastes
Feature activation+0.000
Bowl
Token Bowl
Feature activation+0.000
contender
Token contender
Feature activation+0.000
,
Token,
Feature activation+0.000
losing
Token losing
Feature activation+0.000
by
Token by
Feature activation+0.000
21
Token 21
Feature activation+1.150
in
Token in
Feature activation+0.735
Week
Token Week
Feature activation+0.031
2
Token 2
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.196
gained
Token gained
Feature activation+0.000
by
Token by
Feature activation+0.000
3
Token 3
Feature activation+0.515
.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.000
percent
Token percent
Feature activation+1.284
and
Token and
Feature activation+0.583
commuter
Token commuter
Feature activation+0.000
rail
Token rail
Feature activation+0.000
riders
Token riders
Feature activation+0.000
hip
Tokenhip
Feature activation+0.000
ron
Tokenron
Feature activation+0.000
Legacy
Token Legacy
Feature activation+0.000
was
Token was
Feature activation+0.000
directed
Token directed
Feature activation+0.000
by
Token by
Feature activation+0.000
first
Token first
Feature activation+1.193
-
Token-
Feature activation+0.107
time
Tokentime
Feature activation+1.236
filmmaker
Token filmmaker
Feature activation+0.403
Joseph
Token Joseph
Feature activation+0.000
Kos
Token Kos
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
ambassador
Token ambassador
Feature activation+0.000
by
Token by
Feature activation+0.000
March
Token March
Feature activation+0.869
18
Token 18
Feature activation+1.372
,
Token,
Feature activation+1.266
âĢ
TokenâĢ
Feature activation+0.489
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
Vi
Token Vi
Feature activation+0.000

INTERVAL 0.826 - 1.101
CONTAINS 0.023%

they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
jump
Token jump
Feature activation+0.000
up
Token up
Feature activation+0.000
by
Token by
Feature activation+0.000
over
Token over
Feature activation+1.094
a
Token a
Feature activation+0.000
million
Token million
Feature activation+0.000
barrels
Token barrels
Feature activation+0.033
/
Token/
Feature activation+0.000
day
Tokenday
Feature activation+0.000
the
Token the
Feature activation+0.000
prevalence
Token prevalence
Feature activation+0.000
was
Token was
Feature activation+0.000
estimated
Token estimated
Feature activation+0.000
by
Token by
Feature activation+0.000
sampling
Token sampling
Feature activation+0.837
the
Token the
Feature activation+0.000
psychiatric
Token psychiatric
Feature activation+0.000
clinical
Token clinical
Feature activation+0.000
cases
Token cases
Feature activation+0.000
,
Token,
Feature activation+0.000
address
Token address
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
either
Token either
Feature activation+0.000
by
Token by
Feature activation+0.000
debating
Token debating
Feature activation+0.861
it
Token it
Feature activation+0.000
or
Token or
Feature activation+0.000
voting
Token voting
Feature activation+0.000
it
Token it
Feature activation+0.000
down
Token down
Feature activation+0.000
stock
Token stock
Feature activation+0.000
index
Token index
Feature activation+0.000
rose
Token rose
Feature activation+0.000
by
Token by
Feature activation+0.000
320
Token 320
Feature activation+0.483
%
Token%
Feature activation+1.021
since
Token since
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
2008
Token 2008
Feature activation+0.000
.
Token.
Feature activation+0.000
Learn
Token Learn
Feature activation+0.000
more
Token more
Feature activation+0.000
by
Token by
Feature activation+0.000
visiting
Token visiting
Feature activation+1.654
:
Token:
Feature activation+1.081
Ċ
TokenĊ
Feature activation+0.269
Ċ
TokenĊ
Feature activation+0.164
www
Tokenwww
Feature activation+0.000
.
Token.
Feature activation+0.000
e
Tokene
Feature activation+0.000

INTERVAL 0.551 - 0.826
CONTAINS 0.042%

high
Tokenhigh
Feature activation+0.000
-
Token-
Feature activation+0.000
power
Tokenpower
Feature activation+0.000
radio
Token radio
Feature activation+0.724
ampl
Token ampl
Feature activation+0.000
ifiers
Tokenifiers
Feature activation+0.701
,
Token,
Feature activation+0.000
provide
Token provide
Feature activation+0.000
more
Token more
Feature activation+0.000
WiFi
Token WiFi
Feature activation+0.000
range
Token range
Feature activation+0.000
els
Tokenels
Feature activation+0.000
by
Token by
Feature activation+0.000
tw
Token tw
Feature activation+1.374
os
Tokenos
Feature activation+1.747
,
Token,
Feature activation+0.571
and
Token and
Feature activation+0.692
two
Token two
Feature activation+0.000
dogs
Token dogs
Feature activation+0.000
chained
Token chained
Feature activation+0.000
outside
Token outside
Feature activation+0.000
the
Token the
Feature activation+0.000
horse
Tokenhorse
Feature activation+0.000
for
Token for
Feature activation+0.000
sale
Token sale
Feature activation+0.000
by
Token by
Feature activation+0.000
White
Token White
Feature activation+0.607
horse
Tokenhorse
Feature activation+0.645
Motors
Token Motors
Feature activation+0.000
.
Token.
Feature activation+0.000
Just
Token Just
Feature activation+0.000
where
Token where
Feature activation+0.000
this
Token this
Feature activation+0.000
dec
Token dec
Feature activation+0.000
ert
Tokenert
Feature activation+0.000
ification
Tokenification
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.214
NFL
Token NFL
Feature activation+0.593
PA
TokenPA
Feature activation+0.000
that
Token that
Feature activation+0.000
occurred
Token occurred
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
you
Token you
Feature activation+0.000
sort
Token sort
Feature activation+0.000
them
Token them
Feature activation+0.000
by
Token by
Feature activation+0.000
their
Token their
Feature activation+0.858
frequency
Token frequency
Feature activation+0.620
.
Token.
Feature activation+0.000
Common
Token Common
Feature activation+0.000
words
Token words
Feature activation+0.000
like
Token like
Feature activation+0.000
de
Token de
Feature activation+0.000

INTERVAL 0.275 - 0.551
CONTAINS 0.069%

in
Token in
Feature activation+0.000
place
Token place
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.468
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.290
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
sex
Token sex
Feature activation+0.000
discrimination
Token discrimination
Feature activation+0.000
by
Token by
Feature activation+0.000
not
Token not
Feature activation+1.699
allowing
Token allowing
Feature activation+0.282
her
Token her
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
the
Token the
Feature activation+0.000
boys
Token boys
Feature activation+0.000
indicted
Token indicted
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.263
grand
Token grand
Feature activation+0.117
jury
Token jury
Feature activation+0.259
on
Token on
Feature activation+0.329
Tuesday
Token Tuesday
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
misdemeanor
Token misdemeanor
Feature activation+0.000
charge
Token charge
Feature activation+0.000
is
Token is
Feature activation+0.000
being
Token being
Feature activation+0.000
attended
Token attended
Feature activation+0.000
by
Token by
Feature activation+0.000
regional
Token regional
Feature activation+0.595
and
Token and
Feature activation+0.308
international
Token international
Feature activation+0.000
experts
Token experts
Feature activation+0.000
,
Token,
Feature activation+0.000
startups
Token startups
Feature activation+0.000
,
Token,
Feature activation+0.000
decided
Token decided
Feature activation+0.000
by
Token by
Feature activation+0.000
10
Token 10
Feature activation+0.884
points
Token points
Feature activation+1.301
or
Token or
Feature activation+0.777
less
Token less
Feature activation+0.323
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
getting
Tokengetting
Feature activation+0.000

INTERVAL 0.000 - 0.275
CONTAINS 99.830%

Ļ
TokenĻ
Feature activation+0.000
when
Token when
Feature activation+0.000
she
Token she
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
person
Token person
Feature activation+0.000
that
Token that
Feature activation+0.000
made
Token made
Feature activation+0.000
the
Token the
Feature activation+0.000
difference
Token difference
Feature activation+0.000
?
Token?
Feature activation+0.000
super
Token super
Feature activation+0.000
nova
Tokennova
Feature activation+0.000
lens
Token lens
Feature activation+0.000
ed
Tokened
Feature activation+0.000
into
Token into
Feature activation+0.000
four
Token four
Feature activation+0.000
copies
Token copies
Feature activation+0.000
of
Token of
Feature activation+0.000
itself
Token itself
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.094
no
Token no
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
anti
Token anti
Feature activation+0.000
-
Token-
Feature activation+0.000
dep
Tokendep
Feature activation+0.000
ress
Tokenress
Feature activation+0.000
ant
Tokenant
Feature activation+0.000
Cy
Token Cy
Feature activation+0.000
mb
Tokenmb
Feature activation+0.000
,
Token,
Feature activation+0.000
human
Token human
Feature activation+0.000
reptiles
Token reptiles
Feature activation+0.000
,
Token,
Feature activation+0.000
l
Token l
Feature activation+0.000
izards
Tokenizards
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
sounds
Token sounds
Feature activation+0.000
that
Token that
Feature activation+0.000
these
Token these
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
10
Token 10
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
average
Token average
Feature activation+0.000
of
Token of
Feature activation+0.000
90
Token 90
Feature activation+0.000
games
Token games
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