H2.8 top features

Top feature 0 in H2.8: (feature 21438)

TOP ACTIVATIONS
MAX = 4.755

He
TokenHe
Feature activation+0.000
even
Token even
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+1.675
positive
Token positive
Feature activation+2.680
spin
Token spin
Feature activation+4.755
on
Token on
Feature activation+3.422
bullies
Token bullies
Feature activation+0.000
.
Token.
Feature activation+0.123
Ċ
TokenĊ
Feature activation+0.082
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
custom
Token custom
Feature activation+0.000
was
Token was
Feature activation+0.000
put
Token put
Feature activation+0.000
to
Token to
Feature activation+1.488
rest
Token rest
Feature activation+4.590
,
Token,
Feature activation+0.748
and
Token and
Feature activation+0.205
so
Token so
Feature activation+0.000
began
Token began
Feature activation+0.000
the
Token the
Feature activation+0.000
and
Token and
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+1.337
blind
Token blind
Feature activation+1.660
fold
Tokenfold
Feature activation+1.761
on
Token on
Feature activation+4.414
you
Token you
Feature activation+0.064
and
Token and
Feature activation+0.241
you
Token you
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
,
Token,
Feature activation+0.000
genocide
Token genocide
Feature activation+0.000
.
Token.
Feature activation+0.000
Put
Token Put
Feature activation+0.000
another
Token another
Feature activation+1.835
way
Token way
Feature activation+4.388
,
Token,
Feature activation+0.966
I
Token I
Feature activation+0.230
am
Token am
Feature activation+0.000
hostile
Token hostile
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
these
Token these
Feature activation+0.349
things
Token things
Feature activation+0.000
to
Token to
Feature activation+3.486
great
Token great
Feature activation+1.180
use
Token use
Feature activation+4.344
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
mere
Token mere
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+1.569
foot
Token foot
Feature activation+4.302
wrong
Token wrong
Feature activation+3.377
,
Token,
Feature activation+1.827
because
Token because
Feature activation+0.000
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.000
these
Token these
Feature activation+0.000
people
Token people
Feature activation+0.000
put
Token put
Feature activation+0.000
together
Token together
Feature activation+1.182
a
Token a
Feature activation+1.687
place
Token place
Feature activation+4.276
that
Token that
Feature activation+0.748
was
Token was
Feature activation+0.115
known
Token known
Feature activation+0.000
as
Token as
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ads
Tokenads
Feature activation+0.000
have
Token have
Feature activation+0.000
put
Token put
Feature activation+0.000
in
Token in
Feature activation+1.584
huge
Token huge
Feature activation+0.606
effort
Token effort
Feature activation+4.221
to
Token to
Feature activation+2.530
make
Token make
Feature activation+0.000
it
Token it
Feature activation+0.000
here
Token here
Feature activation+0.000
to
Token to
Feature activation+0.000
The
Token The
Feature activation+0.000
permit
Token permit
Feature activation+0.000
system
Token system
Feature activation+0.000
put
Token put
Feature activation+0.000
in
Token in
Feature activation+1.049
place
Token place
Feature activation+4.196
in
Token in
Feature activation+1.175
the
Token the
Feature activation+0.946
early
Token early
Feature activation+0.319
1990
Token 1990
Feature activation+0.000
s
Tokens
Feature activation+0.000
Let
Token Let
Feature activation+0.000
's
Token's
Feature activation+0.000
put
Token put
Feature activation+0.000
it
Token it
Feature activation+1.786
this
Token this
Feature activation+1.019
way
Token way
Feature activation+4.178
;
Token;
Feature activation+0.000
only
Token only
Feature activation+0.000
a
Token a
Feature activation+0.154
few
Token few
Feature activation+0.000
villains
Token villains
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+1.363
that
Token that
Feature activation+2.139
way
Token way
Feature activation+4.135
,
Token,
Feature activation+0.569
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Podesta
Token Podesta
Feature activation+0.000
responded
Token responded
Feature activation+0.000
lot
Token lot
Feature activation+2.293
of
Token of
Feature activation+1.423
care
Token care
Feature activation+0.914
and
Token and
Feature activation+0.708
attention
Token attention
Feature activation+0.023
into
Token into
Feature activation+4.115
the
Token the
Feature activation+0.000
Winter
Token Winter
Feature activation+0.000
Ap
Token Ap
Feature activation+0.000
f
Tokenf
Feature activation+0.000
el
Tokenel
Feature activation+0.000
"
Token "
Feature activation+0.000
Europe
TokenEurope
Feature activation+0.000
should
Token should
Feature activation+0.000
put
Token put
Feature activation+0.000
an
Token an
Feature activation+1.464
end
Token end
Feature activation+4.113
to
Token to
Feature activation+4.109
social
Token social
Feature activation+0.034
dumping
Token dumping
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Europe
TokenEurope
Feature activation+0.000
should
Token should
Feature activation+0.000
put
Token put
Feature activation+0.000
an
Token an
Feature activation+1.464
end
Token end
Feature activation+4.113
to
Token to
Feature activation+4.109
social
Token social
Feature activation+0.034
dumping
Token dumping
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
put
Token put
Feature activation+0.000
in
Token in
Feature activation+1.662
the
Token the
Feature activation+1.802
time
Token time
Feature activation+2.437
and
Token and
Feature activation+0.661
effort
Token effort
Feature activation+4.041
to
Token to
Feature activation+1.656
mine
Token mine
Feature activation+0.733
its
Token its
Feature activation+0.000
treasure
Token treasure
Feature activation+0.000
trove
Token trove
Feature activation+0.000
just
Token just
Feature activation+0.000
put
Token put
Feature activation+0.207
all
Token all
Feature activation+1.148
my
Token my
Feature activation+2.724
cards
Token cards
Feature activation+1.854
on
Token on
Feature activation+4.031
the
Token the
Feature activation+0.505
table
Token table
Feature activation+0.000
,
Token,
Feature activation+0.873
and
Token and
Feature activation+0.132
dragged
Token dragged
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
provinces
Token provinces
Feature activation+0.000
put
Token put
Feature activation+0.199
in
Token in
Feature activation+1.293
place
Token place
Feature activation+4.009
stop
Token stop
Feature activation+2.445
gap
Tokengap
Feature activation+0.000
refugee
Token refugee
Feature activation+0.000
health
Token health
Feature activation+0.000
coverage
Token coverage
Feature activation+0.000
will
Token will
Feature activation+0.000
put
Token put
Feature activation+0.000
our
Token our
Feature activation+0.000
veterans
Token veterans
Feature activation+0.000
in
Token in
Feature activation+3.693
front
Token front
Feature activation+3.956
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
line
Token line
Feature activation+0.000
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+1.040
lot
Token lot
Feature activation+2.386
of
Token of
Feature activation+1.641
that
Token that
Feature activation+2.042
into
Token into
Feature activation+3.946
effect
Token effect
Feature activation+0.396
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
East
Token East
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
put
Token put
Feature activation+0.012
an
Token an
Feature activation+1.045
end
Token end
Feature activation+3.914
to
Token to
Feature activation+3.425
war
Token war
Feature activation+0.261
in
Token in
Feature activation+1.639
the
Token the
Feature activation+0.099
way
Token way
Feature activation+1.511

Top DFA by src position
MAX = 5.861

.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.049
Top resid features:
Ċ
TokenĊ
Feature activation+0.060
Top resid features:
He
TokenHe
Feature activation+0.081
Top resid features:
even
Token even
Feature activation+0.113
Top resid features:
put
Token put
Feature activation+5.622
Top resid features:
a
Token a
Feature activation+0.358
Top resid features:
positive
Token positive
Feature activation+0.358
Top resid features:
spin
Token spin
Feature activation+0.111
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
bullies
Token bullies
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.044
Top resid features:
point
Token point
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.159
Top resid features:
custom
Token custom
Feature activation+0.025
Top resid features:
was
Token was
Feature activation-0.027
Top resid features:
put
Token put
Feature activation+5.861
Top resid features:
to
Token to
Feature activation+0.245
Top resid features:
rest
Token rest
Feature activation+0.047
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.025
Top resid features:
somebody
Token somebody
Feature activation+0.031
Top resid features:
grabbed
Token grabbed
Feature activation+0.070
Top resid features:
you
Token you
Feature activation+0.020
Top resid features:
and
Token and
Feature activation+0.089
Top resid features:
put
Token put
Feature activation+4.416
Top resid features:
a
Token a
Feature activation+0.334
Top resid features:
blind
Token blind
Feature activation+0.289
Top resid features:
fold
Tokenfold
Feature activation+0.595
Top resid features:
on
Token on
Feature activation+0.251
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.043
Top resid features:
worst
Token worst
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
genocide
Token genocide
Feature activation+0.051
Top resid features:
.
Token.
Feature activation+0.109
Top resid features:
Put
Token Put
Feature activation+5.571
Top resid features:
another
Token another
Feature activation+0.351
Top resid features:
way
Token way
Feature activation+0.036
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
am
Token am
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
Those
Token Those
Feature activation+0.044
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
do
Token do
Feature activation+0.031
Top resid features:
can
Token can
Feature activation-0.004
Top resid features:
put
Token put
Feature activation+5.605
Top resid features:
these
Token these
Feature activation+0.092
Top resid features:
things
Token things
Feature activation-0.043
Top resid features:
to
Token to
Feature activation+0.213
Top resid features:
great
Token great
Feature activation+0.305
Top resid features:
use
Token use
Feature activation+0.053
Top resid features:
it
Token it
Feature activation+0.009
Top resid features:
doesn
Token doesn
Feature activation+0.012
Top resid features:
âĢ
TokenâĢ
Feature activation+0.099
Top resid features:
Ļ
TokenĻ
Feature activation+0.006
Top resid features:
t
Tokent
Feature activation+0.057
Top resid features:
put
Token put
Feature activation+5.378
Top resid features:
a
Token a
Feature activation+0.541
Top resid features:
foot
Token foot
Feature activation+0.016
Top resid features:
wrong
Token wrong
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
because
Token because
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.069
Top resid features:
together
Token together
Feature activation-0.028
Top resid features:
these
Token these
Feature activation+0.033
Top resid features:
people
Token people
Feature activation+0.056
Top resid features:
put
Token put
Feature activation+5.147
Top resid features:
together
Token together
Feature activation+0.511
Top resid features:
a
Token a
Feature activation+0.462
Top resid features:
place
Token place
Feature activation+0.125
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+0.013
Top resid features:
These
Token These
Feature activation+0.045
Top resid features:
l
Token l
Feature activation+0.002
Top resid features:
ads
Tokenads
Feature activation+0.054
Top resid features:
have
Token have
Feature activation+0.058
Top resid features:
put
Token put
Feature activation+5.030
Top resid features:
in
Token in
Feature activation+0.434
Top resid features:
huge
Token huge
Feature activation+0.246
Top resid features:
effort
Token effort
Feature activation+0.090
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
restrictive
Token restrictive
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.065
Top resid features:
The
Token The
Feature activation+0.158
Top resid features:
permit
Token permit
Feature activation+0.089
Top resid features:
system
Token system
Feature activation+0.076
Top resid features:
put
Token put
Feature activation+5.097
Top resid features:
in
Token in
Feature activation+0.592
Top resid features:
place
Token place
Feature activation+0.088
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
early
Token early
Feature activation+0.000
Top resid features:
never
Token never
Feature activation+0.029
Top resid features:
trusted
Token trusted
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.048
Top resid features:
Let
Token Let
Feature activation+0.092
Top resid features:
's
Token's
Feature activation+0.018
Top resid features:
put
Token put
Feature activation+5.300
Top resid features:
it
Token it
Feature activation+0.094
Top resid features:
this
Token this
Feature activation+0.346
Top resid features:
way
Token way
Feature activation+0.027
Top resid features:
;
Token;
Feature activation+0.000
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
let
Token let
Feature activation+0.054
Top resid features:
âĢ
TokenâĢ
Feature activation+0.025
Top resid features:
Ļ
TokenĻ
Feature activation+0.028
Top resid features:
s
Tokens
Feature activation+0.026
Top resid features:
put
Token put
Feature activation+4.978
Top resid features:
it
Token it
Feature activation+0.083
Top resid features:
that
Token that
Feature activation+0.574
Top resid features:
way
Token way
Feature activation+0.063
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.013
Top resid features:
G
Token G
Feature activation+0.006
Top resid features:
ub
Tokenub
Feature activation+0.002
Top resid features:
or
Tokenor
Feature activation-0.001
Top resid features:
have
Token have
Feature activation+0.052
Top resid features:
put
Token put
Feature activation+4.886
Top resid features:
a
Token a
Feature activation+0.079
Top resid features:
lot
Token lot
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.071
Top resid features:
care
Token care
Feature activation-0.021
Top resid features:
and
Token and
Feature activation+0.167
Top resid features:
cker
Tokencker
Feature activation+0.018
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
"
Token "
Feature activation-0.006
Top resid features:
Europe
TokenEurope
Feature activation+0.094
Top resid features:
should
Token should
Feature activation-0.093
Top resid features:
put
Token put
Feature activation+5.395
Top resid features:
an
Token an
Feature activation+0.556
Top resid features:
end
Token end
Feature activation+0.177
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
social
Token social
Feature activation+0.000
Top resid features:
dumping
Token dumping
Feature activation+0.000
Top resid features:
cker
Tokencker
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
"
Token "
Feature activation+0.014
Top resid features:
Europe
TokenEurope
Feature activation+0.094
Top resid features:
should
Token should
Feature activation+0.093
Top resid features:
put
Token put
Feature activation+4.834
Top resid features:
an
Token an
Feature activation+0.387
Top resid features:
end
Token end
Feature activation+0.381
Top resid features:
to
Token to
Feature activation+0.305
Top resid features:
social
Token social
Feature activation+0.000
Top resid features:
dumping
Token dumping
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.014
Top resid features:
only
Token only
Feature activation+0.021
Top resid features:
those
Token those
Feature activation+0.028
Top resid features:
prepared
Token prepared
Feature activation+0.034
Top resid features:
to
Token to
Feature activation+0.062
Top resid features:
put
Token put
Feature activation+4.802
Top resid features:
in
Token in
Feature activation+0.207
Top resid features:
the
Token the
Feature activation+0.344
Top resid features:
time
Token time
Feature activation+0.120
Top resid features:
and
Token and
Feature activation+0.069
Top resid features:
effort
Token effort
Feature activation+0.083
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
story
Token story
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
I
Token I
Feature activation+0.037
Top resid features:
just
Token just
Feature activation+0.041
Top resid features:
put
Token put
Feature activation+4.882
Top resid features:
all
Token all
Feature activation+0.136
Top resid features:
my
Token my
Feature activation+0.281
Top resid features:
cards
Token cards
Feature activation+0.172
Top resid features:
on
Token on
Feature activation+0.258
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.055
Top resid features:
Quebec
Token Quebec
Feature activation+0.044
Top resid features:
and
Token and
Feature activation+0.030
Top resid features:
other
Token other
Feature activation+0.010
Top resid features:
provinces
Token provinces
Feature activation+0.088
Top resid features:
put
Token put
Feature activation+5.107
Top resid features:
in
Token in
Feature activation+0.438
Top resid features:
place
Token place
Feature activation+0.124
Top resid features:
stop
Token stop
Feature activation+0.000
Top resid features:
gap
Tokengap
Feature activation+0.000
Top resid features:
refugee
Token refugee
Feature activation+0.000
Top resid features:
need
Token need
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.026
Top resid features:
president
Token president
Feature activation-0.012
Top resid features:
that
Token that
Feature activation+0.032
Top resid features:
will
Token will
Feature activation+0.011
Top resid features:
put
Token put
Feature activation+4.896
Top resid features:
our
Token our
Feature activation+0.153
Top resid features:
veterans
Token veterans
Feature activation+0.285
Top resid features:
in
Token in
Feature activation+0.392
Top resid features:
front
Token front
Feature activation+0.016
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
We
Token We
Feature activation+0.028
Top resid features:
get
Token get
Feature activation+0.036
Top resid features:
good
Token good
Feature activation-0.009
Top resid features:
feedback
Token feedback
Feature activation-0.024
Top resid features:
and
Token and
Feature activation+0.052
Top resid features:
put
Token put
Feature activation+4.903
Top resid features:
a
Token a
Feature activation+0.130
Top resid features:
lot
Token lot
Feature activation+0.070
Top resid features:
of
Token of
Feature activation+0.101
Top resid features:
that
Token that
Feature activation+0.341
Top resid features:
into
Token into
Feature activation+0.138
Top resid features:
the
Token the
Feature activation+0.044
Top resid features:
Middle
Token Middle
Feature activation-0.015
Top resid features:
East
Token East
Feature activation-0.011
Top resid features:
that
Token that
Feature activation+0.074
Top resid features:
would
Token would
Feature activation+0.041
Top resid features:
put
Token put
Feature activation+5.045
Top resid features:
an
Token an
Feature activation+0.428
Top resid features:
end
Token end
Feature activation+0.127
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
war
Token war
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.02

Head 2: 0.04

Head 3: 0.06

Head 4: 0.05

Head 5: 0.05

Head 6: 0.03

Head 7: 0.02

Head 8: 0.56

Head 9: 0.04

Head 10: 0.05

Head 11: 0.02

Positive logits

endi1.37

leash1.36

overboard1.31

isky1.31

osal1.31

ixel1.30

lid1.26

alam1.23

aretz1.22

iphate1.21

atro1.18

clipboard1.17

shack1.15

Edison1.14

raining1.14

aside1.11

Engineers1.10

aston1.10

ookie1.10

ORN1.09

Negative logits

descended-1.32

entimes-1.29

quadru-1.25

days-1.24

scl-1.24

deport-1.23

xtap-1.20

unfocusedRange-1.19

pread-1.18

embodiments-1.18

arrivals-1.16

descend-1.16

descent-1.16

ctors-1.15

aved-1.13

travers-1.13

Purs-1.13

coh-1.12

-1.09

Rooms-1.08

INTERVAL 4.280 - 4.755
CONTAINS 0.001%

and
Token and
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+1.337
blind
Token blind
Feature activation+1.660
fold
Tokenfold
Feature activation+1.761
on
Token on
Feature activation+4.414
you
Token you
Feature activation+0.064
and
Token and
Feature activation+0.241
you
Token you
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
put
Token put
Feature activation+0.000
these
Token these
Feature activation+0.349
things
Token things
Feature activation+0.000
to
Token to
Feature activation+3.486
great
Token great
Feature activation+1.180
use
Token use
Feature activation+4.344
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
mere
Token mere
Feature activation+0.000
,
Token,
Feature activation+0.000
genocide
Token genocide
Feature activation+0.000
.
Token.
Feature activation+0.000
Put
Token Put
Feature activation+0.000
another
Token another
Feature activation+1.835
way
Token way
Feature activation+4.388
,
Token,
Feature activation+0.966
I
Token I
Feature activation+0.230
am
Token am
Feature activation+0.000
hostile
Token hostile
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
custom
Token custom
Feature activation+0.000
was
Token was
Feature activation+0.000
put
Token put
Feature activation+0.000
to
Token to
Feature activation+1.488
rest
Token rest
Feature activation+4.590
,
Token,
Feature activation+0.748
and
Token and
Feature activation+0.205
so
Token so
Feature activation+0.000
began
Token began
Feature activation+0.000
the
Token the
Feature activation+0.000
He
TokenHe
Feature activation+0.000
even
Token even
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+1.675
positive
Token positive
Feature activation+2.680
spin
Token spin
Feature activation+4.755
on
Token on
Feature activation+3.422
bullies
Token bullies
Feature activation+0.000
.
Token.
Feature activation+0.123
Ċ
TokenĊ
Feature activation+0.082
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.804 - 4.280
CONTAINS 0.002%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
put
Token put
Feature activation+0.000
it
Token it
Feature activation+1.363
that
Token that
Feature activation+2.139
way
Token way
Feature activation+4.135
,
Token,
Feature activation+0.569
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Podesta
Token Podesta
Feature activation+0.000
responded
Token responded
Feature activation+0.000
strives
Token strives
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
science
Token science
Feature activation+0.763
back
Token back
Feature activation+3.012
into
Token into
Feature activation+3.904
the
Token the
Feature activation+0.698
general
Token general
Feature activation+0.000
culture
Token culture
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+1.040
lot
Token lot
Feature activation+2.386
of
Token of
Feature activation+1.641
that
Token that
Feature activation+2.042
into
Token into
Feature activation+3.946
effect
Token effect
Feature activation+0.396
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
East
Token East
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
put
Token put
Feature activation+0.012
an
Token an
Feature activation+1.045
end
Token end
Feature activation+3.914
to
Token to
Feature activation+3.425
war
Token war
Feature activation+0.261
in
Token in
Feature activation+1.639
the
Token the
Feature activation+0.099
way
Token way
Feature activation+1.511
until
Token until
Feature activation+0.000
she
Token she
Feature activation+0.000
puts
Token puts
Feature activation+0.000
me
Token me
Feature activation+0.159
to
Token to
Feature activation+1.812
rest
Token rest
Feature activation+3.817
.
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

INTERVAL 3.329 - 3.804
CONTAINS 0.005%

Put
TokenPut
Feature activation+0.000
the
Token the
Feature activation+0.849
eggs
Token eggs
Feature activation+2.384
and
Token and
Feature activation+1.239
sugar
Token sugar
Feature activation+1.805
into
Token into
Feature activation+3.576
a
Token a
Feature activation+0.450
bowl
Token bowl
Feature activation+0.000
and
Token and
Feature activation+0.000
whisk
Token whisk
Feature activation+0.000
until
Token until
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Put
TokenPut
Feature activation+0.000
this
Token this
Feature activation+0.534
in
Token in
Feature activation+3.504
your
Token your
Feature activation+2.335
bloody
Token bloody
Feature activation+0.011
pipe
Token pipe
Feature activation+0.305
and
Token and
Feature activation+0.000
smoke
Token smoke
Feature activation+0.400
do
Token do
Feature activation+0.000
can
Token can
Feature activation+0.000
put
Token put
Feature activation+0.000
these
Token these
Feature activation+0.349
things
Token things
Feature activation+0.000
to
Token to
Feature activation+3.486
great
Token great
Feature activation+1.180
use
Token use
Feature activation+4.344
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
for
Token for
Feature activation+0.000
I
Token I
Feature activation+0.000
should
Token should
Feature activation+0.000
have
Token have
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+0.829
pressure
Token pressure
Feature activation+3.630
on
Token on
Feature activation+2.734
early
Token early
Feature activation+0.339
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
soon
Token soon
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+1.492
behind
Token behind
Feature activation+3.497
us
Token us
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Und
TokenUnd
Feature activation+0.000

INTERVAL 2.853 - 3.329
CONTAINS 0.007%

ches
Tokenches
Feature activation+0.000
and
Token and
Feature activation+0.000
put
Token put
Feature activation+0.000
her
Token her
Feature activation+0.505
food
Token food
Feature activation+2.233
into
Token into
Feature activation+3.029
them
Token them
Feature activation+0.405
so
Token so
Feature activation+0.000
she
Token she
Feature activation+0.000
can
Token can
Feature activation+0.000
feed
Token feed
Feature activation+0.000
and
Token and
Feature activation+0.000
puts
Token puts
Feature activation+0.000
you
Token you
Feature activation+0.091
to
Token to
Feature activation+1.647
the
Token the
Feature activation+1.130
test
Token test
Feature activation+2.934
in
Token in
Feature activation+0.774
a
Token a
Feature activation+0.228
wide
Token wide
Feature activation+0.000
variety
Token variety
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
Rather
Token Rather
Feature activation+0.000
than
Token than
Feature activation+0.000
put
Token put
Feature activation+0.000
money
Token money
Feature activation+0.759
into
Token into
Feature activation+2.987
a
Token a
Feature activation+1.154
low
Token low
Feature activation+0.000
yield
Token yield
Feature activation+0.307
savings
Token savings
Feature activation+0.000
account
Token account
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
put
Token put
Feature activation+0.000
private
Token private
Feature activation+0.295
property
Token property
Feature activation+0.382
into
Token into
Feature activation+2.996
question
Token question
Feature activation+2.883
,
Token,
Feature activation+0.121
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
demonstrated
Token demonstrated
Feature activation+0.000
interests
Token interests
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+0.792
scare
Token scare
Feature activation+1.450
in
Token in
Feature activation+2.983
most
Token most
Feature activation+0.175
of
Token of
Feature activation+0.267
the
Token the
Feature activation+0.983
audience
Token audience
Feature activation+0.127
.
Token.
Feature activation+0.000

INTERVAL 2.378 - 2.853
CONTAINS 0.010%

set
Token set
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.102
further
Token further
Feature activation+1.178
pressure
Token pressure
Feature activation+2.895
on
Token on
Feature activation+2.545
healthcare
Token healthcare
Feature activation+0.185
systems
Token systems
Feature activation+0.086
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
strain
Token strain
Feature activation+0.000
escalation
Token escalation
Feature activation+0.000
area
Token area
Feature activation+0.000
we
Token we
Feature activation+0.000
put
Token put
Feature activation+0.000
beds
Token beds
Feature activation+2.506
into
Token into
Feature activation+2.643
were
Token were
Feature activation+0.000
full
Token full
Feature activation+0.000
of
Token of
Feature activation+0.000
patients
Token patients
Feature activation+0.000
.
Token.
Feature activation+0.000
recent
Token recent
Feature activation+0.000
months
Token months
Feature activation+0.000
.
Token.
Feature activation+0.000
Put
Token Put
Feature activation+0.000
them
Token them
Feature activation+1.022
in
Token in
Feature activation+2.616
your
Token your
Feature activation+2.040
regular
Token regular
Feature activation+0.000
rotation
Token rotation
Feature activation+0.049
,
Token,
Feature activation+0.284
and
Token and
Feature activation+0.000
credentials
Token credentials
Feature activation+0.000
that
Token that
Feature activation+0.000
put
Token put
Feature activation+0.279
Hunts
Token Hunts
Feature activation+0.459
man
Tokenman
Feature activation+0.000
's
Token's
Feature activation+2.746
resume
Token resume
Feature activation+3.312
near
Token near
Feature activation+0.745
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
of
Token of
Feature activation+0.000
car
Tokencar
Feature activation+0.000
riage
Tokenriage
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
them
Token them
Feature activation+0.707
in
Token in
Feature activation+2.770
(
Token (
Feature activation+0.143
although
Tokenalthough
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 1.902 - 2.378
CONTAINS 0.011%

which
Token which
Feature activation+0.000
he
Token he
Feature activation+0.000
then
Token then
Feature activation+0.000
completely
Token completely
Feature activation+0.000
put
Token put
Feature activation+0.074
behind
Token behind
Feature activation+2.162
him
Token him
Feature activation+0.384
and
Token and
Feature activation+0.830
took
Token took
Feature activation+0.523
a
Token a
Feature activation+0.000
job
Token job
Feature activation+0.000
to
Token to
Feature activation+0.000
putting
Token putting
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.531
face
Token face
Feature activation+2.194
forward
Token forward
Feature activation+2.088
for
Token for
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
including
Token including
Feature activation+0.000
30
Token 30
Feature activation+0.000
-
Token-
Feature activation+0.515
40
Token40
Feature activation+0.000
million
Token million
Feature activation+1.044
Americans
Token Americans
Feature activation+0.337
in
Token in
Feature activation+2.271
uniform
Token uniform
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
treaty
Token treaty
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+0.272
check
Token check
Feature activation+2.875
on
Token on
Feature activation+1.949
the
Token the
Feature activation+0.000
rising
Token rising
Feature activation+0.000
temperature
Token temperature
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
York
Token York
Feature activation+0.000
police
Token police
Feature activation+0.000
officer
Token officer
Feature activation+0.000
put
Token put
Feature activation+0.000
him
Token him
Feature activation+1.043
in
Token in
Feature activation+2.201
a
Token a
Feature activation+1.642
choke
Token choke
Feature activation+0.494
hold
Tokenhold
Feature activation+0.427
for
Token for
Feature activation+0.000
selling
Token selling
Feature activation+0.000

INTERVAL 1.427 - 1.902
CONTAINS 0.020%

at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
concert
Token concert
Feature activation+0.000
put
Token put
Feature activation+0.000
on
Token on
Feature activation+0.802
by
Token by
Feature activation+1.567
Radio
Token Radio
Feature activation+0.000
99
Token 99
Feature activation+0.000
.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.000
Kiss
Token Kiss
Feature activation+0.000
facilities
Token facilities
Feature activation+0.000
standards
Token standards
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
put
Token put
Feature activation+0.000
on
Token on
Feature activation+1.532
hold
Token hold
Feature activation+2.462
by
Token by
Feature activation+1.579
courts
Token courts
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+1.245
uh
Token uh
Feature activation+0.000
,
Token,
Feature activation+0.216
put
Token put
Feature activation+0.000
in
Token in
Feature activation+1.212
your
Token your
Feature activation+1.557
nose
Token nose
Feature activation+0.000
?"
Token?"
Feature activation+0.000
),
Token),
Feature activation+0.000
Madonna
Token Madonna
Feature activation+0.000
laughed
Token laughed
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
put
Token put
Feature activation+0.000
context
Token context
Feature activation+2.346
to
Token to
Feature activation+2.369
it
Token it
Feature activation+1.698
and
Token and
Feature activation+0.208
turn
Token turn
Feature activation+0.000
it
Token it
Feature activation+0.000
into
Token into
Feature activation+0.000
good
Token good
Feature activation+0.000
naked
Token naked
Feature activation+0.000
statue
Token statue
Feature activation+0.626
of
Token of
Feature activation+0.705
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
in
Token in
Feature activation+1.622
Union
Token Union
Feature activation+0.000
Square
Token Square
Feature activation+0.000
.
Token .
Feature activation+0.000
The
Token The
Feature activation+0.000
political
Token political
Feature activation+0.000

INTERVAL 0.951 - 1.427
CONTAINS 0.027%

put
Token put
Feature activation+0.010
The
Token The
Feature activation+0.342
Tro
Token Tro
Feature activation+0.264
th
Tokenth
Feature activation+0.155
on
Token on
Feature activation+3.261
the
Token the
Feature activation+1.036
list
Token list
Feature activation+0.399
,
Token,
Feature activation+0.989
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+0.000
Heat
Token Heat
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
put
Token put
Feature activation+0.000
into
Token into
Feature activation+1.601
production
Token production
Feature activation+1.071
,
Token,
Feature activation+0.000
sooner
Token sooner
Feature activation+0.000
than
Token than
Feature activation+0.000
later
Token later
Feature activation+0.000
.
Token.
Feature activation+0.000
Mar
Token Mar
Feature activation+0.000
oon
Tokenoon
Feature activation+0.000
and
Token and
Feature activation+0.000
White
Token White
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+1.083
game
Token game
Feature activation+2.657
away
Token away
Feature activation+1.970
with
Token with
Feature activation+2.590
three
Token three
Feature activation+0.000
runs
Token runs
Feature activation+0.000
much
Token much
Feature activation+0.000
debate
Token debate
Feature activation+0.000
-
Token -
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
it
Token it
Feature activation+1.315
mildly
Token mildly
Feature activation+0.000
-
Token -
Feature activation+0.277
on
Token on
Feature activation+2.687
the
Token the
Feature activation+0.189
currency
Token currency
Feature activation+0.000
to
Token to
Feature activation+0.000
analyse
Token analyse
Feature activation+0.000
,
Token,
Feature activation+0.000
bluntly
Token bluntly
Feature activation+0.000
put
Token put
Feature activation+0.000
,
Token,
Feature activation+1.413
it
Token it
Feature activation+2.532
is
Token is
Feature activation+0.047
nothing
Token nothing
Feature activation+0.000
but
Token but
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.476 - 0.951
CONTAINS 0.031%

30
Token 30
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
when
Token when
Feature activation+0.000
you
Token you
Feature activation+0.000
put
Token put
Feature activation+0.000
your
Token your
Feature activation+0.631
clothes
Token clothes
Feature activation+2.163
in
Token in
Feature activation+3.000
the
Token the
Feature activation+1.153
laundry
Token laundry
Feature activation+0.016
Ċ
TokenĊ
Feature activation+0.000
t
Token t
Feature activation+0.000
ux
Tokenux
Feature activation+0.000
edo
Tokenedo
Feature activation+0.000
back
Token back
Feature activation+1.929
on
Token on
Feature activation+1.913
to
Token to
Feature activation+0.593
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+0.000
high
Token high
Feature activation+0.000
historical
Token historical
Feature activation+0.000
cleansing
Token cleansing
Feature activation+0.000
that
Token that
Feature activation+0.000
puts
Token puts
Feature activation+0.000
human
Token human
Feature activation+0.000
beings
Token beings
Feature activation+0.708
in
Token in
Feature activation+2.111
the
Token the
Feature activation+1.673
place
Token place
Feature activation+2.550
of
Token of
Feature activation+0.000
God
Token God
Feature activation+0.058
the
Token the
Feature activation+0.999
driver
Token driver
Feature activation+0.261
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
seat
Token seat
Feature activation+0.796
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
That
TokenThat
Feature activation+0.000
financial
Token financial
Feature activation+0.000
in
Token in
Feature activation+1.510
a
Token a
Feature activation+1.254
âĢ
Token âĢ
Feature activation+1.306
ľ
Tokenľ
Feature activation+0.005
very
Tokenvery
Feature activation+0.000
precarious
Token precarious
Feature activation+0.843
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
position
Token position
Feature activation+0.232
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.000 - 0.476
CONTAINS 99.888%

MB
Token MB
Feature activation+0.000
BS
TokenBS
Feature activation+0.000
admission
Token admission
Feature activation+0.000
profess
Token profess
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
P
Token P
Feature activation+0.000
IL
TokenIL
Feature activation+0.000
said
Token said
Feature activation+0.000
turn
Token turn
Feature activation+0.000
created
Token created
Feature activation+0.000
EL
Token EL
Feature activation+0.000
P
TokenP
Feature activation+0.000
Japan
Token Japan
Feature activation+0.000
for
Token for
Feature activation+0.000
continued
Token continued
Feature activation+0.000
development
Token development
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000
the
Token the
Feature activation+0.000
hands
Token hands
Feature activation+0.000
of
Token of
Feature activation+0.000
jihadists
Token jihadists
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Pentagon
Token Pentagon
Feature activation+0.000
said
Token said
Feature activation+0.000
it
Token it
Feature activation+0.000
names
Token names
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
214
Token 214
Feature activation+0.000
local
Token local
Feature activation+0.000
members
Token members
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
military
Token military
Feature activation+0.000
killed
Token killed
Feature activation+0.000
in
Token in
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
tough
Token tough
Feature activation+0.000
one
Token one
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Crawford
Token Crawford
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H2.8: (feature 662)

TOP ACTIVATIONS
MAX = 3.983

that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
turn
Token turn
Feature activation+0.000
back
Token back
Feature activation+0.493
the
Token the
Feature activation+0.512
tide
Token tide
Feature activation+3.983
.
Token.
Feature activation+0.062
Although
Token Although
Feature activation+0.000
he
Token he
Feature activation+0.000
successfully
Token successfully
Feature activation+0.000
rep
Token rep
Feature activation+0.000
reverse
Token reverse
Feature activation+0.000
course
Token course
Feature activation+0.000
and
Token and
Feature activation+0.000
turn
Token turn
Feature activation+0.239
a
Token a
Feature activation+1.281
blind
Token blind
Feature activation+3.726
eye
Token eye
Feature activation+3.417
when
Token when
Feature activation+0.847
a
Token a
Feature activation+0.548
military
Token military
Feature activation+0.000
coup
Token coup
Feature activation+0.000
The
TokenThe
Feature activation+0.000
arrests
Token arrests
Feature activation+0.000
again
Token again
Feature activation+0.000
turned
Token turned
Feature activation+0.000
scrutiny
Token scrutiny
Feature activation+0.000
toward
Token toward
Feature activation+3.723
a
Token a
Feature activation+0.622
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
un
Tokenun
Feature activation+0.000
iversity
Tokeniversity
Feature activation+0.000
nation
Token nation
Feature activation+0.000
safe
Token safe
Feature activation+0.000
and
Token and
Feature activation+0.000
turned
Token turned
Feature activation+0.000
the
Token the
Feature activation+0.354
tide
Token tide
Feature activation+3.609
of
Token of
Feature activation+0.227
war
Token war
Feature activation+0.140
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
against
Token against
Feature activation+1.119
Do
TokenDo
Feature activation+0.000
not
Token not
Feature activation+0.000
turn
Token turn
Feature activation+0.000
off
Token off
Feature activation+1.581
the
Token the
Feature activation+1.503
power
Token power
Feature activation+3.425
or
Token or
Feature activation+0.211
remove
Token remove
Feature activation+0.522
the
Token the
Feature activation+0.000
memory
Token memory
Feature activation+0.000
card
Token card
Feature activation+0.000
course
Token course
Feature activation+0.000
and
Token and
Feature activation+0.000
turn
Token turn
Feature activation+0.239
a
Token a
Feature activation+1.281
blind
Token blind
Feature activation+3.726
eye
Token eye
Feature activation+3.417
when
Token when
Feature activation+0.847
a
Token a
Feature activation+0.548
military
Token military
Feature activation+0.000
coup
Token coup
Feature activation+0.000
ousted
Token ousted
Feature activation+0.000
amara
Tokenamara
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
turned
Token turned
Feature activation+0.000
28
Token 28
Feature activation+1.606
on
Token on
Feature activation+3.303
Tuesday
Token Tuesday
Feature activation+0.000
,
Token,
Feature activation+0.900
can
Token can
Feature activation+0.044
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
media
Token media
Feature activation+0.000
is
Token is
Feature activation+0.000
completely
Token completely
Feature activation+0.000
turning
Token turning
Feature activation+0.000
a
Token a
Feature activation+0.351
blind
Token blind
Feature activation+3.299
eye
Token eye
Feature activation+3.086
to
Token to
Feature activation+0.985
what
Token what
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Rock
Token Rock
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
turned
Token turned
Feature activation+0.000
10
Token 10
Feature activation+1.536
on
Token on
Feature activation+3.243
Saturday
Token Saturday
Feature activation+0.000
,
Token,
Feature activation+0.716
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
giving
Token giving
Feature activation+0.000
I
Token I
Feature activation+0.000
turned
Token turned
Feature activation+0.000
the
Token the
Feature activation+0.668
hot
Token hot
Feature activation+1.664
water
Token water
Feature activation+0.601
on
Token on
Feature activation+3.140
in
Token in
Feature activation+0.058
the
Token the
Feature activation+0.000
bathroom
Token bathroom
Feature activation+0.000
sink
Token sink
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
turned
Token turned
Feature activation+0.000
it
Token it
Feature activation+0.710
on
Token on
Feature activation+3.107
for
Token for
Feature activation+0.000
four
Token four
Feature activation+0.000
months
Token months
Feature activation+0.000
now
Token now
Feature activation+0.164
,
Token,
Feature activation+0.000
Planning
Token Planning
Feature activation+0.000
suggests
Token suggests
Feature activation+0.000
turning
Token turning
Feature activation+0.000
the
Token the
Feature activation+0.033
area
Token area
Feature activation+0.000
around
Token around
Feature activation+3.094
the
Token the
Feature activation+0.000
rail
Token rail
Feature activation+0.000
over
Token over
Feature activation+0.658
pass
Tokenpass
Feature activation+0.000
and
Token and
Feature activation+0.000
is
Token is
Feature activation+0.000
completely
Token completely
Feature activation+0.000
turning
Token turning
Feature activation+0.000
a
Token a
Feature activation+0.351
blind
Token blind
Feature activation+3.299
eye
Token eye
Feature activation+3.086
to
Token to
Feature activation+0.985
what
Token what
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
turn
Tokenturn
Feature activation+0.000
on
Token on
Feature activation+0.907
the
Token the
Feature activation+0.413
lights
Token lights
Feature activation+3.041
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.095
and
Token and
Feature activation+0.633
so
Token so
Feature activation+0.000
on
Token on
Feature activation+0.244
win
Tokenwin
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
turned
Token turned
Feature activation+0.000
20
Token 20
Feature activation+1.628
on
Token on
Feature activation+3.033
July
Token July
Feature activation+0.397
15
Token 15
Feature activation+1.418
,
Token,
Feature activation+0.792
2014
Token 2014
Feature activation+0.983
,
Token,
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
fences
Token fences
Feature activation+0.000
we
Token we
Feature activation+0.000
turned
Token turned
Feature activation+0.000
left
Token left
Feature activation+3.032
a
Token a
Feature activation+0.184
bit
Token bit
Feature activation+0.659
and
Token and
Feature activation+1.381
took
Token took
Feature activation+0.000
off
Token off
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
light
Token light
Feature activation+0.000
turns
Token turns
Feature activation+0.000
red
Token red
Feature activation+3.021
to
Token to
Feature activation+1.456
green
Token green
Feature activation+1.680
,
Token,
Feature activation+0.065
the
Token the
Feature activation+0.249
car
Token car
Feature activation+0.000
record
Token record
Feature activation+0.000
with
Token with
Feature activation+0.000
turning
Token turning
Feature activation+0.000
some
Token some
Feature activation+0.450
guys
Token guys
Feature activation+0.076
around
Token around
Feature activation+2.916
is
Token is
Feature activation+0.000
amazing
Token amazing
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
turn
Tokenturn
Feature activation+0.000
(
Token (
Feature activation+0.000
something
Tokensomething
Feature activation+0.761
)
Token)
Feature activation+0.000
on
Token on
Feature activation+2.915
its
Token its
Feature activation+0.012
head
Token head
Feature activation+0.030
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
(
Token (
Feature activation+0.000
WD
TokenWD
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
turn
Token turn
Feature activation+0.000
it
Token it
Feature activation+1.401
off
Token off
Feature activation+2.880
,
Token,
Feature activation+0.708
be
Token be
Feature activation+0.000
cool
Token cool
Feature activation+0.000
and
Token and
Feature activation+0.000
coast
Token coast
Feature activation+0.000

Top DFA by src position
MAX = 4.434

a
Token a
Feature activation+0.052
Top resid features:
decisive
Token decisive
Feature activation-0.007
Top resid features:
stand
Token stand
Feature activation+0.030
Top resid features:
that
Token that
Feature activation+0.105
Top resid features:
would
Token would
Feature activation+0.015
Top resid features:
turn
Token turn
Feature activation+4.434
Top resid features:
back
Token back
Feature activation+0.298
Top resid features:
the
Token the
Feature activation+0.410
Top resid features:
tide
Token tide
Feature activation+0.141
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Although
Token Although
Feature activation+0.000
Top resid features:
only
Token only
Feature activation+0.030
Top resid features:
to
Token to
Feature activation+0.094
Top resid features:
reverse
Token reverse
Feature activation+0.067
Top resid features:
course
Token course
Feature activation+0.075
Top resid features:
and
Token and
Feature activation+0.087
Top resid features:
turn
Token turn
Feature activation+4.245
Top resid features:
a
Token a
Feature activation+0.328
Top resid features:
blind
Token blind
Feature activation+0.121
Top resid features:
eye
Token eye
Feature activation+0.000
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
The
TokenThe
Feature activation+0.036
Top resid features:
arrests
Token arrests
Feature activation+0.003
Top resid features:
again
Token again
Feature activation-0.015
Top resid features:
turned
Token turned
Feature activation+4.033
Top resid features:
scrutiny
Token scrutiny
Feature activation+0.886
Top resid features:
toward
Token toward
Feature activation+0.185
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
pre
Token pre
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
kept
Token kept
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.048
Top resid features:
nation
Token nation
Feature activation-0.039
Top resid features:
safe
Token safe
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.058
Top resid features:
turned
Token turned
Feature activation+4.357
Top resid features:
the
Token the
Feature activation+0.376
Top resid features:
tide
Token tide
Feature activation+0.139
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
war
Token war
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Do
TokenDo
Feature activation+0.096
Top resid features:
not
Token not
Feature activation+0.032
Top resid features:
turn
Token turn
Feature activation+3.954
Top resid features:
off
Token off
Feature activation+0.325
Top resid features:
the
Token the
Feature activation+0.351
Top resid features:
power
Token power
Feature activation+0.039
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
remove
Token remove
Feature activation+0.000
Top resid features:
only
Token only
Feature activation+0.036
Top resid features:
to
Token to
Feature activation+0.059
Top resid features:
reverse
Token reverse
Feature activation+0.077
Top resid features:
course
Token course
Feature activation+0.065
Top resid features:
and
Token and
Feature activation+0.026
Top resid features:
turn
Token turn
Feature activation+3.858
Top resid features:
a
Token a
Feature activation+0.325
Top resid features:
blind
Token blind
Feature activation+0.296
Top resid features:
eye
Token eye
Feature activation+0.043
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
Am
Token Am
Feature activation+0.012
Top resid features:
uk
Tokenuk
Feature activation+0.001
Top resid features:
amara
Tokenamara
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.086
Top resid features:
who
Token who
Feature activation+0.142
Top resid features:
turned
Token turned
Feature activation+3.901
Top resid features:
28
Token 28
Feature activation+0.372
Top resid features:
on
Token on
Feature activation+0.256
Top resid features:
Tuesday
Token Tuesday
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
how
Token how
Feature activation+0.038
Top resid features:
the
Token the
Feature activation+0.057
Top resid features:
media
Token media
Feature activation-0.095
Top resid features:
is
Token is
Feature activation-0.014
Top resid features:
completely
Token completely
Feature activation+0.025
Top resid features:
turning
Token turning
Feature activation+4.047
Top resid features:
a
Token a
Feature activation+0.519
Top resid features:
blind
Token blind
Feature activation+0.117
Top resid features:
eye
Token eye
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
Sam
Token Sam
Feature activation-0.008
Top resid features:
i
Tokeni
Feature activation+0.003
Top resid features:
Rock
Token Rock
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.030
Top resid features:
who
Token who
Feature activation+0.061
Top resid features:
turned
Token turned
Feature activation+3.846
Top resid features:
10
Token 10
Feature activation+0.478
Top resid features:
on
Token on
Feature activation+0.261
Top resid features:
Saturday
Token Saturday
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
The
TokenThe
Feature activation+0.014
Top resid features:
next
Token next
Feature activation+0.019
Top resid features:
morning
Token morning
Feature activation+0.018
Top resid features:
I
Token I
Feature activation+0.049
Top resid features:
turned
Token turned
Feature activation+3.488
Top resid features:
the
Token the
Feature activation+0.302
Top resid features:
hot
Token hot
Feature activation+0.261
Top resid features:
water
Token water
Feature activation+0.150
Top resid features:
on
Token on
Feature activation+0.286
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
literally
Token literally
Feature activation-0.004
Top resid features:
haven
Token haven
Feature activation+0.025
Top resid features:
âĢ
TokenâĢ
Feature activation+0.077
Top resid features:
Ļ
TokenĻ
Feature activation+0.045
Top resid features:
t
Tokent
Feature activation+0.024
Top resid features:
turned
Token turned
Feature activation+3.828
Top resid features:
it
Token it
Feature activation+0.305
Top resid features:
on
Token on
Feature activation+0.310
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
four
Token four
Feature activation+0.000
Top resid features:
months
Token months
Feature activation+0.000
Top resid features:
DC
Token DC
Feature activation+0.010
Top resid features:
Office
Token Office
Feature activation+0.023
Top resid features:
of
Token of
Feature activation+0.047
Top resid features:
Planning
Token Planning
Feature activation+0.029
Top resid features:
suggests
Token suggests
Feature activation-0.045
Top resid features:
turning
Token turning
Feature activation+3.736
Top resid features:
the
Token the
Feature activation+0.373
Top resid features:
area
Token area
Feature activation+0.155
Top resid features:
around
Token around
Feature activation+0.208
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
rail
Token rail
Feature activation+0.000
Top resid features:
how
Token how
Feature activation+0.033
Top resid features:
the
Token the
Feature activation+0.051
Top resid features:
media
Token media
Feature activation-0.041
Top resid features:
is
Token is
Feature activation-0.012
Top resid features:
completely
Token completely
Feature activation-0.005
Top resid features:
turning
Token turning
Feature activation+3.800
Top resid features:
a
Token a
Feature activation+0.440
Top resid features:
blind
Token blind
Feature activation+0.214
Top resid features:
eye
Token eye
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.020
Top resid features:
Ŀ
TokenĿ
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
âĢ
Token âĢ
Feature activation+0.039
Top resid features:
ľ
Tokenľ
Feature activation+0.018
Top resid features:
turn
Tokenturn
Feature activation+3.898
Top resid features:
on
Token on
Feature activation+0.229
Top resid features:
the
Token the
Feature activation+0.197
Top resid features:
lights
Token lights
Feature activation-0.027
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
in
Tokenin
Feature activation-0.013
Top resid features:
Cor
Token Cor
Feature activation-0.014
Top resid features:
win
Tokenwin
Feature activation-0.028
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
who
Token who
Feature activation+0.057
Top resid features:
turned
Token turned
Feature activation+3.687
Top resid features:
20
Token 20
Feature activation+0.460
Top resid features:
on
Token on
Feature activation+0.275
Top resid features:
July
Token July
Feature activation+0.000
Top resid features:
15
Token 15
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.023
Top resid features:
through
Token through
Feature activation+0.155
Top resid features:
the
Token the
Feature activation+0.184
Top resid features:
fences
Token fences
Feature activation+0.045
Top resid features:
we
Token we
Feature activation+0.121
Top resid features:
turned
Token turned
Feature activation+3.742
Top resid features:
left
Token left
Feature activation+0.128
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
bit
Token bit
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
took
Token took
Feature activation+0.000
Top resid features:
stop
Token stop
Feature activation+0.057
Top resid features:
,
Token,
Feature activation+0.039
Top resid features:
when
Token when
Feature activation+0.081
Top resid features:
the
Token the
Feature activation+0.242
Top resid features:
light
Token light
Feature activation-0.010
Top resid features:
turns
Token turns
Feature activation+3.690
Top resid features:
red
Token red
Feature activation+0.221
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
green
Token green
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:
.
Token.
Feature activation+0.008
Top resid features:
His
Token His
Feature activation-0.002
Top resid features:
track
Token track
Feature activation-0.006
Top resid features:
record
Token record
Feature activation-0.017
Top resid features:
with
Token with
Feature activation+0.089
Top resid features:
turning
Token turning
Feature activation+3.577
Top resid features:
some
Token some
Feature activation+0.402
Top resid features:
guys
Token guys
Feature activation+0.048
Top resid features:
around
Token around
Feature activation+0.184
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
amazing
Token amazing
Feature activation+0.000
Top resid features:
mash
Token mash
Feature activation-0.009
Top resid features:
up
Tokenup
Feature activation-0.017
Top resid features:
of
Token of
Feature activation+0.062
Top resid features:
âĢ
Token âĢ
Feature activation+0.011
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
turn
Tokenturn
Feature activation+3.507
Top resid features:
(
Token (
Feature activation+0.166
Top resid features:
something
Tokensomething
Feature activation+0.344
Top resid features:
)
Token)
Feature activation+0.047
Top resid features:
on
Token on
Feature activation+0.170
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.075
Top resid features:
M
Token M
Feature activation+0.012
Top resid features:
WD
TokenWD
Feature activation+0.013
Top resid features:
and
Token and
Feature activation+0.043
Top resid features:
they
Token they
Feature activation+0.067
Top resid features:
turn
Token turn
Feature activation+3.485
Top resid features:
it
Token it
Feature activation+0.207
Top resid features:
off
Token off
Feature activation+0.308
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
cool
Token cool
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.03

Head 2: 0.04

Head 3: 0.06

Head 4: 0.04

Head 5: 0.07

Head 6: 0.03

Head 7: 0.03

Head 8: 0.53

Head 9: 0.07

Head 10: 0.04

Head 11: 0.03

Positive logits

Vit1.52

zona1.52

ヘラ1.40

TAMADRA1.38

atonin1.38

ragon1.35

stals1.33

psc1.31

Millennium1.29

   1.29

TABLE1.28

ы1.26

knob1.26

1.26

rift1.26

headlights1.25

washer1.25

wagen1.25

Izan1.23

flame1.23

Negative logits

ask-1.69

arching-1.61

interstitial-1.46

cling-1.35

onnaissance-1.33

asking-1.32

ierce-1.29

essions-1.27

stood-1.24

upkeep-1.23

erved-1.22

ently-1.21

ayers-1.20

dared-1.20

querque-1.19

IGN-1.19

ptions-1.18

volunte-1.18

semb-1.16

earch-1.16

INTERVAL 3.585 - 3.983
CONTAINS 0.000%

reverse
Token reverse
Feature activation+0.000
course
Token course
Feature activation+0.000
and
Token and
Feature activation+0.000
turn
Token turn
Feature activation+0.239
a
Token a
Feature activation+1.281
blind
Token blind
Feature activation+3.726
eye
Token eye
Feature activation+3.417
when
Token when
Feature activation+0.847
a
Token a
Feature activation+0.548
military
Token military
Feature activation+0.000
coup
Token coup
Feature activation+0.000
nation
Token nation
Feature activation+0.000
safe
Token safe
Feature activation+0.000
and
Token and
Feature activation+0.000
turned
Token turned
Feature activation+0.000
the
Token the
Feature activation+0.354
tide
Token tide
Feature activation+3.609
of
Token of
Feature activation+0.227
war
Token war
Feature activation+0.140
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
against
Token against
Feature activation+1.119
The
TokenThe
Feature activation+0.000
arrests
Token arrests
Feature activation+0.000
again
Token again
Feature activation+0.000
turned
Token turned
Feature activation+0.000
scrutiny
Token scrutiny
Feature activation+0.000
toward
Token toward
Feature activation+3.723
a
Token a
Feature activation+0.622
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
un
Tokenun
Feature activation+0.000
iversity
Tokeniversity
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
turn
Token turn
Feature activation+0.000
back
Token back
Feature activation+0.493
the
Token the
Feature activation+0.512
tide
Token tide
Feature activation+3.983
.
Token.
Feature activation+0.062
Although
Token Although
Feature activation+0.000
he
Token he
Feature activation+0.000
successfully
Token successfully
Feature activation+0.000
rep
Token rep
Feature activation+0.000

INTERVAL 3.186 - 3.585
CONTAINS 0.001%

course
Token course
Feature activation+0.000
and
Token and
Feature activation+0.000
turn
Token turn
Feature activation+0.239
a
Token a
Feature activation+1.281
blind
Token blind
Feature activation+3.726
eye
Token eye
Feature activation+3.417
when
Token when
Feature activation+0.847
a
Token a
Feature activation+0.548
military
Token military
Feature activation+0.000
coup
Token coup
Feature activation+0.000
ousted
Token ousted
Feature activation+0.000
amara
Tokenamara
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
turned
Token turned
Feature activation+0.000
28
Token 28
Feature activation+1.606
on
Token on
Feature activation+3.303
Tuesday
Token Tuesday
Feature activation+0.000
,
Token,
Feature activation+0.900
can
Token can
Feature activation+0.044
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
media
Token media
Feature activation+0.000
is
Token is
Feature activation+0.000
completely
Token completely
Feature activation+0.000
turning
Token turning
Feature activation+0.000
a
Token a
Feature activation+0.351
blind
Token blind
Feature activation+3.299
eye
Token eye
Feature activation+3.086
to
Token to
Feature activation+0.985
what
Token what
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Rock
Token Rock
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
turned
Token turned
Feature activation+0.000
10
Token 10
Feature activation+1.536
on
Token on
Feature activation+3.243
Saturday
Token Saturday
Feature activation+0.000
,
Token,
Feature activation+0.716
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
giving
Token giving
Feature activation+0.000
Do
TokenDo
Feature activation+0.000
not
Token not
Feature activation+0.000
turn
Token turn
Feature activation+0.000
off
Token off
Feature activation+1.581
the
Token the
Feature activation+1.503
power
Token power
Feature activation+3.425
or
Token or
Feature activation+0.211
remove
Token remove
Feature activation+0.522
the
Token the
Feature activation+0.000
memory
Token memory
Feature activation+0.000
card
Token card
Feature activation+0.000

INTERVAL 2.788 - 3.186
CONTAINS 0.001%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
turned
Token turned
Feature activation+0.000
it
Token it
Feature activation+0.710
on
Token on
Feature activation+3.107
for
Token for
Feature activation+0.000
four
Token four
Feature activation+0.000
months
Token months
Feature activation+0.000
now
Token now
Feature activation+0.164
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
light
Token light
Feature activation+0.000
turns
Token turns
Feature activation+0.000
red
Token red
Feature activation+3.021
to
Token to
Feature activation+1.456
green
Token green
Feature activation+1.680
,
Token,
Feature activation+0.065
the
Token the
Feature activation+0.249
car
Token car
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
turn
Tokenturn
Feature activation+0.000
(
Token (
Feature activation+0.000
something
Tokensomething
Feature activation+0.761
)
Token)
Feature activation+0.000
on
Token on
Feature activation+2.915
its
Token its
Feature activation+0.012
head
Token head
Feature activation+0.030
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
(
Token (
Feature activation+0.000
win
Tokenwin
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
turned
Token turned
Feature activation+0.000
20
Token 20
Feature activation+1.628
on
Token on
Feature activation+3.033
July
Token July
Feature activation+0.397
15
Token 15
Feature activation+1.418
,
Token,
Feature activation+0.792
2014
Token 2014
Feature activation+0.983
,
Token,
Feature activation+0.000
Planning
Token Planning
Feature activation+0.000
suggests
Token suggests
Feature activation+0.000
turning
Token turning
Feature activation+0.000
the
Token the
Feature activation+0.033
area
Token area
Feature activation+0.000
around
Token around
Feature activation+3.094
the
Token the
Feature activation+0.000
rail
Token rail
Feature activation+0.000
over
Token over
Feature activation+0.658
pass
Tokenpass
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 2.390 - 2.788
CONTAINS 0.002%

ĺ
Tokenĺ
Feature activation+0.000
Turn
TokenTurn
Feature activation+0.000
ing
Tokening
Feature activation+0.000
back
Token back
Feature activation+0.170
the
Token the
Feature activation+0.313
clock
Token clock
Feature activation+2.635
âĢ
TokenâĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.514
and
Token and
Feature activation+0.393
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
sky
Token sky
Feature activation+0.000
turned
Token turned
Feature activation+0.000
dark
Token dark
Feature activation+1.379
blue
Token blue
Feature activation+2.533
and
Token and
Feature activation+2.011
later
Token later
Feature activation+0.114
into
Token into
Feature activation+0.080
purple
Token purple
Feature activation+0.089
.
Token.
Feature activation+0.000
victory
Token victory
Feature activation+0.000
,
Token,
Feature activation+0.000
turned
Token turned
Feature activation+0.000
her
Token her
Feature activation+0.000
attention
Token attention
Feature activation+2.351
to
Token to
Feature activation+2.490
down
Token down
Feature activation+0.243
-
Token-
Feature activation+0.000
ticket
Tokenticket
Feature activation+0.000
races
Token races
Feature activation+0.000
,
Token,
Feature activation+0.000
drivers
Token drivers
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
light
Token light
Feature activation+0.000
turns
Token turns
Feature activation+0.000
green
Token green
Feature activation+2.404
,
Token,
Feature activation+1.233
giving
Token giving
Feature activation+0.000
walk
Token walk
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
greater
Token greater
Feature activation+0.000
does
Token does
Feature activation+0.000
well
Token well
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
turn
Token turn
Feature activation+0.000
muscular
Token muscular
Feature activation+2.410
,
Token,
Feature activation+1.640
brain
Token brain
Feature activation+0.473
y
Tokeny
Feature activation+0.000
r
Token r
Feature activation+0.556
iffs
Tokeniffs
Feature activation+0.000

INTERVAL 1.991 - 2.390
CONTAINS 0.002%

presidential
Token presidential
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
turned
Token turned
Feature activation+0.000
a
Token a
Feature activation+0.536
spotlight
Token spotlight
Feature activation+2.028
on
Token on
Feature activation+2.337
this
Token this
Feature activation+0.000
viral
Token viral
Feature activation+0.000
disinformation
Token disinformation
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
might
Token might
Feature activation+0.000
try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
New
Token New
Feature activation+2.212
York
Token York
Feature activation+0.000
into
Token into
Feature activation+0.000
an
Token an
Feature activation+0.498
Israel
Token Israel
Feature activation+0.000
referendum
Token referendum
Feature activation+0.000
phone
Token phone
Feature activation+0.000
without
Token without
Feature activation+0.000
turning
Token turning
Feature activation+0.000
the
Token the
Feature activation+0.091
device
Token device
Feature activation+0.000
off
Token off
Feature activation+2.144
,
Token,
Feature activation+0.381
notes
Token notes
Feature activation+0.000
the
Token the
Feature activation+0.000
Phone
Token Phone
Feature activation+0.000
bl
Tokenbl
Feature activation+0.000
of
Token of
Feature activation+0.000
victory
Token victory
Feature activation+0.000
,
Token,
Feature activation+0.000
turned
Token turned
Feature activation+0.000
her
Token her
Feature activation+0.000
attention
Token attention
Feature activation+2.351
to
Token to
Feature activation+2.490
down
Token down
Feature activation+0.243
-
Token-
Feature activation+0.000
ticket
Tokenticket
Feature activation+0.000
races
Token races
Feature activation+0.000
,
Token,
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
turned
Token turned
Feature activation+0.000
a
Token a
Feature activation+0.973
similar
Token similar
Feature activation+0.000
trick
Token trick
Feature activation+2.007
when
Token when
Feature activation+1.134
he
Token he
Feature activation+0.142
cited
Token cited
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
President
Token President
Feature activation+0.000

INTERVAL 1.593 - 1.991
CONTAINS 0.003%

is
Token is
Feature activation+0.000
looking
Token looking
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
your
Token your
Feature activation+0.112
Twitter
Token Twitter
Feature activation+1.829
frown
Token frown
Feature activation+0.721
s
Tokens
Feature activation+0.000
upside
Token upside
Feature activation+0.185
down
Token down
Feature activation+0.085
.
Token.
Feature activation+0.000
into
Token into
Feature activation+0.679
a
Token a
Feature activation+0.612
full
Token full
Feature activation+0.000
month
Token month
Feature activation+0.000
celebration
Token celebration
Feature activation+0.000
around
Token around
Feature activation+1.620
here
Token here
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
doctor
Token doctor
Feature activation+0.000
turned
Token turned
Feature activation+0.000
congressman
Token congressman
Feature activation+0.000
and
Token and
Feature activation+1.813
currently
Token currently
Feature activation+0.348
the
Token the
Feature activation+0.000
chairman
Token chairman
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
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
circles
Token circles
Feature activation+0.000
turned
Token turned
Feature activation+0.000
red
Token red
Feature activation+1.962
âĢĶ
TokenâĢĶ
Feature activation+0.447
they
Tokenthey
Feature activation+0.498
should
Token should
Feature activation+0.000
have
Token have
Feature activation+0.000
chosen
Token chosen
Feature activation+0.000
is
Token is
Feature activation+0.000
gone
Token gone
Feature activation+0.000
I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000
turn
Token turn
Feature activation+0.000
and
Token and
Feature activation+1.825
face
Token face
Feature activation+1.734
fear
Token fear
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 1.195 - 1.593
CONTAINS 0.006%

with
Token with
Feature activation+0.000
not
Token not
Feature activation+0.000
turning
Token turning
Feature activation+0.000
over
Token over
Feature activation+0.315
his
Token his
Feature activation+0.521
tax
Token tax
Feature activation+1.233
returns
Token returns
Feature activation+0.850
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
press
Token press
Feature activation+0.000
seems
Token seems
Feature activation+0.000
flight
Token flight
Feature activation+0.000
.
Token.
Feature activation+0.000
Turning
Token Turning
Feature activation+0.000
off
Token off
Feature activation+0.417
the
Token the
Feature activation+0.600
engine
Token engine
Feature activation+1.476
roughly
Token roughly
Feature activation+0.289
five
Token five
Feature activation+0.000
seconds
Token seconds
Feature activation+0.000
early
Token early
Feature activation+0.000
would
Token would
Feature activation+0.000
who
Token who
Feature activation+0.000
turned
Token turned
Feature activation+0.000
20
Token 20
Feature activation+1.628
on
Token on
Feature activation+3.033
July
Token July
Feature activation+0.397
15
Token 15
Feature activation+1.418
,
Token,
Feature activation+0.792
2014
Token 2014
Feature activation+0.983
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
eighty
Token eighty
Feature activation+0.000
refugees
Token refugees
Feature activation+0.000
turned
Token turned
Feature activation+0.000
out
Token out
Feature activation+0.335
for
Token for
Feature activation+0.000
eye
Token eye
Feature activation+1.591
exams
Token exams
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
him
Token him
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
turns
Token turns
Feature activation+0.000
his
Token his
Feature activation+1.186
head
Token head
Feature activation+1.546
to
Token to
Feature activation+1.673
locate
Token locate
Feature activation+0.000
the
Token the
Feature activation+0.000
ball
Token ball
Feature activation+0.000
while
Token while
Feature activation+0.000

INTERVAL 0.797 - 1.195
CONTAINS 0.010%

his
Token his
Feature activation+0.000
prog
Token prog
Feature activation+0.000
nosis
Tokennosis
Feature activation+0.000
has
Token has
Feature activation+0.000
turned
Token turned
Feature activation+0.000
grim
Token grim
Feature activation+1.148
.
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
,
Token,
Feature activation+0.092
while
Token while
Feature activation+0.000
turning
Token turning
Feature activation+0.064
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.415
activity
Token activity
Feature activation+0.857
could
Token could
Feature activation+0.569
help
Token help
Feature activation+0.000
fight
Token fight
Feature activation+0.000
infections
Token infections
Feature activation+0.000
or
Token or
Feature activation+0.000
Asia
Token Asia
Feature activation+0.000
tour
Token tour
Feature activation+0.000
,
Token,
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
turned
Token turned
Feature activation+0.000
a
Token a
Feature activation+0.973
similar
Token similar
Feature activation+0.000
trick
Token trick
Feature activation+2.007
when
Token when
Feature activation+1.134
he
Token he
Feature activation+0.142
cited
Token cited
Feature activation+0.000
done
Token done
Feature activation+0.000
an
Token an
Feature activation+0.000
about
Token about
Feature activation+0.000
-
Token-
Feature activation+0.000
turn
Tokenturn
Feature activation+0.000
on
Token on
Feature activation+1.115
bulk
Token bulk
Feature activation+0.000
orders
Token orders
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
facing
Token facing
Feature activation+0.000
turned
Token turned
Feature activation+0.000
down
Token down
Feature activation+0.000
a
Token a
Feature activation+1.018
call
Token call
Feature activation+0.290
up
Tokenup
Feature activation+0.000
from
Token from
Feature activation+0.924
the
Token the
Feature activation+0.000
Alger
Token Alger
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
national
Token national
Feature activation+0.000
team
Token team
Feature activation+0.000

INTERVAL 0.398 - 0.797
CONTAINS 0.020%

,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
turn
Tokenturn
Feature activation+0.000
on
Token on
Feature activation+0.907
the
Token the
Feature activation+0.413
lights
Token lights
Feature activation+3.041
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.095
and
Token and
Feature activation+0.633
so
Token so
Feature activation+0.000
ing
Tokening
Feature activation+0.000
back
Token back
Feature activation+0.170
the
Token the
Feature activation+0.313
clock
Token clock
Feature activation+2.635
âĢ
TokenâĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.514
and
Token and
Feature activation+0.393
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
vent
Tokenvent
Feature activation+0.000
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.547
fiery
Token fiery
Feature activation+1.042
mess
Token mess
Feature activation+0.108
of
Token of
Feature activation+0.000
bone
Token bone
Feature activation+0.563
,
Token,
Feature activation+0.000
cart
Token cart
Feature activation+0.000
ilage
Tokenilage
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
turns
Token turns
Feature activation+0.000
out
Token out
Feature activation+0.164
Victoria
Token Victoria
Feature activation+0.000
has
Token has
Feature activation+0.655
some
Token some
Feature activation+0.000
key
Token key
Feature activation+0.515
information
Token information
Feature activation+0.000
regarding
Token regarding
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
systems
Token systems
Feature activation+0.000
turning
Token turning
Feature activation+0.046
up
Token up
Feature activation+0.272
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.146
violence
Token violence
Feature activation+0.498
-
Token-
Feature activation+0.000
pl
Tokenpl
Feature activation+0.000
ag
Tokenag
Feature activation+0.000
ued
Tokenued
Feature activation+0.000
African
Token African
Feature activation+0.000

INTERVAL 0.000 - 0.398
CONTAINS 99.955%

a
Token a
Feature activation+0.000
Title
Token Title
Feature activation+0.000
IX
Token IX
Feature activation+0.000
requirement
Token requirement
Feature activation+0.000
that
Token that
Feature activation+0.000
schools
Token schools
Feature activation+0.000
administer
Token administer
Feature activation+0.000
all
Token all
Feature activation+0.000
programs
Token programs
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
had
Token had
Feature activation+0.000
arrived
Token arrived
Feature activation+0.000
in
Token in
Feature activation+0.000
Liverpool
Token Liverpool
Feature activation+0.000
early
Token early
Feature activation+0.000
in
Token in
Feature activation+0.000
November
Token November
Feature activation+0.000
18
Token 18
Feature activation+0.000
38
Token38
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
the
Token the
Feature activation+0.000
East
Token East
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+0.000
fast
Tokenfast
Feature activation+0.000
expansion
Token expansion
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
treats
Token treats
Feature activation+0.000
Syrians
Token Syrians
Feature activation+0.000
injured
Token injured
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
civil
Token civil
Feature activation+0.000
war
Token war
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
shut
Token shut
Feature activation+0.000
down
Token down
Feature activation+0.000
on
Token on
Feature activation+0.000
22
Token 22
Feature activation+0.000
nd
Tokennd
Feature activation+0.000
October
Token October
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
.
Token.
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 2 in H2.8: (feature 23367)

TOP ACTIVATIONS
MAX = 3.377

wouldn
Token wouldn
Feature activation+0.000
't
Token't
Feature activation+0.000
bring
Token bring
Feature activation+0.000
good
Token good
Feature activation+0.565
publicity
Token publicity
Feature activation+0.976
to
Token to
Feature activation+3.377
a
Token a
Feature activation+0.620
company
Token company
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
attackers
Token attackers
Feature activation+0.000
Nothing
TokenNothing
Feature activation+0.000
will
Token will
Feature activation+0.000
bring
Token bring
Feature activation+0.000
a
Token a
Feature activation+0.743
smile
Token smile
Feature activation+1.740
to
Token to
Feature activation+3.180
your
Token your
Feature activation+0.180
face
Token face
Feature activation+1.129
faster
Token faster
Feature activation+0.118
this
Token this
Feature activation+0.000
holiday
Token holiday
Feature activation+0.000
would
Token would
Feature activation+0.000
bring
Token bring
Feature activation+0.000
valuable
Token valuable
Feature activation+0.154
business
Token business
Feature activation+0.035
experience
Token experience
Feature activation+1.392
to
Token to
Feature activation+3.158
the
Token the
Feature activation+0.053
Oval
Token Oval
Feature activation+0.000
Office
Token Office
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
this
Token this
Feature activation+0.000
matter
Token matter
Feature activation+0.573
to
Token to
Feature activation+1.621
a
Token a
Feature activation+0.802
close
Token close
Feature activation+2.954
soon
Token soon
Feature activation+0.466
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
her
Token her
Feature activation+0.192
whole
Token whole
Feature activation+0.833
family
Token family
Feature activation+0.969
to
Token to
Feature activation+2.909
space
Token space
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
role
Token role
Feature activation+0.000
was
Token was
Feature activation+0.000
bring
Token bring
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.797
of
Token of
Feature activation+0.886
Broadway
Token Broadway
Feature activation+0.000
to
Token to
Feature activation+2.902
audiences
Token audiences
Feature activation+0.221
who
Token who
Feature activation+0.202
otherwise
Token otherwise
Feature activation+0.000
wouldn
Token wouldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
health
Token health
Feature activation+0.540
concerns
Token concerns
Feature activation+1.346
to
Token to
Feature activation+2.664
the
Token the
Feature activation+0.103
attention
Token attention
Feature activation+2.869
of
Token of
Feature activation+0.000
administrators
Token administrators
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
bring
Token bring
Feature activation+0.000
cancer
Token cancer
Feature activation+0.000
-
Token-
Feature activation+0.701
fighting
Tokenfighting
Feature activation+0.595
molecules
Token molecules
Feature activation+1.224
to
Token to
Feature activation+2.855
the
Token the
Feature activation+0.000
affected
Token affected
Feature activation+0.000
area
Token area
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
years
Token years
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
bike
Token bike
Feature activation+0.000
lanes
Token lanes
Feature activation+0.014
to
Token to
Feature activation+2.846
Browns
Token Browns
Feature activation+0.630
ville
Tokenville
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Sarah
TokenSarah
Feature activation+0.000
effort
Token effort
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
it
Token it
Feature activation+0.109
all
Token all
Feature activation+1.608
to
Token to
Feature activation+2.839
life
Token life
Feature activation+2.659
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Let
TokenLet
Feature activation+0.000
ains
Tokenains
Feature activation+0.000
bring
Token bring
Feature activation+0.000
people
Token people
Feature activation+0.623
and
Token and
Feature activation+1.104
goods
Token goods
Feature activation+2.029
to
Token to
Feature activation+2.811
and
Token and
Feature activation+0.000
from
Token from
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
cities
Token cities
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
not
Token not
Feature activation+0.000
bring
Token bring
Feature activation+0.000
every
Token every
Feature activation+0.000
offender
Token offender
Feature activation+0.000
to
Token to
Feature activation+2.787
justice
Token justice
Feature activation+0.151
,
Token,
Feature activation+0.000
even
Token even
Feature activation+0.000
though
Token though
Feature activation+0.000
the
Token the
Feature activation+0.000
in
Token in
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
Captain
Token Captain
Feature activation+0.000
Britain
Token Britain
Feature activation+0.874
to
Token to
Feature activation+2.038
life
Token life
Feature activation+2.775
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
producer
Token producer
Feature activation+0.000
said
Token said
Feature activation+0.000
lots
Token lots
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
will
Tokenwill
Feature activation+0.000
bring
Token bring
Feature activation+0.000
huge
Token huge
Feature activation+0.308
talent
Token talent
Feature activation+0.766
to
Token to
Feature activation+2.743
a
Token a
Feature activation+1.151
vital
Token vital
Feature activation+0.000
national
Token national
Feature activation+0.000
effort
Token effort
Feature activation+0.329
.
Token.
Feature activation+0.000
an
Token an
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
peace
Token peace
Feature activation+1.066
to
Token to
Feature activation+2.708
the
Token the
Feature activation+0.167
world
Token world
Feature activation+0.488
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
will
Token will
Feature activation+0.000
bring
Token bring
Feature activation+0.000
many
Token many
Feature activation+0.786
new
Token new
Feature activation+1.191
aspects
Token aspects
Feature activation+0.986
to
Token to
Feature activation+2.687
the
Token the
Feature activation+0.064
game
Token game
Feature activation+0.000
:
Token:
Feature activation+0.000
Cooperative
Token Cooperative
Feature activation+0.000
building
Token building
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
downloadable
Token downloadable
Feature activation+0.000
content
Token content
Feature activation+0.000
packs
Token packs
Feature activation+1.044
to
Token to
Feature activation+2.668
Minecraft
Token Minecraft
Feature activation+0.000
for
Token for
Feature activation+0.091
Xbox
Token Xbox
Feature activation+0.000
,
Token,
Feature activation+0.000
featuring
Token featuring
Feature activation+0.000
school
Token school
Feature activation+0.000
after
Token after
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
health
Token health
Feature activation+0.540
concerns
Token concerns
Feature activation+1.346
to
Token to
Feature activation+2.664
the
Token the
Feature activation+0.103
attention
Token attention
Feature activation+2.869
of
Token of
Feature activation+0.000
administrators
Token administrators
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
it
Token it
Feature activation+0.109
all
Token all
Feature activation+1.608
to
Token to
Feature activation+2.839
life
Token life
Feature activation+2.659
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Let
TokenLet
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
bring
Token bring
Feature activation+0.000
some
Token some
Feature activation+0.689
stability
Token stability
Feature activation+1.205
to
Token to
Feature activation+2.628
the
Token the
Feature activation+0.199
states
Token states
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000

Top DFA by src position
MAX = 4.040

most
Token most
Feature activation+0.001
Top resid features:
countries
Token countries
Feature activation+0.037
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
wouldn
Token wouldn
Feature activation+0.003
Top resid features:
't
Token't
Feature activation+0.024
Top resid features:
bring
Token bring
Feature activation+4.040
Top resid features:
good
Token good
Feature activation+0.341
Top resid features:
publicity
Token publicity
Feature activation+0.531
Top resid features:
to
Token to
Feature activation+0.218
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
company
Token company
Feature activation+0.000
Top resid features:
party
Token party
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.104
Top resid features:
Nothing
TokenNothing
Feature activation+0.022
Top resid features:
will
Token will
Feature activation+0.007
Top resid features:
bring
Token bring
Feature activation+3.828
Top resid features:
a
Token a
Feature activation+0.143
Top resid features:
smile
Token smile
Feature activation+0.574
Top resid features:
to
Token to
Feature activation+0.226
Top resid features:
your
Token your
Feature activation+0.000
Top resid features:
face
Token face
Feature activation+0.000
Top resid features:
man
Token man
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
he
Token he
Feature activation+0.027
Top resid features:
would
Token would
Feature activation-0.017
Top resid features:
bring
Token bring
Feature activation+3.673
Top resid features:
valuable
Token valuable
Feature activation+0.134
Top resid features:
business
Token business
Feature activation+0.203
Top resid features:
experience
Token experience
Feature activation+0.666
Top resid features:
to
Token to
Feature activation+0.190
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.002
Top resid features:
FTA
Token FTA
Feature activation+0.007
Top resid features:
looks
Token looks
Feature activation+0.014
Top resid features:
forward
Token forward
Feature activation+0.025
Top resid features:
to
Token to
Feature activation+0.028
Top resid features:
bringing
Token bringing
Feature activation+3.866
Top resid features:
this
Token this
Feature activation+0.030
Top resid features:
matter
Token matter
Feature activation+0.234
Top resid features:
to
Token to
Feature activation+0.200
Top resid features:
a
Token a
Feature activation+0.155
Top resid features:
close
Token close
Feature activation+0.163
Top resid features:
who
Token who
Feature activation+0.009
Top resid features:
makes
Token makes
Feature activation+0.024
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
decision
Token decision
Feature activation+0.036
Top resid features:
to
Token to
Feature activation+0.035
Top resid features:
bring
Token bring
Feature activation+3.705
Top resid features:
her
Token her
Feature activation+0.090
Top resid features:
whole
Token whole
Feature activation+0.221
Top resid features:
family
Token family
Feature activation+0.288
Top resid features:
to
Token to
Feature activation+0.273
Top resid features:
space
Token space
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.031
Top resid features:
joy
Tokenjoy
Feature activation-0.007
Top resid features:
ed
Tokened
Feature activation-0.007
Top resid features:
now
Token now
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.026
Top resid features:
bring
Token bring
Feature activation+3.650
Top resid features:
the
Token the
Feature activation+0.119
Top resid features:
best
Token best
Feature activation+0.215
Top resid features:
of
Token of
Feature activation+0.121
Top resid features:
Broadway
Token Broadway
Feature activation+0.295
Top resid features:
to
Token to
Feature activation+0.231
Top resid features:
return
Token return
Feature activation+0.021
Top resid features:
to
Token to
Feature activation+0.029
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
school
Token school
Feature activation+0.027
Top resid features:
after
Token after
Feature activation+0.099
Top resid features:
bringing
Token bringing
Feature activation+3.486
Top resid features:
health
Token health
Feature activation+0.184
Top resid features:
concerns
Token concerns
Feature activation+0.194
Top resid features:
to
Token to
Feature activation+0.214
Top resid features:
the
Token the
Feature activation+0.299
Top resid features:
attention
Token attention
Feature activation+0.150
Top resid features:
ost
Tokenost
Feature activation+0.007
Top resid features:
im
Tokenim
Feature activation+0.004
Top resid features:
ul
Tokenul
Feature activation+0.013
Top resid features:
ant
Tokenant
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.040
Top resid features:
bring
Token bring
Feature activation+3.783
Top resid features:
cancer
Token cancer
Feature activation+0.161
Top resid features:
-
Token-
Feature activation+0.056
Top resid features:
fighting
Tokenfighting
Feature activation+0.065
Top resid features:
molecules
Token molecules
Feature activation+0.251
Top resid features:
to
Token to
Feature activation+0.298
Top resid features:
worked
Token worked
Feature activation+0.017
Top resid features:
for
Token for
Feature activation+0.047
Top resid features:
two
Token two
Feature activation+0.046
Top resid features:
years
Token years
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.030
Top resid features:
bring
Token bring
Feature activation+3.650
Top resid features:
bike
Token bike
Feature activation+0.264
Top resid features:
lanes
Token lanes
Feature activation+0.316
Top resid features:
to
Token to
Feature activation+0.329
Top resid features:
Browns
Token Browns
Feature activation+0.000
Top resid features:
ville
Tokenville
Feature activation+0.000
Top resid features:
us
Token us
Feature activation-0.002
Top resid features:
in
Token in
Feature activation+0.068
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
effort
Token effort
Feature activation+0.017
Top resid features:
to
Token to
Feature activation+0.042
Top resid features:
bring
Token bring
Feature activation+3.540
Top resid features:
it
Token it
Feature activation+0.114
Top resid features:
all
Token all
Feature activation+0.580
Top resid features:
to
Token to
Feature activation+0.233
Top resid features:
life
Token life
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
000
Token000
Feature activation+0.025
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Tr
Token Tr
Feature activation+0.020
Top resid features:
ains
Tokenains
Feature activation+0.037
Top resid features:
bring
Token bring
Feature activation+3.696
Top resid features:
people
Token people
Feature activation+0.135
Top resid features:
and
Token and
Feature activation+0.113
Top resid features:
goods
Token goods
Feature activation+0.300
Top resid features:
to
Token to
Feature activation+0.272
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.204
Top resid features:
not
Token not
Feature activation+0.035
Top resid features:
bring
Token bring
Feature activation+3.743
Top resid features:
every
Token every
Feature activation+0.007
Top resid features:
offender
Token offender
Feature activation+0.535
Top resid features:
to
Token to
Feature activation+0.269
Top resid features:
justice
Token justice
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.002
Top resid features:
already
Token already
Feature activation+0.008
Top resid features:
stars
Token stars
Feature activation+0.004
Top resid features:
interested
Token interested
Feature activation+0.032
Top resid features:
in
Token in
Feature activation+0.052
Top resid features:
bringing
Token bringing
Feature activation+3.633
Top resid features:
Captain
Token Captain
Feature activation+0.144
Top resid features:
Britain
Token Britain
Feature activation+0.228
Top resid features:
to
Token to
Feature activation+0.356
Top resid features:
life
Token life
Feature activation+0.156
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
said
Token said
Feature activation-0.021
Top resid features:
Livingston
Token Livingston
Feature activation+0.008
Top resid features:
âĢ
Token âĢ
Feature activation+0.066
Top resid features:
ľ
Tokenľ
Feature activation-0.006
Top resid features:
will
Tokenwill
Feature activation+0.024
Top resid features:
bring
Token bring
Feature activation+3.371
Top resid features:
huge
Token huge
Feature activation+0.293
Top resid features:
talent
Token talent
Feature activation+0.478
Top resid features:
to
Token to
Feature activation+0.229
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
vital
Token vital
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
In
Token In
Feature activation+0.067
Top resid features:
an
Token an
Feature activation+0.008
Top resid features:
attempt
Token attempt
Feature activation-0.027
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
bring
Token bring
Feature activation+3.361
Top resid features:
peace
Token peace
Feature activation+0.719
Top resid features:
to
Token to
Feature activation+0.256
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
world
Token world
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
ively
Tokenively
Feature activation+0.011
Top resid features:
multiplayer
Token multiplayer
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.026
Top resid features:
Multiplayer
Token Multiplayer
Feature activation+0.009
Top resid features:
will
Token will
Feature activation+0.028
Top resid features:
bring
Token bring
Feature activation+3.512
Top resid features:
many
Token many
Feature activation+0.165
Top resid features:
new
Token new
Feature activation+0.248
Top resid features:
aspects
Token aspects
Feature activation+0.348
Top resid features:
to
Token to
Feature activation+0.224
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Microsoft
Token Microsoft
Feature activation+0.022
Top resid features:
have
Token have
Feature activation+0.041
Top resid features:
teamed
Token teamed
Feature activation+0.033
Top resid features:
up
Token up
Feature activation+0.016
Top resid features:
to
Token to
Feature activation+0.016
Top resid features:
bring
Token bring
Feature activation+3.389
Top resid features:
downloadable
Token downloadable
Feature activation+0.170
Top resid features:
content
Token content
Feature activation+0.149
Top resid features:
packs
Token packs
Feature activation+0.329
Top resid features:
to
Token to
Feature activation+0.268
Top resid features:
Minecraft
Token Minecraft
Feature activation+0.000
Top resid features:
return
Token return
Feature activation+0.031
Top resid features:
to
Token to
Feature activation+0.023
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
school
Token school
Feature activation+0.052
Top resid features:
after
Token after
Feature activation+0.140
Top resid features:
bringing
Token bringing
Feature activation+3.172
Top resid features:
health
Token health
Feature activation+0.338
Top resid features:
concerns
Token concerns
Feature activation+0.478
Top resid features:
to
Token to
Feature activation+0.247
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
attention
Token attention
Feature activation+0.000
Top resid features:
us
Token us
Feature activation-0.000
Top resid features:
in
Token in
Feature activation+0.057
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
effort
Token effort
Feature activation+0.023
Top resid features:
to
Token to
Feature activation+0.073
Top resid features:
bring
Token bring
Feature activation+3.572
Top resid features:
it
Token it
Feature activation+0.103
Top resid features:
all
Token all
Feature activation+0.098
Top resid features:
to
Token to
Feature activation+0.323
Top resid features:
life
Token life
Feature activation+0.169
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
new
Token new
Feature activation+0.002
Top resid features:
money
Token money
Feature activation-0.010
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
help
Token help
Feature activation+0.024
Top resid features:
bring
Token bring
Feature activation+3.232
Top resid features:
some
Token some
Feature activation+0.087
Top resid features:
stability
Token stability
Feature activation+0.781
Top resid features:
to
Token to
Feature activation+0.228
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
states
Token states
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.03

Head 2: 0.04

Head 3: 0.06

Head 4: 0.04

Head 5: 0.06

Head 6: 0.03

Head 7: 0.02

Head 8: 0.53

Head 9: 0.05

Head 10: 0.05

Head 11: 0.02

Positive logits

rawdownloadcloneembedreportprint1.46

Medina1.41

Mata1.40

ashore1.40

IVERS1.38

unity1.37

inness1.32

habi1.30

hua1.30

ullah1.30

torch1.29

ihar1.28

abilities1.27

izons1.25

trem1.23

ffield1.22

1.22

owsky1.21

osi1.20

hest1.20

Negative logits

advert-1.48

assetsadobe-1.39

Celeb-1.35

gou-1.35

Prot-1.32

Initi-1.26

Dealer-1.25

inately-1.24

adish-1.23

Rolling-1.22

ntil-1.20

ensibly-1.20

raved-1.19

Strateg-1.18

Rack-1.18

tracked-1.16

Storage-1.16

Recomm-1.15

insert-1.15

PAGE-1.12

INTERVAL 3.040 - 3.377
CONTAINS 0.000%

would
Token would
Feature activation+0.000
bring
Token bring
Feature activation+0.000
valuable
Token valuable
Feature activation+0.154
business
Token business
Feature activation+0.035
experience
Token experience
Feature activation+1.392
to
Token to
Feature activation+3.158
the
Token the
Feature activation+0.053
Oval
Token Oval
Feature activation+0.000
Office
Token Office
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
wouldn
Token wouldn
Feature activation+0.000
't
Token't
Feature activation+0.000
bring
Token bring
Feature activation+0.000
good
Token good
Feature activation+0.565
publicity
Token publicity
Feature activation+0.976
to
Token to
Feature activation+3.377
a
Token a
Feature activation+0.620
company
Token company
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
attackers
Token attackers
Feature activation+0.000
Nothing
TokenNothing
Feature activation+0.000
will
Token will
Feature activation+0.000
bring
Token bring
Feature activation+0.000
a
Token a
Feature activation+0.743
smile
Token smile
Feature activation+1.740
to
Token to
Feature activation+3.180
your
Token your
Feature activation+0.180
face
Token face
Feature activation+1.129
faster
Token faster
Feature activation+0.118
this
Token this
Feature activation+0.000
holiday
Token holiday
Feature activation+0.000

INTERVAL 2.702 - 3.040
CONTAINS 0.001%

effort
Token effort
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
it
Token it
Feature activation+0.109
all
Token all
Feature activation+1.608
to
Token to
Feature activation+2.839
life
Token life
Feature activation+2.659
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Let
TokenLet
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
will
Tokenwill
Feature activation+0.000
bring
Token bring
Feature activation+0.000
huge
Token huge
Feature activation+0.308
talent
Token talent
Feature activation+0.766
to
Token to
Feature activation+2.743
a
Token a
Feature activation+1.151
vital
Token vital
Feature activation+0.000
national
Token national
Feature activation+0.000
effort
Token effort
Feature activation+0.329
.
Token.
Feature activation+0.000
bring
Token bring
Feature activation+0.000
cancer
Token cancer
Feature activation+0.000
-
Token-
Feature activation+0.701
fighting
Tokenfighting
Feature activation+0.595
molecules
Token molecules
Feature activation+1.224
to
Token to
Feature activation+2.855
the
Token the
Feature activation+0.000
affected
Token affected
Feature activation+0.000
area
Token area
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
an
Token an
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
peace
Token peace
Feature activation+1.066
to
Token to
Feature activation+2.708
the
Token the
Feature activation+0.167
world
Token world
Feature activation+0.488
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
her
Token her
Feature activation+0.192
whole
Token whole
Feature activation+0.833
family
Token family
Feature activation+0.969
to
Token to
Feature activation+2.909
space
Token space
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
role
Token role
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 2.364 - 2.702
CONTAINS 0.003%

steps
Token steps
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
closure
Token closure
Feature activation+1.821
to
Token to
Feature activation+2.418
the
Token the
Feature activation+0.000
legacy
Token legacy
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Indian
Token Indian
Feature activation+0.000
brought
Token brought
Feature activation+0.000
the
Token the
Feature activation+0.000
sensation
Token sensation
Feature activation+0.827
a
Token a
Feature activation+1.002
little
Token little
Feature activation+0.707
closer
Token closer
Feature activation+2.512
to
Token to
Feature activation+0.417
that
Token that
Feature activation+0.000
of
Token of
Feature activation+0.000
real
Token real
Feature activation+0.000
water
Token water
Feature activation+0.000
may
Token may
Feature activation+0.000
not
Token not
Feature activation+0.000
bring
Token bring
Feature activation+0.000
us
Token us
Feature activation+0.314
any
Token any
Feature activation+0.624
closer
Token closer
Feature activation+2.549
to
Token to
Feature activation+0.706
rat
Token rat
Feature activation+0.000
-
Token-
Feature activation+0.000
brain
Tokenbrain
Feature activation+0.000
pilots
Token pilots
Feature activation+0.000
infrastructure
Token infrastructure
Feature activation+0.000
needed
Token needed
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
the
Token the
Feature activation+0.106
benefits
Token benefits
Feature activation+2.404
of
Token of
Feature activation+0.094
decentral
Token decentral
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
to
Token to
Feature activation+1.959
the
Token the
Feature activation+0.000
helped
Token helped
Feature activation+0.000
me
Token me
Feature activation+0.000
bring
Token bring
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+1.759
life
Token life
Feature activation+2.536
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000

INTERVAL 2.026 - 2.364
CONTAINS 0.003%

fighting
Token fighting
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
job
Token job
Feature activation+0.000
lessness
Tokenlessness
Feature activation+0.000
down
Token down
Feature activation+2.096
from
Token from
Feature activation+0.000
above
Token above
Feature activation+0.000
10
Token 10
Feature activation+0.000
percent
Token percent
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
brought
Token brought
Feature activation+0.000
international
Token international
Feature activation+0.000
attention
Token attention
Feature activation+1.887
to
Token to
Feature activation+2.067
Flint
Token Flint
Feature activation+0.000
's
Token's
Feature activation+0.000
troubles
Token troubles
Feature activation+0.397
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+0.269
massive
Token massive
Feature activation+0.997
BlackBerry
Token BlackBerry
Feature activation+0.000
Play
Token Play
Feature activation+0.000
Book
TokenBook
Feature activation+0.000
to
Token to
Feature activation+2.275
the
Token the
Feature activation+0.000
center
Token center
Feature activation+0.000
dash
Token dash
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
is
Token is
Feature activation+0.000
expected
Token expected
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
the
Token the
Feature activation+0.000
total
Token total
Feature activation+2.099
cost
Token cost
Feature activation+1.486
to
Token to
Feature activation+2.159
no
Token no
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
Tr
Token Tr
Feature activation+0.000
ains
Tokenains
Feature activation+0.000
bring
Token bring
Feature activation+0.000
people
Token people
Feature activation+0.623
and
Token and
Feature activation+1.104
goods
Token goods
Feature activation+2.029
to
Token to
Feature activation+2.811
and
Token and
Feature activation+0.000
from
Token from
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
cities
Token cities
Feature activation+0.000

INTERVAL 1.689 - 2.026
CONTAINS 0.004%

that
Token that
Feature activation+0.000
bring
Token bring
Feature activation+0.120
both
Token both
Feature activation+0.130
utility
Token utility
Feature activation+0.513
and
Token and
Feature activation+0.983
beauty
Token beauty
Feature activation+1.828
to
Token to
Feature activation+2.197
your
Token your
Feature activation+0.000
house
Token house
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
a
Token a
Feature activation+0.912
united
Token united
Feature activation+0.419
UN
Token UN
Feature activation+0.417
Security
Token Security
Feature activation+0.090
Council
Token Council
Feature activation+0.061
vote
Token vote
Feature activation+1.827
to
Token to
Feature activation+1.785
exploit
Token exploit
Feature activation+0.000
it
Token it
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
bring
Token bring
Feature activation+0.000
McGregor
Token McGregor
Feature activation+0.000
to
Token to
Feature activation+1.751
Australia
Token Australia
Feature activation+0.311
like
Token like
Feature activation+0.068
we
Token we
Feature activation+0.000
did
Token did
Feature activation+0.000
with
Token with
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
bring
Token bring
Feature activation+0.000
it
Token it
Feature activation+0.237
in
Token in
Feature activation+1.691
increment
Token increment
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
.
Token.
Feature activation+0.000
Well
Token Well
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
thing
Token thing
Feature activation+0.000
that
Token that
Feature activation+0.000
brings
Token brings
Feature activation+0.000
everyone
Token everyone
Feature activation+0.582
together
Token together
Feature activation+1.740
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
Land
Token Land
Feature activation+0.000

INTERVAL 1.351 - 1.689
CONTAINS 0.006%

the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.556
real
Tokenreal
Feature activation+1.171
world
Token world
Feature activation+1.787
"
Token"
Feature activation+0.866
into
Token into
Feature activation+1.587
The
Token The
Feature activation+0.000
Kid
Token Kid
Feature activation+0.000
's
Token's
Feature activation+0.000
version
Token version
Feature activation+0.000
of
Token of
Feature activation+0.000
1979
Token 1979
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
brings
Token brings
Feature activation+0.000
us
Token us
Feature activation+0.000
to
Token to
Feature activation+1.482
another
Token another
Feature activation+0.000
lady
Token lady
Feature activation+0.000
of
Token of
Feature activation+0.000
Hip
Token Hip
Feature activation+0.000
-
Token-
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
brings
Token brings
Feature activation+0.000
us
Token us
Feature activation+0.000
to
Token to
Feature activation+1.428
a
Token a
Feature activation+0.649
nice
Token nice
Feature activation+0.058
round
Token round
Feature activation+0.696
number
Token number
Feature activation+0.697
.
Token.
Feature activation+0.000
expected
Token expected
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
the
Token the
Feature activation+0.000
total
Token total
Feature activation+2.099
cost
Token cost
Feature activation+1.486
to
Token to
Feature activation+2.159
no
Token no
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
$
Token $
Feature activation+0.000
economical
Token economical
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
about
Token about
Feature activation+0.473
speedy
Token speedy
Feature activation+1.522
subject
Token subject
Feature activation+0.734
ion
Tokenion
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.013 - 1.351
CONTAINS 0.007%

to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
cancer
Token cancer
Feature activation+0.000
-
Token-
Feature activation+0.701
fighting
Tokenfighting
Feature activation+0.595
molecules
Token molecules
Feature activation+1.224
to
Token to
Feature activation+2.855
the
Token the
Feature activation+0.000
affected
Token affected
Feature activation+0.000
area
Token area
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Bring
TokenBring
Feature activation+0.000
an
Token an
Feature activation+0.725
amount
Token amount
Feature activation+1.055
of
Token of
Feature activation+0.490
horsepower
Token horsepower
Feature activation+0.184
you
Token you
Feature activation+0.743
would
Token would
Feature activation+0.000
consider
Token consider
Feature activation+0.000
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
brought
Token brought
Feature activation+0.000
it
Token it
Feature activation+0.000
upon
Token upon
Feature activation+1.037
ourselves
Token ourselves
Feature activation+0.220
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
Wend
Token Wend
Feature activation+0.000
ell
Tokenell
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
a
Token a
Feature activation+0.316
bit
Token bit
Feature activation+0.000
of
Token of
Feature activation+0.707
festive
Token festive
Feature activation+0.000
cheer
Token cheer
Feature activation+1.139
to
Token to
Feature activation+1.614
people
Token people
Feature activation+0.022
who
Token who
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
In
Token In
Feature activation+0.000
an
Token an
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
peace
Token peace
Feature activation+1.066
to
Token to
Feature activation+2.708
the
Token the
Feature activation+0.167
world
Token world
Feature activation+0.488
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000

INTERVAL 0.675 - 1.013
CONTAINS 0.011%

by
Token by
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
its
Token its
Feature activation+0.422
beautiful
Token beautiful
Feature activation+0.086
qualities
Token qualities
Feature activation+0.806
like
Token like
Feature activation+0.870
an
Token an
Feature activation+1.333
actual
Token actual
Feature activation+0.232
season
Token season
Feature activation+0.000
with
Token with
Feature activation+1.668
weekly
Token weekly
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
brought
Token brought
Feature activation+0.000
their
Token their
Feature activation+0.211
set
Token set
Feature activation+0.000
to
Token to
Feature activation+0.925
a
Token a
Feature activation+0.136
natural
Token natural
Feature activation+0.000
c
Token c
Feature activation+0.000
res
Tokenres
Feature activation+0.000
cend
Tokencend
Feature activation+0.000
ul
Tokenul
Feature activation+0.000
ant
Tokenant
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
cancer
Token cancer
Feature activation+0.000
-
Token-
Feature activation+0.701
fighting
Tokenfighting
Feature activation+0.595
molecules
Token molecules
Feature activation+1.224
to
Token to
Feature activation+2.855
the
Token the
Feature activation+0.000
affected
Token affected
Feature activation+0.000
imp
Token imp
Feature activation+0.000
arted
Tokenarted
Feature activation+0.000
brought
Token brought
Feature activation+0.000
the
Token the
Feature activation+0.000
sensation
Token sensation
Feature activation+0.827
a
Token a
Feature activation+1.002
little
Token little
Feature activation+0.707
closer
Token closer
Feature activation+2.512
to
Token to
Feature activation+0.417
that
Token that
Feature activation+0.000
of
Token of
Feature activation+0.000
just
Token just
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
the
Token the
Feature activation+0.000
gem
Token gem
Feature activation+0.000
cost
Token cost
Feature activation+1.830
down
Token down
Feature activation+0.867
for
Token for
Feature activation+0.000
everything
Token everything
Feature activation+0.000
,
Token,
Feature activation+0.000
try
Token try
Feature activation+0.000
Sk
Token Sk
Feature activation+0.000

INTERVAL 0.338 - 0.675
CONTAINS 0.018%

to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
aboard
Token aboard
Feature activation+0.471
a
Token a
Feature activation+0.912
united
Token united
Feature activation+0.419
UN
Token UN
Feature activation+0.417
Security
Token Security
Feature activation+0.090
Council
Token Council
Feature activation+0.061
rey
Tokenrey
Feature activation+0.000
brings
Token brings
Feature activation+0.000
a
Token a
Feature activation+0.638
passion
Token passion
Feature activation+0.135
for
Token for
Feature activation+0.635
efficiency
Token efficiency
Feature activation+0.343
and
Token and
Feature activation+0.104
innovation
Token innovation
Feature activation+0.580
to
Token to
Feature activation+2.199
life
Token life
Feature activation+0.500
with
Token with
Feature activation+0.480
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
analysis
Token analysis
Feature activation+0.000
to
Token to
Feature activation+0.000
bring
Token bring
Feature activation+0.000
you
Token you
Feature activation+0.357
the
Token the
Feature activation+1.335
best
Token best
Feature activation+1.154
buying
Token buying
Feature activation+0.791
advice
Token advice
Feature activation+0.000
possible
Token possible
Feature activation+0.000
000
Token000
Feature activation+0.000
.
Token.
Feature activation+0.000
Tr
Token Tr
Feature activation+0.000
ains
Tokenains
Feature activation+0.000
bring
Token bring
Feature activation+0.000
people
Token people
Feature activation+0.623
and
Token and
Feature activation+1.104
goods
Token goods
Feature activation+2.029
to
Token to
Feature activation+2.811
and
Token and
Feature activation+0.000
from
Token from
Feature activation+0.000
game
Token game
Feature activation+0.000
that
Token that
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
bring
Token bring
Feature activation+0.000
it
Token it
Feature activation+0.470
to
Token to
Feature activation+2.400
the
Token the
Feature activation+0.328
caliber
Token caliber
Feature activation+0.030
of
Token of
Feature activation+0.000
"
Token "
Feature activation+0.000

INTERVAL 0.000 - 0.338
CONTAINS 99.948%

or
Token or
Feature activation+0.000
until
Token until
Feature activation+0.000
the
Token the
Feature activation+0.000
b
Token b
Feature activation+0.000
uns
Tokenuns
Feature activation+0.000
are
Token are
Feature activation+0.000
golden
Token golden
Feature activation+0.000
brown
Token brown
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
bit
Token bit
Feature activation+0.000
more
Token more
Feature activation+0.000
in
Token in
Feature activation+0.000
love
Token love
Feature activation+0.000
with
Token with
Feature activation+0.000
in
Token in
Feature activation+0.000
2018
Token 2018
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Like
TokenLike
Feature activation+0.000
on
Token on
Feature activation+0.000
PlayStation
Token PlayStation
Feature activation+0.000
4
Token 4
Feature activation+0.000
,
Token,
Feature activation+0.000
PlayStation
Token PlayStation
Feature activation+0.000
3
Token 3
Feature activation+0.000
,
Token,
Feature activation+0.000
PlayStation
Token PlayStation
Feature activation+0.000
Vita
Token Vita
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
essay
Token essay
Feature activation+0.000
about
Token about
Feature activation+0.000
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
poem
Token poem
Feature activation+0.000
speaks
Token speaks
Feature activation+0.000
to
Token to
Feature activation+0.000
fundamental
Token fundamental
Feature activation+0.000
truths
Token truths
Feature activation+0.000
.
Token.
Feature activation+0.000
Aw
Token Aw
Feature activation+0.000
from
Token from
Feature activation+0.000
state
Token state
Feature activation+0.000
budgets
Token budgets
Feature activation+0.000
.
Token.
Feature activation+0.000
Yet
Token Yet
Feature activation+0.000
,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
standards
Token standards
Feature activation+0.000
of
Token of
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 3 in H2.8: (feature 8821)

TOP ACTIVATIONS
MAX = 3.220

2014
Token 2014
Feature activation+0.000
that
Token that
Feature activation+0.000
left
Token left
Feature activation+0.186
150
Token 150
Feature activation+0.473
people
Token people
Feature activation+0.559
dead
Token dead
Feature activation+3.220
âĢĶ
Token âĢĶ
Feature activation+0.501
most
Token most
Feature activation+0.389
of
Token of
Feature activation+0.045
them
Token them
Feature activation+0.207
children
Token children
Feature activation+0.060
the
Token the
Feature activation+0.000
plans
Token plans
Feature activation+0.000
left
Token left
Feature activation+0.000
too
Token too
Feature activation+0.000
many
Token many
Feature activation+0.237
unanswered
Token unanswered
Feature activation+2.784
questions
Token questions
Feature activation+0.072
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Arizona
Token Arizona
Feature activation+0.000
that
Token that
Feature activation+0.000
left
Token left
Feature activation+0.000
six
Token six
Feature activation+0.000
people
Token people
Feature activation+0.474
dead
Token dead
Feature activation+2.672
and
Token and
Feature activation+0.114
Democratic
Token Democratic
Feature activation+0.006
congress
Token congress
Feature activation+0.054
woman
Tokenwoman
Feature activation+0.118
Gab
Token Gab
Feature activation+0.000
left
Token left
Feature activation+0.000
an
Token an
Feature activation+0.016
ind
Token ind
Feature activation+1.855
el
Tokenel
Feature activation+0.000
ible
Tokenible
Feature activation+2.199
impression
Token impression
Feature activation+2.669
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
franchise
Token franchise
Feature activation+0.000
is
Token is
Feature activation+0.000
credited
Token credited
Feature activation+0.000
left
Token left
Feature activation+0.000
17
Token 17
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.015
people
Token people
Feature activation+0.030
dead
Token dead
Feature activation+2.574
in
Token in
Feature activation+0.196
17
Token 17
Feature activation+0.000
months
Token months
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
three
Token three
Feature activation+0.000
decades
Token decades
Feature activation+0.000
and
Token and
Feature activation+0.000
left
Token left
Feature activation+0.000
him
Token him
Feature activation+0.951
homeless
Token homeless
Feature activation+2.345
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Father
TokenFather
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Token old
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
left
Token left
Feature activation+0.101
him
Token him
Feature activation+1.055
with
Token with
Feature activation+2.299
my
Token my
Feature activation+0.000
in
Token in
Feature activation+0.057
-
Token-
Feature activation+0.000
laws
Tokenlaws
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
H
TokenH
Feature activation+0.000
ans
Tokenans
Feature activation+0.000
left
Token left
Feature activation+0.000
a
Token a
Feature activation+0.622
mark
Token mark
Feature activation+2.266
on
Token on
Feature activation+0.633
everyone
Token everyone
Feature activation+0.000
he
Token he
Feature activation+0.000
met
Token met
Feature activation+0.000
,
Token,
Feature activation+0.000
run
Token run
Feature activation+0.000
left
Token left
Feature activation+0.000
an
Token an
Feature activation+0.016
ind
Token ind
Feature activation+1.855
el
Tokenel
Feature activation+0.000
ible
Tokenible
Feature activation+2.199
impression
Token impression
Feature activation+2.669
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
franchise
Token franchise
Feature activation+0.000
is
Token is
Feature activation+0.000
This
TokenThis
Feature activation+0.000
has
Token has
Feature activation+0.000
left
Token left
Feature activation+0.000
a
Token a
Feature activation+0.196
political
Token political
Feature activation+0.000
vacuum
Token vacuum
Feature activation+2.158
and
Token and
Feature activation+0.000
various
Token various
Feature activation+0.000
factions
Token factions
Feature activation+0.000
are
Token are
Feature activation+0.000
j
Token j
Feature activation+0.000
April
Token April
Feature activation+0.000
he
Token he
Feature activation+0.000
left
Token left
Feature activation+0.000
all
Token all
Feature activation+0.500
this
Token this
Feature activation+1.480
behind
Token behind
Feature activation+2.145
,
Token,
Feature activation+0.000
escaping
Token escaping
Feature activation+0.000
Syria
Token Syria
Feature activation+0.000
to
Token to
Feature activation+0.000
risk
Token risk
Feature activation+0.000
B
Token B
Feature activation+0.000
ales
Tokenales
Feature activation+0.000
left
Token left
Feature activation+0.036
his
Token his
Feature activation+0.434
remote
Token remote
Feature activation+0.642
outpost
Token outpost
Feature activation+2.137
in
Token in
Feature activation+1.180
an
Token an
Feature activation+0.429
impoverished
Token impoverished
Feature activation+0.500
region
Token region
Feature activation+0.000
of
Token of
Feature activation+0.185
Civil
Token Civil
Feature activation+0.000
War
Token War
Feature activation+0.000
left
Token left
Feature activation+0.000
an
Token an
Feature activation+0.299
enormous
Token enormous
Feature activation+1.079
imprint
Token imprint
Feature activation+2.104
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
consciousness
Token consciousness
Feature activation+0.000
in
Token in
Feature activation+0.000
explosion
Token explosion
Feature activation+0.000
that
Token that
Feature activation+0.000
left
Token left
Feature activation+0.000
29
Token 29
Feature activation+0.000
people
Token people
Feature activation+0.845
hurt
Token hurt
Feature activation+2.071
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Bomb
TokenBomb
Feature activation+0.000
ing
Tokening
Feature activation+0.000
Greg
Token Greg
Feature activation+0.000
orio
Tokenorio
Feature activation+0.000
has
Token has
Feature activation+0.000
left
Token left
Feature activation+0.000
his
Token his
Feature activation+0.102
post
Token post
Feature activation+1.987
as
Token as
Feature activation+1.001
Fifa
Token Fifa
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
left
Token left
Feature activation+0.000
a
Token a
Feature activation+0.000
hole
Token hole
Feature activation+1.976
at
Token at
Feature activation+1.170
corner
Token corner
Feature activation+0.000
for
Token for
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
,
Token,
Feature activation+0.000
ama
Tokenama
Feature activation+0.000
had
Token had
Feature activation+0.000
left
Token left
Feature activation+0.064
the
Token the
Feature activation+0.539
stadium
Token stadium
Feature activation+0.927
for
Token for
Feature activation+1.915
the
Token the
Feature activation+0.314
airport
Token airport
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
like
Token like
Feature activation+0.000
you
Token you
Feature activation+0.000
left
Token left
Feature activation+0.000
the
Token the
Feature activation+0.397
store
Token store
Feature activation+1.018
without
Token without
Feature activation+1.908
paying
Token paying
Feature activation+0.000
for
Token for
Feature activation+0.000
this
Token this
Feature activation+0.000
.
Token.
Feature activation+0.000
No
Token No
Feature activation+0.000
Snowden
Token Snowden
Feature activation+0.000
has
Token has
Feature activation+0.000
left
Token left
Feature activation+0.000
a
Token a
Feature activation+0.142
cryptic
Token cryptic
Feature activation+0.668
tweet
Token tweet
Feature activation+1.899
sparking
Token sparking
Feature activation+0.437
concern
Token concern
Feature activation+0.000
among
Token among
Feature activation+0.000
the
Token the
Feature activation+0.000
masses
Token masses
Feature activation+0.000
he
Token he
Feature activation+0.000
may
Token may
Feature activation+0.000
have
Token have
Feature activation+0.000
left
Token left
Feature activation+0.000
the
Token the
Feature activation+0.060
country
Token country
Feature activation+1.881
based
Token based
Feature activation+0.041
on
Token on
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
found
Token found
Feature activation+0.000
during
Token during
Feature activation+0.000

Top DFA by src position
MAX = 4.216

Pesh
Token Pesh
Feature activation+0.028
Top resid features:
awar
Tokenawar
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.072
Top resid features:
2014
Token 2014
Feature activation+0.014
Top resid features:
that
Token that
Feature activation+0.014
Top resid features:
left
Token left
Feature activation+4.006
Top resid features:
150
Token 150
Feature activation-0.036
Top resid features:
people
Token people
Feature activation+0.263
Top resid features:
dead
Token dead
Feature activation+0.008
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
Far
Token Far
Feature activation+0.014
Top resid features:
ron
Tokenron
Feature activation-0.002
Top resid features:
said
Token said
Feature activation+0.024
Top resid features:
the
Token the
Feature activation+0.031
Top resid features:
plans
Token plans
Feature activation+0.109
Top resid features:
left
Token left
Feature activation+3.643
Top resid features:
too
Token too
Feature activation+0.138
Top resid features:
many
Token many
Feature activation-0.005
Top resid features:
unanswered
Token unanswered
Feature activation+0.028
Top resid features:
questions
Token questions
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.037
Top resid features:
Tucson
Token Tucson
Feature activation-0.025
Top resid features:
,
Token,
Feature activation-0.052
Top resid features:
Arizona
Token Arizona
Feature activation-0.031
Top resid features:
that
Token that
Feature activation+0.031
Top resid features:
left
Token left
Feature activation+3.737
Top resid features:
six
Token six
Feature activation-0.041
Top resid features:
people
Token people
Feature activation+0.259
Top resid features:
dead
Token dead
Feature activation-0.031
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Democratic
Token Democratic
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
six
Token six
Feature activation+0.067
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
year
Tokenyear
Feature activation+0.009
Top resid features:
run
Token run
Feature activation+0.013
Top resid features:
left
Token left
Feature activation+4.216
Top resid features:
an
Token an
Feature activation-0.029
Top resid features:
ind
Token ind
Feature activation-0.091
Top resid features:
el
Tokenel
Feature activation-0.094
Top resid features:
ible
Tokenible
Feature activation-0.039
Top resid features:
impression
Token impression
Feature activation-0.004
Top resid features:
in
Token in
Feature activation+0.039
Top resid features:
an
Token an
Feature activation+0.005
Top resid features:
uprising
Token uprising
Feature activation-0.008
Top resid features:
that
Token that
Feature activation+0.022
Top resid features:
has
Token has
Feature activation+0.026
Top resid features:
left
Token left
Feature activation+3.464
Top resid features:
17
Token 17
Feature activation-0.039
Top resid features:
,
Token,
Feature activation-0.141
Top resid features:
000
Token000
Feature activation+0.180
Top resid features:
people
Token people
Feature activation+0.204
Top resid features:
dead
Token dead
Feature activation-0.023
Top resid features:
more
Token more
Feature activation+0.014
Top resid features:
than
Token than
Feature activation+0.013
Top resid features:
three
Token three
Feature activation+0.002
Top resid features:
decades
Token decades
Feature activation+0.013
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
left
Token left
Feature activation+3.276
Top resid features:
him
Token him
Feature activation+0.177
Top resid features:
homeless
Token homeless
Feature activation-0.059
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:
a
Token a
Feature activation+0.005
Top resid features:
week
Token week
Feature activation+0.030
Top resid features:
old
Token old
Feature activation+0.017
Top resid features:
,
Token,
Feature activation-0.078
Top resid features:
I
Token I
Feature activation+0.074
Top resid features:
left
Token left
Feature activation+3.196
Top resid features:
him
Token him
Feature activation+0.099
Top resid features:
with
Token with
Feature activation+0.118
Top resid features:
my
Token my
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.063
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
H
TokenH
Feature activation+0.037
Top resid features:
ans
Tokenans
Feature activation+0.079
Top resid features:
left
Token left
Feature activation+3.575
Top resid features:
a
Token a
Feature activation-0.056
Top resid features:
mark
Token mark
Feature activation-0.082
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
everyone
Token everyone
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.004
Top resid features:
six
Token six
Feature activation+0.077
Top resid features:
-
Token-
Feature activation+0.009
Top resid features:
year
Tokenyear
Feature activation+0.010
Top resid features:
run
Token run
Feature activation-0.015
Top resid features:
left
Token left
Feature activation+3.497
Top resid features:
an
Token an
Feature activation-0.065
Top resid features:
ind
Token ind
Feature activation+0.055
Top resid features:
el
Tokenel
Feature activation+0.088
Top resid features:
ible
Tokenible
Feature activation-0.128
Top resid features:
impression
Token impression
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.028
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.017
Top resid features:
This
TokenThis
Feature activation+0.055
Top resid features:
has
Token has
Feature activation+0.031
Top resid features:
left
Token left
Feature activation+3.146
Top resid features:
a
Token a
Feature activation-0.048
Top resid features:
political
Token political
Feature activation+0.092
Top resid features:
vacuum
Token vacuum
Feature activation+0.027
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
various
Token various
Feature activation+0.000
Top resid features:
But
Token But
Feature activation+0.043
Top resid features:
on
Token on
Feature activation+0.061
Top resid features:
15
Token 15
Feature activation+0.037
Top resid features:
April
Token April
Feature activation-0.013
Top resid features:
he
Token he
Feature activation+0.061
Top resid features:
left
Token left
Feature activation+3.210
Top resid features:
all
Token all
Feature activation-0.082
Top resid features:
this
Token this
Feature activation+0.030
Top resid features:
behind
Token behind
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
escaping
Token escaping
Feature activation+0.000
Top resid features:
staff
Token staff
Feature activation+0.009
Top resid features:
sergeant
Token sergeant
Feature activation+0.026
Top resid features:
Robert
Token Robert
Feature activation+0.054
Top resid features:
B
Token B
Feature activation+0.006
Top resid features:
ales
Tokenales
Feature activation-0.009
Top resid features:
left
Token left
Feature activation+2.811
Top resid features:
his
Token his
Feature activation+0.059
Top resid features:
remote
Token remote
Feature activation+0.146
Top resid features:
outpost
Token outpost
Feature activation+0.198
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
The
TokenThe
Feature activation+0.043
Top resid features:
Civil
Token Civil
Feature activation+0.041
Top resid features:
War
Token War
Feature activation+0.059
Top resid features:
left
Token left
Feature activation+3.373
Top resid features:
an
Token an
Feature activation-0.096
Top resid features:
enormous
Token enormous
Feature activation+0.151
Top resid features:
imprint
Token imprint
Feature activation-0.066
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.032
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
Chelsea
Token Chelsea
Feature activation+0.033
Top resid features:
explosion
Token explosion
Feature activation+0.053
Top resid features:
that
Token that
Feature activation-0.040
Top resid features:
left
Token left
Feature activation+3.052
Top resid features:
29
Token 29
Feature activation+0.058
Top resid features:
people
Token people
Feature activation+0.297
Top resid features:
hurt
Token hurt
Feature activation-0.076
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
ter
Tokenter
Feature activation+0.004
Top resid features:
De
Token De
Feature activation+0.012
Top resid features:
Greg
Token Greg
Feature activation+0.023
Top resid features:
orio
Tokenorio
Feature activation-0.009
Top resid features:
has
Token has
Feature activation+0.018
Top resid features:
left
Token left
Feature activation+3.031
Top resid features:
his
Token his
Feature activation+0.058
Top resid features:
post
Token post
Feature activation+0.050
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Fifa
Token Fifa
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Cyrus
Token Cyrus
Feature activation-0.004
Top resid features:
Jones
Token Jones
Feature activation+0.016
Top resid features:
to
Token to
Feature activation+0.138
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
NFL
Token NFL
Feature activation+0.033
Top resid features:
left
Token left
Feature activation+3.072
Top resid features:
a
Token a
Feature activation-0.145
Top resid features:
hole
Token hole
Feature activation-0.044
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
corner
Token corner
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Ol
Token Ol
Feature activation+0.027
Top resid features:
si
Tokensi
Feature activation-0.000
Top resid features:
R
Token R
Feature activation+0.028
Top resid features:
ama
Tokenama
Feature activation+0.011
Top resid features:
had
Token had
Feature activation+0.092
Top resid features:
left
Token left
Feature activation+2.458
Top resid features:
the
Token the
Feature activation-0.047
Top resid features:
stadium
Token stadium
Feature activation+0.325
Top resid features:
for
Token for
Feature activation+0.149
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
airport
Token airport
Feature activation+0.000
Top resid features:
So
TokenSo
Feature activation+0.092
Top resid features:
it
Token it
Feature activation+0.036
Top resid features:
looks
Token looks
Feature activation-0.017
Top resid features:
like
Token like
Feature activation+0.026
Top resid features:
you
Token you
Feature activation-0.019
Top resid features:
left
Token left
Feature activation+2.957
Top resid features:
the
Token the
Feature activation-0.033
Top resid features:
store
Token store
Feature activation+0.105
Top resid features:
without
Token without
Feature activation-0.035
Top resid features:
paying
Token paying
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.022
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.026
Top resid features:
Edward
TokenEdward
Feature activation+0.033
Top resid features:
Snowden
Token Snowden
Feature activation+0.057
Top resid features:
has
Token has
Feature activation-0.013
Top resid features:
left
Token left
Feature activation+3.446
Top resid features:
a
Token a
Feature activation-0.142
Top resid features:
cryptic
Token cryptic
Feature activation+0.054
Top resid features:
tweet
Token tweet
Feature activation-0.091
Top resid features:
sparking
Token sparking
Feature activation+0.000
Top resid features:
concern
Token concern
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.058
Top resid features:
suspected
Token suspected
Feature activation+0.019
Top resid features:
he
Token he
Feature activation+0.097
Top resid features:
may
Token may
Feature activation+0.011
Top resid features:
have
Token have
Feature activation+0.025
Top resid features:
left
Token left
Feature activation+2.721
Top resid features:
the
Token the
Feature activation-0.054
Top resid features:
country
Token country
Feature activation+0.101
Top resid features:
based
Token based
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
evidence
Token evidence
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.03

Head 2: 0.05

Head 3: 0.05

Head 4: 0.06

Head 5: 0.05

Head 6: 0.03

Head 7: 0.03

Head 8: 0.52

Head 9: 0.06

Head 10: 0.05

Head 11: 0.02

Positive logits

untouched1.68

charred1.59

Ruk1.55

ash1.50

unfinished1.44

scars1.43

wreckage1.42

Vaugh1.41

ashes1.40

crater1.39

shack1.39

Horowitz1.37

Shogun1.37

USSR1.37

Jah1.34

unsatisf1.34

bruises1.32

unhappy1.32

Islands1.30

unresolved1.30

Negative logits

wcsstore-1.64

arb-1.43

Cosponsors-1.42

Parables-1.36

FactoryReloaded-1.33

mercial-1.32

quickShipAvailable-1.30

Percent-1.29

MN-1.28

idth-1.27

nel-1.27

ided-1.26

dayName-1.25

coh-1.24

iqueness-1.22

guided-1.21

orously-1.20

Called-1.20

CLA-1.19

adal-1.19

INTERVAL 2.898 - 3.220
CONTAINS 0.000%

2014
Token 2014
Feature activation+0.000
that
Token that
Feature activation+0.000
left
Token left
Feature activation+0.186
150
Token 150
Feature activation+0.473
people
Token people
Feature activation+0.559
dead
Token dead
Feature activation+3.220
âĢĶ
Token âĢĶ
Feature activation+0.501
most
Token most
Feature activation+0.389
of
Token of
Feature activation+0.045
them
Token them
Feature activation+0.207
children
Token children
Feature activation+0.060

INTERVAL 2.576 - 2.898
CONTAINS 0.000%

the
Token the
Feature activation+0.000
plans
Token plans
Feature activation+0.000
left
Token left
Feature activation+0.000
too
Token too
Feature activation+0.000
many
Token many
Feature activation+0.237
unanswered
Token unanswered
Feature activation+2.784
questions
Token questions
Feature activation+0.072
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
left
Token left
Feature activation+0.000
an
Token an
Feature activation+0.016
ind
Token ind
Feature activation+1.855
el
Tokenel
Feature activation+0.000
ible
Tokenible
Feature activation+2.199
impression
Token impression
Feature activation+2.669
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
franchise
Token franchise
Feature activation+0.000
is
Token is
Feature activation+0.000
credited
Token credited
Feature activation+0.000
Arizona
Token Arizona
Feature activation+0.000
that
Token that
Feature activation+0.000
left
Token left
Feature activation+0.000
six
Token six
Feature activation+0.000
people
Token people
Feature activation+0.474
dead
Token dead
Feature activation+2.672
and
Token and
Feature activation+0.114
Democratic
Token Democratic
Feature activation+0.006
congress
Token congress
Feature activation+0.054
woman
Tokenwoman
Feature activation+0.118
Gab
Token Gab
Feature activation+0.000

INTERVAL 2.254 - 2.576
CONTAINS 0.000%

three
Token three
Feature activation+0.000
decades
Token decades
Feature activation+0.000
and
Token and
Feature activation+0.000
left
Token left
Feature activation+0.000
him
Token him
Feature activation+0.951
homeless
Token homeless
Feature activation+2.345
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Father
TokenFather
Feature activation+0.000
-
Token-
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
H
TokenH
Feature activation+0.000
ans
Tokenans
Feature activation+0.000
left
Token left
Feature activation+0.000
a
Token a
Feature activation+0.622
mark
Token mark
Feature activation+2.266
on
Token on
Feature activation+0.633
everyone
Token everyone
Feature activation+0.000
he
Token he
Feature activation+0.000
met
Token met
Feature activation+0.000
,
Token,
Feature activation+0.000
left
Token left
Feature activation+0.000
17
Token 17
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.015
people
Token people
Feature activation+0.030
dead
Token dead
Feature activation+2.574
in
Token in
Feature activation+0.196
17
Token 17
Feature activation+0.000
months
Token months
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
old
Token old
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
left
Token left
Feature activation+0.101
him
Token him
Feature activation+1.055
with
Token with
Feature activation+2.299
my
Token my
Feature activation+0.000
in
Token in
Feature activation+0.057
-
Token-
Feature activation+0.000
laws
Tokenlaws
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.932 - 2.254
CONTAINS 0.001%

B
Token B
Feature activation+0.000
ales
Tokenales
Feature activation+0.000
left
Token left
Feature activation+0.036
his
Token his
Feature activation+0.434
remote
Token remote
Feature activation+0.642
outpost
Token outpost
Feature activation+2.137
in
Token in
Feature activation+1.180
an
Token an
Feature activation+0.429
impoverished
Token impoverished
Feature activation+0.500
region
Token region
Feature activation+0.000
of
Token of
Feature activation+0.185
Civil
Token Civil
Feature activation+0.000
War
Token War
Feature activation+0.000
left
Token left
Feature activation+0.000
an
Token an
Feature activation+0.299
enormous
Token enormous
Feature activation+1.079
imprint
Token imprint
Feature activation+2.104
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
consciousness
Token consciousness
Feature activation+0.000
in
Token in
Feature activation+0.000
Greg
Token Greg
Feature activation+0.000
orio
Tokenorio
Feature activation+0.000
has
Token has
Feature activation+0.000
left
Token left
Feature activation+0.000
his
Token his
Feature activation+0.102
post
Token post
Feature activation+1.987
as
Token as
Feature activation+1.001
Fifa
Token Fifa
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
April
Token April
Feature activation+0.000
he
Token he
Feature activation+0.000
left
Token left
Feature activation+0.000
all
Token all
Feature activation+0.500
this
Token this
Feature activation+1.480
behind
Token behind
Feature activation+2.145
,
Token,
Feature activation+0.000
escaping
Token escaping
Feature activation+0.000
Syria
Token Syria
Feature activation+0.000
to
Token to
Feature activation+0.000
risk
Token risk
Feature activation+0.000
This
TokenThis
Feature activation+0.000
has
Token has
Feature activation+0.000
left
Token left
Feature activation+0.000
a
Token a
Feature activation+0.196
political
Token political
Feature activation+0.000
vacuum
Token vacuum
Feature activation+2.158
and
Token and
Feature activation+0.000
various
Token various
Feature activation+0.000
factions
Token factions
Feature activation+0.000
are
Token are
Feature activation+0.000
j
Token j
Feature activation+0.000

INTERVAL 1.610 - 1.932
CONTAINS 0.002%

wetlands
Token wetlands
Feature activation+0.000
has
Token has
Feature activation+0.000
left
Token left
Feature activation+0.000
adjacent
Token adjacent
Feature activation+0.000
areas
Token areas
Feature activation+0.000
more
Token more
Feature activation+1.651
prone
Token prone
Feature activation+0.468
to
Token to
Feature activation+0.000
flooding
Token flooding
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
daughter
Token daughter
Feature activation+0.000
had
Token had
Feature activation+0.000
left
Token left
Feature activation+0.000
the
Token the
Feature activation+0.000
niece
Token niece
Feature activation+0.111
with
Token with
Feature activation+1.780
her
Token her
Feature activation+0.000
brother
Token brother
Feature activation+0.000
so
Token so
Feature activation+0.000
she
Token she
Feature activation+0.000
could
Token could
Feature activation+0.000
when
Token when
Feature activation+0.000
she
Token she
Feature activation+0.000
left
Token left
Feature activation+0.000
neighbouring
Token neighbouring
Feature activation+0.400
Armenia
Token Armenia
Feature activation+0.313
without
Token without
Feature activation+1.754
Internet
Token Internet
Feature activation+0.000
access
Token access
Feature activation+0.043
for
Token for
Feature activation+0.174
twelve
Token twelve
Feature activation+0.000
hours
Token hours
Feature activation+0.000
Steven
Token Steven
Feature activation+0.000
Spielberg
Token Spielberg
Feature activation+0.000
left
Token left
Feature activation+0.299
the
Token the
Feature activation+0.518
Disney
Token Disney
Feature activation+1.320
fold
Token fold
Feature activation+1.774
and
Token and
Feature activation+0.208
went
Token went
Feature activation+0.000
to
Token to
Feature activation+0.000
Universal
Token Universal
Feature activation+0.000
.
Token.
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
run
Token run
Feature activation+0.000
left
Token left
Feature activation+0.000
an
Token an
Feature activation+0.016
ind
Token ind
Feature activation+1.855
el
Tokenel
Feature activation+0.000
ible
Tokenible
Feature activation+2.199
impression
Token impression
Feature activation+2.669
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.288 - 1.610
CONTAINS 0.002%

death
Token death
Feature activation+0.000
left
Token left
Feature activation+0.000
the
Token the
Feature activation+0.393
world
Token world
Feature activation+1.392
heart
Token heart
Feature activation+0.000
broken
Tokenbroken
Feature activation+1.528
on
Token on
Feature activation+0.450
Nov
Token Nov
Feature activation+0.000
.
Token.
Feature activation+0.000
30
Token 30
Feature activation+0.000
.
Token.
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
left
Token left
Feature activation+0.000
our
Token our
Feature activation+0.000
people
Token people
Feature activation+0.926
in
Token in
Feature activation+1.544
had
Token had
Feature activation+0.000
seen
Token seen
Feature activation+0.000
some
Token some
Feature activation+0.000
sparse
Token sparse
Feature activation+0.000
gunfire
Token gunfire
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
left
Token left
Feature activation+0.000
four
Token four
Feature activation+0.205
Americans
Token Americans
Feature activation+1.268
,
Token,
Feature activation+1.302
including
Token including
Feature activation+0.000
a
Token a
Feature activation+0.000
U
Token U
Feature activation+0.207
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.120
fight
Token fight
Feature activation+0.000
that
Token that
Feature activation+0.000
left
Token left
Feature activation+0.052
two
Token two
Feature activation+0.943
patrons
Token patrons
Feature activation+0.068
injured
Token injured
Feature activation+1.607
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
whom
Token whom
Feature activation+0.000
was
Token was
Feature activation+0.000
he
Token he
Feature activation+0.000
left
Token left
Feature activation+0.031
his
Token his
Feature activation+0.140
Kitchen
Token Kitchen
Feature activation+0.000
er
Tokener
Feature activation+0.000
home
Token home
Feature activation+1.377
on
Token on
Feature activation+1.262
a
Token a
Feature activation+0.000
bicycle
Token bicycle
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000

INTERVAL 0.966 - 1.288
CONTAINS 0.004%

the
Token the
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
left
Token left
Feature activation+0.000
a
Token a
Feature activation+0.000
hole
Token hole
Feature activation+1.976
at
Token at
Feature activation+1.170
corner
Token corner
Feature activation+0.000
for
Token for
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
disappears
Token disappears
Feature activation+0.000
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
're
Token're
Feature activation+0.000
left
Token left
Feature activation+0.000
feeling
Token feeling
Feature activation+1.138
whole
Token whole
Feature activation+0.000
and
Token and
Feature activation+0.000
fulfilled
Token fulfilled
Feature activation+0.000
doing
Token doing
Feature activation+0.000
and
Token and
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
left
Token left
Feature activation+0.000
them
Token them
Feature activation+0.435
on
Token on
Feature activation+1.314
for
Token for
Feature activation+1.074
about
Token about
Feature activation+0.000
five
Token five
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
before
Token before
Feature activation+0.000
real
Token real
Feature activation+0.000
left
Tokenleft
Feature activation+0.000
)
Token)
Feature activation+0.028
and
Token and
Feature activation+0.000
left
Token left
Feature activation+0.000
fielder
Token fielder
Feature activation+0.000
Shane
Token Shane
Feature activation+1.247
Peterson
Token Peterson
Feature activation+0.478
collide
Token collide
Feature activation+0.000
while
Token while
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Civil
Token Civil
Feature activation+0.000
War
Token War
Feature activation+0.000
left
Token left
Feature activation+0.000
an
Token an
Feature activation+0.299
enormous
Token enormous
Feature activation+1.079
imprint
Token imprint
Feature activation+2.104
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
consciousness
Token consciousness
Feature activation+0.000

INTERVAL 0.644 - 0.966
CONTAINS 0.006%

Chelsea
Token Chelsea
Feature activation+0.000
explosion
Token explosion
Feature activation+0.000
that
Token that
Feature activation+0.000
left
Token left
Feature activation+0.000
29
Token 29
Feature activation+0.000
people
Token people
Feature activation+0.845
hurt
Token hurt
Feature activation+2.071
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Bomb
TokenBomb
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
we
Token we
Feature activation+0.000
left
Token left
Feature activation+0.000
it
Token it
Feature activation+0.633
,
Token,
Feature activation+0.706
cover
Token cover
Feature activation+0.000
side
Token side
Feature activation+0.000
out
Token out
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
dodge
Token dodge
Feature activation+0.000
if
Token if
Feature activation+0.000
she
Token she
Feature activation+0.000
left
Token left
Feature activation+0.000
it
Token it
Feature activation+0.000
out
Token out
Feature activation+0.911
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
note
Token note
Feature activation+0.000
from
Token from
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
my
Token my
Feature activation+0.000
father
Token father
Feature activation+0.000
left
Token left
Feature activation+0.505
us
Token us
Feature activation+0.753
out
Token out
Feature activation+0.921
of
Token of
Feature activation+1.862
chau
Token chau
Feature activation+0.000
vin
Tokenvin
Feature activation+0.000
istic
Tokenistic
Feature activation+0.000
two
Token two
Feature activation+1.148
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
daughter
Token daughter
Feature activation+0.823
Ad
Token Ad
Feature activation+0.267
ri
Tokenri
Feature activation+0.000
anna
Tokenanna
Feature activation+0.364
alone
Token alone
Feature activation+1.350
in
Token in
Feature activation+0.000

INTERVAL 0.322 - 0.644
CONTAINS 0.010%

ents
Tokenents
Feature activation+0.000
also
Token also
Feature activation+0.000
left
Token left
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
a
Tokena
Feature activation+0.446
mysterious
Token mysterious
Feature activation+0.241
element
Token element
Feature activation+0.000
of
Token of
Feature activation+0.000
Scottish
Token Scottish
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
trolls
Token trolls
Feature activation+0.000
they
Token they
Feature activation+0.000
left
Token left
Feature activation+0.248
behind
Token behind
Feature activation+0.506
on
Token on
Feature activation+0.637
4
Token 4
Feature activation+0.000
chan
Tokenchan
Feature activation+0.000
have
Token have
Feature activation+0.000
seen
Token seen
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
either
Token either
Feature activation+0.000
left
Token left
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.623
the
Token the
Feature activation+0.644
presidential
Token presidential
Feature activation+0.000
debates
Token debates
Feature activation+0.162
and
Token and
Feature activation+0.005
campaigns
Token campaigns
Feature activation+0.000
that
Token that
Feature activation+0.000
left
Token left
Feature activation+0.000
me
Token me
Feature activation+0.766
so
Token so
Feature activation+0.655
sed
Token sed
Feature activation+0.804
ated
Tokenated
Feature activation+0.335
,
Token,
Feature activation+0.000
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
When
Token When
Feature activation+0.000
I
Token I
Feature activation+0.000
left
Token left
Feature activation+0.000
,
Token,
Feature activation+0.039
I
Token I
Feature activation+0.000
thought
Token thought
Feature activation+0.429
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
M
TokenM
Feature activation+0.000
m
Tokenm
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.322
CONTAINS 99.974%

Dianne
Token Dianne
Feature activation+0.000
Feinstein
Token Feinstein
Feature activation+0.000
or
Token or
Feature activation+0.000
some
Token some
Feature activation+0.000
Democrat
Token Democrat
Feature activation+0.000
of
Token of
Feature activation+0.000
stature
Token stature
Feature activation+0.000
has
Token has
Feature activation+0.000
the
Token the
Feature activation+0.000
decency
Token decency
Feature activation+0.000
to
Token to
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
dire
Token dire
Feature activation+0.000
predictions
Token predictions
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+0.000
and
Token and
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
phone
Token phone
Feature activation+0.000
with
Token with
Feature activation+0.000
self
Token self
Feature activation+0.000
-
Token-
Feature activation+0.000
identified
Tokenidentified
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
voters
Token voters
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
ile
Tokenile
Feature activation+0.000
an
Tokenan
Feature activation+0.000
President
Token President
Feature activation+0.000
Sebastian
Token Sebastian
Feature activation+0.000
Pi
Token Pi
Feature activation+0.000
ñ
Tokenñ
Feature activation+0.000
era
Tokenera
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
remarks
Token remarks
Feature activation+0.000
at
Token at
Feature activation+0.000
miles
Token miles
Feature activation+0.000
inland
Token inland
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
coast
Token coast
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Connecticut
Token Connecticut
Feature activation+0.000
River
Token River
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H2.8: (feature 1626)

TOP ACTIVATIONS
MAX = 2.877

interest
Token interest
Feature activation+0.000
,
Token,
Feature activation+0.000
do
Token do
Feature activation+0.000
yourself
Token yourself
Feature activation+0.687
a
Token a
Feature activation+0.680
favor
Token favor
Feature activation+2.877
and
Token and
Feature activation+0.113
head
Token head
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
International
Token International
Feature activation+0.000
badly
Token badly
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+0.000
wall
Token wall
Feature activation+0.000
with
Token with
Feature activation+2.602
him
Token him
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
liked
Token liked
Feature activation+0.000
him
Token him
Feature activation+0.000
right
Token right
Feature activation+1.856
thing
Token thing
Feature activation+2.090
to
Token to
Feature activation+2.333
do
Token do
Feature activation+0.000
which
Token which
Feature activation+0.174
is
Token is
Feature activation+2.421
to
Token to
Feature activation+0.947
put
Token put
Feature activation+0.000
ourselves
Token ourselves
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
deep
Token deep
Feature activation+0.000
prospect
Token prospect
Feature activation+0.000
pool
Token pool
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
talking
Token talking
Feature activation+2.369
rather
Token rather
Feature activation+0.845
than
Token than
Feature activation+1.213
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
splash
Token splash
Feature activation+0.000
us
Token us
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.742
things
Token things
Feature activation+2.345
that
Token that
Feature activation+1.441
we
Token we
Feature activation+0.321
used
Token used
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
medical
Tokenmedical
Feature activation+0.000
students
Token students
Feature activation+0.000
and
Token and
Feature activation+0.000
do
Token do
Feature activation+0.000
dinosaur
Token dinosaur
Feature activation+0.000
research
Token research
Feature activation+2.337
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
side
Token side
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
do
Token do
Feature activation+0.181
the
Token the
Feature activation+0.418
right
Token right
Feature activation+1.856
thing
Token thing
Feature activation+2.090
to
Token to
Feature activation+2.333
do
Token do
Feature activation+0.000
which
Token which
Feature activation+0.174
is
Token is
Feature activation+2.421
to
Token to
Feature activation+0.947
put
Token put
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
research
Token research
Feature activation+2.319
,
Token,
Feature activation+0.887
his
Token his
Feature activation+0.191
team
Token team
Feature activation+0.000
placed
Token placed
Feature activation+0.000
a
Token a
Feature activation+0.000
'
Token '
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
anything
Token anything
Feature activation+0.602
to
Token to
Feature activation+2.308
promote
Token promote
Feature activation+0.000
the
Token the
Feature activation+0.000
process
Token process
Feature activation+0.000
",
Token ",
Feature activation+0.000
will
Token will
Feature activation+0.000
't
Token't
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
NHL
Token NHL
Feature activation+0.000
any
Token any
Feature activation+0.682
favors
Token favors
Feature activation+2.286
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
cream
Token cream
Feature activation+0.000
would
Token would
Feature activation+0.000
rise
Token rise
Feature activation+0.000
acies
Tokenacies
Feature activation+0.000
do
Token do
Feature activation+0.000
some
Token some
Feature activation+0.482
of
Token of
Feature activation+1.009
the
Token the
Feature activation+0.608
things
Token things
Feature activation+2.270
they
Token they
Feature activation+0.913
do
Token do
Feature activation+0.674
,
Token,
Feature activation+0.952
and
Token and
Feature activation+0.663
obviously
Token obviously
Feature activation+0.000
abella
Tokenabella
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
away
Token away
Feature activation+0.000
with
Token with
Feature activation+2.264
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.387
political
Token political
Feature activation+0.019
adversaries
Token adversaries
Feature activation+0.000
won
Token won
Feature activation+0.000
't
Token't
Feature activation+0.000
actually
Token actually
Feature activation+0.000
do
Token do
Feature activation+0.000
much
Token much
Feature activation+0.000
to
Token to
Feature activation+2.226
stop
Token stop
Feature activation+0.000
any
Token any
Feature activation+0.000
harassment
Token harassment
Feature activation+0.000
,
Token,
Feature activation+0.000
since
Token since
Feature activation+0.000
who
Token who
Feature activation+0.000
will
Token will
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.524
to
Token to
Feature activation+2.207
limit
Token limit
Feature activation+0.000
its
Token its
Feature activation+0.000
excess
Token excess
Feature activation+0.000
es
Tokenes
Feature activation+0.000
dominated
Token dominated
Feature activation+0.000
were
Token were
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+1.053
research
Token research
Feature activation+2.207
they
Token they
Feature activation+0.000
would
Token would
Feature activation+0.155
discover
Token discover
Feature activation+0.000
that
Token that
Feature activation+0.000
Single
Token Single
Feature activation+0.000
be
Token be
Feature activation+0.000
doing
Token doing
Feature activation+0.000
us
Token us
Feature activation+0.000
a
Token a
Feature activation+0.326
huge
Token huge
Feature activation+0.000
favor
Token favor
Feature activation+2.192
!
Token!
Feature activation+0.000
The
Token The
Feature activation+0.000
more
Token more
Feature activation+0.000
people
Token people
Feature activation+0.000
we
Token we
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
do
Token do
Feature activation+0.000
all
Token all
Feature activation+0.724
the
Token the
Feature activation+0.975
things
Token things
Feature activation+2.191
you
Token you
Feature activation+0.776
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
looking
Token looking
Feature activation+0.000
commissioners
Token commissioners
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+1.586
thing
Token thing
Feature activation+2.129
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Editor
TokenEditor
Feature activation+0.000
's
Token's
Feature activation+0.000
less
Token less
Feature activation+0.010
energy
Token energy
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
with
Token with
Feature activation+2.125
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
new
Token new
Feature activation+0.000
system
Token system
Feature activation+0.000
works
Token works
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
will
Token will
Feature activation+0.000
do
Token do
Feature activation+0.000
little
Token little
Feature activation+0.446
to
Token to
Feature activation+2.098
reassure
Token reassure
Feature activation+0.000
a
Token a
Feature activation+0.000
growing
Token growing
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000

Top DFA by src position
MAX = 3.521

ed
Tokened
Feature activation+0.013
Top resid features:
your
Token your
Feature activation+0.005
Top resid features:
paranormal
Token paranormal
Feature activation+0.034
Top resid features:
interest
Token interest
Feature activation-0.020
Top resid features:
,
Token,
Feature activation-0.018
Top resid features:
do
Token do
Feature activation+3.417
Top resid features:
yourself
Token yourself
Feature activation+0.095
Top resid features:
a
Token a
Feature activation+0.825
Top resid features:
favor
Token favor
Feature activation+0.071
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
head
Token head
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.039
Top resid features:
I
Token I
Feature activation-0.004
Top resid features:
wanted
Token wanted
Feature activation-0.012
Top resid features:
badly
Token badly
Feature activation+0.069
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
do
Token do
Feature activation+3.165
Top resid features:
a
Token a
Feature activation+0.577
Top resid features:
wall
Token wall
Feature activation+0.406
Top resid features:
with
Token with
Feature activation+0.022
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.330
Top resid features:
the
Token the
Feature activation+0.040
Top resid features:
right
Token right
Feature activation+0.035
Top resid features:
thing
Token thing
Feature activation+0.026
Top resid features:
to
Token to
Feature activation+0.094
Top resid features:
do
Token do
Feature activation+2.456
Top resid features:
which
Token which
Feature activation+0.983
Top resid features:
is
Token is
Feature activation-0.013
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
put
Token put
Feature activation+0.000
Top resid features:
ourselves
Token ourselves
Feature activation+0.000
Top resid features:
let
Token let
Feature activation+0.022
Top resid features:
their
Token their
Feature activation+0.022
Top resid features:
deep
Token deep
Feature activation+0.001
Top resid features:
prospect
Token prospect
Feature activation+0.036
Top resid features:
pool
Token pool
Feature activation+0.127
Top resid features:
do
Token do
Feature activation+2.996
Top resid features:
the
Token the
Feature activation+0.715
Top resid features:
talking
Token talking
Feature activation+0.081
Top resid features:
rather
Token rather
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
ab
Tokenab
Feature activation-0.000
Top resid features:
ler
Tokenler
Feature activation-0.009
Top resid features:
for
Token for
Feature activation+0.037
Top resid features:
us
Token us
Feature activation+0.015
Top resid features:
to
Token to
Feature activation+0.025
Top resid features:
do
Token do
Feature activation+2.917
Top resid features:
the
Token the
Feature activation+0.424
Top resid features:
same
Token same
Feature activation+0.409
Top resid features:
things
Token things
Feature activation+0.066
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
teaching
Token teaching
Feature activation-0.010
Top resid features:
pre
Token pre
Feature activation+0.032
Top resid features:
medical
Tokenmedical
Feature activation-0.011
Top resid features:
students
Token students
Feature activation-0.028
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
do
Token do
Feature activation+3.230
Top resid features:
dinosaur
Token dinosaur
Feature activation+0.503
Top resid features:
research
Token research
Feature activation+0.154
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
side
Token side
Feature activation+0.000
Top resid features:
same
Token same
Feature activation+0.006
Top resid features:
things
Token things
Feature activation+0.015
Top resid features:
that
Token that
Feature activation+0.007
Top resid features:
he
Token he
Feature activation+0.037
Top resid features:
would
Token would
Feature activation-0.006
Top resid features:
do
Token do
Feature activation+2.619
Top resid features:
the
Token the
Feature activation+0.371
Top resid features:
right
Token right
Feature activation+0.195
Top resid features:
thing
Token thing
Feature activation+0.576
Top resid features:
to
Token to
Feature activation+0.062
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
dive
Token dive
Feature activation+0.018
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
To
TokenTo
Feature activation-0.043
Top resid features:
do
Token do
Feature activation+3.338
Top resid features:
the
Token the
Feature activation+0.596
Top resid features:
research
Token research
Feature activation+0.068
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
team
Token team
Feature activation+0.000
Top resid features:
them
Token them
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
'
Token '
Feature activation+0.007
Top resid features:
we
Token we
Feature activation+0.063
Top resid features:
can
Token can
Feature activation+0.070
Top resid features:
do
Token do
Feature activation+2.896
Top resid features:
anything
Token anything
Feature activation+0.855
Top resid features:
to
Token to
Feature activation+0.071
Top resid features:
promote
Token promote
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
process
Token process
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
1
Token1
Feature activation-0.001
Top resid features:
system
Token system
Feature activation-0.008
Top resid features:
wouldn
Token wouldn
Feature activation-0.009
Top resid features:
't
Token't
Feature activation+0.032
Top resid features:
do
Token do
Feature activation+2.709
Top resid features:
the
Token the
Feature activation+0.179
Top resid features:
NHL
Token NHL
Feature activation+0.239
Top resid features:
any
Token any
Feature activation+0.581
Top resid features:
favors
Token favors
Feature activation+0.129
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
understand
Token understand
Feature activation+0.002
Top resid features:
why
Token why
Feature activation+0.007
Top resid features:
government
Token government
Feature activation+0.014
Top resid features:
bureaucr
Token bureaucr
Feature activation+0.028
Top resid features:
acies
Tokenacies
Feature activation-0.040
Top resid features:
do
Token do
Feature activation+2.864
Top resid features:
some
Token some
Feature activation+0.153
Top resid features:
of
Token of
Feature activation+0.269
Top resid features:
the
Token the
Feature activation+0.527
Top resid features:
things
Token things
Feature activation+0.076
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
Queen
Token Queen
Feature activation-0.004
Top resid features:
Is
Token Is
Feature activation-0.005
Top resid features:
abella
Tokenabella
Feature activation-0.014
Top resid features:
wanted
Token wanted
Feature activation-0.004
Top resid features:
to
Token to
Feature activation-0.013
Top resid features:
do
Token do
Feature activation+3.521
Top resid features:
away
Token away
Feature activation+0.420
Top resid features:
with
Token with
Feature activation+0.006
Top resid features:
many
Token many
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:
that
Token that
Feature activation-0.001
Top resid features:
this
Token this
Feature activation+0.100
Top resid features:
won
Token won
Feature activation+0.006
Top resid features:
't
Token't
Feature activation+0.030
Top resid features:
actually
Token actually
Feature activation+0.012
Top resid features:
do
Token do
Feature activation+2.683
Top resid features:
much
Token much
Feature activation+0.958
Top resid features:
to
Token to
Feature activation+0.047
Top resid features:
stop
Token stop
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
harassment
Token harassment
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.009
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
and
Token and
Feature activation-0.018
Top resid features:
who
Token who
Feature activation+0.060
Top resid features:
will
Token will
Feature activation+0.009
Top resid features:
do
Token do
Feature activation+2.875
Top resid features:
the
Token the
Feature activation+0.501
Top resid features:
most
Token most
Feature activation+0.361
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
limit
Token limit
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
Trump
Token Trump
Feature activation-0.028
Top resid features:
administration
Token administration
Feature activation+0.004
Top resid features:
were
Token were
Feature activation-0.076
Top resid features:
to
Token to
Feature activation-0.060
Top resid features:
do
Token do
Feature activation+3.278
Top resid features:
a
Token a
Feature activation+0.404
Top resid features:
little
Token little
Feature activation+0.355
Top resid features:
research
Token research
Feature activation+0.099
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
forums
Token forums
Feature activation-0.033
Top resid features:
,
Token,
Feature activation-0.030
Top resid features:
you
Token you
Feature activation-0.019
Top resid features:
would
Token would
Feature activation+0.004
Top resid features:
be
Token be
Feature activation-0.015
Top resid features:
doing
Token doing
Feature activation+2.913
Top resid features:
us
Token us
Feature activation+0.164
Top resid features:
a
Token a
Feature activation+0.581
Top resid features:
huge
Token huge
Feature activation+0.229
Top resid features:
favor
Token favor
Feature activation+0.036
Top resid features:
!
Token!
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
they
Token they
Feature activation+0.012
Top resid features:
penetrate
Token penetrate
Feature activation+0.061
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
they
Token they
Feature activation+0.018
Top resid features:
do
Token do
Feature activation+2.682
Top resid features:
all
Token all
Feature activation+0.233
Top resid features:
the
Token the
Feature activation+0.685
Top resid features:
things
Token things
Feature activation+0.086
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
should
Token should
Feature activation+0.006
Top resid features:
urge
Token urge
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
commissioners
Token commissioners
Feature activation-0.026
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
do
Token do
Feature activation+2.896
Top resid features:
the
Token the
Feature activation+0.459
Top resid features:
right
Token right
Feature activation+0.306
Top resid features:
thing
Token thing
Feature activation+0.085
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
also
Token also
Feature activation-0.002
Top resid features:
significantly
Token significantly
Feature activation+0.036
Top resid features:
less
Token less
Feature activation+0.105
Top resid features:
energy
Token energy
Feature activation+0.055
Top resid features:
to
Token to
Feature activation-0.028
Top resid features:
do
Token do
Feature activation+2.750
Top resid features:
it
Token it
Feature activation+0.647
Top resid features:
with
Token with
Feature activation+0.048
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
This
Token This
Feature activation+0.000
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.016
Top resid features:
Ċ
TokenĊ
Feature activation-0.031
Top resid features:
Ċ
TokenĊ
Feature activation-0.027
Top resid features:
This
TokenThis
Feature activation+0.111
Top resid features:
will
Token will
Feature activation+0.004
Top resid features:
do
Token do
Feature activation+2.833
Top resid features:
little
Token little
Feature activation+0.806
Top resid features:
to
Token to
Feature activation+0.055
Top resid features:
reassure
Token reassure
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
growing
Token growing
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.02

Head 2: 0.08

Head 3: 0.07

Head 4: 0.03

Head 5: 0.06

Head 6: 0.02

Head 7: 0.02

Head 8: 0.51

Head 9: 0.06

Head 10: 0.05

Head 11: 0.03

Positive logits

utical1.76

advertising1.48

Abstract1.47

stals1.44

ña1.41

ylum1.38

Hogan1.36

idon1.35

ーク1.35

FORE1.33

Fax1.33

heric1.30

andowski1.29

sis1.28

osure1.28

asso1.28

amazon1.26

RW1.26

flourish1.26

ADS1.25

Negative logits

Tru-1.56

cancell-1.46

descended-1.33

ented-1.32

Rebell-1.30

scrapped-1.28

Dwell-1.28

cab-1.27

accus-1.26

leader-1.25

crew-1.24

Chev-1.23

sshd-1.23

acted-1.21

Chosen-1.20

itted-1.19

liner-1.19

suppressed-1.19

dwell-1.19

angered-1.19

INTERVAL 2.589 - 2.877
CONTAINS 0.000%

interest
Token interest
Feature activation+0.000
,
Token,
Feature activation+0.000
do
Token do
Feature activation+0.000
yourself
Token yourself
Feature activation+0.687
a
Token a
Feature activation+0.680
favor
Token favor
Feature activation+2.877
and
Token and
Feature activation+0.113
head
Token head
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
International
Token International
Feature activation+0.000
badly
Token badly
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+0.000
wall
Token wall
Feature activation+0.000
with
Token with
Feature activation+2.602
him
Token him
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
liked
Token liked
Feature activation+0.000
him
Token him
Feature activation+0.000

INTERVAL 2.302 - 2.589
CONTAINS 0.001%

medical
Tokenmedical
Feature activation+0.000
students
Token students
Feature activation+0.000
and
Token and
Feature activation+0.000
do
Token do
Feature activation+0.000
dinosaur
Token dinosaur
Feature activation+0.000
research
Token research
Feature activation+2.337
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
side
Token side
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
'
Token '
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
anything
Token anything
Feature activation+0.602
to
Token to
Feature activation+2.308
promote
Token promote
Feature activation+0.000
the
Token the
Feature activation+0.000
process
Token process
Feature activation+0.000
",
Token ",
Feature activation+0.000
will
Token will
Feature activation+0.000
deep
Token deep
Feature activation+0.000
prospect
Token prospect
Feature activation+0.000
pool
Token pool
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
talking
Token talking
Feature activation+2.369
rather
Token rather
Feature activation+0.845
than
Token than
Feature activation+1.213
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
splash
Token splash
Feature activation+0.000
right
Token right
Feature activation+1.856
thing
Token thing
Feature activation+2.090
to
Token to
Feature activation+2.333
do
Token do
Feature activation+0.000
which
Token which
Feature activation+0.174
is
Token is
Feature activation+2.421
to
Token to
Feature activation+0.947
put
Token put
Feature activation+0.000
ourselves
Token ourselves
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
would
Token would
Feature activation+0.000
do
Token do
Feature activation+0.181
the
Token the
Feature activation+0.418
right
Token right
Feature activation+1.856
thing
Token thing
Feature activation+2.090
to
Token to
Feature activation+2.333
do
Token do
Feature activation+0.000
which
Token which
Feature activation+0.174
is
Token is
Feature activation+2.421
to
Token to
Feature activation+0.947
put
Token put
Feature activation+0.000

INTERVAL 2.014 - 2.302
CONTAINS 0.002%

acies
Tokenacies
Feature activation+0.000
do
Token do
Feature activation+0.000
some
Token some
Feature activation+0.482
of
Token of
Feature activation+1.009
the
Token the
Feature activation+0.608
things
Token things
Feature activation+2.270
they
Token they
Feature activation+0.913
do
Token do
Feature activation+0.674
,
Token,
Feature activation+0.952
and
Token and
Feature activation+0.663
obviously
Token obviously
Feature activation+0.000
abella
Tokenabella
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
away
Token away
Feature activation+0.000
with
Token with
Feature activation+2.264
many
Token many
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.387
political
Token political
Feature activation+0.019
adversaries
Token adversaries
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
do
Token do
Feature activation+0.000
what
Token what
Feature activation+0.639
is
Token is
Feature activation+2.027
only
Token only
Feature activation+0.218
natural
Token natural
Feature activation+0.000
;
Token;
Feature activation+0.000
they
Token they
Feature activation+0.000
close
Token close
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
do
Token do
Feature activation+0.000
all
Token all
Feature activation+0.724
the
Token the
Feature activation+0.975
things
Token things
Feature activation+2.191
you
Token you
Feature activation+0.776
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
looking
Token looking
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
will
Token will
Feature activation+0.000
do
Token do
Feature activation+0.000
little
Token little
Feature activation+0.446
to
Token to
Feature activation+2.098
reassure
Token reassure
Feature activation+0.000
a
Token a
Feature activation+0.000
growing
Token growing
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.726 - 2.014
CONTAINS 0.003%

would
Token would
Feature activation+0.000
try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
away
Token away
Feature activation+0.000
with
Token with
Feature activation+2.003
a
Token a
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.250
ĺ
Tokenĺ
Feature activation+0.000
Z
TokenZ
Feature activation+0.000
ion
Tokenion
Feature activation+0.000
an
Token an
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
more
Token more
Feature activation+0.428
to
Token to
Feature activation+1.889
strengthen
Token strengthen
Feature activation+0.000
the
Token the
Feature activation+0.000
links
Token links
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
industry
Token industry
Feature activation+0.000
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
more
Token more
Feature activation+0.494
to
Token to
Feature activation+1.834
help
Token help
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
housing
Token housing
Feature activation+0.000
crisis
Token crisis
Feature activation+0.000
ley
Tokenley
Feature activation+0.000
Cooper
Token Cooper
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
it
Token it
Feature activation+0.117
all
Token all
Feature activation+1.815
,
Token,
Feature activation+0.224
from
Token from
Feature activation+0.000
comedy
Token comedy
Feature activation+0.000
(
Token (
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Las
Token Las
Feature activation+0.000
Vegas
Token Vegas
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
promotional
Token promotional
Feature activation+0.000
work
Token work
Feature activation+1.980
decides
Token decides
Feature activation+0.000
to
Token to
Feature activation+0.000
strap
Token strap
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.439 - 1.726
CONTAINS 0.007%

expect
Token expect
Feature activation+0.000
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+1.454
more
Token more
Feature activation+1.468
of
Token of
Feature activation+1.176
that
Token that
Feature activation+0.929
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
else
Token else
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+0.119
better
Token better
Feature activation+1.857
job
Token job
Feature activation+1.657
of
Token of
Feature activation+0.436
decoding
Token decoding
Feature activation+0.312
it
Token it
Feature activation+0.000
than
Token than
Feature activation+0.451
me
Token me
Feature activation+0.000
atheists
Token atheists
Feature activation+0.000
hoping
Token hoping
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
some
Token some
Feature activation+0.145
good
Token good
Feature activation+1.636
in
Token in
Feature activation+1.305
the
Token the
Feature activation+0.287
world
Token world
Feature activation+0.000
together
Token together
Feature activation+0.485
.
Token.
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
doing
Token doing
Feature activation+0.000
too
Token too
Feature activation+0.000
many
Token many
Feature activation+0.359
things
Token things
Feature activation+1.497
,
Token,
Feature activation+0.251
it
Token it
Feature activation+0.191
âĢ
TokenâĢ
Feature activation+0.095
Ļ
TokenĻ
Feature activation+0.013
s
Tokens
Feature activation+0.063
also
Token also
Feature activation+0.000
there
Token there
Feature activation+0.000
doing
Token doing
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.327
thing
Token thing
Feature activation+1.496
,
Token,
Feature activation+0.289
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000

INTERVAL 1.151 - 1.439
CONTAINS 0.012%

,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
this
Token this
Feature activation+0.275
in
Token in
Feature activation+1.231
your
Token your
Feature activation+0.389
yard
Token yard
Feature activation+0.000
or
Token or
Feature activation+0.285
neighborhood
Token neighborhood
Feature activation+0.000
,
Token,
Feature activation+0.000
7
Token7
Feature activation+0.000
]
Token]
Feature activation+0.000
would
Token would
Feature activation+0.000
it
Token it
Feature activation+0.000
do
Token do
Feature activation+0.090
to
Token to
Feature activation+1.157
simply
Token simply
Feature activation+0.000
leave
Token leave
Feature activation+0.000
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
present
Token present
Feature activation+0.000
month
Token month
Feature activation+0.034
.
Token.
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
does
Token does
Feature activation+0.000
it
Token it
Feature activation+0.220
just
Token just
Feature activation+1.324
as
Token as
Feature activation+0.422
regularly
Token regularly
Feature activation+0.188
,
Token,
Feature activation+0.028
but
Token but
Feature activation+0.277
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
do
Tokendo
Feature activation+0.000
more
Token more
Feature activation+0.000
good
Token good
Feature activation+1.415
elsewhere
Token elsewhere
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+0.000
anything
Token anything
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
with
Token with
Feature activation+1.369
the
Token the
Feature activation+0.000
decision
Token decision
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.863 - 1.151
CONTAINS 0.018%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
do
Token do
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+1.012
inform
Token inform
Feature activation+0.000
women
Token women
Feature activation+0.000
about
Token about
Feature activation+0.000
certain
Token certain
Feature activation+0.000
aspects
Token aspects
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
doing
Token doing
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+1.025
job
Token job
Feature activation+0.950
(
Token (
Feature activation+0.000
25
Token25
Feature activation+0.000
percent
Token percent
Feature activation+0.000
),
Token),
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
actually
Token actually
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
procedural
Token procedural
Feature activation+1.033
steps
Token steps
Feature activation+0.559
fairly
Token fairly
Feature activation+0.213
mechanically
Token mechanically
Feature activation+0.041
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
doing
Token doing
Feature activation+0.000
what
Token what
Feature activation+0.065
I
Token I
Feature activation+1.040
can
Token can
Feature activation+1.153
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Someone
TokenSomeone
Feature activation+0.000
who
Token who
Feature activation+0.000
does
Token does
Feature activation+0.000
a
Token a
Feature activation+0.000
thing
Token thing
Feature activation+1.080
like
Token like
Feature activation+0.015
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.535
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.575 - 0.863
CONTAINS 0.027%

that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.000
got
Token got
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
less
Token less
Feature activation+0.592
of
Token of
Feature activation+0.258
with
Token with
Feature activation+1.908
somebody
Token somebody
Feature activation+0.000
like
Token like
Feature activation+0.000
Thor
Token Thor
Feature activation+0.000
because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
what
Token what
Feature activation+0.000
I
Token I
Feature activation+0.000
do
Token do
Feature activation+0.080
for
Token for
Feature activation+0.776
a
Token a
Feature activation+0.000
living
Token living
Feature activation+0.000
,
Token,
Feature activation+0.077
and
Token and
Feature activation+0.021
as
Token as
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.223
that
Token that
Feature activation+0.617
without
Token without
Feature activation+0.595
him
Token him
Feature activation+0.000
.''
Token.''
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
They
TokenThey
Feature activation+0.000
the
Token the
Feature activation+0.608
things
Token things
Feature activation+2.270
they
Token they
Feature activation+0.913
do
Token do
Feature activation+0.674
,
Token,
Feature activation+0.952
and
Token and
Feature activation+0.663
obviously
Token obviously
Feature activation+0.000
that
Token that
Feature activation+0.000
includes
Token includes
Feature activation+0.000
the
Token the
Feature activation+0.000
Food
Token Food
Feature activation+0.000
agency
Token agency
Feature activation+0.000
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
done
Token done
Feature activation+0.000
more
Token more
Feature activation+0.000
to
Token to
Feature activation+0.677
hurt
Token hurt
Feature activation+0.000
consumers
Token consumers
Feature activation+0.000
than
Token than
Feature activation+0.000
help
Token help
Feature activation+0.000
them
Token them
Feature activation+0.000

INTERVAL 0.288 - 0.575
CONTAINS 0.047%

what
Token what
Feature activation+0.761
they
Token they
Feature activation+1.102
want
Token want
Feature activation+0.544
so
Token so
Feature activation+0.117
it
Token it
Feature activation+0.000
can
Token can
Feature activation+0.470
br
Token br
Feature activation+0.000
ag
Tokenag
Feature activation+0.000
about
Token about
Feature activation+0.000
a
Token a
Feature activation+0.000
historic
Token historic
Feature activation+0.000
But
Token But
Feature activation+0.000
what
Token what
Feature activation+0.000
we
Token we
Feature activation+0.000
do
Token do
Feature activation+0.000
know
Token know
Feature activation+0.856
is
Token is
Feature activation+0.323
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Hus
Token Hus
Feature activation+0.000
kies
Tokenkies
Feature activation+0.000
are
Token are
Feature activation+0.059
immediate
Token immediate
Feature activation+0.000
grades
Token grades
Feature activation+0.000
we
Token we
Feature activation+0.000
all
Token all
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.350
minute
Token minute
Feature activation+0.000
a
Token a
Feature activation+0.342
player
Token player
Feature activation+0.000
is
Token is
Feature activation+1.620
picked
Token picked
Feature activation+0.000
moment
Token moment
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
do
Token do
Feature activation+0.000
,
Token,
Feature activation+0.829
organized
Token organized
Feature activation+0.339
crime
Token crime
Feature activation+0.440
will
Token will
Feature activation+0.000
come
Token come
Feature activation+0.000
after
Token after
Feature activation+0.000
us
Token us
Feature activation+0.000
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.112
with
Token with
Feature activation+1.705
it
Token it
Feature activation+0.161
,
Token,
Feature activation+0.289
and
Token and
Feature activation+0.066
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

INTERVAL 0.000 - 0.288
CONTAINS 99.883%

the
Token the
Feature activation+0.000
Christian
Token Christian
Feature activation+0.000
Social
Token Social
Feature activation+0.000
Union
Token Union
Feature activation+0.000
(
Token (
Feature activation+0.000
CS
TokenCS
Feature activation+0.000
U
TokenU
Feature activation+0.000
),
Token),
Feature activation+0.000
were
Token were
Feature activation+0.000
just
Token just
Feature activation+0.000
per
Token per
Feature activation+0.000
[
Token [
Feature activation+0.000
_
Token_
Feature activation+0.000
2
Token2
Feature activation+0.000
_
Token_
Feature activation+0.000
]
Token]
Feature activation+0.000
.
Token .
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
If
TokenIf
Feature activation+0.000
the
Token the
Feature activation+0.000
proposed
Token proposed
Feature activation+0.000
bipartisan
Token bipartisan
Feature activation+0.000
accused
Token accused
Feature activation+0.000
US
Token US
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
services
Token services
Feature activation+0.000
of
Token of
Feature activation+0.000
giving
Token giving
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000
green
Tokengreen
Feature activation+0.000
light
Token light
Feature activation+0.000
for
Token for
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
tables
Token tables
Feature activation+0.000
are
Token are
Feature activation+0.000
here
Token here
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
great
Token great
Feature activation+0.000
mysteries
Token mysteries
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
it
Token it
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
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 H2.8: (feature 12215)

TOP ACTIVATIONS
MAX = 4.525

to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
their
Token their
Feature activation+0.265
Islam
Token Islam
Feature activation+0.495
a
Token a
Feature activation+0.454
secret
Token secret
Feature activation+4.525
in
Token in
Feature activation+0.951
the
Token the
Feature activation+0.072
beginning
Token beginning
Feature activation+0.000
for
Token for
Feature activation+0.008
fear
Token fear
Feature activation+0.000
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.246
numbers
Token numbers
Feature activation+0.659
secret
Token secret
Feature activation+4.448
is
Token is
Feature activation+0.538
just
Token just
Feature activation+0.320
one
Token one
Feature activation+0.000
in
Token in
Feature activation+0.011
a
Token a
Feature activation+0.000
say
Token say
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.358
world
Token world
Feature activation+0.518
safe
Token safe
Feature activation+4.384
from
Token from
Feature activation+0.000
Iran
Token Iran
Feature activation+0.144
's
Token's
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
ambitions
Token ambitions
Feature activation+0.000
an
Token an
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
patients
Token patients
Feature activation+1.521
safe
Token safe
Feature activation+4.264
from
Token from
Feature activation+0.000
aerial
Token aerial
Feature activation+0.000
and
Token and
Feature activation+0.147
artillery
Token artillery
Feature activation+0.000
bombardment
Token bombardment
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
my
Token my
Feature activation+1.007
family
Token family
Feature activation+0.721
safe
Token safe
Feature activation+4.244
.
Token.
Feature activation+0.027
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
proud
Token proud
Feature activation+0.000
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
you
Token you
Feature activation+0.464
posted
Token posted
Feature activation+4.223
on
Token on
Feature activation+0.737
how
Token how
Feature activation+0.000
that
Token that
Feature activation+0.000
works
Token works
Feature activation+0.000
out
Token out
Feature activation+0.000
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
the
Token the
Feature activation+0.709
streets
Token streets
Feature activation+0.523
safe
Token safe
Feature activation+4.204
for
Token for
Feature activation+1.603
all
Token all
Feature activation+0.000
New
Token New
Feature activation+0.000
Yorkers
Token Yorkers
Feature activation+0.000
.
Token.
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
keep
Token keep
Feature activation+0.000
your
Token your
Feature activation+0.888
house
Token house
Feature activation+2.366
safe
Token safe
Feature activation+4.099
,
Token,
Feature activation+1.111
especially
Token especially
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
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
my
Token my
Feature activation+0.447
options
Token options
Feature activation+0.000
open
Token open
Feature activation+4.029
because
Token because
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
still
Token still
Feature activation+0.000
like
Token like
Feature activation+0.000
information
Tokeninformation
Feature activation+0.000
laws
Token laws
Feature activation+0.000
help
Token help
Feature activation+0.000
keep
Token keep
Feature activation+0.000
governments
Token governments
Feature activation+0.100
honest
Token honest
Feature activation+4.012
and
Token and
Feature activation+0.793
First
Token First
Feature activation+0.012
Nations
Token Nations
Feature activation+0.000
governments
Token governments
Feature activation+0.100
are
Token are
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
a
Token a
Feature activation+0.000
low
Token low
Feature activation+3.117
profile
Token profile
Feature activation+3.961
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Davis
TokenDavis
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
those
Token those
Feature activation+0.000
other
Token other
Feature activation+0.126
unions
Token unions
Feature activation+1.113
neutral
Token neutral
Feature activation+3.914
.
Token.
Feature activation+0.042
Any
Token Any
Feature activation+0.000
word
Token word
Feature activation+0.000
on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
s
Tokens
Feature activation+0.000
ability
Token ability
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
informed
Token informed
Feature activation+3.870
has
Token has
Feature activation+0.178
slipped
Token slipped
Feature activation+0.000
among
Token among
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
and
Token and
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
page
Token page
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
yourself
Token yourself
Feature activation+0.235
updated
Token updated
Feature activation+3.825
on
Token on
Feature activation+2.077
all
Token all
Feature activation+0.413
the
Token the
Feature activation+0.090
latest
Token latest
Feature activation+0.444
from
Token from
Feature activation+0.241
"
Token"
Feature activation+0.000
That
TokenThat
Feature activation+0.000
's
Token's
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
them
Token them
Feature activation+0.319
honest
Token honest
Feature activation+3.750
in
Token in
Feature activation+1.428
a
Token a
Feature activation+0.477
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.452
places
Token places
Feature activation+0.401
scramble
Token scramble
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
their
Token their
Feature activation+0.248
data
Token data
Feature activation+0.842
secure
Token secure
Feature activation+3.736
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Super
TokenSuper
Feature activation+0.000
fish
Tokenfish
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
our
Token our
Feature activation+0.018
journalism
Token journalism
Feature activation+1.642
open
Token open
Feature activation+3.728
and
Token and
Feature activation+0.000
accessible
Token accessible
Feature activation+2.685
and
Token and
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+0.000
out
Token out
Feature activation+0.000
there
Token there
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
me
Token me
Feature activation+0.986
busy
Token busy
Feature activation+3.672
writing
Token writing
Feature activation+1.727
,
Token,
Feature activation+0.379
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
but
Token but
Feature activation+0.000
we
Token we
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
you
Token you
Feature activation+0.737
updated
Token updated
Feature activation+3.651
on
Token on
Feature activation+1.797
ther
Token ther
Feature activation+0.000
stuff
Token stuff
Feature activation+0.000
)
Token)
Feature activation+0.171
.
Token .
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.381
rest
Token rest
Feature activation+0.112
of
Token of
Feature activation+1.600
us
Token us
Feature activation+0.874
alive
Token alive
Feature activation+3.640
and
Token and
Feature activation+0.000
well
Token well
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Since
TokenSince
Feature activation+0.000

Top DFA by src position
MAX = 5.419

to
Token to
Feature activation-0.008
Top resid features:
Islam
Token Islam
Feature activation+0.007
Top resid features:
were
Token were
Feature activation-0.021
Top resid features:
forced
Token forced
Feature activation+0.055
Top resid features:
to
Token to
Feature activation-0.046
Top resid features:
keep
Token keep
Feature activation+5.238
Top resid features:
their
Token their
Feature activation+0.124
Top resid features:
Islam
Token Islam
Feature activation+0.247
Top resid features:
a
Token a
Feature activation+0.374
Top resid features:
secret
Token secret
Feature activation+0.114
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
The
TokenThe
Feature activation+0.020
Top resid features:
decision
Token decision
Feature activation+0.018
Top resid features:
to
Token to
Feature activation-0.078
Top resid features:
keep
Token keep
Feature activation+5.419
Top resid features:
the
Token the
Feature activation+0.453
Top resid features:
numbers
Token numbers
Feature activation+0.237
Top resid features:
secret
Token secret
Feature activation+0.196
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.023
Top resid features:
his
Token his
Feature activation+0.012
Top resid features:
supporters
Token supporters
Feature activation+0.015
Top resid features:
say
Token say
Feature activation+0.036
Top resid features:
will
Token will
Feature activation+0.016
Top resid features:
keep
Token keep
Feature activation+4.997
Top resid features:
the
Token the
Feature activation+0.303
Top resid features:
world
Token world
Feature activation+0.524
Top resid features:
safe
Token safe
Feature activation+0.182
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
Iran
Token Iran
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
in
Token in
Feature activation+0.028
Top resid features:
an
Token an
Feature activation+0.020
Top resid features:
attempt
Token attempt
Feature activation+0.039
Top resid features:
to
Token to
Feature activation-0.057
Top resid features:
keep
Token keep
Feature activation+5.083
Top resid features:
patients
Token patients
Feature activation+0.461
Top resid features:
safe
Token safe
Feature activation+0.219
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
aerial
Token aerial
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
NRA
Token NRA
Feature activation+0.010
Top resid features:
gear
Token gear
Feature activation+0.028
Top resid features:
I
Token I
Feature activation+0.034
Top resid features:
need
Token need
Feature activation+0.040
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
keep
Token keep
Feature activation+5.024
Top resid features:
my
Token my
Feature activation+0.274
Top resid features:
family
Token family
Feature activation+0.253
Top resid features:
safe
Token safe
Feature activation+0.203
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
future
Token future
Feature activation+0.023
Top resid features:
employment
Token employment
Feature activation+0.009
Top resid features:
.
Token.
Feature activation-0.054
Top resid features:
I
Token I
Feature activation+0.038
Top resid features:
will
Token will
Feature activation+0.009
Top resid features:
keep
Token keep
Feature activation+5.021
Top resid features:
you
Token you
Feature activation+0.573
Top resid features:
posted
Token posted
Feature activation+0.295
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
how
Token how
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
important
Token important
Feature activation+0.023
Top resid features:
their
Token their
Feature activation+0.001
Top resid features:
participation
Token participation
Feature activation-0.007
Top resid features:
is
Token is
Feature activation+0.010
Top resid features:
in
Token in
Feature activation-0.023
Top resid features:
keeping
Token keeping
Feature activation+4.837
Top resid features:
the
Token the
Feature activation+0.280
Top resid features:
streets
Token streets
Feature activation+0.450
Top resid features:
safe
Token safe
Feature activation+0.189
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
reported
Token reported
Feature activation+0.032
Top resid features:
about
Token about
Feature activation+0.032
Top resid features:
how
Token how
Feature activation+0.015
Top resid features:
you
Token you
Feature activation-0.014
Top resid features:
can
Token can
Feature activation-0.001
Top resid features:
keep
Token keep
Feature activation+5.090
Top resid features:
your
Token your
Feature activation+0.196
Top resid features:
house
Token house
Feature activation+0.281
Top resid features:
safe
Token safe
Feature activation+0.184
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
especially
Token especially
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation-0.009
Top resid features:
Obviously
TokenObviously
Feature activation+0.001
Top resid features:
I
Token I
Feature activation+0.012
Top resid features:
need
Token need
Feature activation+0.031
Top resid features:
to
Token to
Feature activation-0.027
Top resid features:
keep
Token keep
Feature activation+4.775
Top resid features:
my
Token my
Feature activation+0.318
Top resid features:
options
Token options
Feature activation+0.489
Top resid features:
open
Token open
Feature activation+0.210
Top resid features:
because
Token because
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
to
Tokento
Feature activation+0.001
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
information
Tokeninformation
Feature activation+0.014
Top resid features:
laws
Token laws
Feature activation+0.058
Top resid features:
help
Token help
Feature activation-0.020
Top resid features:
keep
Token keep
Feature activation+4.862
Top resid features:
governments
Token governments
Feature activation+0.449
Top resid features:
honest
Token honest
Feature activation+0.254
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
First
Token First
Feature activation+0.000
Top resid features:
Nations
Token Nations
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
She
Token She
Feature activation+0.027
Top resid features:
just
Token just
Feature activation+0.035
Top resid features:
wants
Token wants
Feature activation+0.020
Top resid features:
to
Token to
Feature activation-0.037
Top resid features:
keep
Token keep
Feature activation+4.737
Top resid features:
a
Token a
Feature activation+0.419
Top resid features:
low
Token low
Feature activation+0.268
Top resid features:
profile
Token profile
Feature activation+0.104
Top resid features:
."
Token."
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
agree
Token agree
Feature activation+0.029
Top resid features:
we
Token we
Feature activation+0.017
Top resid features:
should
Token should
Feature activation+0.005
Top resid features:
push
Token push
Feature activation+0.120
Top resid features:
to
Token to
Feature activation-0.026
Top resid features:
keep
Token keep
Feature activation+4.445
Top resid features:
those
Token those
Feature activation+0.157
Top resid features:
other
Token other
Feature activation+0.438
Top resid features:
unions
Token unions
Feature activation+0.351
Top resid features:
neutral
Token neutral
Feature activation+0.154
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.015
Top resid features:
Ļ
TokenĻ
Feature activation-0.007
Top resid features:
s
Tokens
Feature activation-0.004
Top resid features:
ability
Token ability
Feature activation-0.045
Top resid features:
to
Token to
Feature activation-0.035
Top resid features:
keep
Token keep
Feature activation+4.837
Top resid features:
Americans
Token Americans
Feature activation+0.367
Top resid features:
informed
Token informed
Feature activation+0.326
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
slipped
Token slipped
Feature activation+0.000
Top resid features:
among
Token among
Feature activation+0.000
Top resid features:
join
Token join
Feature activation+0.055
Top resid features:
our
Token our
Feature activation+0.033
Top resid features:
Facebook
Token Facebook
Feature activation+0.045
Top resid features:
page
Token page
Feature activation+0.056
Top resid features:
to
Token to
Feature activation-0.060
Top resid features:
keep
Token keep
Feature activation+4.476
Top resid features:
yourself
Token yourself
Feature activation+0.606
Top resid features:
updated
Token updated
Feature activation+0.283
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
"
Token"
Feature activation+0.018
Top resid features:
That
TokenThat
Feature activation+0.038
Top resid features:
's
Token's
Feature activation-0.025
Top resid features:
keeping
Token keeping
Feature activation+4.608
Top resid features:
them
Token them
Feature activation+0.462
Top resid features:
honest
Token honest
Feature activation+0.239
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
lot
Token lot
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.020
Top resid features:
have
Token have
Feature activation+0.031
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
scramble
Token scramble
Feature activation+0.083
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
keep
Token keep
Feature activation+4.249
Top resid features:
their
Token their
Feature activation+0.347
Top resid features:
data
Token data
Feature activation+0.514
Top resid features:
secure
Token secure
Feature activation+0.203
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
wall
Tokenwall
Feature activation+0.031
Top resid features:
.
Token.
Feature activation+0.029
Top resid features:
We
Token We
Feature activation+0.016
Top resid features:
want
Token want
Feature activation+0.016
Top resid features:
to
Token to
Feature activation-0.057
Top resid features:
keep
Token keep
Feature activation+4.450
Top resid features:
our
Token our
Feature activation+0.322
Top resid features:
journalism
Token journalism
Feature activation+0.264
Top resid features:
open
Token open
Feature activation+0.166
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
accessible
Token accessible
Feature activation+0.000
Top resid features:
material
Token material
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.007
Top resid features:
out
Token out
Feature activation+0.054
Top resid features:
there
Token there
Feature activation+0.106
Top resid features:
to
Token to
Feature activation-0.113
Top resid features:
keep
Token keep
Feature activation+4.328
Top resid features:
me
Token me
Feature activation+0.616
Top resid features:
busy
Token busy
Feature activation+0.320
Top resid features:
writing
Token writing
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
game
Token game
Feature activation-0.002
Top resid features:
(
Token (
Feature activation+0.033
Top resid features:
but
Token but
Feature activation+0.001
Top resid features:
we
Token we
Feature activation+0.049
Top resid features:
will
Token will
Feature activation-0.031
Top resid features:
keep
Token keep
Feature activation+4.489
Top resid features:
you
Token you
Feature activation+0.531
Top resid features:
updated
Token updated
Feature activation+0.303
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
ther
Token ther
Feature activation+0.000
Top resid features:
stuff
Token stuff
Feature activation+0.000
Top resid features:
could
Token could
Feature activation+0.012
Top resid features:
allocate
Token allocate
Feature activation+0.032
Top resid features:
some
Token some
Feature activation+0.040
Top resid features:
profits
Token profits
Feature activation+0.036
Top resid features:
to
Token to
Feature activation-0.034
Top resid features:
keep
Token keep
Feature activation+4.374
Top resid features:
the
Token the
Feature activation+0.115
Top resid features:
rest
Token rest
Feature activation+0.085
Top resid features:
of
Token of
Feature activation+0.068
Top resid features:
us
Token us
Feature activation+0.432
Top resid features:
alive
Token alive
Feature activation+0.256
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.02

Head 2: 0.04

Head 3: 0.07

Head 4: 0.04

Head 5: 0.07

Head 6: 0.03

Head 7: 0.03

Head 8: 0.51

Head 9: 0.05

Head 10: 0.05

Head 11: 0.03

Positive logits

sterile1.38

Marketable1.29

Sustainable1.25

tightly1.25

rift1.25

atonin1.24

cium1.24

Nightmares1.23

biod1.20

Hes1.18

Rey1.18

Tight1.17

Shine1.16

Records1.15

Satellite1.15

Healthy1.15

afloat1.14

ysis1.13

Awakens1.13

steady1.12

Negative logits

aru-1.35

Latin-1.30

illon-1.25

assault-1.24

ajo-1.22

major-1.21

METHOD-1.20

interstitial-1.20

LER-1.19

-1.18

lot-1.14

IAL-1.14

drop-1.13

etz-1.13

ricanes-1.13

asus-1.13

bern-1.12

Lt-1.12

Marsh-1.12

je-1.12

INTERVAL 4.073 - 4.525
CONTAINS 0.001%

.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
you
Token you
Feature activation+0.464
posted
Token posted
Feature activation+4.223
on
Token on
Feature activation+0.737
how
Token how
Feature activation+0.000
that
Token that
Feature activation+0.000
works
Token works
Feature activation+0.000
out
Token out
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
my
Token my
Feature activation+1.007
family
Token family
Feature activation+0.721
safe
Token safe
Feature activation+4.244
.
Token.
Feature activation+0.027
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
proud
Token proud
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.358
world
Token world
Feature activation+0.518
safe
Token safe
Feature activation+4.384
from
Token from
Feature activation+0.000
Iran
Token Iran
Feature activation+0.144
's
Token's
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
ambitions
Token ambitions
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
their
Token their
Feature activation+0.265
Islam
Token Islam
Feature activation+0.495
a
Token a
Feature activation+0.454
secret
Token secret
Feature activation+4.525
in
Token in
Feature activation+0.951
the
Token the
Feature activation+0.072
beginning
Token beginning
Feature activation+0.000
for
Token for
Feature activation+0.008
fear
Token fear
Feature activation+0.000
an
Token an
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
patients
Token patients
Feature activation+1.521
safe
Token safe
Feature activation+4.264
from
Token from
Feature activation+0.000
aerial
Token aerial
Feature activation+0.000
and
Token and
Feature activation+0.147
artillery
Token artillery
Feature activation+0.000
bombardment
Token bombardment
Feature activation+0.000

INTERVAL 3.620 - 4.073
CONTAINS 0.001%

to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
those
Token those
Feature activation+0.000
other
Token other
Feature activation+0.126
unions
Token unions
Feature activation+1.113
neutral
Token neutral
Feature activation+3.914
.
Token.
Feature activation+0.042
Any
Token Any
Feature activation+0.000
word
Token word
Feature activation+0.000
on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
our
Token our
Feature activation+0.018
journalism
Token journalism
Feature activation+1.642
open
Token open
Feature activation+3.728
and
Token and
Feature activation+0.000
accessible
Token accessible
Feature activation+2.685
and
Token and
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.381
rest
Token rest
Feature activation+0.112
of
Token of
Feature activation+1.600
us
Token us
Feature activation+0.874
alive
Token alive
Feature activation+3.640
and
Token and
Feature activation+0.000
well
Token well
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Since
TokenSince
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
a
Token a
Feature activation+0.000
low
Token low
Feature activation+3.117
profile
Token profile
Feature activation+3.961
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Davis
TokenDavis
Feature activation+0.000
,
Token,
Feature activation+0.000
information
Tokeninformation
Feature activation+0.000
laws
Token laws
Feature activation+0.000
help
Token help
Feature activation+0.000
keep
Token keep
Feature activation+0.000
governments
Token governments
Feature activation+0.100
honest
Token honest
Feature activation+4.012
and
Token and
Feature activation+0.793
First
Token First
Feature activation+0.012
Nations
Token Nations
Feature activation+0.000
governments
Token governments
Feature activation+0.100
are
Token are
Feature activation+0.000

INTERVAL 3.168 - 3.620
CONTAINS 0.003%

the
Token the
Feature activation+0.000
baby
Token baby
Feature activation+0.000
,
Token,
Feature activation+0.000
keep
Token keep
Feature activation+0.000
her
Token her
Feature activation+0.224
upright
Token upright
Feature activation+3.418
,
Token,
Feature activation+1.151
support
Token support
Feature activation+0.000
her
Token her
Feature activation+0.000
head
Token head
Feature activation+0.000
.
Token.
Feature activation+0.000
technology
Token technology
Feature activation+0.000
needed
Token needed
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
food
Token food
Feature activation+0.000
fresh
Token fresh
Feature activation+3.539
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
study
Token study
Feature activation+0.000
from
Token from
Feature activation+0.000
he
Token he
Feature activation+0.000
'll
Token'll
Feature activation+0.000
keep
Token keep
Feature activation+0.000
that
Token that
Feature activation+0.000
plant
Token plant
Feature activation+2.719
open
Token open
Feature activation+3.219
,"
Token,"
Feature activation+0.000
Ryan
Token Ryan
Feature activation+0.000
said
Token said
Feature activation+0.000
during
Token during
Feature activation+0.000
a
Token a
Feature activation+0.000
told
Token told
Feature activation+0.000
to
Token to
Feature activation+0.000
"
Token "
Feature activation+0.000
keep
Tokenkeep
Feature activation+0.000
a
Token a
Feature activation+0.000
secret
Token secret
Feature activation+3.437
"
Token"
Feature activation+0.400
from
Token from
Feature activation+1.624
.
Token.
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
more
Token more
Feature activation+0.000
in
Token in
Feature activation+0.000
repairs
Token repairs
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
systems
Token systems
Feature activation+0.000
running
Token running
Feature activation+3.256
safely
Token safely
Feature activation+1.705
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Other
TokenOther
Feature activation+0.000

INTERVAL 2.715 - 3.168
CONTAINS 0.003%

bit
Token bit
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Tokenhas
Feature activation+0.000
kept
Token kept
Feature activation+0.000
us
Token us
Feature activation+0.000
busy
Token busy
Feature activation+3.014
).
Token).
Feature activation+0.067
First
Token First
Feature activation+0.000
off
Token off
Feature activation+0.000
,
Token,
Feature activation+0.000
Collider
Token Collider
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
roster
Token roster
Feature activation+1.182
spots
Token spots
Feature activation+0.549
with
Token with
Feature activation+3.079
their
Token their
Feature activation+0.187
organizations
Token organizations
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
just
Token just
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
a
Token a
Feature activation+0.000
low
Token low
Feature activation+3.117
profile
Token profile
Feature activation+3.961
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Davis
TokenDavis
Feature activation+0.000
s
Tokens
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
them
Token them
Feature activation+0.603
all
Token all
Feature activation+2.931
straight
Token straight
Feature activation+3.029
.
Token.
Feature activation+0.006
You
Token You
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
:
Token:
Feature activation+0.000
Keep
Token Keep
Feature activation+0.000
your
Token your
Feature activation+0.729
back
Token back
Feature activation+0.000
straight
Token straight
Feature activation+3.295
with
Token with
Feature activation+2.780
your
Token your
Feature activation+0.059
chest
Token chest
Feature activation+0.000
pushed
Token pushed
Feature activation+0.076
forward
Token forward
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 2.263 - 2.715
CONTAINS 0.004%

the
Token the
Feature activation+0.000
animal
Token animal
Feature activation+0.000
must
Token must
Feature activation+0.000
keep
Token keep
Feature activation+0.000
a
Token a
Feature activation+0.000
constant
Token constant
Feature activation+2.665
gradient
Token gradient
Feature activation+0.227
of
Token of
Feature activation+0.622
shell
Token shell
Feature activation+0.449
growth
Token growth
Feature activation+0.000
rate
Token rate
Feature activation+0.142
data
Token data
Feature activation+0.000
you
Token you
Feature activation+0.000
mean
Token mean
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
private
Token private
Feature activation+2.272
can
Token can
Feature activation+0.000
leak
Token leak
Feature activation+0.924
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
sites
Token sites
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
kept
Token kept
Feature activation+0.000
a
Token a
Feature activation+0.000
written
Token written
Feature activation+2.284
record
Token record
Feature activation+0.572
of
Token of
Feature activation+0.364
what
Token what
Feature activation+0.029
payment
Token payment
Feature activation+0.000
methods
Token methods
Feature activation+0.000
keep
Token keep
Feature activation+0.000
themselves
Token themselves
Feature activation+0.312
and
Token and
Feature activation+0.416
their
Token their
Feature activation+0.497
children
Token children
Feature activation+0.202
separated
Token separated
Feature activation+2.670
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
dealings
Token dealings
Feature activation+0.000
while
Token while
Feature activation+0.000
searching
Token searching
Feature activation+0.000
Change
Token Change
Feature activation+0.000
things
Token things
Feature activation+0.000
.
Token.
Feature activation+0.000
Keep
Token Keep
Feature activation+0.000
in
Token in
Feature activation+0.000
touch
Token touch
Feature activation+2.621
and
Token and
Feature activation+0.000
tell
Token tell
Feature activation+0.716
her
Token her
Feature activation+0.000
the
Token the
Feature activation+0.000
truth
Token truth
Feature activation+0.000

INTERVAL 1.810 - 2.263
CONTAINS 0.007%

for
Token for
Feature activation+0.000
ways
Token ways
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.338
practice
Token practice
Feature activation+2.090
alive
Token alive
Feature activation+3.580
here
Token here
Feature activation+0.344
in
Token in
Feature activation+0.210
the
Token the
Feature activation+0.000
States
Token States
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Eagles
Token Eagles
Feature activation+0.000
kept
Token kept
Feature activation+0.000
him
Token him
Feature activation+0.500
around
Token around
Feature activation+2.181
and
Token and
Feature activation+0.493
tried
Token tried
Feature activation+0.145
to
Token to
Feature activation+0.000
transform
Token transform
Feature activation+0.000
him
Token him
Feature activation+0.000
the
Token the
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
law
Token law
Feature activation+0.882
and
Token and
Feature activation+1.886
order
Token order
Feature activation+1.432
for
Token for
Feature activation+0.677
others
Token others
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
desire
Token desire
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.367
process
Token process
Feature activation+1.607
moving
Token moving
Feature activation+2.042
along
Token along
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
believe
Token believe
Feature activation+0.000
there
Token there
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
use
Token use
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
their
Token their
Feature activation+0.281
private
Token private
Feature activation+2.146
information
Token information
Feature activation+0.000
safe
Token safe
Feature activation+3.611
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.358 - 1.810
CONTAINS 0.011%

âĢĵ
TokenâĢĵ
Feature activation+0.000
whose
Tokenwhose
Feature activation+0.000
identity
Token identity
Feature activation+0.000
is
Token is
Feature activation+0.000
kept
Token kept
Feature activation+0.000
anonymous
Token anonymous
Feature activation+1.605
in
Token in
Feature activation+0.628
the
Token the
Feature activation+0.120
indictment
Token indictment
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.000
to
Tokento
Feature activation+0.000
I
Token I
Feature activation+0.000
like
Token like
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
double
Token double
Feature activation+0.874
D
Token D
Feature activation+0.812
aze
Tokenaze
Feature activation+1.674
.
Token.
Feature activation+0.755
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
think
Token think
Feature activation+0.000
frequently
Token frequently
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.158
a
Token a
Feature activation+0.397
step
Token step
Feature activation+0.701
ahead
Token ahead
Feature activation+1.443
of
Token of
Feature activation+0.000
detection
Token detection
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
also
Token also
Feature activation+0.000
employment
Token employment
Feature activation+0.000
and
Token and
Feature activation+0.000
keep
Token keep
Feature activation+0.000
long
Token long
Feature activation+2.119
term
Token term
Feature activation+1.824
inflation
Token inflation
Feature activation+1.517
expectation
Token expectation
Feature activation+2.869
well
Token well
Feature activation+1.112
anchored
Token anchored
Feature activation+1.260
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
understandably
Token understandably
Feature activation+0.000
keep
Token keep
Feature activation+0.000
their
Token their
Feature activation+0.516
facilities
Token facilities
Feature activation+1.553
under
Token under
Feature activation+1.914
elaborate
Token elaborate
Feature activation+0.000
lockdown
Token lockdown
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000

INTERVAL 0.905 - 1.358
CONTAINS 0.019%

Ļ
TokenĻ
Feature activation+0.000
LL
TokenLL
Feature activation+0.000
K
Token K
Feature activation+0.000
EEP
TokenEEP
Feature activation+0.000
YOU
Token YOU
Feature activation+0.000
U
Token U
Feature activation+1.087
PDATED
TokenPDATED
Feature activation+0.727
!
Token!
Feature activation+0.153
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Throughout
TokenThroughout
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
keep
Tokenkeep
Feature activation+0.000
an
Token an
Feature activation+0.000
ice
Token ice
Feature activation+0.605
pack
Token pack
Feature activation+1.178
on
Token on
Feature activation+0.294
my
Token my
Feature activation+0.000
head
Token head
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
the
Token the
Feature activation+0.584
starting
Token starting
Feature activation+0.825
two
Token two
Feature activation+0.000
guard
Token guard
Feature activation+0.236
out
Token out
Feature activation+1.532
of
Token of
Feature activation+0.978
Portland
Token Portland
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
season
Token season
Feature activation+0.000
infrastructure
Token infrastructure
Feature activation+0.000
system
Token system
Feature activation+0.000
that
Token that
Feature activation+0.000
can
Token can
Feature activation+0.000
keep
Token keep
Feature activation+0.000
pace
Token pace
Feature activation+1.273
with
Token with
Feature activation+2.172
advances
Token advances
Feature activation+0.000
in
Token in
Feature activation+0.085
production
Token production
Feature activation+0.000
,
Token,
Feature activation+0.028
mean
Token mean
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
private
Token private
Feature activation+2.272
can
Token can
Feature activation+0.000
leak
Token leak
Feature activation+0.924
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
sites
Token sites
Feature activation+0.000
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.000

INTERVAL 0.453 - 0.905
CONTAINS 0.029%

to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.415
pressure
Token pressure
Feature activation+1.262
steady
Token steady
Feature activation+1.785
in
Token in
Feature activation+0.620
order
Token order
Feature activation+0.387
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
the
Token the
Feature activation+0.000
water
Token water
Feature activation+0.000
just
Token just
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
focused
Token focused
Feature activation+1.669
,
Token,
Feature activation+0.717
get
Token get
Feature activation+0.000
my
Token my
Feature activation+0.000
head
Token head
Feature activation+0.000
down
Token down
Feature activation+0.126
and
Token and
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
R
TokenR
Feature activation+0.000
ows
Tokenows
Feature activation+0.000
:
Token:
Feature activation+0.000
Keep
Token Keep
Feature activation+0.000
your
Token your
Feature activation+0.729
back
Token back
Feature activation+0.000
straight
Token straight
Feature activation+3.295
with
Token with
Feature activation+2.780
your
Token your
Feature activation+0.059
chest
Token chest
Feature activation+0.000
finds
Token finds
Feature activation+0.000
with
Token with
Feature activation+0.000
others
Token others
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.853
information
Token information
Feature activation+1.146
flowing
Token flowing
Feature activation+2.198
and
Token and
Feature activation+0.418
our
Token our
Feature activation+0.184
hobby
Token hobby
Feature activation+0.010
employment
Token employment
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
you
Token you
Feature activation+0.464
posted
Token posted
Feature activation+4.223
on
Token on
Feature activation+0.737
how
Token how
Feature activation+0.000
that
Token that
Feature activation+0.000
works
Token works
Feature activation+0.000

INTERVAL 0.000 - 0.453
CONTAINS 99.923%

iPhone
Token iPhone
Feature activation+0.000
and
Token and
Feature activation+0.000
Android
Token Android
Feature activation+0.000
,
Token,
Feature activation+0.000
defeating
Token defeating
Feature activation+0.000
antiv
Token antiv
Feature activation+0.000
irus
Tokenirus
Feature activation+0.000
programs
Token programs
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
program
Token program
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
controversial
Token controversial
Feature activation+0.000
,
Token,
Feature activation+0.000
cognitive
Token cognitive
Feature activation+0.000
performance
Token performance
Feature activation+0.000
scores
Token scores
Feature activation+0.000
are
Token are
Feature activation+0.000
widely
Token widely
Feature activation+0.000
used
Token used
Feature activation+0.000
5
Token5
Feature activation+0.000
mb
Tokenmb
Feature activation+0.000
d
Tokend
Feature activation+0.000
below
Token below
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
all
Token all
Feature activation+0.000
time
Token time
Feature activation+0.000
peak
Token peak
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
seems
Token seems
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
set
Token set
Feature activation+0.000
off
Token off
Feature activation+0.000
the
Token the
Feature activation+0.000
fire
Token fire
Feature activation+0.000
storm
Tokenstorm
Feature activation+0.000
over
Token over
Feature activation+0.165
the
Token the
Feature activation+0.000
weekend
Token weekend
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
not
Token not
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
everything
Token everything
Feature activation+0.000
.
Token.
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H2.8: (feature 23314)

TOP ACTIVATIONS
MAX = 3.188

that
Token that
Feature activation+0.000
habit
Token habit
Feature activation+0.000
ually
Tokenually
Feature activation+0.000
leave
Token leave
Feature activation+0.000
that
Token that
Feature activation+0.098
mark
Token mark
Feature activation+3.188
in
Token in
Feature activation+0.497
the
Token the
Feature activation+0.017
dust
Token dust
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
could
Token could
Feature activation+0.000
potentially
Token potentially
Feature activation+0.000
leave
Token leave
Feature activation+0.000
power
Token power
Feature activation+0.747
producers
Token producers
Feature activation+0.000
without
Token without
Feature activation+2.949
enough
Token enough
Feature activation+0.000
buyers
Token buyers
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
leave
Token leave
Feature activation+0.000
too
Token too
Feature activation+0.000
many
Token many
Feature activation+1.463
without
Token without
Feature activation+2.793
coverage
Token coverage
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sen
TokenSen
Feature activation+0.000
I
TokenI
Feature activation+0.000
leave
Token leave
Feature activation+0.000
my
Token my
Feature activation+0.000
play
Token play
Feature activation+1.053
books
Tokenbooks
Feature activation+0.000
alone
Token alone
Feature activation+2.788
.
Token.
Feature activation+0.125
Everything
Token Everything
Feature activation+0.000
you
Token you
Feature activation+0.000
need
Token need
Feature activation+0.000
is
Token is
Feature activation+0.000
The
Token The
Feature activation+0.000
whisk
Token whisk
Feature activation+0.000
should
Token should
Feature activation+0.000
leave
Token leave
Feature activation+0.000
an
Token an
Feature activation+0.428
impression
Token impression
Feature activation+2.782
in
Token in
Feature activation+1.780
the
Token the
Feature activation+0.831
mixture
Token mixture
Feature activation+0.185
.
Token.
Feature activation+0.000
S
Token S
Feature activation+0.000
an
Token an
Feature activation+0.000
email
Token email
Feature activation+0.000
,
Token,
Feature activation+0.000
leave
Token leave
Feature activation+0.104
a
Token a
Feature activation+0.487
comment
Token comment
Feature activation+2.757
,
Token,
Feature activation+0.554
or
Token or
Feature activation+0.449
hit
Token hit
Feature activation+0.000
me
Token me
Feature activation+0.000
up
Token up
Feature activation+0.000
Germany
Token Germany
Feature activation+0.000
policymakers
Token policymakers
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
it
Token it
Feature activation+0.330
alone
Token alone
Feature activation+2.704
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
this
Token this
Feature activation+0.000
stuff
Token stuff
Feature activation+0.000
leave
Token leave
Feature activation+0.000
me
Token me
Feature activation+0.457
a
Token a
Feature activation+1.329
comment
Token comment
Feature activation+2.691
below
Token below
Feature activation+1.814
and
Token and
Feature activation+0.000
let
Token let
Feature activation+0.000
me
Token me
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.000
let
Token let
Feature activation+0.000
me
Token me
Feature activation+0.000
leave
Token leave
Feature activation+0.000
you
Token you
Feature activation+0.478
with
Token with
Feature activation+2.676
this
Token this
Feature activation+0.276
:
Token:
Feature activation+0.298
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
https
Tokenhttps
Feature activation+0.000
Don
TokenDon
Feature activation+0.000
't
Token't
Feature activation+0.000
!
Token!
Feature activation+0.000
Leave
Token Leave
Feature activation+0.000
it
Token it
Feature activation+0.379
alone
Token alone
Feature activation+2.666
!"
Token!"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
î
Tokenî
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
--
Token --
Feature activation+0.000
violated
Token violated
Feature activation+0.000
"
Token "
Feature activation+0.000
leave
Tokenleave
Feature activation+0.000
no
Token no
Feature activation+0.000
trace
Token trace
Feature activation+2.641
"
Token"
Feature activation+0.000
principles
Token principles
Feature activation+0.000
with
Token with
Feature activation+1.454
one
Token one
Feature activation+0.000
stray
Token stray
Feature activation+0.000
why
Token why
Feature activation+0.000
would
Token would
Feature activation+0.000
he
Token he
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+0.522
company
Token company
Feature activation+2.532
right
Token right
Feature activation+1.103
before
Token before
Feature activation+0.675
the
Token the
Feature activation+0.000
launch
Token launch
Feature activation+0.000
he
Token he
Feature activation+0.000
address
Token address
Feature activation+0.000
:
Token:
Feature activation+0.000
Leave
Token Leave
Feature activation+0.000
this
Token this
Feature activation+0.000
field
Token field
Feature activation+0.000
empty
Token empty
Feature activation+2.459
if
Token if
Feature activation+0.588
you
Token you
Feature activation+0.506
're
Token're
Feature activation+0.000
human
Token human
Feature activation+0.000
:
Token:
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
car
Token car
Feature activation+0.000
ownership
Token ownership
Feature activation+0.047
behind
Token behind
Feature activation+2.455
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
may
Token may
Feature activation+0.000
practical
Token practical
Feature activation+0.000
nightmare
Token nightmare
Feature activation+0.000
,
Token,
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
them
Token them
Feature activation+0.463
with
Token with
Feature activation+2.454
virtually
Token virtually
Feature activation+0.000
nothing
Token nothing
Feature activation+0.097
but
Token but
Feature activation+0.000
a
Token a
Feature activation+0.355
lawsuit
Token lawsuit
Feature activation+0.000
which
Token which
Feature activation+0.000
will
Token will
Feature activation+0.000
leave
Token leave
Feature activation+0.000
a
Token a
Feature activation+0.339
permanent
Token permanent
Feature activation+2.144
dent
Token dent
Feature activation+2.385
in
Token in
Feature activation+0.000
our
Token our
Feature activation+0.000
nation
Token nation
Feature activation+0.000
's
Token's
Feature activation+0.000
prosperity
Token prosperity
Feature activation+0.000
How
TokenHow
Feature activation+0.000
's
Token's
Feature activation+0.000
that
Token that
Feature activation+0.000
leave
Token leave
Feature activation+0.000
me
Token me
Feature activation+0.030
alone
Token alone
Feature activation+2.362
personal
Token personal
Feature activation+0.510
liberty
Token liberty
Feature activation+0.000
thing
Token thing
Feature activation+0.840
working
Token working
Feature activation+0.280
out
Token out
Feature activation+0.000
iated
Tokeniated
Feature activation+0.000
,
Token,
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
everything
Token everything
Feature activation+0.000
horribly
Token horribly
Feature activation+0.000
mutated
Token mutated
Feature activation+2.326
and
Token and
Feature activation+0.000
hating
Token hating
Feature activation+0.000
your
Token your
Feature activation+0.000
guts
Token guts
Feature activation+0.000
.
Token.
Feature activation+0.000
so
Token so
Feature activation+0.000
he
Token he
Feature activation+0.000
could
Token could
Feature activation+0.000
leave
Token leave
Feature activation+0.000
a
Token a
Feature activation+0.556
legacy
Token legacy
Feature activation+2.293
of
Token of
Feature activation+0.919
inconsistent
Token inconsistent
Feature activation+0.521
,
Token,
Feature activation+0.000
erratic
Token erratic
Feature activation+0.000
,
Token,
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
will
Token will
Feature activation+0.000
leave
Token leave
Feature activation+0.000
her
Token her
Feature activation+0.142
with
Token with
Feature activation+2.292
you
Token you
Feature activation+0.252
.
Token.
Feature activation+0.000
Take
Token Take
Feature activation+0.000
care
Token care
Feature activation+0.000
of
Token of
Feature activation+0.000

Top DFA by src position
MAX = 5.151

World
Token World
Feature activation-0.000
Top resid features:
wines
Token wines
Feature activation+0.016
Top resid features:
that
Token that
Feature activation-0.012
Top resid features:
habit
Token habit
Feature activation+0.036
Top resid features:
ually
Tokenually
Feature activation-0.044
Top resid features:
leave
Token leave
Feature activation+5.151
Top resid features:
that
Token that
Feature activation+0.075
Top resid features:
mark
Token mark
Feature activation+0.186
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
dust
Token dust
Feature activation+0.000
Top resid features:
A
TokenA
Feature activation+0.018
Top resid features:
hefty
Token hefty
Feature activation+0.019
Top resid features:
ADD
Token ADD
Feature activation+0.017
Top resid features:
could
Token could
Feature activation+0.026
Top resid features:
potentially
Token potentially
Feature activation+0.031
Top resid features:
leave
Token leave
Feature activation+4.453
Top resid features:
power
Token power
Feature activation+0.109
Top resid features:
producers
Token producers
Feature activation+0.204
Top resid features:
without
Token without
Feature activation+0.199
Top resid features:
enough
Token enough
Feature activation+0.000
Top resid features:
buyers
Token buyers
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
who
Token who
Feature activation-0.006
Top resid features:
fear
Token fear
Feature activation+0.043
Top resid features:
it
Token it
Feature activation+0.044
Top resid features:
would
Token would
Feature activation-0.000
Top resid features:
leave
Token leave
Feature activation+4.420
Top resid features:
too
Token too
Feature activation+0.089
Top resid features:
many
Token many
Feature activation+0.240
Top resid features:
without
Token without
Feature activation+0.122
Top resid features:
coverage
Token coverage
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation-0.011
Top resid features:
Basics
Token Basics
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.044
Top resid features:
Ċ
TokenĊ
Feature activation-0.051
Top resid features:
I
TokenI
Feature activation+0.011
Top resid features:
leave
Token leave
Feature activation+4.891
Top resid features:
my
Token my
Feature activation+0.091
Top resid features:
play
Token play
Feature activation-0.007
Top resid features:
books
Tokenbooks
Feature activation+0.054
Top resid features:
alone
Token alone
Feature activation+0.073
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
fluffy
Token fluffy
Feature activation+0.016
Top resid features:
.
Token.
Feature activation-0.102
Top resid features:
The
Token The
Feature activation-0.013
Top resid features:
whisk
Token whisk
Feature activation+0.002
Top resid features:
should
Token should
Feature activation+0.001
Top resid features:
leave
Token leave
Feature activation+4.774
Top resid features:
an
Token an
Feature activation+0.178
Top resid features:
impression
Token impression
Feature activation+0.047
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
mixture
Token mixture
Feature activation+0.000
Top resid features:
shoot
Token shoot
Feature activation+0.209
Top resid features:
me
Token me
Feature activation+0.015
Top resid features:
an
Token an
Feature activation+0.015
Top resid features:
email
Token email
Feature activation+0.128
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
leave
Token leave
Feature activation+4.132
Top resid features:
a
Token a
Feature activation+0.275
Top resid features:
comment
Token comment
Feature activation+0.067
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
hit
Token hit
Feature activation+0.000
Top resid features:
vin
Tokenvin
Feature activation+0.003
Top resid features:
ced
Tokenced
Feature activation+0.001
Top resid features:
Germany
Token Germany
Feature activation+0.052
Top resid features:
policymakers
Token policymakers
Feature activation+0.038
Top resid features:
to
Token to
Feature activation-0.033
Top resid features:
leave
Token leave
Feature activation+4.387
Top resid features:
it
Token it
Feature activation+0.264
Top resid features:
alone
Token alone
Feature activation+0.106
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:
dig
Token dig
Feature activation+0.086
Top resid features:
any
Token any
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.027
Top resid features:
this
Token this
Feature activation+0.045
Top resid features:
stuff
Token stuff
Feature activation+0.066
Top resid features:
leave
Token leave
Feature activation+4.494
Top resid features:
me
Token me
Feature activation+0.089
Top resid features:
a
Token a
Feature activation+0.179
Top resid features:
comment
Token comment
Feature activation+0.036
Top resid features:
below
Token below
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Dark
Token Dark
Feature activation-0.010
Top resid features:
Matter
Token Matter
Feature activation-0.023
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
let
Token let
Feature activation-0.059
Top resid features:
me
Token me
Feature activation+0.030
Top resid features:
leave
Token leave
Feature activation+4.546
Top resid features:
you
Token you
Feature activation+0.352
Top resid features:
with
Token with
Feature activation+0.101
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.007
Top resid features:
"
Token "
Feature activation-0.010
Top resid features:
Don
TokenDon
Feature activation-0.000
Top resid features:
't
Token't
Feature activation+0.024
Top resid features:
!
Token!
Feature activation-0.074
Top resid features:
Leave
Token Leave
Feature activation+4.555
Top resid features:
it
Token it
Feature activation+0.207
Top resid features:
alone
Token alone
Feature activation+0.082
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:
impact
Tokenimpact
Feature activation-0.001
Top resid features:
style
Token style
Feature activation-0.001
Top resid features:
--
Token --
Feature activation-0.041
Top resid features:
violated
Token violated
Feature activation+0.048
Top resid features:
"
Token "
Feature activation-0.043
Top resid features:
leave
Tokenleave
Feature activation+4.410
Top resid features:
no
Token no
Feature activation+0.267
Top resid features:
trace
Token trace
Feature activation+0.167
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
principles
Token principles
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.083
Top resid features:
So
Token So
Feature activation-0.067
Top resid features:
why
Token why
Feature activation-0.025
Top resid features:
would
Token would
Feature activation+0.045
Top resid features:
he
Token he
Feature activation+0.024
Top resid features:
leave
Token leave
Feature activation+4.374
Top resid features:
the
Token the
Feature activation+0.189
Top resid features:
company
Token company
Feature activation+0.120
Top resid features:
right
Token right
Feature activation+0.000
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
here
Token here
Feature activation+0.009
Top resid features:
!
Token!
Feature activation-0.042
Top resid features:
Email
Token Email
Feature activation+0.075
Top resid features:
address
Token address
Feature activation+0.043
Top resid features:
:
Token:
Feature activation-0.042
Top resid features:
Leave
Token Leave
Feature activation+4.097
Top resid features:
this
Token this
Feature activation+0.239
Top resid features:
field
Token field
Feature activation+0.039
Top resid features:
empty
Token empty
Feature activation+0.101
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.004
Top resid features:
trained
Tokentrained
Feature activation+0.018
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.033
Top resid features:
leave
Token leave
Feature activation+4.358
Top resid features:
car
Token car
Feature activation+0.047
Top resid features:
ownership
Token ownership
Feature activation+0.100
Top resid features:
behind
Token behind
Feature activation+0.168
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
into
Token into
Feature activation+0.059
Top resid features:
a
Token a
Feature activation+0.022
Top resid features:
practical
Token practical
Feature activation+0.004
Top resid features:
nightmare
Token nightmare
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.022
Top resid features:
leaving
Token leaving
Feature activation+4.142
Top resid features:
them
Token them
Feature activation+0.304
Top resid features:
with
Token with
Feature activation+0.125
Top resid features:
virtually
Token virtually
Feature activation+0.000
Top resid features:
nothing
Token nothing
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
high
Token high
Feature activation-0.008
Top resid features:
unemployment
Token unemployment
Feature activation+0.041
Top resid features:
which
Token which
Feature activation-0.005
Top resid features:
will
Token will
Feature activation-0.021
Top resid features:
leave
Token leave
Feature activation+4.059
Top resid features:
a
Token a
Feature activation+0.096
Top resid features:
permanent
Token permanent
Feature activation+0.253
Top resid features:
dent
Token dent
Feature activation+0.151
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.015
Top resid features:
"
Token "
Feature activation-0.017
Top resid features:
How
TokenHow
Feature activation-0.103
Top resid features:
's
Token's
Feature activation+0.032
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
leave
Token leave
Feature activation+4.251
Top resid features:
me
Token me
Feature activation+0.216
Top resid features:
alone
Token alone
Feature activation+0.138
Top resid features:
personal
Token personal
Feature activation+0.000
Top resid features:
liberty
Token liberty
Feature activation+0.000
Top resid features:
thing
Token thing
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.294
Top resid features:
iated
Tokeniated
Feature activation+0.079
Top resid features:
,
Token,
Feature activation-0.059
Top resid features:
leaving
Token leaving
Feature activation+3.749
Top resid features:
everything
Token everything
Feature activation+0.387
Top resid features:
horribly
Token horribly
Feature activation+0.429
Top resid features:
mutated
Token mutated
Feature activation-0.086
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
hating
Token hating
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.087
Top resid features:
NYU
Token NYU
Feature activation+0.063
Top resid features:
so
Token so
Feature activation+0.034
Top resid features:
he
Token he
Feature activation+0.002
Top resid features:
could
Token could
Feature activation-0.005
Top resid features:
leave
Token leave
Feature activation+3.732
Top resid features:
a
Token a
Feature activation+0.222
Top resid features:
legacy
Token legacy
Feature activation+0.150
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
inconsistent
Token inconsistent
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
âĢ
Token âĢ
Feature activation+0.014
Top resid features:
ľ
Tokenľ
Feature activation+0.013
Top resid features:
I
TokenI
Feature activation+0.020
Top resid features:
will
Token will
Feature activation+0.065
Top resid features:
leave
Token leave
Feature activation+4.048
Top resid features:
her
Token her
Feature activation+0.187
Top resid features:
with
Token with
Feature activation+0.111
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Take
Token Take
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.03

Head 2: 0.04

Head 3: 0.05

Head 4: 0.04

Head 5: 0.06

Head 6: 0.03

Head 7: 0.03

Head 8: 0.50

Head 9: 0.06

Head 10: 0.06

Head 11: 0.03

Positive logits

Islands1.54

untouched1.44

crater1.38

intact1.34

Ruk1.33

asis1.33

ashes1.33

ash1.32

charred1.30

tidy1.29

unatt1.27

unfinished1.25

clut1.25

scars1.23

barren1.22

belt1.22

Hole1.22

unhappy1.22

Conserv1.19

wreckage1.19

Negative logits

Cosponsors-1.38

wcsstore-1.35

quickShipAvailable-1.29

temperament-1.25

coh-1.24

utm-1.21

iqueness-1.20

FactoryReloaded-1.18

FN-1.17

ACTION-1.17

MN-1.16

nesday-1.15

ologne-1.14

trak-1.13

MON-1.13

Gian-1.13

fielded-1.12

appropri-1.11

tactics-1.09

reach-1.09

INTERVAL 2.869 - 3.188
CONTAINS 0.000%

that
Token that
Feature activation+0.000
habit
Token habit
Feature activation+0.000
ually
Tokenually
Feature activation+0.000
leave
Token leave
Feature activation+0.000
that
Token that
Feature activation+0.098
mark
Token mark
Feature activation+3.188
in
Token in
Feature activation+0.497
the
Token the
Feature activation+0.017
dust
Token dust
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
could
Token could
Feature activation+0.000
potentially
Token potentially
Feature activation+0.000
leave
Token leave
Feature activation+0.000
power
Token power
Feature activation+0.747
producers
Token producers
Feature activation+0.000
without
Token without
Feature activation+2.949
enough
Token enough
Feature activation+0.000
buyers
Token buyers
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000

INTERVAL 2.551 - 2.869
CONTAINS 0.001%

The
Token The
Feature activation+0.000
whisk
Token whisk
Feature activation+0.000
should
Token should
Feature activation+0.000
leave
Token leave
Feature activation+0.000
an
Token an
Feature activation+0.428
impression
Token impression
Feature activation+2.782
in
Token in
Feature activation+1.780
the
Token the
Feature activation+0.831
mixture
Token mixture
Feature activation+0.185
.
Token.
Feature activation+0.000
S
Token S
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
leave
Token leave
Feature activation+0.000
too
Token too
Feature activation+0.000
many
Token many
Feature activation+1.463
without
Token without
Feature activation+2.793
coverage
Token coverage
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sen
TokenSen
Feature activation+0.000
Don
TokenDon
Feature activation+0.000
't
Token't
Feature activation+0.000
!
Token!
Feature activation+0.000
Leave
Token Leave
Feature activation+0.000
it
Token it
Feature activation+0.379
alone
Token alone
Feature activation+2.666
!"
Token!"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
î
Tokenî
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
,
Token,
Feature activation+0.000
let
Token let
Feature activation+0.000
me
Token me
Feature activation+0.000
leave
Token leave
Feature activation+0.000
you
Token you
Feature activation+0.478
with
Token with
Feature activation+2.676
this
Token this
Feature activation+0.276
:
Token:
Feature activation+0.298
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
https
Tokenhttps
Feature activation+0.000
I
TokenI
Feature activation+0.000
leave
Token leave
Feature activation+0.000
my
Token my
Feature activation+0.000
play
Token play
Feature activation+1.053
books
Tokenbooks
Feature activation+0.000
alone
Token alone
Feature activation+2.788
.
Token.
Feature activation+0.125
Everything
Token Everything
Feature activation+0.000
you
Token you
Feature activation+0.000
need
Token need
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 2.232 - 2.551
CONTAINS 0.001%

Ŀ
TokenĿ
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
car
Token car
Feature activation+0.000
ownership
Token ownership
Feature activation+0.047
behind
Token behind
Feature activation+2.455
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
may
Token may
Feature activation+0.000
How
TokenHow
Feature activation+0.000
's
Token's
Feature activation+0.000
that
Token that
Feature activation+0.000
leave
Token leave
Feature activation+0.000
me
Token me
Feature activation+0.030
alone
Token alone
Feature activation+2.362
personal
Token personal
Feature activation+0.510
liberty
Token liberty
Feature activation+0.000
thing
Token thing
Feature activation+0.840
working
Token working
Feature activation+0.280
out
Token out
Feature activation+0.000
which
Token which
Feature activation+0.000
will
Token will
Feature activation+0.000
leave
Token leave
Feature activation+0.000
a
Token a
Feature activation+0.339
permanent
Token permanent
Feature activation+2.144
dent
Token dent
Feature activation+2.385
in
Token in
Feature activation+0.000
our
Token our
Feature activation+0.000
nation
Token nation
Feature activation+0.000
's
Token's
Feature activation+0.000
prosperity
Token prosperity
Feature activation+0.000
iated
Tokeniated
Feature activation+0.000
,
Token,
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
everything
Token everything
Feature activation+0.000
horribly
Token horribly
Feature activation+0.000
mutated
Token mutated
Feature activation+2.326
and
Token and
Feature activation+0.000
hating
Token hating
Feature activation+0.000
your
Token your
Feature activation+0.000
guts
Token guts
Feature activation+0.000
.
Token.
Feature activation+0.000
so
Token so
Feature activation+0.000
he
Token he
Feature activation+0.000
could
Token could
Feature activation+0.000
leave
Token leave
Feature activation+0.000
a
Token a
Feature activation+0.556
legacy
Token legacy
Feature activation+2.293
of
Token of
Feature activation+0.919
inconsistent
Token inconsistent
Feature activation+0.521
,
Token,
Feature activation+0.000
erratic
Token erratic
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.913 - 2.232
CONTAINS 0.002%

You
Token You
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
home
Token home
Feature activation+0.000
for
Token for
Feature activation+1.941
work
Token work
Feature activation+0.168
or
Token or
Feature activation+0.000
err
Token err
Feature activation+0.000
ands
Tokenands
Feature activation+0.000
AND
Token AND
Feature activation+0.000
ed
Tokened
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
leave
Token leave
Feature activation+0.000
asphalt
Token asphalt
Feature activation+0.043
behind
Token behind
Feature activation+1.915
as
Token as
Feature activation+1.929
a
Token a
Feature activation+0.653
waste
Token waste
Feature activation+0.468
product
Token product
Feature activation+0.124
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
leave
Token leave
Feature activation+0.000
asphalt
Token asphalt
Feature activation+0.043
behind
Token behind
Feature activation+1.915
as
Token as
Feature activation+1.929
a
Token a
Feature activation+0.653
waste
Token waste
Feature activation+0.468
product
Token product
Feature activation+0.124
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
tor
Token tor
Feature activation+0.000
ched
Tokenched
Feature activation+0.000
,
Token,
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
without
Token without
Feature activation+2.136
power
Token power
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
even
Token even
Feature activation+0.000
did
Token did
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
some
Token some
Feature activation+0.338
communities
Token communities
Feature activation+0.823
in
Token in
Feature activation+1.426
India
Token India
Feature activation+0.529
with
Token with
Feature activation+1.926
so
Token so
Feature activation+0.000
few
Token few
Feature activation+0.000
girls
Token girls
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000

INTERVAL 1.594 - 1.913
CONTAINS 0.003%

whisk
Token whisk
Feature activation+0.000
should
Token should
Feature activation+0.000
leave
Token leave
Feature activation+0.000
an
Token an
Feature activation+0.428
impression
Token impression
Feature activation+2.782
in
Token in
Feature activation+1.780
the
Token the
Feature activation+0.831
mixture
Token mixture
Feature activation+0.185
.
Token.
Feature activation+0.000
S
Token S
Feature activation+0.000
ieve
Tokenieve
Feature activation+0.000
do
Token do
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Leave
Token Leave
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+1.652
Bloomberg
Token Bloomberg
Feature activation+0.000
to
Token to
Feature activation+1.868
be
Token be
Feature activation+0.857
so
Token so
Feature activation+0.000
heavy
Token heavy
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
are
Token are
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
nothing
Token nothing
Feature activation+0.054
to
Token to
Feature activation+1.718
chance
Token chance
Feature activation+1.386
.
Token.
Feature activation+0.000
City
Token City
Feature activation+0.000
,
Token,
Feature activation+0.000
State
Token State
Feature activation+0.000
leaves
Token leaves
Feature activation+0.000
the
Token the
Feature activation+0.000
Sutherland
Token Sutherland
Feature activation+0.478
Local
Token Local
Feature activation+0.093
Court
Token Court
Feature activation+0.528
on
Token on
Feature activation+1.706
Monday
Token Monday
Feature activation+0.000
.
Token.
Feature activation+0.000
Credit
Token Credit
Feature activation+0.000
:
Token:
Feature activation+0.000
A
TokenA
Feature activation+0.000
isher
Tokenisher
Feature activation+0.000
,
Token,
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
Fuj
Token Fuj
Feature activation+0.471
ita
Tokenita
Feature activation+1.699
at
Token at
Feature activation+1.704
#
Token #
Feature activation+0.000
12
Token12
Feature activation+0.000
.[
Token.[
Feature activation+0.000
12
Token12
Feature activation+0.000
]
Token]
Feature activation+0.000

INTERVAL 1.275 - 1.594
CONTAINS 0.004%

for
Token for
Feature activation+0.000
Britain
Token Britain
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+1.438
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
single
Token single
Feature activation+0.451
market
Token market
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
Add
Token Add
Feature activation+0.000
is
Tokenis
Feature activation+0.000
Ab
Token Ab
Feature activation+0.846
aba
Tokenaba
Feature activation+0.651
in
Token in
Feature activation+1.387
haste
Token haste
Feature activation+0.067
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
might
Token might
Feature activation+0.000
well
Token well
Feature activation+0.000
easy
Token easy
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.067
in
Token in
Feature activation+0.189
their
Token their
Feature activation+0.652
space
Token space
Feature activation+1.401
âĢĶ
Token âĢĶ
Feature activation+0.045
earnest
Token earnest
Feature activation+0.000
,
Token,
Feature activation+0.000
occasionally
Token occasionally
Feature activation+0.000
dusty
Token dusty
Feature activation+0.000
fear
Token fear
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
leave
Token leave
Feature activation+0.000
too
Token too
Feature activation+0.000
many
Token many
Feature activation+1.463
without
Token without
Feature activation+2.793
coverage
Token coverage
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
Token But
Feature activation+0.000
he
Token he
Feature activation+0.000
leaves
Token leaves
Feature activation+0.000
the
Token the
Feature activation+0.000
Lions
Token Lions
Feature activation+0.355
with
Token with
Feature activation+1.445
no
Token no
Feature activation+0.000
regrets
Token regrets
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.956 - 1.275
CONTAINS 0.006%

to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
certain
Token certain
Feature activation+0.000
important
Token important
Feature activation+0.025
artifacts
Token artifacts
Feature activation+2.085
while
Token while
Feature activation+1.007
maintaining
Token maintaining
Feature activation+0.000
breathtaking
Token breathtaking
Feature activation+0.000
quality
Token quality
Feature activation+0.000
and
Token and
Feature activation+0.000
every
Token every
Feature activation+0.000
it
Token it
Feature activation+0.000
do
Token do
Feature activation+0.000
to
Token to
Feature activation+0.000
simply
Token simply
Feature activation+0.000
leave
Token leave
Feature activation+0.000
him
Token him
Feature activation+1.076
to
Token to
Feature activation+1.514
present
Token present
Feature activation+0.175
himself
Token himself
Feature activation+0.000
as
Token as
Feature activation+0.005
a
Token a
Feature activation+0.125
weapon
Token weapon
Feature activation+0.000
was
Token was
Feature activation+0.000
deployed
Token deployed
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.970
D
Token D
Feature activation+0.000
ax
Tokenax
Feature activation+0.000
am
Tokenam
Feature activation+0.000
ites
Tokenites
Feature activation+0.000
no
Token no
Feature activation+1.444
leaving
Token leaving
Feature activation+0.000
or
Token or
Feature activation+0.000
charging
Token charging
Feature activation+0.385
a
Token a
Feature activation+0.864
battery
Token battery
Feature activation+0.576
in
Token in
Feature activation+1.055
a
Token a
Feature activation+0.249
hot
Token hot
Feature activation+0.000
environment
Token environment
Feature activation+0.334
can
Token can
Feature activation+0.000
cause
Token cause
Feature activation+0.000
border
Token border
Feature activation+0.000
bill
Token bill
Feature activation+0.000
before
Token before
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
leave
Token leave
Feature activation+0.000
town
Token town
Feature activation+1.086
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Under
TokenUnder
Feature activation+0.000
House
Token House
Feature activation+0.000

INTERVAL 0.638 - 0.956
CONTAINS 0.008%

Bills
Token Bills
Feature activation+1.319
'
Token'
Feature activation+0.000
final
Token final
Feature activation+0.175
two
Token two
Feature activation+0.000
games
Token games
Feature activation+0.000
as
Token as
Feature activation+0.766
a
Token a
Feature activation+0.000
form
Token form
Feature activation+0.000
ality
Tokenality
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
anybody
Token anybody
Feature activation+0.805
craving
Token craving
Feature activation+1.120
a
Token a
Feature activation+0.000
return
Token return
Feature activation+0.000
home
Token home
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Le
TokenLe
Feature activation+0.000
aving
Tokenaving
Feature activation+0.000
my
Token my
Feature activation+0.000
own
Token own
Feature activation+1.177
children
Token children
Feature activation+0.760
for
Token for
Feature activation+2.100
six
Token six
Feature activation+0.000
months
Token months
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
for
Token for
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
Add
Token Add
Feature activation+0.000
is
Tokenis
Feature activation+0.000
Ab
Token Ab
Feature activation+0.846
aba
Tokenaba
Feature activation+0.651
in
Token in
Feature activation+1.387
haste
Token haste
Feature activation+0.067
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
might
Token might
Feature activation+0.000
s
Tokens
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
a
Token a
Feature activation+0.164
totally
Token totally
Feature activation+0.841
contaminated
Token contaminated
Feature activation+1.816
site
Token site
Feature activation+0.777
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
J
TokenJ
Feature activation+0.000
U
TokenU
Feature activation+0.000

INTERVAL 0.319 - 0.638
CONTAINS 0.013%

need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+0.041
jail
Token jail
Feature activation+1.491
and
Token and
Feature activation+0.398
create
Token create
Feature activation+0.000
a
Token a
Feature activation+0.000
bridge
Token bridge
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
of
Token of
Feature activation+1.138
a
Token a
Feature activation+0.877
peace
Token peace
Feature activation+0.432
-
Token-
Feature activation+0.000
maker
Tokenmaker
Feature activation+0.067
between
Token between
Feature activation+0.576
the
Token the
Feature activation+0.000
Israelis
Token Israelis
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Palestinians
Token Palestinians
Feature activation+0.000
them
Token them
Feature activation+0.463
with
Token with
Feature activation+2.454
virtually
Token virtually
Feature activation+0.000
nothing
Token nothing
Feature activation+0.097
but
Token but
Feature activation+0.000
a
Token a
Feature activation+0.355
lawsuit
Token lawsuit
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Leave
Token Leave
Feature activation+0.000
this
Token this
Feature activation+0.000
field
Token field
Feature activation+0.000
empty
Token empty
Feature activation+2.459
if
Token if
Feature activation+0.588
you
Token you
Feature activation+0.506
're
Token're
Feature activation+0.000
human
Token human
Feature activation+0.000
:
Token:
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Nev
TokenNev
Feature activation+0.000
who
Token who
Feature activation+0.000
enter
Token enter
Feature activation+0.000
and
Token and
Feature activation+0.000
leave
Token leave
Feature activation+0.000
public
Token public
Feature activation+0.000
service
Token service
Feature activation+0.357
.
Token.
Feature activation+0.000
Finally
Token Finally
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
O
Token O
Feature activation+0.000

INTERVAL 0.000 - 0.319
CONTAINS 99.962%

:
Token:
Feature activation+0.000
Mike
Token Mike
Feature activation+0.000
K
Token K
Feature activation+0.000
ep
Tokenep
Feature activation+0.000
ka
Tokenka
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+0.000
Chronicle
Token Chronicle
Feature activation+0.000
Image
Token Image
Feature activation+0.000
1
Token 1
Feature activation+0.000
of
Token of
Feature activation+0.000
to
Token to
Feature activation+0.000
identify
Token identify
Feature activation+0.000
the
Token the
Feature activation+0.000
value
Token value
Feature activation+0.000
drivers
Token drivers
Feature activation+0.000
of
Token of
Feature activation+0.000
potential
Token potential
Feature activation+0.000
partners
Token partners
Feature activation+0.000
by
Token by
Feature activation+0.000
analyzing
Token analyzing
Feature activation+0.000
their
Token their
Feature activation+0.000
elite
Token elite
Feature activation+0.000
units
Token units
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+0.000
Green
Token Green
Feature activation+0.000
Bere
Token Bere
Feature activation+0.000
ts
Tokents
Feature activation+0.000
or
Token or
Feature activation+0.000
Navy
Token Navy
Feature activation+0.000
SEAL
Token SEAL
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
plant
Token plant
Feature activation+0.000
but
Token but
Feature activation+0.000
a
Token a
Feature activation+0.000
un
Token un
Feature activation+0.000
spoken
Tokenspoken
Feature activation+0.000
symbol
Token symbol
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
Nation
Token Nation
Feature activation+0.000
.
Token.
Feature activation+0.000
watchdog
Token watchdog
Feature activation+0.000
agency
Token agency
Feature activation+0.000
that
Token that
Feature activation+0.000
provides
Token provides
Feature activation+0.000
investigative
Token investigative
Feature activation+0.000
support
Token support
Feature activation+0.000
to
Token to
Feature activation+0.000
legislators
Token legislators
Feature activation+0.000
,
Token,
Feature activation+0.000
will
Token will
Feature activation+0.000
look
Token look
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 H2.8: (feature 2950)

TOP ACTIVATIONS
MAX = 3.618

Giants
Token Giants
Feature activation+0.000
spent
Token spent
Feature activation+0.000
$
Token $
Feature activation+0.914
200
Token200
Feature activation+1.968
million
Token million
Feature activation+3.438
on
Token on
Feature activation+3.618
payroll
Token payroll
Feature activation+0.502
this
Token this
Feature activation+0.026
year
Token year
Feature activation+1.790
,
Token,
Feature activation+0.103
which
Token which
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Giants
Token Giants
Feature activation+0.000
spent
Token spent
Feature activation+0.000
$
Token $
Feature activation+0.914
200
Token200
Feature activation+1.968
million
Token million
Feature activation+3.438
on
Token on
Feature activation+3.618
payroll
Token payroll
Feature activation+0.502
this
Token this
Feature activation+0.026
year
Token year
Feature activation+1.790
,
Token,
Feature activation+0.103
)
Token)
Feature activation+0.000
spent
Token spent
Feature activation+0.143
a
Token a
Feature activation+0.061
lot
Token lot
Feature activation+1.881
of
Token of
Feature activation+2.877
time
Token time
Feature activation+3.406
m
Token m
Feature activation+1.409
udd
Tokenudd
Feature activation+0.000
ying
Tokenying
Feature activation+0.000
the
Token the
Feature activation+0.000
waters
Token waters
Feature activation+0.000
second
Token second
Feature activation+0.414
half
Token half
Feature activation+1.729
of
Token of
Feature activation+1.955
last
Token last
Feature activation+2.131
season
Token season
Feature activation+2.521
on
Token on
Feature activation+3.358
loan
Token loan
Feature activation+0.000
at
Token at
Feature activation+0.000
Villa
Token Villa
Feature activation+0.000
Park
Token Park
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
spent
Token spent
Feature activation+0.000
three
Token three
Feature activation+0.336
days
Token days
Feature activation+0.749
on
Token on
Feature activation+3.341
a
Token a
Feature activation+0.440
rocky
Token rocky
Feature activation+0.000
floor
Token floor
Feature activation+0.000
on
Token on
Feature activation+2.519
my
Token my
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+1.134
of
Token of
Feature activation+2.787
time
Token time
Feature activation+3.322
in
Token in
Feature activation+1.599
South
Token South
Feature activation+0.000
East
Token East
Feature activation+0.000
Asia
Token Asia
Feature activation+0.000
.
Token.
Feature activation+0.024
spent
Token spent
Feature activation+0.000
more
Token more
Feature activation+1.080
than
Token than
Feature activation+2.278
$
Token $
Feature activation+2.630
142
Token142
Feature activation+1.084
million
Token million
Feature activation+3.267
of
Token of
Feature activation+1.233
her
Token her
Feature activation+0.456
own
Token own
Feature activation+0.000
money
Token money
Feature activation+0.324
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
great
Token great
Feature activation+0.780
number
Token number
Feature activation+0.999
of
Token of
Feature activation+2.037
hours
Token hours
Feature activation+2.590
on
Token on
Feature activation+3.252
a
Token a
Feature activation+0.000
surprisingly
Token surprisingly
Feature activation+0.000
uncomfortable
Token uncomfortable
Feature activation+0.000
coach
Token coach
Feature activation+0.000
bus
Token bus
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+1.027
of
Token of
Feature activation+2.691
time
Token time
Feature activation+3.179
thinking
Token thinking
Feature activation+0.179
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
sacrament
Token sacrament
Feature activation+0.000
of
Token of
Feature activation+0.000
when
Token when
Feature activation+0.000
they
Token they
Feature activation+0.000
spent
Token spent
Feature activation+0.000
21
Token 21
Feature activation+0.307
days
Token days
Feature activation+1.492
on
Token on
Feature activation+3.095
a
Token a
Feature activation+0.064
diet
Token diet
Feature activation+0.240
low
Token low
Feature activation+0.000
in
Token in
Feature activation+0.000
F
Token F
Feature activation+0.000
15
Token 15
Feature activation+0.004
years
Token years
Feature activation+1.072
,
Token,
Feature activation+1.348
7
Token 7
Feature activation+0.864
months
Token months
Feature activation+2.781
on
Token on
Feature activation+3.085
death
Token death
Feature activation+0.000
row
Token row
Feature activation+0.000
.
Token.
Feature activation+0.000
Though
Token Though
Feature activation+0.000
12
Token 12
Feature activation+0.000
oc
Tokenoc
Feature activation+0.000
chi
Tokenchi
Feature activation+0.000
spent
Token spent
Feature activation+0.000
some
Token some
Feature activation+0.236
time
Token time
Feature activation+1.979
on
Token on
Feature activation+3.075
stage
Token stage
Feature activation+0.403
talking
Token talking
Feature activation+0.000
about
Token about
Feature activation+0.000
Infinity
Token Infinity
Feature activation+0.000
2
Token 2
Feature activation+0.000
spent
Token spent
Feature activation+0.000
the
Token the
Feature activation+0.000
rest
Token rest
Feature activation+1.317
of
Token of
Feature activation+0.992
the
Token the
Feature activation+1.996
day
Token day
Feature activation+3.036
walking
Token walking
Feature activation+0.059
around
Token around
Feature activation+0.000
campus
Token campus
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
kids
Token kids
Feature activation+0.000
his
Token his
Feature activation+0.000
allies
Token allies
Feature activation+0.000
spent
Token spent
Feature activation+0.000
$
Token $
Feature activation+0.593
140
Token140
Feature activation+1.383
million
Token million
Feature activation+3.031
dollars
Token dollars
Feature activation+2.976
in
Token in
Feature activation+1.654
January
Token January
Feature activation+0.299
alone
Token alone
Feature activation+0.000
in
Token in
Feature activation+0.000
West
Token West
Feature activation+0.000
,
Token,
Feature activation+0.000
spent
Token spent
Feature activation+0.000
$
Token $
Feature activation+0.832
300
Token300
Feature activation+1.601
million
Token million
Feature activation+2.995
.
Token.
Feature activation+0.734
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
With
TokenWith
Feature activation+0.000
San
Token San
Feature activation+0.000
allies
Token allies
Feature activation+0.000
spent
Token spent
Feature activation+0.000
$
Token $
Feature activation+0.593
140
Token140
Feature activation+1.383
million
Token million
Feature activation+3.031
dollars
Token dollars
Feature activation+2.976
in
Token in
Feature activation+1.654
January
Token January
Feature activation+0.299
alone
Token alone
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
a
Token a
Feature activation+0.075
total
Token total
Feature activation+1.622
of
Token of
Feature activation+1.596
6
Token 6
Feature activation+0.905
89
Token89
Feature activation+0.242
days
Token days
Feature activation+2.963
at
Token at
Feature activation+2.209
the
Token the
Feature activation+0.000
charity
Token charity
Feature activation+0.000
's
Token's
Feature activation+0.000
Old
Token Old
Feature activation+0.000
we
Token we
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+1.329
of
Token of
Feature activation+2.257
time
Token time
Feature activation+2.955
acting
Token acting
Feature activation+0.712
those
Token those
Feature activation+0.000
things
Token things
Feature activation+0.000
out
Token out
Feature activation+0.000
.
Token.
Feature activation+0.000
You
TokenYou
Feature activation+0.000
spend
Token spend
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+1.506
of
Token of
Feature activation+2.363
time
Token time
Feature activation+2.898
checking
Token checking
Feature activation+0.058
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Tokena
Feature activation+0.000
)
Token)
Feature activation+0.000
spent
Token spent
Feature activation+0.143
a
Token a
Feature activation+0.061
lot
Token lot
Feature activation+1.881
of
Token of
Feature activation+2.877
time
Token time
Feature activation+3.406
m
Token m
Feature activation+1.409
udd
Tokenudd
Feature activation+0.000
ying
Tokenying
Feature activation+0.000
the
Token the
Feature activation+0.000

Top DFA by src position
MAX = 5.393

of
Token of
Feature activation-0.007
Top resid features:
his
Token his
Feature activation+0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.051
Top resid features:
The
TokenThe
Feature activation-0.058
Top resid features:
Giants
Token Giants
Feature activation-0.010
Top resid features:
spent
Token spent
Feature activation+5.236
Top resid features:
$
Token $
Feature activation-0.157
Top resid features:
200
Token200
Feature activation-0.048
Top resid features:
million
Token million
Feature activation-0.049
Top resid features:
on
Token on
Feature activation+0.040
Top resid features:
payroll
Token payroll
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.015
Top resid features:
his
Token his
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.115
Top resid features:
The
TokenThe
Feature activation-0.032
Top resid features:
Giants
Token Giants
Feature activation-0.039
Top resid features:
spent
Token spent
Feature activation+5.393
Top resid features:
$
Token $
Feature activation-0.174
Top resid features:
200
Token200
Feature activation-0.268
Top resid features:
million
Token million
Feature activation+0.001
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
payroll
Token payroll
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.043
Top resid features:
Michael
Token Michael
Feature activation-0.050
Top resid features:
Bar
Token Bar
Feature activation-0.032
Top resid features:
a
Tokena
Feature activation+0.012
Top resid features:
)
Token)
Feature activation+0.007
Top resid features:
spent
Token spent
Feature activation+5.050
Top resid features:
a
Token a
Feature activation-0.047
Top resid features:
lot
Token lot
Feature activation-0.044
Top resid features:
of
Token of
Feature activation-0.106
Top resid features:
time
Token time
Feature activation-0.012
Top resid features:
m
Token m
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.025
Top resid features:
John
TokenJohn
Feature activation-0.014
Top resid features:
stone
Tokenstone
Feature activation-0.011
Top resid features:
,
Token,
Feature activation-0.020
Top resid features:
who
Token who
Feature activation-0.002
Top resid features:
spent
Token spent
Feature activation+4.502
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
second
Token second
Feature activation-0.047
Top resid features:
half
Token half
Feature activation+0.031
Top resid features:
of
Token of
Feature activation-0.031
Top resid features:
last
Token last
Feature activation+0.039
Top resid features:
Because
TokenBecause
Feature activation+0.048
Top resid features:
of
Token of
Feature activation-0.007
Top resid features:
this
Token this
Feature activation-0.030
Top resid features:
,
Token,
Feature activation-0.092
Top resid features:
I
Token I
Feature activation-0.062
Top resid features:
spent
Token spent
Feature activation+4.571
Top resid features:
three
Token three
Feature activation-0.065
Top resid features:
days
Token days
Feature activation+0.323
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
rocky
Token rocky
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.034
Top resid features:
I
Token I
Feature activation-0.008
Top resid features:
âĢ
TokenâĢ
Feature activation-0.032
Top resid features:
Ļ
TokenĻ
Feature activation-0.022
Top resid features:
ve
Tokenve
Feature activation-0.018
Top resid features:
spent
Token spent
Feature activation+4.808
Top resid features:
a
Token a
Feature activation-0.033
Top resid features:
lot
Token lot
Feature activation+0.014
Top resid features:
of
Token of
Feature activation-0.121
Top resid features:
time
Token time
Feature activation-0.010
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.213
Top resid features:
who
Token who
Feature activation-0.050
Top resid features:
spent
Token spent
Feature activation+4.592
Top resid features:
more
Token more
Feature activation+0.011
Top resid features:
than
Token than
Feature activation-0.101
Top resid features:
$
Token $
Feature activation-0.143
Top resid features:
142
Token142
Feature activation+0.293
Top resid features:
million
Token million
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.022
Top resid features:
Ċ
TokenĊ
Feature activation-0.043
Top resid features:
Ċ
TokenĊ
Feature activation-0.056
Top resid features:
I
TokenI
Feature activation-0.015
Top resid features:
then
Token then
Feature activation-0.045
Top resid features:
spent
Token spent
Feature activation+4.729
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
great
Token great
Feature activation-0.041
Top resid features:
number
Token number
Feature activation-0.042
Top resid features:
of
Token of
Feature activation-0.059
Top resid features:
hours
Token hours
Feature activation+0.052
Top resid features:
,
Token,
Feature activation-0.034
Top resid features:
I
Token I
Feature activation-0.008
Top resid features:
âĢ
TokenâĢ
Feature activation-0.036
Top resid features:
Ļ
TokenĻ
Feature activation-0.027
Top resid features:
ve
Tokenve
Feature activation-0.034
Top resid features:
spent
Token spent
Feature activation+4.719
Top resid features:
a
Token a
Feature activation-0.049
Top resid features:
lot
Token lot
Feature activation-0.006
Top resid features:
of
Token of
Feature activation-0.129
Top resid features:
time
Token time
Feature activation-0.018
Top resid features:
thinking
Token thinking
Feature activation+0.000
Top resid features:
symptoms
Token symptoms
Feature activation-0.029
Top resid features:
in
Token in
Feature activation+0.012
Top resid features:
half
Token half
Feature activation+0.003
Top resid features:
when
Token when
Feature activation-0.105
Top resid features:
they
Token they
Feature activation-0.067
Top resid features:
spent
Token spent
Feature activation+4.107
Top resid features:
21
Token 21
Feature activation+0.057
Top resid features:
days
Token days
Feature activation+0.309
Top resid features:
on
Token on
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
diet
Token diet
Feature activation+0.000
Top resid features:
average
Token average
Feature activation-0.021
Top resid features:
,
Token,
Feature activation-0.018
Top resid features:
these
Token these
Feature activation-0.029
Top resid features:
inmates
Token inmates
Feature activation+0.002
Top resid features:
have
Token have
Feature activation+0.019
Top resid features:
spent
Token spent
Feature activation+4.071
Top resid features:
15
Token 15
Feature activation+0.005
Top resid features:
years
Token years
Feature activation-0.008
Top resid features:
,
Token,
Feature activation-0.078
Top resid features:
7
Token 7
Feature activation-0.001
Top resid features:
months
Token months
Feature activation+0.368
Top resid features:
John
Token John
Feature activation-0.038
Top resid features:
V
Token V
Feature activation-0.007
Top resid features:
ign
Tokenign
Feature activation-0.014
Top resid features:
oc
Tokenoc
Feature activation-0.001
Top resid features:
chi
Tokenchi
Feature activation-0.041
Top resid features:
spent
Token spent
Feature activation+4.310
Top resid features:
some
Token some
Feature activation+0.052
Top resid features:
time
Token time
Feature activation+0.058
Top resid features:
on
Token on
Feature activation+0.007
Top resid features:
stage
Token stage
Feature activation+0.000
Top resid features:
talking
Token talking
Feature activation+0.000
Top resid features:
Awards
Token Awards
Feature activation-0.017
Top resid features:
Show
Token Show
Feature activation+0.008
Top resid features:
case
Tokencase
Feature activation-0.014
Top resid features:
,
Token,
Feature activation-0.045
Top resid features:
and
Token and
Feature activation-0.078
Top resid features:
spent
Token spent
Feature activation+4.218
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
rest
Token rest
Feature activation+0.048
Top resid features:
of
Token of
Feature activation+0.166
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
day
Token day
Feature activation+0.009
Top resid features:
Governor
Token Governor
Feature activation-0.022
Top resid features:
Walker
Token Walker
Feature activation-0.019
Top resid features:
and
Token and
Feature activation-0.054
Top resid features:
his
Token his
Feature activation-0.014
Top resid features:
allies
Token allies
Feature activation-0.107
Top resid features:
spent
Token spent
Feature activation+4.515
Top resid features:
$
Token $
Feature activation-0.113
Top resid features:
140
Token140
Feature activation+0.067
Top resid features:
million
Token million
Feature activation+0.002
Top resid features:
dollars
Token dollars
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.017
Top resid features:
National
Token National
Feature activation-0.005
Top resid features:
League
Token League
Feature activation+0.001
Top resid features:
West
Token West
Feature activation-0.038
Top resid features:
,
Token,
Feature activation-0.090
Top resid features:
spent
Token spent
Feature activation+4.424
Top resid features:
$
Token $
Feature activation-0.154
Top resid features:
300
Token300
Feature activation+0.021
Top resid features:
million
Token million
Feature activation+0.036
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Governor
Token Governor
Feature activation-0.020
Top resid features:
Walker
Token Walker
Feature activation-0.019
Top resid features:
and
Token and
Feature activation-0.043
Top resid features:
his
Token his
Feature activation+0.010
Top resid features:
allies
Token allies
Feature activation-0.094
Top resid features:
spent
Token spent
Feature activation+4.499
Top resid features:
$
Token $
Feature activation-0.020
Top resid features:
140
Token140
Feature activation+0.030
Top resid features:
million
Token million
Feature activation-0.028
Top resid features:
dollars
Token dollars
Feature activation-0.060
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
old
Tokenold
Feature activation-0.013
Top resid features:
m
Token m
Feature activation-0.008
Top resid features:
ong
Tokenong
Feature activation+0.001
Top resid features:
rel
Tokenrel
Feature activation-0.025
Top resid features:
,
Token,
Feature activation-0.088
Top resid features:
spent
Token spent
Feature activation+4.445
Top resid features:
a
Token a
Feature activation-0.014
Top resid features:
total
Token total
Feature activation+0.089
Top resid features:
of
Token of
Feature activation-0.087
Top resid features:
6
Token 6
Feature activation-0.017
Top resid features:
89
Token89
Feature activation+0.006
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
adventure
Token adventure
Feature activation-0.024
Top resid features:
,
Token,
Feature activation-0.018
Top resid features:
and
Token and
Feature activation-0.054
Top resid features:
we
Token we
Feature activation-0.055
Top resid features:
spent
Token spent
Feature activation+4.554
Top resid features:
a
Token a
Feature activation-0.050
Top resid features:
lot
Token lot
Feature activation-0.029
Top resid features:
of
Token of
Feature activation-0.093
Top resid features:
time
Token time
Feature activation+0.006
Top resid features:
acting
Token acting
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
work
Token work
Feature activation-0.045
Top resid features:
.
Token.
Feature activation-0.091
Top resid features:
"
Token "
Feature activation-0.011
Top resid features:
You
TokenYou
Feature activation-0.018
Top resid features:
spend
Token spend
Feature activation+4.472
Top resid features:
a
Token a
Feature activation-0.073
Top resid features:
lot
Token lot
Feature activation-0.028
Top resid features:
of
Token of
Feature activation-0.076
Top resid features:
time
Token time
Feature activation-0.030
Top resid features:
checking
Token checking
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.045
Top resid features:
Michael
Token Michael
Feature activation-0.082
Top resid features:
Bar
Token Bar
Feature activation-0.053
Top resid features:
a
Tokena
Feature activation+0.009
Top resid features:
)
Token)
Feature activation+0.033
Top resid features:
spent
Token spent
Feature activation+4.513
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
lot
Token lot
Feature activation-0.184
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
m
Token m
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.03

Head 2: 0.04

Head 3: 0.05

Head 4: 0.05

Head 5: 0.06

Head 6: 0.04

Head 7: 0.02

Head 8: 0.50

Head 9: 0.07

Head 10: 0.05

Head 11: 0.02

Positive logits

hedon1.67

agos1.66

educ1.34

████████1.30

ibur1.29

ocating1.28

anwhile1.27

1.24

hea1.24

amazon1.23

oling1.23

Craigslist1.22

frivol1.21

Stim1.21

Tradable1.21

Revelations1.19

????????1.19

aganda1.19

adesh1.19

aples1.18

Negative logits

Ey-1.50

��-1.39

stood-1.36

gravity-1.22

Sky-1.19

MC-1.19

tempered-1.19

Winged-1.18

fields-1.17

arius-1.17

oste-1.17

HEAD-1.16

wrinkles-1.15

fields-1.14

ghosts-1.14

��-1.13

ozyg-1.12

-1.12

taller-1.11

Skies-1.11

INTERVAL 3.256 - 3.618
CONTAINS 0.001%

Giants
Token Giants
Feature activation+0.000
spent
Token spent
Feature activation+0.000
$
Token $
Feature activation+0.914
200
Token200
Feature activation+1.968
million
Token million
Feature activation+3.438
on
Token on
Feature activation+3.618
payroll
Token payroll
Feature activation+0.502
this
Token this
Feature activation+0.026
year
Token year
Feature activation+1.790
,
Token,
Feature activation+0.103
which
Token which
Feature activation+0.000
spent
Token spent
Feature activation+0.000
more
Token more
Feature activation+1.080
than
Token than
Feature activation+2.278
$
Token $
Feature activation+2.630
142
Token142
Feature activation+1.084
million
Token million
Feature activation+3.267
of
Token of
Feature activation+1.233
her
Token her
Feature activation+0.456
own
Token own
Feature activation+0.000
money
Token money
Feature activation+0.324
in
Token in
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Giants
Token Giants
Feature activation+0.000
spent
Token spent
Feature activation+0.000
$
Token $
Feature activation+0.914
200
Token200
Feature activation+1.968
million
Token million
Feature activation+3.438
on
Token on
Feature activation+3.618
payroll
Token payroll
Feature activation+0.502
this
Token this
Feature activation+0.026
year
Token year
Feature activation+1.790
,
Token,
Feature activation+0.103
)
Token)
Feature activation+0.000
spent
Token spent
Feature activation+0.143
a
Token a
Feature activation+0.061
lot
Token lot
Feature activation+1.881
of
Token of
Feature activation+2.877
time
Token time
Feature activation+3.406
m
Token m
Feature activation+1.409
udd
Tokenudd
Feature activation+0.000
ying
Tokenying
Feature activation+0.000
the
Token the
Feature activation+0.000
waters
Token waters
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
spent
Token spent
Feature activation+0.000
three
Token three
Feature activation+0.336
days
Token days
Feature activation+0.749
on
Token on
Feature activation+3.341
a
Token a
Feature activation+0.440
rocky
Token rocky
Feature activation+0.000
floor
Token floor
Feature activation+0.000
on
Token on
Feature activation+2.519
my
Token my
Feature activation+0.000

INTERVAL 2.895 - 3.256
CONTAINS 0.001%

oc
Tokenoc
Feature activation+0.000
chi
Tokenchi
Feature activation+0.000
spent
Token spent
Feature activation+0.000
some
Token some
Feature activation+0.236
time
Token time
Feature activation+1.979
on
Token on
Feature activation+3.075
stage
Token stage
Feature activation+0.403
talking
Token talking
Feature activation+0.000
about
Token about
Feature activation+0.000
Infinity
Token Infinity
Feature activation+0.000
2
Token 2
Feature activation+0.000
when
Token when
Feature activation+0.000
they
Token they
Feature activation+0.000
spent
Token spent
Feature activation+0.000
21
Token 21
Feature activation+0.307
days
Token days
Feature activation+1.492
on
Token on
Feature activation+3.095
a
Token a
Feature activation+0.064
diet
Token diet
Feature activation+0.240
low
Token low
Feature activation+0.000
in
Token in
Feature activation+0.000
F
Token F
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+1.027
of
Token of
Feature activation+2.691
time
Token time
Feature activation+3.179
thinking
Token thinking
Feature activation+0.179
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
sacrament
Token sacrament
Feature activation+0.000
of
Token of
Feature activation+0.000
we
Token we
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+1.329
of
Token of
Feature activation+2.257
time
Token time
Feature activation+2.955
acting
Token acting
Feature activation+0.712
those
Token those
Feature activation+0.000
things
Token things
Feature activation+0.000
out
Token out
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.075
total
Token total
Feature activation+1.622
of
Token of
Feature activation+1.596
6
Token 6
Feature activation+0.905
89
Token89
Feature activation+0.242
days
Token days
Feature activation+2.963
at
Token at
Feature activation+2.209
the
Token the
Feature activation+0.000
charity
Token charity
Feature activation+0.000
's
Token's
Feature activation+0.000
Old
Token Old
Feature activation+0.000

INTERVAL 2.533 - 2.895
CONTAINS 0.005%

.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
I
Token I
Feature activation+0.000
spent
Token spent
Feature activation+0.000
all
Token all
Feature activation+0.144
day
Token day
Feature activation+2.580
Friday
Token Friday
Feature activation+1.943
working
Token working
Feature activation+0.167
the
Token the
Feature activation+0.000
logistics
Token logistics
Feature activation+0.000
of
Token of
Feature activation+0.136
spent
Token spent
Feature activation+0.000
$
Token $
Feature activation+0.719
8
Token8
Feature activation+1.480
16
Token16
Feature activation+1.210
,
Token,
Feature activation+1.612
000
Token000
Feature activation+2.800
on
Token on
Feature activation+2.836
consulting
Token consulting
Feature activation+0.000
(
Token (
Feature activation+0.000
d
Tokend
Feature activation+0.000
oled
Tokenoled
Feature activation+0.000
of
Token of
Feature activation+0.000
Commerce
Token Commerce
Feature activation+0.000
spent
Token spent
Feature activation+0.000
$
Token $
Feature activation+0.562
32
Token32
Feature activation+1.104
million
Token million
Feature activation+2.827
on
Token on
Feature activation+2.790
67
Token 67
Feature activation+0.066
House
Token House
Feature activation+0.000
and
Token and
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
t
Tokent
Feature activation+0.000
have
Token have
Feature activation+0.000
normally
Token normally
Feature activation+0.000
spent
Token spent
Feature activation+0.000
one
Token one
Feature activation+0.821
of
Token of
Feature activation+2.542
my
Token my
Feature activation+1.711
I
Token I
Feature activation+0.461
OU
TokenOU
Feature activation+0.000
s
Tokens
Feature activation+0.186
on
Token on
Feature activation+2.804
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+0.000
great
Token great
Feature activation+0.780
number
Token number
Feature activation+0.999
of
Token of
Feature activation+2.037
hours
Token hours
Feature activation+2.590
on
Token on
Feature activation+3.252
a
Token a
Feature activation+0.000
surprisingly
Token surprisingly
Feature activation+0.000
uncomfortable
Token uncomfortable
Feature activation+0.000
coach
Token coach
Feature activation+0.000

INTERVAL 2.171 - 2.533
CONTAINS 0.004%

I
TokenI
Feature activation+0.000
hope
Token hope
Feature activation+0.000
you
Token you
Feature activation+0.000
spend
Token spend
Feature activation+0.000
every
Token every
Feature activation+0.679
day
Token day
Feature activation+2.281
in
Token in
Feature activation+1.776
prison
Token prison
Feature activation+0.970
thinking
Token thinking
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
and
Token and
Feature activation+0.000
spend
Token spend
Feature activation+0.000
a
Token a
Feature activation+0.000
couple
Token couple
Feature activation+1.052
of
Token of
Feature activation+2.205
hours
Token hours
Feature activation+2.091
folding
Token folding
Feature activation+0.179
proteins
Token proteins
Feature activation+0.000
and
Token and
Feature activation+0.000
RNA
Token RNA
Feature activation+0.000
I
Token I
Feature activation+0.000
spent
Token spent
Feature activation+0.000
my
Token my
Feature activation+0.070
Super
Token Super
Feature activation+1.149
bowl
Tokenbowl
Feature activation+1.675
Sunday
Token Sunday
Feature activation+2.439
organizing
Token organizing
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
important
Token important
Feature activation+0.248
section
Token section
Feature activation+0.000
in
Token in
Feature activation+0.000
Kentucky
Token Kentucky
Feature activation+0.000
spent
Token spent
Feature activation+0.000
five
Token five
Feature activation+0.444
extra
Token extra
Feature activation+2.322
months
Token months
Feature activation+2.400
in
Token in
Feature activation+1.696
jail
Token jail
Feature activation+1.095
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
human
Token human
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
spent
Token spent
Feature activation+0.000
the
Token the
Feature activation+0.000
majority
Token majority
Feature activation+0.690
of
Token of
Feature activation+2.184
his
Token his
Feature activation+1.397
college
Token college
Feature activation+1.252
football
Token football
Feature activation+0.628
career
Token career
Feature activation+1.800
working
Token working
Feature activation+0.000

INTERVAL 1.809 - 2.171
CONTAINS 0.006%

and
Token and
Feature activation+0.000
spent
Token spent
Feature activation+0.000
the
Token the
Feature activation+0.000
rest
Token rest
Feature activation+1.317
of
Token of
Feature activation+0.992
the
Token the
Feature activation+1.996
day
Token day
Feature activation+3.036
walking
Token walking
Feature activation+0.059
around
Token around
Feature activation+0.000
campus
Token campus
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
to
Token to
Feature activation+0.000
spend
Token spend
Feature activation+0.000
a
Token a
Feature activation+0.000
couple
Token couple
Feature activation+0.951
of
Token of
Feature activation+1.954
weeks
Token weeks
Feature activation+2.100
eating
Token eating
Feature activation+0.551
fish
Token fish
Feature activation+0.000
that
Token that
Feature activation+0.000
were
Token were
Feature activation+0.000
still
Token still
Feature activation+0.000
ign
Tokenign
Feature activation+0.000
oc
Tokenoc
Feature activation+0.000
chi
Tokenchi
Feature activation+0.000
spent
Token spent
Feature activation+0.000
some
Token some
Feature activation+0.236
time
Token time
Feature activation+1.979
on
Token on
Feature activation+3.075
stage
Token stage
Feature activation+0.403
talking
Token talking
Feature activation+0.000
about
Token about
Feature activation+0.000
Infinity
Token Infinity
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
spent
Token spent
Feature activation+0.000
three
Token three
Feature activation+0.630
decades
Token decades
Feature activation+1.428
building
Token building
Feature activation+1.917
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
many
Token many
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
spend
Token spend
Feature activation+0.000
a
Token a
Feature activation+0.000
couple
Token couple
Feature activation+1.052
of
Token of
Feature activation+2.205
hours
Token hours
Feature activation+2.091
folding
Token folding
Feature activation+0.179
proteins
Token proteins
Feature activation+0.000
and
Token and
Feature activation+0.000
RNA
Token RNA
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 1.447 - 1.809
CONTAINS 0.006%

accused
Token accused
Feature activation+0.000
of
Token of
Feature activation+0.000
spending
Token spending
Feature activation+0.000
more
Token more
Feature activation+0.591
than
Token than
Feature activation+0.111
$
Token $
Feature activation+1.637
100
Token100
Feature activation+0.595
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.907
in
Token in
Feature activation+0.000
union
Token union
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
You
TokenYou
Feature activation+0.000
spend
Token spend
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+1.506
of
Token of
Feature activation+2.363
time
Token time
Feature activation+2.898
checking
Token checking
Feature activation+0.058
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
It
Token It
Feature activation+0.000
spends
Token spends
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+1.239
more
Token more
Feature activation+2.682
time
Token time
Feature activation+1.632
talking
Token talking
Feature activation+0.000
about
Token about
Feature activation+0.000
how
Token how
Feature activation+0.000
many
Token many
Feature activation+0.000
people
Token people
Feature activation+0.000
half
Token half
Feature activation+0.000
when
Token when
Feature activation+0.000
they
Token they
Feature activation+0.000
spent
Token spent
Feature activation+0.000
21
Token 21
Feature activation+0.307
days
Token days
Feature activation+1.492
on
Token on
Feature activation+3.095
a
Token a
Feature activation+0.064
diet
Token diet
Feature activation+0.240
low
Token low
Feature activation+0.000
in
Token in
Feature activation+0.000
%
Token%
Feature activation+0.899
of
Token of
Feature activation+1.246
your
Token your
Feature activation+0.573
bonus
Token bonus
Feature activation+0.000
points
Token points
Feature activation+0.000
on
Token on
Feature activation+1.482
most
Token most
Feature activation+0.000
module
Token module
Feature activation+0.000
from
Token from
Feature activation+0.000
our
Token our
Feature activation+0.000
E
Token E
Feature activation+0.000

INTERVAL 1.085 - 1.447
CONTAINS 0.009%

spend
Token spend
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.748
60
Token 60
Feature activation+0.588
%
Token%
Feature activation+0.901
of
Token of
Feature activation+1.235
your
Token your
Feature activation+0.580
bonus
Token bonus
Feature activation+0.000
points
Token points
Feature activation+0.009
on
Token on
Feature activation+1.751
most
Token most
Feature activation+0.000
common
Token common
Feature activation+0.000
?
Token?
Feature activation+0.000
They
Token They
Feature activation+0.000
spent
Token spent
Feature activation+0.000
this
Token this
Feature activation+0.097
week
Token week
Feature activation+1.436
beating
Token beating
Feature activation+2.645
up
Token up
Feature activation+0.000
on
Token on
Feature activation+1.391
Canadian
Token Canadian
Feature activation+0.000
teams
Token teams
Feature activation+0.034
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.000
spend
Token spend
Feature activation+0.000
much
Token much
Feature activation+0.659
of
Token of
Feature activation+1.984
my
Token my
Feature activation+1.272
time
Token time
Feature activation+2.457
travelling
Token travelling
Feature activation+0.281
the
Token the
Feature activation+0.000
length
Token length
Feature activation+0.574
and
Token and
Feature activation+0.005
to
Token to
Feature activation+0.000
spend
Token spend
Feature activation+0.000
an
Token an
Feature activation+0.000
abnorm
Token abnorm
Feature activation+0.000
ally
Tokenally
Feature activation+0.669
large
Token large
Feature activation+1.241
amount
Token amount
Feature activation+1.475
of
Token of
Feature activation+0.949
time
Token time
Feature activation+2.519
repairing
Token repairing
Feature activation+0.000
incoming
Token incoming
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
all
Token all
Feature activation+0.000
spent
Token spent
Feature activation+0.000
years
Token years
Feature activation+0.701
psych
Token psych
Feature activation+1.206
oan
Tokenoan
Feature activation+0.313
aly
Tokenaly
Feature activation+0.000
zing
Tokenzing
Feature activation+0.366
Bush
Token Bush
Feature activation+0.440
and
Token and
Feature activation+0.000

INTERVAL 0.724 - 1.085
CONTAINS 0.012%

one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
which
Token which
Feature activation+0.000
he
Token he
Feature activation+0.000
spent
Token spent
Feature activation+0.000
on
Token on
Feature activation+0.770
the
Token the
Feature activation+0.153
team
Token team
Feature activation+1.591
âĢ
TokenâĢ
Feature activation+0.336
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.559
this
Token this
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
spent
Token spent
Feature activation+0.000
three
Token three
Feature activation+0.336
days
Token days
Feature activation+0.749
on
Token on
Feature activation+3.341
a
Token a
Feature activation+0.440
rocky
Token rocky
Feature activation+0.000
floor
Token floor
Feature activation+0.000
on
Token on
Feature activation+2.519
to
Token to
Feature activation+0.000
spend
Token spend
Feature activation+0.000
significant
Token significant
Feature activation+0.000
sums
Token sums
Feature activation+0.493
of
Token of
Feature activation+0.498
public
Token public
Feature activation+0.741
money
Token money
Feature activation+1.461
fighting
Token fighting
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
closure
Tokenclosure
Feature activation+0.000
had
Token had
Feature activation+0.000
spent
Token spent
Feature activation+0.000
most
Token most
Feature activation+0.404
of
Token of
Feature activation+1.937
her
Token her
Feature activation+1.796
professional
Token professional
Feature activation+0.790
career
Token career
Feature activation+1.596
in
Token in
Feature activation+0.658
the
Token the
Feature activation+0.000
military
Token military
Feature activation+0.000
.
Token.
Feature activation+0.000
while
Token while
Feature activation+0.000
62
Token 62
Feature activation+0.000
%
Token%
Feature activation+0.000
spent
Token spent
Feature activation+0.000
more
Token more
Feature activation+0.630
than
Token than
Feature activation+0.892
two
Token two
Feature activation+1.201
hours
Token hours
Feature activation+1.936
a
Token a
Feature activation+0.471
week
Token week
Feature activation+1.256
on
Token on
Feature activation+1.799

INTERVAL 0.362 - 0.724
CONTAINS 0.014%

a
Token a
Feature activation+0.000
polymer
Token polymer
Feature activation+0.000
company
Token company
Feature activation+0.000
,
Token,
Feature activation+0.000
spent
Token spent
Feature activation+0.000
$
Token $
Feature activation+0.722
8
Token8
Feature activation+1.298
.
Token.
Feature activation+1.381
2
Token2
Feature activation+1.278
million
Token million
Feature activation+2.860
of
Token of
Feature activation+1.554
spent
Token spent
Feature activation+0.000
many
Token many
Feature activation+0.083
years
Token years
Feature activation+0.750
in
Token in
Feature activation+1.599
academic
Token academic
Feature activation+0.007
environments
Token environments
Feature activation+0.426
,
Token,
Feature activation+0.223
giving
Token giving
Feature activation+0.000
her
Token her
Feature activation+0.000
an
Token an
Feature activation+0.000
insider
Token insider
Feature activation+0.000
choose
Token choose
Feature activation+0.000
to
Token to
Feature activation+0.000
spend
Token spend
Feature activation+0.000
significant
Token significant
Feature activation+0.000
sums
Token sums
Feature activation+0.493
of
Token of
Feature activation+0.498
public
Token public
Feature activation+0.741
money
Token money
Feature activation+1.461
fighting
Token fighting
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
team
Token team
Feature activation+0.000
spent
Token spent
Feature activation+0.000
months
Token months
Feature activation+0.509
systematically
Token systematically
Feature activation+0.632
ruling
Token ruling
Feature activation+0.000
out
Token out
Feature activation+0.000
all
Token all
Feature activation+0.000
other
Token other
Feature activation+0.000
alternative
Token alternative
Feature activation+0.000
community
Token community
Feature activation+0.000
college
Token college
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
spent
Token spent
Feature activation+0.000
some
Token some
Feature activation+0.480
time
Token time
Feature activation+1.691
surfing
Token surfing
Feature activation+0.034
Web
Token Web
Feature activation+0.000
MD
TokenMD
Feature activation+0.000
,
Token,
Feature activation+0.393

INTERVAL 0.000 - 0.362
CONTAINS 99.943%

the
Token the
Feature activation+0.000
Sau
Token Sau
Feature activation+0.000
ber
Tokenber
Feature activation+0.000
for
Token for
Feature activation+0.000
example
Token example
Feature activation+0.000
,
Token,
Feature activation+0.000
black
Token black
Feature activation+0.000
,
Token,
Feature activation+0.000
white
Token white
Feature activation+0.000
and
Token and
Feature activation+0.000
red
Token red
Feature activation+0.000
murdered
Token murdered
Feature activation+0.000
friend
Token friend
Feature activation+0.000
inv
Token inv
Feature activation+0.000
oc
Tokenoc
Feature activation+0.000
atively
Tokenatively
Feature activation+0.000
as
Token as
Feature activation+0.000
"
Token "
Feature activation+0.000
é
Tokené
Feature activation+0.000
c
Tokenc
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
vant
Tokenvant
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Min
TokenMin
Feature activation+0.000
ister
Tokenister
Feature activation+0.000
of
Token of
Feature activation+0.000
State
Token State
Feature activation+0.000
for
Token for
Feature activation+0.000
Information
Token Information
Feature activation+0.000
and
Token and
Feature activation+0.000
Broadcasting
Token Broadcasting
Feature activation+0.000
Raj
Token Raj
Feature activation+0.000
y
Tokeny
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
quite
Token quite
Feature activation+0.000
the
Token the
Feature activation+0.000
leap
Token leap
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
that
Token that
Feature activation+0.000
finished
Token finished
Feature activation+0.000
No
Token No
Feature activation+0.000
one
Token one
Feature activation+0.000
where
Token where
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
have
Token have
Feature activation+0.000
sought
Token sought
Feature activation+0.000
to
Token to
Feature activation+0.000
find
Token find
Feature activation+0.000
common
Token common
Feature activation+0.000
ground
Token ground
Feature activation+0.000
with
Token with
Feature activation+0.000
Republicans
Token Republicans
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 H2.8: (feature 24239)

TOP ACTIVATIONS
MAX = 2.585

lifestyle
Token lifestyle
Feature activation+0.000
and
Token and
Feature activation+0.000
either
Token either
Feature activation+0.000
start
Token start
Feature activation+0.000
a
Token a
Feature activation+0.126
business
Token business
Feature activation+2.220
or
Token or
Feature activation+0.000
become
Token become
Feature activation+0.000
that
Token that
Feature activation+0.000
free
Token free
Feature activation+0.000
agent
Token agent
Feature activation+0.000
Orlando
Token Orlando
Feature activation+0.000
Magic
Token Magic
Feature activation+0.000
have
Token have
Feature activation+0.000
started
Token started
Feature activation+0.000
this
Token this
Feature activation+0.391
season
Token season
Feature activation+2.202
really
Token really
Feature activation+0.456
well
Token well
Feature activation+0.639
,
Token,
Feature activation+0.000
going
Token going
Feature activation+0.000
2
Token 2
Feature activation+0.000
minded
Token minded
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
the
Token the
Feature activation+0.000
season
Token season
Feature activation+1.839
with
Token with
Feature activation+2.097
Emmanuel
Token Emmanuel
Feature activation+0.000
Ad
Token Ad
Feature activation+0.000
eb
Tokeneb
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
or
Tokenor
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
started
Token started
Feature activation+0.000
half
Token half
Feature activation+0.000
the
Token the
Feature activation+0.530
season
Token season
Feature activation+2.096
and
Token and
Feature activation+1.071
I
Token I
Feature activation+0.532
worked
Token worked
Feature activation+0.120
my
Token my
Feature activation+0.000
way
Token way
Feature activation+0.000
Heath
Token Heath
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
begin
Token begin
Feature activation+0.000
the
Token the
Feature activation+0.000
process
Token process
Feature activation+2.048
all
Token all
Feature activation+0.410
over
Token over
Feature activation+0.381
again
Token again
Feature activation+0.227
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
-
Token -
Feature activation+0.000
Legislation
Token Legislation
Feature activation+0.000
to
Token to
Feature activation+0.000
begin
Token begin
Feature activation+0.000
the
Token the
Feature activation+0.000
process
Token process
Feature activation+2.030
of
Token of
Feature activation+0.000
transferring
Token transferring
Feature activation+0.403
European
Token European
Feature activation+0.000
Union
Token Union
Feature activation+0.000
law
Token law
Feature activation+0.000
at
Tokenat
Feature activation+0.043
k
Tokenk
Feature activation+0.000
al
Tokenal
Feature activation+0.000
"
Token"
Feature activation+0.206
certification
Token certification
Feature activation+0.153
process
Token process
Feature activation+1.954
for
Token for
Feature activation+0.000
those
Token those
Feature activation+0.000
filmmakers
Token filmmakers
Feature activation+0.000
who
Token who
Feature activation+0.000
are
Token are
Feature activation+0.000
your
Token your
Feature activation+0.000
own
Token own
Feature activation+0.381
100
Token 100
Feature activation+0.283
-
Token-
Feature activation+0.000
day
Tokenday
Feature activation+0.383
project
Token project
Feature activation+1.947
!
Token!
Feature activation+0.084
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Scroll
TokenScroll
Feature activation+0.000
down
Token down
Feature activation+0.000
're
Token're
Feature activation+0.000
supposed
Token supposed
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
our
Token our
Feature activation+0.000
new
Token new
Feature activation+1.932
Republican
Token Republican
Feature activation+0.382
era
Token era
Feature activation+1.642
.'"
Token.'"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
great
Token great
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
a
Token a
Feature activation+0.114
career
Token career
Feature activation+1.925
,
Token,
Feature activation+0.387
the
Token the
Feature activation+0.256
emotional
Token emotional
Feature activation+0.099
factor
Token factor
Feature activation+0.211
of
Token of
Feature activation+0.000
son
Tokenson
Feature activation+0.000
had
Token had
Feature activation+0.000
barely
Token barely
Feature activation+0.000
started
Token started
Feature activation+0.000
his
Token his
Feature activation+0.000
new
Token new
Feature activation+1.875
job
Token job
Feature activation+0.901
at
Token at
Feature activation+0.546
the
Token the
Feature activation+0.000
University
Token University
Feature activation+0.000
of
Token of
Feature activation+0.000
Virgin
Token Virgin
Feature activation+0.000
Galactic
Token Galactic
Feature activation+0.000
will
Token will
Feature activation+0.000
begin
Token begin
Feature activation+0.000
commercial
Token commercial
Feature activation+1.057
operations
Token operations
Feature activation+1.851
here
Token here
Feature activation+0.769
at
Token at
Feature activation+0.954
Spac
Token Spac
Feature activation+0.000
eport
Tokeneport
Feature activation+0.000
America
Token America
Feature activation+0.000
as
Tokenas
Feature activation+0.000
minded
Token minded
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
the
Token the
Feature activation+0.000
season
Token season
Feature activation+1.839
with
Token with
Feature activation+2.097
Emmanuel
Token Emmanuel
Feature activation+0.000
Ad
Token Ad
Feature activation+0.000
eb
Tokeneb
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
"
Token "
Feature activation+0.000
Jump
TokenJump
Feature activation+0.000
-
Token-
Feature activation+0.000
Start
TokenStart
Feature activation+0.000
Our
Token Our
Feature activation+0.000
Business
Token Business
Feature activation+1.803
Start
Token Start
Feature activation+0.000
-
Token-
Feature activation+0.000
U
TokenU
Feature activation+0.646
ps
Tokenps
Feature activation+0.298
Act
Token Act
Feature activation+0.000
the
Token the
Feature activation+0.200
late
Token late
Feature activation+0.186
14
Token 14
Feature activation+0.211
70
Token70
Feature activation+0.000
s
Tokens
Feature activation+0.308
when
Token when
Feature activation+1.779
Spain
Token Spain
Feature activation+0.000
's
Token's
Feature activation+0.000
King
Token King
Feature activation+0.000
Ferdinand
Token Ferdinand
Feature activation+0.000
and
Token and
Feature activation+0.000
Aaron
TokenAaron
Feature activation+0.000
Cook
Token Cook
Feature activation+0.000
will
Token will
Feature activation+0.000
start
Token start
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.465
against
Token against
Feature activation+1.775
Baltimore
Token Baltimore
Feature activation+0.000
in
Token in
Feature activation+0.220
place
Token place
Feature activation+0.000
of
Token of
Feature activation+0.000
Josh
Token Josh
Feature activation+0.000
Should
Token Should
Feature activation+0.000
he
Token he
Feature activation+0.000
start
Token start
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+1.591
step
Token step
Feature activation+1.770
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
courts
Token courts
Feature activation+0.000
hip
Tokenhip
Feature activation+0.000
ritual
Token ritual
Feature activation+0.740
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
begins
Token begins
Feature activation+0.000
the
Token the
Feature activation+0.000
journey
Token journey
Feature activation+1.766
into
Token into
Feature activation+0.000
Haskell
Token Haskell
Feature activation+0.000
frameworks
Token frameworks
Feature activation+0.000
.
Token.
Feature activation+0.188
Ċ
TokenĊ
Feature activation+0.000
Works
TokenWorks
Feature activation+0.000
film
Token film
Feature activation+0.000
that
Token that
Feature activation+0.000
started
Token started
Feature activation+0.000
it
Token it
Feature activation+0.185
all
Token all
Feature activation+1.760
,
Token,
Feature activation+0.465
brings
Token brings
Feature activation+0.000
the
Token the
Feature activation+0.000
hilarious
Token hilarious
Feature activation+0.000
story
Token story
Feature activation+0.000
Patriot
Token Patriot
Feature activation+0.000
Act
Token Act
Feature activation+0.000
has
Token has
Feature activation+0.000
begun
Token begun
Feature activation+0.000
its
Token its
Feature activation+0.062
course
Token course
Feature activation+1.743
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
House
Token House
Feature activation+0.000
,
Token,
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000

Top DFA by src position
MAX = 3.103

choose
Token choose
Feature activation+0.034
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
lifestyle
Token lifestyle
Feature activation+0.053
Top resid features:
and
Token and
Feature activation-0.049
Top resid features:
either
Token either
Feature activation-0.040
Top resid features:
start
Token start
Feature activation+2.913
Top resid features:
a
Token a
Feature activation+0.358
Top resid features:
business
Token business
Feature activation+0.055
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
become
Token become
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.031
Top resid features:
The
TokenThe
Feature activation-0.023
Top resid features:
Orlando
Token Orlando
Feature activation-0.002
Top resid features:
Magic
Token Magic
Feature activation-0.006
Top resid features:
have
Token have
Feature activation-0.125
Top resid features:
started
Token started
Feature activation+3.103
Top resid features:
this
Token this
Feature activation+0.308
Top resid features:
season
Token season
Feature activation+0.138
Top resid features:
really
Token really
Feature activation+0.000
Top resid features:
well
Token well
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.052
Top resid features:
as
Tokenas
Feature activation-0.015
Top resid features:
minded
Token minded
Feature activation+0.017
Top resid features:
to
Token to
Feature activation-0.044
Top resid features:
start
Token start
Feature activation+2.710
Top resid features:
the
Token the
Feature activation+0.302
Top resid features:
season
Token season
Feature activation+0.270
Top resid features:
with
Token with
Feature activation+0.085
Top resid features:
Emmanuel
Token Emmanuel
Feature activation+0.000
Top resid features:
Ad
Token Ad
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.004
Top resid features:
for
Token for
Feature activation+0.018
Top resid features:
anything
Token anything
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.035
Top resid features:
I
Token I
Feature activation-0.005
Top resid features:
started
Token started
Feature activation+2.771
Top resid features:
half
Token half
Feature activation+0.075
Top resid features:
the
Token the
Feature activation+0.156
Top resid features:
season
Token season
Feature activation+0.155
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
result
Token result
Feature activation-0.026
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
Heath
Token Heath
Feature activation+0.059
Top resid features:
had
Token had
Feature activation+0.007
Top resid features:
to
Token to
Feature activation-0.150
Top resid features:
begin
Token begin
Feature activation+2.702
Top resid features:
the
Token the
Feature activation+0.313
Top resid features:
process
Token process
Feature activation+0.139
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
again
Token again
Feature activation+0.000
Top resid features:
Reuters
TokenReuters
Feature activation-0.010
Top resid features:
)
Token)
Feature activation+0.006
Top resid features:
-
Token -
Feature activation-0.011
Top resid features:
Legislation
Token Legislation
Feature activation+0.099
Top resid features:
to
Token to
Feature activation-0.241
Top resid features:
begin
Token begin
Feature activation+2.891
Top resid features:
the
Token the
Feature activation+0.282
Top resid features:
process
Token process
Feature activation+0.114
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
transferring
Token transferring
Feature activation+0.000
Top resid features:
European
Token European
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.041
Top resid features:
We
Token We
Feature activation+0.003
Top resid features:
also
Token also
Feature activation+0.003
Top resid features:
plan
Token plan
Feature activation+0.033
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
start
Token start
Feature activation+2.407
Top resid features:
a
Token a
Feature activation+0.131
Top resid features:
"
Token "
Feature activation+0.037
Top resid features:
t
Tokent
Feature activation+0.009
Top resid features:
at
Tokenat
Feature activation+0.036
Top resid features:
k
Tokenk
Feature activation+0.033
Top resid features:
pand
Token pand
Feature activation+0.015
Top resid features:
as
Tokenas
Feature activation+0.014
Top resid features:
are
Token are
Feature activation-0.016
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.006
Top resid features:
consider
Token consider
Feature activation+0.033
Top resid features:
starting
Token starting
Feature activation+2.488
Top resid features:
your
Token your
Feature activation+0.140
Top resid features:
own
Token own
Feature activation+0.032
Top resid features:
100
Token 100
Feature activation+0.030
Top resid features:
-
Token-
Feature activation+0.087
Top resid features:
day
Tokenday
Feature activation+0.138
Top resid features:
how
Token how
Feature activation-0.033
Top resid features:
we
Token we
Feature activation+0.002
Top resid features:
're
Token're
Feature activation-0.093
Top resid features:
supposed
Token supposed
Feature activation-0.046
Top resid features:
to
Token to
Feature activation-0.066
Top resid features:
start
Token start
Feature activation+2.647
Top resid features:
our
Token our
Feature activation+0.452
Top resid features:
new
Token new
Feature activation+0.095
Top resid features:
Republican
Token Republican
Feature activation+0.000
Top resid features:
era
Token era
Feature activation+0.000
Top resid features:
.'"
Token.'"
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
great
Token great
Feature activation+0.021
Top resid features:
way
Token way
Feature activation+0.010
Top resid features:
to
Token to
Feature activation-0.063
Top resid features:
start
Token start
Feature activation+2.559
Top resid features:
a
Token a
Feature activation+0.280
Top resid features:
career
Token career
Feature activation+0.116
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
emotional
Token emotional
Feature activation+0.000
Top resid features:
Jerry
Token Jerry
Feature activation+0.000
Top resid features:
Dob
Token Dob
Feature activation-0.006
Top resid features:
son
Tokenson
Feature activation-0.015
Top resid features:
had
Token had
Feature activation-0.057
Top resid features:
barely
Token barely
Feature activation+0.122
Top resid features:
started
Token started
Feature activation+2.276
Top resid features:
his
Token his
Feature activation+0.502
Top resid features:
new
Token new
Feature activation+0.080
Top resid features:
job
Token job
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
completed
Token completed
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
Virgin
Token Virgin
Feature activation+0.043
Top resid features:
Galactic
Token Galactic
Feature activation-0.004
Top resid features:
will
Token will
Feature activation-0.110
Top resid features:
begin
Token begin
Feature activation+2.672
Top resid features:
commercial
Token commercial
Feature activation+0.284
Top resid features:
operations
Token operations
Feature activation+0.028
Top resid features:
here
Token here
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
Spac
Token Spac
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.067
Top resid features:
as
Tokenas
Feature activation+0.002
Top resid features:
minded
Token minded
Feature activation-0.025
Top resid features:
to
Token to
Feature activation-0.111
Top resid features:
start
Token start
Feature activation+2.631
Top resid features:
the
Token the
Feature activation+0.299
Top resid features:
season
Token season
Feature activation+0.255
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Emmanuel
Token Emmanuel
Feature activation+0.000
Top resid features:
Ad
Token Ad
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
"
Token "
Feature activation+0.026
Top resid features:
Jump
TokenJump
Feature activation+0.097
Top resid features:
-
Token-
Feature activation-0.045
Top resid features:
Start
TokenStart
Feature activation+2.371
Top resid features:
Our
Token Our
Feature activation+0.332
Top resid features:
Business
Token Business
Feature activation-0.019
Top resid features:
Start
Token Start
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
U
TokenU
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
The
TokenThe
Feature activation-0.018
Top resid features:
Spanish
Token Spanish
Feature activation+0.011
Top resid features:
Inquisition
Token Inquisition
Feature activation-0.007
Top resid features:
began
Token began
Feature activation+2.443
Top resid features:
in
Token in
Feature activation+0.076
Top resid features:
the
Token the
Feature activation+0.120
Top resid features:
late
Token late
Feature activation+0.024
Top resid features:
14
Token 14
Feature activation+0.022
Top resid features:
70
Token70
Feature activation+0.098
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
Ċ
TokenĊ
Feature activation+0.034
Top resid features:
Aaron
TokenAaron
Feature activation-0.009
Top resid features:
Cook
Token Cook
Feature activation+0.013
Top resid features:
will
Token will
Feature activation-0.120
Top resid features:
start
Token start
Feature activation+2.378
Top resid features:
Saturday
Token Saturday
Feature activation+0.251
Top resid features:
against
Token against
Feature activation+0.112
Top resid features:
Baltimore
Token Baltimore
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
place
Token place
Feature activation+0.000
Top resid features:
decision
Token decision
Feature activation-0.011
Top resid features:
making
Token making
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.046
Top resid features:
Should
Token Should
Feature activation-0.078
Top resid features:
he
Token he
Feature activation+0.019
Top resid features:
start
Token start
Feature activation+2.508
Top resid features:
the
Token the
Feature activation+0.146
Top resid features:
next
Token next
Feature activation+0.254
Top resid features:
step
Token step
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
This
Token This
Feature activation-0.001
Top resid features:
time
Token time
Feature activation+0.022
Top resid features:
out
Token out
Feature activation+0.022
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
he
Token he
Feature activation+0.019
Top resid features:
begins
Token begins
Feature activation+2.412
Top resid features:
the
Token the
Feature activation+0.343
Top resid features:
journey
Token journey
Feature activation+0.119
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
Haskell
Token Haskell
Feature activation+0.000
Top resid features:
frameworks
Token frameworks
Feature activation+0.000
Top resid features:
winning
Token winning
Feature activation+0.024
Top resid features:
Dream
Token Dream
Feature activation+0.023
Top resid features:
Works
TokenWorks
Feature activation+0.002
Top resid features:
film
Token film
Feature activation+0.019
Top resid features:
that
Token that
Feature activation-0.012
Top resid features:
started
Token started
Feature activation+2.519
Top resid features:
it
Token it
Feature activation+0.197
Top resid features:
all
Token all
Feature activation+0.109
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
brings
Token brings
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
semble
Tokensemble
Feature activation+0.044
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
Patriot
Token Patriot
Feature activation+0.008
Top resid features:
Act
Token Act
Feature activation+0.044
Top resid features:
has
Token has
Feature activation-0.109
Top resid features:
begun
Token begun
Feature activation+2.479
Top resid features:
its
Token its
Feature activation+0.379
Top resid features:
course
Token course
Feature activation+0.084
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
House
Token House
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.04

Head 2: 0.04

Head 3: 0.06

Head 4: 0.04

Head 5: 0.05

Head 6: 0.04

Head 7: 0.02

Head 8: 0.50

Head 9: 0.06

Head 10: 0.07

Head 11: 0.03

Positive logits

ALK1.66

MAP1.57

auntlet1.53

OSS1.46

ideshow1.39

Aid1.36

Dialogue1.31

LIST1.31

anza1.28

ORY1.28

[|1.27

ILD1.26

anew1.25

CONCLUS1.25

Studio1.24

ogue1.23

��1.23

Phase1.22

NAT1.21

Tank1.20

Negative logits

elector-1.42

ité-1.40

pi-1.38

stood-1.36

computed-1.36

clipboard-1.35

surfaces-1.34

verages-1.34

buttocks-1.33

accur-1.31

vanquished-1.31

confir-1.30

bounced-1.29

ophe-1.29

deceased-1.26

older-1.24

spills-1.23

warts-1.19

hid-1.19

handled-1.19

INTERVAL 2.327 - 2.585
CONTAINS 0.000%

INTERVAL 2.068 - 2.327
CONTAINS 0.000%

.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
started
Token started
Feature activation+0.000
half
Token half
Feature activation+0.000
the
Token the
Feature activation+0.530
season
Token season
Feature activation+2.096
and
Token and
Feature activation+1.071
I
Token I
Feature activation+0.532
worked
Token worked
Feature activation+0.120
my
Token my
Feature activation+0.000
way
Token way
Feature activation+0.000
Orlando
Token Orlando
Feature activation+0.000
Magic
Token Magic
Feature activation+0.000
have
Token have
Feature activation+0.000
started
Token started
Feature activation+0.000
this
Token this
Feature activation+0.391
season
Token season
Feature activation+2.202
really
Token really
Feature activation+0.456
well
Token well
Feature activation+0.639
,
Token,
Feature activation+0.000
going
Token going
Feature activation+0.000
2
Token 2
Feature activation+0.000
minded
Token minded
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
the
Token the
Feature activation+0.000
season
Token season
Feature activation+1.839
with
Token with
Feature activation+2.097
Emmanuel
Token Emmanuel
Feature activation+0.000
Ad
Token Ad
Feature activation+0.000
eb
Tokeneb
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
or
Tokenor
Feature activation+0.000
lifestyle
Token lifestyle
Feature activation+0.000
and
Token and
Feature activation+0.000
either
Token either
Feature activation+0.000
start
Token start
Feature activation+0.000
a
Token a
Feature activation+0.126
business
Token business
Feature activation+2.220
or
Token or
Feature activation+0.000
become
Token become
Feature activation+0.000
that
Token that
Feature activation+0.000
free
Token free
Feature activation+0.000
agent
Token agent
Feature activation+0.000

INTERVAL 1.810 - 2.068
CONTAINS 0.001%

Heath
Token Heath
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
begin
Token begin
Feature activation+0.000
the
Token the
Feature activation+0.000
process
Token process
Feature activation+2.048
all
Token all
Feature activation+0.410
over
Token over
Feature activation+0.381
again
Token again
Feature activation+0.227
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
Virgin
Token Virgin
Feature activation+0.000
Galactic
Token Galactic
Feature activation+0.000
will
Token will
Feature activation+0.000
begin
Token begin
Feature activation+0.000
commercial
Token commercial
Feature activation+1.057
operations
Token operations
Feature activation+1.851
here
Token here
Feature activation+0.769
at
Token at
Feature activation+0.954
Spac
Token Spac
Feature activation+0.000
eport
Tokeneport
Feature activation+0.000
America
Token America
Feature activation+0.000
-
Token -
Feature activation+0.000
Legislation
Token Legislation
Feature activation+0.000
to
Token to
Feature activation+0.000
begin
Token begin
Feature activation+0.000
the
Token the
Feature activation+0.000
process
Token process
Feature activation+2.030
of
Token of
Feature activation+0.000
transferring
Token transferring
Feature activation+0.403
European
Token European
Feature activation+0.000
Union
Token Union
Feature activation+0.000
law
Token law
Feature activation+0.000
at
Tokenat
Feature activation+0.043
k
Tokenk
Feature activation+0.000
al
Tokenal
Feature activation+0.000
"
Token"
Feature activation+0.206
certification
Token certification
Feature activation+0.153
process
Token process
Feature activation+1.954
for
Token for
Feature activation+0.000
those
Token those
Feature activation+0.000
filmmakers
Token filmmakers
Feature activation+0.000
who
Token who
Feature activation+0.000
are
Token are
Feature activation+0.000
son
Tokenson
Feature activation+0.000
had
Token had
Feature activation+0.000
barely
Token barely
Feature activation+0.000
started
Token started
Feature activation+0.000
his
Token his
Feature activation+0.000
new
Token new
Feature activation+1.875
job
Token job
Feature activation+0.901
at
Token at
Feature activation+0.546
the
Token the
Feature activation+0.000
University
Token University
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.551 - 1.810
CONTAINS 0.003%

massage
Token massage
Feature activation+0.000
therapist
Token therapist
Feature activation+0.000
,
Token,
Feature activation+0.000
started
Token started
Feature activation+0.000
their
Token their
Feature activation+0.207
business
Token business
Feature activation+1.738
of
Token of
Feature activation+0.000
facial
Token facial
Feature activation+0.000
massage
Token massage
Feature activation+0.000
and
Token and
Feature activation+0.165
exercise
Token exercise
Feature activation+0.205
minster
Tokenminster
Feature activation+0.000
plans
Token plans
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
demolition
Token demolition
Feature activation+0.865
on
Token on
Feature activation+1.715
the
Token the
Feature activation+0.000
1980
Token 1980
Feature activation+0.410
s
Tokens
Feature activation+0.000
-
Token-
Feature activation+0.000
era
Tokenera
Feature activation+0.000
event
Token event
Feature activation+0.000
started
Token started
Feature activation+0.000
more
Token more
Feature activation+0.000
or
Token or
Feature activation+0.447
less
Token less
Feature activation+1.520
on
Token on
Feature activation+1.566
time
Token time
Feature activation+0.000
.
Token.
Feature activation+0.311
Gandhi
Token Gandhi
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
stunning
Token stunning
Feature activation+0.000
claim
Token claim
Feature activation+0.000
started
Token started
Feature activation+0.000
out
Token out
Feature activation+0.000
on
Token on
Feature activation+1.623
Facebook
Token Facebook
Feature activation+0.000
,
Token,
Feature activation+0.373
and
Token and
Feature activation+0.487
many
Token many
Feature activation+0.000
immediately
Token immediately
Feature activation+0.005
crisis
Token crisis
Feature activation+0.000
began
Token began
Feature activation+0.000
in
Token in
Feature activation+0.000
February
Token February
Feature activation+0.496
1938
Token 1938
Feature activation+0.369
when
Token when
Feature activation+1.580
Hitler
Token Hitler
Feature activation+0.000
demanded
Token demanded
Feature activation+0.000
self
Token self
Feature activation+0.000
-
Token-
Feature activation+0.000
determination
Tokendetermination
Feature activation+0.000

INTERVAL 1.293 - 1.551
CONTAINS 0.006%

with
Token with
Feature activation+0.000
San
Token San
Feature activation+0.000
Francisco
Token Francisco
Feature activation+0.000
starting
Token starting
Feature activation+0.000
fresh
Token fresh
Feature activation+0.422
with
Token with
Feature activation+1.456
a
Token a
Feature activation+0.201
new
Token new
Feature activation+0.275
general
Token general
Feature activation+0.000
manager
Token manager
Feature activation+0.000
and
Token and
Feature activation+0.000
beginning
Token beginning
Feature activation+0.000
but
Token but
Feature activation+0.000
then
Token then
Feature activation+0.000
we
Token we
Feature activation+0.000
started
Token started
Feature activation+0.000
playing
Token playing
Feature activation+1.412
and
Token and
Feature activation+0.108
it
Token it
Feature activation+0.190
was
Token was
Feature activation+0.050
nice
Token nice
Feature activation+0.000
to
Token to
Feature activation+0.000
for
Token for
Feature activation+0.000
fifteen
Token fifteen
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
,
Token,
Feature activation+0.000
start
Token start
Feature activation+0.000
writing
Token writing
Feature activation+1.302
,
Token,
Feature activation+0.052
and
Token and
Feature activation+0.186
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
and
Token and
Feature activation+0.000
commenced
Token commenced
Feature activation+0.000
official
Token official
Feature activation+0.000
inf
Token inf
Feature activation+0.000
raction
Tokenraction
Feature activation+0.000
proceedings
Token proceedings
Feature activation+1.408
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
UK
Token UK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
J
TokenJ
Feature activation+0.000
ago
Tokenago
Feature activation+0.000
started
Token started
Feature activation+0.000
gl
Token gl
Feature activation+0.000
iding
Tokeniding
Feature activation+0.279
when
Token when
Feature activation+1.455
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.040
15
Token 15
Feature activation+0.000
and
Token and
Feature activation+0.000
recently
Token recently
Feature activation+0.000

INTERVAL 1.034 - 1.293
CONTAINS 0.008%

to
Token to
Feature activation+0.051
actually
Token actually
Feature activation+0.000
research
Token research
Feature activation+0.743
it
Token it
Feature activation+0.000
and
Token and
Feature activation+0.045
look
Token look
Feature activation+1.186
into
Token into
Feature activation+0.000
it
Token it
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
current
Token current
Feature activation+0.000
evolution
Token evolution
Feature activation+0.000
began
Token began
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
longer
Token longer
Feature activation+1.043
ago
Token ago
Feature activation+1.060
than
Token than
Feature activation+0.214
farming
Token farming
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
ome
Tokenome
Feature activation+0.000
split
Token split
Feature activation+0.000
starting
Token starting
Feature activation+0.000
goalkeeper
Token goalkeeper
Feature activation+0.000
duties
Token duties
Feature activation+0.000
with
Token with
Feature activation+1.142
Nick
Token Nick
Feature activation+0.000
Noble
Token Noble
Feature activation+0.000
,
Token,
Feature activation+0.000
starting
Token starting
Feature activation+0.000
13
Token 13
Feature activation+0.031
M
TokenM
Feature activation+0.000
aine
Tokenaine
Feature activation+0.000
)
Token)
Feature activation+0.000
started
Token started
Feature activation+0.000
the
Token the
Feature activation+0.000
group
Token group
Feature activation+1.143
,
Token,
Feature activation+1.123
and
Token and
Feature activation+0.915
Sens
Token Sens
Feature activation+0.000
.
Token.
Feature activation+0.000
Lisa
Token Lisa
Feature activation+0.000
started
Token started
Feature activation+0.000
14
Token 14
Feature activation+0.541
of
Token of
Feature activation+0.159
15
Token 15
Feature activation+0.311
games
Token games
Feature activation+1.026
as
Token as
Feature activation+1.182
a
Token a
Feature activation+0.326
red
Token red
Feature activation+0.036
shirt
Tokenshirt
Feature activation+0.000
freshman
Token freshman
Feature activation+0.000
during
Token during
Feature activation+0.000

INTERVAL 0.776 - 1.034
CONTAINS 0.012%

co
Tokenco
Feature activation+0.000
since
Token since
Feature activation+0.000
he
Token he
Feature activation+0.000
began
Token began
Feature activation+0.000
his
Token his
Feature activation+0.000
collection
Token collection
Feature activation+0.804
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Fr
TokenFr
Feature activation+0.000
ances
Tokenances
Feature activation+0.000
the
Token the
Feature activation+0.000
fall
Token fall
Feature activation+0.000
began
Token began
Feature activation+0.000
around
Token around
Feature activation+0.000
1991
Token 1991
Feature activation+0.207
;
Token;
Feature activation+0.839
in
Token in
Feature activation+0.285
Britain
Token Britain
Feature activation+0.000
it
Token it
Feature activation+0.000
began
Token began
Feature activation+0.000
around
Token around
Feature activation+0.000
-
Token-
Feature activation+0.000
17
Token17
Feature activation+0.000
season
Token season
Feature activation+0.000
,
Token,
Feature activation+0.000
starting
Token starting
Feature activation+0.154
next
Token next
Feature activation+0.958
August
Token August
Feature activation+0.822
.
Token.
Feature activation+0.360
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
However
TokenHowever
Feature activation+0.000
example
Token example
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
start
Token start
Feature activation+0.000
work
Token work
Feature activation+0.887
at
Token at
Feature activation+0.631
7
Token 7
Feature activation+0.000
:
Token:
Feature activation+0.404
30
Token30
Feature activation+0.000
AM
Token AM
Feature activation+0.000
comic
Token comic
Feature activation+0.000
con
Token con
Feature activation+0.000
!
Token!
Feature activation+0.000
Started
Token Started
Feature activation+0.000
in
Token in
Feature activation+0.000
2006
Token 2006
Feature activation+0.836
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.293
one
Token one
Feature activation+0.000
is
Token is
Feature activation+0.000
dedicated
Token dedicated
Feature activation+0.000

INTERVAL 0.517 - 0.776
CONTAINS 0.024%

to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
a
Token a
Feature activation+0.000
small
Token small
Feature activation+1.330
brush
Token brush
Feature activation+0.186
fire
Tokenfire
Feature activation+0.585
this
Token this
Feature activation+0.449
past
Token past
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
via
Token via
Feature activation+0.000
his
Token his
Feature activation+0.000
3
Token 3
Feature activation+0.000
pm
Token pm
Feature activation+0.000
.
Token.
Feature activation+0.000
Starting
Token Starting
Feature activation+0.000
off
Token off
Feature activation+0.066
with
Token with
Feature activation+0.720
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
T
TokenT
Feature activation+0.000
il
Tokenil
Feature activation+0.000
gul
Token gul
Feature activation+0.000
Before
TokenBefore
Feature activation+0.000
you
Token you
Feature activation+0.000
start
Token start
Feature activation+0.000
in
Token in
Feature activation+0.000
Photoshop
Token Photoshop
Feature activation+0.160
,
Token,
Feature activation+0.595
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
the
Token the
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
caucus
Token caucus
Feature activation+0.000
to
Token to
Feature activation+0.000
begin
Token begin
Feature activation+0.000
with
Token with
Feature activation+0.630
.
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
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
gesture
Token gesture
Feature activation+0.000
was
Token was
Feature activation+0.000
started
Token started
Feature activation+0.000
by
Token by
Feature activation+0.700
former
Token former
Feature activation+0.000
San
Token San
Feature activation+0.000
Francisco
Token Francisco
Feature activation+0.000
49
Token 49
Feature activation+0.000
ers
Tokeners
Feature activation+0.000

INTERVAL 0.259 - 0.517
CONTAINS 0.036%

oe
Tokenoe
Feature activation+0.000
z
Tokenz
Feature activation+0.000
started
Token started
Feature activation+0.000
life
Token life
Feature activation+0.000
as
Token as
Feature activation+0.970
free
Token free
Feature activation+0.442
-
Token-
Feature activation+0.000
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.000
play
Tokenplay
Feature activation+0.000
mobile
Token mobile
Feature activation+0.000
father
Token father
Feature activation+0.000
founded
Token founded
Feature activation+0.000
the
Token the
Feature activation+0.000
Fore
Token Fore
Feature activation+0.000
most
Tokenmost
Feature activation+0.000
Group
Token Group
Feature activation+0.303
shipping
Token shipping
Feature activation+0.000
and
Token and
Feature activation+0.000
trading
Token trading
Feature activation+0.000
company
Token company
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.367
with
Token with
Feature activation+1.331
a
Token a
Feature activation+0.002
national
Token national
Feature activation+0.000
forum
Token forum
Feature activation+0.000
where
Token where
Feature activation+0.397
a
Token a
Feature activation+0.000
thousand
Token thousand
Feature activation+0.000
attendees
Token attendees
Feature activation+0.000
where
Token where
Feature activation+0.000
chosen
Token chosen
Feature activation+0.000
Starting
Token Starting
Feature activation+0.000
around
Token around
Feature activation+0.028
2010
Token 2010
Feature activation+0.483
,
Token,
Feature activation+0.488
pharmaceutical
Token pharmaceutical
Feature activation+0.000
companies
Token companies
Feature activation+0.263
in
Token in
Feature activation+0.088
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
facial
Token facial
Feature activation+0.000
massage
Token massage
Feature activation+0.000
and
Token and
Feature activation+0.165
exercise
Token exercise
Feature activation+0.205
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.499
ago
Token ago
Feature activation+0.024
with
Token with
Feature activation+0.000
private
Token private
Feature activation+0.000
events
Token events
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.000 - 0.259
CONTAINS 99.908%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
AT
TokenAT
Feature activation+0.000
&
Token&
Feature activation+0.000
T
TokenT
Feature activation+0.000
remains
Token remains
Feature activation+0.000
confident
Token confident
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
will
Token will
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
the
Token the
Feature activation+0.000
detection
Token detection
Feature activation+0.000
dogs
Token dogs
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
purchase
Token purchase
Feature activation+0.000
and
Token and
Feature activation+0.000
placement
Token placement
Feature activation+0.000
of
Token of
Feature activation+0.000
meat
Token meat
Feature activation+0.000
in
Token in
Feature activation+0.000
races
Token races
Feature activation+0.000
as
Token as
Feature activation+0.000
you
Token you
Feature activation+0.000
did
Token did
Feature activation+0.000
with
Token with
Feature activation+0.000
your
Token your
Feature activation+0.000
online
Token online
Feature activation+0.000
ads
Token ads
Feature activation+0.000
.
Token.
Feature activation+0.000
Everyone
Token Everyone
Feature activation+0.000
does
Token does
Feature activation+0.000
ad
Tokenad
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
,
Token,
Feature activation+0.000
Pas
Token Pas
Feature activation+0.000
ni
Tokenni
Feature activation+0.000
and
Token and
Feature activation+0.000
J
Token J
Feature activation+0.000
iw
Tokeniw
Feature activation+0.000
ani
Tokenani
Feature activation+0.000
during
Token during
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
smarter
Token smarter
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
topic
Token topic
Feature activation+0.000
or
Token or
Feature activation+0.000
that
Token that
Feature activation+0.000
topic
Token topic
Feature activation+0.000
.'
Token.'
Feature activation+0.000
In
Token In
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H2.8: (feature 3023)

TOP ACTIVATIONS
MAX = 4.297

corpses
Token corpses
Feature activation+0.000
would
Token would
Feature activation+0.000
set
Token set
Feature activation+0.000
a
Token a
Feature activation+1.109
dangerous
Token dangerous
Feature activation+1.296
precedent
Token precedent
Feature activation+4.297
,
Token,
Feature activation+0.127
giving
Token giving
Feature activation+0.000
rapists
Token rapists
Feature activation+0.000
and
Token and
Feature activation+0.000
child
Token child
Feature activation+0.000
facts
Token facts
Feature activation+0.000
can
Token can
Feature activation+0.000
set
Token set
Feature activation+0.000
administrator
Token administrator
Feature activation+0.000
Pruitt
Token Pruitt
Feature activation+0.442
straight
Token straight
Feature activation+4.280
.
Token.
Feature activation+0.000
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
m
Tokenm
Feature activation+0.000
doing
Token doing
Feature activation+0.000
and
Token and
Feature activation+0.000
set
Token set
Feature activation+0.000
her
Token her
Feature activation+1.273
free
Token free
Feature activation+4.108
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
you
Token you
Feature activation+0.000
Miller
Token Miller
Feature activation+0.000
could
Token could
Feature activation+0.000
've
Token've
Feature activation+0.000
set
Token set
Feature activation+0.000
sack
Token sack
Feature activation+0.735
records
Token records
Feature activation+4.105
in
Token in
Feature activation+0.895
those
Token those
Feature activation+0.000
contests
Token contests
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sear
Token Sear
Feature activation+0.000
ls
Tokenls
Feature activation+0.000
set
Token set
Feature activation+0.102
a
Token a
Feature activation+1.535
world
Token world
Feature activation+0.262
record
Token record
Feature activation+4.097
for
Token for
Feature activation+1.725
dirt
Token dirt
Feature activation+0.000
jumping
Token jumping
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
originally
Token originally
Feature activation+0.000
set
Token set
Feature activation+0.000
a
Token a
Feature activation+1.182
Monday
Token Monday
Feature activation+0.724
deadline
Token deadline
Feature activation+3.994
to
Token to
Feature activation+2.634
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
agreement
Token agreement
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
single
Token single
Feature activation+0.000
-
Token-
Feature activation+0.000
game
Tokengame
Feature activation+0.000
record
Token record
Feature activation+3.920
for
Token for
Feature activation+0.000
3
Token 3
Feature activation+0.000
-
Token-
Feature activation+0.000
point
Tokenpoint
Feature activation+0.000
field
Token field
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
set
Token set
Feature activation+0.000
a
Token a
Feature activation+1.284
new
Token new
Feature activation+2.465
goal
Token goal
Feature activation+3.647
of
Token of
Feature activation+0.000
reducing
Token reducing
Feature activation+0.000
US
Token US
Feature activation+0.000
levels
Token levels
Feature activation+0.000
between
Token between
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
set
Token set
Feature activation+0.295
myself
Token myself
Feature activation+0.663
the
Token the
Feature activation+1.495
goal
Token goal
Feature activation+3.558
of
Token of
Feature activation+0.000
building
Token building
Feature activation+0.079
a
Token a
Feature activation+0.000
simple
Token simple
Feature activation+0.107
neural
Token neural
Feature activation+0.000
globe
Token globe
Feature activation+0.000
scrambling
Token scrambling
Feature activation+0.000
to
Token to
Feature activation+0.000
set
Token set
Feature activation+0.000
up
Token up
Feature activation+0.000
shop
Token shop
Feature activation+3.530
.
Token.
Feature activation+0.000
Indonesia
Token Indonesia
Feature activation+0.000
,
Token,
Feature activation+0.000
meanwhile
Token meanwhile
Feature activation+0.000
,
Token,
Feature activation+0.000
position
Token position
Feature activation+0.000
to
Token to
Feature activation+0.000
set
Token set
Feature activation+0.000
this
Token this
Feature activation+0.000
in
Token in
Feature activation+0.423
motion
Token motion
Feature activation+3.448
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
Pf
Token Pf
Feature activation+0.000
au
Tokenau
Feature activation+0.000
then
Token then
Feature activation+0.000
set
Token set
Feature activation+0.272
her
Token her
Feature activation+1.550
sights
Token sights
Feature activation+3.391
on
Token on
Feature activation+0.368
le
Token le
Feature activation+0.000
pro
Tokenpro
Feature activation+0.000
sy
Tokensy
Feature activation+0.000
elimination
Token elimination
Feature activation+0.000
3
Token 3
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
has
Token has
Feature activation+0.000
set
Token set
Feature activation+0.000
records
Token records
Feature activation+3.367
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.307
biggest
Token biggest
Feature activation+0.000
animated
Token animated
Feature activation+0.000
movie
Token movie
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.000
set
Token set
Feature activation+0.441
the
Token the
Feature activation+1.948
previous
Token previous
Feature activation+2.470
benchmark
Token benchmark
Feature activation+3.290
in
Token in
Feature activation+1.526
1972
Token 1972
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
27
Token 27
Feature activation+0.000
their
Token their
Feature activation+0.000
heads
Token heads
Feature activation+0.000
who
Token who
Feature activation+0.000
set
Token set
Feature activation+0.276
up
Token up
Feature activation+0.523
camp
Token camp
Feature activation+3.237
outside
Token outside
Feature activation+0.000
the
Token the
Feature activation+0.288
gig
Token gig
Feature activation+0.000
and
Token and
Feature activation+0.000
proceeded
Token proceeded
Feature activation+0.000
Muslim
Token Muslim
Feature activation+0.000
,
Token,
Feature activation+0.000
setting
Token setting
Feature activation+0.000
a
Token a
Feature activation+0.743
dangerous
Token dangerous
Feature activation+0.706
precedent
Token precedent
Feature activation+3.184
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
has
Token has
Feature activation+0.000
set
Token set
Feature activation+0.000
a
Token a
Feature activation+1.063
specific
Token specific
Feature activation+2.091
goal
Token goal
Feature activation+3.178
for
Token for
Feature activation+1.058
moving
Token moving
Feature activation+0.013
towards
Token towards
Feature activation+0.000
a
Token a
Feature activation+0.000
health
Token health
Feature activation+0.000
budget
Token budget
Feature activation+0.000
architect
Token architect
Feature activation+0.000
,
Token,
Feature activation+0.000
sets
Token sets
Feature activation+0.275
his
Token his
Feature activation+1.240
sights
Token sights
Feature activation+3.097
on
Token on
Feature activation+0.148
fighting
Token fighting
Feature activation+0.000
poverty
Token poverty
Feature activation+0.000
and
Token and
Feature activation+0.000
winning
Token winning
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
wish
Token wish
Feature activation+0.000
to
Token to
Feature activation+0.000
set
Token set
Feature activation+0.000
straight
Token straight
Feature activation+3.062
some
Token some
Feature activation+1.344
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.682
issues
Token issues
Feature activation+0.000
which
Token which
Feature activation+0.000
after
Token after
Feature activation+0.000
sunset
Token sunset
Feature activation+0.000
,
Token,
Feature activation+0.000
set
Token set
Feature activation+0.000
up
Token up
Feature activation+0.035
camp
Token camp
Feature activation+3.057
fires
Tokenfires
Feature activation+2.755
and
Token and
Feature activation+0.480
consume
Token consume
Feature activation+0.000
alcohol
Token alcohol
Feature activation+0.000
A
Token A
Feature activation+0.000

Top DFA by src position
MAX = 5.078

have
Token have
Feature activation+0.020
Top resid features:
sex
Token sex
Feature activation+0.032
Top resid features:
with
Token with
Feature activation+0.070
Top resid features:
corpses
Token corpses
Feature activation+0.044
Top resid features:
would
Token would
Feature activation+0.012
Top resid features:
set
Token set
Feature activation+4.995
Top resid features:
a
Token a
Feature activation+0.120
Top resid features:
dangerous
Token dangerous
Feature activation+0.085
Top resid features:
precedent
Token precedent
Feature activation+0.133
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
giving
Token giving
Feature activation+0.000
Top resid features:
review
Token review
Feature activation+0.053
Top resid features:
of
Token of
Feature activation+0.079
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
facts
Token facts
Feature activation-0.000
Top resid features:
can
Token can
Feature activation+0.034
Top resid features:
set
Token set
Feature activation+5.078
Top resid features:
administrator
Token administrator
Feature activation+0.033
Top resid features:
Pruitt
Token Pruitt
Feature activation+0.148
Top resid features:
straight
Token straight
Feature activation+0.117
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
There
Token There
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.041
Top resid features:
Ļ
TokenĻ
Feature activation+0.019
Top resid features:
m
Tokenm
Feature activation+0.056
Top resid features:
doing
Token doing
Feature activation+0.121
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
set
Token set
Feature activation+4.857
Top resid features:
her
Token her
Feature activation+0.095
Top resid features:
free
Token free
Feature activation+0.155
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:
Flynn
Token Flynn
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
Miller
Token Miller
Feature activation+0.006
Top resid features:
could
Token could
Feature activation+0.013
Top resid features:
've
Token've
Feature activation+0.049
Top resid features:
set
Token set
Feature activation+4.734
Top resid features:
sack
Token sack
Feature activation+0.423
Top resid features:
records
Token records
Feature activation+0.186
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
contests
Token contests
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.033
Top resid features:
days
Token days
Feature activation+0.040
Top resid features:
after
Token after
Feature activation+0.135
Top resid features:
Sear
Token Sear
Feature activation+0.032
Top resid features:
ls
Tokenls
Feature activation-0.010
Top resid features:
set
Token set
Feature activation+5.063
Top resid features:
a
Token a
Feature activation+0.112
Top resid features:
world
Token world
Feature activation-0.304
Top resid features:
record
Token record
Feature activation+0.140
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
dirt
Token dirt
Feature activation+0.000
Top resid features:
game
Token game
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
Union
Token Union
Feature activation+0.024
Top resid features:
leaders
Token leaders
Feature activation+0.021
Top resid features:
originally
Token originally
Feature activation+0.000
Top resid features:
set
Token set
Feature activation+4.834
Top resid features:
a
Token a
Feature activation+0.082
Top resid features:
Monday
Token Monday
Feature activation+0.231
Top resid features:
deadline
Token deadline
Feature activation+0.185
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
come
Token come
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.188
Top resid features:
126
Token126
Feature activation+0.002
Top resid features:
)
Token)
Feature activation+0.019
Top resid features:
and
Token and
Feature activation+0.051
Top resid features:
set
Token set
Feature activation+4.413
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
Knights
Token Knights
Feature activation+0.022
Top resid features:
âĢ
TokenâĢ
Feature activation+0.108
Top resid features:
Ļ
TokenĻ
Feature activation-0.007
Top resid features:
single
Token single
Feature activation+0.138
Top resid features:
"
Token "
Feature activation+0.012
Top resid features:
historic
Tokenhistoric
Feature activation+0.042
Top resid features:
",
Token",
Feature activation+0.029
Top resid features:
as
Token as
Feature activation+0.061
Top resid features:
he
Token he
Feature activation-0.005
Top resid features:
set
Token set
Feature activation+4.270
Top resid features:
a
Token a
Feature activation+0.075
Top resid features:
new
Token new
Feature activation+0.271
Top resid features:
goal
Token goal
Feature activation+0.080
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
reducing
Token reducing
Feature activation+0.000
Top resid features:
learn
Token learn
Feature activation+0.074
Top resid features:
about
Token about
Feature activation+0.075
Top resid features:
AI
Token AI
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
I
Token I
Feature activation+0.010
Top resid features:
set
Token set
Feature activation+4.441
Top resid features:
myself
Token myself
Feature activation-0.050
Top resid features:
the
Token the
Feature activation+0.074
Top resid features:
goal
Token goal
Feature activation+0.099
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
building
Token building
Feature activation+0.000
Top resid features:
across
Token across
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
globe
Token globe
Feature activation+0.025
Top resid features:
scrambling
Token scrambling
Feature activation+0.066
Top resid features:
to
Token to
Feature activation+0.029
Top resid features:
set
Token set
Feature activation+4.310
Top resid features:
up
Token up
Feature activation+0.109
Top resid features:
shop
Token shop
Feature activation+0.125
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Indonesia
Token Indonesia
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
was
Token was
Feature activation-0.011
Top resid features:
in
Token in
Feature activation+0.020
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
position
Token position
Feature activation+0.014
Top resid features:
to
Token to
Feature activation-0.011
Top resid features:
set
Token set
Feature activation+4.686
Top resid features:
this
Token this
Feature activation-0.034
Top resid features:
in
Token in
Feature activation+0.113
Top resid features:
motion
Token motion
Feature activation+0.029
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
Dr
Token Dr
Feature activation-0.000
Top resid features:
Pf
Token Pf
Feature activation+0.044
Top resid features:
au
Tokenau
Feature activation-0.012
Top resid features:
then
Token then
Feature activation+0.036
Top resid features:
set
Token set
Feature activation+4.316
Top resid features:
her
Token her
Feature activation+0.089
Top resid features:
sights
Token sights
Feature activation+0.094
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
le
Token le
Feature activation+0.000
Top resid features:
pro
Tokenpro
Feature activation+0.000
Top resid features:
Me
Token Me
Feature activation+0.028
Top resid features:
3
Token 3
Feature activation+0.064
Top resid features:
âĢ
TokenâĢ
Feature activation+0.035
Top resid features:
Ŀ
TokenĿ
Feature activation+0.008
Top resid features:
has
Token has
Feature activation+0.087
Top resid features:
set
Token set
Feature activation+4.100
Top resid features:
records
Token records
Feature activation+0.221
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
biggest
Token biggest
Feature activation+0.000
Top resid features:
animated
Token animated
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.071
Top resid features:
West
Token West
Feature activation+0.022
Top resid features:
Germany
Token Germany
Feature activation+0.036
Top resid features:
when
Token when
Feature activation+0.044
Top resid features:
he
Token he
Feature activation-0.017
Top resid features:
set
Token set
Feature activation+4.098
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
previous
Token previous
Feature activation+0.034
Top resid features:
benchmark
Token benchmark
Feature activation+0.138
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
1972
Token 1972
Feature activation+0.000
Top resid features:
strapped
Token strapped
Feature activation+0.038
Top resid features:
to
Token to
Feature activation+0.069
Top resid features:
their
Token their
Feature activation+0.017
Top resid features:
heads
Token heads
Feature activation+0.021
Top resid features:
who
Token who
Feature activation+0.067
Top resid features:
set
Token set
Feature activation+4.090
Top resid features:
up
Token up
Feature activation+0.008
Top resid features:
camp
Token camp
Feature activation+0.126
Top resid features:
outside
Token outside
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
gig
Token gig
Feature activation+0.000
Top resid features:
definition
Token definition
Feature activation+0.027
Top resid features:
of
Token of
Feature activation+0.060
Top resid features:
a
Token a
Feature activation+0.017
Top resid features:
Muslim
Token Muslim
Feature activation-0.011
Top resid features:
,
Token,
Feature activation-0.073
Top resid features:
setting
Token setting
Feature activation+3.948
Top resid features:
a
Token a
Feature activation+0.106
Top resid features:
dangerous
Token dangerous
Feature activation+0.130
Top resid features:
precedent
Token precedent
Feature activation+0.158
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.034
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
federal
Token federal
Feature activation+0.018
Top resid features:
government
Token government
Feature activation+0.009
Top resid features:
has
Token has
Feature activation+0.084
Top resid features:
set
Token set
Feature activation+4.101
Top resid features:
a
Token a
Feature activation+0.110
Top resid features:
specific
Token specific
Feature activation-0.091
Top resid features:
goal
Token goal
Feature activation+0.085
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
moving
Token moving
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.022
Top resid features:
s
Tokens
Feature activation+0.012
Top resid features:
budget
Token budget
Feature activation+0.064
Top resid features:
architect
Token architect
Feature activation+0.032
Top resid features:
,
Token,
Feature activation-0.069
Top resid features:
sets
Token sets
Feature activation+3.740
Top resid features:
his
Token his
Feature activation+0.315
Top resid features:
sights
Token sights
Feature activation+0.157
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
fighting
Token fighting
Feature activation+0.000
Top resid features:
poverty
Token poverty
Feature activation+0.000
Top resid features:
city
Token city
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
I
Token I
Feature activation+0.061
Top resid features:
wish
Token wish
Feature activation+0.187
Top resid features:
to
Token to
Feature activation-0.075
Top resid features:
set
Token set
Feature activation+4.149
Top resid features:
straight
Token straight
Feature activation+0.107
Top resid features:
some
Token some
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:
issues
Token issues
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.252
Top resid features:
area
Token area
Feature activation+0.013
Top resid features:
after
Token after
Feature activation+0.104
Top resid features:
sunset
Token sunset
Feature activation+0.062
Top resid features:
,
Token,
Feature activation-0.050
Top resid features:
set
Token set
Feature activation+4.015
Top resid features:
up
Token up
Feature activation-0.033
Top resid features:
camp
Token camp
Feature activation+0.312
Top resid features:
fires
Tokenfires
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
consume
Token consume
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.02

Head 2: 0.05

Head 3: 0.06

Head 4: 0.04

Head 5: 0.06

Head 6: 0.03

Head 7: 0.02

Head 8: 0.50

Head 9: 0.06

Head 10: 0.05

Head 11: 0.04

Positive logits

precedent1.65

rift1.43

Horowitz1.41

altar1.34

mileage1.31

expectation1.30

Abbey1.29

odds1.29

lid1.25

Sail1.25

Alpine1.24

eligibility1.24

Tune1.22

knots1.22

aside1.22

Toro1.22

Rw1.20

margin1.15

deadline1.15

Isle1.15

Negative logits

iors-1.59

enegger-1.43

entimes-1.41

plete-1.40

groupon-1.36

ocom-1.28

ittle-1.27

unte-1.24

odcast-1.23

inately-1.23

regenerate-1.21

stuff-1.21

packed-1.21

spread-1.21

minded-1.20

aucas-1.20

builders-1.20

akening-1.20

glomer-1.19

forms-1.19

INTERVAL 3.867 - 4.297
CONTAINS 0.001%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
single
Token single
Feature activation+0.000
-
Token-
Feature activation+0.000
game
Tokengame
Feature activation+0.000
record
Token record
Feature activation+3.920
for
Token for
Feature activation+0.000
3
Token 3
Feature activation+0.000
-
Token-
Feature activation+0.000
point
Tokenpoint
Feature activation+0.000
field
Token field
Feature activation+0.000
facts
Token facts
Feature activation+0.000
can
Token can
Feature activation+0.000
set
Token set
Feature activation+0.000
administrator
Token administrator
Feature activation+0.000
Pruitt
Token Pruitt
Feature activation+0.442
straight
Token straight
Feature activation+4.280
.
Token.
Feature activation+0.000
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
leaders
Token leaders
Feature activation+0.000
originally
Token originally
Feature activation+0.000
set
Token set
Feature activation+0.000
a
Token a
Feature activation+1.182
Monday
Token Monday
Feature activation+0.724
deadline
Token deadline
Feature activation+3.994
to
Token to
Feature activation+2.634
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
agreement
Token agreement
Feature activation+0.000
Sear
Token Sear
Feature activation+0.000
ls
Tokenls
Feature activation+0.000
set
Token set
Feature activation+0.102
a
Token a
Feature activation+1.535
world
Token world
Feature activation+0.262
record
Token record
Feature activation+4.097
for
Token for
Feature activation+1.725
dirt
Token dirt
Feature activation+0.000
jumping
Token jumping
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
corpses
Token corpses
Feature activation+0.000
would
Token would
Feature activation+0.000
set
Token set
Feature activation+0.000
a
Token a
Feature activation+1.109
dangerous
Token dangerous
Feature activation+1.296
precedent
Token precedent
Feature activation+4.297
,
Token,
Feature activation+0.127
giving
Token giving
Feature activation+0.000
rapists
Token rapists
Feature activation+0.000
and
Token and
Feature activation+0.000
child
Token child
Feature activation+0.000

INTERVAL 3.438 - 3.867
CONTAINS 0.000%

as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
set
Token set
Feature activation+0.000
a
Token a
Feature activation+1.284
new
Token new
Feature activation+2.465
goal
Token goal
Feature activation+3.647
of
Token of
Feature activation+0.000
reducing
Token reducing
Feature activation+0.000
US
Token US
Feature activation+0.000
levels
Token levels
Feature activation+0.000
between
Token between
Feature activation+0.000
position
Token position
Feature activation+0.000
to
Token to
Feature activation+0.000
set
Token set
Feature activation+0.000
this
Token this
Feature activation+0.000
in
Token in
Feature activation+0.423
motion
Token motion
Feature activation+3.448
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
globe
Token globe
Feature activation+0.000
scrambling
Token scrambling
Feature activation+0.000
to
Token to
Feature activation+0.000
set
Token set
Feature activation+0.000
up
Token up
Feature activation+0.000
shop
Token shop
Feature activation+3.530
.
Token.
Feature activation+0.000
Indonesia
Token Indonesia
Feature activation+0.000
,
Token,
Feature activation+0.000
meanwhile
Token meanwhile
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
set
Token set
Feature activation+0.295
myself
Token myself
Feature activation+0.663
the
Token the
Feature activation+1.495
goal
Token goal
Feature activation+3.558
of
Token of
Feature activation+0.000
building
Token building
Feature activation+0.079
a
Token a
Feature activation+0.000
simple
Token simple
Feature activation+0.107
neural
Token neural
Feature activation+0.000

INTERVAL 3.008 - 3.438
CONTAINS 0.001%

Muslim
Token Muslim
Feature activation+0.000
,
Token,
Feature activation+0.000
setting
Token setting
Feature activation+0.000
a
Token a
Feature activation+0.743
dangerous
Token dangerous
Feature activation+0.706
precedent
Token precedent
Feature activation+3.184
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
the
Token the
Feature activation+0.000
their
Token their
Feature activation+0.000
heads
Token heads
Feature activation+0.000
who
Token who
Feature activation+0.000
set
Token set
Feature activation+0.276
up
Token up
Feature activation+0.523
camp
Token camp
Feature activation+3.237
outside
Token outside
Feature activation+0.000
the
Token the
Feature activation+0.288
gig
Token gig
Feature activation+0.000
and
Token and
Feature activation+0.000
proceeded
Token proceeded
Feature activation+0.000
government
Token government
Feature activation+0.000
has
Token has
Feature activation+0.000
set
Token set
Feature activation+0.000
a
Token a
Feature activation+1.063
specific
Token specific
Feature activation+2.091
goal
Token goal
Feature activation+3.178
for
Token for
Feature activation+1.058
moving
Token moving
Feature activation+0.013
towards
Token towards
Feature activation+0.000
a
Token a
Feature activation+0.000
health
Token health
Feature activation+0.000
budget
Token budget
Feature activation+0.000
architect
Token architect
Feature activation+0.000
,
Token,
Feature activation+0.000
sets
Token sets
Feature activation+0.275
his
Token his
Feature activation+1.240
sights
Token sights
Feature activation+3.097
on
Token on
Feature activation+0.148
fighting
Token fighting
Feature activation+0.000
poverty
Token poverty
Feature activation+0.000
and
Token and
Feature activation+0.000
winning
Token winning
Feature activation+0.000
Pf
Token Pf
Feature activation+0.000
au
Tokenau
Feature activation+0.000
then
Token then
Feature activation+0.000
set
Token set
Feature activation+0.272
her
Token her
Feature activation+1.550
sights
Token sights
Feature activation+3.391
on
Token on
Feature activation+0.368
le
Token le
Feature activation+0.000
pro
Tokenpro
Feature activation+0.000
sy
Tokensy
Feature activation+0.000
elimination
Token elimination
Feature activation+0.000

INTERVAL 2.578 - 3.008
CONTAINS 0.002%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
set
Token set
Feature activation+0.044
my
Token my
Feature activation+1.859
alarm
Token alarm
Feature activation+2.787
for
Token for
Feature activation+1.944
seven
Token seven
Feature activation+0.000
hours
Token hours
Feature activation+0.000
((
Token ((
Feature activation+0.000
4
Token4
Feature activation+0.000
is
Token is
Feature activation+0.000
intent
Token intent
Feature activation+0.000
on
Token on
Feature activation+0.000
setting
Token setting
Feature activation+0.000
you
Token you
Feature activation+0.000
straight
Token straight
Feature activation+2.633
,
Token,
Feature activation+0.053
at
Token at
Feature activation+0.000
length
Token length
Feature activation+0.000
if
Token if
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
world
Token world
Feature activation+0.000
attempted
Token attempted
Feature activation+0.000
to
Token to
Feature activation+0.000
set
Token set
Feature activation+0.000
a
Token a
Feature activation+0.702
new
Token new
Feature activation+2.709
course
Token course
Feature activation+1.105
for
Token for
Feature activation+1.730
Catholic
Token Catholic
Feature activation+0.000
-
Token-
Feature activation+0.000
Jewish
TokenJewish
Feature activation+0.115
businesses
Token businesses
Feature activation+0.000
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
set
Token set
Feature activation+0.000
their
Token their
Feature activation+1.355
sights
Token sights
Feature activation+2.699
on
Token on
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
in
Token in
Feature activation+0.000
recent
Token recent
Feature activation+0.000
years
Token years
Feature activation+0.000
it
Token it
Feature activation+0.000
later
Token later
Feature activation+0.000
.
Token.
Feature activation+0.000
Set
Token Set
Feature activation+0.039
a
Token a
Feature activation+1.249
timer
Token timer
Feature activation+2.941
for
Token for
Feature activation+1.951
fifteen
Token fifteen
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
,
Token,
Feature activation+0.000
start
Token start
Feature activation+0.000

INTERVAL 2.149 - 2.578
CONTAINS 0.004%

neau
Tokenneau
Feature activation+0.000
to
Token to
Feature activation+0.000
set
Token set
Feature activation+0.000
a
Token a
Feature activation+0.979
clear
Token clear
Feature activation+0.916
target
Token target
Feature activation+2.312
for
Token for
Feature activation+0.817
er
Token er
Feature activation+0.000
asing
Tokenasing
Feature activation+0.000
the
Token the
Feature activation+0.000
deficit
Token deficit
Feature activation+0.000
new
Token new
Feature activation+0.000
set
Token set
Feature activation+0.000
of
Token of
Feature activation+0.000
National
Token National
Feature activation+0.374
Focus
Token Focus
Feature activation+1.965
goals
Token goals
Feature activation+2.151
aimed
Token aimed
Feature activation+0.128
squarely
Token squarely
Feature activation+0.000
at
Token at
Feature activation+0.000
annoying
Token annoying
Feature activation+0.000
Great
Token Great
Feature activation+0.000
",
Token",
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
set
Token set
Feature activation+0.000
a
Token a
Feature activation+1.284
new
Token new
Feature activation+2.465
goal
Token goal
Feature activation+3.647
of
Token of
Feature activation+0.000
reducing
Token reducing
Feature activation+0.000
US
Token US
Feature activation+0.000
levels
Token levels
Feature activation+0.000
after
Token after
Feature activation+0.000
reportedly
Token reportedly
Feature activation+0.000
setting
Token setting
Feature activation+0.000
himself
Token himself
Feature activation+0.429
on
Token on
Feature activation+1.139
fire
Token fire
Feature activation+2.154
in
Token in
Feature activation+0.787
front
Token front
Feature activation+0.576
of
Token of
Feature activation+0.000
businesses
Token businesses
Feature activation+0.000
at
Token at
Feature activation+0.000
funding
Token funding
Feature activation+0.000
capital
Token capital
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
goals
Token goals
Feature activation+0.000
set
Token set
Feature activation+0.051
by
Token by
Feature activation+2.576
the
Token the
Feature activation+0.182
project
Token project
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.719 - 2.149
CONTAINS 0.005%

,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
set
Token set
Feature activation+0.284
a
Token a
Feature activation+1.470
timer
Token timer
Feature activation+2.637
for
Token for
Feature activation+2.050
just
Token just
Feature activation+0.105
half
Token half
Feature activation+0.000
an
Token an
Feature activation+0.000
hour
Token hour
Feature activation+0.000
.
Token.
Feature activation+0.000
def
Token def
Feature activation+0.000
set
Token set
Feature activation+0.000
_
Token_
Feature activation+1.543
role
Tokenrole
Feature activation+1.680
(
Token(
Feature activation+1.833
role
Tokenrole
Feature activation+1.757
)
Token)
Feature activation+1.006
@
Token @
Feature activation+0.006
role
Tokenrole
Feature activation+0.294
=
Token =
Feature activation+0.000
role
Token role
Feature activation+0.000
-
Token-
Feature activation+0.000
ret
Tokenret
Feature activation+0.000
irement
Tokenirement
Feature activation+0.000
had
Token had
Feature activation+0.000
set
Token set
Feature activation+0.000
about
Token about
Feature activation+1.769
assembling
Token assembling
Feature activation+0.000
his
Token his
Feature activation+0.000
collection
Token collection
Feature activation+0.000
of
Token of
Feature activation+0.000
Alf
Token Alf
Feature activation+0.000
by
Token by
Feature activation+0.000
scoring
Token scoring
Feature activation+0.000
set
Token set
Feature activation+0.000
-
Token-
Feature activation+0.159
piece
Tokenpiece
Feature activation+0.000
goals
Token goals
Feature activation+1.804
in
Token in
Feature activation+0.160
half
Token half
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
games
Token games
Feature activation+0.000
at
Token at
Feature activation+0.000
police
Token police
Feature activation+0.000
and
Token and
Feature activation+0.000
set
Token set
Feature activation+0.141
fire
Token fire
Feature activation+2.544
to
Token to
Feature activation+1.748
a
Token a
Feature activation+0.696
lim
Token lim
Feature activation+0.637
ous
Tokenous
Feature activation+0.000
ine
Tokenine
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 1.289 - 1.719
CONTAINS 0.006%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Set
TokenSet
Feature activation+0.000
a
Token a
Feature activation+0.785
timer
Token timer
Feature activation+2.703
for
Token for
Feature activation+1.318
30
Token 30
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
when
Token when
Feature activation+0.000
you
Token you
Feature activation+0.000
put
Token put
Feature activation+0.000
to
Token to
Feature activation+0.000
set
Token set
Feature activation+0.000
the
Token the
Feature activation+0.994
mood
Token mood
Feature activation+2.333
,
Token,
Feature activation+0.550
sway
Token sway
Feature activation+1.428
ing
Tokening
Feature activation+0.000
in
Token in
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.061
the
Token the
Feature activation+0.000
connection
Token connection
Feature activation+0.000
with
Token with
Feature activation+0.000
setting
Token setting
Feature activation+0.000
a
Token a
Feature activation+0.768
fire
Token fire
Feature activation+2.661
in
Token in
Feature activation+1.468
Son
Token Son
Feature activation+0.000
oma
Tokenoma
Feature activation+0.000
County
Token County
Feature activation+0.000
Wine
Token Wine
Feature activation+0.465
Country
Token Country
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
set
Token set
Feature activation+0.000
in
Token in
Feature activation+0.000
stone
Token stone
Feature activation+1.440
yet
Token yet
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
Wong
Token Wong
Feature activation+0.000
Fu
Token Fu
Feature activation+0.000
A
TokenA
Feature activation+0.000
magistrate
Token magistrate
Feature activation+0.000
judge
Token judge
Feature activation+0.000
set
Token set
Feature activation+0.000
H
Token H
Feature activation+1.085
aney
Tokenaney
Feature activation+1.320
's
Token's
Feature activation+2.360
bond
Token bond
Feature activation+1.118
at
Token at
Feature activation+0.595
$
Token $
Feature activation+0.000
100
Token100
Feature activation+0.000

INTERVAL 0.859 - 1.289
CONTAINS 0.011%

They
TokenThey
Feature activation+0.000
set
Token set
Feature activation+0.175
up
Token up
Feature activation+0.000
communication
Token communication
Feature activation+0.724
systems
Token systems
Feature activation+0.785
,
Token,
Feature activation+0.997
roads
Token roads
Feature activation+0.529
,
Token,
Feature activation+0.061
railways
Token railways
Feature activation+0.068
,
Token,
Feature activation+0.000
power
Token power
Feature activation+0.000
learn
Token learn
Feature activation+0.000
it
Token it
Feature activation+0.000
and
Token and
Feature activation+0.000
set
Token set
Feature activation+0.014
up
Token up
Feature activation+0.593
their
Token their
Feature activation+1.222
own
Token own
Feature activation+2.186
organizations
Token organizations
Feature activation+0.077
that
Token that
Feature activation+0.648
were
Token were
Feature activation+0.000
independent
Token independent
Feature activation+0.000
date
Token date
Feature activation+0.000
he
Token he
Feature activation+0.000
set
Token set
Feature activation+0.669
with
Token with
Feature activation+0.375
allies
Token allies
Feature activation+0.492
to
Token to
Feature activation+1.069
close
Token close
Feature activation+0.000
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
war
Token war
Feature activation+0.000
,
Token,
Feature activation+0.000
also
Token also
Feature activation+0.000
sets
Token sets
Feature activation+0.194
out
Token out
Feature activation+0.000
an
Token an
Feature activation+0.000
alternative
Token alternative
Feature activation+1.449
menu
Token menu
Feature activation+1.037
of
Token of
Feature activation+0.000
options
Token options
Feature activation+0.000
which
Token which
Feature activation+0.000
he
Token he
Feature activation+0.000
thinks
Token thinks
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Duo
Token Duo
Feature activation+0.000
camera
Token camera
Feature activation+0.000
set
Token set
Feature activation+0.000
-
Token-
Feature activation+1.133
up
Tokenup
Feature activation+0.000
on
Token on
Feature activation+0.215
the
Token the
Feature activation+0.000
HTC
Token HTC
Feature activation+0.000
One
Token One
Feature activation+0.000

INTERVAL 0.430 - 0.859
CONTAINS 0.019%

Set
TokenSet
Feature activation+0.410
=
Token=
Feature activation+0.764
<
Token<
Feature activation+0.192
repl
Tokenrepl
Feature activation+1.051
ica
Tokenica
Feature activation+0.493
Set
TokenSet
Feature activation+0.735
Name
TokenName
Feature activation+0.448
>"
Token>"
Feature activation+0.000
function
Token function
Feature activation+0.000
connect
Token connect
Feature activation+0.000
(
Token(
Feature activation+0.000
is
Token is
Feature activation+0.000
you
Token you
Feature activation+0.000
set
Token set
Feature activation+0.000
your
Token your
Feature activation+1.108
watt
Token watt
Feature activation+0.112
age
Tokenage
Feature activation+0.604
level
Token level
Feature activation+2.253
and
Token and
Feature activation+0.202
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
gets
Token gets
Feature activation+0.000
san
Tokensan
Feature activation+0.000
ct
Tokenct
Feature activation+0.000
u
Tokenu
Feature activation+0.000
aries
Tokenaries
Feature activation+0.212
"
Token"
Feature activation+0.259
for
Token for
Feature activation+0.574
women
Token women
Feature activation+0.000
)
Token)
Feature activation+0.000
or
Token or
Feature activation+0.000
other
Token other
Feature activation+0.000
mass
Token mass
Feature activation+0.000
assigned
Token assigned
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
key
Token key
Feature activation+0.000
set
Token set
Feature activation+0.000
PA
Token PA
Feature activation+0.697
or
Token or
Feature activation+0.204
2
Token 2
Feature activation+0.000
nd
Tokennd
Feature activation+0.000
2
Token 2
Feature activation+0.000
nd
Tokennd
Feature activation+0.000
athing
Tokenathing
Feature activation+0.000
Set
Token Set
Feature activation+0.000
Review
Token Review
Feature activation+0.000
&
Token &
Feature activation+0.048
Play
Token Play
Feature activation+0.000
testing
Tokentesting
Feature activation+0.675
Guide
Token Guide
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Introduction
TokenIntroduction
Feature activation+0.000
:
Token:
Feature activation+0.000

INTERVAL 0.000 - 0.430
CONTAINS 99.952%

time
Token time
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
appointment
Token appointment
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Tokenbut
Feature activation+0.000
was
Token was
Feature activation+0.000
promoted
Token promoted
Feature activation+0.000
to
Token to
Feature activation+0.000
rear
Token rear
Feature activation+0.000
adm
Token adm
Feature activation+0.000
mix
Token mix
Feature activation+0.000
"
Token "
Feature activation+0.000
cock
Tokencock
Feature activation+0.000
-
Token-
Feature activation+0.000
blocking
Tokenblocking
Feature activation+0.000
"
Token"
Feature activation+0.000
her
Token her
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
"
Token"
Feature activation+0.000
in
Token in
Feature activation+0.000
UP
Token UP
Feature activation+0.000
's
Token's
Feature activation+0.000
Bund
Token Bund
Feature activation+0.000
el
Tokenel
Feature activation+0.000
k
Tokenk
Feature activation+0.000
hand
Tokenhand
Feature activation+0.000
stops
Token stops
Feature activation+0.000
wedding
Token wedding
Feature activation+0.000
,
Token,
Feature activation+0.000
pe
Token pe
Feature activation+0.000
eks
Tokeneks
Feature activation+0.000
)
Token)
Feature activation+0.000
from
Token from
Feature activation+0.000
upcoming
Token upcoming
Feature activation+0.000
product
Token product
Feature activation+0.000
releases
Token releases
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
themed
Token themed
Feature activation+0.000
subscription
Token subscription
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
GM
TokenGM
Feature activation+0.000
Ryan
Token Ryan
Feature activation+0.000
Pace
Token Pace
Feature activation+0.000
believes
Token believes
Feature activation+0.000
Am
Token Am
Feature activation+0.000
uk
Tokenuk
Feature activation+0.000
amara
Tokenamara
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