H4.0 top features

Top feature 0 in H4.0: (feature 19344)

TOP ACTIVATIONS
MAX = 4.625

to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
an
Token an
Feature activation+2.322
eco
Token eco
Feature activation+2.100
-
Token-
Feature activation+0.000
friendly
Tokenfriendly
Feature activation+4.625
website
Token website
Feature activation+3.699
,
Token,
Feature activation+0.569
be
Token be
Feature activation+0.000
ready
Token ready
Feature activation+0.000
to
Token to
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
doing
Token doing
Feature activation+0.000
some
Token some
Feature activation+0.337
very
Token very
Feature activation+3.788
exciting
Token exciting
Feature activation+4.595
things
Token things
Feature activation+3.355
with
Token with
Feature activation+1.132
Sonic
Token Sonic
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
one
Token one
Feature activation+2.141
or
Token or
Feature activation+1.409
more
Token more
Feature activation+1.242
of
Token of
Feature activation+2.905
the
Token the
Feature activation+3.614
following
Token following
Feature activation+4.317
:
Token:
Feature activation+1.732
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
--
Token--
Feature activation+0.000
Run
TokenRun
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
all
Token all
Feature activation+0.369
of
Token of
Feature activation+3.236
your
Token your
Feature activation+4.235
score
Token score
Feature activation+3.059
tweaking
Token tweaking
Feature activation+2.992
in
Token in
Feature activation+2.338
Digital
Token Digital
Feature activation+0.000
Per
Token Per
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
some
Token some
Feature activation+0.442
very
Token very
Feature activation+3.553
helpful
Token helpful
Feature activation+4.232
things
Token things
Feature activation+3.401
for
Token for
Feature activation+1.423
the
Token the
Feature activation+0.000
economy
Token economy
Feature activation+0.000
by
Token by
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+1.181
procedural
Token procedural
Feature activation+1.887
steps
Token steps
Feature activation+4.219
fairly
Token fairly
Feature activation+1.629
mechanically
Token mechanically
Feature activation+0.983
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
edge
Token edge
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
that
Token that
Feature activation+0.450
sort
Token sort
Feature activation+3.137
of
Token of
Feature activation+4.193
thing
Token thing
Feature activation+2.748
.
Token.
Feature activation+0.344
And
Token And
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
both
Token both
Feature activation+0.113
of
Token of
Feature activation+0.766
these
Token these
Feature activation+4.184
on
Token on
Feature activation+2.915
my
Token my
Feature activation+0.000
own
Token own
Feature activation+0.000
for
Token for
Feature activation+0.000
little
Token little
Feature activation+0.000
If
Token If
Feature activation+0.000
we
Token we
Feature activation+0.000
do
Token do
Feature activation+0.000
one
Token one
Feature activation+2.010
acc
Token acc
Feature activation+2.651
reditation
Tokenreditation
Feature activation+4.090
,
Token,
Feature activation+1.259
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
lever
Token lever
Feature activation+0.000
aged
Tokenaged
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
doing
Token doing
Feature activation+0.000
the
Token the
Feature activation+2.309
bidding
Token bidding
Feature activation+2.163
of
Token of
Feature activation+4.069
powerful
Token powerful
Feature activation+0.000
dark
Token dark
Feature activation+0.000
forces
Token forces
Feature activation+0.000
running
Token running
Feature activation+0.000
the
Token the
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+1.890
little
Token little
Feature activation+2.565
more
Token more
Feature activation+3.421
of
Token of
Feature activation+4.018
that
Token that
Feature activation+4.051
.
Token.
Feature activation+0.140
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
feel
Token feel
Feature activation+0.000
are
Token are
Feature activation+0.000
doing
Token doing
Feature activation+0.000
the
Token the
Feature activation+2.632
most
Token most
Feature activation+3.414
interesting
Token interesting
Feature activation+4.050
and
Token and
Feature activation+0.696
innovative
Token innovative
Feature activation+4.042
work
Token work
Feature activation+3.382
right
Token right
Feature activation+2.248
now
Token now
Feature activation+0.000
doing
Token doing
Feature activation+0.000
the
Token the
Feature activation+2.632
most
Token most
Feature activation+3.414
interesting
Token interesting
Feature activation+4.050
and
Token and
Feature activation+0.696
innovative
Token innovative
Feature activation+4.042
work
Token work
Feature activation+3.382
right
Token right
Feature activation+2.248
now
Token now
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+1.890
little
Token little
Feature activation+2.565
more
Token more
Feature activation+3.421
of
Token of
Feature activation+4.018
that
Token that
Feature activation+4.051
.
Token.
Feature activation+0.140
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
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
much
Token much
Feature activation+1.452
writing
Token writing
Feature activation+4.017
at
Token at
Feature activation+0.624
all
Token all
Feature activation+0.000
.
Token.
Feature activation+0.167
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
that
Token that
Feature activation+0.000
were
Token were
Feature activation+0.000
doing
Token doing
Feature activation+0.000
nothing
Token nothing
Feature activation+0.244
more
Token more
Feature activation+1.957
than
Token than
Feature activation+3.877
peacefully
Token peacefully
Feature activation+0.809
assembling
Token assembling
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
was
Token was
Feature activation+0.000
We
Token We
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+2.372
bunch
Token bunch
Feature activation+2.506
of
Token of
Feature activation+3.673
stuff
Token stuff
Feature activation+3.862
together
Token together
Feature activation+0.853
,
Token,
Feature activation+0.282
and
Token and
Feature activation+0.000
off
Token off
Feature activation+0.000
the
Token the
Feature activation+0.000
I
Token I
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+1.705
lot
Token lot
Feature activation+1.771
of
Token of
Feature activation+3.385
things
Token things
Feature activation+3.862
that
Token that
Feature activation+3.450
he
Token he
Feature activation+0.000
does
Token does
Feature activation+0.000
now
Token now
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
some
Token some
Feature activation+1.777
actual
Token actual
Feature activation+3.156
soldier
Token soldier
Feature activation+1.355
ing
Tokening
Feature activation+3.849
,
Token,
Feature activation+2.517
you
Token you
Feature activation+0.000
simply
Token simply
Feature activation+0.000
take
Token take
Feature activation+0.000
leave
Token leave
Feature activation+0.000
%
Token%
Feature activation+0.000
will
Token will
Feature activation+0.000
do
Token do
Feature activation+0.000
twice
Token twice
Feature activation+0.000
as
Token as
Feature activation+1.914
much
Token much
Feature activation+3.846
damage
Token damage
Feature activation+0.637
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000
gun
Token gun
Feature activation+0.000
at
Token at
Feature activation+0.000

Top DFA by src position
MAX = 5.369

showcase
Token showcase
Feature activation+0.031
Top resid features:
will
Token will
Feature activation+0.023
Top resid features:
inspire
Token inspire
Feature activation+0.025
Top resid features:
you
Token you
Feature activation+0.021
Top resid features:
to
Token to
Feature activation+0.043
Top resid features:
do
Token do
Feature activation+4.980
Top resid features:
an
Token an
Feature activation+0.239
Top resid features:
eco
Token eco
Feature activation+0.023
Top resid features:
-
Token-
Feature activation+0.294
Top resid features:
friendly
Tokenfriendly
Feature activation+0.169
Top resid features:
website
Token website
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.043
Top resid features:
We
Token We
Feature activation+0.019
Top resid features:
âĢ
TokenâĢ
Feature activation+0.018
Top resid features:
Ļ
TokenĻ
Feature activation+0.011
Top resid features:
re
Tokenre
Feature activation-0.003
Top resid features:
doing
Token doing
Feature activation+5.339
Top resid features:
some
Token some
Feature activation+0.379
Top resid features:
very
Token very
Feature activation+0.055
Top resid features:
exciting
Token exciting
Feature activation+0.077
Top resid features:
things
Token things
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
been
Token been
Feature activation-0.080
Top resid features:
exposed
Token exposed
Feature activation+0.006
Top resid features:
by
Token by
Feature activation+0.009
Top resid features:
Wikileaks
Token Wikileaks
Feature activation-0.003
Top resid features:
of
Token of
Feature activation+0.049
Top resid features:
doing
Token doing
Feature activation+4.848
Top resid features:
one
Token one
Feature activation+0.092
Top resid features:
or
Token or
Feature activation+0.068
Top resid features:
more
Token more
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.223
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
time
Token time
Feature activation+0.036
Top resid features:
saving
Token saving
Feature activation+0.007
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
You
Token You
Feature activation+0.009
Top resid features:
can
Token can
Feature activation-0.114
Top resid features:
do
Token do
Feature activation+5.369
Top resid features:
all
Token all
Feature activation+0.092
Top resid features:
of
Token of
Feature activation-0.034
Top resid features:
your
Token your
Feature activation+0.128
Top resid features:
score
Token score
Feature activation+0.000
Top resid features:
tweaking
Token tweaking
Feature activation+0.000
Top resid features:
president
Token president
Feature activation-0.005
Top resid features:
believes
Token believes
Feature activation-0.036
Top resid features:
that
Token that
Feature activation-0.031
Top resid features:
we
Token we
Feature activation+0.001
Top resid features:
can
Token can
Feature activation-0.028
Top resid features:
do
Token do
Feature activation+4.915
Top resid features:
some
Token some
Feature activation+0.292
Top resid features:
very
Token very
Feature activation+0.132
Top resid features:
helpful
Token helpful
Feature activation+0.153
Top resid features:
things
Token things
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
turns
Token turns
Feature activation-0.043
Top resid features:
out
Token out
Feature activation-0.082
Top resid features:
you
Token you
Feature activation+0.035
Top resid features:
can
Token can
Feature activation+0.037
Top resid features:
actually
Token actually
Feature activation+0.034
Top resid features:
do
Token do
Feature activation+4.856
Top resid features:
the
Token the
Feature activation+0.193
Top resid features:
procedural
Token procedural
Feature activation+0.160
Top resid features:
steps
Token steps
Feature activation+0.255
Top resid features:
fairly
Token fairly
Feature activation+0.000
Top resid features:
mechanically
Token mechanically
Feature activation+0.000
Top resid features:
live
Token live
Feature activation+0.053
Top resid features:
on
Token on
Feature activation+0.006
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
edge
Token edge
Feature activation-0.045
Top resid features:
to
Token to
Feature activation+0.040
Top resid features:
do
Token do
Feature activation+4.642
Top resid features:
that
Token that
Feature activation-0.026
Top resid features:
sort
Token sort
Feature activation+0.554
Top resid features:
of
Token of
Feature activation+0.130
Top resid features:
thing
Token thing
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Thankfully
Token Thankfully
Feature activation-0.112
Top resid features:
I
Token I
Feature activation-0.009
Top resid features:
'm
Token'm
Feature activation+0.005
Top resid features:
able
Token able
Feature activation-0.108
Top resid features:
to
Token to
Feature activation-0.028
Top resid features:
do
Token do
Feature activation+4.757
Top resid features:
both
Token both
Feature activation+0.588
Top resid features:
of
Token of
Feature activation+0.278
Top resid features:
these
Token these
Feature activation+0.033
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
my
Token my
Feature activation+0.000
Top resid features:
Google
Token Google
Feature activation+0.003
Top resid features:
product
Token product
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.048
Top resid features:
If
Token If
Feature activation-0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+4.415
Top resid features:
one
Token one
Feature activation+0.571
Top resid features:
acc
Token acc
Feature activation+0.081
Top resid features:
reditation
Tokenreditation
Feature activation+0.029
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
script
Token script
Feature activation-0.000
Top resid features:
handed
Token handed
Feature activation-0.005
Top resid features:
them
Token them
Feature activation-0.021
Top resid features:
,
Token,
Feature activation+0.128
Top resid features:
doing
Token doing
Feature activation+4.581
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
bidding
Token bidding
Feature activation+0.633
Top resid features:
of
Token of
Feature activation-0.052
Top resid features:
powerful
Token powerful
Feature activation+0.000
Top resid features:
dark
Token dark
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
would
Token would
Feature activation-0.000
Top resid features:
expect
Token expect
Feature activation-0.004
Top resid features:
him
Token him
Feature activation-0.034
Top resid features:
to
Token to
Feature activation+0.060
Top resid features:
do
Token do
Feature activation+4.615
Top resid features:
a
Token a
Feature activation+0.116
Top resid features:
little
Token little
Feature activation+0.242
Top resid features:
more
Token more
Feature activation+0.106
Top resid features:
of
Token of
Feature activation+0.280
Top resid features:
that
Token that
Feature activation-0.082
Top resid features:
brands
Token brands
Feature activation-0.043
Top resid features:
do
Token do
Feature activation+0.059
Top resid features:
you
Token you
Feature activation+0.027
Top resid features:
feel
Token feel
Feature activation+0.030
Top resid features:
are
Token are
Feature activation+0.073
Top resid features:
doing
Token doing
Feature activation+4.584
Top resid features:
the
Token the
Feature activation+0.086
Top resid features:
most
Token most
Feature activation+0.475
Top resid features:
interesting
Token interesting
Feature activation+0.038
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
innovative
Token innovative
Feature activation+0.000
Top resid features:
brands
Token brands
Feature activation-0.031
Top resid features:
do
Token do
Feature activation+0.035
Top resid features:
you
Token you
Feature activation+0.014
Top resid features:
feel
Token feel
Feature activation-0.018
Top resid features:
are
Token are
Feature activation+0.035
Top resid features:
doing
Token doing
Feature activation+4.428
Top resid features:
the
Token the
Feature activation+0.056
Top resid features:
most
Token most
Feature activation+0.456
Top resid features:
interesting
Token interesting
Feature activation+0.072
Top resid features:
and
Token and
Feature activation+0.398
Top resid features:
innovative
Token innovative
Feature activation-0.065
Top resid features:
I
Token I
Feature activation+0.014
Top resid features:
would
Token would
Feature activation+0.002
Top resid features:
expect
Token expect
Feature activation-0.010
Top resid features:
him
Token him
Feature activation-0.000
Top resid features:
to
Token to
Feature activation+0.063
Top resid features:
do
Token do
Feature activation+4.256
Top resid features:
a
Token a
Feature activation+0.093
Top resid features:
little
Token little
Feature activation+0.380
Top resid features:
more
Token more
Feature activation+0.377
Top resid features:
of
Token of
Feature activation+0.089
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.019
Top resid features:
didn
Token didn
Feature activation-0.005
Top resid features:
âĢ
TokenâĢ
Feature activation+0.126
Top resid features:
Ļ
TokenĻ
Feature activation+0.013
Top resid features:
t
Tokent
Feature activation+0.013
Top resid features:
do
Token do
Feature activation+4.844
Top resid features:
much
Token much
Feature activation+0.011
Top resid features:
writing
Token writing
Feature activation+0.149
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
indigenous
Token indigenous
Feature activation-0.018
Top resid features:
protect
Token protect
Feature activation-0.001
Top resid features:
ors
Tokenors
Feature activation-0.001
Top resid features:
that
Token that
Feature activation-0.015
Top resid features:
were
Token were
Feature activation+0.027
Top resid features:
doing
Token doing
Feature activation+4.635
Top resid features:
nothing
Token nothing
Feature activation-0.030
Top resid features:
more
Token more
Feature activation+0.277
Top resid features:
than
Token than
Feature activation+0.142
Top resid features:
peacefully
Token peacefully
Feature activation+0.000
Top resid features:
assembling
Token assembling
Feature activation+0.000
Top resid features:
talk
Token talk
Feature activation+0.018
Top resid features:
about
Token about
Feature activation+0.010
Top resid features:
anything
Token anything
Feature activation-0.013
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
We
Token We
Feature activation-0.004
Top resid features:
do
Token do
Feature activation+4.651
Top resid features:
a
Token a
Feature activation+0.087
Top resid features:
bunch
Token bunch
Feature activation+0.148
Top resid features:
of
Token of
Feature activation+0.156
Top resid features:
stuff
Token stuff
Feature activation+0.042
Top resid features:
together
Token together
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
corner
Token corner
Feature activation-0.010
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
I
Token I
Feature activation+0.039
Top resid features:
do
Token do
Feature activation+4.676
Top resid features:
a
Token a
Feature activation+0.104
Top resid features:
lot
Token lot
Feature activation+0.153
Top resid features:
of
Token of
Feature activation+0.069
Top resid features:
things
Token things
Feature activation+0.081
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
ars
Tokenars
Feature activation+0.000
Top resid features:
are
Token are
Feature activation-0.010
Top resid features:
sent
Token sent
Feature activation+0.012
Top resid features:
overseas
Token overseas
Feature activation-0.003
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
do
Token do
Feature activation+4.537
Top resid features:
some
Token some
Feature activation+0.136
Top resid features:
actual
Token actual
Feature activation+0.117
Top resid features:
soldier
Token soldier
Feature activation+0.148
Top resid features:
ing
Tokening
Feature activation+0.104
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
guns
Token guns
Feature activation-0.074
Top resid features:
at
Token at
Feature activation+0.009
Top resid features:
40
Token 40
Feature activation+0.011
Top resid features:
%
Token%
Feature activation+0.064
Top resid features:
will
Token will
Feature activation+0.062
Top resid features:
do
Token do
Feature activation+4.709
Top resid features:
twice
Token twice
Feature activation+0.042
Top resid features:
as
Token as
Feature activation+0.144
Top resid features:
much
Token much
Feature activation+0.114
Top resid features:
damage
Token damage
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.51

Head 1: 0.04

Head 2: 0.02

Head 3: 0.05

Head 4: 0.03

Head 5: 0.04

Head 6: 0.04

Head 7: 0.09

Head 8: 0.02

Head 9: 0.05

Head 10: 0.01

Head 11: 0.09

Positive logits

iatrics1.53

grunt1.50

unia1.41

migrate1.38

chores1.37

strip1.37

homework1.36

oodoo1.31

rehab1.30

emulate1.29

work1.28

damage1.26

intermitt1.25

harm1.23

upkeep1.22

recreate1.19

bidding1.18

rundown1.17

concurrently1.17

imitate1.17

Negative logits

ウス-1.51

Magikarp-1.37

urated-1.37

Phi-1.32

76561-1.31

vanquished-1.26

Bound-1.25

opened-1.25

osponsors-1.23

rounded-1.22

ceilings-1.22

jected-1.20

Courage-1.19

EStreamFrame-1.19

Arri-1.19

being-1.19

iets-1.16

laure-1.16

boards-1.15

Advis-1.15

INTERVAL 4.162 - 4.625
CONTAINS 0.001%

edge
Token edge
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
that
Token that
Feature activation+0.450
sort
Token sort
Feature activation+3.137
of
Token of
Feature activation+4.193
thing
Token thing
Feature activation+2.748
.
Token.
Feature activation+0.344
And
Token And
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
all
Token all
Feature activation+0.369
of
Token of
Feature activation+3.236
your
Token your
Feature activation+4.235
score
Token score
Feature activation+3.059
tweaking
Token tweaking
Feature activation+2.992
in
Token in
Feature activation+2.338
Digital
Token Digital
Feature activation+0.000
Per
Token Per
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
an
Token an
Feature activation+2.322
eco
Token eco
Feature activation+2.100
-
Token-
Feature activation+0.000
friendly
Tokenfriendly
Feature activation+4.625
website
Token website
Feature activation+3.699
,
Token,
Feature activation+0.569
be
Token be
Feature activation+0.000
ready
Token ready
Feature activation+0.000
to
Token to
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
doing
Token doing
Feature activation+0.000
some
Token some
Feature activation+0.337
very
Token very
Feature activation+3.788
exciting
Token exciting
Feature activation+4.595
things
Token things
Feature activation+3.355
with
Token with
Feature activation+1.132
Sonic
Token Sonic
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
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
some
Token some
Feature activation+0.442
very
Token very
Feature activation+3.553
helpful
Token helpful
Feature activation+4.232
things
Token things
Feature activation+3.401
for
Token for
Feature activation+1.423
the
Token the
Feature activation+0.000
economy
Token economy
Feature activation+0.000
by
Token by
Feature activation+0.000

INTERVAL 3.700 - 4.162
CONTAINS 0.002%

doing
Token doing
Feature activation+0.000
the
Token the
Feature activation+2.632
most
Token most
Feature activation+3.414
interesting
Token interesting
Feature activation+4.050
and
Token and
Feature activation+0.696
innovative
Token innovative
Feature activation+4.042
work
Token work
Feature activation+3.382
right
Token right
Feature activation+2.248
now
Token now
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
doing
Token doing
Feature activation+0.000
the
Token the
Feature activation+2.309
bidding
Token bidding
Feature activation+2.163
of
Token of
Feature activation+4.069
powerful
Token powerful
Feature activation+0.000
dark
Token dark
Feature activation+0.000
forces
Token forces
Feature activation+0.000
running
Token running
Feature activation+0.000
the
Token the
Feature activation+0.000
We
Token We
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+2.372
bunch
Token bunch
Feature activation+2.506
of
Token of
Feature activation+3.673
stuff
Token stuff
Feature activation+3.862
together
Token together
Feature activation+0.853
,
Token,
Feature activation+0.282
and
Token and
Feature activation+0.000
off
Token off
Feature activation+0.000
the
Token the
Feature activation+0.000
feel
Token feel
Feature activation+0.000
are
Token are
Feature activation+0.000
doing
Token doing
Feature activation+0.000
the
Token the
Feature activation+2.632
most
Token most
Feature activation+3.414
interesting
Token interesting
Feature activation+4.050
and
Token and
Feature activation+0.696
innovative
Token innovative
Feature activation+4.042
work
Token work
Feature activation+3.382
right
Token right
Feature activation+2.248
now
Token now
Feature activation+0.000
that
Token that
Feature activation+0.000
were
Token were
Feature activation+0.000
doing
Token doing
Feature activation+0.000
nothing
Token nothing
Feature activation+0.244
more
Token more
Feature activation+1.957
than
Token than
Feature activation+3.877
peacefully
Token peacefully
Feature activation+0.809
assembling
Token assembling
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 3.237 - 3.700
CONTAINS 0.006%

do
Token do
Feature activation+0.000
an
Token an
Feature activation+2.322
eco
Token eco
Feature activation+2.100
-
Token-
Feature activation+0.000
friendly
Tokenfriendly
Feature activation+4.625
website
Token website
Feature activation+3.699
,
Token,
Feature activation+0.569
be
Token be
Feature activation+0.000
ready
Token ready
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
and
Token and
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+1.283
most
Token most
Feature activation+3.602
to
Token to
Feature activation+3.123
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
stay
Token stay
Feature activation+0.000
around
Token around
Feature activation+0.000
and
Token and
Feature activation+0.000
do
Token do
Feature activation+0.000
some
Token some
Feature activation+0.845
hands
Token hands
Feature activation+3.338
on
Token on
Feature activation+1.991
development
Token development
Feature activation+0.000
with
Token with
Feature activation+0.200
others
Token others
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
if
Token if
Feature activation+0.000
doing
Token doing
Feature activation+0.000
their
Token their
Feature activation+2.334
best
Token best
Feature activation+3.308
to
Token to
Feature activation+1.099
down
Token down
Feature activation+0.000
play
Tokenplay
Feature activation+0.000
the
Token the
Feature activation+0.000
sensational
Token sensational
Feature activation+0.000
you
Token you
Feature activation+0.000
wanna
Token wanna
Feature activation+0.000
do
Token do
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
it
Tokenit
Feature activation+3.309
tonight
Token tonight
Feature activation+0.368
"
Token"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Roy
TokenRoy
Feature activation+0.000

INTERVAL 2.775 - 3.237
CONTAINS 0.007%

your
Token your
Feature activation+0.000
money
Token money
Feature activation+0.000
is
Token is
Feature activation+0.000
doing
Token doing
Feature activation+0.000
substantive
Token substantive
Feature activation+1.819
good
Token good
Feature activation+2.965
?
Token?
Feature activation+0.000
How
Token How
Feature activation+0.000
widely
Token widely
Feature activation+0.000
are
Token are
Feature activation+0.000
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
doing
Token doing
Feature activation+0.000
F
Token F
Feature activation+1.550
TR
TokenTR
Feature activation+3.179
mostly
Token mostly
Feature activation+3.225
out
Token out
Feature activation+3.487
of
Token of
Feature activation+3.477
sense
Token sense
Feature activation+0.000
of
Token of
Feature activation+0.000
t
Tokent
Feature activation+0.000
done
Token done
Feature activation+0.000
some
Token some
Feature activation+0.263
of
Token of
Feature activation+3.231
the
Token the
Feature activation+3.535
things
Token things
Feature activation+2.980
it
Token it
Feature activation+1.527
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
General
Token General
Feature activation+0.000
computers
Token computers
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
ever
Token ever
Feature activation+0.000
more
Token more
Feature activation+2.255
things
Token things
Feature activation+3.073
,
Token,
Feature activation+0.428
from
Token from
Feature activation+0.154
recognizing
Token recognizing
Feature activation+0.000
the
Token the
Feature activation+0.000
contents
Token contents
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
any
Token any
Feature activation+0.771
major
Token major
Feature activation+3.352
press
Token press
Feature activation+2.876
obligation
Token obligation
Feature activation+2.889
together
Token together
Feature activation+0.439
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
way
Token way
Feature activation+0.000
both
Token both
Feature activation+0.000

INTERVAL 2.312 - 2.775
CONTAINS 0.015%

When
Token When
Feature activation+0.000
companies
Token companies
Feature activation+0.000
do
Token do
Feature activation+0.000
this
Token this
Feature activation+1.151
sort
Token sort
Feature activation+1.205
of
Token of
Feature activation+2.325
thing
Token thing
Feature activation+2.817
,
Token,
Feature activation+0.870
it
Token it
Feature activation+0.000
piss
Token piss
Feature activation+0.000
es
Tokenes
Feature activation+0.000
here
Token here
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
did
Token did
Feature activation+0.000
some
Token some
Feature activation+1.095
good
Token good
Feature activation+2.686
things
Token things
Feature activation+2.600
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
not
Token not
Feature activation+0.000
good
Token good
Feature activation+0.000
and
Token and
Feature activation+0.000
now
Token now
Feature activation+0.000
does
Token does
Feature activation+0.000
all
Token all
Feature activation+0.739
the
Token the
Feature activation+2.477
buying
Token buying
Feature activation+2.757
.
Token.
Feature activation+0.408
Sister
Token Sister
Feature activation+0.000
Gina
Token Gina
Feature activation+0.000
also
Token also
Feature activation+0.000
comes
Token comes
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
any
Token any
Feature activation+0.000
kind
Token kind
Feature activation+2.499
of
Token of
Feature activation+3.563
due
Token due
Feature activation+2.763
diligence
Token diligence
Feature activation+2.626
as
Token as
Feature activation+0.058
it
Token it
Feature activation+0.000
engages
Token engages
Feature activation+0.000
in
Token in
Feature activation+0.000
done
Token done
Feature activation+0.000
extensive
Token extensive
Feature activation+1.305
post
Token post
Feature activation+0.000
-
Token-
Feature activation+0.000
grad
Tokengrad
Feature activation+0.000
education
Token education
Feature activation+2.706
in
Token in
Feature activation+0.572
an
Token an
Feature activation+0.000
effort
Token effort
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000

INTERVAL 1.850 - 2.312
CONTAINS 0.019%

Ultimately
Token Ultimately
Feature activation+0.000
,
Token,
Feature activation+0.000
Mubarak
Token Mubarak
Feature activation+0.000
will
Token will
Feature activation+0.000
do
Token do
Feature activation+0.000
whatever
Token whatever
Feature activation+1.879
he
Token he
Feature activation+1.402
has
Token has
Feature activation+0.326
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
to
Token to
Feature activation+0.000
voted
Token voted
Feature activation+0.000
for
Token for
Feature activation+0.000
Yanukovych
Token Yanukovych
Feature activation+0.000
did
Token did
Feature activation+0.000
so
Token so
Feature activation+0.000
out
Token out
Feature activation+1.938
of
Token of
Feature activation+0.860
suspicion
Token suspicion
Feature activation+0.000
of
Token of
Feature activation+0.000
Y
Token Y
Feature activation+0.000
ush
Tokenush
Feature activation+0.000
would
Token would
Feature activation+0.000
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+1.890
little
Token little
Feature activation+2.565
more
Token more
Feature activation+3.421
of
Token of
Feature activation+4.018
that
Token that
Feature activation+4.051
.
Token.
Feature activation+0.140
get
Token get
Feature activation+0.000
farther
Token farther
Feature activation+0.000
and
Token and
Feature activation+0.000
do
Token do
Feature activation+0.176
more
Token more
Feature activation+1.342
coding
Token coding
Feature activation+2.170
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000
went
Token went
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
we
Token we
Feature activation+0.000
did
Token did
Feature activation+0.000
a
Token a
Feature activation+1.204
great
Token great
Feature activation+1.908
job
Token job
Feature activation+0.370
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

INTERVAL 1.387 - 1.850
CONTAINS 0.022%

,
Token,
Feature activation+0.261
better
Token better
Feature activation+1.036
,
Token,
Feature activation+0.000
smarter
Token smarter
Feature activation+3.156
,
Token,
Feature activation+0.103
cheaper
Token cheaper
Feature activation+1.492
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
things
Token things
Feature activation+0.000
tools
Token tools
Feature activation+0.000
they
Token they
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
their
Token their
Feature activation+1.564
job
Token job
Feature activation+1.938
safely
Token safely
Feature activation+0.274
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
building
Token building
Feature activation+0.000
,
Token,
Feature activation+0.000
K
Token K
Feature activation+0.000
FC
TokenFC
Feature activation+0.000
is
Token is
Feature activation+0.000
doing
Token doing
Feature activation+0.000
a
Token a
Feature activation+1.571
roaring
Token roaring
Feature activation+2.296
business
Token business
Feature activation+0.000
with
Token with
Feature activation+0.195
close
Token close
Feature activation+0.000
to
Token to
Feature activation+0.000
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
is
Token is
Feature activation+1.443
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
a
Token a
Feature activation+0.000
unique
Token unique
Feature activation+0.000
visual
Token visual
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
do
Token do
Feature activation+0.000
enough
Token enough
Feature activation+1.707
to
Token to
Feature activation+1.765
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

INTERVAL 0.925 - 1.387
CONTAINS 0.027%

.
Token.
Feature activation+0.000
What
Token What
Feature activation+0.000
business
Token business
Feature activation+0.000
does
Token does
Feature activation+0.000
the
Token the
Feature activation+0.330
government
Token government
Feature activation+1.068
have
Token have
Feature activation+0.484
making
Token making
Feature activation+0.000
rules
Token rules
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
scene
Token scene
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+0.978
special
Token special
Feature activation+1.832
dance
Token dance
Feature activation+0.482
with
Token with
Feature activation+0.000
Bennett
Token Bennett
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
going
Token going
Feature activation+0.000
about
Token about
Feature activation+0.000
doing
Token doing
Feature activation+0.000
their
Token their
Feature activation+1.078
assigned
Token assigned
Feature activation+2.195
work
Token work
Feature activation+2.632
in
Token in
Feature activation+0.335
a
Token a
Feature activation+0.000
method
Token method
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+0.000
all
Token all
Feature activation+1.357
,
Token,
Feature activation+1.032
from
Token from
Feature activation+1.179
comedy
Token comedy
Feature activation+0.000
(
Token (
Feature activation+0.000
The
TokenThe
Feature activation+0.000
now
Token now
Feature activation+0.000
on
Token on
Feature activation+0.000
why
Token why
Feature activation+0.000
he
Token he
Feature activation+0.000
did
Token did
Feature activation+0.000
what
Token what
Feature activation+0.976
he
Token he
Feature activation+1.232
did
Token did
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
don
Token don
Feature activation+0.000

INTERVAL 0.462 - 0.925
CONTAINS 0.036%

the
Token the
Feature activation+0.000
riders
Token riders
Feature activation+0.000
did
Token did
Feature activation+0.000
130
Token 130
Feature activation+1.077
or
Token or
Feature activation+0.000
so
Token so
Feature activation+0.489
hours
Token hours
Feature activation+0.752
of
Token of
Feature activation+2.411
work
Token work
Feature activation+2.509
,
Token,
Feature activation+0.938
each
Token each
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
do
Token do
Feature activation+0.000
X
Token X
Feature activation+0.564
SL
TokenSL
Feature activation+0.392
T
TokenT
Feature activation+1.011
.
Token.
Feature activation+1.306
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
who
Token who
Feature activation+0.000
long
Token long
Feature activation+0.000
ed
Tokened
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
something
Token something
Feature activation+0.738
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
even
Token even
Feature activation+0.000
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
One
TokenOne
Feature activation+0.000
thing
Token thing
Feature activation+0.000
we
Token we
Feature activation+0.000
'll
Token'll
Feature activation+0.000
do
Token do
Feature activation+0.000
is
Token is
Feature activation+0.798
dive
Token dive
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
impact
Token impact
Feature activation+0.000
of
Token of
Feature activation+0.000
like
Token like
Feature activation+0.000
Loft
Token Loft
Feature activation+0.000
on
Tokenon
Feature activation+0.000
has
Token has
Feature activation+0.000
done
Token done
Feature activation+0.000
some
Token some
Feature activation+0.562
things
Token things
Feature activation+1.779
to
Token to
Feature activation+2.007
improve
Token improve
Feature activation+0.000
his
Token his
Feature activation+0.000
speed
Token speed
Feature activation+0.000

INTERVAL 0.000 - 0.462
CONTAINS 99.866%

:
Token:
Feature activation+0.000
re
Token re
Feature activation+0.000
ams
Tokenams
Feature activation+0.000
of
Token of
Feature activation+0.000
papers
Token papers
Feature activation+0.000
plus
Token plus
Feature activation+0.000
a
Token a
Feature activation+0.000
corn
Token corn
Feature activation+0.000
uc
Tokenuc
Feature activation+0.000
opia
Tokenopia
Feature activation+0.000
of
Token of
Feature activation+0.000
)
Token)
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Command
Token Command
Feature activation+0.000
ant
Tokenant
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
fren
Token fren
Feature activation+0.000
z
Tokenz
Feature activation+0.000
ied
Tokenied
Feature activation+0.000
cuts
Token cuts
Feature activation+0.000
come
Token come
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
heels
Token heels
Feature activation+0.000
of
Token of
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
efforts
Token efforts
Feature activation+0.000
to
Token to
Feature activation+0.000
reduce
Token reduce
Feature activation+0.000
overhead
Token overhead
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+0.000
shorter
Token shorter
Feature activation+0.000
.
Token.
Feature activation+0.000
En
Token En
Feature activation+0.000
o
Tokeno
Feature activation+0.000
related
Token related
Feature activation+0.000
the
Token the
Feature activation+0.000
story
Token story
Feature activation+0.000
Rather
TokenRather
Feature activation+0.000
than
Token than
Feature activation+0.000
look
Token look
Feature activation+0.000
beyond
Token beyond
Feature activation+0.000
the
Token the
Feature activation+0.000
councils
Token councils
Feature activation+0.000
and
Token and
Feature activation+0.000
see
Token see
Feature activation+0.000
what
Token what
Feature activation+0.000
tribes
Token tribes
Feature activation+0.000
historically
Token historically
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 H4.0: (feature 85)

TOP ACTIVATIONS
MAX = 4.007

test
Token test
Feature activation+0.000
and
Token and
Feature activation+0.000
share
Token share
Feature activation+0.232
simple
Token simple
Feature activation+2.221
or
Token or
Feature activation+0.000
complex
Token complex
Feature activation+4.007
interactions
Token interactions
Feature activation+2.443
with
Token with
Feature activation+1.362
a
Token a
Feature activation+0.000
design
Token design
Feature activation+0.000
team
Token team
Feature activation+0.000
pregnancy
Token pregnancy
Feature activation+0.000
.[
Token.[
Feature activation+0.000
8
Token8
Feature activation+0.000
])
Token])
Feature activation+0.000
Sharing
Token Sharing
Feature activation+0.752
time
Token time
Feature activation+3.766
together
Token together
Feature activation+2.588
and
Token and
Feature activation+0.674
finding
Token finding
Feature activation+1.353
common
Token common
Feature activation+0.000
interests
Token interests
Feature activation+0.000
up
Token up
Feature activation+0.000
sharing
Token sharing
Feature activation+0.515
the
Token the
Feature activation+3.224
bot
Token bot
Feature activation+0.221
lane
Tokenlane
Feature activation+1.128
with
Token with
Feature activation+3.666
two
Token two
Feature activation+0.000
different
Token different
Feature activation+0.000
supports
Token supports
Feature activation+0.000
:
Token:
Feature activation+0.000
Ale
Token Ale
Feature activation+0.000
state
Token state
Feature activation+0.000
party
Token party
Feature activation+0.000
shares
Token shares
Feature activation+1.431
these
Token these
Feature activation+2.550
receipts
Token receipts
Feature activation+2.856
with
Token with
Feature activation+3.620
such
Token such
Feature activation+0.000
groups
Token groups
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
Hamilton
Token Hamilton
Feature activation+0.000
free
Token free
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
sharing
Token sharing
Feature activation+0.020
the
Token the
Feature activation+3.294
work
Token work
Feature activation+3.533
they
Token they
Feature activation+1.646
've
Token've
Feature activation+0.000
done
Token done
Feature activation+0.000
as
Token as
Feature activation+0.000
part
Token part
Feature activation+0.000
she
Token she
Feature activation+0.000
has
Token has
Feature activation+0.000
shared
Token shared
Feature activation+0.000
a
Token a
Feature activation+3.087
few
Token few
Feature activation+3.034
of
Token of
Feature activation+3.532
her
Token her
Feature activation+3.355
winning
Token winning
Feature activation+1.219
ingredients
Token ingredients
Feature activation+0.739
with
Token with
Feature activation+1.896
us
Token us
Feature activation+0.000
minister
Token minister
Feature activation+0.000
insisted
Token insisted
Feature activation+0.000
she
Token she
Feature activation+0.000
shares
Token shares
Feature activation+2.118
people
Token people
Feature activation+2.443
's
Token's
Feature activation+3.519
concerns
Token concerns
Feature activation+2.802
and
Token and
Feature activation+0.199
remains
Token remains
Feature activation+0.000
committed
Token committed
Feature activation+0.000
to
Token to
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
shared
Token shared
Feature activation+0.000
the
Token the
Feature activation+2.993
team
Token team
Feature activation+3.468
lead
Token lead
Feature activation+3.758
with
Token with
Feature activation+3.237
five
Token five
Feature activation+0.000
goals
Token goals
Feature activation+0.000
in
Token in
Feature activation+0.000
umble
Tokenumble
Feature activation+0.000
B
Token B
Feature activation+0.000
izz
Tokenizz
Feature activation+0.000
will
Token will
Feature activation+0.000
share
Token share
Feature activation+0.145
the
Token the
Feature activation+3.467
app
Token app
Feature activation+0.418
's
Token's
Feature activation+1.621
"
Token "
Feature activation+0.629
women
Tokenwomen
Feature activation+0.000
first
Token first
Feature activation+0.000
.
Token.
Feature activation+0.000
Currently
Token Currently
Feature activation+0.000
it
Token it
Feature activation+0.000
shares
Token shares
Feature activation+1.775
the
Token the
Feature activation+3.165
same
Token same
Feature activation+3.455
slot
Token slot
Feature activation+2.511
as
Token as
Feature activation+0.546
colour
Token colour
Feature activation+0.000
crystals
Token crystals
Feature activation+0.000
.
Token.
Feature activation+0.000
wrongdoing
Token wrongdoing
Feature activation+0.000
following
Token following
Feature activation+0.000
allegations
Token allegations
Feature activation+0.000
he
Token he
Feature activation+0.000
shared
Token shared
Feature activation+0.199
private
Token private
Feature activation+3.416
information
Token information
Feature activation+2.431
without
Token without
Feature activation+1.862
consent
Token consent
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ingram
Token Ingram
Feature activation+0.000
.
Token.
Feature activation+0.000
Ingram
Token Ingram
Feature activation+0.000
shares
Token shares
Feature activation+0.850
a
Token a
Feature activation+3.306
draft
Token draft
Feature activation+3.415
position
Token position
Feature activation+3.156
with
Token with
Feature activation+2.659
Ball
Token Ball
Feature activation+0.000
,
Token,
Feature activation+0.000
being
Token being
Feature activation+0.000
an
Token an
Feature activation+0.000
assault
Token assault
Feature activation+0.000
rifle
Token rifle
Feature activation+0.000
,
Token,
Feature activation+0.000
shares
Token shares
Feature activation+0.639
a
Token a
Feature activation+3.415
"
Token "
Feature activation+1.750
f
Tokenf
Feature activation+0.176
ist
Tokenist
Feature activation+0.000
bump
Token bump
Feature activation+0.000
"
Token"
Feature activation+1.148
af
Tokenaf
Feature activation+0.000
zai
Tokenzai
Feature activation+0.000
went
Token went
Feature activation+0.000
on
Token on
Feature activation+0.000
share
Token share
Feature activation+0.000
the
Token the
Feature activation+3.413
Nobel
Token Nobel
Feature activation+0.539
Peace
Token Peace
Feature activation+0.000
Prize
Token Prize
Feature activation+0.430
in
Token in
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
has
Token has
Feature activation+0.000
shared
Token shared
Feature activation+0.000
a
Token a
Feature activation+3.087
few
Token few
Feature activation+3.034
of
Token of
Feature activation+3.532
her
Token her
Feature activation+3.355
winning
Token winning
Feature activation+1.219
ingredients
Token ingredients
Feature activation+0.739
with
Token with
Feature activation+1.896
us
Token us
Feature activation+0.000
.
Token.
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
easy
Token easy
Feature activation+0.000
as
Token as
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
a
Token a
Feature activation+3.343
URL
Token URL
Feature activation+2.439
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
the
Token the
Feature activation+0.000
SAP
Token SAP
Feature activation+0.000
Center
Token Center
Feature activation+0.000
,
Token,
Feature activation+0.000
sharing
Token sharing
Feature activation+0.423
the
Token the
Feature activation+3.342
same
Token same
Feature activation+2.989
arena
Token arena
Feature activation+1.860
as
Token as
Feature activation+0.786
the
Token the
Feature activation+0.000
NHL
Token NHL
Feature activation+0.000
Brandon
Token Brandon
Feature activation+0.000
Ingram
Token Ingram
Feature activation+0.000
.
Token.
Feature activation+0.000
Ingram
Token Ingram
Feature activation+0.000
shares
Token shares
Feature activation+0.850
a
Token a
Feature activation+3.306
draft
Token draft
Feature activation+3.415
position
Token position
Feature activation+3.156
with
Token with
Feature activation+2.659
Ball
Token Ball
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
free
Token free
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
sharing
Token sharing
Feature activation+0.020
the
Token the
Feature activation+3.294
work
Token work
Feature activation+3.533
they
Token they
Feature activation+1.646
've
Token've
Feature activation+0.000
done
Token done
Feature activation+0.000
as
Token as
Feature activation+0.000
Anarch
Token Anarch
Feature activation+0.000
ists
Tokenists
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
the
Token the
Feature activation+2.599
same
Token same
Feature activation+2.755
basic
Token basic
Feature activation+3.250
tendencies
Token tendencies
Feature activation+1.388
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 4.923

lightweight
Token lightweight
Feature activation+0.010
Top resid features:
alternative
Token alternative
Feature activation-0.008
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
test
Token test
Feature activation+0.009
Top resid features:
and
Token and
Feature activation+0.044
Top resid features:
share
Token share
Feature activation+4.431
Top resid features:
simple
Token simple
Feature activation+0.080
Top resid features:
or
Token or
Feature activation+0.168
Top resid features:
complex
Token complex
Feature activation+0.018
Top resid features:
interactions
Token interactions
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
during
Token during
Feature activation+0.006
Top resid features:
pregnancy
Token pregnancy
Feature activation-0.009
Top resid features:
.[
Token.[
Feature activation+0.004
Top resid features:
8
Token8
Feature activation+0.002
Top resid features:
])
Token])
Feature activation-0.006
Top resid features:
Sharing
Token Sharing
Feature activation+4.839
Top resid features:
time
Token time
Feature activation-0.131
Top resid features:
together
Token together
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
finding
Token finding
Feature activation+0.000
Top resid features:
common
Token common
Feature activation+0.000
Top resid features:
where
Token where
Feature activation+0.027
Top resid features:
he
Token he
Feature activation-0.020
Top resid features:
would
Token would
Feature activation+0.017
Top resid features:
end
Token end
Feature activation-0.004
Top resid features:
up
Token up
Feature activation-0.026
Top resid features:
sharing
Token sharing
Feature activation+4.911
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
bot
Token bot
Feature activation-0.000
Top resid features:
lane
Tokenlane
Feature activation+0.075
Top resid features:
with
Token with
Feature activation-0.425
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
The
TokenThe
Feature activation+0.003
Top resid features:
state
Token state
Feature activation+0.003
Top resid features:
party
Token party
Feature activation-0.001
Top resid features:
shares
Token shares
Feature activation+4.873
Top resid features:
these
Token these
Feature activation+0.024
Top resid features:
receipts
Token receipts
Feature activation-0.169
Top resid features:
with
Token with
Feature activation-0.243
Top resid features:
such
Token such
Feature activation+0.000
Top resid features:
groups
Token groups
Feature activation+0.000
Top resid features:
performance
Token performance
Feature activation+0.003
Top resid features:
for
Token for
Feature activation-0.003
Top resid features:
free
Token free
Feature activation-0.031
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
or
Token or
Feature activation+0.019
Top resid features:
sharing
Token sharing
Feature activation+4.740
Top resid features:
the
Token the
Feature activation-0.116
Top resid features:
work
Token work
Feature activation-0.279
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
've
Token've
Feature activation+0.000
Top resid features:
done
Token done
Feature activation+0.000
Top resid features:
now
Token now
Feature activation+0.005
Top resid features:
!)
Token!)
Feature activation-0.009
Top resid features:
but
Token but
Feature activation+0.054
Top resid features:
she
Token she
Feature activation-0.008
Top resid features:
has
Token has
Feature activation+0.053
Top resid features:
shared
Token shared
Feature activation+4.272
Top resid features:
a
Token a
Feature activation+0.058
Top resid features:
few
Token few
Feature activation-0.087
Top resid features:
of
Token of
Feature activation+0.024
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
winning
Token winning
Feature activation+0.000
Top resid features:
former
Token former
Feature activation+0.003
Top resid features:
health
Token health
Feature activation+0.006
Top resid features:
minister
Token minister
Feature activation-0.003
Top resid features:
insisted
Token insisted
Feature activation-0.018
Top resid features:
she
Token she
Feature activation+0.011
Top resid features:
shares
Token shares
Feature activation+4.505
Top resid features:
people
Token people
Feature activation+0.100
Top resid features:
's
Token's
Feature activation-0.125
Top resid features:
concerns
Token concerns
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
remains
Token remains
Feature activation+0.000
Top resid features:
23
Token 23
Feature activation-0.065
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
year
Tokenyear
Feature activation+0.004
Top resid features:
-
Token-
Feature activation-0.005
Top resid features:
old
Tokenold
Feature activation+0.010
Top resid features:
shared
Token shared
Feature activation+4.923
Top resid features:
the
Token the
Feature activation-0.326
Top resid features:
team
Token team
Feature activation-0.134
Top resid features:
lead
Token lead
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
five
Token five
Feature activation+0.000
Top resid features:
B
Token B
Feature activation-0.001
Top resid features:
umble
Tokenumble
Feature activation-0.005
Top resid features:
B
Token B
Feature activation-0.026
Top resid features:
izz
Tokenizz
Feature activation-0.003
Top resid features:
will
Token will
Feature activation+0.099
Top resid features:
share
Token share
Feature activation+4.423
Top resid features:
the
Token the
Feature activation-0.216
Top resid features:
app
Token app
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
women
Tokenwomen
Feature activation+0.000
Top resid features:
your
Token your
Feature activation-0.004
Top resid features:
weapons
Token weapons
Feature activation-0.017
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Currently
Token Currently
Feature activation+0.017
Top resid features:
it
Token it
Feature activation-0.062
Top resid features:
shares
Token shares
Feature activation+4.815
Top resid features:
the
Token the
Feature activation-0.210
Top resid features:
same
Token same
Feature activation-0.125
Top resid features:
slot
Token slot
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
colour
Token colour
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.001
Top resid features:
wrongdoing
Token wrongdoing
Feature activation-0.043
Top resid features:
following
Token following
Feature activation+0.030
Top resid features:
allegations
Token allegations
Feature activation-0.176
Top resid features:
he
Token he
Feature activation-0.004
Top resid features:
shared
Token shared
Feature activation+4.483
Top resid features:
private
Token private
Feature activation-0.020
Top resid features:
information
Token information
Feature activation+0.000
Top resid features:
without
Token without
Feature activation+0.000
Top resid features:
consent
Token consent
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
forward
Token forward
Feature activation-0.010
Top resid features:
Brandon
Token Brandon
Feature activation+0.003
Top resid features:
Ingram
Token Ingram
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
Ingram
Token Ingram
Feature activation-0.024
Top resid features:
shares
Token shares
Feature activation+4.728
Top resid features:
a
Token a
Feature activation-0.311
Top resid features:
draft
Token draft
Feature activation-0.043
Top resid features:
position
Token position
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Ball
Token Ball
Feature activation+0.000
Top resid features:
packing
Token packing
Feature activation-0.020
Top resid features:
an
Token an
Feature activation-0.040
Top resid features:
assault
Token assault
Feature activation-0.013
Top resid features:
rifle
Token rifle
Feature activation-0.024
Top resid features:
,
Token,
Feature activation-0.042
Top resid features:
shares
Token shares
Feature activation+4.581
Top resid features:
a
Token a
Feature activation-0.154
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
f
Tokenf
Feature activation+0.000
Top resid features:
ist
Tokenist
Feature activation+0.000
Top resid features:
bump
Token bump
Feature activation+0.000
Top resid features:
ous
Tokenous
Feature activation+0.009
Top resid features:
af
Tokenaf
Feature activation+0.011
Top resid features:
zai
Tokenzai
Feature activation-0.001
Top resid features:
went
Token went
Feature activation-0.076
Top resid features:
on
Token on
Feature activation+0.023
Top resid features:
share
Token share
Feature activation+4.696
Top resid features:
the
Token the
Feature activation-0.266
Top resid features:
Nobel
Token Nobel
Feature activation+0.000
Top resid features:
Peace
Token Peace
Feature activation+0.000
Top resid features:
Prize
Token Prize
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
now
Token now
Feature activation+0.001
Top resid features:
!)
Token!)
Feature activation-0.010
Top resid features:
but
Token but
Feature activation+0.015
Top resid features:
she
Token she
Feature activation-0.004
Top resid features:
has
Token has
Feature activation+0.034
Top resid features:
shared
Token shared
Feature activation+4.203
Top resid features:
a
Token a
Feature activation+0.035
Top resid features:
few
Token few
Feature activation+0.131
Top resid features:
of
Token of
Feature activation-0.170
Top resid features:
her
Token her
Feature activation-0.056
Top resid features:
winning
Token winning
Feature activation+0.000
Top resid features:
created
Token created
Feature activation-0.013
Top resid features:
is
Token is
Feature activation-0.028
Top resid features:
as
Token as
Feature activation-0.003
Top resid features:
easy
Token easy
Feature activation-0.021
Top resid features:
as
Token as
Feature activation-0.095
Top resid features:
sharing
Token sharing
Feature activation+4.608
Top resid features:
a
Token a
Feature activation-0.127
Top resid features:
URL
Token URL
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
at
Token at
Feature activation-0.017
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
SAP
Token SAP
Feature activation+0.002
Top resid features:
Center
Token Center
Feature activation-0.013
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
sharing
Token sharing
Feature activation+4.446
Top resid features:
the
Token the
Feature activation-0.254
Top resid features:
same
Token same
Feature activation+0.000
Top resid features:
arena
Token arena
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
forward
Token forward
Feature activation-0.001
Top resid features:
Brandon
Token Brandon
Feature activation+0.003
Top resid features:
Ingram
Token Ingram
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.062
Top resid features:
Ingram
Token Ingram
Feature activation-0.050
Top resid features:
shares
Token shares
Feature activation+4.480
Top resid features:
a
Token a
Feature activation-0.159
Top resid features:
draft
Token draft
Feature activation+0.000
Top resid features:
position
Token position
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Ball
Token Ball
Feature activation+0.000
Top resid features:
performance
Token performance
Feature activation+0.012
Top resid features:
for
Token for
Feature activation+0.001
Top resid features:
free
Token free
Feature activation-0.019
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
or
Token or
Feature activation-0.017
Top resid features:
sharing
Token sharing
Feature activation+4.425
Top resid features:
the
Token the
Feature activation-0.258
Top resid features:
work
Token work
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
've
Token've
Feature activation+0.000
Top resid features:
done
Token done
Feature activation+0.000
Top resid features:
ist
Tokenist
Feature activation-0.002
Top resid features:
fraternity
Token fraternity
Feature activation-0.010
Top resid features:
between
Token between
Feature activation+0.021
Top resid features:
Anarch
Token Anarch
Feature activation-0.027
Top resid features:
ists
Tokenists
Feature activation-0.017
Top resid features:
sharing
Token sharing
Feature activation+4.346
Top resid features:
the
Token the
Feature activation+0.050
Top resid features:
same
Token same
Feature activation-0.088
Top resid features:
basic
Token basic
Feature activation-0.017
Top resid features:
tendencies
Token tendencies
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.50

Head 1: 0.04

Head 2: 0.02

Head 3: 0.04

Head 4: 0.02

Head 5: 0.04

Head 6: 0.04

Head 7: 0.09

Head 8: 0.02

Head 9: 0.05

Head 10: 0.02

Head 11: 0.11

Positive logits

edin1.48

redits1.34

Tokens1.24

certs1.20

PsyNetMessage1.20

secrets1.17

coins1.16

details1.14

iguous1.13

ournals1.12

statically1.12

CentOS1.12

onyms1.11

ourses1.11

shared1.10

coordinates1.10

peacefully1.09

links1.09

ourced1.09

eas1.09

Negative logits

��-1.52

paio-1.33

reckoning-1.30

-1.24

secretary-1.22

ramp-1.17

practition-1.14

iff-1.14

brig-1.14

IFF-1.13

icer-1.12

antom-1.12

iller-1.12

barr-1.12

-1.11

PUT-1.11

pione-1.11

CHECK-1.11

wagen-1.10

��-1.10

INTERVAL 3.606 - 4.007
CONTAINS 0.001%

pregnancy
Token pregnancy
Feature activation+0.000
.[
Token.[
Feature activation+0.000
8
Token8
Feature activation+0.000
])
Token])
Feature activation+0.000
Sharing
Token Sharing
Feature activation+0.752
time
Token time
Feature activation+3.766
together
Token together
Feature activation+2.588
and
Token and
Feature activation+0.674
finding
Token finding
Feature activation+1.353
common
Token common
Feature activation+0.000
interests
Token interests
Feature activation+0.000
up
Token up
Feature activation+0.000
sharing
Token sharing
Feature activation+0.515
the
Token the
Feature activation+3.224
bot
Token bot
Feature activation+0.221
lane
Tokenlane
Feature activation+1.128
with
Token with
Feature activation+3.666
two
Token two
Feature activation+0.000
different
Token different
Feature activation+0.000
supports
Token supports
Feature activation+0.000
:
Token:
Feature activation+0.000
Ale
Token Ale
Feature activation+0.000
state
Token state
Feature activation+0.000
party
Token party
Feature activation+0.000
shares
Token shares
Feature activation+1.431
these
Token these
Feature activation+2.550
receipts
Token receipts
Feature activation+2.856
with
Token with
Feature activation+3.620
such
Token such
Feature activation+0.000
groups
Token groups
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
Hamilton
Token Hamilton
Feature activation+0.000
test
Token test
Feature activation+0.000
and
Token and
Feature activation+0.000
share
Token share
Feature activation+0.232
simple
Token simple
Feature activation+2.221
or
Token or
Feature activation+0.000
complex
Token complex
Feature activation+4.007
interactions
Token interactions
Feature activation+2.443
with
Token with
Feature activation+1.362
a
Token a
Feature activation+0.000
design
Token design
Feature activation+0.000
team
Token team
Feature activation+0.000

INTERVAL 3.206 - 3.606
CONTAINS 0.002%

fast
Token fast
Feature activation+0.000
access
Token access
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Share
TokenShare
Feature activation+0.000
a
Token a
Feature activation+3.210
Video
Token Video
Feature activation+1.540
/
Token/
Feature activation+0.567
Photo
TokenPhoto
Feature activation+0.175
from
Token from
Feature activation+2.565
Gallery
Token Gallery
Feature activation+0.000
wrongdoing
Token wrongdoing
Feature activation+0.000
following
Token following
Feature activation+0.000
allegations
Token allegations
Feature activation+0.000
he
Token he
Feature activation+0.000
shared
Token shared
Feature activation+0.199
private
Token private
Feature activation+3.416
information
Token information
Feature activation+2.431
without
Token without
Feature activation+1.862
consent
Token consent
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
shares
Token shares
Feature activation+0.506
his
Token his
Feature activation+2.345
short
Token short
Feature activation+2.700
list
Token list
Feature activation+3.224
of
Token of
Feature activation+0.901
the
Token the
Feature activation+0.000
compet
Token compet
Feature activation+0.000
encies
Tokenencies
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
Currently
Token Currently
Feature activation+0.000
it
Token it
Feature activation+0.000
shares
Token shares
Feature activation+1.775
the
Token the
Feature activation+3.165
same
Token same
Feature activation+3.455
slot
Token slot
Feature activation+2.511
as
Token as
Feature activation+0.546
colour
Token colour
Feature activation+0.000
crystals
Token crystals
Feature activation+0.000
.
Token.
Feature activation+0.000
Red
Token Red
Feature activation+0.000
is
Tokenis
Feature activation+0.000
to
Token to
Feature activation+0.000
share
Token share
Feature activation+0.000
user
Token user
Feature activation+0.261
sessions
Token sessions
Feature activation+3.230
with
Token with
Feature activation+1.543
other
Token other
Feature activation+0.000
frameworks
Token frameworks
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000

INTERVAL 2.805 - 3.206
CONTAINS 0.004%

she
Token she
Feature activation+0.000
has
Token has
Feature activation+0.000
never
Token never
Feature activation+0.000
shared
Token shared
Feature activation+0.280
water
Token water
Feature activation+2.634
with
Token with
Feature activation+3.004
a
Token a
Feature activation+0.000
male
Token male
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
-
Token-
Feature activation+0.000
formed
Tokenformed
Feature activation+0.000
PAC
Token PAC
Feature activation+0.000
shares
Token shares
Feature activation+0.000
an
Token an
Feature activation+3.156
address
Token address
Feature activation+2.780
and
Token and
Feature activation+0.128
chief
Token chief
Feature activation+0.000
financial
Token financial
Feature activation+0.000
officer
Token officer
Feature activation+0.000
,
Token,
Feature activation+0.000
Ben
Token Ben
Feature activation+0.000
io
Tokenio
Feature activation+0.000
ff
Tokenff
Feature activation+0.000
shared
Token shared
Feature activation+0.000
a
Token a
Feature activation+2.808
video
Token video
Feature activation+1.389
of
Token of
Feature activation+0.644
a
Token a
Feature activation+0.000
mountain
Token mountain
Feature activation+0.000
lion
Token lion
Feature activation+0.000
mountainous
Token mountainous
Feature activation+0.000
province
Token province
Feature activation+0.000
that
Token that
Feature activation+0.000
shares
Token shares
Feature activation+0.768
a
Token a
Feature activation+2.687
long
Token long
Feature activation+3.194
and
Token and
Feature activation+0.000
porous
Token porous
Feature activation+2.516
border
Token border
Feature activation+2.619
with
Token with
Feature activation+1.452
law
Token law
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
.
Token.
Feature activation+0.000
Currently
Token Currently
Feature activation+0.000
it
Token it
Feature activation+0.000
shares
Token shares
Feature activation+1.775
the
Token the
Feature activation+3.165
same
Token same
Feature activation+3.455
slot
Token slot
Feature activation+2.511
as
Token as
Feature activation+0.546
colour
Token colour
Feature activation+0.000
crystals
Token crystals
Feature activation+0.000

INTERVAL 2.404 - 2.805
CONTAINS 0.005%

won
Token won
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
share
Token share
Feature activation+0.000
them
Token them
Feature activation+2.464
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Ingram
Token Ingram
Feature activation+0.000
shares
Token shares
Feature activation+0.850
a
Token a
Feature activation+3.306
draft
Token draft
Feature activation+3.415
position
Token position
Feature activation+3.156
with
Token with
Feature activation+2.659
Ball
Token Ball
Feature activation+0.000
,
Token,
Feature activation+0.000
being
Token being
Feature activation+0.000
selected
Token selected
Feature activation+0.000
second
Token second
Feature activation+0.000
sure
Token sure
Feature activation+0.000
to
Token to
Feature activation+0.000
share
Token share
Feature activation+0.313
your
Token your
Feature activation+2.654
finds
Token finds
Feature activation+1.333
with
Token with
Feature activation+2.786
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+0.000
information
Token information
Feature activation+0.000
immigrants
Token immigrants
Feature activation+0.000
who
Token who
Feature activation+0.000
"
Token "
Feature activation+0.000
share
Tokenshare
Feature activation+0.037
our
Token our
Feature activation+2.848
values
Token values
Feature activation+2.767
"
Token"
Feature activation+0.739
and
Token and
Feature activation+0.072
"
Token "
Feature activation+0.000
love
Tokenlove
Feature activation+1.005
our
Token our
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
has
Token has
Feature activation+0.000
never
Token never
Feature activation+0.000
shared
Token shared
Feature activation+0.280
water
Token water
Feature activation+2.634
with
Token with
Feature activation+3.004
a
Token a
Feature activation+0.000
male
Token male
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.004 - 2.404
CONTAINS 0.004%

I
Token I
Feature activation+0.000
wouldn
Token wouldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
share
Token share
Feature activation+2.069
that
Token that
Feature activation+0.367
,
Token,
Feature activation+0.230
but
Token but
Feature activation+0.000
can
Token can
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
dance
Token dance
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
share
Token share
Feature activation+0.179
enlight
Token enlight
Feature activation+0.000
ening
Tokenening
Feature activation+2.341
conversation
Token conversation
Feature activation+2.243
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
oman
Tokenoman
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
to
Token to
Feature activation+0.000
share
Token share
Feature activation+0.000
his
Token his
Feature activation+1.917
body
Token body
Feature activation+2.189
with
Token with
Feature activation+1.307
anyone
Token anyone
Feature activation+0.000
else
Token else
Feature activation+0.000
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.000
and
Token and
Feature activation+0.000
plan
Token plan
Feature activation+0.000
to
Token to
Feature activation+0.000
share
Token share
Feature activation+0.367
this
Token this
Feature activation+2.903
experience
Token experience
Feature activation+2.402
with
Token with
Feature activation+2.068
the
Token the
Feature activation+0.000
rest
Token rest
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
at
Token at
Feature activation+0.000
Civil
Token Civil
Feature activation+0.000
Maps
Token Maps
Feature activation+0.000
is
Token is
Feature activation+0.000
sharing
Token sharing
Feature activation+0.014
footage
Token footage
Feature activation+2.135
of
Token of
Feature activation+1.834
a
Token a
Feature activation+0.000
recent
Token recent
Feature activation+0.000
localization
Token localization
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.603 - 2.004
CONTAINS 0.005%

yet
Token yet
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
share
Token share
Feature activation+0.550
the
Token the
Feature activation+2.342
awesome
Token awesome
Feature activation+1.656
experience
Token experience
Feature activation+0.459
of
Token of
Feature activation+0.467
Prec
Token Prec
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
with
Token with
Feature activation+0.737
share
Token share
Feature activation+0.218
their
Token their
Feature activation+1.712
sacred
Token sacred
Feature activation+2.862
experiences
Token experiences
Feature activation+1.129
cautiously
Token cautiously
Feature activation+1.138
with
Token with
Feature activation+1.815
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
will
Token will
Feature activation+0.000
not
Token not
Feature activation+0.000
mock
Token mock
Feature activation+0.000
Civil
Token Civil
Feature activation+0.000
Maps
Token Maps
Feature activation+0.000
is
Token is
Feature activation+0.000
sharing
Token sharing
Feature activation+0.014
footage
Token footage
Feature activation+2.135
of
Token of
Feature activation+1.834
a
Token a
Feature activation+0.000
recent
Token recent
Feature activation+0.000
localization
Token localization
Feature activation+0.000
and
Token and
Feature activation+0.000
map
Token map
Feature activation+0.000
Artist
Token Artist
Feature activation+0.000
Awards
Token Awards
Feature activation+0.000
which
Token which
Feature activation+0.000
he
Token he
Feature activation+0.000
shared
Token shared
Feature activation+0.220
with
Token with
Feature activation+1.940
Jake
Token Jake
Feature activation+0.000
Sim
Token Sim
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000
technology
Token technology
Feature activation+0.000
or
Token or
Feature activation+0.000
knowledge
Token knowledge
Feature activation+0.000
was
Token was
Feature activation+0.000
ever
Token ever
Feature activation+0.000
shared
Token shared
Feature activation+1.990
as
Token as
Feature activation+1.299
freely
Token freely
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.005
as
Token as
Feature activation+0.000

INTERVAL 1.202 - 1.603
CONTAINS 0.005%

him
Token him
Feature activation+0.000
defeated
Token defeated
Feature activation+0.000
were
Token were
Feature activation+0.000
presumably
Token presumably
Feature activation+0.000
not
Token not
Feature activation+0.000
shared
Token shared
Feature activation+1.435
by
Token by
Feature activation+0.294
Lam
Token Lam
Feature activation+0.000
my
Tokenmy
Feature activation+0.000
in
Token in
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
stop
Token stop
Feature activation+0.000
college
Token college
Feature activation+0.000
guys
Token guys
Feature activation+0.000
from
Token from
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
links
Token links
Feature activation+1.570
from
Token from
Feature activation+0.336
Bro
Token Bro
Feature activation+0.000
B
TokenB
Feature activation+0.000
ible
Tokenible
Feature activation+0.000
and
Token and
Feature activation+0.000
em
Token em
Feature activation+0.000
powers
Tokenpowers
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
share
Token share
Feature activation+0.508
reviews
Token reviews
Feature activation+1.370
and
Token and
Feature activation+2.074
content
Token content
Feature activation+2.084
about
Token about
Feature activation+0.865
your
Token your
Feature activation+0.000
product
Token product
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
to
Token to
Feature activation+0.000
share
Token share
Feature activation+0.000
his
Token his
Feature activation+1.917
body
Token body
Feature activation+2.189
with
Token with
Feature activation+1.307
anyone
Token anyone
Feature activation+0.000
else
Token else
Feature activation+0.000
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.000
.
Token.
Feature activation+0.000
Ben
Token Ben
Feature activation+0.000
io
Tokenio
Feature activation+0.000
ff
Tokenff
Feature activation+0.000
shared
Token shared
Feature activation+0.000
a
Token a
Feature activation+2.808
video
Token video
Feature activation+1.389
of
Token of
Feature activation+0.644
a
Token a
Feature activation+0.000
mountain
Token mountain
Feature activation+0.000
lion
Token lion
Feature activation+0.000
walking
Token walking
Feature activation+0.000

INTERVAL 0.801 - 1.202
CONTAINS 0.005%

shared
Token shared
Feature activation+0.000
a
Token a
Feature activation+2.325
moment
Token moment
Feature activation+2.317
and
Token and
Feature activation+0.000
a
Token a
Feature activation+3.053
hug
Token hug
Feature activation+0.850
on
Token on
Feature activation+0.000
stage
Token stage
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
billion
Tokenbillion
Feature activation+0.000
-
Token-
Feature activation+0.000
euro
Tokeneuro
Feature activation+0.000
cost
Token cost
Feature activation+0.000
is
Token is
Feature activation+0.000
shared
Token shared
Feature activation+0.842
25
Token 25
Feature activation+0.000
-
Token-
Feature activation+0.000
75
Token75
Feature activation+0.000
%
Token%
Feature activation+0.850
by
Token by
Feature activation+0.217
ade
Tokenade
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
shared
Token shared
Feature activation+0.000
their
Token their
Feature activation+1.327
glowing
Token glowing
Feature activation+0.896
thoughts
Token thoughts
Feature activation+0.000
on
Token on
Feature activation+0.000
social
Token social
Feature activation+0.000
media
Token media
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
share
Token share
Feature activation+0.218
their
Token their
Feature activation+1.712
sacred
Token sacred
Feature activation+2.862
experiences
Token experiences
Feature activation+1.129
cautiously
Token cautiously
Feature activation+1.138
with
Token with
Feature activation+1.815
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
will
Token will
Feature activation+0.000
not
Token not
Feature activation+0.000
own
Token own
Feature activation+0.000
player
Token player
Feature activation+0.000
skins
Token skins
Feature activation+0.000
to
Token to
Feature activation+0.000
share
Token share
Feature activation+0.505
with
Token with
Feature activation+0.808
others
Token others
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000

INTERVAL 0.401 - 0.801
CONTAINS 0.008%

share
Token share
Feature activation+0.000
your
Token your
Feature activation+1.384
Fan
Token Fan
Feature activation+0.000
The
Token The
Feature activation+0.000
ories
Tokenories
Feature activation+1.356
,
Token,
Feature activation+0.484
or
Token or
Feature activation+0.000
email
Token email
Feature activation+0.000
any
Token any
Feature activation+0.000
Fan
Token Fan
Feature activation+0.000
The
Token The
Feature activation+0.000
plays
Token plays
Feature activation+0.000
in
Token in
Feature activation+0.000
excellence
Token excellence
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
shares
Token shares
Feature activation+0.506
his
Token his
Feature activation+2.345
short
Token short
Feature activation+2.700
list
Token list
Feature activation+3.224
of
Token of
Feature activation+0.901
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Share
TokenShare
Feature activation+0.000
Have
Token Have
Feature activation+0.000
a
Token a
Feature activation+0.000
tip
Token tip
Feature activation+0.477
for
Token for
Feature activation+0.000
us
Token us
Feature activation+0.000
?
Token?
Feature activation+0.000
Awesome
Token Awesome
Feature activation+0.000
!
Token!
Feature activation+0.000
that
Token that
Feature activation+0.000
tourist
Token tourist
Feature activation+0.000
cities
Token cities
Feature activation+0.000
have
Token have
Feature activation+0.000
in
Token in
Feature activation+0.000
common
Token common
Feature activation+0.443
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
iconic
Token iconic
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
we
Token we
Feature activation+0.000
ought
Token ought
Feature activation+0.000
to
Token to
Feature activation+0.000
share
Token share
Feature activation+0.496
it
Token it
Feature activation+2.210
with
Token with
Feature activation+2.085
the
Token the
Feature activation+0.000
public
Token public
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.401
CONTAINS 99.961%

only
Token only
Feature activation+0.000
negative
Token negative
Feature activation+0.000
rested
Token rested
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
tax
Token tax
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
levy
Token levy
Feature activation+0.000
on
Token on
Feature activation+0.000
just
Token just
Feature activation+0.000
one
Token one
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
MSNBC
Token MSNBC
Feature activation+0.000
show
Token show
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
11
Token 11
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Hour
Token Hour
Feature activation+0.000
,
Token,
Feature activation+0.000
sub
Token sub
Feature activation+0.000
par
Tokenpar
Feature activation+0.000
record
Token record
Feature activation+0.000
).
Token).
Feature activation+0.000
Here
Token Here
Feature activation+0.000
are
Token are
Feature activation+0.000
three
Token three
Feature activation+0.000
needs
Token needs
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
greeted
Token greeted
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
simple
Token simple
Feature activation+0.000
op
Token op
Feature activation+0.000
ulence
Tokenulence
Feature activation+0.000
of
Token of
Feature activation+0.000
natural
Token natural
Feature activation+0.000
light
Token light
Feature activation+0.000
and
Token and
Feature activation+0.000
material
Token material
Feature activation+0.000
Link
TokenLink
Feature activation+0.000
z
Tokenz
Feature activation+0.000
Link
Token Link
Feature activation+0.000
-
Token-
Feature activation+0.000
up
Tokenup
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Enjoy
TokenEnjoy
Feature activation+0.000
&
Token &
Feature activation+0.000
until
Token until
Feature activation+0.000
next
Token next
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 H4.0: (feature 12154)

TOP ACTIVATIONS
MAX = 4.025

taken
Token taken
Feature activation+0.000
tens
Token tens
Feature activation+0.873
of
Token of
Feature activation+1.911
thousands
Token thousands
Feature activation+3.485
of
Token of
Feature activation+3.503
dollars
Token dollars
Feature activation+4.025
in
Token in
Feature activation+3.571
free
Token free
Feature activation+1.121
bies
Tokenbies
Feature activation+0.127
-
Token -
Feature activation+0.000
more
Token more
Feature activation+0.000
taken
Token taken
Feature activation+0.000
$
Token $
Feature activation+2.462
15
Token15
Feature activation+2.868
.
Token.
Feature activation+0.338
51
Token51
Feature activation+0.635
million
Token million
Feature activation+3.916
(
Token (
Feature activation+0.398
94
Token94
Feature activation+0.000
.
Token.
Feature activation+0.000
02
Token02
Feature activation+0.000
million
Token million
Feature activation+0.040
take
Token take
Feature activation+0.000
a
Token a
Feature activation+1.471
great
Token great
Feature activation+3.115
deal
Token deal
Feature activation+3.766
of
Token of
Feature activation+3.838
time
Token time
Feature activation+3.860
to
Token to
Feature activation+3.208
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
conclusion
Token conclusion
Feature activation+0.000
may
Token may
Feature activation+0.000
take
Token take
Feature activation+0.000
a
Token a
Feature activation+1.471
great
Token great
Feature activation+3.115
deal
Token deal
Feature activation+3.766
of
Token of
Feature activation+3.838
time
Token time
Feature activation+3.860
to
Token to
Feature activation+3.208
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
TO
Token TO
Feature activation+0.000
TA
Token TA
Feature activation+0.000
KE
TokenKE
Feature activation+0.000
A
Token A
Feature activation+1.797
LOT
Token LOT
Feature activation+3.108
OF
Token OF
Feature activation+3.817
THEIR
Token THEIR
Feature activation+2.478
ATT
Token ATT
Feature activation+3.221
ENTION
TokenENTION
Feature activation+3.721
OVER
Token OVER
Feature activation+1.058
THE
Token THE
Feature activation+0.000
amon
Tokenamon
Feature activation+0.000
may
Token may
Feature activation+0.000
take
Token take
Feature activation+0.000
a
Token a
Feature activation+1.471
great
Token great
Feature activation+3.115
deal
Token deal
Feature activation+3.766
of
Token of
Feature activation+3.838
time
Token time
Feature activation+3.860
to
Token to
Feature activation+3.208
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
A
Token A
Feature activation+1.797
LOT
Token LOT
Feature activation+3.108
OF
Token OF
Feature activation+3.817
THEIR
Token THEIR
Feature activation+2.478
ATT
Token ATT
Feature activation+3.221
ENTION
TokenENTION
Feature activation+3.721
OVER
Token OVER
Feature activation+1.058
THE
Token THE
Feature activation+0.000
NEXT
Token NEXT
Feature activation+0.000
WEEK
Token WEEK
Feature activation+0.000
OR
Token OR
Feature activation+0.000
I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000
take
Token take
Feature activation+0.000
an
Token an
Feature activation+2.014
idiosyncr
Token idiosyncr
Feature activation+1.549
atic
Tokenatic
Feature activation+3.706
look
Token look
Feature activation+0.197
at
Token at
Feature activation+0.000
mathematical
Token mathematical
Feature activation+0.000
aspects
Token aspects
Feature activation+0.000
of
Token of
Feature activation+0.000
took
Token took
Feature activation+0.000
a
Token a
Feature activation+1.142
lot
Token lot
Feature activation+2.505
of
Token of
Feature activation+3.167
their
Token their
Feature activation+2.793
own
Token own
Feature activation+3.660
notes
Token notes
Feature activation+1.098
in
Token in
Feature activation+0.397
addition
Token addition
Feature activation+0.000
to
Token to
Feature activation+0.000
handing
Token handing
Feature activation+0.000
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
take
Token take
Feature activation+0.000
a
Token a
Feature activation+1.578
lot
Token lot
Feature activation+2.704
of
Token of
Feature activation+3.656
risks
Token risks
Feature activation+0.018
and
Token and
Feature activation+0.099
we
Token we
Feature activation+0.000
try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
taken
Token taken
Feature activation+0.000
any
Token any
Feature activation+2.389
other
Token other
Feature activation+3.077
concrete
Token concrete
Feature activation+3.632
steps
Token steps
Feature activation+0.295
that
Token that
Feature activation+0.836
might
Token might
Feature activation+0.070
indicate
Token indicate
Feature activation+0.000
a
Token a
Feature activation+0.000
tens
Token tens
Feature activation+0.873
of
Token of
Feature activation+1.911
thousands
Token thousands
Feature activation+3.485
of
Token of
Feature activation+3.503
dollars
Token dollars
Feature activation+4.025
in
Token in
Feature activation+3.571
free
Token free
Feature activation+1.121
bies
Tokenbies
Feature activation+0.127
-
Token -
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
take
Token take
Feature activation+0.000
all
Token all
Feature activation+0.093
the
Token the
Feature activation+1.414
energy
Token energy
Feature activation+3.570
out
Token out
Feature activation+0.113
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
air
Token air
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
must
Token must
Feature activation+0.000
take
Token take
Feature activation+0.000
remed
Token remed
Feature activation+0.000
ial
Tokenial
Feature activation+3.568
courses
Token courses
Feature activation+0.970
in
Token in
Feature activation+0.448
the
Token the
Feature activation+0.000
discipline
Token discipline
Feature activation+0.000
in
Token in
Feature activation+0.000
take
Token take
Feature activation+0.000
a
Token a
Feature activation+1.561
good
Token good
Feature activation+3.397
,
Token,
Feature activation+0.466
long
Token long
Feature activation+1.749
hard
Token hard
Feature activation+3.566
look
Token look
Feature activation+2.111
at
Token at
Feature activation+0.000
yourselves
Token yourselves
Feature activation+0.000
because
Token because
Feature activation+0.000
this
Token this
Feature activation+0.000
insurance
Token insurance
Feature activation+0.000
companies
Token companies
Feature activation+0.000
that
Token that
Feature activation+0.000
take
Token take
Feature activation+0.000
a
Token a
Feature activation+1.587
financial
Token financial
Feature activation+3.533
hit
Token hit
Feature activation+2.173
by
Token by
Feature activation+0.160
participating
Token participating
Feature activation+0.000
in
Token in
Feature activation+0.000
government
Token government
Feature activation+0.000
fantasy
Token fantasy
Feature activation+0.000
sports
Token sports
Feature activation+0.000
takes
Token takes
Feature activation+0.000
the
Token the
Feature activation+0.868
most
Token most
Feature activation+2.315
fun
Token fun
Feature activation+3.532
part
Token part
Feature activation+2.188
of
Token of
Feature activation+2.358
fantasy
Token fantasy
Feature activation+0.000
sports
Token sports
Feature activation+0.000
-
Token -
Feature activation+0.185
-
Token-
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
-
Token-
Feature activation+0.000
she
Tokenshe
Feature activation+0.000
lf
Tokenlf
Feature activation+0.000
routine
Token routine
Feature activation+3.509
and
Token and
Feature activation+0.599
just
Token just
Feature activation+0.000
compile
Token compile
Feature activation+0.000
it
Token it
Feature activation+0.000
for
Token for
Feature activation+0.000
has
Token has
Feature activation+0.000
taken
Token taken
Feature activation+0.000
tens
Token tens
Feature activation+0.873
of
Token of
Feature activation+1.911
thousands
Token thousands
Feature activation+3.485
of
Token of
Feature activation+3.503
dollars
Token dollars
Feature activation+4.025
in
Token in
Feature activation+3.571
free
Token free
Feature activation+1.121
bies
Tokenbies
Feature activation+0.127
-
Token -
Feature activation+0.000
take
Token take
Feature activation+0.000
an
Token an
Feature activation+1.095
average
Token average
Feature activation+2.081
of
Token of
Feature activation+3.183
25
Token 25
Feature activation+3.284
years
Token years
Feature activation+3.486
to
Token to
Feature activation+2.987
decom
Token decom
Feature activation+0.000
pose
Tokenpose
Feature activation+0.000
.(
Token.(
Feature activation+0.000
7
Token7
Feature activation+0.000

Top DFA by src position
MAX = 5.102

in
Token in
Feature activation+0.014
Top resid features:
government
Token government
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.024
Top resid features:
Kaine
Token Kaine
Feature activation+0.016
Top resid features:
has
Token has
Feature activation-0.088
Top resid features:
taken
Token taken
Feature activation+5.102
Top resid features:
tens
Token tens
Feature activation+0.020
Top resid features:
of
Token of
Feature activation+0.030
Top resid features:
thousands
Token thousands
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.191
Top resid features:
dollars
Token dollars
Feature activation-0.104
Top resid features:
Yun
Token Yun
Feature activation+0.005
Top resid features:
-
Token-
Feature activation-0.005
Top resid features:
fat
Tokenfat
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
has
Token has
Feature activation-0.051
Top resid features:
taken
Token taken
Feature activation+4.581
Top resid features:
$
Token $
Feature activation+0.301
Top resid features:
15
Token15
Feature activation+0.052
Top resid features:
.
Token.
Feature activation+0.099
Top resid features:
51
Token51
Feature activation+0.407
Top resid features:
million
Token million
Feature activation-0.288
Top resid features:
that
Token that
Feature activation-0.002
Top resid features:
while
Token while
Feature activation-0.033
Top resid features:
Car
Token Car
Feature activation+0.000
Top resid features:
amon
Tokenamon
Feature activation+0.004
Top resid features:
may
Token may
Feature activation-0.021
Top resid features:
take
Token take
Feature activation+4.410
Top resid features:
a
Token a
Feature activation+0.066
Top resid features:
great
Token great
Feature activation+0.155
Top resid features:
deal
Token deal
Feature activation+0.024
Top resid features:
of
Token of
Feature activation+0.356
Top resid features:
time
Token time
Feature activation+0.161
Top resid features:
that
Token that
Feature activation-0.005
Top resid features:
while
Token while
Feature activation-0.034
Top resid features:
Car
Token Car
Feature activation+0.001
Top resid features:
amon
Tokenamon
Feature activation+0.004
Top resid features:
may
Token may
Feature activation-0.037
Top resid features:
take
Token take
Feature activation+4.313
Top resid features:
a
Token a
Feature activation+0.052
Top resid features:
great
Token great
Feature activation+0.256
Top resid features:
deal
Token deal
Feature activation+0.595
Top resid features:
of
Token of
Feature activation-0.047
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
Y
TokenY
Feature activation-0.009
Top resid features:
GO
Token GO
Feature activation-0.008
Top resid features:
ING
TokenING
Feature activation-0.015
Top resid features:
TO
Token TO
Feature activation+0.027
Top resid features:
TA
Token TA
Feature activation+0.028
Top resid features:
KE
TokenKE
Feature activation+4.630
Top resid features:
A
Token A
Feature activation+0.059
Top resid features:
LOT
Token LOT
Feature activation+0.568
Top resid features:
OF
Token OF
Feature activation-0.269
Top resid features:
THEIR
Token THEIR
Feature activation+0.000
Top resid features:
ATT
Token ATT
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
while
Token while
Feature activation-0.017
Top resid features:
Car
Token Car
Feature activation+0.003
Top resid features:
amon
Tokenamon
Feature activation+0.002
Top resid features:
may
Token may
Feature activation-0.046
Top resid features:
take
Token take
Feature activation+4.593
Top resid features:
a
Token a
Feature activation+0.042
Top resid features:
great
Token great
Feature activation+0.612
Top resid features:
deal
Token deal
Feature activation-0.218
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
Y
TokenY
Feature activation-0.007
Top resid features:
GO
Token GO
Feature activation-0.013
Top resid features:
ING
TokenING
Feature activation+0.001
Top resid features:
TO
Token TO
Feature activation+0.002
Top resid features:
TA
Token TA
Feature activation+0.019
Top resid features:
KE
TokenKE
Feature activation+4.452
Top resid features:
A
Token A
Feature activation+0.099
Top resid features:
LOT
Token LOT
Feature activation+0.029
Top resid features:
OF
Token OF
Feature activation-0.003
Top resid features:
THEIR
Token THEIR
Feature activation+0.184
Top resid features:
ATT
Token ATT
Feature activation+0.262
Top resid features:
Mathematics
Token Mathematics
Feature activation-0.014
Top resid features:
Awareness
Token Awareness
Feature activation+0.019
Top resid features:
Month
Token Month
Feature activation+0.039
Top resid features:
I
Token I
Feature activation-0.009
Top resid features:
will
Token will
Feature activation+0.008
Top resid features:
take
Token take
Feature activation+4.130
Top resid features:
an
Token an
Feature activation+0.104
Top resid features:
idiosyncr
Token idiosyncr
Feature activation+0.567
Top resid features:
atic
Tokenatic
Feature activation+0.005
Top resid features:
look
Token look
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
outgoing
Token outgoing
Feature activation+0.002
Top resid features:
commander
Token commander
Feature activation+0.001
Top resid features:
says
Token says
Feature activation-0.038
Top resid features:
his
Token his
Feature activation-0.002
Top resid features:
soldiers
Token soldiers
Feature activation-0.037
Top resid features:
took
Token took
Feature activation+4.325
Top resid features:
a
Token a
Feature activation+0.052
Top resid features:
lot
Token lot
Feature activation+0.202
Top resid features:
of
Token of
Feature activation+0.068
Top resid features:
their
Token their
Feature activation+0.308
Top resid features:
own
Token own
Feature activation+0.046
Top resid features:
try
Token try
Feature activation-0.070
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
lot
Token lot
Feature activation-0.004
Top resid features:
and
Token and
Feature activation+0.055
Top resid features:
we
Token we
Feature activation+0.028
Top resid features:
take
Token take
Feature activation+4.351
Top resid features:
a
Token a
Feature activation+0.083
Top resid features:
lot
Token lot
Feature activation+0.535
Top resid features:
of
Token of
Feature activation-0.135
Top resid features:
risks
Token risks
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
not
Token not
Feature activation-0.007
Top resid features:
known
Token known
Feature activation-0.023
Top resid features:
however
Token however
Feature activation+0.016
Top resid features:
to
Token to
Feature activation-0.017
Top resid features:
have
Token have
Feature activation-0.064
Top resid features:
taken
Token taken
Feature activation+4.281
Top resid features:
any
Token any
Feature activation+0.116
Top resid features:
other
Token other
Feature activation+0.633
Top resid features:
concrete
Token concrete
Feature activation-0.089
Top resid features:
steps
Token steps
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
government
Token government
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
Kaine
Token Kaine
Feature activation-0.002
Top resid features:
has
Token has
Feature activation-0.093
Top resid features:
taken
Token taken
Feature activation+4.571
Top resid features:
tens
Token tens
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.022
Top resid features:
thousands
Token thousands
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.018
Top resid features:
dollars
Token dollars
Feature activation+0.413
Top resid features:
you
Token you
Feature activation+0.056
Top resid features:
can
Token can
Feature activation-0.013
Top resid features:
âĢ
TokenâĢ
Feature activation+0.054
Top resid features:
Ļ
TokenĻ
Feature activation+0.029
Top resid features:
t
Tokent
Feature activation-0.015
Top resid features:
take
Token take
Feature activation+4.372
Top resid features:
all
Token all
Feature activation+0.196
Top resid features:
the
Token the
Feature activation+0.120
Top resid features:
energy
Token energy
Feature activation-0.006
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.002
Top resid features:
area
Token area
Feature activation-0.013
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
they
Token they
Feature activation-0.008
Top resid features:
must
Token must
Feature activation-0.163
Top resid features:
take
Token take
Feature activation+4.529
Top resid features:
remed
Token remed
Feature activation+0.491
Top resid features:
ial
Tokenial
Feature activation+0.024
Top resid features:
courses
Token courses
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
'd
Token'd
Feature activation+0.005
Top resid features:
like
Token like
Feature activation-0.004
Top resid features:
for
Token for
Feature activation+0.009
Top resid features:
you
Token you
Feature activation+0.029
Top resid features:
to
Token to
Feature activation-0.025
Top resid features:
take
Token take
Feature activation+4.079
Top resid features:
a
Token a
Feature activation+0.071
Top resid features:
good
Token good
Feature activation+0.105
Top resid features:
,
Token,
Feature activation+0.165
Top resid features:
long
Token long
Feature activation+0.360
Top resid features:
hard
Token hard
Feature activation-0.022
Top resid features:
to
Token to
Feature activation-0.014
Top resid features:
help
Token help
Feature activation-0.024
Top resid features:
insurance
Token insurance
Feature activation-0.042
Top resid features:
companies
Token companies
Feature activation-0.010
Top resid features:
that
Token that
Feature activation+0.005
Top resid features:
take
Token take
Feature activation+4.689
Top resid features:
a
Token a
Feature activation+0.042
Top resid features:
financial
Token financial
Feature activation+0.081
Top resid features:
hit
Token hit
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
participating
Token participating
Feature activation+0.000
Top resid features:
ups
Tokenups
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
Daily
Token Daily
Feature activation+0.014
Top resid features:
fantasy
Token fantasy
Feature activation-0.005
Top resid features:
sports
Token sports
Feature activation-0.009
Top resid features:
takes
Token takes
Feature activation+4.286
Top resid features:
the
Token the
Feature activation+0.227
Top resid features:
most
Token most
Feature activation+0.429
Top resid features:
fun
Token fun
Feature activation-0.194
Top resid features:
part
Token part
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
You
Token You
Feature activation+0.010
Top resid features:
definitely
Token definitely
Feature activation-0.022
Top resid features:
can
Token can
Feature activation-0.046
Top resid features:
't
Token't
Feature activation-0.066
Top resid features:
take
Token take
Feature activation+4.202
Top resid features:
an
Token an
Feature activation+0.540
Top resid features:
off
Token off
Feature activation+0.055
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
the
Tokenthe
Feature activation-0.038
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
government
Token government
Feature activation+0.017
Top resid features:
,
Token,
Feature activation-0.021
Top resid features:
Kaine
Token Kaine
Feature activation+0.000
Top resid features:
has
Token has
Feature activation-0.099
Top resid features:
taken
Token taken
Feature activation+4.282
Top resid features:
tens
Token tens
Feature activation+0.041
Top resid features:
of
Token of
Feature activation+0.019
Top resid features:
thousands
Token thousands
Feature activation+0.518
Top resid features:
of
Token of
Feature activation-0.022
Top resid features:
dollars
Token dollars
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.027
Top resid features:
Cig
Token Cig
Feature activation+0.012
Top resid features:
arette
Tokenarette
Feature activation+0.017
Top resid features:
but
Token but
Feature activation+0.001
Top resid features:
ts
Tokents
Feature activation-0.028
Top resid features:
take
Token take
Feature activation+4.174
Top resid features:
an
Token an
Feature activation+0.054
Top resid features:
average
Token average
Feature activation+0.041
Top resid features:
of
Token of
Feature activation+0.205
Top resid features:
25
Token 25
Feature activation+0.371
Top resid features:
years
Token years
Feature activation-0.127
Top resid features:

Decoder Weights Distribution

Head 0: 0.50

Head 1: 0.04

Head 2: 0.02

Head 3: 0.04

Head 4: 0.02

Head 5: 0.05

Head 6: 0.04

Head 7: 0.10

Head 8: 0.02

Head 9: 0.06

Head 10: 0.01

Head 11: 0.10

Positive logits

seriously1.71

virginity1.42

lightly1.37

cogn1.32

reins1.24

aback1.24

offline1.22

Seriously1.22

away1.20

kindly1.19

cues1.18

precautions1.17

ABV1.14

wraps1.12

liberties1.12

stride1.10

kef1.10

overboard1.10

largeDownload1.10

hostage1.09

Negative logits

athy-1.36

ntil-1.34

anky-1.21

-+-+-1.21

coasts-1.17

Associated-1.16

appa-1.15

ceiling-1.14

ambo-1.13

ndra-1.11

wonders-1.10

ailability-1.10

inclusion-1.10

envy-1.09

osity-1.09

ambush-1.08

beginnings-1.07

uce-1.07

Stars-1.07

Compatibility-1.07

INTERVAL 3.623 - 4.025
CONTAINS 0.001%

TO
Token TO
Feature activation+0.000
TA
Token TA
Feature activation+0.000
KE
TokenKE
Feature activation+0.000
A
Token A
Feature activation+1.797
LOT
Token LOT
Feature activation+3.108
OF
Token OF
Feature activation+3.817
THEIR
Token THEIR
Feature activation+2.478
ATT
Token ATT
Feature activation+3.221
ENTION
TokenENTION
Feature activation+3.721
OVER
Token OVER
Feature activation+1.058
THE
Token THE
Feature activation+0.000
I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000
take
Token take
Feature activation+0.000
an
Token an
Feature activation+2.014
idiosyncr
Token idiosyncr
Feature activation+1.549
atic
Tokenatic
Feature activation+3.706
look
Token look
Feature activation+0.197
at
Token at
Feature activation+0.000
mathematical
Token mathematical
Feature activation+0.000
aspects
Token aspects
Feature activation+0.000
of
Token of
Feature activation+0.000
amon
Tokenamon
Feature activation+0.000
may
Token may
Feature activation+0.000
take
Token take
Feature activation+0.000
a
Token a
Feature activation+1.471
great
Token great
Feature activation+3.115
deal
Token deal
Feature activation+3.766
of
Token of
Feature activation+3.838
time
Token time
Feature activation+3.860
to
Token to
Feature activation+3.208
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
taken
Token taken
Feature activation+0.000
any
Token any
Feature activation+2.389
other
Token other
Feature activation+3.077
concrete
Token concrete
Feature activation+3.632
steps
Token steps
Feature activation+0.295
that
Token that
Feature activation+0.836
might
Token might
Feature activation+0.070
indicate
Token indicate
Feature activation+0.000
a
Token a
Feature activation+0.000
taken
Token taken
Feature activation+0.000
tens
Token tens
Feature activation+0.873
of
Token of
Feature activation+1.911
thousands
Token thousands
Feature activation+3.485
of
Token of
Feature activation+3.503
dollars
Token dollars
Feature activation+4.025
in
Token in
Feature activation+3.571
free
Token free
Feature activation+1.121
bies
Tokenbies
Feature activation+0.127
-
Token -
Feature activation+0.000
more
Token more
Feature activation+0.000

INTERVAL 3.220 - 3.623
CONTAINS 0.004%

and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.000
taken
Token taken
Feature activation+0.000
millions
Token millions
Feature activation+1.221
of
Token of
Feature activation+2.426
dollars
Token dollars
Feature activation+3.249
over
Token over
Feature activation+2.106
the
Token the
Feature activation+0.000
years
Token years
Feature activation+0.000
from
Token from
Feature activation+0.000
industry
Token industry
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
taken
Token taken
Feature activation+0.000
the
Token the
Feature activation+1.439
three
Token three
Feature activation+1.806
languages
Token languages
Feature activation+3.357
and
Token and
Feature activation+1.949
combined
Token combined
Feature activation+0.000
them
Token them
Feature activation+0.000
into
Token into
Feature activation+0.000
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
-
Token-
Feature activation+0.000
she
Tokenshe
Feature activation+0.000
lf
Tokenlf
Feature activation+0.000
routine
Token routine
Feature activation+3.509
and
Token and
Feature activation+0.599
just
Token just
Feature activation+0.000
compile
Token compile
Feature activation+0.000
it
Token it
Feature activation+0.000
for
Token for
Feature activation+0.000
had
Token had
Feature activation+0.000
taken
Token taken
Feature activation+0.000
the
Token the
Feature activation+1.854
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
right
Tokenright
Feature activation+3.304
decisions
Token decisions
Feature activation+1.951
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
on
Token on
Feature activation+1.784
the
Token the
Feature activation+0.000
heart
Token heart
Feature activation+0.000
-
Token-
Feature activation+0.000
mel
Tokenmel
Feature activation+0.000
ting
Tokenting
Feature activation+1.454
qu
Token qu
Feature activation+0.040
ips
Tokenips
Feature activation+3.342
and
Token and
Feature activation+0.952
smile
Token smile
Feature activation+0.000
for
Token for
Feature activation+1.562
soft
Token soft
Feature activation+0.000
ness
Tokenness
Feature activation+0.000

INTERVAL 2.818 - 3.220
CONTAINS 0.008%

that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
taking
Token taking
Feature activation+0.000
the
Token the
Feature activation+0.000
tech
Token tech
Feature activation+1.278
world
Token world
Feature activation+2.935
by
Token by
Feature activation+1.994
storm
Token storm
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.000
but
Token but
Feature activation+0.000
ts
Tokents
Feature activation+0.000
take
Token take
Feature activation+0.000
an
Token an
Feature activation+1.095
average
Token average
Feature activation+2.081
of
Token of
Feature activation+3.183
25
Token 25
Feature activation+3.284
years
Token years
Feature activation+3.486
to
Token to
Feature activation+2.987
decom
Token decom
Feature activation+0.000
pose
Tokenpose
Feature activation+0.000
EU
Token EU
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
have
Token have
Feature activation+0.000
taken
Token taken
Feature activation+0.000
an
Token an
Feature activation+2.198
"
Token "
Feature activation+2.926
important
Tokenimportant
Feature activation+3.334
step
Token step
Feature activation+0.000
forward
Token forward
Feature activation+0.000
"
Token"
Feature activation+0.550
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
Take
Token Take
Feature activation+0.000
long
Token long
Feature activation+1.157
runs
Token runs
Feature activation+2.826
on
Token on
Feature activation+2.232
the
Token the
Feature activation+0.000
weekends
Token weekends
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
let
Token let
Feature activation+0.000
you
Token you
Feature activation+0.000
take
Token take
Feature activation+0.000
this
Token this
Feature activation+0.596
giant
Token giant
Feature activation+1.127
display
Token display
Feature activation+3.065
anywhere
Token anywhere
Feature activation+1.275
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
've
Token've
Feature activation+0.000
taken
Token taken
Feature activation+0.000

INTERVAL 2.415 - 2.818
CONTAINS 0.013%

says
Token says
Feature activation+0.000
his
Token his
Feature activation+0.000
soldiers
Token soldiers
Feature activation+0.000
took
Token took
Feature activation+0.000
a
Token a
Feature activation+1.142
lot
Token lot
Feature activation+2.505
of
Token of
Feature activation+3.167
their
Token their
Feature activation+2.793
own
Token own
Feature activation+3.660
notes
Token notes
Feature activation+1.098
in
Token in
Feature activation+0.397
but
Token but
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
took
Token took
Feature activation+0.000
those
Token those
Feature activation+0.842
programs
Token programs
Feature activation+2.596
away
Token away
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
take
Token take
Feature activation+0.000
a
Token a
Feature activation+2.500
cut
Token cut
Feature activation+2.048
from
Token from
Feature activation+0.421
their
Token their
Feature activation+0.000
profits
Token profits
Feature activation+0.000
.
Token.
Feature activation+0.000
0
Token0
Feature activation+0.000
and
Token and
Feature activation+0.000
took
Token took
Feature activation+0.000
roughly
Token roughly
Feature activation+1.338
three
Token three
Feature activation+3.096
days
Token days
Feature activation+2.459
to
Token to
Feature activation+1.971
fully
Token fully
Feature activation+0.000
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
print
Token print
Feature activation+0.000
The
TokenThe
Feature activation+0.000
App
Token App
Feature activation+0.000
Store
Token Store
Feature activation+0.000
took
Token took
Feature activation+0.000
a
Token a
Feature activation+1.288
little
Token little
Feature activation+2.459
under
Token under
Feature activation+2.884
two
Token two
Feature activation+2.716
and
Token and
Feature activation+0.235
half
Token half
Feature activation+2.250
years
Token years
Feature activation+2.909

INTERVAL 2.013 - 2.415
CONTAINS 0.016%

Daily
Token Daily
Feature activation+0.000
fantasy
Token fantasy
Feature activation+0.000
sports
Token sports
Feature activation+0.000
takes
Token takes
Feature activation+0.000
the
Token the
Feature activation+0.868
most
Token most
Feature activation+2.315
fun
Token fun
Feature activation+3.532
part
Token part
Feature activation+2.188
of
Token of
Feature activation+2.358
fantasy
Token fantasy
Feature activation+0.000
sports
Token sports
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
air
Token air
Feature activation+0.000
strikes
Token strikes
Feature activation+0.000
took
Token took
Feature activation+0.000
rebel
Token rebel
Feature activation+0.000
ground
Token ground
Feature activation+2.158
near
Token near
Feature activation+0.000
Aleppo
Token Aleppo
Feature activation+0.000
and
Token and
Feature activation+0.000
set
Token set
Feature activation+0.000
their
Token their
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
would
Token would
Feature activation+0.000
oppose
Token oppose
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
taking
Token taking
Feature activation+0.000
military
Token military
Feature activation+2.030
action
Token action
Feature activation+0.289
in
Token in
Feature activation+0.000
Syria
Token Syria
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
also
Token also
Feature activation+0.000
vital
Token vital
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
other
Token other
Feature activation+1.096
important
Token important
Feature activation+2.185
steps
Token steps
Feature activation+0.000
to
Token to
Feature activation+0.338
ensure
Token ensure
Feature activation+0.000
that
Token that
Feature activation+0.000
your
Token your
Feature activation+0.000
recovery
Token recovery
Feature activation+0.000
will
Token will
Feature activation+0.000
take
Token take
Feature activation+0.000
10
Token 10
Feature activation+0.753
or
Token or
Feature activation+0.000
12
Token 12
Feature activation+2.063
years
Token years
Feature activation+3.014
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.610 - 2.013
CONTAINS 0.022%

a
Token a
Feature activation+1.823
bunch
Token bunch
Feature activation+2.899
of
Token of
Feature activation+2.847
French
Token French
Feature activation+1.845
text
Token text
Feature activation+3.005
and
Token and
Feature activation+1.972
you
Token you
Feature activation+0.000
count
Token count
Feature activation+0.000
how
Token how
Feature activation+0.000
many
Token many
Feature activation+0.000
times
Token times
Feature activation+0.000
not
Token not
Feature activation+0.000
take
Token take
Feature activation+0.000
his
Token his
Feature activation+0.000
duty
Token duty
Feature activation+0.000
nor
Token nor
Feature activation+0.000
his
Token his
Feature activation+1.650
rhetoric
Token rhetoric
Feature activation+1.229
seriously
Token seriously
Feature activation+0.000
and
Token and
Feature activation+0.000
brought
Token brought
Feature activation+0.000
great
Token great
Feature activation+0.000
instruct
Token instruct
Feature activation+0.000
ing
Tokening
Feature activation+0.000
him
Token him
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
10
Token 10
Feature activation+1.762
minutes
Token minutes
Feature activation+2.215
to
Token to
Feature activation+1.960
think
Token think
Feature activation+0.000
about
Token about
Feature activation+0.000
why
Token why
Feature activation+0.000
with
Token with
Feature activation+0.000
domestic
Token domestic
Feature activation+0.000
movies
Token movies
Feature activation+0.000
taking
Token taking
Feature activation+0.000
$
Token $
Feature activation+1.802
2
Token2
Feature activation+1.956
.
Token.
Feature activation+0.000
12
Token12
Feature activation+0.517
billion
Token billion
Feature activation+2.645
of
Token of
Feature activation+2.618
that
Token that
Feature activation+1.289
has
Token has
Feature activation+0.000
taken
Token taken
Feature activation+0.000
bike
Token bike
Feature activation+0.000
-
Token-
Feature activation+0.000
comm
Tokencomm
Feature activation+0.000
uters
Tokenuters
Feature activation+1.669
along
Token along
Feature activation+0.614
this
Token this
Feature activation+0.000
short
Token short
Feature activation+0.000
two
Token two
Feature activation+0.000
kilomet
Token kilomet
Feature activation+0.000

INTERVAL 1.208 - 1.610
CONTAINS 0.029%

,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
journey
Token journey
Feature activation+0.000
took
Token took
Feature activation+0.000
24
Token 24
Feature activation+0.684
hours
Token hours
Feature activation+1.231
and
Token and
Feature activation+0.077
was
Token was
Feature activation+0.000
fraught
Token fraught
Feature activation+0.000
with
Token with
Feature activation+0.000
risk
Token risk
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Purpose
Token Purpose
Feature activation+0.000
taking
Token taking
Feature activation+0.000
the
Token the
Feature activation+1.291
silver
Token silver
Feature activation+1.580
medal
Token medal
Feature activation+1.295
.
Token.
Feature activation+0.000
Hidden
Token Hidden
Feature activation+0.000
Figures
Token Figures
Feature activation+0.000
profits
Token profits
Feature activation+2.454
and
Token and
Feature activation+0.857
let
Token let
Feature activation+0.000
government
Token government
Feature activation+0.000
take
Token take
Feature activation+0.000
the
Token the
Feature activation+1.541
downside
Token downside
Feature activation+2.749
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Belgian
Token Belgian
Feature activation+0.000
like
Token like
Feature activation+0.000
for
Token for
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
a
Token a
Feature activation+1.561
good
Token good
Feature activation+3.397
,
Token,
Feature activation+0.466
long
Token long
Feature activation+1.749
hard
Token hard
Feature activation+3.566
look
Token look
Feature activation+2.111
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
take
Token take
Feature activation+0.000
his
Token his
Feature activation+0.000
cross
Token cross
Feature activation+0.000
and
Token and
Feature activation+1.477
follow
Token follow
Feature activation+0.000
me
Token me
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
worthy
Token worthy
Feature activation+0.000

INTERVAL 0.805 - 1.208
CONTAINS 0.034%

,
Token,
Feature activation+0.000
Im
Token Im
Feature activation+0.000
es
Tokenes
Feature activation+0.000
took
Token took
Feature activation+0.000
Adams
Token Adams
Feature activation+0.777
âĢ
TokenâĢ
Feature activation+1.019
Ļ
TokenĻ
Feature activation+0.798
advice
Token advice
Feature activation+2.312
and
Token and
Feature activation+2.117
audition
Token audition
Feature activation+0.000
ed
Tokened
Feature activation+0.000
.
Token.
Feature activation+0.000
Instead
Token Instead
Feature activation+0.000
he
Token he
Feature activation+0.000
took
Token took
Feature activation+0.000
the
Token the
Feature activation+0.796
"
Token "
Feature activation+1.175
Oh
TokenOh
Feature activation+0.048
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
very
Token very
Feature activation+0.664
violent
Token violent
Feature activation+3.157
actions
Token actions
Feature activation+0.916
like
Token like
Feature activation+0.000
cutting
Token cutting
Feature activation+0.000
off
Token off
Feature activation+0.000
a
Token a
Feature activation+0.000
head
Token head
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
took
Token took
Feature activation+0.000
"
Token "
Feature activation+0.000
seven
Tokenseven
Feature activation+0.743
years
Token years
Feature activation+1.121
"
Token"
Feature activation+1.049
to
Token to
Feature activation+0.000
raise
Token raise
Feature activation+0.000
enough
Token enough
Feature activation+0.000
money
Token money
Feature activation+0.000
environment
Token environment
Feature activation+0.000
suggests
Token suggests
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
to
Token to
Feature activation+0.000
taking
Token taking
Feature activation+0.000
iodine
Token iodine
Feature activation+1.206
,
Token,
Feature activation+0.508
but
Token but
Feature activation+0.000
avoiding
Token avoiding
Feature activation+0.000
ice
Token ice
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 0.403 - 0.805
CONTAINS 0.039%

would
Token would
Feature activation+0.000
take
Token take
Feature activation+0.000
anywhere
Token anywhere
Feature activation+0.000
from
Token from
Feature activation+0.000
several
Token several
Feature activation+0.000
days
Token days
Feature activation+0.699
to
Token to
Feature activation+0.346
weeks
Token weeks
Feature activation+0.192
to
Token to
Feature activation+0.601
go
Token go
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
issues
Token issues
Feature activation+0.000
,
Token,
Feature activation+0.000
taking
Token taking
Feature activation+0.000
a
Token a
Feature activation+1.387
shot
Token shot
Feature activation+0.620
at
Token at
Feature activation+0.645
the
Token the
Feature activation+0.000
man
Token man
Feature activation+0.000
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.000
are
Token are
Feature activation+0.000
probably
Token probably
Feature activation+0.000
taking
Token taking
Feature activation+0.000
a
Token a
Feature activation+1.853
loss
Token loss
Feature activation+1.086
on
Token on
Feature activation+0.707
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
aren
Token aren
Feature activation+0.000
't
Token't
Feature activation+0.000
live
Token live
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
take
Token take
Feature activation+0.000
for
Token for
Feature activation+0.644
granted
Token granted
Feature activation+0.000
).
Token).
Feature activation+0.000
More
Token More
Feature activation+0.000
than
Token than
Feature activation+0.000
half
Token half
Feature activation+0.000
way
Token way
Feature activation+0.000
would
Token would
Feature activation+0.000
take
Token take
Feature activation+0.000
3
Token 3
Feature activation+0.643
to
Token to
Feature activation+0.180
4
Token 4
Feature activation+0.551
years
Token years
Feature activation+2.056
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.000 - 0.403
CONTAINS 99.833%

create
Token create
Feature activation+0.000
unique
Token unique
Feature activation+0.000
experiences
Token experiences
Feature activation+0.000
almost
Token almost
Feature activation+0.000
anywhere
Token anywhere
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
home
Token home
Feature activation+0.000
.
Token.
Feature activation+0.000
Connect
Token Connect
Feature activation+0.000
s
Tokens
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
census
Token census
Feature activation+0.000
in
Token in
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
the
Token the
Feature activation+0.000
white
Token white
Feature activation+0.000
tigers
Token tigers
Feature activation+0.000
are
Token are
Feature activation+0.000
Already
TokenAlready
Feature activation+0.000
,
Token,
Feature activation+0.000
law
Token law
Feature activation+0.000
enforcement
Token enforcement
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000
near
Token near
Feature activation+0.000
St
Token St
Feature activation+0.000
.
Token.
Feature activation+0.000
Louis
Token Louis
Feature activation+0.000
,
Token,
Feature activation+0.000
Missouri
Token Missouri
Feature activation+0.000
.
Token.
Feature activation+0.000
H
Token H
Feature activation+0.000
oe
Tokenoe
Feature activation+0.000
y
Tokeny
Feature activation+0.000
,
Token,
Feature activation+0.000
Roy
Token Roy
Feature activation+0.000
R
Token R
Feature activation+0.000
itchie
Tokenitchie
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
syn
Token syn
Feature activation+0.000
ops
Tokenops
Feature activation+0.000
es
Tokenes
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
90
Token90
Feature activation+0.000
s
Tokens
Feature activation+0.000
cartoon
Token cartoon
Feature activation+0.000
Street
Token Street
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 H4.0: (feature 3986)

TOP ACTIVATIONS
MAX = 4.804

not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
val
Token val
Feature activation+0.000
u
Tokenu
Feature activation+0.000
ables
Tokenables
Feature activation+4.804
inside
Token inside
Feature activation+3.904
our
Token our
Feature activation+0.000
vehicles
Token vehicles
Feature activation+0.000
,
Token,
Feature activation+0.118
because
Token because
Feature activation+0.000
Mike
TokenMike
Feature activation+0.000
H
Token H
Feature activation+0.000
.
Token.
Feature activation+0.000
left
Token left
Feature activation+0.000
this
Token this
Feature activation+2.382
response
Token response
Feature activation+4.604
to
Token to
Feature activation+3.541
her
Token her
Feature activation+0.000
post
Token post
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+3.602
out
Token out
Feature activation+4.576
,"
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
fin
Token fin
Feature activation+0.000
isher
Tokenisher
Feature activation+0.000
left
Token left
Feature activation+0.000
G
Token G
Feature activation+0.000
oss
Tokenoss
Feature activation+0.000
little
Token little
Feature activation+4.565
opportunity
Token opportunity
Feature activation+1.910
to
Token to
Feature activation+2.225
succeed
Token succeed
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
might
Token might
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+2.308
A
Token A
Feature activation+1.149
7
Token7
Feature activation+1.115
a
Token a
Feature activation+4.531
very
Token very
Feature activation+0.454
frustrated
Token frustrated
Feature activation+0.000
man
Token man
Feature activation+0.000
.
Token.
Feature activation+0.205
Ċ
TokenĊ
Feature activation+0.000
was
Token was
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
left
Token left
Feature activation+0.000
nothing
Token nothing
Feature activation+2.447
on
Token on
Feature activation+4.527
the
Token the
Feature activation+0.000
table
Token table
Feature activation+0.000
,
Token,
Feature activation+0.331
living
Token living
Feature activation+0.000
life
Token life
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
left
Token left
Feature activation+0.267
them
Token them
Feature activation+3.535
on
Token on
Feature activation+4.412
for
Token for
Feature activation+0.000
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
the
Token the
Feature activation+0.000
light
Token light
Feature activation+0.000
leave
Token leave
Feature activation+0.000
his
Token his
Feature activation+2.565
mother
Token mother
Feature activation+1.510
's
Token's
Feature activation+4.375
eyes
Token eyes
Feature activation+3.770
as
Token as
Feature activation+3.109
she
Token she
Feature activation+0.000
saw
Token saw
Feature activation+0.000
her
Token her
Feature activation+0.000
that
Token that
Feature activation+0.000
past
Token past
Feature activation+0.000
and
Token and
Feature activation+0.000
leave
Token leave
Feature activation+0.000
it
Token it
Feature activation+2.418
right
Token right
Feature activation+4.373
here
Token here
Feature activation+2.286
.
Token.
Feature activation+0.459
That
Token That
Feature activation+0.000
is
Token is
Feature activation+0.000
my
Token my
Feature activation+0.000
always
Token always
Feature activation+0.000
best
Token best
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
them
Token them
Feature activation+2.947
be
Token be
Feature activation+4.320
.
Token.
Feature activation+0.599
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
left
Token left
Feature activation+1.042
a
Token a
Feature activation+4.264
little
Token little
Feature activation+3.019
perplex
Token perplex
Feature activation+1.451
ed
Tokened
Feature activation+1.578
.
Token.
Feature activation+0.000
Old
Token Old
Feature activation+0.000
left
Token left
Feature activation+0.000
an
Token an
Feature activation+4.046
ind
Token ind
Feature activation+1.058
el
Tokenel
Feature activation+0.000
ible
Tokenible
Feature activation+2.934
impression
Token impression
Feature activation+4.255
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
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
left
Token left
Feature activation+0.000
the
Token the
Feature activation+2.163
system
Token system
Feature activation+2.750
that
Token that
Feature activation+4.101
much
Token much
Feature activation+0.631
weaker
Token weaker
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
process
Token process
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+3.077
enormous
Token enormous
Feature activation+4.093
imprint
Token imprint
Feature activation+2.561
on
Token on
Feature activation+1.488
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
consciousness
Token consciousness
Feature activation+0.000
six
Token six
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+4.046
ind
Token ind
Feature activation+1.058
el
Tokenel
Feature activation+0.000
ible
Tokenible
Feature activation+2.934
impression
Token impression
Feature activation+4.255
and
Token and
Feature activation+0.000
chance
Token chance
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+2.136
organization
Token organization
Feature activation+2.491
as
Token as
Feature activation+4.029
a
Token a
Feature activation+0.490
free
Token free
Feature activation+0.000
agent
Token agent
Feature activation+0.000
if
Token if
Feature activation+0.000
Boston
Token Boston
Feature activation+0.000
W
Token W
Feature activation+0.000
ND
TokenND
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
a
Token a
Feature activation+2.751
message
Token message
Feature activation+4.005
for
Token for
Feature activation+3.786
Garfield
Token Garfield
Feature activation+0.000
County
Token County
Feature activation+0.000
Mag
Token Mag
Feature activation+0.000
istrate
Tokenistrate
Feature activation+0.000
Ċ
TokenĊ
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+0.500
own
Token own
Feature activation+3.937
children
Token children
Feature activation+0.040
for
Token for
Feature activation+1.738
six
Token six
Feature activation+0.000
months
Token months
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
val
Token val
Feature activation+0.000
u
Tokenu
Feature activation+0.000
ables
Tokenables
Feature activation+4.804
inside
Token inside
Feature activation+3.904
our
Token our
Feature activation+0.000
vehicles
Token vehicles
Feature activation+0.000
,
Token,
Feature activation+0.118
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
persuaded
Token persuaded
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+2.712
car
Token car
Feature activation+3.827
and
Token and
Feature activation+2.560
was
Token was
Feature activation+0.000
placed
Token placed
Feature activation+0.000
under
Token under
Feature activation+0.000
arrest
Token arrest
Feature activation+0.000

Top DFA by src position
MAX = 5.144

We
Token We
Feature activation+0.011
Top resid features:
were
Token were
Feature activation+0.014
Top resid features:
warned
Token warned
Feature activation+0.001
Top resid features:
not
Token not
Feature activation+0.009
Top resid features:
to
Token to
Feature activation-0.058
Top resid features:
leave
Token leave
Feature activation+5.134
Top resid features:
val
Token val
Feature activation+0.201
Top resid features:
u
Tokenu
Feature activation+0.139
Top resid features:
ables
Tokenables
Feature activation+0.463
Top resid features:
inside
Token inside
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Mike
TokenMike
Feature activation+0.009
Top resid features:
H
Token H
Feature activation-0.015
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
left
Token left
Feature activation+4.892
Top resid features:
this
Token this
Feature activation+0.288
Top resid features:
response
Token response
Feature activation+0.576
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
post
Token post
Feature activation+0.000
Top resid features:
even
Token even
Feature activation-0.008
Top resid features:
worse
Token worse
Feature activation+0.006
Top resid features:
dodge
Token dodge
Feature activation+0.057
Top resid features:
if
Token if
Feature activation+0.024
Top resid features:
she
Token she
Feature activation+0.008
Top resid features:
left
Token left
Feature activation+5.002
Top resid features:
it
Token it
Feature activation+0.378
Top resid features:
out
Token out
Feature activation+0.217
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.022
Top resid features:
arguably
Token arguably
Feature activation+0.016
Top resid features:
faster
Token faster
Feature activation+0.066
Top resid features:
fin
Token fin
Feature activation+0.006
Top resid features:
isher
Tokenisher
Feature activation+0.018
Top resid features:
left
Token left
Feature activation+5.004
Top resid features:
G
Token G
Feature activation+0.044
Top resid features:
oss
Tokenoss
Feature activation+0.264
Top resid features:
little
Token little
Feature activation+0.176
Top resid features:
opportunity
Token opportunity
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
home
Token home
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
otherwise
Token otherwise
Feature activation-0.069
Top resid features:
you
Token you
Feature activation+0.028
Top resid features:
might
Token might
Feature activation-0.028
Top resid features:
leave
Token leave
Feature activation+4.663
Top resid features:
the
Token the
Feature activation+0.162
Top resid features:
A
Token A
Feature activation+0.057
Top resid features:
7
Token7
Feature activation+0.518
Top resid features:
a
Token a
Feature activation+0.418
Top resid features:
very
Token very
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
quality
Token quality
Feature activation-0.001
Top resid features:
was
Token was
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.072
Top resid features:
He
Token He
Feature activation+0.026
Top resid features:
left
Token left
Feature activation+4.908
Top resid features:
nothing
Token nothing
Feature activation+0.330
Top resid features:
on
Token on
Feature activation+0.336
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
table
Token table
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
outlines
Token outlines
Feature activation+0.321
Top resid features:
,
Token,
Feature activation+0.055
Top resid features:
and
Token and
Feature activation+0.051
Top resid features:
I
Token I
Feature activation+0.047
Top resid features:
left
Token left
Feature activation+4.498
Top resid features:
them
Token them
Feature activation+0.238
Top resid features:
on
Token on
Feature activation+0.386
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
five
Token five
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.073
Top resid features:
I
Token I
Feature activation+0.015
Top resid features:
saw
Token saw
Feature activation-0.020
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
light
Token light
Feature activation+0.032
Top resid features:
leave
Token leave
Feature activation+4.713
Top resid features:
his
Token his
Feature activation+0.075
Top resid features:
mother
Token mother
Feature activation+0.519
Top resid features:
's
Token's
Feature activation+0.235
Top resid features:
eyes
Token eyes
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
me
Token me
Feature activation+0.010
Top resid features:
from
Token from
Feature activation+0.058
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
past
Token past
Feature activation+0.025
Top resid features:
and
Token and
Feature activation+0.018
Top resid features:
leave
Token leave
Feature activation+4.589
Top resid features:
it
Token it
Feature activation+0.326
Top resid features:
right
Token right
Feature activation+0.351
Top resid features:
here
Token here
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
That
Token That
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.016
Top resid features:
s
Tokens
Feature activation+0.029
Top resid features:
always
Token always
Feature activation+0.011
Top resid features:
best
Token best
Feature activation-0.007
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
leave
Token leave
Feature activation+4.639
Top resid features:
them
Token them
Feature activation+0.320
Top resid features:
be
Token be
Feature activation+0.452
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
However
Token However
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
issues
Token issues
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
they
Token they
Feature activation+0.047
Top resid features:
might
Token might
Feature activation-0.051
Top resid features:
be
Token be
Feature activation+0.061
Top resid features:
left
Token left
Feature activation+5.144
Top resid features:
a
Token a
Feature activation+0.156
Top resid features:
little
Token little
Feature activation+0.000
Top resid features:
perplex
Token perplex
Feature activation+0.000
Top resid features:
ed
Tokened
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.017
Top resid features:
six
Token six
Feature activation+0.046
Top resid features:
-
Token-
Feature activation+0.017
Top resid features:
year
Tokenyear
Feature activation+0.047
Top resid features:
run
Token run
Feature activation+0.101
Top resid features:
left
Token left
Feature activation+4.506
Top resid features:
an
Token an
Feature activation+0.108
Top resid features:
ind
Token ind
Feature activation+0.041
Top resid features:
el
Tokenel
Feature activation+0.015
Top resid features:
ible
Tokenible
Feature activation+0.328
Top resid features:
impression
Token impression
Feature activation+0.097
Top resid features:
they
Token they
Feature activation+0.013
Top resid features:
had
Token had
Feature activation+0.012
Top resid features:
wished
Token wished
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+0.115
Top resid features:
and
Token and
Feature activation+0.098
Top resid features:
left
Token left
Feature activation+4.158
Top resid features:
the
Token the
Feature activation+0.133
Top resid features:
system
Token system
Feature activation+0.657
Top resid features:
that
Token that
Feature activation+0.108
Top resid features:
much
Token much
Feature activation+0.000
Top resid features:
weaker
Token weaker
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
The
TokenThe
Feature activation+0.009
Top resid features:
Civil
Token Civil
Feature activation+0.014
Top resid features:
War
Token War
Feature activation+0.116
Top resid features:
left
Token left
Feature activation+5.099
Top resid features:
an
Token an
Feature activation-0.198
Top resid features:
enormous
Token enormous
Feature activation+0.182
Top resid features:
imprint
Token imprint
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.037
Top resid features:
six
Token six
Feature activation+0.053
Top resid features:
-
Token-
Feature activation+0.040
Top resid features:
year
Tokenyear
Feature activation+0.079
Top resid features:
run
Token run
Feature activation+0.171
Top resid features:
left
Token left
Feature activation+4.763
Top resid features:
an
Token an
Feature activation+0.046
Top resid features:
ind
Token ind
Feature activation+0.000
Top resid features:
el
Tokenel
Feature activation+0.000
Top resid features:
ible
Tokenible
Feature activation+0.000
Top resid features:
impression
Token impression
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
have
Token have
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.050
Top resid features:
chance
Token chance
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.063
Top resid features:
leave
Token leave
Feature activation+4.317
Top resid features:
the
Token the
Feature activation+0.131
Top resid features:
organization
Token organization
Feature activation+0.397
Top resid features:
as
Token as
Feature activation+0.224
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
free
Token free
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
allow
Token allow
Feature activation-0.002
Top resid features:
W
Token W
Feature activation+0.075
Top resid features:
ND
TokenND
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.082
Top resid features:
leave
Token leave
Feature activation+4.866
Top resid features:
a
Token a
Feature activation-0.225
Top resid features:
message
Token message
Feature activation+0.331
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Garfield
Token Garfield
Feature activation+0.000
Top resid features:
County
Token County
Feature activation+0.000
Top resid features:
family
Token family
Feature activation-0.018
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Le
TokenLe
Feature activation+0.002
Top resid features:
aving
Tokenaving
Feature activation+4.784
Top resid features:
my
Token my
Feature activation+0.039
Top resid features:
own
Token own
Feature activation+0.189
Top resid features:
children
Token children
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
six
Token six
Feature activation+0.000
Top resid features:
We
Token We
Feature activation+0.011
Top resid features:
were
Token were
Feature activation+0.010
Top resid features:
warned
Token warned
Feature activation+0.004
Top resid features:
not
Token not
Feature activation+0.027
Top resid features:
to
Token to
Feature activation-0.043
Top resid features:
leave
Token leave
Feature activation+3.762
Top resid features:
val
Token val
Feature activation+0.176
Top resid features:
u
Tokenu
Feature activation+0.018
Top resid features:
ables
Tokenables
Feature activation+0.670
Top resid features:
inside
Token inside
Feature activation+0.385
Top resid features:
our
Token our
Feature activation+0.000
Top resid features:
He
Token He
Feature activation+0.009
Top resid features:
was
Token was
Feature activation+0.009
Top resid features:
eventually
Token eventually
Feature activation+0.018
Top resid features:
persuaded
Token persuaded
Feature activation-0.016
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
leave
Token leave
Feature activation+4.964
Top resid features:
the
Token the
Feature activation-0.297
Top resid features:
car
Token car
Feature activation+0.150
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
placed
Token placed
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.50

Head 1: 0.04

Head 2: 0.02

Head 3: 0.05

Head 4: 0.03

Head 5: 0.03

Head 6: 0.03

Head 7: 0.10

Head 8: 0.02

Head 9: 0.08

Head 10: 0.01

Head 11: 0.09

Positive logits

unatt1.65

unprotected1.52

untouched1.51

intact1.46

voic1.46

unfinished1.38

mark1.30

prematurely1.30

crater1.29

inactive1.28

undone1.25

unanswered1.23

notation1.21

unsatisf1.20

hole1.20

Hole1.19

Pastebin1.19

rusty1.17

altogether1.17

shack1.14

Negative logits

Cosponsors-1.56

mage-1.23

GW-1.22

taboola-1.21

QL-1.19

strike-1.15

ーク-1.10

ACTIONS-1.10

Compare-1.09

-1.07

Interstitial-1.05

Brach-1.04

Strikes-1.04

srfN-1.03

psi-1.03

guiName-1.02

sqor-1.02

uates-1.02

skill-1.02

eryl-1.01

INTERVAL 4.324 - 4.804
CONTAINS 0.001%

fin
Token fin
Feature activation+0.000
isher
Tokenisher
Feature activation+0.000
left
Token left
Feature activation+0.000
G
Token G
Feature activation+0.000
oss
Tokenoss
Feature activation+0.000
little
Token little
Feature activation+4.565
opportunity
Token opportunity
Feature activation+1.910
to
Token to
Feature activation+2.225
succeed
Token succeed
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
val
Token val
Feature activation+0.000
u
Tokenu
Feature activation+0.000
ables
Tokenables
Feature activation+4.804
inside
Token inside
Feature activation+3.904
our
Token our
Feature activation+0.000
vehicles
Token vehicles
Feature activation+0.000
,
Token,
Feature activation+0.118
because
Token because
Feature activation+0.000
that
Token that
Feature activation+0.000
past
Token past
Feature activation+0.000
and
Token and
Feature activation+0.000
leave
Token leave
Feature activation+0.000
it
Token it
Feature activation+2.418
right
Token right
Feature activation+4.373
here
Token here
Feature activation+2.286
.
Token.
Feature activation+0.459
That
Token That
Feature activation+0.000
is
Token is
Feature activation+0.000
my
Token my
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
left
Token left
Feature activation+0.267
them
Token them
Feature activation+3.535
on
Token on
Feature activation+4.412
for
Token for
Feature activation+0.000
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
the
Token the
Feature activation+0.000
light
Token light
Feature activation+0.000
leave
Token leave
Feature activation+0.000
his
Token his
Feature activation+2.565
mother
Token mother
Feature activation+1.510
's
Token's
Feature activation+4.375
eyes
Token eyes
Feature activation+3.770
as
Token as
Feature activation+3.109
she
Token she
Feature activation+0.000
saw
Token saw
Feature activation+0.000
her
Token her
Feature activation+0.000

INTERVAL 3.844 - 4.324
CONTAINS 0.001%

always
Token always
Feature activation+0.000
best
Token best
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
them
Token them
Feature activation+2.947
be
Token be
Feature activation+4.320
.
Token.
Feature activation+0.599
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
left
Token left
Feature activation+1.042
a
Token a
Feature activation+4.264
little
Token little
Feature activation+3.019
perplex
Token perplex
Feature activation+1.451
ed
Tokened
Feature activation+1.578
.
Token.
Feature activation+0.000
Old
Token Old
Feature activation+0.000
chance
Token chance
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+2.136
organization
Token organization
Feature activation+2.491
as
Token as
Feature activation+4.029
a
Token a
Feature activation+0.490
free
Token free
Feature activation+0.000
agent
Token agent
Feature activation+0.000
if
Token if
Feature activation+0.000
Boston
Token Boston
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
val
Token val
Feature activation+0.000
u
Tokenu
Feature activation+0.000
ables
Tokenables
Feature activation+4.804
inside
Token inside
Feature activation+3.904
our
Token our
Feature activation+0.000
vehicles
Token vehicles
Feature activation+0.000
,
Token,
Feature activation+0.118
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.000
an
Token an
Feature activation+4.046
ind
Token ind
Feature activation+1.058
el
Tokenel
Feature activation+0.000
ible
Tokenible
Feature activation+2.934
impression
Token impression
Feature activation+4.255
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

INTERVAL 3.363 - 3.844
CONTAINS 0.004%

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+1.381
company
Token company
Feature activation+1.758
right
Token right
Feature activation+3.597
before
Token before
Feature activation+0.705
the
Token the
Feature activation+0.000
launch
Token launch
Feature activation+0.000
he
Token he
Feature activation+0.000
promised
Token promised
Feature activation+0.000
of
Token of
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+1.725
a
Token a
Feature activation+3.755
comment
Token comment
Feature activation+0.000
below
Token below
Feature activation+0.449
and
Token and
Feature activation+0.441
let
Token let
Feature activation+0.000
me
Token me
Feature activation+0.000
not
Token not
Feature activation+0.000
leave
Token leave
Feature activation+0.000
too
Token too
Feature activation+2.591
much
Token much
Feature activation+3.510
leg
Token leg
Feature activation+3.182
room
Token room
Feature activation+3.412
.
Token.
Feature activation+0.042
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
you
Token you
Feature activation+0.000
leave
Token leave
Feature activation+0.007
your
Token your
Feature activation+0.678
phone
Token phone
Feature activation+3.374
in
Token in
Feature activation+3.646
the
Token the
Feature activation+0.000
bedroom
Token bedroom
Feature activation+0.000
,
Token,
Feature activation+0.025
just
Token just
Feature activation+0.000
the
Token the
Feature activation+0.000
cruiser
Token cruiser
Feature activation+0.000
and
Token and
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+2.699
area
Token area
Feature activation+3.485
.
Token.
Feature activation+0.276
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
H
TokenH
Feature activation+0.000
arrison
Tokenarrison
Feature activation+0.000

INTERVAL 2.883 - 3.363
CONTAINS 0.005%

Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
leave
Token leave
Feature activation+0.000
my
Token my
Feature activation+1.178
play
Token play
Feature activation+0.838
books
Tokenbooks
Feature activation+3.124
alone
Token alone
Feature activation+2.816
.
Token.
Feature activation+0.206
Everything
Token Everything
Feature activation+0.000
you
Token you
Feature activation+0.000
need
Token need
Feature activation+0.000
Jones
Token Jones
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+2.915
hole
Token hole
Feature activation+1.232
at
Token at
Feature activation+0.000
corner
Token corner
Feature activation+0.000
for
Token for
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
made
Token made
Feature activation+0.000
plans
Token plans
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+2.028
ground
Token ground
Feature activation+3.354
early
Token early
Feature activation+1.774
and
Token and
Feature activation+0.000
return
Token return
Feature activation+0.000
to
Token to
Feature activation+0.000
London
Token London
Feature activation+0.000
s
Tokens
Feature activation+0.000
always
Token always
Feature activation+0.000
best
Token best
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
them
Token them
Feature activation+2.947
be
Token be
Feature activation+4.320
.
Token.
Feature activation+0.599
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
run
Token run
Feature activation+0.000
left
Token left
Feature activation+0.000
an
Token an
Feature activation+4.046
ind
Token ind
Feature activation+1.058
el
Tokenel
Feature activation+0.000
ible
Tokenible
Feature activation+2.934
impression
Token impression
Feature activation+4.255
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

INTERVAL 2.402 - 2.883
CONTAINS 0.009%

Union
Token Union
Feature activation+0.000
David
Token David
Feature activation+0.000
Davis
Token Davis
Feature activation+0.000
leaves
Token leaves
Feature activation+0.000
Downing
Token Downing
Feature activation+0.000
Street
Token Street
Feature activation+2.820
after
Token after
Feature activation+0.174
a
Token a
Feature activation+0.000
cabinet
Token cabinet
Feature activation+0.000
meeting
Token meeting
Feature activation+0.000
in
Token in
Feature activation+0.000
national
Token national
Feature activation+0.000
spokeswoman
Token spokeswoman
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
left
Token left
Feature activation+0.000
-
Token-
Feature activation+2.430
wing
Tokenwing
Feature activation+0.000
political
Token political
Feature activation+0.000
group
Token group
Feature activation+0.000
called
Token called
Feature activation+0.000
Solid
Token Solid
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
left
Token left
Feature activation+0.000
it
Token it
Feature activation+2.022
in
Token in
Feature activation+2.655
2013
Token 2013
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+0.000
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
system
Token system
Feature activation+0.000
is
Token is
Feature activation+0.000
left
Token left
Feature activation+0.172
up
Token up
Feature activation+2.639
to
Token to
Feature activation+0.538
states
Token states
Feature activation+0.000
,
Token,
Feature activation+0.000
implementation
Token implementation
Feature activation+0.000
would
Token would
Feature activation+0.000
's
Token's
Feature activation+0.000
important
Token important
Feature activation+0.000
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
leave
Token leave
Feature activation+0.097
them
Token them
Feature activation+2.474
that
Token that
Feature activation+2.436
way
Token way
Feature activation+0.147
,
Token,
Feature activation+0.112
or
Token or
Feature activation+0.000
else
Token else
Feature activation+0.000

INTERVAL 1.922 - 2.402
CONTAINS 0.011%

Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
left
Token left
Feature activation+0.000
our
Token our
Feature activation+1.851
people
Token people
Feature activation+0.353
in
Token in
Feature activation+2.339
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
Steven
Token Steven
Feature activation+0.000
Spielberg
Token Spielberg
Feature activation+0.000
left
Token left
Feature activation+0.000
the
Token the
Feature activation+1.688
Disney
Token Disney
Feature activation+0.000
fold
Token fold
Feature activation+2.022
and
Token and
Feature activation+0.330
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
re
Tokenre
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+1.887
police
Token police
Feature activation+0.312
commissioner
Token commissioner
Feature activation+0.418
office
Token office
Feature activation+2.002
in
Token in
Feature activation+0.971
Koch
Token Koch
Feature activation+0.000
i
Tokeni
Feature activation+0.000
January
Token January
Feature activation+0.000
18
Token 18
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+1.859
post
Token post
Feature activation+0.422
as
Token as
Feature activation+2.215
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
head
Token head
Feature activation+0.000
once
Token once
Feature activation+0.000
he
Token he
Feature activation+0.000
left
Token left
Feature activation+0.000
the
Token the
Feature activation+2.294
consulate
Token consulate
Feature activation+2.936
for
Token for
Feature activation+2.371
entering
Token entering
Feature activation+0.000
the
Token the
Feature activation+0.000
diplomatic
Token diplomatic
Feature activation+0.000
post
Token post
Feature activation+0.000
without
Token without
Feature activation+0.000

INTERVAL 1.441 - 1.922
CONTAINS 0.013%

law
Token law
Feature activation+0.000
enforcement
Token enforcement
Feature activation+0.000
staff
Token staff
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+1.589
country
Token country
Feature activation+2.065
obviously
Token obviously
Feature activation+2.003
reveals
Token reveals
Feature activation+0.213
that
Token that
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
15
Token 15
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+0.000
this
Token this
Feature activation+1.883
behind
Token behind
Feature activation+0.771
,
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
the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
leave
Token leave
Feature activation+0.000
residents
Token residents
Feature activation+1.495
"
Token "
Feature activation+3.815
in
Tokenin
Feature activation+2.838
the
Token the
Feature activation+0.000
l
Token l
Feature activation+0.000
urch
Tokenurch
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+0.000
ita
Tokenita
Feature activation+2.111
at
Token at
Feature activation+1.605
#
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
unable
Token unable
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
American
Token American
Feature activation+2.408
Samoa
Token Samoa
Feature activation+3.630
and
Token and
Feature activation+1.854
return
Token return
Feature activation+0.000
to
Token to
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

INTERVAL 0.961 - 1.441
CONTAINS 0.014%

we
Token we
Feature activation+0.000
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+2.689
jail
Token jail
Feature activation+1.357
and
Token and
Feature activation+1.294
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
YouTube
Token YouTube
Feature activation+0.000
video
Token video
Feature activation+0.000
and
Token and
Feature activation+0.000
leave
Token leave
Feature activation+0.000
comments
Token comments
Feature activation+0.000
with
Token with
Feature activation+1.073
my
Token my
Feature activation+0.000
name
Token name
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
name
Token name
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+1.199
European
Token European
Feature activation+1.020
"
Token "
Feature activation+1.822
family
Tokenfamily
Feature activation+1.594
."
Token."
Feature activation+1.049
Ċ
TokenĊ
Feature activation+0.000
staff
Token staff
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+1.000
service
Token service
Feature activation+1.242
.
Token.
Feature activation+0.000
Finally
Token Finally
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
a
Token a
Feature activation+2.740
totally
Token totally
Feature activation+2.013
contaminated
Token contaminated
Feature activation+1.127
site
Token site
Feature activation+1.688
.
Token.
Feature activation+0.049
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
J
TokenJ
Feature activation+0.000

INTERVAL 0.480 - 0.961
CONTAINS 0.015%

eared
Tokeneared
Feature activation+0.000
in
Token in
Feature activation+0.000
blood
Token blood
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
left
Token left
Feature activation+0.751
blood
Token blood
Feature activation+2.881
stains
Token stains
Feature activation+1.336
on
Token on
Feature activation+2.592
my
Token my
Feature activation+0.000
hands
Token hands
Feature activation+0.000
a
Token a
Feature activation+0.000
sergeant
Token sergeant
Feature activation+0.000
left
Token left
Feature activation+0.000
the
Token the
Feature activation+1.496
hospital
Token hospital
Feature activation+2.602
against
Token against
Feature activation+0.789
orders
Token orders
Feature activation+0.000
,
Token,
Feature activation+0.000
command
Token command
Feature activation+0.000
e
Tokene
Feature activation+0.000
ered
Tokenered
Feature activation+0.000
it
Token it
Feature activation+0.000
or
Token or
Feature activation+0.000
leave
Token leave
Feature activation+0.000
it
Token it
Feature activation+1.896
,
Token,
Feature activation+1.707
and
Token and
Feature activation+0.667
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
machine
Token machine
Feature activation+0.000
,
Token,
Feature activation+0.000
leave
Token leave
Feature activation+0.000
a
Token a
Feature activation+3.322
message
Token message
Feature activation+3.592
,
Token,
Feature activation+0.797
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
water
Token water
Feature activation+0.000
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
leave
Token leave
Feature activation+0.000
his
Token his
Feature activation+1.012
post
Token post
Feature activation+1.387
if
Token if
Feature activation+0.813
he
Token he
Feature activation+0.000
felt
Token felt
Feature activation+0.000
he
Token he
Feature activation+0.000
were
Token were
Feature activation+0.000
being
Token being
Feature activation+0.000

INTERVAL 0.000 - 0.480
CONTAINS 99.927%

deterior
Token deterior
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
while
Token while
Feature activation+0.000
awaiting
Token awaiting
Feature activation+0.000
therapy
Token therapy
Feature activation+0.000
.
Token.
Feature activation+0.000
Her
Token Her
Feature activation+0.000
patients
Token patients
Feature activation+0.000
include
Token include
Feature activation+0.000
a
Token a
Feature activation+0.000
health
Token health
Feature activation+0.000
failed
Token failed
Feature activation+0.000
to
Token to
Feature activation+0.000
achieve
Token achieve
Feature activation+0.000
in
Token in
Feature activation+0.000
1953
Token 1953
Feature activation+0.000
finally
Token finally
Feature activation+0.000
took
Token took
Feature activation+0.000
place
Token place
Feature activation+0.000
in
Token in
Feature activation+0.000
1973
Token 1973
Feature activation+0.000
when
Token when
Feature activation+0.000
again
Token again
Feature activation+0.000
rallying
Token rallying
Feature activation+0.000
to
Token to
Feature activation+0.000
protect
Token protect
Feature activation+0.000
a
Token a
Feature activation+0.000
stand
Token stand
Feature activation+0.000
of
Token of
Feature activation+0.000
trees
Token trees
Feature activation+0.000
known
Token known
Feature activation+0.000
as
Token as
Feature activation+0.000
The
Token The
Feature activation+0.000
be
Token be
Feature activation+0.000
impossible
Token impossible
Feature activation+0.000
to
Token to
Feature activation+0.000
ever
Token ever
Feature activation+0.000
sign
Token sign
Feature activation+0.000
a
Token a
Feature activation+0.000
peace
Token peace
Feature activation+0.000
treaty
Token treaty
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Middle
Token Middle
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
local
Token local
Feature activation+0.000
homeowners
Token homeowners
Feature activation+0.000
was
Token was
Feature activation+0.000
essentially
Token essentially
Feature activation+0.000
flat
Token flat
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H4.0: (feature 13826)

TOP ACTIVATIONS
MAX = 4.822

opened
Token opened
Feature activation+0.008
New
Token New
Feature activation+2.641
York
Token York
Feature activation+3.928
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+4.822
contest
Token contest
Feature activation+2.432
by
Token by
Feature activation+1.150
accusing
Token accusing
Feature activation+0.000
Michael
Token Michael
Feature activation+0.000
D
Token D
Feature activation+0.000
potential
Token potential
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.226
the
Token the
Feature activation+2.668
cup
Token cup
Feature activation+3.024
too
Token too
Feature activation+4.460
much
Token much
Feature activation+3.920
for
Token for
Feature activation+3.000
you
Token you
Feature activation+0.000
(
Token (
Feature activation+0.000
You
TokenYou
Feature activation+0.000
open
Token open
Feature activation+0.618
up
Token up
Feature activation+2.807
the
Token the
Feature activation+3.300
entire
Token entire
Feature activation+2.518
Act
Token Act
Feature activation+1.599
to
Token to
Feature activation+4.457
revision
Token revision
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
regulation
Token regulation
Feature activation+0.000
-
Token-
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
open
Token open
Feature activation+0.000
myself
Token myself
Feature activation+2.317
up
Token up
Feature activation+4.419
to
Token to
Feature activation+2.241
Wasteland
Token Wasteland
Feature activation+0.000
without
Token without
Feature activation+0.000
really
Token really
Feature activation+0.000
accompl
Token accompl
Feature activation+0.000
her
Tokenher
Feature activation+0.000
also
Token also
Feature activation+0.000
opened
Token opened
Feature activation+0.000
a
Token a
Feature activation+2.076
couple
Token couple
Feature activation+1.758
of
Token of
Feature activation+4.262
Titan
Token Titan
Feature activation+0.881
Pad
TokenPad
Feature activation+0.370
pages
Token pages
Feature activation+3.345
to
Token to
Feature activation+3.568
crowd
Token crowd
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.000
the
Token the
Feature activation+2.523
store
Token store
Feature activation+3.343
to
Token to
Feature activation+4.218
individual
Token individual
Feature activation+0.000
merchants
Token merchants
Feature activation+0.000
who
Token who
Feature activation+0.000
could
Token could
Feature activation+0.000
sell
Token sell
Feature activation+0.000
ijing
Tokenijing
Feature activation+0.000
will
Token will
Feature activation+0.000
open
Token open
Feature activation+0.000
its
Token its
Feature activation+3.106
economy
Token economy
Feature activation+3.609
at
Token at
Feature activation+3.931
the
Token the
Feature activation+0.000
pace
Token pace
Feature activation+0.000
it
Token it
Feature activation+0.000
deems
Token deems
Feature activation+0.000
to
Token to
Feature activation+0.000
way
Tokenway
Feature activation+0.000
race
Token race
Feature activation+0.000
,
Token,
Feature activation+0.000
opened
Token opened
Feature activation+0.008
New
Token New
Feature activation+2.641
York
Token York
Feature activation+3.928
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+4.822
contest
Token contest
Feature activation+2.432
by
Token by
Feature activation+1.150
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.226
the
Token the
Feature activation+2.668
cup
Token cup
Feature activation+3.024
too
Token too
Feature activation+4.460
much
Token much
Feature activation+3.920
for
Token for
Feature activation+3.000
you
Token you
Feature activation+0.000
(
Token (
Feature activation+0.000
You
TokenYou
Feature activation+0.000
can
Token can
Feature activation+0.000
Industries
Token Industries
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.264
the
Token the
Feature activation+2.619
very
Token very
Feature activation+2.949
first
Token first
Feature activation+3.902
private
Token private
Feature activation+2.352
sector
Token sector
Feature activation+1.752
small
Token small
Feature activation+2.081
arms
Token arms
Feature activation+0.270
factory
Token factory
Feature activation+3.290
takes
Token takes
Feature activation+0.000
steps
Token steps
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.703
flights
Token flights
Feature activation+1.350
to
Token to
Feature activation+3.889
US
Token US
Feature activation+0.000
on
Token on
Feature activation+0.569
sidelines
Token sidelines
Feature activation+0.000
of
Token of
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
N
TokenN
Feature activation+0.000
.,
Token.,
Feature activation+0.000
opened
Token opened
Feature activation+0.302
the
Token the
Feature activation+2.519
meeting
Token meeting
Feature activation+3.023
by
Token by
Feature activation+3.831
expressing
Token expressing
Feature activation+0.054
concerns
Token concerns
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
political
Token political
Feature activation+0.000
Smith
Token Smith
Feature activation+0.000
soon
Token soon
Feature activation+0.000
after
Token after
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.000
were
Token were
Feature activation+0.000
opened
Token opened
Feature activation+3.818
earlier
Token earlier
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
for
Token for
Feature activation+1.216
the
Token the
Feature activation+0.000
T
Token T
Feature activation+0.000
anger
Tokenanger
Feature activation+0.000
would
Token would
Feature activation+0.000
open
Token open
Feature activation+0.000
an
Token an
Feature activation+3.317
outlet
Token outlet
Feature activation+3.802
mall
Token mall
Feature activation+3.333
there
Token there
Feature activation+1.693
,
Token,
Feature activation+0.586
along
Token along
Feature activation+1.354
Loop
Token Loop
Feature activation+0.000
I
Token I
Feature activation+0.000
opened
Token opened
Feature activation+0.218
a
Token a
Feature activation+2.693
computer
Token computer
Feature activation+3.510
repair
Token repair
Feature activation+1.729
shop
Token shop
Feature activation+3.782
and
Token and
Feature activation+3.082
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
exact
Token exact
Feature activation+0.000
so
Token so
Feature activation+0.000
would
Token would
Feature activation+0.000
open
Token open
Feature activation+0.000
its
Token its
Feature activation+3.339
borders
Token borders
Feature activation+0.295
to
Token to
Feature activation+3.704
terrorists
Token terrorists
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Israel
TokenIsrael
Feature activation+0.000
opening
Token opening
Feature activation+0.000
one
Token one
Feature activation+2.802
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.821
mind
Token mind
Feature activation+3.690
up
Token up
Feature activation+3.261
to
Token to
Feature activation+3.301
new
Token new
Feature activation+0.000
ways
Token ways
Feature activation+0.000
of
Token of
Feature activation+0.000
consecutive
Token consecutive
Feature activation+0.000
losses
Token losses
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.000
the
Token the
Feature activation+3.367
season
Token season
Feature activation+3.674
.
Token.
Feature activation+0.259
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Disney
Token Disney
Feature activation+0.000
finally
Token finally
Feature activation+0.000
opened
Token opened
Feature activation+0.000
Tr
Token Tr
Feature activation+0.111
on
Tokenon
Feature activation+0.000
Legacy
Token Legacy
Feature activation+3.630
in
Token in
Feature activation+3.403
theaters
Token theaters
Feature activation+0.000
on
Token on
Feature activation+0.992
December
Token December
Feature activation+0.000
17
Token 17
Feature activation+0.000
Be
TokenBe
Feature activation+0.000
ijing
Tokenijing
Feature activation+0.000
will
Token will
Feature activation+0.000
open
Token open
Feature activation+0.000
its
Token its
Feature activation+3.106
economy
Token economy
Feature activation+3.609
at
Token at
Feature activation+3.931
the
Token the
Feature activation+0.000
pace
Token pace
Feature activation+0.000
it
Token it
Feature activation+0.000
deems
Token deems
Feature activation+0.000

Top DFA by src position
MAX = 5.661

three
Token three
Feature activation-0.009
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
way
Tokenway
Feature activation+0.019
Top resid features:
race
Token race
Feature activation+0.018
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
opened
Token opened
Feature activation+5.516
Top resid features:
New
Token New
Feature activation+0.078
Top resid features:
York
Token York
Feature activation+0.325
Top resid features:
âĢ
TokenâĢ
Feature activation-0.102
Top resid features:
Ļ
TokenĻ
Feature activation+0.440
Top resid features:
s
Tokens
Feature activation-0.140
Top resid features:
always
Token always
Feature activation-0.050
Top resid features:
has
Token has
Feature activation-0.007
Top resid features:
the
Token the
Feature activation-0.020
Top resid features:
potential
Token potential
Feature activation+0.069
Top resid features:
to
Token to
Feature activation+0.064
Top resid features:
open
Token open
Feature activation+5.333
Top resid features:
the
Token the
Feature activation+0.181
Top resid features:
cup
Token cup
Feature activation+0.155
Top resid features:
too
Token too
Feature activation+0.052
Top resid features:
much
Token much
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Air
Token Air
Feature activation-0.001
Top resid features:
Act
Token Act
Feature activation+0.004
Top resid features:
,
Token,
Feature activation-0.014
Top resid features:
which
Token which
Feature activation+0.001
Top resid features:
would
Token would
Feature activation+0.033
Top resid features:
open
Token open
Feature activation+4.933
Top resid features:
up
Token up
Feature activation+0.248
Top resid features:
the
Token the
Feature activation+0.178
Top resid features:
entire
Token entire
Feature activation+0.100
Top resid features:
Act
Token Act
Feature activation+0.371
Top resid features:
to
Token to
Feature activation+0.090
Top resid features:
worst
Token worst
Feature activation+0.021
Top resid features:
option
Token option
Feature activation+0.017
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
I
Token I
Feature activation-0.030
Top resid features:
would
Token would
Feature activation+0.011
Top resid features:
open
Token open
Feature activation+5.661
Top resid features:
myself
Token myself
Feature activation+0.039
Top resid features:
up
Token up
Feature activation+0.007
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Wasteland
Token Wasteland
Feature activation+0.000
Top resid features:
without
Token without
Feature activation+0.000
Top resid features:
ease
Token ease
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
As
Token As
Feature activation+0.024
Top resid features:
her
Tokenher
Feature activation-0.011
Top resid features:
also
Token also
Feature activation+0.015
Top resid features:
opened
Token opened
Feature activation+5.100
Top resid features:
a
Token a
Feature activation+0.115
Top resid features:
couple
Token couple
Feature activation+0.292
Top resid features:
of
Token of
Feature activation+0.085
Top resid features:
Titan
Token Titan
Feature activation+0.000
Top resid features:
Pad
TokenPad
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.012
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
management
Token management
Feature activation+0.040
Top resid features:
wants
Token wants
Feature activation-0.012
Top resid features:
to
Token to
Feature activation+0.023
Top resid features:
open
Token open
Feature activation+5.033
Top resid features:
the
Token the
Feature activation+0.196
Top resid features:
store
Token store
Feature activation+0.285
Top resid features:
to
Token to
Feature activation+0.124
Top resid features:
individual
Token individual
Feature activation+0.000
Top resid features:
merchants
Token merchants
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:
Be
TokenBe
Feature activation+0.002
Top resid features:
ijing
Tokenijing
Feature activation-0.001
Top resid features:
will
Token will
Feature activation+0.016
Top resid features:
open
Token open
Feature activation+4.714
Top resid features:
its
Token its
Feature activation+0.168
Top resid features:
economy
Token economy
Feature activation+0.453
Top resid features:
at
Token at
Feature activation-0.026
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
pace
Token pace
Feature activation+0.000
Top resid features:
three
Token three
Feature activation-0.022
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
way
Tokenway
Feature activation+0.023
Top resid features:
race
Token race
Feature activation+0.053
Top resid features:
,
Token,
Feature activation+0.044
Top resid features:
opened
Token opened
Feature activation+5.335
Top resid features:
New
Token New
Feature activation-0.282
Top resid features:
York
Token York
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
always
Token always
Feature activation-0.015
Top resid features:
has
Token has
Feature activation-0.007
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
potential
Token potential
Feature activation+0.048
Top resid features:
to
Token to
Feature activation+0.055
Top resid features:
open
Token open
Feature activation+4.723
Top resid features:
the
Token the
Feature activation+0.180
Top resid features:
cup
Token cup
Feature activation+0.147
Top resid features:
too
Token too
Feature activation+0.132
Top resid features:
much
Token much
Feature activation-0.002
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.008
Top resid features:
Israeli
Token Israeli
Feature activation-0.026
Top resid features:
Weapons
Token Weapons
Feature activation-0.010
Top resid features:
Industries
Token Industries
Feature activation-0.008
Top resid features:
to
Token to
Feature activation+0.101
Top resid features:
open
Token open
Feature activation+4.837
Top resid features:
the
Token the
Feature activation+0.171
Top resid features:
very
Token very
Feature activation-0.061
Top resid features:
first
Token first
Feature activation+0.210
Top resid features:
private
Token private
Feature activation+0.000
Top resid features:
sector
Token sector
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.078
Top resid features:
takes
Token takes
Feature activation+0.004
Top resid features:
steps
Token steps
Feature activation+0.064
Top resid features:
to
Token to
Feature activation+0.051
Top resid features:
open
Token open
Feature activation+4.446
Top resid features:
flights
Token flights
Feature activation+0.685
Top resid features:
to
Token to
Feature activation+0.035
Top resid features:
US
Token US
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
sidelines
Token sidelines
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.018
Top resid features:
U
Token U
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
N
TokenN
Feature activation+0.007
Top resid features:
.,
Token.,
Feature activation+0.030
Top resid features:
opened
Token opened
Feature activation+4.261
Top resid features:
the
Token the
Feature activation+0.489
Top resid features:
meeting
Token meeting
Feature activation+0.193
Top resid features:
by
Token by
Feature activation+0.168
Top resid features:
expressing
Token expressing
Feature activation+0.000
Top resid features:
concerns
Token concerns
Feature activation+0.000
Top resid features:
Smith
Token Smith
Feature activation-0.003
Top resid features:
soon
Token soon
Feature activation-0.021
Top resid features:
after
Token after
Feature activation+0.118
Top resid features:
negotiations
Token negotiations
Feature activation+0.293
Top resid features:
were
Token were
Feature activation+0.056
Top resid features:
opened
Token opened
Feature activation+4.787
Top resid features:
earlier
Token earlier
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
announcement
Token announcement
Feature activation+0.025
Top resid features:
that
Token that
Feature activation+0.021
Top resid features:
T
Token T
Feature activation-0.011
Top resid features:
anger
Tokenanger
Feature activation+0.081
Top resid features:
would
Token would
Feature activation+0.028
Top resid features:
open
Token open
Feature activation+4.838
Top resid features:
an
Token an
Feature activation-0.097
Top resid features:
outlet
Token outlet
Feature activation+0.241
Top resid features:
mall
Token mall
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
high
Token high
Feature activation+0.005
Top resid features:
school
Token school
Feature activation-0.084
Top resid features:
I
Token I
Feature activation+0.014
Top resid features:
opened
Token opened
Feature activation+4.827
Top resid features:
a
Token a
Feature activation+0.169
Top resid features:
computer
Token computer
Feature activation+0.230
Top resid features:
repair
Token repair
Feature activation-0.010
Top resid features:
shop
Token shop
Feature activation-0.034
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.102
Top resid features:
so
Token so
Feature activation+0.032
Top resid features:
would
Token would
Feature activation+0.025
Top resid features:
open
Token open
Feature activation+4.336
Top resid features:
its
Token its
Feature activation+0.215
Top resid features:
borders
Token borders
Feature activation+0.405
Top resid features:
to
Token to
Feature activation+0.065
Top resid features:
terrorists
Token terrorists
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
tar
Token tar
Feature activation+0.011
Top resid features:
ot
Tokenot
Feature activation+0.010
Top resid features:
included
Token included
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
involve
Token involve
Feature activation+0.010
Top resid features:
opening
Token opening
Feature activation+5.020
Top resid features:
one
Token one
Feature activation+0.013
Top resid features:
âĢ
TokenâĢ
Feature activation+0.028
Top resid features:
Ļ
TokenĻ
Feature activation-0.005
Top resid features:
s
Tokens
Feature activation+0.094
Top resid features:
mind
Token mind
Feature activation-0.079
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
three
Token three
Feature activation-0.023
Top resid features:
consecutive
Token consecutive
Feature activation+0.007
Top resid features:
losses
Token losses
Feature activation+0.049
Top resid features:
to
Token to
Feature activation+0.049
Top resid features:
open
Token open
Feature activation+4.987
Top resid features:
the
Token the
Feature activation-0.029
Top resid features:
season
Token season
Feature activation-0.034
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.008
Top resid features:
Con
TokenCon
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Disney
Token Disney
Feature activation-0.055
Top resid features:
finally
Token finally
Feature activation+0.060
Top resid features:
opened
Token opened
Feature activation+4.587
Top resid features:
Tr
Token Tr
Feature activation+0.102
Top resid features:
on
Tokenon
Feature activation+0.024
Top resid features:
Legacy
Token Legacy
Feature activation+0.120
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
theaters
Token theaters
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Be
TokenBe
Feature activation+0.002
Top resid features:
ijing
Tokenijing
Feature activation+0.045
Top resid features:
will
Token will
Feature activation+0.043
Top resid features:
open
Token open
Feature activation+5.299
Top resid features:
its
Token its
Feature activation-0.387
Top resid features:
economy
Token economy
Feature activation-0.042
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
pace
Token pace
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.49

Head 1: 0.03

Head 2: 0.02

Head 3: 0.04

Head 4: 0.03

Head 5: 0.04

Head 6: 0.04

Head 7: 0.11

Head 8: 0.02

Head 9: 0.07

Head 10: 0.02

Head 11: 0.10

Positive logits

MRI1.42

doors1.35

Reviewer1.33

valves1.30

Doors1.30

Dialog1.27

epad1.26

doors1.22

astery1.20

cgi1.19

gallery1.18

anew1.17

Flavoring1.16

drawer1.16

gates1.15

Accessed1.12

allery1.12

library1.11

chapter1.11

Shop1.10

Negative logits

eger-1.30

verages-1.25

omorphic-1.23

outcome-1.19

outcomes-1.15

exaggeration-1.07

acquitted-1.07

jad-1.04

Jou-1.03

axe-1.02

elong-1.01

pi-1.01

accur-1.01

accomplished-1.00

enne-1.00

xual-1.00

flown-0.99

neau-0.99

Cats-0.99

characterization-0.99

INTERVAL 4.340 - 4.822
CONTAINS 0.000%

potential
Token potential
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.226
the
Token the
Feature activation+2.668
cup
Token cup
Feature activation+3.024
too
Token too
Feature activation+4.460
much
Token much
Feature activation+3.920
for
Token for
Feature activation+3.000
you
Token you
Feature activation+0.000
(
Token (
Feature activation+0.000
You
TokenYou
Feature activation+0.000
open
Token open
Feature activation+0.618
up
Token up
Feature activation+2.807
the
Token the
Feature activation+3.300
entire
Token entire
Feature activation+2.518
Act
Token Act
Feature activation+1.599
to
Token to
Feature activation+4.457
revision
Token revision
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
regulation
Token regulation
Feature activation+0.000
-
Token-
Feature activation+0.000
opened
Token opened
Feature activation+0.008
New
Token New
Feature activation+2.641
York
Token York
Feature activation+3.928
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+4.822
contest
Token contest
Feature activation+2.432
by
Token by
Feature activation+1.150
accusing
Token accusing
Feature activation+0.000
Michael
Token Michael
Feature activation+0.000
D
Token D
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
open
Token open
Feature activation+0.000
myself
Token myself
Feature activation+2.317
up
Token up
Feature activation+4.419
to
Token to
Feature activation+2.241
Wasteland
Token Wasteland
Feature activation+0.000
without
Token without
Feature activation+0.000
really
Token really
Feature activation+0.000
accompl
Token accompl
Feature activation+0.000

INTERVAL 3.857 - 4.340
CONTAINS 0.001%

to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.226
the
Token the
Feature activation+2.668
cup
Token cup
Feature activation+3.024
too
Token too
Feature activation+4.460
much
Token much
Feature activation+3.920
for
Token for
Feature activation+3.000
you
Token you
Feature activation+0.000
(
Token (
Feature activation+0.000
You
TokenYou
Feature activation+0.000
can
Token can
Feature activation+0.000
her
Tokenher
Feature activation+0.000
also
Token also
Feature activation+0.000
opened
Token opened
Feature activation+0.000
a
Token a
Feature activation+2.076
couple
Token couple
Feature activation+1.758
of
Token of
Feature activation+4.262
Titan
Token Titan
Feature activation+0.881
Pad
TokenPad
Feature activation+0.370
pages
Token pages
Feature activation+3.345
to
Token to
Feature activation+3.568
crowd
Token crowd
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.000
the
Token the
Feature activation+2.523
store
Token store
Feature activation+3.343
to
Token to
Feature activation+4.218
individual
Token individual
Feature activation+0.000
merchants
Token merchants
Feature activation+0.000
who
Token who
Feature activation+0.000
could
Token could
Feature activation+0.000
sell
Token sell
Feature activation+0.000
Industries
Token Industries
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.264
the
Token the
Feature activation+2.619
very
Token very
Feature activation+2.949
first
Token first
Feature activation+3.902
private
Token private
Feature activation+2.352
sector
Token sector
Feature activation+1.752
small
Token small
Feature activation+2.081
arms
Token arms
Feature activation+0.270
factory
Token factory
Feature activation+3.290
way
Tokenway
Feature activation+0.000
race
Token race
Feature activation+0.000
,
Token,
Feature activation+0.000
opened
Token opened
Feature activation+0.008
New
Token New
Feature activation+2.641
York
Token York
Feature activation+3.928
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+4.822
contest
Token contest
Feature activation+2.432
by
Token by
Feature activation+1.150

INTERVAL 3.375 - 3.857
CONTAINS 0.002%

so
Token so
Feature activation+0.000
would
Token would
Feature activation+0.000
open
Token open
Feature activation+0.000
its
Token its
Feature activation+3.339
borders
Token borders
Feature activation+0.295
to
Token to
Feature activation+3.704
terrorists
Token terrorists
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Israel
TokenIsrael
Feature activation+0.000
Smith
Token Smith
Feature activation+0.000
soon
Token soon
Feature activation+0.000
after
Token after
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.000
were
Token were
Feature activation+0.000
opened
Token opened
Feature activation+3.818
earlier
Token earlier
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
for
Token for
Feature activation+1.216
the
Token the
Feature activation+0.000
T
Token T
Feature activation+0.000
anger
Tokenanger
Feature activation+0.000
would
Token would
Feature activation+0.000
open
Token open
Feature activation+0.000
an
Token an
Feature activation+3.317
outlet
Token outlet
Feature activation+3.802
mall
Token mall
Feature activation+3.333
there
Token there
Feature activation+1.693
,
Token,
Feature activation+0.586
along
Token along
Feature activation+1.354
Loop
Token Loop
Feature activation+0.000
opening
Token opening
Feature activation+0.000
one
Token one
Feature activation+2.802
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.821
mind
Token mind
Feature activation+3.690
up
Token up
Feature activation+3.261
to
Token to
Feature activation+3.301
new
Token new
Feature activation+0.000
ways
Token ways
Feature activation+0.000
of
Token of
Feature activation+0.000
consecutive
Token consecutive
Feature activation+0.000
losses
Token losses
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.000
the
Token the
Feature activation+3.367
season
Token season
Feature activation+3.674
.
Token.
Feature activation+0.259
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000

INTERVAL 2.893 - 3.375
CONTAINS 0.005%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
ovsky
Tokenovsky
Feature activation+0.000
opened
Token opened
Feature activation+0.000
his
Token his
Feature activation+2.847
first
Token first
Feature activation+4.086
laundry
Token laundry
Feature activation+3.304
delivery
Token delivery
Feature activation+3.519
service
Token service
Feature activation+2.983
,
Token,
Feature activation+3.072
Slate
Token Slate
Feature activation+0.000
,
Token,
Feature activation+0.000
first
Token first
Feature activation+3.902
private
Token private
Feature activation+2.352
sector
Token sector
Feature activation+1.752
small
Token small
Feature activation+2.081
arms
Token arms
Feature activation+0.270
factory
Token factory
Feature activation+3.290
in
Token in
Feature activation+1.415
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.821
mind
Token mind
Feature activation+3.690
up
Token up
Feature activation+3.261
to
Token to
Feature activation+3.301
new
Token new
Feature activation+0.000
ways
Token ways
Feature activation+0.000
of
Token of
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
.
Token.
Feature activation+0.000
opened
Token opened
Feature activation+0.218
a
Token a
Feature activation+2.693
computer
Token computer
Feature activation+3.510
repair
Token repair
Feature activation+1.729
shop
Token shop
Feature activation+3.782
and
Token and
Feature activation+3.082
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
exact
Token exact
Feature activation+0.000
Pant
Token Pant
Feature activation+0.000
Windows
Token Windows
Feature activation+1.407
RT
Token RT
Feature activation+0.000
version
Token version
Feature activation+1.794
of
Token of
Feature activation+1.259
Word
Token Word
Feature activation+0.000
to
Token to
Feature activation+3.195
take
Token take
Feature activation+0.000
notes
Token notes
Feature activation+0.000
.
Token.
Feature activation+0.000
Pair
Token Pair
Feature activation+0.000
ing
Tokening
Feature activation+0.000

INTERVAL 2.411 - 2.893
CONTAINS 0.006%

expand
Token expand
Feature activation+0.000
their
Token their
Feature activation+0.000
offerings
Token offerings
Feature activation+0.000
and
Token and
Feature activation+0.000
open
Token open
Feature activation+0.097
a
Token a
Feature activation+2.725
larger
Token larger
Feature activation+3.010
format
Token format
Feature activation+2.551
store
Token store
Feature activation+3.308
in
Token in
Feature activation+2.377
University
Token University
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
opened
Token opened
Feature activation+0.483
a
Token a
Feature activation+2.366
gallery
Token gallery
Feature activation+3.104
to
Token to
Feature activation+2.727
display
Token display
Feature activation+0.309
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
Unfortunately
Token Unfortunately
Feature activation+0.000
,
Token,
Feature activation+0.000
potential
Token potential
Feature activation+0.000
holes
Token holes
Feature activation+0.000
you
Token you
Feature activation+0.000
open
Token open
Feature activation+1.289
up
Token up
Feature activation+1.700
for
Token for
Feature activation+2.602
your
Token your
Feature activation+0.000
data
Token data
Feature activation+0.000
to
Token to
Feature activation+0.000
leak
Token leak
Feature activation+0.000
through
Token through
Feature activation+0.000
-
Token-
Feature activation+0.000
way
Tokenway
Feature activation+0.000
race
Token race
Feature activation+0.000
,
Token,
Feature activation+0.000
opened
Token opened
Feature activation+0.008
New
Token New
Feature activation+2.641
York
Token York
Feature activation+3.928
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+4.822
contest
Token contest
Feature activation+2.432
involve
Token involve
Feature activation+0.000
opening
Token opening
Feature activation+0.000
one
Token one
Feature activation+2.802
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+2.821
mind
Token mind
Feature activation+3.690
up
Token up
Feature activation+3.261
to
Token to
Feature activation+3.301
new
Token new
Feature activation+0.000
ways
Token ways
Feature activation+0.000

INTERVAL 1.929 - 2.411
CONTAINS 0.007%

that
Token that
Feature activation+0.000
once
Token once
Feature activation+0.000
you
Token you
Feature activation+0.000
open
Token open
Feature activation+1.266
the
Token the
Feature activation+1.849
score
Token score
Feature activation+2.274
in
Token in
Feature activation+1.752
Fin
Token Fin
Feature activation+0.000
ale
Tokenale
Feature activation+0.000
or
Token or
Feature activation+0.000
S
Token S
Feature activation+0.000
Cy
Token Cy
Feature activation+0.000
g
Tokeng
Feature activation+0.000
win
Tokenwin
Feature activation+0.000
64
Token64
Feature activation+0.000
terminal
Token terminal
Feature activation+2.021
with
Token with
Feature activation+1.996
a
Token a
Feature activation+0.000
Cy
Token Cy
Feature activation+0.000
g
Tokeng
Feature activation+0.000
win
Tokenwin
Feature activation+0.000
git
Token git
Feature activation+0.000
acquired
Token acquired
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
open
Token open
Feature activation+0.000
-
Token-
Feature activation+0.000
s
Tokens
Feature activation+2.111
ourced
Tokenourced
Feature activation+0.000
DR
Token DR
Feature activation+0.000
-
Token-
Feature activation+0.000
DOS
TokenDOS
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.000
since
Token since
Feature activation+0.000
opened
Token opened
Feature activation+0.000
stores
Token stores
Feature activation+1.835
on
Token on
Feature activation+2.257
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
280
Token 280
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.000
the
Token the
Feature activation+2.103
door
Token door
Feature activation+2.353
for
Token for
Feature activation+2.080
someone
Token someone
Feature activation+0.000
who
Token who
Feature activation+0.000
would
Token would
Feature activation+0.000
remind
Token remind
Feature activation+0.000
him
Token him
Feature activation+0.000

INTERVAL 1.447 - 1.929
CONTAINS 0.008%

all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
nor
Token nor
Feature activation+0.000
did
Token did
Feature activation+0.000
opening
Token opening
Feature activation+0.000
the
Token the
Feature activation+1.914
supplied
Token supplied
Feature activation+2.600
Windows
Token Windows
Feature activation+1.407
RT
Token RT
Feature activation+0.000
version
Token version
Feature activation+1.794
of
Token of
Feature activation+1.259
I
Token I
Feature activation+0.000
opened
Token opened
Feature activation+0.389
my
Token my
Feature activation+2.453
eyes
Token eyes
Feature activation+2.486
the
Token the
Feature activation+1.529
lights
Token lights
Feature activation+1.746
are
Token are
Feature activation+0.000
out
Token out
Feature activation+0.000
and
Token and
Feature activation+0.000
here
Token here
Feature activation+0.000
comes
Token comes
Feature activation+0.000
aggress
Token aggress
Feature activation+0.000
ors
Tokenors
Feature activation+0.000
broke
Token broke
Feature activation+0.000
open
Token open
Feature activation+0.000
the
Token the
Feature activation+1.123
safe
Token safe
Feature activation+1.459
and
Token and
Feature activation+0.000
made
Token made
Feature activation+0.000
off
Token off
Feature activation+0.000
with
Token with
Feature activation+0.000
two
Token two
Feature activation+0.000
open
Token open
Feature activation+0.264
the
Token the
Feature activation+2.619
very
Token very
Feature activation+2.949
first
Token first
Feature activation+3.902
private
Token private
Feature activation+2.352
sector
Token sector
Feature activation+1.752
small
Token small
Feature activation+2.081
arms
Token arms
Feature activation+0.270
factory
Token factory
Feature activation+3.290
in
Token in
Feature activation+1.415
the
Token the
Feature activation+0.000
ek
Tokenek
Feature activation+0.000
ith
Tokenith
Feature activation+0.000
succeeded
Token succeeded
Feature activation+0.000
in
Token in
Feature activation+0.000
opening
Token opening
Feature activation+0.000
the
Token the
Feature activation+1.608
C
Token C
Feature activation+0.521
asket
Tokenasket
Feature activation+1.401
at
Token at
Feature activation+2.344
the
Token the
Feature activation+0.000
loss
Token loss
Feature activation+0.000

INTERVAL 0.964 - 1.447
CONTAINS 0.008%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.454
mind
Token mind
Feature activation+2.147
up
Token up
Feature activation+1.276
to
Token to
Feature activation+1.163
new
Token new
Feature activation+0.000
ways
Token ways
Feature activation+0.000
of
Token of
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
.
Token.
Feature activation+0.000
reforms
Token reforms
Feature activation+0.000
and
Token and
Feature activation+0.000
opening
Token opening
Feature activation+0.000
-
Token-
Feature activation+0.197
up
Tokenup
Feature activation+1.548
policies
Token policies
Feature activation+1.252
were
Token were
Feature activation+0.000
fuelled
Token fuelled
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
normal
Token normal
Feature activation+0.000
opened
Tokenopened
Feature activation+0.000
up
Token up
Feature activation+1.235
"
Token"
Feature activation+0.162
the
Token the
Feature activation+2.152
Australian
Token Australian
Feature activation+0.000
economy
Token economy
Feature activation+1.132
,
Token,
Feature activation+0.898
and
Token and
Feature activation+0.384
who
Token who
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
government
Token government
Feature activation+0.000
calculated
Token calculated
Feature activation+0.000
the
Token the
Feature activation+0.000
opening
Token opening
Feature activation+0.000
of
Token of
Feature activation+2.752
European
Token European
Feature activation+1.382
markets
Token markets
Feature activation+2.757
to
Token to
Feature activation+1.980
Canadian
Token Canadian
Feature activation+0.000
shrimp
Token shrimp
Feature activation+0.000
and
Token and
Feature activation+0.000
House
Token House
Feature activation+2.333
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Capital
Token Capital
Feature activation+0.000
Region
Token Region
Feature activation+0.000
at
Token at
Feature activation+1.392
141
Token 141
Feature activation+0.000
S
Token S
Feature activation+0.000
.
Token.
Feature activation+0.000
Lake
Token Lake
Feature activation+0.000
Ave
Token Ave
Feature activation+0.000

INTERVAL 0.482 - 0.964
CONTAINS 0.010%

buy
Token buy
Feature activation+0.000
it
Token it
Feature activation+0.000
and
Token and
Feature activation+0.000
open
Token open
Feature activation+0.544
it
Token it
Feature activation+2.359
.
Token.
Feature activation+0.859
Nintendo
Token Nintendo
Feature activation+0.000
is
Token is
Feature activation+0.000
getting
Token getting
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
,
Token,
Feature activation+0.293
once
Token once
Feature activation+0.120
a
Token a
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.550
we
Token we
Feature activation+0.000
've
Token've
Feature activation+0.000
had
Token had
Feature activation+0.000
lines
Token lines
Feature activation+0.000
out
Token out
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
open
Token open
Feature activation+0.000
-
Token-
Feature activation+0.726
ended
Tokenended
Feature activation+0.000
questions
Token questions
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Gained
Token Gained
Feature activation+0.000
popularity
Token popularity
Feature activation+0.000
,
Token,
Feature activation+0.000
opened
Token opened
Feature activation+0.000
doors
Token doors
Feature activation+1.220
to
Token to
Feature activation+0.813
concerts
Token concerts
Feature activation+0.000
abroad
Token abroad
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
1991
Token 1991
Feature activation+0.000
site
Token site
Feature activation+0.000
could
Token could
Feature activation+0.014
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
open
Tokenopen
Feature activation+0.387
as
Token as
Feature activation+0.653
early
Token early
Feature activation+0.000
as
Token as
Feature activation+0.000
January
Token January
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.482
CONTAINS 99.954%

Bal
Token Bal
Feature activation+0.000
cor
Tokencor
Feature activation+0.000
p
Tokenp
Feature activation+0.000
could
Token could
Feature activation+0.000
not
Token not
Feature activation+0.000
raise
Token raise
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
funds
Token funds
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
end
Token end
Feature activation+0.000
game
Tokengame
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Her
TokenHer
Feature activation+0.000
oes
Tokenoes
Feature activation+0.000
nonetheless
Token nonetheless
Feature activation+0.000
ab
Token ab
Feature activation+0.000
ounded
Tokenounded
Feature activation+0.000
,
Token,
Feature activation+0.000
setup
Token setup
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
simply
Token simply
Feature activation+0.000
use
Token use
Feature activation+0.000
a
Token a
Feature activation+0.000
sub
Token sub
Feature activation+0.000
-
Token-
Feature activation+0.000
project
Tokenproject
Feature activation+0.000
heart
Token heart
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Fed
Token Fed
Feature activation+0.000
is
Token is
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
encourage
Token encourage
Feature activation+0.000
a
Token a
Feature activation+0.000
unified
Token unified
Feature activation+0.000
solution
Token solution
Feature activation+0.000
that
Token that
Feature activation+0.000
combines
Token combines
Feature activation+0.000
video
Token video
Feature activation+0.000
management
Token management
Feature activation+0.000
,
Token,
Feature activation+0.000
access
Token access
Feature activation+0.000
control
Token control
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 5 in H4.0: (feature 9687)

TOP ACTIVATIONS
MAX = 4.936

feedback
Token feedback
Feature activation+0.000
and
Token and
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+2.978
lot
Token lot
Feature activation+3.606
of
Token of
Feature activation+4.936
that
Token that
Feature activation+4.214
into
Token into
Feature activation+0.548
effect
Token effect
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
put
Tokenput
Feature activation+0.000
America
Token America
Feature activation+2.857
first
Token first
Feature activation+4.331
,
Token,
Feature activation+1.897
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
but
Token but
Feature activation+0.000
there
Token there
Feature activation+0.000
putting
Token putting
Feature activation+0.000
a
Token a
Feature activation+2.898
championship
Token championship
Feature activation+4.033
-
Token-
Feature activation+0.000
caliber
Tokencaliber
Feature activation+1.484
team
Token team
Feature activation+4.328
on
Token on
Feature activation+3.649
the
Token the
Feature activation+0.000
field
Token field
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
s
Tokens
Feature activation+0.000
certainly
Token certainly
Feature activation+0.000
putting
Token putting
Feature activation+0.000
a
Token a
Feature activation+2.422
lot
Token lot
Feature activation+2.493
more
Token more
Feature activation+4.219
stress
Token stress
Feature activation+1.421
on
Token on
Feature activation+0.140
our
Token our
Feature activation+0.000
pitching
Token pitching
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+2.978
lot
Token lot
Feature activation+3.606
of
Token of
Feature activation+4.936
that
Token that
Feature activation+4.214
into
Token into
Feature activation+0.548
effect
Token effect
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
saying
Token saying
Feature activation+0.000
he
Token he
Feature activation+0.000
put
Token put
Feature activation+0.000
his
Token his
Feature activation+2.492
own
Token own
Feature activation+4.207
life
Token life
Feature activation+3.580
at
Token at
Feature activation+2.527
risk
Token risk
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
he
Token he
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+1.955
back
Token back
Feature activation+4.201
into
Token into
Feature activation+0.290
the
Token the
Feature activation+0.000
general
Token general
Feature activation+0.000
culture
Token culture
Feature activation+0.000
.
Token.
Feature activation+0.000
Jonathan
Token Jonathan
Feature activation+0.000
I
Token I
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
put
Token put
Feature activation+0.000
all
Token all
Feature activation+1.516
their
Token their
Feature activation+4.069
eggs
Token eggs
Feature activation+1.726
in
Token in
Feature activation+1.862
the
Token the
Feature activation+0.516
industrial
Token industrial
Feature activation+0.000
design
Token design
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+2.048
finer
Token finer
Feature activation+3.079
point
Token point
Feature activation+4.042
on
Token on
Feature activation+1.534
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
real
Token real
Feature activation+0.000
cost
Token cost
Feature activation+0.000
of
Token of
Feature activation+0.000
not
Token not
Feature activation+0.000
putting
Token putting
Feature activation+0.000
a
Token a
Feature activation+2.898
championship
Token championship
Feature activation+4.033
-
Token-
Feature activation+0.000
caliber
Tokencaliber
Feature activation+1.484
team
Token team
Feature activation+4.328
on
Token on
Feature activation+3.649
the
Token the
Feature activation+0.000
to
Token to
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
put
Tokenput
Feature activation+0.000
an
Token an
Feature activation+2.815
artificial
Token artificial
Feature activation+3.955
timeline
Token timeline
Feature activation+3.029
on
Token on
Feature activation+2.348
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
put
Token put
Feature activation+0.000
N
Token N
Feature activation+0.605
uke
Tokenuke
Feature activation+0.000
or
Token or
Feature activation+2.847
Over
Token Over
Feature activation+1.029
pass
Tokenpass
Feature activation+3.861
in
Token in
Feature activation+3.611
the
Token the
Feature activation+0.000
pool
Token pool
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
or
Tokenor
Feature activation+0.000
have
Token have
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+2.113
lot
Token lot
Feature activation+2.752
of
Token of
Feature activation+3.834
care
Token care
Feature activation+3.255
and
Token and
Feature activation+2.421
attention
Token attention
Feature activation+2.348
into
Token into
Feature activation+1.131
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
're
Token're
Feature activation+0.000
putting
Token putting
Feature activation+0.000
their
Token their
Feature activation+2.432
best
Token best
Feature activation+3.802
foot
Token foot
Feature activation+2.091
forward
Token forward
Feature activation+1.192
,
Token,
Feature activation+0.419
with
Token with
Feature activation+0.000
S
Token S
Feature activation+0.000
right
Token right
Feature activation+0.045
-
Token-
Feature activation+0.000
wing
Tokenwing
Feature activation+0.734
radical
Token radical
Feature activation+0.909
ism
Tokenism
Feature activation+2.371
in
Token in
Feature activation+3.766
its
Token its
Feature activation+0.000
place
Token place
Feature activation+0.000
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
climate
Token climate
Feature activation+0.000
change
Token change
Feature activation+0.000
and
Token and
Feature activation+0.000
put
Token put
Feature activation+0.000
many
Token many
Feature activation+1.920
Americans
Token Americans
Feature activation+3.714
back
Token back
Feature activation+2.110
to
Token to
Feature activation+0.737
work
Token work
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
for
Token for
Feature activation+0.000
office
Token office
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
their
Token their
Feature activation+2.262
own
Token own
Feature activation+3.708
policies
Token policies
Feature activation+1.990
into
Token into
Feature activation+0.000
place
Token place
Feature activation+0.000
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
offense
Token offense
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
't
Token't
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+1.830
game
Token game
Feature activation+3.657
out
Token out
Feature activation+2.264
of
Token of
Feature activation+3.564
reach
Token reach
Feature activation+0.000
,
Token,
Feature activation+0.000
AS
Token AS
Feature activation+0.000
a
Token a
Feature activation+2.898
championship
Token championship
Feature activation+4.033
-
Token-
Feature activation+0.000
caliber
Tokencaliber
Feature activation+1.484
team
Token team
Feature activation+4.328
on
Token on
Feature activation+3.649
the
Token the
Feature activation+0.000
field
Token field
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
85
Token 85
Feature activation+3.102
,
Token,
Feature activation+0.879
000
Token000
Feature activation+2.425
people
Token people
Feature activation+1.711
out
Token out
Feature activation+2.599
of
Token of
Feature activation+3.646
work
Token work
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

Top DFA by src position
MAX = 5.710

We
Token We
Feature activation-0.003
Top resid features:
get
Token get
Feature activation-0.023
Top resid features:
good
Token good
Feature activation-0.054
Top resid features:
feedback
Token feedback
Feature activation-0.022
Top resid features:
and
Token and
Feature activation+0.033
Top resid features:
put
Token put
Feature activation+5.710
Top resid features:
a
Token a
Feature activation+0.051
Top resid features:
lot
Token lot
Feature activation+0.479
Top resid features:
of
Token of
Feature activation-0.067
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.009
Top resid features:
promised
Token promised
Feature activation+0.006
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
âĢ
Token âĢ
Feature activation+0.008
Top resid features:
ľ
Tokenľ
Feature activation+0.012
Top resid features:
put
Tokenput
Feature activation+5.133
Top resid features:
America
Token America
Feature activation+0.355
Top resid features:
first
Token first
Feature activation-0.102
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
at
Token at
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
cost
Token cost
Feature activation-0.055
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
not
Token not
Feature activation-0.007
Top resid features:
putting
Token putting
Feature activation+5.021
Top resid features:
a
Token a
Feature activation+0.144
Top resid features:
championship
Token championship
Feature activation-0.023
Top resid features:
-
Token-
Feature activation+0.022
Top resid features:
caliber
Tokencaliber
Feature activation+0.403
Top resid features:
team
Token team
Feature activation-0.153
Top resid features:
it
Token it
Feature activation-0.020
Top resid features:
âĢ
TokenâĢ
Feature activation+0.030
Top resid features:
Ļ
TokenĻ
Feature activation+0.013
Top resid features:
s
Tokens
Feature activation-0.009
Top resid features:
certainly
Token certainly
Feature activation-0.020
Top resid features:
putting
Token putting
Feature activation+4.832
Top resid features:
a
Token a
Feature activation+0.082
Top resid features:
lot
Token lot
Feature activation+0.479
Top resid features:
more
Token more
Feature activation-0.089
Top resid features:
stress
Token stress
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
We
Token We
Feature activation+0.008
Top resid features:
get
Token get
Feature activation-0.007
Top resid features:
good
Token good
Feature activation-0.026
Top resid features:
feedback
Token feedback
Feature activation+0.011
Top resid features:
and
Token and
Feature activation+0.023
Top resid features:
put
Token put
Feature activation+4.880
Top resid features:
a
Token a
Feature activation+0.090
Top resid features:
lot
Token lot
Feature activation+0.138
Top resid features:
of
Token of
Feature activation+0.238
Top resid features:
that
Token that
Feature activation+0.012
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.016
Top resid features:
hero
Token hero
Feature activation-0.025
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
saying
Token saying
Feature activation-0.037
Top resid features:
he
Token he
Feature activation+0.001
Top resid features:
put
Token put
Feature activation+5.289
Top resid features:
his
Token his
Feature activation+0.068
Top resid features:
own
Token own
Feature activation-0.029
Top resid features:
life
Token life
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
risk
Token risk
Feature activation+0.000
Top resid features:
outreach
Token outreach
Feature activation-0.005
Top resid features:
where
Token where
Feature activation-0.041
Top resid features:
he
Token he
Feature activation+0.024
Top resid features:
strives
Token strives
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
put
Token put
Feature activation+4.768
Top resid features:
science
Token science
Feature activation+0.550
Top resid features:
back
Token back
Feature activation-0.024
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
general
Token general
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
s
Tokens
Feature activation+0.030
Top resid features:
Jonathan
Token Jonathan
Feature activation+0.023
Top resid features:
I
Token I
Feature activation+0.011
Top resid features:
ve
Tokenve
Feature activation-0.005
Top resid features:
put
Token put
Feature activation+4.846
Top resid features:
all
Token all
Feature activation+0.350
Top resid features:
their
Token their
Feature activation-0.141
Top resid features:
eggs
Token eggs
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
anonymous
Token anonymous
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
To
TokenTo
Feature activation-0.242
Top resid features:
put
Token put
Feature activation+4.662
Top resid features:
a
Token a
Feature activation+0.078
Top resid features:
finer
Token finer
Feature activation+0.390
Top resid features:
point
Token point
Feature activation+0.242
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.013
Top resid features:
cost
Token cost
Feature activation-0.008
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
not
Token not
Feature activation-0.032
Top resid features:
putting
Token putting
Feature activation+5.361
Top resid features:
a
Token a
Feature activation-0.155
Top resid features:
championship
Token championship
Feature activation-0.089
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
caliber
Tokencaliber
Feature activation+0.000
Top resid features:
team
Token team
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.020
Top resid features:
Ŀ
TokenĿ
Feature activation-0.008
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
âĢ
Token âĢ
Feature activation-0.034
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
put
Tokenput
Feature activation+4.863
Top resid features:
an
Token an
Feature activation+0.136
Top resid features:
artificial
Token artificial
Feature activation+0.137
Top resid features:
timeline
Token timeline
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.008
Top resid features:
huge
Token huge
Feature activation-0.001
Top resid features:
surprise
Token surprise
Feature activation-0.003
Top resid features:
if
Token if
Feature activation-0.054
Top resid features:
they
Token they
Feature activation+0.044
Top resid features:
put
Token put
Feature activation+3.993
Top resid features:
N
Token N
Feature activation+0.064
Top resid features:
uke
Tokenuke
Feature activation+0.020
Top resid features:
or
Token or
Feature activation+0.467
Top resid features:
Over
Token Over
Feature activation+0.386
Top resid features:
pass
Tokenpass
Feature activation-0.023
Top resid features:
that
Token that
Feature activation-0.129
Top resid features:
G
Token G
Feature activation+0.022
Top resid features:
ub
Tokenub
Feature activation+0.016
Top resid features:
or
Tokenor
Feature activation+0.016
Top resid features:
have
Token have
Feature activation+0.086
Top resid features:
put
Token put
Feature activation+4.561
Top resid features:
a
Token a
Feature activation+0.065
Top resid features:
lot
Token lot
Feature activation+0.597
Top resid features:
of
Token of
Feature activation-0.105
Top resid features:
care
Token care
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
for
Token for
Feature activation-0.047
Top resid features:
now
Token now
Feature activation+0.009
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
they
Token they
Feature activation-0.014
Top resid features:
're
Token're
Feature activation-0.048
Top resid features:
putting
Token putting
Feature activation+4.972
Top resid features:
their
Token their
Feature activation+0.166
Top resid features:
best
Token best
Feature activation-0.069
Top resid features:
foot
Token foot
Feature activation+0.000
Top resid features:
forward
Token forward
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
confident
Token confident
Feature activation+0.001
Top resid features:
Mr
Token Mr
Feature activation+0.005
Top resid features:
Macron
Token Macron
Feature activation+0.017
Top resid features:
would
Token would
Feature activation+0.036
Top resid features:
"
Token "
Feature activation+0.058
Top resid features:
put
Tokenput
Feature activation+4.186
Top resid features:
right
Token right
Feature activation+0.163
Top resid features:
-
Token-
Feature activation+0.075
Top resid features:
wing
Tokenwing
Feature activation+0.146
Top resid features:
radical
Token radical
Feature activation+0.006
Top resid features:
ism
Tokenism
Feature activation+0.246
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.121
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
climate
Token climate
Feature activation-0.023
Top resid features:
change
Token change
Feature activation-0.051
Top resid features:
and
Token and
Feature activation+0.029
Top resid features:
put
Token put
Feature activation+4.441
Top resid features:
many
Token many
Feature activation+0.466
Top resid features:
Americans
Token Americans
Feature activation-0.062
Top resid features:
back
Token back
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
work
Token work
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.075
Top resid features:
ran
Token ran
Feature activation+0.028
Top resid features:
for
Token for
Feature activation-0.062
Top resid features:
office
Token office
Feature activation+0.011
Top resid features:
to
Token to
Feature activation-0.009
Top resid features:
put
Token put
Feature activation+4.713
Top resid features:
their
Token their
Feature activation+0.089
Top resid features:
own
Token own
Feature activation-0.025
Top resid features:
policies
Token policies
Feature activation+0.000
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
place
Token place
Feature activation+0.000
Top resid features:
While
Token While
Feature activation+0.005
Top resid features:
their
Token their
Feature activation-0.005
Top resid features:
offense
Token offense
Feature activation+0.043
Top resid features:
couldn
Token couldn
Feature activation-0.061
Top resid features:
't
Token't
Feature activation-0.048
Top resid features:
put
Token put
Feature activation+4.845
Top resid features:
the
Token the
Feature activation+0.073
Top resid features:
game
Token game
Feature activation-0.090
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
reach
Token reach
Feature activation+0.000
Top resid features:
at
Token at
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.013
Top resid features:
cost
Token cost
Feature activation-0.075
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
not
Token not
Feature activation-0.047
Top resid features:
putting
Token putting
Feature activation+4.760
Top resid features:
a
Token a
Feature activation+0.096
Top resid features:
championship
Token championship
Feature activation-0.038
Top resid features:
-
Token-
Feature activation+0.015
Top resid features:
caliber
Tokencaliber
Feature activation+0.021
Top resid features:
team
Token team
Feature activation+0.222
Top resid features:
Arthur
Token Arthur
Feature activation+0.003
Top resid features:
Andersen
Token Andersen
Feature activation+0.007
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
whose
Token whose
Feature activation+0.002
Top resid features:
indictment
Token indictment
Feature activation-0.041
Top resid features:
put
Token put
Feature activation+4.204
Top resid features:
about
Token about
Feature activation+0.072
Top resid features:
85
Token 85
Feature activation+0.049
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
000
Token000
Feature activation+0.186
Top resid features:
people
Token people
Feature activation+0.141
Top resid features:

Decoder Weights Distribution

Head 0: 0.49

Head 1: 0.05

Head 2: 0.02

Head 3: 0.06

Head 4: 0.02

Head 5: 0.05

Head 6: 0.04

Head 7: 0.11

Head 8: 0.02

Head 9: 0.05

Head 10: 0.01

Head 11: 0.09

Positive logits

aside1.54

chuk1.43

toget1.32

PID1.30

onto1.30

together1.25

overboard1.25

shack1.24

numbered1.22

rawdownloadcloneembedreportprint1.21

into1.16

together1.15

Vaughan1.15

eki1.14

isine1.13

firmly1.12

oos1.10

pload1.10

wraps1.10

Maxim1.10

Negative logits

Hispanic-1.23

enhagen-1.12

imester-1.12

sth-1.11

Returns-1.09

comments-1.08

ldom-1.07

fm-1.06

[];-1.06

uno-1.05

ennial-1.05

xual-1.04

&&-1.03

demand-1.03

Base-1.03

Train-1.02

illary-1.02

orea-1.01

Application-1.01

aturday-1.01

INTERVAL 4.442 - 4.936
CONTAINS 0.000%

feedback
Token feedback
Feature activation+0.000
and
Token and
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+2.978
lot
Token lot
Feature activation+3.606
of
Token of
Feature activation+4.936
that
Token that
Feature activation+4.214
into
Token into
Feature activation+0.548
effect
Token effect
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.949 - 4.442
CONTAINS 0.001%

,
Token,
Feature activation+0.000
saying
Token saying
Feature activation+0.000
he
Token he
Feature activation+0.000
put
Token put
Feature activation+0.000
his
Token his
Feature activation+2.492
own
Token own
Feature activation+4.207
life
Token life
Feature activation+3.580
at
Token at
Feature activation+2.527
risk
Token risk
Feature activation+0.000
to
Token to
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
he
Token he
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+1.955
back
Token back
Feature activation+4.201
into
Token into
Feature activation+0.290
the
Token the
Feature activation+0.000
general
Token general
Feature activation+0.000
culture
Token culture
Feature activation+0.000
.
Token.
Feature activation+0.000
s
Tokens
Feature activation+0.000
certainly
Token certainly
Feature activation+0.000
putting
Token putting
Feature activation+0.000
a
Token a
Feature activation+2.422
lot
Token lot
Feature activation+2.493
more
Token more
Feature activation+4.219
stress
Token stress
Feature activation+1.421
on
Token on
Feature activation+0.140
our
Token our
Feature activation+0.000
pitching
Token pitching
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
put
Tokenput
Feature activation+0.000
America
Token America
Feature activation+2.857
first
Token first
Feature activation+4.331
,
Token,
Feature activation+1.897
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
but
Token but
Feature activation+0.000
there
Token there
Feature activation+0.000
and
Token and
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+2.978
lot
Token lot
Feature activation+3.606
of
Token of
Feature activation+4.936
that
Token that
Feature activation+4.214
into
Token into
Feature activation+0.548
effect
Token effect
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.455 - 3.949
CONTAINS 0.003%

that
Token that
Feature activation+0.000
will
Token will
Feature activation+0.000
put
Token put
Feature activation+0.000
our
Token our
Feature activation+2.095
veterans
Token veterans
Feature activation+2.501
in
Token in
Feature activation+3.485
front
Token front
Feature activation+0.000
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
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
're
Token're
Feature activation+0.000
putting
Token putting
Feature activation+0.000
their
Token their
Feature activation+2.432
best
Token best
Feature activation+3.802
foot
Token foot
Feature activation+2.091
forward
Token forward
Feature activation+1.192
,
Token,
Feature activation+0.419
with
Token with
Feature activation+0.000
S
Token S
Feature activation+0.000
Lucky
Token Lucky
Feature activation+0.000
Peach
Token Peach
Feature activation+0.000
,
Token,
Feature activation+0.000
Put
Token Put
Feature activation+0.000
A
Token A
Feature activation+3.485
Egg
Token Egg
Feature activation+3.633
On
Token On
Feature activation+1.895
It
Token It
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+0.000
G
Token G
Feature activation+0.000
creat
Tokencreat
Feature activation+0.127
ive
Tokenive
Feature activation+3.499
solutions
Token solutions
Feature activation+3.472
âĢ
TokenâĢ
Feature activation+0.834
Ŀ
TokenĿ
Feature activation+0.983
to
Token to
Feature activation+3.482
Minister
Token Minister
Feature activation+0.000
for
Token for
Feature activation+0.000
Heritage
Token Heritage
Feature activation+0.000
Jimmy
Token Jimmy
Feature activation+0.000
De
Token De
Feature activation+0.000
considering
Token considering
Feature activation+0.000
putting
Token putting
Feature activation+0.000
30
Token 30
Feature activation+2.241
-
Token-
Feature activation+0.560
40
Token40
Feature activation+0.664
million
Token million
Feature activation+3.564
Americans
Token Americans
Feature activation+3.234
in
Token in
Feature activation+3.116
uniform
Token uniform
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.961 - 3.455
CONTAINS 0.004%

Ċ
TokenĊ
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+2.422
positive
Token positive
Feature activation+3.252
spin
Token spin
Feature activation+0.781
on
Token on
Feature activation+0.108
bullies
Token bullies
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
akis
Tokenakis
Feature activation+0.000
of
Token of
Feature activation+0.000
putting
Token putting
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.477
public
Tokenpublic
Feature activation+3.024
pressure
Token pressure
Feature activation+2.768
on
Token on
Feature activation+1.199
Israel
Token Israel
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Caleb
Token Caleb
Feature activation+0.000
Rogers
Token Rogers
Feature activation+0.000
filed
Token filed
Feature activation+0.000
a
Token a
Feature activation+0.000
put
Token put
Feature activation+0.000
-
Token-
Feature activation+3.437
back
Tokenback
Feature activation+0.288
notice
Token notice
Feature activation+0.000
with
Token with
Feature activation+0.000
Youtube
Token Youtube
Feature activation+0.000
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+2.113
lot
Token lot
Feature activation+2.752
of
Token of
Feature activation+3.834
care
Token care
Feature activation+3.255
and
Token and
Feature activation+2.421
attention
Token attention
Feature activation+2.348
into
Token into
Feature activation+1.131
the
Token the
Feature activation+0.000
Winter
Token Winter
Feature activation+0.000
putting
Token putting
Feature activation+0.000
the
Token the
Feature activation+1.665
t
Token t
Feature activation+1.057
ux
Tokenux
Feature activation+0.000
edo
Tokenedo
Feature activation+1.842
back
Token back
Feature activation+3.400
on
Token on
Feature activation+1.649
to
Token to
Feature activation+0.000
rel
Token rel
Feature activation+0.000
ive
Tokenive
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 2.468 - 2.961
CONTAINS 0.007%

just
Token just
Feature activation+0.000
put
Token put
Feature activation+0.000
all
Token all
Feature activation+1.674
my
Token my
Feature activation+3.157
cards
Token cards
Feature activation+3.360
on
Token on
Feature activation+2.696
the
Token the
Feature activation+0.000
table
Token table
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
dragged
Token dragged
Feature activation+0.000
never
Token never
Feature activation+0.000
seen
Token seen
Feature activation+0.000
him
Token him
Feature activation+0.000
put
Token put
Feature activation+0.000
anyone
Token anyone
Feature activation+2.482
in
Token in
Feature activation+2.515
a
Token a
Feature activation+0.109
bad
Token bad
Feature activation+0.000
situation
Token situation
Feature activation+0.000
.'
Token.'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Putting
TokenPutting
Feature activation+0.000
a
Token a
Feature activation+2.245
finer
Token finer
Feature activation+2.932
point
Token point
Feature activation+2.701
on
Token on
Feature activation+1.491
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
if
Tokenif
Feature activation+0.000
it
Token it
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
their
Token their
Feature activation+2.161
head
Token head
Feature activation+2.780
down
Token down
Feature activation+0.181
and
Token and
Feature activation+0.000
crank
Token crank
Feature activation+0.000
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
fight
Token fight
Feature activation+0.000
,
Token,
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+2.254
fascinating
Token fascinating
Feature activation+2.585
twist
Token twist
Feature activation+3.016
on
Token on
Feature activation+0.489
his
Token his
Feature activation+0.000
record
Token record
Feature activation+0.000
this
Token this
Feature activation+0.000

INTERVAL 1.974 - 2.468
CONTAINS 0.012%

tried
Token tried
Feature activation+0.000
putting
Token putting
Feature activation+0.000
the
Token the
Feature activation+1.551
pump
Token pump
Feature activation+2.287
motor
Token motor
Feature activation+1.219
and
Token and
Feature activation+2.090
my
Token my
Feature activation+0.000
wallet
Token wallet
Feature activation+0.317
in
Token in
Feature activation+1.570
the
Token the
Feature activation+0.000
locker
Token locker
Feature activation+0.000
they
Token they
Feature activation+0.000
would
Token would
Feature activation+0.000
try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
a
Token a
Feature activation+2.357
stop
Token stop
Feature activation+0.544
to
Token to
Feature activation+2.138
this
Token this
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
,
Token,
Feature activation+0.000
putting
Token putting
Feature activation+0.000
the
Token the
Feature activation+1.533
movie
Token movie
Feature activation+1.952
three
Token three
Feature activation+3.123
million
Token million
Feature activation+2.213
dollars
Token dollars
Feature activation+2.795
over
Token over
Feature activation+2.176
budget
Token budget
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
many
Token many
Feature activation+0.000
people
Token people
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+2.066
Fab
Token Fab
Feature activation+0.000
Mel
Token Mel
Feature activation+0.000
o
Tokeno
Feature activation+0.000
-
Token-
Feature activation+0.000
less
Tokenless
Feature activation+0.099
Budget
Token Budget
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Putting
TokenPutting
Feature activation+0.000
a
Token a
Feature activation+2.245
finer
Token finer
Feature activation+2.932
point
Token point
Feature activation+2.701
on
Token on
Feature activation+1.491
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.481 - 1.974
CONTAINS 0.012%

this
Token this
Feature activation+0.000
by
Token by
Feature activation+0.000
putting
Token putting
Feature activation+0.000
your
Token your
Feature activation+0.200
code
Token code
Feature activation+0.506
front
Token front
Feature activation+1.729
and
Token and
Feature activation+0.000
center
Token center
Feature activation+0.000
,
Token,
Feature activation+0.369
highlighting
Token highlighting
Feature activation+0.000
the
Token the
Feature activation+0.000
Farm
Token Farm
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Put
TokenPut
Feature activation+0.000
your
Token your
Feature activation+1.054
vehicle
Token vehicle
Feature activation+1.682
on
Token on
Feature activation+1.263
autop
Token autop
Feature activation+0.000
ilot
Tokenilot
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
and
Token and
Feature activation+0.000
looking
Token looking
Feature activation+0.000
forward
Token forward
Feature activation+0.000
to
Token to
Feature activation+0.000
putting
Token putting
Feature activation+0.000
the
Token the
Feature activation+1.665
t
Token t
Feature activation+1.057
ux
Tokenux
Feature activation+0.000
edo
Tokenedo
Feature activation+1.842
back
Token back
Feature activation+3.400
on
Token on
Feature activation+1.649
hard
Token hard
Feature activation+0.000
at
Token at
Feature activation+0.000
work
Token work
Feature activation+0.000
putting
Token putting
Feature activation+0.000
code
Token code
Feature activation+0.324
on
Token on
Feature activation+1.876
the
Token the
Feature activation+0.000
tiny
Token tiny
Feature activation+0.000
little
Token little
Feature activation+0.000
micro
Token micro
Feature activation+0.000
controller
Tokencontroller
Feature activation+0.000
infield
Token infield
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
two
Token two
Feature activation+1.405
runners
Token runners
Feature activation+1.702
on
Token on
Feature activation+1.849
before
Token before
Feature activation+0.474
Kent
Token Kent
Feature activation+0.000
f
Token f
Feature activation+0.000
anned
Tokenanned
Feature activation+0.000
Dylan
Token Dylan
Feature activation+0.000

INTERVAL 0.987 - 1.481
CONTAINS 0.012%

whole
Token whole
Feature activation+0.000
city
Token city
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
put
Token put
Feature activation+0.314
under
Token under
Feature activation+1.065
curfew
Token curfew
Feature activation+0.000
,
Token,
Feature activation+0.000
effectively
Token effectively
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
Defense
Token Defense
Feature activation+0.000
Intelligence
Token Intelligence
Feature activation+0.000
Agency
Token Agency
Feature activation+0.000
puts
Token puts
Feature activation+0.000
the
Token the
Feature activation+0.745
number
Token number
Feature activation+1.196
of
Token of
Feature activation+0.158
groups
Token groups
Feature activation+0.000
at
Token at
Feature activation+0.804
1
Token 1
Feature activation+0.000
,
Token,
Feature activation+0.000
lot
Token lot
Feature activation+2.752
of
Token of
Feature activation+3.834
care
Token care
Feature activation+3.255
and
Token and
Feature activation+2.421
attention
Token attention
Feature activation+2.348
into
Token into
Feature activation+1.131
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
than
Token than
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
estimates
Token estimates
Feature activation+0.000
that
Token that
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+1.375
number
Token number
Feature activation+1.699
of
Token of
Feature activation+0.041
school
Token school
Feature activation+0.000
children
Token children
Feature activation+0.000
who
Token who
Feature activation+0.403
extra
Token extra
Feature activation+0.000
security
Token security
Feature activation+0.000
measures
Token measures
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
put
Token put
Feature activation+1.140
in
Token in
Feature activation+2.147
place
Token place
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.494 - 0.987
CONTAINS 0.019%

approaches
Token approaches
Feature activation+0.000
to
Token to
Feature activation+0.000
putting
Token putting
Feature activation+0.000
a
Token a
Feature activation+1.765
printer
Token printer
Feature activation+2.200
on
Token on
Feature activation+0.542
a
Token a
Feature activation+0.000
network
Token network
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
first
Token first
Feature activation+0.000
required
Token required
Feature activation+0.000
placing
Token placing
Feature activation+0.000
a
Token a
Feature activation+0.000
device
Token device
Feature activation+0.260
or
Token or
Feature activation+0.310
sensor
Token sensor
Feature activation+0.689
near
Token near
Feature activation+0.018
an
Token an
Feature activation+0.000
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.000
Qaeda
TokenQaeda
Feature activation+0.000
capable
Token capable
Feature activation+0.000
of
Token of
Feature activation+0.000
placing
Token placing
Feature activation+0.000
payload
Token payload
Feature activation+0.000
s
Tokens
Feature activation+1.519
weighing
Token weighing
Feature activation+0.794
between
Token between
Feature activation+0.000
2
Token 2
Feature activation+0.000
metric
Token metric
Feature activation+0.000
tons
Token tons
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
team
Token team
Feature activation+0.000
placed
Token placed
Feature activation+0.000
a
Token a
Feature activation+0.000
special
Token special
Feature activation+0.496
,
Token,
Feature activation+0.000
portable
Token portable
Feature activation+0.855
flow
Token flow
Feature activation+0.155
meter
Token meter
Feature activation+0.534
,
Token,
Feature activation+0.907
a
Token a
Feature activation+0.000
special
Token special
Feature activation+0.496
,
Token,
Feature activation+0.000
portable
Token portable
Feature activation+0.855
flow
Token flow
Feature activation+0.155
meter
Token meter
Feature activation+0.534
,
Token,
Feature activation+0.907
designed
Token designed
Feature activation+0.009
by
Token by
Feature activation+0.000
Bro
Token Bro
Feature activation+0.000
ds
Tokends
Feature activation+0.000

INTERVAL 0.000 - 0.494
CONTAINS 99.930%

had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
deal
Token deal
Feature activation+0.000
with
Token with
Feature activation+0.000
that
Token that
Feature activation+0.000
heat
Token heat
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
James
Token James
Feature activation+0.000
had
Token had
Feature activation+0.000
played
Token played
Feature activation+0.000
s
Tokens
Feature activation+0.000
no
Token no
Feature activation+0.000
denying
Token denying
Feature activation+0.000
the
Token the
Feature activation+0.000
Australian
Token Australian
Feature activation+0.000
actor
Token actor
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
natural
Token natural
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
website
Token website
Feature activation+0.000
stated
Token stated
Feature activation+0.000
,
Token,
Feature activation+0.000
although
Token although
Feature activation+0.000
no
Token no
Feature activation+0.000
documentation
Token documentation
Feature activation+0.000
is
Token is
Feature activation+0.000
provided
Token provided
Feature activation+0.000
to
Token to
Feature activation+0.000
even
Token even
Feature activation+0.000
though
Token though
Feature activation+0.000
that
Token that
Feature activation+0.000
had
Token had
Feature activation+0.000
not
Token not
Feature activation+0.000
come
Token come
Feature activation+0.000
close
Token close
Feature activation+0.000
to
Token to
Feature activation+0.000
airing
Token airing
Feature activation+0.000
when
Token when
Feature activation+0.000
this
Token this
Feature activation+0.000
study
Token study
Feature activation+0.000
indicate
Token indicate
Feature activation+0.000
that
Token that
Feature activation+0.000
additional
Token additional
Feature activation+0.000
study
Token study
Feature activation+0.000
is
Token is
Feature activation+0.000
warranted
Token warranted
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
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 H4.0: (feature 12482)

TOP ACTIVATIONS
MAX = 4.104

onia
Tokenonia
Feature activation+0.000
plans
Token plans
Feature activation+0.000
to
Token to
Feature activation+0.000
issue
Token issue
Feature activation+1.960
residents
Token residents
Feature activation+2.689
yellow
Token yellow
Feature activation+4.104
tags
Token tags
Feature activation+2.136
to
Token to
Feature activation+2.104
hang
Token hang
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
that
Token that
Feature activation+0.000
issue
Token issue
Feature activation+2.707
debt
Token debt
Feature activation+2.879
and
Token and
Feature activation+3.237
equity
Token equity
Feature activation+2.182
to
Token to
Feature activation+3.877
the
Token the
Feature activation+0.000
largest
Token largest
Feature activation+0.000
credit
Token credit
Feature activation+0.000
rating
Token rating
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000
House
Token House
Feature activation+0.000
has
Token has
Feature activation+0.000
issued
Token issued
Feature activation+0.743
an
Token an
Feature activation+2.757
obviously
Token obviously
Feature activation+1.379
false
Token false
Feature activation+3.605
,
Token,
Feature activation+0.000
misleading
Token misleading
Feature activation+2.829
and
Token and
Feature activation+0.000
amateur
Token amateur
Feature activation+0.000
ish
Tokenish
Feature activation+0.373
Minister
Token Minister
Feature activation+0.000
Tony
Token Tony
Feature activation+0.000
Abbott
Token Abbott
Feature activation+0.000
issues
Token issues
Feature activation+2.254
the
Token the
Feature activation+2.493
warning
Token warning
Feature activation+3.556
on
Token on
Feature activation+0.491
Wednesday
Token Wednesday
Feature activation+0.000
morning
Token morning
Feature activation+0.000
.
Token.
Feature activation+0.000
Credit
Token Credit
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
regularly
Token regularly
Feature activation+0.000
issues
Token issues
Feature activation+3.504
election
Token election
Feature activation+1.136
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.218
guidance
Token guidance
Feature activation+3.012
on
Token on
Feature activation+2.238
-
Token-
Feature activation+0.000
S
TokenS
Feature activation+0.000
isi
Tokenisi
Feature activation+0.000
may
Token may
Feature activation+0.000
issue
Token issue
Feature activation+2.669
a
Token a
Feature activation+3.480
presidential
Token presidential
Feature activation+3.045
pardon
Token pardon
Feature activation+0.699
,
Token,
Feature activation+0.161
but
Token but
Feature activation+0.000
he
Token he
Feature activation+0.000
failed
Token failed
Feature activation+0.000
to
Token to
Feature activation+0.000
issue
Token issue
Feature activation+2.328
the
Token the
Feature activation+3.278
EC
Token EC
Feature activation+2.211
with
Token with
Feature activation+3.373
precise
Token precise
Feature activation+0.000
figures
Token figures
Feature activation+0.000
documenting
Token documenting
Feature activation+0.000
an
Token an
Feature activation+0.000
annual
Token annual
Feature activation+0.000
government
Token government
Feature activation+0.000
has
Token has
Feature activation+0.000
failed
Token failed
Feature activation+0.000
to
Token to
Feature activation+0.000
issue
Token issue
Feature activation+2.328
the
Token the
Feature activation+3.278
EC
Token EC
Feature activation+2.211
with
Token with
Feature activation+3.373
precise
Token precise
Feature activation+0.000
figures
Token figures
Feature activation+0.000
documenting
Token documenting
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.000
issued
Token issued
Feature activation+0.198
lawmakers
Token lawmakers
Feature activation+2.046
an
Token an
Feature activation+3.258
ult
Token ult
Feature activation+0.000
im
Tokenim
Feature activation+0.000
atum
Tokenatum
Feature activation+0.364
Thursday
Token Thursday
Feature activation+0.000
night
Token night
Feature activation+0.000
from
Token from
Feature activation+0.000
companies
Token companies
Feature activation+0.000
that
Token that
Feature activation+0.000
issue
Token issue
Feature activation+2.707
debt
Token debt
Feature activation+2.879
and
Token and
Feature activation+3.237
equity
Token equity
Feature activation+2.182
to
Token to
Feature activation+3.877
the
Token the
Feature activation+0.000
largest
Token largest
Feature activation+0.000
credit
Token credit
Feature activation+0.000
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000
approve
Token approve
Feature activation+0.000
and
Token and
Feature activation+0.000
issue
Token issue
Feature activation+1.818
a
Token a
Feature activation+3.198
statement
Token statement
Feature activation+2.887
condemning
Token condemning
Feature activation+0.000
the
Token the
Feature activation+0.000
blacklist
Token blacklist
Feature activation+0.000
ing
Tokening
Feature activation+0.000
data
Token data
Feature activation+0.000
streams
Token streams
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
issuance
Token issuance
Feature activation+0.000
of
Token of
Feature activation+3.191
secret
Token secret
Feature activation+3.072
warrants
Token warrants
Feature activation+1.657
,
Token,
Feature activation+0.181
a
Token a
Feature activation+0.000
practice
Token practice
Feature activation+0.000
streams
Token streams
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
issuance
Token issuance
Feature activation+0.000
of
Token of
Feature activation+3.191
secret
Token secret
Feature activation+3.072
warrants
Token warrants
Feature activation+1.657
,
Token,
Feature activation+0.181
a
Token a
Feature activation+0.000
practice
Token practice
Feature activation+0.000
currently
Token currently
Feature activation+0.000
S
TokenS
Feature activation+0.000
isi
Tokenisi
Feature activation+0.000
may
Token may
Feature activation+0.000
issue
Token issue
Feature activation+2.669
a
Token a
Feature activation+3.480
presidential
Token presidential
Feature activation+3.045
pardon
Token pardon
Feature activation+0.699
,
Token,
Feature activation+0.161
but
Token but
Feature activation+0.000
he
Token he
Feature activation+0.000
maintains
Token maintains
Feature activation+0.000
regularly
Token regularly
Feature activation+0.000
issues
Token issues
Feature activation+3.504
election
Token election
Feature activation+1.136
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.218
guidance
Token guidance
Feature activation+3.012
on
Token on
Feature activation+2.238
political
Token political
Feature activation+0.000
activity
Token activity
Feature activation+0.000
for
Token for
Feature activation+0.280
service
Token service
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
foundation
Token foundation
Feature activation+0.000
issued
Token issued
Feature activation+0.000
grants
Token grants
Feature activation+2.956
totaling
Token totaling
Feature activation+0.958
$
Token $
Feature activation+0.000
3
Token3
Feature activation+0.000
.
Token.
Feature activation+0.000
6
Token6
Feature activation+0.000
the
Token the
Feature activation+0.000
door
Token door
Feature activation+0.000
open
Token open
Feature activation+0.000
to
Token to
Feature activation+0.000
issuing
Token issuing
Feature activation+0.000
them
Token them
Feature activation+2.928
unilaterally
Token unilaterally
Feature activation+2.013
âĢĶ
Token âĢĶ
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
say
Token say
Feature activation+0.000
they
Token they
Feature activation+0.000
to
Token to
Feature activation+0.000
approve
Token approve
Feature activation+0.000
and
Token and
Feature activation+0.000
issue
Token issue
Feature activation+1.818
a
Token a
Feature activation+3.198
statement
Token statement
Feature activation+2.887
condemning
Token condemning
Feature activation+0.000
the
Token the
Feature activation+0.000
blacklist
Token blacklist
Feature activation+0.000
ing
Tokening
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
companies
Token companies
Feature activation+0.000
that
Token that
Feature activation+0.000
issue
Token issue
Feature activation+2.707
debt
Token debt
Feature activation+2.879
and
Token and
Feature activation+3.237
equity
Token equity
Feature activation+2.182
to
Token to
Feature activation+3.877
the
Token the
Feature activation+0.000
largest
Token largest
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.000
issued
Token issued
Feature activation+0.506
the
Token the
Feature activation+2.877
findings
Token findings
Feature activation+1.854
of
Token of
Feature activation+1.919
his
Token his
Feature activation+0.000
#
Token #
Feature activation+0.000
Design
TokenDesign
Feature activation+0.000

Top DFA by src position
MAX = 5.470

Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Le
TokenLe
Feature activation-0.000
Top resid features:
onia
Tokenonia
Feature activation+0.005
Top resid features:
plans
Token plans
Feature activation-0.035
Top resid features:
to
Token to
Feature activation-0.084
Top resid features:
issue
Token issue
Feature activation+5.470
Top resid features:
residents
Token residents
Feature activation-0.064
Top resid features:
yellow
Token yellow
Feature activation-0.312
Top resid features:
tags
Token tags
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
hang
Token hang
Feature activation+0.000
Top resid features:
chain
Token chain
Feature activation-0.017
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
from
Token from
Feature activation-0.126
Top resid features:
companies
Token companies
Feature activation+0.001
Top resid features:
that
Token that
Feature activation-0.016
Top resid features:
issue
Token issue
Feature activation+5.311
Top resid features:
debt
Token debt
Feature activation+0.098
Top resid features:
and
Token and
Feature activation+0.037
Top resid features:
equity
Token equity
Feature activation-0.162
Top resid features:
to
Token to
Feature activation-0.392
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
where
Token where
Feature activation+0.014
Top resid features:
the
Token the
Feature activation-0.020
Top resid features:
White
Token White
Feature activation+0.019
Top resid features:
House
Token House
Feature activation-0.033
Top resid features:
has
Token has
Feature activation+0.068
Top resid features:
issued
Token issued
Feature activation+4.399
Top resid features:
an
Token an
Feature activation+0.032
Top resid features:
obviously
Token obviously
Feature activation+0.236
Top resid features:
false
Token false
Feature activation-0.144
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
misleading
Token misleading
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.004
Top resid features:
Prime
TokenPrime
Feature activation+0.009
Top resid features:
Minister
Token Minister
Feature activation+0.021
Top resid features:
Tony
Token Tony
Feature activation+0.013
Top resid features:
Abbott
Token Abbott
Feature activation+0.031
Top resid features:
issues
Token issues
Feature activation+4.985
Top resid features:
the
Token the
Feature activation-0.298
Top resid features:
warning
Token warning
Feature activation-0.274
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Wednesday
Token Wednesday
Feature activation+0.000
Top resid features:
morning
Token morning
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.040
Top resid features:
Ċ
TokenĊ
Feature activation-0.040
Top resid features:
The
TokenThe
Feature activation-0.007
Top resid features:
Pentagon
Token Pentagon
Feature activation+0.130
Top resid features:
regularly
Token regularly
Feature activation-0.152
Top resid features:
issues
Token issues
Feature activation+4.551
Top resid features:
election
Token election
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
year
Tokenyear
Feature activation+0.000
Top resid features:
guidance
Token guidance
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
el
Token el
Feature activation+0.007
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
S
TokenS
Feature activation+0.009
Top resid features:
isi
Tokenisi
Feature activation+0.041
Top resid features:
may
Token may
Feature activation-0.129
Top resid features:
issue
Token issue
Feature activation+4.914
Top resid features:
a
Token a
Feature activation-0.331
Top resid features:
presidential
Token presidential
Feature activation+0.000
Top resid features:
pardon
Token pardon
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
British
Token British
Feature activation+0.006
Top resid features:
government
Token government
Feature activation+0.004
Top resid features:
has
Token has
Feature activation+0.019
Top resid features:
failed
Token failed
Feature activation-0.036
Top resid features:
to
Token to
Feature activation-0.121
Top resid features:
issue
Token issue
Feature activation+4.541
Top resid features:
the
Token the
Feature activation+0.128
Top resid features:
EC
Token EC
Feature activation-0.231
Top resid features:
with
Token with
Feature activation-0.002
Top resid features:
precise
Token precise
Feature activation+0.000
Top resid features:
figures
Token figures
Feature activation+0.000
Top resid features:
British
Token British
Feature activation+0.019
Top resid features:
government
Token government
Feature activation+0.005
Top resid features:
has
Token has
Feature activation+0.032
Top resid features:
failed
Token failed
Feature activation+0.007
Top resid features:
to
Token to
Feature activation-0.147
Top resid features:
issue
Token issue
Feature activation+4.908
Top resid features:
the
Token the
Feature activation-0.495
Top resid features:
EC
Token EC
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
precise
Token precise
Feature activation+0.000
Top resid features:
figures
Token figures
Feature activation+0.000
Top resid features:
week
Token week
Feature activation+0.001
Top resid features:
:
Token:
Feature activation+0.052
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Trump
TokenTrump
Feature activation+0.028
Top resid features:
issued
Token issued
Feature activation+4.465
Top resid features:
lawmakers
Token lawmakers
Feature activation-0.122
Top resid features:
an
Token an
Feature activation-0.222
Top resid features:
ult
Token ult
Feature activation+0.000
Top resid features:
im
Tokenim
Feature activation+0.000
Top resid features:
atum
Tokenatum
Feature activation+0.000
Top resid features:
chain
Token chain
Feature activation-0.022
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
from
Token from
Feature activation+0.076
Top resid features:
companies
Token companies
Feature activation-0.035
Top resid features:
that
Token that
Feature activation-0.028
Top resid features:
issue
Token issue
Feature activation+4.603
Top resid features:
debt
Token debt
Feature activation-0.306
Top resid features:
and
Token and
Feature activation-0.103
Top resid features:
equity
Token equity
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
clerics
Token clerics
Feature activation-0.003
Top resid features:
was
Token was
Feature activation+0.012
Top resid features:
to
Token to
Feature activation+0.022
Top resid features:
approve
Token approve
Feature activation-0.021
Top resid features:
and
Token and
Feature activation-0.092
Top resid features:
issue
Token issue
Feature activation+4.958
Top resid features:
a
Token a
Feature activation-0.541
Top resid features:
statement
Token statement
Feature activation+0.000
Top resid features:
condemning
Token condemning
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
blacklist
Token blacklist
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.048
Top resid features:
data
Token data
Feature activation+0.015
Top resid features:
streams
Token streams
Feature activation-0.010
Top resid features:
through
Token through
Feature activation-0.121
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
issuance
Token issuance
Feature activation+4.839
Top resid features:
of
Token of
Feature activation-0.519
Top resid features:
secret
Token secret
Feature activation+0.000
Top resid features:
warrants
Token warrants
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
their
Token their
Feature activation-0.042
Top resid features:
data
Token data
Feature activation-0.019
Top resid features:
streams
Token streams
Feature activation-0.024
Top resid features:
through
Token through
Feature activation-0.156
Top resid features:
the
Token the
Feature activation-0.075
Top resid features:
issuance
Token issuance
Feature activation+4.916
Top resid features:
of
Token of
Feature activation-0.401
Top resid features:
secret
Token secret
Feature activation-0.180
Top resid features:
warrants
Token warrants
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
el
Token el
Feature activation-0.001
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
S
TokenS
Feature activation+0.007
Top resid features:
isi
Tokenisi
Feature activation+0.024
Top resid features:
may
Token may
Feature activation-0.123
Top resid features:
issue
Token issue
Feature activation+4.698
Top resid features:
a
Token a
Feature activation-0.271
Top resid features:
presidential
Token presidential
Feature activation-0.278
Top resid features:
pardon
Token pardon
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.020
Top resid features:
Ċ
TokenĊ
Feature activation-0.011
Top resid features:
The
TokenThe
Feature activation+0.001
Top resid features:
Pentagon
Token Pentagon
Feature activation+0.035
Top resid features:
regularly
Token regularly
Feature activation-0.294
Top resid features:
issues
Token issues
Feature activation+4.500
Top resid features:
election
Token election
Feature activation+0.107
Top resid features:
-
Token-
Feature activation+0.043
Top resid features:
year
Tokenyear
Feature activation-0.229
Top resid features:
guidance
Token guidance
Feature activation-0.255
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
taxes
Token taxes
Feature activation+0.116
Top resid features:
,
Token,
Feature activation+0.034
Top resid features:
while
Token while
Feature activation-0.032
Top resid features:
the
Token the
Feature activation-0.036
Top resid features:
foundation
Token foundation
Feature activation-0.086
Top resid features:
issued
Token issued
Feature activation+3.949
Top resid features:
grants
Token grants
Feature activation-0.197
Top resid features:
totaling
Token totaling
Feature activation+0.000
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
3
Token3
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
keeping
Token keeping
Feature activation-0.047
Top resid features:
the
Token the
Feature activation-0.149
Top resid features:
door
Token door
Feature activation-0.052
Top resid features:
open
Token open
Feature activation-0.018
Top resid features:
to
Token to
Feature activation-0.068
Top resid features:
issuing
Token issuing
Feature activation+4.526
Top resid features:
them
Token them
Feature activation-0.243
Top resid features:
unilaterally
Token unilaterally
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
Republicans
Token Republicans
Feature activation+0.000
Top resid features:
say
Token say
Feature activation+0.000
Top resid features:
clerics
Token clerics
Feature activation+0.004
Top resid features:
was
Token was
Feature activation+0.007
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
approve
Token approve
Feature activation+0.123
Top resid features:
and
Token and
Feature activation-0.046
Top resid features:
issue
Token issue
Feature activation+4.496
Top resid features:
a
Token a
Feature activation-0.405
Top resid features:
statement
Token statement
Feature activation-0.192
Top resid features:
condemning
Token condemning
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
blacklist
Token blacklist
Feature activation+0.000
Top resid features:
chain
Token chain
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
from
Token from
Feature activation+0.015
Top resid features:
companies
Token companies
Feature activation-0.189
Top resid features:
that
Token that
Feature activation-0.079
Top resid features:
issue
Token issue
Feature activation+4.293
Top resid features:
debt
Token debt
Feature activation-0.203
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
equity
Token equity
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
where
Token where
Feature activation-0.101
Top resid features:
he
Token he
Feature activation-0.052
Top resid features:
issued
Token issued
Feature activation+4.393
Top resid features:
the
Token the
Feature activation-0.358
Top resid features:
findings
Token findings
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
#
Token #
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.49

Head 1: 0.03

Head 2: 0.03

Head 3: 0.05

Head 4: 0.04

Head 5: 0.04

Head 6: 0.06

Head 7: 0.09

Head 8: 0.02

Head 9: 0.06

Head 10: 0.02

Head 11: 0.08

Positive logits

licences1.46

apology1.37

licenses1.36

warranties1.34

certificates1.30

license1.29

refunds1.26

vouchers1.25

supplemental1.25

スト1.24

summary1.18

showc1.18

demand1.14

instructions1.13

passes1.12

ilts1.12

exclusive1.11

licence1.11

unilaterally1.11

compulsory1.10

Negative logits

uncture-1.40

ulhu-1.39

obos-1.35

quickShipAvailable-1.29

ife-1.25

natureconservancy-1.25

cluded-1.17

eleph-1.17

ources-1.16

brut-1.15

onge-1.13

isans-1.13

itty-1.10

occurrences-1.09

abby-1.09

artney-1.08

ategory-1.07

rities-1.07

earchers-1.06

jung-1.05

INTERVAL 3.694 - 4.104
CONTAINS 0.000%

onia
Tokenonia
Feature activation+0.000
plans
Token plans
Feature activation+0.000
to
Token to
Feature activation+0.000
issue
Token issue
Feature activation+1.960
residents
Token residents
Feature activation+2.689
yellow
Token yellow
Feature activation+4.104
tags
Token tags
Feature activation+2.136
to
Token to
Feature activation+2.104
hang
Token hang
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
that
Token that
Feature activation+0.000
issue
Token issue
Feature activation+2.707
debt
Token debt
Feature activation+2.879
and
Token and
Feature activation+3.237
equity
Token equity
Feature activation+2.182
to
Token to
Feature activation+3.877
the
Token the
Feature activation+0.000
largest
Token largest
Feature activation+0.000
credit
Token credit
Feature activation+0.000
rating
Token rating
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000

INTERVAL 3.283 - 3.694
CONTAINS 0.001%

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
regularly
Token regularly
Feature activation+0.000
issues
Token issues
Feature activation+3.504
election
Token election
Feature activation+1.136
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.218
guidance
Token guidance
Feature activation+3.012
on
Token on
Feature activation+2.238
House
Token House
Feature activation+0.000
has
Token has
Feature activation+0.000
issued
Token issued
Feature activation+0.743
an
Token an
Feature activation+2.757
obviously
Token obviously
Feature activation+1.379
false
Token false
Feature activation+3.605
,
Token,
Feature activation+0.000
misleading
Token misleading
Feature activation+2.829
and
Token and
Feature activation+0.000
amateur
Token amateur
Feature activation+0.000
ish
Tokenish
Feature activation+0.373
failed
Token failed
Feature activation+0.000
to
Token to
Feature activation+0.000
issue
Token issue
Feature activation+2.328
the
Token the
Feature activation+3.278
EC
Token EC
Feature activation+2.211
with
Token with
Feature activation+3.373
precise
Token precise
Feature activation+0.000
figures
Token figures
Feature activation+0.000
documenting
Token documenting
Feature activation+0.000
an
Token an
Feature activation+0.000
annual
Token annual
Feature activation+0.000
-
Token-
Feature activation+0.000
S
TokenS
Feature activation+0.000
isi
Tokenisi
Feature activation+0.000
may
Token may
Feature activation+0.000
issue
Token issue
Feature activation+2.669
a
Token a
Feature activation+3.480
presidential
Token presidential
Feature activation+3.045
pardon
Token pardon
Feature activation+0.699
,
Token,
Feature activation+0.161
but
Token but
Feature activation+0.000
he
Token he
Feature activation+0.000
Minister
Token Minister
Feature activation+0.000
Tony
Token Tony
Feature activation+0.000
Abbott
Token Abbott
Feature activation+0.000
issues
Token issues
Feature activation+2.254
the
Token the
Feature activation+2.493
warning
Token warning
Feature activation+3.556
on
Token on
Feature activation+0.491
Wednesday
Token Wednesday
Feature activation+0.000
morning
Token morning
Feature activation+0.000
.
Token.
Feature activation+0.000
Credit
Token Credit
Feature activation+0.000

INTERVAL 2.873 - 3.283
CONTAINS 0.001%

streams
Token streams
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
issuance
Token issuance
Feature activation+0.000
of
Token of
Feature activation+3.191
secret
Token secret
Feature activation+3.072
warrants
Token warrants
Feature activation+1.657
,
Token,
Feature activation+0.181
a
Token a
Feature activation+0.000
practice
Token practice
Feature activation+0.000
currently
Token currently
Feature activation+0.000
government
Token government
Feature activation+0.000
has
Token has
Feature activation+0.000
failed
Token failed
Feature activation+0.000
to
Token to
Feature activation+0.000
issue
Token issue
Feature activation+2.328
the
Token the
Feature activation+3.278
EC
Token EC
Feature activation+2.211
with
Token with
Feature activation+3.373
precise
Token precise
Feature activation+0.000
figures
Token figures
Feature activation+0.000
documenting
Token documenting
Feature activation+0.000
the
Token the
Feature activation+0.000
door
Token door
Feature activation+0.000
open
Token open
Feature activation+0.000
to
Token to
Feature activation+0.000
issuing
Token issuing
Feature activation+0.000
them
Token them
Feature activation+2.928
unilaterally
Token unilaterally
Feature activation+2.013
âĢĶ
Token âĢĶ
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
say
Token say
Feature activation+0.000
they
Token they
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.000
issued
Token issued
Feature activation+0.198
lawmakers
Token lawmakers
Feature activation+2.046
an
Token an
Feature activation+3.258
ult
Token ult
Feature activation+0.000
im
Tokenim
Feature activation+0.000
atum
Tokenatum
Feature activation+0.364
Thursday
Token Thursday
Feature activation+0.000
night
Token night
Feature activation+0.000
S
TokenS
Feature activation+0.000
isi
Tokenisi
Feature activation+0.000
may
Token may
Feature activation+0.000
issue
Token issue
Feature activation+2.669
a
Token a
Feature activation+3.480
presidential
Token presidential
Feature activation+3.045
pardon
Token pardon
Feature activation+0.699
,
Token,
Feature activation+0.161
but
Token but
Feature activation+0.000
he
Token he
Feature activation+0.000
maintains
Token maintains
Feature activation+0.000

INTERVAL 2.462 - 2.873
CONTAINS 0.002%

is
Token is
Feature activation+0.000
preparing
Token preparing
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000
issuing
Token issuing
Feature activation+0.575
a
Token a
Feature activation+2.734
design
Token design
Feature activation+2.534
/
Token/
Feature activation+0.000
build
Tokenbuild
Feature activation+0.975
R
Token R
Feature activation+0.742
FP
TokenFP
Feature activation+1.918
Prime
TokenPrime
Feature activation+0.000
Minister
Token Minister
Feature activation+0.000
Tony
Token Tony
Feature activation+0.000
Abbott
Token Abbott
Feature activation+0.000
issues
Token issues
Feature activation+2.254
the
Token the
Feature activation+2.493
warning
Token warning
Feature activation+3.556
on
Token on
Feature activation+0.491
Wednesday
Token Wednesday
Feature activation+0.000
morning
Token morning
Feature activation+0.000
.
Token.
Feature activation+0.000
wrapper
Token wrapper
Feature activation+0.000
to
Token to
Feature activation+0.000
issue
Token issue
Feature activation+1.486
simple
Token simple
Feature activation+2.383
API
Token API
Feature activation+2.127
queries
Token queries
Feature activation+2.520
can
Token can
Feature activation+0.390
be
Token be
Feature activation+0.000
found
Token found
Feature activation+0.000
on
Token on
Feature activation+0.000
our
Token our
Feature activation+0.000
Franc
TokenFranc
Feature activation+0.000
is
Tokenis
Feature activation+0.000
has
Token has
Feature activation+0.000
already
Token already
Feature activation+0.000
issued
Token issued
Feature activation+0.851
an
Token an
Feature activation+2.674
apology
Token apology
Feature activation+1.223
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Catholic
Token Catholic
Feature activation+0.000
church
Token church
Feature activation+0.000
German
Token German
Feature activation+0.000
government
Token government
Feature activation+0.000
to
Token to
Feature activation+0.000
issue
Token issue
Feature activation+2.503
a
Token a
Feature activation+2.262
warning
Token warning
Feature activation+2.514
about
Token about
Feature activation+0.684
Firefox
Token Firefox
Feature activation+0.000
3
Token 3
Feature activation+0.000
.
Token.
Feature activation+0.000
6
Token6
Feature activation+0.000

INTERVAL 2.052 - 2.462
CONTAINS 0.003%

issued
Token issued
Feature activation+0.000
a
Token a
Feature activation+0.507
slew
Token slew
Feature activation+0.804
of
Token of
Feature activation+2.435
subpoen
Token subpoen
Feature activation+0.283
as
Tokenas
Feature activation+2.251
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
sign
Token sign
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Prime
TokenPrime
Feature activation+0.000
Minister
Token Minister
Feature activation+0.000
Tony
Token Tony
Feature activation+0.000
Abbott
Token Abbott
Feature activation+0.000
issues
Token issues
Feature activation+2.254
the
Token the
Feature activation+2.493
warning
Token warning
Feature activation+3.556
on
Token on
Feature activation+0.491
Wednesday
Token Wednesday
Feature activation+0.000
morning
Token morning
Feature activation+0.000
the
Token the
Feature activation+0.000
initial
Token initial
Feature activation+0.000
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
issue
Token issue
Feature activation+0.837
a
Token a
Feature activation+2.457
20
Token 20
Feature activation+0.631
-
Token-
Feature activation+0.000
day
Tokenday
Feature activation+0.405
visa
Token visa
Feature activation+0.000
to
Token to
Feature activation+0.542
environment
Token environment
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
had
Token had
Feature activation+0.000
issued
Token issued
Feature activation+0.309
a
Token a
Feature activation+1.559
draft
Token draft
Feature activation+2.233
notification
Token notification
Feature activation+0.824
,
Token,
Feature activation+0.506
identifying
Token identifying
Feature activation+0.000
60
Token 60
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
issue
Token issue
Feature activation+1.960
residents
Token residents
Feature activation+2.689
yellow
Token yellow
Feature activation+4.104
tags
Token tags
Feature activation+2.136
to
Token to
Feature activation+2.104
hang
Token hang
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
cars
Token cars
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.642 - 2.052
CONTAINS 0.004%

after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
Harper
Token Harper
Feature activation+0.000
government
Token government
Feature activation+0.000
issued
Token issued
Feature activation+0.310
a
Token a
Feature activation+1.770
legal
Token legal
Feature activation+1.782
threat
Token threat
Feature activation+1.097
over
Token over
Feature activation+0.025
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
]
Token]
Feature activation+0.000
CB
Token CB
Feature activation+0.000
SA
TokenSA
Feature activation+0.000
issued
Token issued
Feature activation+0.400
us
Token us
Feature activation+1.818
authorization
Token authorization
Feature activation+0.000
to
Token to
Feature activation+0.000
import
Token import
Feature activation+0.000
products
Token products
Feature activation+0.000
duty
Token duty
Feature activation+0.000
.
Token.
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
even
Token even
Feature activation+0.000
issued
Token issued
Feature activation+0.000
$
Token $
Feature activation+1.779
17
Token17
Feature activation+1.842
billion
Token billion
Feature activation+1.997
in
Token in
Feature activation+2.812
debt
Token debt
Feature activation+2.248
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
bugs
Token bugs
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
L
TokenL
Feature activation+0.000
ank
Tokenank
Feature activation+0.000
ford
Tokenford
Feature activation+0.000
issues
Token issues
Feature activation+1.839
statement
Token statement
Feature activation+2.753
of
Token of
Feature activation+2.769
support
Token support
Feature activation+0.000
following
Token following
Feature activation+0.000
President
Token President
Feature activation+0.000
in
Token in
Feature activation+0.000
N
Token N
Feature activation+0.000
airo
Tokenairo
Feature activation+0.000
bi
Tokenbi
Feature activation+0.000
issued
Token issued
Feature activation+0.272
her
Token her
Feature activation+1.946
a
Token a
Feature activation+2.392
new
Token new
Feature activation+2.425
passport
Token passport
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.231 - 1.642
CONTAINS 0.004%

Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
Python
Token Python
Feature activation+0.000
wrapper
Token wrapper
Feature activation+0.000
to
Token to
Feature activation+0.000
issue
Token issue
Feature activation+1.486
simple
Token simple
Feature activation+2.383
API
Token API
Feature activation+2.127
queries
Token queries
Feature activation+2.520
can
Token can
Feature activation+0.390
be
Token be
Feature activation+0.000
h
Token h
Feature activation+0.000
ives
Tokenives
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
issued
Token issued
Feature activation+0.325
fines
Token fines
Feature activation+1.347
to
Token to
Feature activation+1.476
some
Token some
Feature activation+0.000
viol
Token viol
Feature activation+0.000
ators
Tokenators
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
issued
Token issued
Feature activation+0.032
a
Token a
Feature activation+1.475
waiver
Token waiver
Feature activation+1.292
for
Token for
Feature activation+0.000
South
Token South
Feature activation+0.000
Sudan
Token Sudan
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+0.000
has
Token has
Feature activation+0.000
just
Token just
Feature activation+0.000
issued
Token issued
Feature activation+0.603
its
Token its
Feature activation+1.541
long
Token long
Feature activation+2.278
-
Token-
Feature activation+0.000
awaited
Tokenawaited
Feature activation+2.733
judgment
Token judgment
Feature activation+0.337
in
Token in
Feature activation+0.000
issue
Token issue
Feature activation+1.014
a
Token a
Feature activation+2.527
statement
Token statement
Feature activation+2.092
of
Token of
Feature activation+0.000
regret
Token regret
Feature activation+0.000
and
Token and
Feature activation+1.339
award
Token award
Feature activation+0.000
compensation
Token compensation
Feature activation+0.000
of
Token of
Feature activation+0.000
£
Token £
Feature activation+0.000
19
Token19
Feature activation+0.000

INTERVAL 0.821 - 1.231
CONTAINS 0.003%

the
Token the
Feature activation+0.000
issue
Token issue
Feature activation+0.000
which
Token which
Feature activation+0.000
issued
Token issued
Feature activation+0.000
a
Token a
Feature activation+2.313
report
Token report
Feature activation+1.088
during
Token during
Feature activation+0.000
January
Token January
Feature activation+0.000
1959
Token 1959
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
Federal
Token Federal
Feature activation+0.000
Aviation
Token Aviation
Feature activation+0.000
Administration
Token Administration
Feature activation+0.000
also
Token also
Feature activation+0.000
issued
Token issued
Feature activation+0.824
a
Token a
Feature activation+1.088
temporary
Token temporary
Feature activation+1.299
no
Token no
Feature activation+0.000
-
Token-
Feature activation+0.000
fly
Tokenfly
Feature activation+0.000
zone
Token zone
Feature activation+0.242
British
Token British
Feature activation+0.000
agreement
Token agreement
Feature activation+0.000
in
Token in
Feature activation+0.000
June
Token June
Feature activation+0.000
to
Token to
Feature activation+0.000
issue
Token issue
Feature activation+1.014
a
Token a
Feature activation+2.527
statement
Token statement
Feature activation+2.092
of
Token of
Feature activation+0.000
regret
Token regret
Feature activation+0.000
and
Token and
Feature activation+1.339
the
Token the
Feature activation+0.000
production
Token production
Feature activation+0.000
of
Token of
Feature activation+0.000
everything
Token everything
Feature activation+0.000
from
Token from
Feature activation+0.021
armored
Token armored
Feature activation+0.876
vehicles
Token vehicles
Feature activation+0.364
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
somewhat
Token somewhat
Feature activation+0.000
notorious
Token notorious
Feature activation+0.000
Harper
Token Harper
Feature activation+0.000
government
Token government
Feature activation+0.000
issued
Token issued
Feature activation+0.310
a
Token a
Feature activation+1.770
legal
Token legal
Feature activation+1.782
threat
Token threat
Feature activation+1.097
over
Token over
Feature activation+0.025
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
's
Token's
Feature activation+0.000
plan
Token plan
Feature activation+0.000

INTERVAL 0.410 - 0.821
CONTAINS 0.006%

a
Token a
Feature activation+1.271
rare
Token rare
Feature activation+1.537
worldwide
Token worldwide
Feature activation+1.316
travel
Token travel
Feature activation+0.239
alert
Token alert
Feature activation+0.800
on
Token on
Feature activation+0.463
Monday
Token Monday
Feature activation+0.000
,
Token,
Feature activation+0.000
warning
Token warning
Feature activation+0.000
American
Token American
Feature activation+0.000
travelers
Token travelers
Feature activation+0.000
Federal
Token Federal
Feature activation+0.000
Aviation
Token Aviation
Feature activation+0.000
Administration
Token Administration
Feature activation+0.000
issued
Token issued
Feature activation+0.000
a
Token a
Feature activation+0.598
"
Token "
Feature activation+0.819
special
Tokenspecial
Feature activation+2.087
notice
Token notice
Feature activation+0.475
"
Token"
Feature activation+0.507
regarding
Token regarding
Feature activation+0.000
Ukrainian
Token Ukrainian
Feature activation+0.000
pol
Tokenpol
Feature activation+0.000
issued
Token issued
Feature activation+0.000
a
Token a
Feature activation+1.187
Red
Token Red
Feature activation+0.000
Notice
Token Notice
Feature activation+0.572
wanted
Token wanted
Feature activation+0.600
-
Token-
Feature activation+0.000
pers
Tokenpers
Feature activation+0.000
ons
Tokenons
Feature activation+0.000
alert
Token alert
Feature activation+0.645
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.000
Shelby
Token Shelby
Feature activation+0.000
fired
Token fired
Feature activation+0.000
the
Token the
Feature activation+0.000
fatal
Token fatal
Feature activation+0.000
shot
Token shot
Feature activation+0.614
soon
Token soon
Feature activation+0.000
afterward
Token afterward
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
god
Token god
Feature activation+0.000
of
Token of
Feature activation+0.000
medicine
Token medicine
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
issued
Tokenissued
Feature activation+0.972
this
Token this
Feature activation+0.598
statement
Token statement
Feature activation+0.366
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000

INTERVAL 0.000 - 0.410
CONTAINS 99.976%

orn
Tokenorn
Feature activation+0.000
Lawrence
Token Lawrence
Feature activation+0.000
and
Token and
Feature activation+0.000
Mary
Token Mary
Feature activation+0.000
Jane
Token Jane
Feature activation+0.000
B
Token B
Feature activation+0.000
edd
Tokenedd
Feature activation+0.000
all
Tokenall
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
park
Token park
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
oldest
Token oldest
Feature activation+0.000
existing
Token existing
Feature activation+0.000
parliament
Token parliament
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
,
Token,
Feature activation+0.000
first
Token first
Feature activation+0.000
touchdowns
Token touchdowns
Feature activation+0.000
.
Token.
Feature activation+0.000
Too
Token Too
Feature activation+0.000
bad
Token bad
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
four
Token four
Feature activation+0.000
years
Token years
Feature activation+0.000
ago
Token ago
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ales
Tokenales
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
companions
Token companions
Feature activation+0.000
find
Token find
Feature activation+0.000
the
Token the
Feature activation+0.000
abandoned
Token abandoned
Feature activation+0.000
ranch
Token ranch
Feature activation+0.000
owned
Token owned
Feature activation+0.000
by
Token by
Feature activation+0.000
Tom
Token Tom
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Honda
Token Honda
Feature activation+0.000
CR
Token CR
Feature activation+0.000
750
Token750
Feature activation+0.000
race
Token race
Feature activation+0.000
bike
Tokenbike
Feature activation+0.000
,
Token,
Feature activation+0.000
Honda
Token Honda
Feature activation+0.000
released
Token released
Feature activation+0.000
the
Token the
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 7 in H4.0: (feature 9231)

TOP ACTIVATIONS
MAX = 5.214

conditions
Token conditions
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
the
Token the
Feature activation+4.356
boards
Token boards
Feature activation+3.617
out
Token out
Feature activation+5.214
as
Token as
Feature activation+0.873
Barn
Token Barn
Feature activation+0.000
aby
Tokenaby
Feature activation+0.000
explains
Token explains
Feature activation+0.000
:
Token:
Feature activation+0.000
then
Token then
Feature activation+0.000
let
Token let
Feature activation+0.000
the
Token the
Feature activation+0.000
players
Token players
Feature activation+0.000
try
Token try
Feature activation+0.000
it
Token it
Feature activation+5.023
for
Token for
Feature activation+4.809
real
Token real
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
let
Token let
Feature activation+0.000
the
Token the
Feature activation+0.000
players
Token players
Feature activation+0.000
try
Token try
Feature activation+0.000
it
Token it
Feature activation+5.023
for
Token for
Feature activation+4.809
real
Token real
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Those
TokenThose
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
welcome
Token welcome
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
them
Token them
Feature activation+4.675
,
Token,
Feature activation+1.039
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
North
Token North
Feature activation+0.000
Korean
Token Korean
Feature activation+0.000
designers
Token designers
Feature activation+0.000
tried
Token tried
Feature activation+0.000
their
Token their
Feature activation+3.695
hands
Token hands
Feature activation+4.403
at
Token at
Feature activation+3.401
a
Token a
Feature activation+0.019
Western
Token Western
Feature activation+0.000
-
Token-
Feature activation+0.000
style
Tokenstyle
Feature activation+0.000
are
Token are
Feature activation+0.000
interested
Token interested
Feature activation+0.000
in
Token in
Feature activation+0.000
trying
Token trying
Feature activation+0.000
your
Token your
Feature activation+3.639
hand
Token hand
Feature activation+4.389
at
Token at
Feature activation+1.767
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
design
Token design
Feature activation+0.059
for
Token for
Feature activation+1.147
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
got
Token got
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
this
Token this
Feature activation+4.378
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Its
Token Its
Feature activation+0.000
e
Token e
Feature activation+0.000
set
Token set
Feature activation+0.000
of
Token of
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
the
Token the
Feature activation+4.356
boards
Token boards
Feature activation+3.617
out
Token out
Feature activation+5.214
as
Token as
Feature activation+0.873
Barn
Token Barn
Feature activation+0.000
aby
Tokenaby
Feature activation+0.000
the
Token the
Feature activation+0.000
movie
Token movie
Feature activation+0.000
and
Token and
Feature activation+0.000
try
Token try
Feature activation+0.000
it
Token it
Feature activation+3.536
out
Token out
Feature activation+4.310
yourself
Token yourself
Feature activation+0.526
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Of
TokenOf
Feature activation+0.000
and
Token and
Feature activation+0.000
much
Token much
Feature activation+0.000
more
Token more
Feature activation+0.000
,
Token,
Feature activation+0.000
try
Token try
Feature activation+0.000
an
Token an
Feature activation+4.297
All
Token All
Feature activation+0.484
Access
Token Access
Feature activation+0.000
Digital
Token Digital
Feature activation+0.000
subscription
Token subscription
Feature activation+1.539
:
Token:
Feature activation+0.000
to
Token to
Feature activation+0.000
rush
Token rush
Feature activation+0.000
out
Token out
Feature activation+0.000
and
Token and
Feature activation+0.000
try
Token try
Feature activation+0.000
an
Token an
Feature activation+4.295
experimental
Token experimental
Feature activation+3.953
treatment
Token treatment
Feature activation+3.430
;
Token;
Feature activation+0.000
for
Token for
Feature activation+0.000
you
Token you
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
tried
Token tried
Feature activation+0.000
so
Token so
Feature activation+2.845
many
Token many
Feature activation+4.023
different
Token different
Feature activation+4.149
natural
Token natural
Feature activation+3.275
conco
Token conco
Feature activation+0.128
ctions
Tokenctions
Feature activation+3.295
like
Token like
Feature activation+2.225
fl
Token fl
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
thought
Token thought
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
it
Token it
Feature activation+4.127
as
Token as
Feature activation+3.533
the
Token the
Feature activation+0.000
king
Token king
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
the
Token the
Feature activation+3.677
bra
Token bra
Feature activation+1.133
on
Token on
Feature activation+4.097
again
Token again
Feature activation+0.000
at
Token at
Feature activation+0.931
this
Token this
Feature activation+0.000
point
Token point
Feature activation+0.000
to
Token to
Feature activation+0.000
classic
Token classic
Feature activation+0.000
game
Token game
Feature activation+0.000
,
Token,
Feature activation+0.000
now
Token now
Feature activation+0.000
try
Token try
Feature activation+0.000
it
Token it
Feature activation+4.077
with
Token with
Feature activation+3.492
this
Token this
Feature activation+0.000
exciting
Token exciting
Feature activation+0.000
New
Token New
Feature activation+0.000
Twist
Token Twist
Feature activation+0.000
had
Token had
Feature activation+0.000
insisted
Token insisted
Feature activation+0.000
on
Token on
Feature activation+0.000
trying
Token trying
Feature activation+0.000
the
Token the
Feature activation+3.282
case
Token case
Feature activation+4.075
,
Token,
Feature activation+1.978
District
Token District
Feature activation+0.000
Judge
Token Judge
Feature activation+0.000
Ron
Token Ron
Feature activation+0.000
R
Token R
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
w
Tokenw
Feature activation+0.000
illing
Tokenilling
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
other
Token other
Feature activation+4.050
directing
Token directing
Feature activation+0.123
projects
Token projects
Feature activation+3.110
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
tried
Token tried
Feature activation+0.000
so
Token so
Feature activation+2.845
many
Token many
Feature activation+4.023
different
Token different
Feature activation+4.149
natural
Token natural
Feature activation+3.275
conco
Token conco
Feature activation+0.128
ctions
Tokenctions
Feature activation+3.295
like
Token like
Feature activation+2.225
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
try
Token try
Feature activation+0.000
a
Token a
Feature activation+3.995
lot
Token lot
Feature activation+3.371
and
Token and
Feature activation+2.706
we
Token we
Feature activation+0.000
take
Token take
Feature activation+0.000
a
Token a
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
she
Token she
Feature activation+0.000
will
Token will
Feature activation+0.000
try
Token try
Feature activation+0.000
a
Token a
Feature activation+3.982
tactic
Token tactic
Feature activation+3.865
new
Token new
Feature activation+3.731
to
Token to
Feature activation+0.000
federal
Token federal
Feature activation+0.000
trials
Token trials
Feature activation+0.000

Top DFA by src position
MAX = 6.023

specific
Token specific
Feature activation+0.031
Top resid features:
set
Token set
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.017
Top resid features:
conditions
Token conditions
Feature activation+0.007
Top resid features:
to
Token to
Feature activation+0.048
Top resid features:
try
Token try
Feature activation+5.757
Top resid features:
the
Token the
Feature activation+0.078
Top resid features:
boards
Token boards
Feature activation+0.059
Top resid features:
out
Token out
Feature activation+0.308
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Barn
Token Barn
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.026
Top resid features:
then
Token then
Feature activation-0.001
Top resid features:
let
Token let
Feature activation+0.061
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
players
Token players
Feature activation-0.032
Top resid features:
try
Token try
Feature activation+6.023
Top resid features:
it
Token it
Feature activation+0.091
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
real
Token real
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.019
Top resid features:
then
Token then
Feature activation+0.007
Top resid features:
let
Token let
Feature activation+0.061
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
players
Token players
Feature activation-0.010
Top resid features:
try
Token try
Feature activation+5.471
Top resid features:
it
Token it
Feature activation+0.302
Top resid features:
for
Token for
Feature activation+0.136
Top resid features:
real
Token real
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
I
Token I
Feature activation-0.015
Top resid features:
are
Token are
Feature activation-0.014
Top resid features:
not
Token not
Feature activation-0.106
Top resid features:
welcome
Token welcome
Feature activation-0.017
Top resid features:
to
Token to
Feature activation-0.020
Top resid features:
try
Token try
Feature activation+5.806
Top resid features:
them
Token them
Feature activation+0.120
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
don
Token don
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
If
TokenIf
Feature activation-0.011
Top resid features:
North
Token North
Feature activation+0.003
Top resid features:
Korean
Token Korean
Feature activation+0.006
Top resid features:
designers
Token designers
Feature activation-0.018
Top resid features:
tried
Token tried
Feature activation+5.309
Top resid features:
their
Token their
Feature activation+0.259
Top resid features:
hands
Token hands
Feature activation+0.102
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
Western
Token Western
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.017
Top resid features:
you
Token you
Feature activation-0.009
Top resid features:
are
Token are
Feature activation-0.009
Top resid features:
interested
Token interested
Feature activation-0.033
Top resid features:
in
Token in
Feature activation+0.025
Top resid features:
trying
Token trying
Feature activation+5.092
Top resid features:
your
Token your
Feature activation+0.191
Top resid features:
hand
Token hand
Feature activation+0.241
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
3
Token 3
Feature activation+0.000
Top resid features:
D
TokenD
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.024
Top resid features:
Ļ
TokenĻ
Feature activation-0.017
Top resid features:
ve
Tokenve
Feature activation+0.009
Top resid features:
got
Token got
Feature activation-0.080
Top resid features:
to
Token to
Feature activation-0.016
Top resid features:
try
Token try
Feature activation+5.539
Top resid features:
this
Token this
Feature activation+0.179
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
Its
Token Its
Feature activation+0.000
Top resid features:
specific
Token specific
Feature activation+0.041
Top resid features:
set
Token set
Feature activation+0.037
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
conditions
Token conditions
Feature activation+0.017
Top resid features:
to
Token to
Feature activation+0.062
Top resid features:
try
Token try
Feature activation+5.158
Top resid features:
the
Token the
Feature activation+0.181
Top resid features:
boards
Token boards
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Barn
Token Barn
Feature activation+0.000
Top resid features:
so
Token so
Feature activation-0.000
Top resid features:
watch
Token watch
Feature activation-0.115
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
movie
Token movie
Feature activation+0.070
Top resid features:
and
Token and
Feature activation+0.067
Top resid features:
try
Token try
Feature activation+5.112
Top resid features:
it
Token it
Feature activation+0.192
Top resid features:
out
Token out
Feature activation+0.141
Top resid features:
yourself
Token yourself
Feature activation+0.000
Top resid features:
!
Token!
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
news
Token news
Feature activation-0.044
Top resid features:
and
Token and
Feature activation-0.007
Top resid features:
much
Token much
Feature activation+0.028
Top resid features:
more
Token more
Feature activation-0.023
Top resid features:
,
Token,
Feature activation-0.054
Top resid features:
try
Token try
Feature activation+5.298
Top resid features:
an
Token an
Feature activation+0.299
Top resid features:
All
Token All
Feature activation+0.000
Top resid features:
Access
Token Access
Feature activation+0.000
Top resid features:
Digital
Token Digital
Feature activation+0.000
Top resid features:
subscription
Token subscription
Feature activation+0.000
Top resid features:
you
Token you
Feature activation-0.033
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
rush
Token rush
Feature activation+0.013
Top resid features:
out
Token out
Feature activation+0.025
Top resid features:
and
Token and
Feature activation+0.051
Top resid features:
try
Token try
Feature activation+5.200
Top resid features:
an
Token an
Feature activation+0.200
Top resid features:
experimental
Token experimental
Feature activation+0.000
Top resid features:
treatment
Token treatment
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Yet
TokenYet
Feature activation+0.007
Top resid features:
I
Token I
Feature activation+0.013
Top resid features:
âĢ
TokenâĢ
Feature activation-0.007
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
ve
Tokenve
Feature activation+0.001
Top resid features:
tried
Token tried
Feature activation+4.927
Top resid features:
so
Token so
Feature activation-0.022
Top resid features:
many
Token many
Feature activation+0.229
Top resid features:
different
Token different
Feature activation+0.121
Top resid features:
natural
Token natural
Feature activation+0.000
Top resid features:
conco
Token conco
Feature activation+0.000
Top resid features:
so
Token so
Feature activation-0.008
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
I
Token I
Feature activation-0.007
Top resid features:
thought
Token thought
Feature activation+0.024
Top resid features:
to
Token to
Feature activation+0.110
Top resid features:
try
Token try
Feature activation+5.098
Top resid features:
it
Token it
Feature activation+0.116
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
king
Token king
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.002
Top resid features:
you
Token you
Feature activation-0.001
Top resid features:
definitely
Token definitely
Feature activation+0.011
Top resid features:
want
Token want
Feature activation-0.011
Top resid features:
to
Token to
Feature activation+0.028
Top resid features:
try
Token try
Feature activation+4.763
Top resid features:
the
Token the
Feature activation+0.086
Top resid features:
bra
Token bra
Feature activation+0.020
Top resid features:
on
Token on
Feature activation+0.258
Top resid features:
again
Token again
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
classic
Token classic
Feature activation-0.003
Top resid features:
game
Token game
Feature activation-0.020
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
now
Token now
Feature activation-0.004
Top resid features:
try
Token try
Feature activation+5.143
Top resid features:
it
Token it
Feature activation+0.086
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
exciting
Token exciting
Feature activation+0.000
Top resid features:
New
Token New
Feature activation+0.000
Top resid features:
H
TokenH
Feature activation-0.004
Top resid features:
ood
Tokenood
Feature activation-0.007
Top resid features:
had
Token had
Feature activation-0.028
Top resid features:
insisted
Token insisted
Feature activation+0.042
Top resid features:
on
Token on
Feature activation+0.016
Top resid features:
trying
Token trying
Feature activation+4.744
Top resid features:
the
Token the
Feature activation+0.316
Top resid features:
case
Token case
Feature activation+0.156
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
District
Token District
Feature activation+0.000
Top resid features:
Judge
Token Judge
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.010
Top resid features:
ľ
Tokenľ
Feature activation-0.008
Top resid features:
w
Tokenw
Feature activation+0.012
Top resid features:
illing
Tokenilling
Feature activation+0.028
Top resid features:
to
Token to
Feature activation-0.011
Top resid features:
try
Token try
Feature activation+5.075
Top resid features:
other
Token other
Feature activation+0.182
Top resid features:
directing
Token directing
Feature activation+0.000
Top resid features:
projects
Token projects
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Yet
TokenYet
Feature activation+0.005
Top resid features:
I
Token I
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation-0.039
Top resid features:
Ļ
TokenĻ
Feature activation-0.001
Top resid features:
ve
Tokenve
Feature activation-0.027
Top resid features:
tried
Token tried
Feature activation+5.066
Top resid features:
so
Token so
Feature activation+0.148
Top resid features:
many
Token many
Feature activation+0.004
Top resid features:
different
Token different
Feature activation+0.000
Top resid features:
natural
Token natural
Feature activation+0.000
Top resid features:
conco
Token conco
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.020
Top resid features:
Ċ
TokenĊ
Feature activation-0.026
Top resid features:
âĢ
TokenâĢ
Feature activation+0.014
Top resid features:
ľ
Tokenľ
Feature activation-0.003
Top resid features:
We
TokenWe
Feature activation-0.041
Top resid features:
try
Token try
Feature activation+5.190
Top resid features:
a
Token a
Feature activation+0.156
Top resid features:
lot
Token lot
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
take
Token take
Feature activation+0.000
Top resid features:
said
Token said
Feature activation-0.024
Top resid features:
last
Token last
Feature activation-0.008
Top resid features:
week
Token week
Feature activation-0.013
Top resid features:
she
Token she
Feature activation-0.022
Top resid features:
will
Token will
Feature activation-0.004
Top resid features:
try
Token try
Feature activation+5.128
Top resid features:
a
Token a
Feature activation+0.160
Top resid features:
tactic
Token tactic
Feature activation+0.000
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
federal
Token federal
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.49

Head 1: 0.04

Head 2: 0.02

Head 3: 0.04

Head 4: 0.02

Head 5: 0.04

Head 6: 0.04

Head 7: 0.08

Head 8: 0.02

Head 9: 0.06

Head 10: 0.02

Head 11: 0.14

Positive logits

cleaners1.36

unsuccessfully1.35

ihilation1.35

istries1.34

hement1.34

ggles1.33

advoc1.32

pmwiki1.30

mx1.29

compar1.28

remedies1.28

ework1.28

uden1.26

Downloadha1.25

iatrics1.25

unal1.24

utical1.23

harder1.20

ums1.20

alternatives1.16

Negative logits

$$-1.36

Deaths-1.21

iya-1.20

Contribut-1.16

FAT-1.13

Violent-1.12

Printed-1.12

(\-1.11

Occup-1.09

Calories-1.09

Donation-1.08

ensable-1.08

\--1.07

Boxing-1.07

opausal-1.06

<-1.06

Riding-1.05

=~-1.05

IGHT-1.05

Learns-1.05

INTERVAL 4.693 - 5.214
CONTAINS 0.000%

conditions
Token conditions
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
the
Token the
Feature activation+4.356
boards
Token boards
Feature activation+3.617
out
Token out
Feature activation+5.214
as
Token as
Feature activation+0.873
Barn
Token Barn
Feature activation+0.000
aby
Tokenaby
Feature activation+0.000
explains
Token explains
Feature activation+0.000
:
Token:
Feature activation+0.000
then
Token then
Feature activation+0.000
let
Token let
Feature activation+0.000
the
Token the
Feature activation+0.000
players
Token players
Feature activation+0.000
try
Token try
Feature activation+0.000
it
Token it
Feature activation+5.023
for
Token for
Feature activation+4.809
real
Token real
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
let
Token let
Feature activation+0.000
the
Token the
Feature activation+0.000
players
Token players
Feature activation+0.000
try
Token try
Feature activation+0.000
it
Token it
Feature activation+5.023
for
Token for
Feature activation+4.809
real
Token real
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Those
TokenThose
Feature activation+0.000

INTERVAL 4.171 - 4.693
CONTAINS 0.001%

set
Token set
Feature activation+0.000
of
Token of
Feature activation+0.000
conditions
Token conditions
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
the
Token the
Feature activation+4.356
boards
Token boards
Feature activation+3.617
out
Token out
Feature activation+5.214
as
Token as
Feature activation+0.873
Barn
Token Barn
Feature activation+0.000
aby
Tokenaby
Feature activation+0.000
to
Token to
Feature activation+0.000
rush
Token rush
Feature activation+0.000
out
Token out
Feature activation+0.000
and
Token and
Feature activation+0.000
try
Token try
Feature activation+0.000
an
Token an
Feature activation+4.295
experimental
Token experimental
Feature activation+3.953
treatment
Token treatment
Feature activation+3.430
;
Token;
Feature activation+0.000
for
Token for
Feature activation+0.000
you
Token you
Feature activation+0.000
North
Token North
Feature activation+0.000
Korean
Token Korean
Feature activation+0.000
designers
Token designers
Feature activation+0.000
tried
Token tried
Feature activation+0.000
their
Token their
Feature activation+3.695
hands
Token hands
Feature activation+4.403
at
Token at
Feature activation+3.401
a
Token a
Feature activation+0.019
Western
Token Western
Feature activation+0.000
-
Token-
Feature activation+0.000
style
Tokenstyle
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
got
Token got
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
this
Token this
Feature activation+4.378
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Its
Token Its
Feature activation+0.000
e
Token e
Feature activation+0.000
are
Token are
Feature activation+0.000
interested
Token interested
Feature activation+0.000
in
Token in
Feature activation+0.000
trying
Token trying
Feature activation+0.000
your
Token your
Feature activation+3.639
hand
Token hand
Feature activation+4.389
at
Token at
Feature activation+1.767
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
design
Token design
Feature activation+0.059
for
Token for
Feature activation+1.147

INTERVAL 3.650 - 4.171
CONTAINS 0.002%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
tried
Token tried
Feature activation+0.000
so
Token so
Feature activation+2.845
many
Token many
Feature activation+4.023
different
Token different
Feature activation+4.149
natural
Token natural
Feature activation+3.275
conco
Token conco
Feature activation+0.128
ctions
Tokenctions
Feature activation+3.295
like
Token like
Feature activation+2.225
she
Token she
Feature activation+0.000
will
Token will
Feature activation+0.000
try
Token try
Feature activation+0.000
a
Token a
Feature activation+3.982
tactic
Token tactic
Feature activation+3.865
new
Token new
Feature activation+3.731
to
Token to
Feature activation+0.000
federal
Token federal
Feature activation+0.000
trials
Token trials
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
she
Token she
Feature activation+0.000
will
Token will
Feature activation+0.000
try
Token try
Feature activation+0.000
a
Token a
Feature activation+3.982
tactic
Token tactic
Feature activation+3.865
new
Token new
Feature activation+3.731
to
Token to
Feature activation+0.000
federal
Token federal
Feature activation+0.000
trials
Token trials
Feature activation+0.000
these
Token these
Feature activation+0.000
other
Token other
Feature activation+0.000
guys
Token guys
Feature activation+0.000
that
Token that
Feature activation+0.000
tried
Token tried
Feature activation+0.000
the
Token the
Feature activation+3.728
approach
Token approach
Feature activation+4.044
of
Token of
Feature activation+0.723
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.386
be
Token be
Feature activation+0.844
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
tried
Token tried
Feature activation+0.000
out
Token out
Feature activation+3.878
haven
Token haven
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
worked
Token worked
Feature activation+0.000

INTERVAL 3.128 - 3.650
CONTAINS 0.002%

I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
never
Token never
Feature activation+0.000
tried
Token tried
Feature activation+0.000
red
Token red
Feature activation+1.827
velvet
Token velvet
Feature activation+3.396
cake
Token cake
Feature activation+3.361
!
Token!
Feature activation+0.849
I
Token I
Feature activation+0.000
know
Token know
Feature activation+0.000
how
Token how
Feature activation+0.000
so
Token so
Feature activation+2.845
many
Token many
Feature activation+4.023
different
Token different
Feature activation+4.149
natural
Token natural
Feature activation+3.275
conco
Token conco
Feature activation+0.128
ctions
Tokenctions
Feature activation+3.295
like
Token like
Feature activation+2.225
fl
Token fl
Feature activation+0.000
ax
Tokenax
Feature activation+0.000
seed
Token seed
Feature activation+0.000
hair
Token hair
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
tried
Token tried
Feature activation+0.000
so
Token so
Feature activation+2.845
many
Token many
Feature activation+4.023
different
Token different
Feature activation+4.149
natural
Token natural
Feature activation+3.275
conco
Token conco
Feature activation+0.128
ctions
Tokenctions
Feature activation+3.295
like
Token like
Feature activation+2.225
fl
Token fl
Feature activation+0.000
ax
Tokenax
Feature activation+0.000
out
Token out
Feature activation+0.000
and
Token and
Feature activation+0.000
try
Token try
Feature activation+0.000
an
Token an
Feature activation+4.295
experimental
Token experimental
Feature activation+3.953
treatment
Token treatment
Feature activation+3.430
;
Token;
Feature activation+0.000
for
Token for
Feature activation+0.000
you
Token you
Feature activation+0.000
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
ve
Tokenve
Feature activation+0.000
probably
Token probably
Feature activation+0.000
tried
Token tried
Feature activation+0.000
it
Token it
Feature activation+3.395
!
Token!
Feature activation+0.429
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000

INTERVAL 2.607 - 3.128
CONTAINS 0.002%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.969
Steam
Token Steam
Feature activation+1.633
VR
TokenVR
Feature activation+0.000
system
Token system
Feature activation+1.729
back
Token back
Feature activation+3.007
in
Token in
Feature activation+0.654
2014
Token 2014
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000
without
Token without
Feature activation+0.000
ever
Token ever
Feature activation+0.000
trying
Token trying
Feature activation+0.000
one
Token one
Feature activation+3.737
of
Token of
Feature activation+2.740
the
Token the
Feature activation+2.958
most
Token most
Feature activation+1.772
delicious
Token delicious
Feature activation+1.219
cakes
Token cakes
Feature activation+1.175
on
Token on
Feature activation+2.048
the
Token the
Feature activation+0.000
long
Token long
Feature activation+0.000
without
Token without
Feature activation+0.000
ever
Token ever
Feature activation+0.000
trying
Token trying
Feature activation+0.000
one
Token one
Feature activation+3.737
of
Token of
Feature activation+2.740
the
Token the
Feature activation+2.958
most
Token most
Feature activation+1.772
delicious
Token delicious
Feature activation+1.219
cakes
Token cakes
Feature activation+1.175
on
Token on
Feature activation+2.048
uries
Tokenuries
Feature activation+0.000
are
Token are
Feature activation+0.000
incapable
Token incapable
Feature activation+0.000
of
Token of
Feature activation+0.000
trying
Token trying
Feature activation+0.000
a
Token a
Feature activation+2.944
white
Token white
Feature activation+2.101
person
Token person
Feature activation+2.616
fairly
Token fairly
Feature activation+3.279
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
tried
Token tried
Feature activation+0.000
it
Token it
Feature activation+2.937
all
Token all
Feature activation+2.803
and
Token and
Feature activation+1.867
over
Token over
Feature activation+0.000
1100
Token 1100
Feature activation+0.000
people
Token people
Feature activation+0.014
ended
Token ended
Feature activation+0.000

INTERVAL 2.086 - 2.607
CONTAINS 0.001%

,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
try
Token try
Feature activation+0.000
this
Token this
Feature activation+3.349
one
Token one
Feature activation+2.698
again
Token again
Feature activation+2.473
?
Token?
Feature activation+0.000
Can
Token Can
Feature activation+0.000
he
Token he
Feature activation+0.000
approach
Token approach
Feature activation+0.000
the
Token the
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Greens
Token Greens
Feature activation+0.000
'
Token'
Feature activation+0.000
approach
Token approach
Feature activation+0.000
was
Token was
Feature activation+0.000
tried
Token tried
Feature activation+2.399
by
Token by
Feature activation+2.130
the
Token the
Feature activation+0.000
previous
Token previous
Feature activation+0.000
government
Token government
Feature activation+0.000
.
Token.
Feature activation+0.000
in
Tokenin
Feature activation+0.000
tried
Token tried
Feature activation+0.000
no
Token no
Feature activation+2.033
less
Token less
Feature activation+2.697
than
Token than
Feature activation+1.982
four
Token four
Feature activation+2.479
times
Token times
Feature activation+2.007
with
Token with
Feature activation+1.799
fraudulent
Token fraudulent
Feature activation+0.000
marriages
Token marriages
Feature activation+0.000
to
Token to
Feature activation+0.000
orically
Tokenorically
Feature activation+0.000
claim
Token claim
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
trying
Token trying
Feature activation+0.000
and
Token and
Feature activation+2.290
are
Token are
Feature activation+0.000
determined
Token determined
Feature activation+0.000
to
Token to
Feature activation+0.000
curtail
Token curtail
Feature activation+0.000
.
Token.
Feature activation+0.000
are
Token are
Feature activation+0.000
incapable
Token incapable
Feature activation+0.000
of
Token of
Feature activation+0.000
trying
Token trying
Feature activation+0.000
a
Token a
Feature activation+2.944
white
Token white
Feature activation+2.101
person
Token person
Feature activation+2.616
fairly
Token fairly
Feature activation+3.279
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.564 - 2.086
CONTAINS 0.002%

free
Token free
Feature activation+0.000
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
never
Token never
Feature activation+0.000
tried
Token tried
Feature activation+0.000
red
Token red
Feature activation+1.827
velvet
Token velvet
Feature activation+3.396
cake
Token cake
Feature activation+3.361
!
Token!
Feature activation+0.849
I
Token I
Feature activation+0.000
know
Token know
Feature activation+0.000
no
Token no
Feature activation+2.033
less
Token less
Feature activation+2.697
than
Token than
Feature activation+1.982
four
Token four
Feature activation+2.479
times
Token times
Feature activation+2.007
with
Token with
Feature activation+1.799
fraudulent
Token fraudulent
Feature activation+0.000
marriages
Token marriages
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
permanent
Token permanent
Feature activation+0.000
of
Token of
Feature activation+2.740
the
Token the
Feature activation+2.958
most
Token most
Feature activation+1.772
delicious
Token delicious
Feature activation+1.219
cakes
Token cakes
Feature activation+1.175
on
Token on
Feature activation+2.048
the
Token the
Feature activation+0.000
planet
Token planet
Feature activation+0.000
?
Token?
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
they
Token they
Feature activation+0.000
go
Token go
Feature activation+0.000
with
Token with
Feature activation+0.000
tried
Token tried
Feature activation+0.000
and
Token and
Feature activation+0.803
true
Token true
Feature activation+1.597
leadership
Token leadership
Feature activation+0.000
,
Token,
Feature activation+0.000
hoping
Token hoping
Feature activation+0.000
that
Token that
Feature activation+0.000
trends
Token trends
Feature activation+0.000
war
Token war
Feature activation+0.000
if
Token if
Feature activation+0.000
possible
Token possible
Feature activation+0.000
and
Token and
Feature activation+0.000
try
Token try
Feature activation+0.000
as
Token as
Feature activation+1.823
soon
Token soon
Feature activation+0.269
as
Token as
Feature activation+0.000
possible
Token possible
Feature activation+0.562
to
Token to
Feature activation+1.368
reach
Token reach
Feature activation+0.000

INTERVAL 1.043 - 1.564
CONTAINS 0.002%

programmer
Token programmer
Feature activation+0.000
's
Token's
Feature activation+0.000
solid
Token solid
Feature activation+0.000
modeling
Token modeling
Feature activation+0.000
tool
Token tool
Feature activation+0.009
)
Token)
Feature activation+1.467
to
Token to
Feature activation+3.680
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
designs
Token designs
Feature activation+0.000
.
Token.
Feature activation+0.000
trying
Token trying
Feature activation+0.000
one
Token one
Feature activation+3.737
of
Token of
Feature activation+2.740
the
Token the
Feature activation+2.958
most
Token most
Feature activation+1.772
delicious
Token delicious
Feature activation+1.219
cakes
Token cakes
Feature activation+1.175
on
Token on
Feature activation+2.048
the
Token the
Feature activation+0.000
planet
Token planet
Feature activation+0.000
?
Token?
Feature activation+0.000
try
Token try
Feature activation+0.000
as
Token as
Feature activation+1.823
soon
Token soon
Feature activation+0.269
as
Token as
Feature activation+0.000
possible
Token possible
Feature activation+0.562
to
Token to
Feature activation+1.368
reach
Token reach
Feature activation+0.000
an
Token an
Feature activation+0.000
agreement
Token agreement
Feature activation+0.000
between
Token between
Feature activation+0.000
Israelis
Token Israelis
Feature activation+0.000
Th
Token Th
Feature activation+0.314
ug
Tokenug
Feature activation+0.000
Kitchen
Token Kitchen
Feature activation+0.931
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.093
Lav
Token Lav
Feature activation+0.000
ender
Tokenender
Feature activation+0.000
Lemon
Token Lemon
Feature activation+0.000
ade
Tokenade
Feature activation+0.000
plus
Token plus
Feature activation+0.474
definitely
Token definitely
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
try
Token try
Feature activation+0.000
the
Token the
Feature activation+3.677
bra
Token bra
Feature activation+1.133
on
Token on
Feature activation+4.097
again
Token again
Feature activation+0.000
at
Token at
Feature activation+0.931
this
Token this
Feature activation+0.000
point
Token point
Feature activation+0.000

INTERVAL 0.521 - 1.043
CONTAINS 0.005%

laws
Token laws
Feature activation+0.000
and
Token and
Feature activation+0.000
stop
Token stop
Feature activation+0.000
sing
Token sing
Feature activation+0.000
ling
Tokenling
Feature activation+0.000
out
Token out
Feature activation+0.711
these
Token these
Feature activation+0.226
ethnic
Token ethnic
Feature activation+0.000
minority
Token minority
Feature activation+0.000
communities
Token communities
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
refuse
Token refuse
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
experimented
Token experimented
Feature activation+0.020
on
Token on
Feature activation+0.649
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
That
TokenThat
Feature activation+0.000
patients
Token patients
Feature activation+0.000
also
Token also
Feature activation+0.000
tried
Token tried
Feature activation+0.000
hex
Token hex
Feature activation+0.000
pat
Tokenpat
Feature activation+0.000
,
Token,
Feature activation+1.359
tags
Token tags
Feature activation+0.763
oup
Tokenoup
Feature activation+0.000
,
Token,
Feature activation+0.108
H
Token H
Feature activation+0.000
XT
TokenXT
Feature activation+0.000
,
Token,
Feature activation+0.000
5
Token5
Feature activation+0.000
]
Token]
Feature activation+0.000
HD
Token HD
Feature activation+0.000
TV
TokenTV
Feature activation+0.000
attempts
Token attempts
Feature activation+0.000
to
Token to
Feature activation+0.844
offer
Token offer
Feature activation+0.000
arises
Token arises
Feature activation+0.000
from
Token from
Feature activation+0.000
increased
Token increased
Feature activation+0.000
resolution
Token resolution
Feature activation+0.000
oxidation
Token oxidation
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
try
Token try
Feature activation+0.000
pt
Tokenpt
Feature activation+2.957
ath
Tokenath
Feature activation+0.531
ion
Tokenion
Feature activation+0.000
ine
Tokenine
Feature activation+0.000
linkage
Token linkage
Feature activation+0.000
was
Token was
Feature activation+0.000
achieved
Token achieved
Feature activation+0.000

INTERVAL 0.000 - 0.521
CONTAINS 99.981%

return
Token return
Feature activation+0.000
duties
Token duties
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Beck
TokenBeck
Feature activation+0.000
ham
Tokenham
Feature activation+0.000
returned
Token returned
Feature activation+0.000
21
Token 21
Feature activation+0.000
pun
Token pun
Feature activation+0.000
ts
Tokents
Feature activation+0.000
Benedict
Token Benedict
Feature activation+0.000
,
Token,
Feature activation+0.000
(
Token (
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
),
Token),
Feature activation+0.000
c
Token c
Feature activation+0.000
erc
Tokenerc
Feature activation+0.000
et
Tokenet
Feature activation+0.000
at
Tokenat
Feature activation+0.000
,
Token,
Feature activation+0.000
Ã
Token Ã
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
pay
Token pay
Feature activation+0.000
close
Token close
Feature activation+0.000
attention
Token attention
Feature activation+0.000
to
Token to
Feature activation+0.000
every
Token every
Feature activation+0.000
detail
Token detail
Feature activation+0.000
before
Token before
Feature activation+0.000
posting
Token posting
Feature activation+0.000
their
Token their
Feature activation+0.000
sites
Token sites
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
urnal
Tokenurnal
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
runs
Token runs
Feature activation+0.000
on
Token on
Feature activation+0.000
by
Token by
Feature activation+0.000
going
Token going
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
settings
Token settings
Feature activation+0.000
weren
Token weren
Feature activation+0.000
't
Token't
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
why
Token why
Feature activation+0.000
patients
Token patients
Feature activation+0.000
suffered
Token suffered
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 8 in H4.0: (feature 4219)

TOP ACTIVATIONS
MAX = 5.206

have
Token have
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.522
good
Token good
Feature activation+4.311
deal
Token deal
Feature activation+5.123
of
Token of
Feature activation+5.206
their
Token their
Feature activation+4.461
lives
Token lives
Feature activation+4.469
banging
Token banging
Feature activation+0.000
their
Token their
Feature activation+0.000
heads
Token heads
Feature activation+0.000
me
Token me
Feature activation+0.000
have
Token have
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.552
lot
Token lot
Feature activation+4.255
of
Token of
Feature activation+5.159
air
Token air
Feature activation+4.467
time
Tokentime
Feature activation+4.695
and
Token and
Feature activation+3.223
ink
Token ink
Feature activation+3.602
these
Token these
Feature activation+0.000
head
Tokenhead
Feature activation+0.000
have
Token have
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.522
good
Token good
Feature activation+4.311
deal
Token deal
Feature activation+5.123
of
Token of
Feature activation+5.206
their
Token their
Feature activation+4.461
lives
Token lives
Feature activation+4.469
banging
Token banging
Feature activation+0.000
their
Token their
Feature activation+0.000
then
Token then
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.063
great
Token great
Feature activation+2.970
number
Token number
Feature activation+3.725
of
Token of
Feature activation+4.840
hours
Token hours
Feature activation+4.072
on
Token on
Feature activation+1.433
a
Token a
Feature activation+0.000
surprisingly
Token surprisingly
Feature activation+0.000
uncomfortable
Token uncomfortable
Feature activation+0.000
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.466
lot
Token lot
Feature activation+4.028
of
Token of
Feature activation+4.703
time
Token time
Feature activation+3.837
acting
Token acting
Feature activation+0.000
those
Token those
Feature activation+0.000
things
Token things
Feature activation+0.000
out
Token out
Feature activation+0.000
spent
Token spent
Feature activation+0.000
the
Token the
Feature activation+2.594
rest
Token rest
Feature activation+4.150
of
Token of
Feature activation+4.242
the
Token the
Feature activation+3.347
day
Token day
Feature activation+4.689
walking
Token walking
Feature activation+0.000
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
a
Tokena
Feature activation+0.000
)
Token)
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.238
lot
Token lot
Feature activation+3.719
of
Token of
Feature activation+4.689
time
Token time
Feature activation+2.976
m
Token m
Feature activation+0.000
udd
Tokenudd
Feature activation+0.000
ying
Tokenying
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.000
spent
Token spent
Feature activation+0.000
much
Token much
Feature activation+2.765
of
Token of
Feature activation+4.684
his
Token his
Feature activation+4.217
career
Token career
Feature activation+3.673
talking
Token talking
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.513
lot
Token lot
Feature activation+3.890
of
Token of
Feature activation+4.646
time
Token time
Feature activation+3.418
in
Token in
Feature activation+2.525
South
Token South
Feature activation+0.000
East
Token East
Feature activation+0.000
Asia
Token Asia
Feature activation+0.193
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
spent
Token spent
Feature activation+0.000
the
Token the
Feature activation+2.833
majority
Token majority
Feature activation+4.188
of
Token of
Feature activation+4.599
his
Token his
Feature activation+4.131
college
Token college
Feature activation+2.124
football
Token football
Feature activation+2.361
career
Token career
Feature activation+4.429
working
Token working
Feature activation+0.902
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.532
lot
Token lot
Feature activation+3.914
of
Token of
Feature activation+4.598
time
Token time
Feature activation+3.621
thinking
Token thinking
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
sacrament
Token sacrament
Feature activation+0.000
and
Token and
Feature activation+0.000
undoubtedly
Token undoubtedly
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.456
good
Token good
Feature activation+3.831
while
Token while
Feature activation+4.598
after
Token after
Feature activation+3.071
the
Token the
Feature activation+0.000
session
Token session
Feature activation+0.000
getting
Token getting
Feature activation+0.000
sand
Token sand
Feature activation+0.000
a
Token a
Feature activation+2.522
good
Token good
Feature activation+4.311
deal
Token deal
Feature activation+5.123
of
Token of
Feature activation+5.206
their
Token their
Feature activation+4.461
lives
Token lives
Feature activation+4.469
banging
Token banging
Feature activation+0.000
their
Token their
Feature activation+0.000
heads
Token heads
Feature activation+0.000
against
Token against
Feature activation+0.000
a
Token a
Feature activation+0.000
have
Token have
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.552
lot
Token lot
Feature activation+4.255
of
Token of
Feature activation+5.159
air
Token air
Feature activation+4.467
time
Tokentime
Feature activation+4.695
and
Token and
Feature activation+3.223
ink
Token ink
Feature activation+3.602
these
Token these
Feature activation+0.000
past
Token past
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.522
good
Token good
Feature activation+4.311
deal
Token deal
Feature activation+5.123
of
Token of
Feature activation+5.206
their
Token their
Feature activation+4.461
lives
Token lives
Feature activation+4.469
banging
Token banging
Feature activation+0.000
their
Token their
Feature activation+0.000
heads
Token heads
Feature activation+0.000
against
Token against
Feature activation+0.000
guy
Token guy
Feature activation+0.000
who
Token who
Feature activation+0.000
she
Token she
Feature activation+0.000
spent
Token spent
Feature activation+0.000
most
Token most
Feature activation+2.757
of
Token of
Feature activation+4.432
her
Token her
Feature activation+4.076
weeks
Token weeks
Feature activation+3.527
with
Token with
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
and
Token and
Feature activation+0.000
spent
Token spent
Feature activation+0.000
more
Token more
Feature activation+2.463
than
Token than
Feature activation+4.343
a
Token a
Feature activation+3.772
decade
Token decade
Feature activation+4.430
modeling
Token modeling
Feature activation+0.000
the
Token the
Feature activation+0.000
growth
Token growth
Feature activation+0.000
of
Token of
Feature activation+0.000
breast
Token breast
Feature activation+0.000
majority
Token majority
Feature activation+4.188
of
Token of
Feature activation+4.599
his
Token his
Feature activation+4.131
college
Token college
Feature activation+2.124
football
Token football
Feature activation+2.361
career
Token career
Feature activation+4.429
working
Token working
Feature activation+0.902
out
Token out
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
secondary
Token secondary
Feature activation+0.000
guy
Token guy
Feature activation+0.000
who
Token who
Feature activation+0.000
she
Token she
Feature activation+0.000
spent
Token spent
Feature activation+0.000
most
Token most
Feature activation+2.684
of
Token of
Feature activation+4.414
her
Token her
Feature activation+4.081
weeks
Token weeks
Feature activation+3.758
with
Token with
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
1980
Token 1980
Feature activation+0.000
s
Tokens
Feature activation+0.000
and
Token and
Feature activation+0.000
spent
Token spent
Feature activation+0.000
more
Token more
Feature activation+2.463
than
Token than
Feature activation+4.343
a
Token a
Feature activation+3.772
decade
Token decade
Feature activation+4.430
modeling
Token modeling
Feature activation+0.000
the
Token the
Feature activation+0.000
growth
Token growth
Feature activation+0.000

Top DFA by src position
MAX = 6.032

Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Radio
TokenRadio
Feature activation+0.062
Top resid features:
head
Tokenhead
Feature activation-0.053
Top resid features:
have
Token have
Feature activation-0.065
Top resid features:
spent
Token spent
Feature activation+5.810
Top resid features:
a
Token a
Feature activation+0.072
Top resid features:
good
Token good
Feature activation+0.183
Top resid features:
deal
Token deal
Feature activation+0.346
Top resid features:
of
Token of
Feature activation+0.049
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
People
Token People
Feature activation-0.001
Top resid features:
like
Token like
Feature activation+0.017
Top resid features:
me
Token me
Feature activation-0.045
Top resid features:
have
Token have
Feature activation-0.029
Top resid features:
spent
Token spent
Feature activation+6.032
Top resid features:
a
Token a
Feature activation+0.067
Top resid features:
lot
Token lot
Feature activation+0.226
Top resid features:
of
Token of
Feature activation+0.041
Top resid features:
air
Token air
Feature activation+0.000
Top resid features:
time
Tokentime
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
Radio
TokenRadio
Feature activation+0.017
Top resid features:
head
Tokenhead
Feature activation-0.019
Top resid features:
have
Token have
Feature activation-0.103
Top resid features:
spent
Token spent
Feature activation+5.828
Top resid features:
a
Token a
Feature activation+0.112
Top resid features:
good
Token good
Feature activation+0.479
Top resid features:
deal
Token deal
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
I
TokenI
Feature activation+0.039
Top resid features:
then
Token then
Feature activation-0.016
Top resid features:
spent
Token spent
Feature activation+5.319
Top resid features:
a
Token a
Feature activation+0.045
Top resid features:
great
Token great
Feature activation+0.233
Top resid features:
number
Token number
Feature activation+0.358
Top resid features:
of
Token of
Feature activation+0.075
Top resid features:
hours
Token hours
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
adventure
Token adventure
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.073
Top resid features:
we
Token we
Feature activation+0.007
Top resid features:
spent
Token spent
Feature activation+5.600
Top resid features:
a
Token a
Feature activation+0.082
Top resid features:
lot
Token lot
Feature activation+0.169
Top resid features:
of
Token of
Feature activation+0.038
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
acting
Token acting
Feature activation+0.000
Top resid features:
Awards
Token Awards
Feature activation+0.064
Top resid features:
Show
Token Show
Feature activation-0.013
Top resid features:
case
Tokencase
Feature activation-0.014
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.062
Top resid features:
spent
Token spent
Feature activation+5.549
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
rest
Token rest
Feature activation+0.223
Top resid features:
of
Token of
Feature activation+0.052
Top resid features:
the
Token the
Feature activation-0.268
Top resid features:
day
Token day
Feature activation+0.095
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
Michael
Token Michael
Feature activation-0.005
Top resid features:
Bar
Token Bar
Feature activation-0.028
Top resid features:
a
Tokena
Feature activation-0.005
Top resid features:
)
Token)
Feature activation-0.040
Top resid features:
spent
Token spent
Feature activation+5.665
Top resid features:
a
Token a
Feature activation+0.085
Top resid features:
lot
Token lot
Feature activation+0.152
Top resid features:
of
Token of
Feature activation+0.056
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
m
Token m
Feature activation+0.000
Top resid features:
Professor
Token Professor
Feature activation+0.001
Top resid features:
Dawkins
Token Dawkins
Feature activation-0.015
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.022
Top resid features:
who
Token who
Feature activation-0.007
Top resid features:
has
Token has
Feature activation-0.024
Top resid features:
spent
Token spent
Feature activation+5.691
Top resid features:
much
Token much
Feature activation+0.098
Top resid features:
of
Token of
Feature activation+0.078
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
career
Token career
Feature activation+0.000
Top resid features:
talking
Token talking
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
I
Token I
Feature activation+0.024
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation-0.015
Top resid features:
ve
Tokenve
Feature activation+0.043
Top resid features:
spent
Token spent
Feature activation+5.532
Top resid features:
a
Token a
Feature activation+0.074
Top resid features:
lot
Token lot
Feature activation+0.044
Top resid features:
of
Token of
Feature activation+0.042
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
spring
Token spring
Feature activation+0.006
Top resid features:
practice
Token practice
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
he
Token he
Feature activation+0.047
Top resid features:
spent
Token spent
Feature activation+5.678
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
majority
Token majority
Feature activation-0.018
Top resid features:
of
Token of
Feature activation-0.019
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
college
Token college
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
I
Token I
Feature activation+0.054
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ļ
TokenĻ
Feature activation-0.014
Top resid features:
ve
Tokenve
Feature activation+0.059
Top resid features:
spent
Token spent
Feature activation+5.444
Top resid features:
a
Token a
Feature activation+0.070
Top resid features:
lot
Token lot
Feature activation+0.029
Top resid features:
of
Token of
Feature activation+0.042
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
thinking
Token thinking
Feature activation+0.000
Top resid features:
taking
Token taking
Feature activation-0.084
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
beating
Token beating
Feature activation-0.039
Top resid features:
and
Token and
Feature activation+0.024
Top resid features:
undoubtedly
Token undoubtedly
Feature activation-0.036
Top resid features:
spent
Token spent
Feature activation+5.527
Top resid features:
a
Token a
Feature activation+0.089
Top resid features:
good
Token good
Feature activation+0.397
Top resid features:
while
Token while
Feature activation+0.071
Top resid features:
after
Token after
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Radio
TokenRadio
Feature activation+0.028
Top resid features:
head
Tokenhead
Feature activation-0.082
Top resid features:
have
Token have
Feature activation-0.063
Top resid features:
spent
Token spent
Feature activation+5.235
Top resid features:
a
Token a
Feature activation+0.083
Top resid features:
good
Token good
Feature activation+0.084
Top resid features:
deal
Token deal
Feature activation+0.046
Top resid features:
of
Token of
Feature activation+0.110
Top resid features:
their
Token their
Feature activation+0.094
Top resid features:
.
Token.
Feature activation+0.046
Top resid features:
People
Token People
Feature activation+0.015
Top resid features:
like
Token like
Feature activation+0.011
Top resid features:
me
Token me
Feature activation-0.045
Top resid features:
have
Token have
Feature activation-0.013
Top resid features:
spent
Token spent
Feature activation+5.337
Top resid features:
a
Token a
Feature activation+0.064
Top resid features:
lot
Token lot
Feature activation+0.073
Top resid features:
of
Token of
Feature activation-0.047
Top resid features:
air
Token air
Feature activation+0.092
Top resid features:
time
Tokentime
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Radio
TokenRadio
Feature activation+0.039
Top resid features:
head
Tokenhead
Feature activation-0.091
Top resid features:
have
Token have
Feature activation-0.060
Top resid features:
spent
Token spent
Feature activation+5.621
Top resid features:
a
Token a
Feature activation+0.070
Top resid features:
good
Token good
Feature activation+0.057
Top resid features:
deal
Token deal
Feature activation+0.089
Top resid features:
of
Token of
Feature activation-0.102
Top resid features:
their
Token their
Feature activation-0.063
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
guy
Token guy
Feature activation-0.000
Top resid features:
who
Token who
Feature activation-0.088
Top resid features:
she
Token she
Feature activation-0.016
Top resid features:
spent
Token spent
Feature activation+5.860
Top resid features:
most
Token most
Feature activation-0.130
Top resid features:
of
Token of
Feature activation-0.080
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
weeks
Token weeks
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.013
Top resid features:
early
Token early
Feature activation+0.010
Top resid features:
1980
Token 1980
Feature activation-0.007
Top resid features:
s
Tokens
Feature activation-0.043
Top resid features:
and
Token and
Feature activation+0.090
Top resid features:
spent
Token spent
Feature activation+4.772
Top resid features:
more
Token more
Feature activation+0.071
Top resid features:
than
Token than
Feature activation+0.127
Top resid features:
a
Token a
Feature activation+0.270
Top resid features:
decade
Token decade
Feature activation+0.108
Top resid features:
modeling
Token modeling
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.019
Top resid features:
spring
Token spring
Feature activation-0.002
Top resid features:
practice
Token practice
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.020
Top resid features:
he
Token he
Feature activation+0.023
Top resid features:
spent
Token spent
Feature activation+4.976
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
majority
Token majority
Feature activation+0.056
Top resid features:
of
Token of
Feature activation+0.142
Top resid features:
his
Token his
Feature activation+0.203
Top resid features:
college
Token college
Feature activation+0.107
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
guy
Token guy
Feature activation-0.008
Top resid features:
who
Token who
Feature activation-0.088
Top resid features:
she
Token she
Feature activation-0.008
Top resid features:
spent
Token spent
Feature activation+5.793
Top resid features:
most
Token most
Feature activation-0.109
Top resid features:
of
Token of
Feature activation-0.077
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
weeks
Token weeks
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
early
Token early
Feature activation+0.017
Top resid features:
1980
Token 1980
Feature activation+0.018
Top resid features:
s
Tokens
Feature activation-0.013
Top resid features:
and
Token and
Feature activation+0.073
Top resid features:
spent
Token spent
Feature activation+5.059
Top resid features:
more
Token more
Feature activation+0.164
Top resid features:
than
Token than
Feature activation+0.136
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
decade
Token decade
Feature activation+0.000
Top resid features:
modeling
Token modeling
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.48

Head 1: 0.03

Head 2: 0.02

Head 3: 0.04

Head 4: 0.03

Head 5: 0.05

Head 6: 0.04

Head 7: 0.10

Head 8: 0.02

Head 9: 0.07

Head 10: 0.01

Head 11: 0.11

Positive logits

ega1.53

arant1.30

bourg1.29

eful1.28

dollars1.19

ibur1.19

RON1.18

tenance1.17

$$1.16

wisely1.16

amazon1.16

Beau1.15

bon1.14

imbabwe1.14

(~1.13

scarce1.12

illions1.12

acha1.11

ald1.11

agna1.11

Negative logits

bandwagon-1.32

wrinkles-1.22

ceilings-1.22

sidelines-1.18

fronts-1.17

flaws-1.17

trends-1.16

inconsistencies-1.14

ippers-1.14

Repe-1.12

od-1.08

shoulders-1.05

scanners-1.05

ゴン-1.05

shores-1.05

axis-1.03

wearer-1.03

paio-1.01

opl-1.01

basis-1.01

INTERVAL 4.686 - 5.206
CONTAINS 0.001%

then
Token then
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.063
great
Token great
Feature activation+2.970
number
Token number
Feature activation+3.725
of
Token of
Feature activation+4.840
hours
Token hours
Feature activation+4.072
on
Token on
Feature activation+1.433
a
Token a
Feature activation+0.000
surprisingly
Token surprisingly
Feature activation+0.000
uncomfortable
Token uncomfortable
Feature activation+0.000
me
Token me
Feature activation+0.000
have
Token have
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.552
lot
Token lot
Feature activation+4.255
of
Token of
Feature activation+5.159
air
Token air
Feature activation+4.467
time
Tokentime
Feature activation+4.695
and
Token and
Feature activation+3.223
ink
Token ink
Feature activation+3.602
these
Token these
Feature activation+0.000
a
Tokena
Feature activation+0.000
)
Token)
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.238
lot
Token lot
Feature activation+3.719
of
Token of
Feature activation+4.689
time
Token time
Feature activation+2.976
m
Token m
Feature activation+0.000
udd
Tokenudd
Feature activation+0.000
ying
Tokenying
Feature activation+0.000
the
Token the
Feature activation+0.000
have
Token have
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.522
good
Token good
Feature activation+4.311
deal
Token deal
Feature activation+5.123
of
Token of
Feature activation+5.206
their
Token their
Feature activation+4.461
lives
Token lives
Feature activation+4.469
banging
Token banging
Feature activation+0.000
their
Token their
Feature activation+0.000
heads
Token heads
Feature activation+0.000
head
Tokenhead
Feature activation+0.000
have
Token have
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.522
good
Token good
Feature activation+4.311
deal
Token deal
Feature activation+5.123
of
Token of
Feature activation+5.206
their
Token their
Feature activation+4.461
lives
Token lives
Feature activation+4.469
banging
Token banging
Feature activation+0.000
their
Token their
Feature activation+0.000

INTERVAL 4.165 - 4.686
CONTAINS 0.002%

Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.513
lot
Token lot
Feature activation+3.890
of
Token of
Feature activation+4.646
time
Token time
Feature activation+3.418
in
Token in
Feature activation+2.525
South
Token South
Feature activation+0.000
East
Token East
Feature activation+0.000
Asia
Token Asia
Feature activation+0.193
majority
Token majority
Feature activation+4.188
of
Token of
Feature activation+4.599
his
Token his
Feature activation+4.131
college
Token college
Feature activation+2.124
football
Token football
Feature activation+2.361
career
Token career
Feature activation+4.429
working
Token working
Feature activation+0.902
out
Token out
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
secondary
Token secondary
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.532
lot
Token lot
Feature activation+3.914
of
Token of
Feature activation+4.598
time
Token time
Feature activation+3.621
thinking
Token thinking
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
sacrament
Token sacrament
Feature activation+0.000
and
Token and
Feature activation+0.000
undoubtedly
Token undoubtedly
Feature activation+0.000
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+2.456
good
Token good
Feature activation+3.831
while
Token while
Feature activation+4.598
after
Token after
Feature activation+3.071
the
Token the
Feature activation+0.000
session
Token session
Feature activation+0.000
getting
Token getting
Feature activation+0.000
sand
Token sand
Feature activation+0.000
a
Token a
Feature activation+2.522
good
Token good
Feature activation+4.311
deal
Token deal
Feature activation+5.123
of
Token of
Feature activation+5.206
their
Token their
Feature activation+4.461
lives
Token lives
Feature activation+4.469
banging
Token banging
Feature activation+0.000
their
Token their
Feature activation+0.000
heads
Token heads
Feature activation+0.000
against
Token against
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 3.644 - 4.165
CONTAINS 0.004%

spent
Token spent
Feature activation+0.000
more
Token more
Feature activation+2.736
than
Token than
Feature activation+4.403
$
Token $
Feature activation+2.760
142
Token142
Feature activation+2.945
million
Token million
Feature activation+4.039
of
Token of
Feature activation+4.021
her
Token her
Feature activation+0.828
own
Token own
Feature activation+1.315
money
Token money
Feature activation+1.637
in
Token in
Feature activation+0.573
billionaire
Token billionaire
Feature activation+0.000
who
Token who
Feature activation+0.000
had
Token had
Feature activation+0.000
spent
Token spent
Feature activation+0.000
most
Token most
Feature activation+1.979
of
Token of
Feature activation+3.961
her
Token her
Feature activation+3.718
professional
Token professional
Feature activation+2.917
career
Token career
Feature activation+2.555
in
Token in
Feature activation+1.119
the
Token the
Feature activation+0.000
exhibition
Token exhibition
Feature activation+0.000
said
Token said
Feature activation+0.000
they
Token they
Feature activation+0.000
spent
Token spent
Feature activation+0.000
nearly
Token nearly
Feature activation+1.473
the
Token the
Feature activation+3.935
entire
Token entire
Feature activation+3.786
time
Token time
Feature activation+1.706
in
Token in
Feature activation+1.933
heated
Token heated
Feature activation+0.000
discussion
Token discussion
Feature activation+0.032
case
Tokencase
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
spent
Token spent
Feature activation+0.000
the
Token the
Feature activation+2.594
rest
Token rest
Feature activation+4.150
of
Token of
Feature activation+4.242
the
Token the
Feature activation+3.347
day
Token day
Feature activation+4.689
walking
Token walking
Feature activation+0.000
around
Token around
Feature activation+0.000
And
Token And
Feature activation+0.000
because
Token because
Feature activation+0.000
we
Token we
Feature activation+0.000
spend
Token spend
Feature activation+0.000
much
Token much
Feature activation+1.424
of
Token of
Feature activation+3.738
our
Token our
Feature activation+3.423
time
Token time
Feature activation+2.412
on
Token on
Feature activation+1.519
computers
Token computers
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 3.124 - 3.644
CONTAINS 0.004%

she
Token she
Feature activation+0.000
spent
Token spent
Feature activation+0.000
most
Token most
Feature activation+2.757
of
Token of
Feature activation+4.432
her
Token her
Feature activation+4.076
weeks
Token weeks
Feature activation+3.527
with
Token with
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
her
Token her
Feature activation+0.000
attorney
Token attorney
Feature activation+0.000
âĢ
TokenâĢ
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+2.578
decades
Token decades
Feature activation+3.584
building
Token building
Feature activation+0.000
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
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+2.497
time
Token time
Feature activation+3.250
surfing
Token surfing
Feature activation+0.000
Web
Token Web
Feature activation+0.000
MD
TokenMD
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
psychologist
Token psychologist
Feature activation+0.000
who
Token who
Feature activation+0.000
spent
Token spent
Feature activation+0.000
nearly
Token nearly
Feature activation+1.617
his
Token his
Feature activation+2.974
entire
Token entire
Feature activation+3.311
career
Token career
Feature activation+1.768
at
Token at
Feature activation+0.265
Teachers
Token Teachers
Feature activation+0.000
College
Token College
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.000
spend
Token spend
Feature activation+0.253
huge
Token huge
Feature activation+1.661
amounts
Token amounts
Feature activation+2.848
of
Token of
Feature activation+3.547
time
Token time
Feature activation+1.898
connected
Token connected
Feature activation+0.302
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
survey
Token survey
Feature activation+0.000

INTERVAL 2.603 - 3.124
CONTAINS 0.008%

inmate
Token inmate
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+2.133
extra
Token extra
Feature activation+2.888
months
Token months
Feature activation+2.857
in
Token in
Feature activation+0.962
jail
Token jail
Feature activation+0.000
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
spent
Token spent
Feature activation+0.000
that
Token that
Feature activation+2.307
time
Token time
Feature activation+2.753
researching
Token researching
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
topics
Token topics
Feature activation+0.000
as
Token as
Feature activation+0.000
Robert
Token Robert
Feature activation+0.000
Gordon
Token Gordon
Feature activation+0.000
University
Token University
Feature activation+0.000
spent
Token spent
Feature activation+0.000
two
Token two
Feature activation+2.278
years
Token years
Feature activation+2.677
assessing
Token assessing
Feature activation+0.000
measurements
Token measurements
Feature activation+0.000
of
Token of
Feature activation+0.000
hundreds
Token hundreds
Feature activation+0.000
of
Token of
Feature activation+0.000
who
Token who
Feature activation+0.000
spent
Token spent
Feature activation+0.000
more
Token more
Feature activation+2.736
than
Token than
Feature activation+4.403
$
Token $
Feature activation+2.760
142
Token142
Feature activation+2.945
million
Token million
Feature activation+4.039
of
Token of
Feature activation+4.021
her
Token her
Feature activation+0.828
own
Token own
Feature activation+1.315
money
Token money
Feature activation+1.637
can
Token can
Feature activation+0.000
spend
Token spend
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.801
60
Token 60
Feature activation+2.926
%
Token%
Feature activation+2.911
of
Token of
Feature activation+3.013
your
Token your
Feature activation+2.221
bonus
Token bonus
Feature activation+1.956
points
Token points
Feature activation+1.208
on
Token on
Feature activation+0.866

INTERVAL 2.082 - 2.603
CONTAINS 0.009%

the
Token the
Feature activation+2.833
majority
Token majority
Feature activation+4.188
of
Token of
Feature activation+4.599
his
Token his
Feature activation+4.131
college
Token college
Feature activation+2.124
football
Token football
Feature activation+2.361
career
Token career
Feature activation+4.429
working
Token working
Feature activation+0.902
out
Token out
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
like
Token like
Feature activation+0.000
this
Token this
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
spends
Token spends
Feature activation+0.000
his
Token his
Feature activation+2.101
day
Token day
Feature activation+2.524
on
Token on
Feature activation+2.112
the
Token the
Feature activation+0.000
internet
Token internet
Feature activation+0.000
telling
Token telling
Feature activation+0.000
you
Token you
Feature activation+0.000
spend
Token spend
Feature activation+0.000
most
Token most
Feature activation+1.296
of
Token of
Feature activation+2.816
your
Token your
Feature activation+2.892
time
Token time
Feature activation+2.509
analyzing
Token analyzing
Feature activation+0.000
SQL
Token SQL
Feature activation+0.000
queries
Token queries
Feature activation+0.000
.
Token.
Feature activation+0.000
Or
Token Or
Feature activation+0.000
Mr
TokenMr
Feature activation+0.000
P
Token P
Feature activation+0.000
ree
Tokenree
Feature activation+0.000
ce
Tokence
Feature activation+0.000
spent
Token spent
Feature activation+0.000
his
Token his
Feature activation+2.373
week
Token week
Feature activation+0.908
days
Tokendays
Feature activation+2.342
working
Token working
Feature activation+0.000
in
Token in
Feature activation+0.000
Johannes
Token Johannes
Feature activation+0.000
the
Token the
Feature activation+1.676
bulk
Token bulk
Feature activation+2.829
of
Token of
Feature activation+4.254
the
Token the
Feature activation+3.680
rally
Token rally
Feature activation+3.014
un
Token un
Feature activation+2.176
loading
Tokenloading
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
news
Token news
Feature activation+0.000
media
Token media
Feature activation+0.000

INTERVAL 1.562 - 2.082
CONTAINS 0.008%

Anyway
TokenAnyway
Feature activation+0.000
,
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
my
Token my
Feature activation+2.062
Super
Token Super
Feature activation+1.051
bowl
Tokenbowl
Feature activation+1.999
Sunday
Token Sunday
Feature activation+2.451
organizing
Token organizing
Feature activation+0.104
the
Token the
Feature activation+0.000
to
Token to
Feature activation+0.000
spend
Token spend
Feature activation+0.000
a
Token a
Feature activation+0.753
few
Token few
Feature activation+1.887
hundred
Token hundred
Feature activation+2.344
billion
Token billion
Feature activation+2.064
more
Token more
Feature activation+2.414
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Well
TokenWell
Feature activation+0.000
the
Token the
Feature activation+0.000
school
Token school
Feature activation+0.000
also
Token also
Feature activation+0.000
spent
Token spent
Feature activation+0.000
$
Token $
Feature activation+1.208
7
Token7
Feature activation+1.879
,
Token,
Feature activation+1.011
500
Token500
Feature activation+3.908
installing
Token installing
Feature activation+0.000
water
Token water
Feature activation+0.000
bub
Token bub
Feature activation+0.000
$
Token $
Feature activation+0.317
8
Token8
Feature activation+1.172
16
Token16
Feature activation+1.366
,
Token,
Feature activation+0.155
000
Token000
Feature activation+3.122
on
Token on
Feature activation+1.816
consulting
Token consulting
Feature activation+0.000
(
Token (
Feature activation+0.000
d
Tokend
Feature activation+0.000
oled
Tokenoled
Feature activation+0.000
out
Token out
Feature activation+0.000
grateful
Token grateful
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
spend
Token spend
Feature activation+0.000
this
Token this
Feature activation+1.782
quality
Token quality
Feature activation+2.461
time
Token time
Feature activation+0.966
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.041 - 1.562
CONTAINS 0.008%

60
Token 60
Feature activation+2.926
%
Token%
Feature activation+2.911
of
Token of
Feature activation+3.013
your
Token your
Feature activation+2.221
bonus
Token bonus
Feature activation+1.956
points
Token points
Feature activation+1.208
on
Token on
Feature activation+0.866
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
spending
Token spending
Feature activation+0.000
the
Token the
Feature activation+0.245
biggest
Token biggest
Feature activation+1.409
share
Token share
Feature activation+1.830
of
Token of
Feature activation+1.851
their
Token their
Feature activation+1.083
household
Token household
Feature activation+0.199
pay
Token pay
Feature activation+0.548
among
Token among
Feature activation+0.000
major
Token major
Feature activation+0.000
U
Token U
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
fortunate
Token fortunate
Feature activation+0.000
to
Token to
Feature activation+0.000
spend
Token spend
Feature activation+0.000
so
Token so
Feature activation+1.378
much
Token much
Feature activation+3.728
time
Token time
Feature activation+0.368
with
Token with
Feature activation+0.000
Hans
Token Hans
Feature activation+0.000
on
Token on
Feature activation+0.000
station
Token station
Feature activation+0.000
where
Token where
Feature activation+0.000
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
spend
Token spend
Feature activation+0.000
the
Token the
Feature activation+1.355
next
Token next
Feature activation+2.288
six
Token six
Feature activation+2.579
months
Token months
Feature activation+1.382
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
because
Token because
Feature activation+0.000
we
Token we
Feature activation+0.000
spend
Token spend
Feature activation+0.000
much
Token much
Feature activation+1.424
of
Token of
Feature activation+3.738
our
Token our
Feature activation+3.423
time
Token time
Feature activation+2.412
on
Token on
Feature activation+1.519
computers
Token computers
Feature activation+0.000

INTERVAL 0.521 - 1.041
CONTAINS 0.010%

The
Token The
Feature activation+0.000
comedian
Token comedian
Feature activation+0.000
spent
Token spent
Feature activation+0.000
the
Token the
Feature activation+2.341
evening
Token evening
Feature activation+2.318
st
Token st
Feature activation+0.716
rolling
Tokenrolling
Feature activation+0.000
the
Token the
Feature activation+0.000
grounds
Token grounds
Feature activation+0.000
,
Token,
Feature activation+0.000
ming
Token ming
Feature activation+0.000
t
Tokent
Feature activation+0.000
spend
Token spend
Feature activation+0.000
it
Token it
Feature activation+0.196
and
Token and
Feature activation+0.851
the
Token the
Feature activation+0.570
game
Token game
Feature activation+0.822
time
Token time
Feature activation+0.000
clock
Token clock
Feature activation+0.144
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
11
Token 11
Feature activation+0.000
normally
Token normally
Feature activation+0.000
spent
Token spent
Feature activation+0.000
one
Token one
Feature activation+2.488
of
Token of
Feature activation+3.798
my
Token my
Feature activation+3.546
I
Token I
Feature activation+0.592
OU
TokenOU
Feature activation+0.000
s
Tokens
Feature activation+1.367
on
Token on
Feature activation+3.389
a
Token a
Feature activation+0.000
game
Token game
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
spend
Token spend
Feature activation+0.000
only
Token only
Feature activation+0.192
six
Token six
Feature activation+2.773
months
Token months
Feature activation+1.101
in
Token in
Feature activation+0.624
Cairo
Token Cairo
Feature activation+0.000
.
Token.
Feature activation+0.000
Little
Token Little
Feature activation+0.000
did
Token did
Feature activation+0.000
I
Token I
Feature activation+0.000
biggest
Token biggest
Feature activation+1.409
share
Token share
Feature activation+1.830
of
Token of
Feature activation+1.851
their
Token their
Feature activation+1.083
household
Token household
Feature activation+0.199
pay
Token pay
Feature activation+0.548
among
Token among
Feature activation+0.000
major
Token major
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000

INTERVAL 0.000 - 0.521
CONTAINS 99.945%

Ċ
TokenĊ
Feature activation+0.000
>
Token>
Feature activation+0.000
Make
Token Make
Feature activation+0.000
Mic
Token Mic
Feature activation+0.000
ah
Tokenah
Feature activation+0.000
Hyde
Token Hyde
Feature activation+0.000
your
Token your
Feature activation+0.000
CB
Token CB
Feature activation+0.000
5
Token5
Feature activation+0.000
and
Token and
Feature activation+0.000
start
Token start
Feature activation+0.000
Some
Token Some
Feature activation+0.000
p
Tokenp
Feature activation+0.000
ony
Tokenony
Feature activation+0.000
:
Token:
Feature activation+0.000
Professional
Token Professional
Feature activation+0.000
h
Token h
Feature activation+0.000
ool
Tokenool
Feature activation+0.000
igan
Tokenigan
Feature activation+0.000
/
Token/
Feature activation+0.000
lay
Tokenlay
Feature activation+0.000
about
Tokenabout
Feature activation+0.000
to
Token to
Feature activation+0.000
beat
Token beat
Feature activation+0.000
the
Token the
Feature activation+0.000
crap
Token crap
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
help
Token help
Feature activation+0.000
their
Token their
Feature activation+0.000
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.000
and
Token and
Feature activation+0.000
use
Token use
Feature activation+0.000
of
Token of
Feature activation+0.000
fossil
Token fossil
Feature activation+0.000
fuels
Token fuels
Feature activation+0.000
more
Token more
Feature activation+0.000
clean
Token clean
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Leader
Token Leader
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
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 H4.0: (feature 24574)

TOP ACTIVATIONS
MAX = 4.650

15
Token15
Feature activation+0.000
Ju
Token Ju
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
forced
Token forced
Feature activation+0.000
the
Token the
Feature activation+2.983
longest
Token longest
Feature activation+4.650
average
Token average
Feature activation+1.200
shot
Token shot
Feature activation+0.191
in
Token in
Feature activation+0.507
Serie
Token Serie
Feature activation+0.000
A
Token A
Feature activation+0.000
forced
Token forced
Feature activation+0.000
the
Token the
Feature activation+2.526
extra
Token extra
Feature activation+3.408
pit
Token pit
Feature activation+0.000
st
Tokenst
Feature activation+0.000
ops
Tokenops
Feature activation+4.584
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
He
TokenHe
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Bears
Token Bears
Feature activation+0.000
forced
Token forced
Feature activation+0.000
only
Token only
Feature activation+1.892
11
Token 11
Feature activation+4.255
turnovers
Token turnovers
Feature activation+2.016
last
Token last
Feature activation+0.000
season
Token season
Feature activation+0.000
,
Token,
Feature activation+0.082
tying
Token tying
Feature activation+0.000
les
Tokenles
Feature activation+0.000
between
Token between
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
forced
Token forced
Feature activation+0.000
a
Token a
Feature activation+3.426
brief
Token brief
Feature activation+4.229
suspension
Token suspension
Feature activation+2.848
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
voting
Token voting
Feature activation+0.000
session
Token session
Feature activation+0.000
of
Token of
Feature activation+0.000
fighting
Token fighting
Feature activation+0.000
,
Token,
Feature activation+0.000
forced
Token forced
Feature activation+0.000
the
Token the
Feature activation+2.937
complete
Token complete
Feature activation+4.164
surrender
Token surrender
Feature activation+2.935
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
French
Token French
Feature activation+0.000
colonial
Token colonial
Feature activation+0.000
tering
Tokentering
Feature activation+0.000
region
Token region
Feature activation+0.000
forces
Token forces
Feature activation+1.224
a
Token a
Feature activation+2.962
theological
Token theological
Feature activation+3.935
question
Token question
Feature activation+4.020
:
Token:
Feature activation+0.000
How
Token How
Feature activation+0.000
does
Token does
Feature activation+0.000
God
Token God
Feature activation+0.000
feel
Token feel
Feature activation+0.000
a
Token a
Feature activation+2.823
sleepy
Token sleepy
Feature activation+2.609
East
Token East
Feature activation+1.096
Bay
Token Bay
Feature activation+0.769
suburb
Token suburb
Feature activation+1.753
to
Token to
Feature activation+3.941
go
Token go
Feature activation+0.000
dense
Token dense
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
el
Tokenel
Feature activation+0.000
tering
Tokentering
Feature activation+0.000
region
Token region
Feature activation+0.000
forces
Token forces
Feature activation+1.224
a
Token a
Feature activation+2.962
theological
Token theological
Feature activation+3.935
question
Token question
Feature activation+4.020
:
Token:
Feature activation+0.000
How
Token How
Feature activation+0.000
does
Token does
Feature activation+0.000
God
Token God
Feature activation+0.000
Planning
Token Planning
Feature activation+0.000
Bill
Token Bill
Feature activation+0.000
,
Token,
Feature activation+0.000
forced
Token forced
Feature activation+0.000
academ
Token academ
Feature activation+0.000
isation
Tokenisation
Feature activation+3.564
,
Token,
Feature activation+0.742
the
Token the
Feature activation+0.155
local
Token local
Feature activation+0.000
isation
Tokenisation
Feature activation+1.432
of
Token of
Feature activation+0.000
party
Token party
Feature activation+0.000
line
Token line
Feature activation+0.000
vote
Token vote
Feature activation+0.000
forced
Token forced
Feature activation+0.000
her
Token her
Feature activation+2.014
off
Token off
Feature activation+3.521
the
Token the
Feature activation+0.000
floor
Token floor
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
immediate
Token immediate
Feature activation+0.000
in
Token in
Feature activation+0.000
Detroit
Token Detroit
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
forced
Token forced
Feature activation+0.000
their
Token their
Feature activation+3.483
Burger
Token Burger
Feature activation+1.556
King
Token King
Feature activation+3.392
to
Token to
Feature activation+2.574
close
Token close
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+2.479
D
Token D
Feature activation+0.678
ax
Tokenax
Feature activation+0.000
am
Tokenam
Feature activation+0.000
ites
Tokenites
Feature activation+1.704
off
Token off
Feature activation+3.470
of
Token of
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+0.000
has
Token has
Feature activation+0.000
forced
Token forced
Feature activation+0.000
the
Token the
Feature activation+2.572
Communist
Token Communist
Feature activation+1.741
leadership
Token leadership
Feature activation+3.429
to
Token to
Feature activation+1.579
confront
Token confront
Feature activation+0.000
allegations
Token allegations
Feature activation+0.000
of
Token of
Feature activation+0.000
wrongdoing
Token wrongdoing
Feature activation+0.000
uff
Tokenuff
Feature activation+0.000
les
Tokenles
Feature activation+0.000
between
Token between
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
forced
Token forced
Feature activation+0.000
a
Token a
Feature activation+3.426
brief
Token brief
Feature activation+4.229
suspension
Token suspension
Feature activation+2.848
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
voting
Token voting
Feature activation+0.000
ups
Tokenups
Feature activation+0.000
that
Token that
Feature activation+0.000
ultimately
Token ultimately
Feature activation+0.000
forced
Token forced
Feature activation+0.000
the
Token the
Feature activation+2.526
extra
Token extra
Feature activation+3.408
pit
Token pit
Feature activation+0.000
st
Tokenst
Feature activation+0.000
ops
Tokenops
Feature activation+4.584
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
forced
Token forced
Feature activation+0.000
their
Token their
Feature activation+3.483
Burger
Token Burger
Feature activation+1.556
King
Token King
Feature activation+3.392
to
Token to
Feature activation+2.574
close
Token close
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
day
Token day
Feature activation+0.000
,
Token,
Feature activation+0.000
America
Token America
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
forced
Token forced
Feature activation+0.501
into
Token into
Feature activation+3.371
water
Token water
Feature activation+0.000
wars
Token wars
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.109
to
Token to
Feature activation+0.000
forced
Token forced
Feature activation+0.000
Ge
Token Ge
Feature activation+0.000
og
Tokenog
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
gan
Tokengan
Feature activation+0.000
into
Token into
Feature activation+3.316
a
Token a
Feature activation+0.000
denial
Token denial
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.000
people
Token people
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
will
Token will
Feature activation+0.000
force
Token force
Feature activation+0.000
our
Token our
Feature activation+3.290
people
Token people
Feature activation+2.387
into
Token into
Feature activation+2.219
more
Token more
Feature activation+0.000
wars
Token wars
Feature activation+0.000
of
Token of
Feature activation+0.000
-
Token-
Feature activation+0.000
under
Tokenunder
Feature activation+0.000
staff
Tokenstaff
Feature activation+1.680
ed
Tokened
Feature activation+2.796
IT
Token IT
Feature activation+1.611
managers
Token managers
Feature activation+3.251
to
Token to
Feature activation+2.707
shut
Token shut
Feature activation+0.000
them
Token them
Feature activation+0.000
down
Token down
Feature activation+0.000
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 5.690

14
Token 14
Feature activation-0.003
Top resid features:
/
Token/
Feature activation+0.004
Top resid features:
15
Token15
Feature activation-0.004
Top resid features:
Ju
Token Ju
Feature activation+0.030
Top resid features:
ve
Tokenve
Feature activation-0.016
Top resid features:
forced
Token forced
Feature activation+5.667
Top resid features:
the
Token the
Feature activation+0.668
Top resid features:
longest
Token longest
Feature activation+0.089
Top resid features:
average
Token average
Feature activation+0.000
Top resid features:
shot
Token shot
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
lock
Token lock
Feature activation+0.003
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
ups
Tokenups
Feature activation+0.017
Top resid features:
that
Token that
Feature activation+0.023
Top resid features:
ultimately
Token ultimately
Feature activation-0.010
Top resid features:
forced
Token forced
Feature activation+4.737
Top resid features:
the
Token the
Feature activation+0.146
Top resid features:
extra
Token extra
Feature activation+0.410
Top resid features:
pit
Token pit
Feature activation+0.112
Top resid features:
st
Tokenst
Feature activation+0.398
Top resid features:
ops
Tokenops
Feature activation+0.299
Top resid features:
.
Token.
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation-0.017
Top resid features:
Ċ
TokenĊ
Feature activation-0.020
Top resid features:
The
TokenThe
Feature activation+0.004
Top resid features:
Bears
Token Bears
Feature activation+0.071
Top resid features:
forced
Token forced
Feature activation+5.690
Top resid features:
only
Token only
Feature activation+0.015
Top resid features:
11
Token 11
Feature activation+0.053
Top resid features:
turnovers
Token turnovers
Feature activation+0.000
Top resid features:
last
Token last
Feature activation+0.000
Top resid features:
season
Token season
Feature activation+0.000
Top resid features:
Sc
Token Sc
Feature activation+0.002
Top resid features:
uff
Tokenuff
Feature activation-0.011
Top resid features:
les
Tokenles
Feature activation+0.000
Top resid features:
between
Token between
Feature activation-0.067
Top resid features:
lawmakers
Token lawmakers
Feature activation+0.025
Top resid features:
forced
Token forced
Feature activation+5.393
Top resid features:
a
Token a
Feature activation+0.247
Top resid features:
brief
Token brief
Feature activation+0.066
Top resid features:
suspension
Token suspension
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
55
Token 55
Feature activation+0.016
Top resid features:
days
Token days
Feature activation+0.023
Top resid features:
of
Token of
Feature activation+0.017
Top resid features:
fighting
Token fighting
Feature activation+0.044
Top resid features:
,
Token,
Feature activation+0.044
Top resid features:
forced
Token forced
Feature activation+5.060
Top resid features:
the
Token the
Feature activation+0.364
Top resid features:
complete
Token complete
Feature activation+0.013
Top resid features:
surrender
Token surrender
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:
our
Token our
Feature activation+0.074
Top resid features:
sw
Token sw
Feature activation+0.018
Top resid features:
el
Tokenel
Feature activation+0.012
Top resid features:
tering
Tokentering
Feature activation+0.021
Top resid features:
region
Token region
Feature activation+0.022
Top resid features:
forces
Token forces
Feature activation+4.583
Top resid features:
a
Token a
Feature activation+0.172
Top resid features:
theological
Token theological
Feature activation+0.245
Top resid features:
question
Token question
Feature activation+0.350
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
How
Token How
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.021
Top resid features:
heading
Token heading
Feature activation-0.003
Top resid features:
to
Token to
Feature activation-0.024
Top resid features:
court
Token court
Feature activation-0.003
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
force
Token force
Feature activation+5.002
Top resid features:
a
Token a
Feature activation+0.177
Top resid features:
sleepy
Token sleepy
Feature activation+0.011
Top resid features:
East
Token East
Feature activation+0.013
Top resid features:
Bay
Token Bay
Feature activation-0.016
Top resid features:
suburb
Token suburb
Feature activation+0.319
Top resid features:
our
Token our
Feature activation+0.067
Top resid features:
sw
Token sw
Feature activation+0.003
Top resid features:
el
Tokenel
Feature activation+0.017
Top resid features:
tering
Tokentering
Feature activation+0.018
Top resid features:
region
Token region
Feature activation+0.031
Top resid features:
forces
Token forces
Feature activation+4.501
Top resid features:
a
Token a
Feature activation+0.617
Top resid features:
theological
Token theological
Feature activation+0.128
Top resid features:
question
Token question
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
How
Token How
Feature activation+0.000
Top resid features:
Housing
Token Housing
Feature activation-0.021
Top resid features:
and
Token and
Feature activation-0.007
Top resid features:
Planning
Token Planning
Feature activation+0.001
Top resid features:
Bill
Token Bill
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.074
Top resid features:
forced
Token forced
Feature activation+4.842
Top resid features:
academ
Token academ
Feature activation-0.079
Top resid features:
isation
Tokenisation
Feature activation+0.313
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
local
Token local
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
a
Token a
Feature activation+0.026
Top resid features:
party
Token party
Feature activation+0.046
Top resid features:
line
Token line
Feature activation-0.018
Top resid features:
vote
Token vote
Feature activation+0.018
Top resid features:
forced
Token forced
Feature activation+4.568
Top resid features:
her
Token her
Feature activation+0.399
Top resid features:
off
Token off
Feature activation-0.009
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
floor
Token floor
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
ris
Tokenris
Feature activation-0.004
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
Detroit
Token Detroit
Feature activation-0.020
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
who
Token who
Feature activation+0.099
Top resid features:
forced
Token forced
Feature activation+4.960
Top resid features:
their
Token their
Feature activation+0.007
Top resid features:
Burger
Token Burger
Feature activation+0.000
Top resid features:
King
Token King
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
close
Token close
Feature activation+0.000
Top resid features:
create
Token create
Feature activation-0.019
Top resid features:
a
Token a
Feature activation-0.013
Top resid features:
weapon
Token weapon
Feature activation+0.004
Top resid features:
that
Token that
Feature activation+0.043
Top resid features:
would
Token would
Feature activation+0.030
Top resid features:
force
Token force
Feature activation+4.542
Top resid features:
the
Token the
Feature activation+0.083
Top resid features:
D
Token D
Feature activation+0.079
Top resid features:
ax
Tokenax
Feature activation+0.021
Top resid features:
am
Tokenam
Feature activation-0.003
Top resid features:
ites
Tokenites
Feature activation+0.467
Top resid features:
China
Token China
Feature activation+0.034
Top resid features:
.
Token.
Feature activation+0.045
Top resid features:
The
Token The
Feature activation+0.005
Top resid features:
case
Token case
Feature activation-0.001
Top resid features:
has
Token has
Feature activation+0.026
Top resid features:
forced
Token forced
Feature activation+4.283
Top resid features:
the
Token the
Feature activation+0.151
Top resid features:
Communist
Token Communist
Feature activation+0.196
Top resid features:
leadership
Token leadership
Feature activation+0.220
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
confront
Token confront
Feature activation+0.000
Top resid features:
Sc
Token Sc
Feature activation+0.010
Top resid features:
uff
Tokenuff
Feature activation+0.019
Top resid features:
les
Tokenles
Feature activation+0.033
Top resid features:
between
Token between
Feature activation-0.128
Top resid features:
lawmakers
Token lawmakers
Feature activation+0.030
Top resid features:
forced
Token forced
Feature activation+4.943
Top resid features:
a
Token a
Feature activation-0.074
Top resid features:
brief
Token brief
Feature activation+0.000
Top resid features:
suspension
Token suspension
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
lock
Token lock
Feature activation+0.038
Top resid features:
-
Token-
Feature activation+0.019
Top resid features:
ups
Tokenups
Feature activation-0.010
Top resid features:
that
Token that
Feature activation+0.067
Top resid features:
ultimately
Token ultimately
Feature activation-0.016
Top resid features:
forced
Token forced
Feature activation+4.253
Top resid features:
the
Token the
Feature activation+0.457
Top resid features:
extra
Token extra
Feature activation+0.125
Top resid features:
pit
Token pit
Feature activation+0.000
Top resid features:
st
Tokenst
Feature activation+0.000
Top resid features:
ops
Tokenops
Feature activation+0.000
Top resid features:
ris
Tokenris
Feature activation-0.006
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
Detroit
Token Detroit
Feature activation-0.028
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
who
Token who
Feature activation+0.062
Top resid features:
forced
Token forced
Feature activation+4.050
Top resid features:
their
Token their
Feature activation+0.299
Top resid features:
Burger
Token Burger
Feature activation+0.056
Top resid features:
King
Token King
Feature activation+0.376
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
close
Token close
Feature activation+0.000
Top resid features:
soon
Token soon
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.090
Top resid features:
America
Token America
Feature activation+0.110
Top resid features:
will
Token will
Feature activation+0.044
Top resid features:
be
Token be
Feature activation+0.031
Top resid features:
forced
Token forced
Feature activation+4.834
Top resid features:
into
Token into
Feature activation-0.129
Top resid features:
water
Token water
Feature activation+0.000
Top resid features:
wars
Token wars
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
order
Token order
Feature activation+0.000
Top resid features:
break
Token break
Feature activation+0.022
Top resid features:
with
Token with
Feature activation-0.008
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
past
Token past
Feature activation+0.016
Top resid features:
that
Token that
Feature activation+0.083
Top resid features:
forced
Token forced
Feature activation+4.337
Top resid features:
Ge
Token Ge
Feature activation+0.151
Top resid features:
og
Tokenog
Feature activation+0.036
Top resid features:
he
Tokenhe
Feature activation-0.067
Top resid features:
gan
Tokengan
Feature activation+0.438
Top resid features:
into
Token into
Feature activation-0.097
Top resid features:
our
Token our
Feature activation+0.059
Top resid features:
people
Token people
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.080
Top resid features:
This
Token This
Feature activation+0.068
Top resid features:
will
Token will
Feature activation+0.035
Top resid features:
force
Token force
Feature activation+4.426
Top resid features:
our
Token our
Feature activation+0.048
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
wars
Token wars
Feature activation+0.000
Top resid features:
endless
Token endless
Feature activation+0.023
Top resid features:
racks
Token racks
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.022
Top resid features:
servers
Token servers
Feature activation+0.003
Top resid features:
soon
Token soon
Feature activation+0.003
Top resid features:
forces
Token forces
Feature activation+4.066
Top resid features:
now
Token now
Feature activation+0.065
Top resid features:
-
Token-
Feature activation+0.073
Top resid features:
under
Tokenunder
Feature activation+0.007
Top resid features:
staff
Tokenstaff
Feature activation+0.037
Top resid features:
ed
Tokened
Feature activation+0.027
Top resid features:

Decoder Weights Distribution

Head 0: 0.48

Head 1: 0.05

Head 2: 0.02

Head 3: 0.04

Head 4: 0.03

Head 5: 0.03

Head 6: 0.04

Head 7: 0.09

Head 8: 0.02

Head 9: 0.06

Head 10: 0.02

Head 11: 0.11

Positive logits

onto1.58

into1.44

havoc1.44

into1.35

nir1.34

awa1.27

onto1.24

wedge1.23

ressor1.19

INTO1.17

1.16

aeda1.14

DERR1.10

iscovery1.09

igure1.06

PUT1.06

ه1.04

Exit1.03

Narr1.03

Fla1.03

Negative logits

ording-1.15

istg-1.12

Typical-1.11

izoph-1.11

betrayed-1.08

龍契士-1.07

ICAN-1.03

"}],"-1.03

opal-1.02

terday-1.02

ordial-1.02

tipped-1.00

ufficient-1.00

FFFF-0.99

Blueprint-0.99

eric-0.98

00000000-0.98

使-0.98

"},{"-0.97

Threat-0.97

INTERVAL 4.185 - 4.650
CONTAINS 0.000%

15
Token15
Feature activation+0.000
Ju
Token Ju
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
forced
Token forced
Feature activation+0.000
the
Token the
Feature activation+2.983
longest
Token longest
Feature activation+4.650
average
Token average
Feature activation+1.200
shot
Token shot
Feature activation+0.191
in
Token in
Feature activation+0.507
Serie
Token Serie
Feature activation+0.000
A
Token A
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Bears
Token Bears
Feature activation+0.000
forced
Token forced
Feature activation+0.000
only
Token only
Feature activation+1.892
11
Token 11
Feature activation+4.255
turnovers
Token turnovers
Feature activation+2.016
last
Token last
Feature activation+0.000
season
Token season
Feature activation+0.000
,
Token,
Feature activation+0.082
tying
Token tying
Feature activation+0.000
forced
Token forced
Feature activation+0.000
the
Token the
Feature activation+2.526
extra
Token extra
Feature activation+3.408
pit
Token pit
Feature activation+0.000
st
Tokenst
Feature activation+0.000
ops
Tokenops
Feature activation+4.584
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
He
TokenHe
Feature activation+0.000
les
Tokenles
Feature activation+0.000
between
Token between
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
forced
Token forced
Feature activation+0.000
a
Token a
Feature activation+3.426
brief
Token brief
Feature activation+4.229
suspension
Token suspension
Feature activation+2.848
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
voting
Token voting
Feature activation+0.000
session
Token session
Feature activation+0.000

INTERVAL 3.720 - 4.185
CONTAINS 0.000%

of
Token of
Feature activation+0.000
fighting
Token fighting
Feature activation+0.000
,
Token,
Feature activation+0.000
forced
Token forced
Feature activation+0.000
the
Token the
Feature activation+2.937
complete
Token complete
Feature activation+4.164
surrender
Token surrender
Feature activation+2.935
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
French
Token French
Feature activation+0.000
colonial
Token colonial
Feature activation+0.000
a
Token a
Feature activation+2.823
sleepy
Token sleepy
Feature activation+2.609
East
Token East
Feature activation+1.096
Bay
Token Bay
Feature activation+0.769
suburb
Token suburb
Feature activation+1.753
to
Token to
Feature activation+3.941
go
Token go
Feature activation+0.000
dense
Token dense
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
el
Tokenel
Feature activation+0.000
tering
Tokentering
Feature activation+0.000
region
Token region
Feature activation+0.000
forces
Token forces
Feature activation+1.224
a
Token a
Feature activation+2.962
theological
Token theological
Feature activation+3.935
question
Token question
Feature activation+4.020
:
Token:
Feature activation+0.000
How
Token How
Feature activation+0.000
does
Token does
Feature activation+0.000
God
Token God
Feature activation+0.000
tering
Tokentering
Feature activation+0.000
region
Token region
Feature activation+0.000
forces
Token forces
Feature activation+1.224
a
Token a
Feature activation+2.962
theological
Token theological
Feature activation+3.935
question
Token question
Feature activation+4.020
:
Token:
Feature activation+0.000
How
Token How
Feature activation+0.000
does
Token does
Feature activation+0.000
God
Token God
Feature activation+0.000
feel
Token feel
Feature activation+0.000

INTERVAL 3.255 - 3.720
CONTAINS 0.001%

case
Token case
Feature activation+0.000
has
Token has
Feature activation+0.000
forced
Token forced
Feature activation+0.000
the
Token the
Feature activation+2.572
Communist
Token Communist
Feature activation+1.741
leadership
Token leadership
Feature activation+3.429
to
Token to
Feature activation+1.579
confront
Token confront
Feature activation+0.000
allegations
Token allegations
Feature activation+0.000
of
Token of
Feature activation+0.000
wrongdoing
Token wrongdoing
Feature activation+0.000
in
Token in
Feature activation+0.000
Detroit
Token Detroit
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
forced
Token forced
Feature activation+0.000
their
Token their
Feature activation+3.483
Burger
Token Burger
Feature activation+1.556
King
Token King
Feature activation+3.392
to
Token to
Feature activation+2.574
close
Token close
Feature activation+0.000
for
Token for
Feature activation+0.000
uff
Tokenuff
Feature activation+0.000
les
Tokenles
Feature activation+0.000
between
Token between
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
forced
Token forced
Feature activation+0.000
a
Token a
Feature activation+3.426
brief
Token brief
Feature activation+4.229
suspension
Token suspension
Feature activation+2.848
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
voting
Token voting
Feature activation+0.000
people
Token people
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
will
Token will
Feature activation+0.000
force
Token force
Feature activation+0.000
our
Token our
Feature activation+3.290
people
Token people
Feature activation+2.387
into
Token into
Feature activation+2.219
more
Token more
Feature activation+0.000
wars
Token wars
Feature activation+0.000
of
Token of
Feature activation+0.000
Planning
Token Planning
Feature activation+0.000
Bill
Token Bill
Feature activation+0.000
,
Token,
Feature activation+0.000
forced
Token forced
Feature activation+0.000
academ
Token academ
Feature activation+0.000
isation
Tokenisation
Feature activation+3.564
,
Token,
Feature activation+0.742
the
Token the
Feature activation+0.155
local
Token local
Feature activation+0.000
isation
Tokenisation
Feature activation+1.432
of
Token of
Feature activation+0.000

INTERVAL 2.790 - 3.255
CONTAINS 0.002%

between
Token between
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
forced
Token forced
Feature activation+0.000
a
Token a
Feature activation+3.426
brief
Token brief
Feature activation+4.229
suspension
Token suspension
Feature activation+2.848
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
voting
Token voting
Feature activation+0.000
session
Token session
Feature activation+0.000
.
Token.
Feature activation+0.000
/
Token/
Feature activation+0.000
15
Token15
Feature activation+0.000
Ju
Token Ju
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
forced
Token forced
Feature activation+0.000
the
Token the
Feature activation+2.983
longest
Token longest
Feature activation+4.650
average
Token average
Feature activation+1.200
shot
Token shot
Feature activation+0.191
in
Token in
Feature activation+0.507
Serie
Token Serie
Feature activation+0.000
sw
Token sw
Feature activation+0.000
el
Tokenel
Feature activation+0.000
tering
Tokentering
Feature activation+0.000
region
Token region
Feature activation+0.000
forces
Token forces
Feature activation+1.224
a
Token a
Feature activation+2.962
theological
Token theological
Feature activation+3.935
question
Token question
Feature activation+4.020
:
Token:
Feature activation+0.000
How
Token How
Feature activation+0.000
does
Token does
Feature activation+0.000
the
Token the
Feature activation+0.000
federal
Token federal
Feature activation+0.000
level
Token level
Feature activation+0.000
and
Token and
Feature activation+0.000
forced
Token forced
Feature activation+0.000
on
Token on
Feature activation+2.884
every
Token every
Feature activation+0.000
American
Token American
Feature activation+0.000
community
Token community
Feature activation+0.000
,
Token,
Feature activation+0.000
whether
Token whether
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.408
s
Tokens
Feature activation+2.853
law
Token law
Feature activation+2.203
enforcement
Token enforcement
Feature activation+1.964
staff
Token staff
Feature activation+3.143
to
Token to
Feature activation+2.901
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
obviously
Token obviously
Feature activation+0.000
reveals
Token reveals
Feature activation+0.000

INTERVAL 2.325 - 2.790
CONTAINS 0.002%

early
Token early
Feature activation+2.934
in
Token in
Feature activation+0.673
the
Token the
Feature activation+0.000
Korean
Token Korean
Feature activation+0.000
War
Token War
Feature activation+0.000
from
Token from
Feature activation+2.508
August
Token August
Feature activation+0.000
15
Token 15
Feature activation+0.000
to
Token to
Feature activation+0.000
September
Token September
Feature activation+0.000
19
Token 19
Feature activation+0.000
who
Token who
Feature activation+0.000
forced
Token forced
Feature activation+0.000
their
Token their
Feature activation+3.483
Burger
Token Burger
Feature activation+1.556
King
Token King
Feature activation+3.392
to
Token to
Feature activation+2.574
close
Token close
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
day
Token day
Feature activation+0.000
in
Token in
Feature activation+0.000
under
Tokenunder
Feature activation+0.000
staff
Tokenstaff
Feature activation+1.680
ed
Tokened
Feature activation+2.796
IT
Token IT
Feature activation+1.611
managers
Token managers
Feature activation+3.251
to
Token to
Feature activation+2.707
shut
Token shut
Feature activation+0.000
them
Token them
Feature activation+0.000
down
Token down
Feature activation+0.000
,
Token,
Feature activation+0.000
costing
Token costing
Feature activation+0.000
ST
Token ST
Feature activation+0.000
P
TokenP
Feature activation+0.000
plans
Token plans
Feature activation+0.000
would
Token would
Feature activation+0.000
force
Token force
Feature activation+0.000
the
Token the
Feature activation+2.515
closure
Token closure
Feature activation+2.807
of
Token of
Feature activation+0.000
E
Token E
Feature activation+0.000
aling
Tokenaling
Feature activation+0.000
and
Token and
Feature activation+0.000
towns
Token towns
Feature activation+0.000
folk
Tokenfolk
Feature activation+0.000
fear
Token fear
Feature activation+0.000
that
Token that
Feature activation+0.000
forcing
Token forcing
Feature activation+0.000
Muhammad
Token Muhammad
Feature activation+2.403
to
Token to
Feature activation+1.098
appear
Token appear
Feature activation+0.000
in
Token in
Feature activation+0.000
public
Token public
Feature activation+0.000
will
Token will
Feature activation+0.000

INTERVAL 1.860 - 2.325
CONTAINS 0.003%

I
TokenI
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
force
Token force
Feature activation+0.000
Bethesda
Token Bethesda
Feature activation+1.749
to
Token to
Feature activation+2.189
reveal
Token reveal
Feature activation+0.000
something
Token something
Feature activation+0.000
during
Token during
Feature activation+0.000
VG
Token VG
Feature activation+0.000
X
TokenX
Feature activation+0.000
his
Token his
Feature activation+0.000
gam
Token gam
Feature activation+0.000
bit
Tokenbit
Feature activation+0.000
forced
Token forced
Feature activation+0.000
China
Token China
Feature activation+1.967
to
Token to
Feature activation+2.126
deal
Token deal
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
scandal
Token scandal
Feature activation+0.000
with
Token with
Feature activation+0.000
said
Token said
Feature activation+0.000
his
Token his
Feature activation+0.000
gam
Token gam
Feature activation+0.000
bit
Tokenbit
Feature activation+0.000
forced
Token forced
Feature activation+0.000
China
Token China
Feature activation+1.967
to
Token to
Feature activation+2.126
deal
Token deal
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
scandal
Token scandal
Feature activation+0.000
Mon
Token Mon
Feature activation+0.000
-
Token-
Feature activation+0.000
El
TokenEl
Feature activation+0.000
was
Token was
Feature activation+0.000
forced
Token forced
Feature activation+0.000
off
Token off
Feature activation+2.249
the
Token the
Feature activation+0.000
planet
Token planet
Feature activation+0.000
to
Token to
Feature activation+0.000
survive
Token survive
Feature activation+0.000
,
Token,
Feature activation+0.000
idea
Token idea
Feature activation+0.000
they
Token they
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.000
forced
Token forced
Feature activation+0.000
him
Token him
Feature activation+2.121
to
Token to
Feature activation+0.184
kick
Token kick
Feature activation+0.000
me
Token me
Feature activation+0.000
and
Token and
Feature activation+0.000
Bill
Token Bill
Feature activation+0.000

INTERVAL 1.395 - 1.860
CONTAINS 0.003%

situation
Token situation
Feature activation+0.000
forces
Token forces
Feature activation+1.133
Moscow
Token Moscow
Feature activation+1.710
and
Token and
Feature activation+2.091
Tehran
Token Tehran
Feature activation+1.170
to
Token to
Feature activation+1.852
adjust
Token adjust
Feature activation+0.000
their
Token their
Feature activation+0.000
plans
Token plans
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
Panama
Token Panama
Feature activation+0.000
Papers
Token Papers
Feature activation+0.000
have
Token have
Feature activation+0.000
forced
Token forced
Feature activation+0.000
British
Token British
Feature activation+1.588
politicians
Token politicians
Feature activation+2.196
to
Token to
Feature activation+0.796
reveal
Token reveal
Feature activation+0.000
tax
Token tax
Feature activation+0.000
details
Token details
Feature activation+0.000
conflict
Token conflict
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
situation
Token situation
Feature activation+0.000
forces
Token forces
Feature activation+1.133
Moscow
Token Moscow
Feature activation+1.710
and
Token and
Feature activation+2.091
Tehran
Token Tehran
Feature activation+1.170
to
Token to
Feature activation+1.852
adjust
Token adjust
Feature activation+0.000
their
Token their
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000
force
Token force
Feature activation+0.000
Bethesda
Token Bethesda
Feature activation+1.749
to
Token to
Feature activation+2.189
reveal
Token reveal
Feature activation+0.000
something
Token something
Feature activation+0.000
during
Token during
Feature activation+0.000
VG
Token VG
Feature activation+0.000
force
Token force
Feature activation+0.000
the
Token the
Feature activation+2.479
D
Token D
Feature activation+0.678
ax
Tokenax
Feature activation+0.000
am
Tokenam
Feature activation+0.000
ites
Tokenites
Feature activation+1.704
off
Token off
Feature activation+3.470
of
Token of
Feature activation+0.000
Earth
Token Earth
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000

INTERVAL 0.930 - 1.395
CONTAINS 0.004%

,
Token,
Feature activation+0.000
Henderson
Token Henderson
Feature activation+0.000
forced
Token forced
Feature activation+0.000
Mas
Token Mas
Feature activation+0.000
v
Tokenv
Feature activation+0.000
idal
Tokenidal
Feature activation+1.135
to
Token to
Feature activation+2.167
resort
Token resort
Feature activation+0.000
to
Token to
Feature activation+0.000
throwing
Token throwing
Feature activation+0.000
strikes
Token strikes
Feature activation+0.000
animals
Token animals
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
forced
Token forced
Feature activation+1.271
to
Token to
Feature activation+0.220
make
Token make
Feature activation+0.000
changes
Token changes
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Depression
Token Depression
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
forced
Token forced
Feature activation+0.000
Zion
Token Zion
Feature activation+0.600
Industries
Token Industries
Feature activation+1.020
into
Token into
Feature activation+3.137
bankruptcy
Token bankruptcy
Feature activation+0.000
.
Token.
Feature activation+0.119
In
Token In
Feature activation+0.000
1935
Token 1935
Feature activation+0.000
the
Token the
Feature activation+0.000
conflict
Token conflict
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
situation
Token situation
Feature activation+0.000
forces
Token forces
Feature activation+1.133
Moscow
Token Moscow
Feature activation+1.710
and
Token and
Feature activation+2.091
Tehran
Token Tehran
Feature activation+1.170
to
Token to
Feature activation+1.852
adjust
Token adjust
Feature activation+0.000
hem
Tokenhem
Feature activation+0.000
ite
Tokenite
Feature activation+0.000
regime
Token regime
Feature activation+2.832
in
Token in
Feature activation+2.025
Jordan
Token Jordan
Feature activation+0.000
to
Token to
Feature activation+1.177
abandon
Token abandon
Feature activation+0.000
its
Token its
Feature activation+0.000
pro
Token pro
Feature activation+0.000
-
Token-
Feature activation+0.000
Western
TokenWestern
Feature activation+0.000

INTERVAL 0.465 - 0.930
CONTAINS 0.005%

er
Tokener
Feature activation+0.000
because
Token because
Feature activation+0.000
he
Token he
Feature activation+0.000
forces
Token forces
Feature activation+0.000
me
Token me
Feature activation+1.468
to
Token to
Feature activation+0.521
see
Token see
Feature activation+0.000
things
Token things
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
often
Token often
Feature activation+0.000
government
Token government
Feature activation+0.000
from
Token from
Feature activation+0.000
compelling
Token compelling
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
service
Token service
Feature activation+0.025
providers
Token providers
Feature activation+0.812
to
Token to
Feature activation+0.212
secretly
Token secretly
Feature activation+0.000
permit
Token permit
Feature activation+0.000
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.000
Bill
Token Bill
Feature activation+0.000
,
Token,
Feature activation+0.000
forced
Token forced
Feature activation+0.000
academ
Token academ
Feature activation+0.000
isation
Tokenisation
Feature activation+3.564
,
Token,
Feature activation+0.742
the
Token the
Feature activation+0.155
local
Token local
Feature activation+0.000
isation
Tokenisation
Feature activation+1.432
of
Token of
Feature activation+0.000
business
Token business
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
possibly
Token possibly
Feature activation+0.000
forcing
Token forcing
Feature activation+0.536
cycles
Token cycles
Feature activation+2.170
of
Token of
Feature activation+0.220
freezing
Token freezing
Feature activation+0.000
and
Token and
Feature activation+0.000
th
Token th
Feature activation+0.000
forced
Token forced
Feature activation+0.000
the
Token the
Feature activation+2.983
longest
Token longest
Feature activation+4.650
average
Token average
Feature activation+1.200
shot
Token shot
Feature activation+0.191
in
Token in
Feature activation+0.507
Serie
Token Serie
Feature activation+0.000
A
Token A
Feature activation+0.000
,
Token,
Feature activation+0.000
now
Token now
Feature activation+0.000
they
Token they
Feature activation+0.000

INTERVAL 0.000 - 0.465
CONTAINS 99.979%

a
Token a
Feature activation+0.000
spider
Token spider
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
irrad
Token irrad
Feature activation+0.000
iated
Tokeniated
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
rather
Token rather
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
interest
Token interest
Feature activation+0.000
to
Token to
Feature activation+0.000
treat
Token treat
Feature activation+0.000
the
Token the
Feature activation+0.000
women
Token women
Feature activation+0.000
well
Token well
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
for
Token for
Feature activation+0.000
somehow
Token somehow
Feature activation+0.000
,
Token,
Feature activation+0.000
things
Token things
Feature activation+0.000
seem
Token seem
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
off
Token off
Feature activation+0.000
.
Token.
Feature activation+0.000
Especially
Token Especially
Feature activation+0.000
that
Token that
Feature activation+0.000
too
Token too
Feature activation+0.000
-
Token-
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
exceptionally
Token exceptionally
Feature activation+0.000
eclectic
Token eclectic
Feature activation+0.000
,
Token,
Feature activation+0.000
art
Token art
Feature activation+0.000
fully
Tokenfully
Feature activation+0.000
affordable
Token affordable
Feature activation+0.000
store
Token store
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
tim
Tokentim
Feature activation+0.000
ing
Tokening
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
and
Token and
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
im
Tokenim
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