H7.3 top features

Top feature 0 in H7.3: (feature 11281)

TOP ACTIVATIONS
MAX = 5.183

hosts
Token hosts
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
guests
Token guests
Feature activation+1.480
are
Token are
Feature activation+5.183
the
Token the
Feature activation+2.553
real
Token real
Feature activation+0.845
protagonists
Token protagonists
Feature activation+0.363
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
income
Token income
Feature activation+0.020
of
Token of
Feature activation+0.326
households
Token households
Feature activation+0.000
,
Token,
Feature activation+4.735
which
Token which
Feature activation+2.505
has
Token has
Feature activation+1.383
fluct
Token fluct
Feature activation+0.000
uated
Tokenuated
Feature activation+0.046
as
Token as
Feature activation+0.000
droid
Token droid
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+1.207
a
Token a
Feature activation+0.947
humanoid
Token humanoid
Feature activation+0.733
,
Token,
Feature activation+4.427
who
Token who
Feature activation+2.364
refers
Token refers
Feature activation+0.185
to
Token to
Feature activation+0.193
a
Token a
Feature activation+0.000
supreme
Token supreme
Feature activation+0.000
A
Token A
Feature activation+0.000
doctor
Token doctor
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
legislators
Token legislators
Feature activation+0.093
,
Token,
Feature activation+3.652
should
Token should
Feature activation+2.361
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
ability
Token ability
Feature activation+0.198
to
Token to
Feature activation+0.404
building
Token building
Feature activation+0.000
bridges
Token bridges
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
walls
Token walls
Feature activation+0.384
,
Token,
Feature activation+3.601
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
his
Token his
Feature activation+0.000
remark
Token remark
Feature activation+0.000
on
Token on
Feature activation+0.000
U
TokenU
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
Premiership
Token Premiership
Feature activation+0.000
Rugby
Token Rugby
Feature activation+0.000
,
Token,
Feature activation+3.448
and
Token and
Feature activation+0.063
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
't
Token't
Feature activation+0.000
just
Token just
Feature activation+0.000
said
Token said
Feature activation+0.000
Wang
Token Wang
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
Bo
Token Bo
Feature activation+0.000
,
Token,
Feature activation+3.185
"
Token "
Feature activation+0.223
is
Tokenis
Feature activation+1.472
probably
Token probably
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
to
Token to
Feature activation+0.179
help
Token help
Feature activation+0.099
make
Token make
Feature activation+0.000
it
Token it
Feature activation+0.092
right
Token right
Feature activation+0.071
,
Token,
Feature activation+3.080
has
Token has
Feature activation+1.017
become
Token become
Feature activation+1.135
all
Token all
Feature activation+0.000
too
Token too
Feature activation+0.000
common
Token common
Feature activation+0.000
policy
Token policy
Feature activation+0.000
improvements
Token improvements
Feature activation+0.000
from
Token from
Feature activation+0.000
federal
Token federal
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+2.869
has
Token has
Feature activation+0.639
provided
Token provided
Feature activation+0.000
the
Token the
Feature activation+0.000
vast
Token vast
Feature activation+0.000
majority
Token majority
Feature activation+0.000
,
Token,
Feature activation+0.227
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
carrot
Token carrot
Feature activation+0.000
,
Token,
Feature activation+2.839
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.020
demand
Token demand
Feature activation+0.000
that
Token that
Feature activation+0.000
those
Token those
Feature activation+0.000
are
Token are
Feature activation+0.000
flexible
Token flexible
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
rigid
Token rigid
Feature activation+0.487
,
Token,
Feature activation+2.758
so
Token so
Feature activation+0.000
their
Token their
Feature activation+0.000
shape
Token shape
Feature activation+0.000
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
guests
Token guests
Feature activation+1.480
are
Token are
Feature activation+5.183
the
Token the
Feature activation+2.553
real
Token real
Feature activation+0.845
protagonists
Token protagonists
Feature activation+0.363
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
not
Token not
Feature activation+0.000
for
Token for
Feature activation+0.000
simply
Token simply
Feature activation+0.000
showing
Token showing
Feature activation+0.000
up
Token up
Feature activation+0.000
,
Token,
Feature activation+2.514
or
Token or
Feature activation+0.000
mind
Token mind
Feature activation+0.000
lessly
Tokenlessly
Feature activation+0.000
driving
Token driving
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
income
Token income
Feature activation+0.020
of
Token of
Feature activation+0.326
households
Token households
Feature activation+0.000
,
Token,
Feature activation+4.735
which
Token which
Feature activation+2.505
has
Token has
Feature activation+1.383
fluct
Token fluct
Feature activation+0.000
uated
Tokenuated
Feature activation+0.046
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+0.026
the
Token the
Feature activation+0.000
tumor
Token tumor
Feature activation+0.000
,
Token,
Feature activation+2.438
in
Token in
Feature activation+0.636
the
Token the
Feature activation+0.640
hopes
Token hopes
Feature activation+0.000
of
Token of
Feature activation+0.000
generating
Token generating
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+1.207
a
Token a
Feature activation+0.947
humanoid
Token humanoid
Feature activation+0.733
,
Token,
Feature activation+4.427
who
Token who
Feature activation+2.364
refers
Token refers
Feature activation+0.185
to
Token to
Feature activation+0.193
a
Token a
Feature activation+0.000
supreme
Token supreme
Feature activation+0.000
being
Token being
Feature activation+0.000
doctor
Token doctor
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
legislators
Token legislators
Feature activation+0.093
,
Token,
Feature activation+3.652
should
Token should
Feature activation+2.361
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
ability
Token ability
Feature activation+0.198
to
Token to
Feature activation+0.404
prescribe
Token prescribe
Feature activation+0.000
be
Token be
Feature activation+0.000
sued
Token sued
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+2.341
by
Token by
Feature activation+0.000
Allah
Token Allah
Feature activation+0.000
,
Token,
Feature activation+0.588
I
Token I
Feature activation+0.000
swear
Token swear
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
not
Token not
Feature activation+0.000
in
Token in
Feature activation+0.000
Milwaukee
Token Milwaukee
Feature activation+0.309
,
Token,
Feature activation+2.293
than
Token than
Feature activation+0.000
most
Token most
Feature activation+0.000
likely
Token likely
Feature activation+0.000
in
Token in
Feature activation+0.000
Seattle
Token Seattle
Feature activation+0.000
Idaho
Token Idaho
Feature activation+0.000
and
Token and
Feature activation+0.000
Alaska
Token Alaska
Feature activation+0.000
and
Token and
Feature activation+0.000
Arizona
Token Arizona
Feature activation+0.000
,
Token,
Feature activation+2.228
which
Token which
Feature activation+0.125
are
Token are
Feature activation+0.267
also
Token also
Feature activation+0.000
covered
Token covered
Feature activation+0.000
by
Token by
Feature activation+0.000

Top DFA by src position
MAX = 5.499

feature
Token feature
Feature activation+0.001
Top resid features:
:
Token:
Feature activation-0.019
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
hosts
Token hosts
Feature activation+0.032
Top resid features:
and
Token and
Feature activation+0.051
Top resid features:
not
Token not
Feature activation+5.499
Top resid features:
the
Token the
Feature activation+0.224
Top resid features:
guests
Token guests
Feature activation+0.098
Top resid features:
are
Token are
Feature activation+0.025
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
real
Token real
Feature activation+0.000
Top resid features:
individuals
Token individuals
Feature activation+0.040
Top resid features:
âĢ
TokenâĢ
Feature activation+0.009
Top resid features:
Ļ
TokenĻ
Feature activation+0.016
Top resid features:
income
Token income
Feature activation+0.018
Top resid features:
,
Token,
Feature activation+0.040
Top resid features:
not
Token not
Feature activation+4.598
Top resid features:
the
Token the
Feature activation+0.561
Top resid features:
income
Token income
Feature activation+0.025
Top resid features:
of
Token of
Feature activation-0.034
Top resid features:
households
Token households
Feature activation-0.025
Top resid features:
,
Token,
Feature activation+0.072
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation+0.002
Top resid features:
a
Token a
Feature activation+0.016
Top resid features:
droid
Token droid
Feature activation+0.038
Top resid features:
,
Token,
Feature activation+0.184
Top resid features:
not
Token not
Feature activation+4.261
Top resid features:
a
Token a
Feature activation+0.542
Top resid features:
humanoid
Token humanoid
Feature activation+0.028
Top resid features:
,
Token,
Feature activation+0.056
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
refers
Token refers
Feature activation+0.000
Top resid features:
method
Token method
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
A
Token A
Feature activation+0.001
Top resid features:
doctor
Token doctor
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
not
Token not
Feature activation+4.105
Top resid features:
legislators
Token legislators
Feature activation+0.162
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
should
Token should
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
speaks
Token speaks
Feature activation-0.021
Top resid features:
about
Token about
Feature activation+0.010
Top resid features:
building
Token building
Feature activation-0.028
Top resid features:
bridges
Token bridges
Feature activation-0.046
Top resid features:
,
Token,
Feature activation+0.051
Top resid features:
not
Token not
Feature activation+4.263
Top resid features:
walls
Token walls
Feature activation+0.033
Top resid features:
,
Token,
Feature activation+0.046
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.013
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
RF
Token RF
Feature activation+0.008
Top resid features:
U
TokenU
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.032
Top resid features:
not
Token not
Feature activation+3.948
Top resid features:
Premiership
Token Premiership
Feature activation-0.013
Top resid features:
Rugby
Token Rugby
Feature activation+0.088
Top resid features:
,
Token,
Feature activation+0.067
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
Pa
Token Pa
Feature activation-0.007
Top resid features:
al
Tokenal
Feature activation+0.002
Top resid features:
said
Token said
Feature activation+0.032
Top resid features:
Wang
Token Wang
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
not
Token not
Feature activation+3.693
Top resid features:
Bo
Token Bo
Feature activation+0.052
Top resid features:
,
Token,
Feature activation+0.074
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
is
Tokenis
Feature activation+0.000
Top resid features:
probably
Token probably
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
our
Token our
Feature activation-0.003
Top resid features:
world
Token world
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
rather
Token rather
Feature activation+1.173
Top resid features:
than
Token than
Feature activation+2.300
Top resid features:
a
Token a
Feature activation+0.136
Top resid features:
force
Token force
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
help
Token help
Feature activation-0.005
Top resid features:
make
Token make
Feature activation-0.021
Top resid features:
quality
Token quality
Feature activation-0.012
Top resid features:
from
Token from
Feature activation+0.037
Top resid features:
competing
Token competing
Feature activation-0.002
Top resid features:
companies
Token companies
Feature activation-0.003
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.034
Top resid features:
not
Token not
Feature activation+3.276
Top resid features:
claimed
Token claimed
Feature activation+0.018
Top resid features:
policy
Token policy
Feature activation+0.026
Top resid features:
improvements
Token improvements
Feature activation+0.004
Top resid features:
from
Token from
Feature activation+0.067
Top resid features:
federal
Token federal
Feature activation-0.004
Top resid features:
use
Token use
Feature activation-0.010
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
stick
Token stick
Feature activation-0.024
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
rather
Token rather
Feature activation+0.455
Top resid features:
than
Token than
Feature activation+2.507
Top resid features:
the
Token the
Feature activation+0.453
Top resid features:
carrot
Token carrot
Feature activation-0.016
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
must
Token must
Feature activation+0.000
Top resid features:
things
Tokenthings
Feature activation+0.004
Top resid features:
that
Token that
Feature activation-0.010
Top resid features:
are
Token are
Feature activation-0.015
Top resid features:
flexible
Token flexible
Feature activation-0.070
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
not
Token not
Feature activation+3.488
Top resid features:
rigid
Token rigid
Feature activation-0.031
Top resid features:
,
Token,
Feature activation+0.039
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
shape
Token shape
Feature activation+0.000
Top resid features:
feature
Token feature
Feature activation+0.001
Top resid features:
:
Token:
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
hosts
Token hosts
Feature activation-0.109
Top resid features:
and
Token and
Feature activation+0.037
Top resid features:
not
Token not
Feature activation+3.031
Top resid features:
the
Token the
Feature activation+0.262
Top resid features:
guests
Token guests
Feature activation+0.062
Top resid features:
are
Token are
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
real
Token real
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
job
Token job
Feature activation+0.008
Top resid features:
well
Token well
Feature activation+0.013
Top resid features:
done
Token done
Feature activation+0.029
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
not
Token not
Feature activation+2.915
Top resid features:
for
Token for
Feature activation+0.118
Top resid features:
simply
Token simply
Feature activation+0.092
Top resid features:
showing
Token showing
Feature activation+0.013
Top resid features:
up
Token up
Feature activation-0.034
Top resid features:
,
Token,
Feature activation+0.051
Top resid features:
individuals
Token individuals
Feature activation+0.031
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.020
Top resid features:
income
Token income
Feature activation+0.034
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
not
Token not
Feature activation+2.413
Top resid features:
the
Token the
Feature activation+0.271
Top resid features:
income
Token income
Feature activation+0.028
Top resid features:
of
Token of
Feature activation+0.076
Top resid features:
households
Token households
Feature activation+0.044
Top resid features:
,
Token,
Feature activation+0.116
Top resid features:
immune
Token immune
Feature activation+0.010
Top resid features:
system
Token system
Feature activation+0.019
Top resid features:
directly
Token directly
Feature activation+0.044
Top resid features:
,
Token,
Feature activation+0.043
Top resid features:
instead
Token instead
Feature activation+0.385
Top resid features:
of
Token of
Feature activation+2.102
Top resid features:
the
Token the
Feature activation+0.420
Top resid features:
tumor
Token tumor
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.054
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation+0.009
Top resid features:
a
Token a
Feature activation+0.048
Top resid features:
droid
Token droid
Feature activation+0.052
Top resid features:
,
Token,
Feature activation+0.106
Top resid features:
not
Token not
Feature activation+2.160
Top resid features:
a
Token a
Feature activation+0.500
Top resid features:
humanoid
Token humanoid
Feature activation+0.080
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
who
Token who
Feature activation+0.037
Top resid features:
refers
Token refers
Feature activation+0.000
Top resid features:
method
Token method
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
A
Token A
Feature activation+0.004
Top resid features:
doctor
Token doctor
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.028
Top resid features:
not
Token not
Feature activation+2.775
Top resid features:
legislators
Token legislators
Feature activation+0.118
Top resid features:
,
Token,
Feature activation+0.071
Top resid features:
should
Token should
Feature activation+0.018
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
They
Token They
Feature activation-0.001
Top resid features:
should
Token should
Feature activation+0.019
Top resid features:
be
Token be
Feature activation-0.001
Top resid features:
sued
Token sued
Feature activation+0.089
Top resid features:
,
Token,
Feature activation+0.056
Top resid features:
not
Token not
Feature activation+2.273
Top resid features:
me
Token me
Feature activation+0.369
Top resid features:
,
Token,
Feature activation+0.133
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
Allah
Token Allah
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
new
Token new
Feature activation-0.005
Top resid features:
arena
Token arena
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
if
Token if
Feature activation+0.151
Top resid features:
not
Token not
Feature activation+2.518
Top resid features:
in
Token in
Feature activation+0.229
Top resid features:
Milwaukee
Token Milwaukee
Feature activation+0.112
Top resid features:
,
Token,
Feature activation+0.073
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
only
Token only
Feature activation-0.015
Top resid features:
applied
Token applied
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.007
Top resid features:
California
Token California
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
not
Token not
Feature activation+2.767
Top resid features:
states
Token states
Feature activation+0.082
Top resid features:
like
Token like
Feature activation+0.022
Top resid features:
Idaho
Token Idaho
Feature activation-0.034
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
Alaska
Token Alaska
Feature activation+0.039
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.01

Head 3: 0.45

Head 4: 0.12

Head 5: 0.06

Head 6: 0.04

Head 7: 0.03

Head 8: 0.07

Head 9: 0.05

Head 10: 0.03

Head 11: 0.05

Positive logits

causation2.22

Construct1.96

construct1.90

ogenesis1.85

Caption1.82

beh1.80

fruitful1.74

src1.74

lead1.72

erate1.71

decisive1.70

adjud1.68

explanation1.67

worth1.67

Thy1.67

culp1.67

weight1.66

proceedings1.65

chalk1.65

stakes1.65

Negative logits

anmar-2.55

instead-2.36

NV-2.32

ivers-2.20

wcsstore-2.11

-2.09

nces-2.06

naissance-1.98

nb-1.95

instead-1.95

lov-1.94

nr-1.94

puter-1.93

edly-1.92

IENCE-1.89

liament-1.89

igl-1.87

thereto-1.86

Reincarn-1.82

FN-1.80

INTERVAL 4.665 - 5.183
CONTAINS 0.000%

not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
income
Token income
Feature activation+0.020
of
Token of
Feature activation+0.326
households
Token households
Feature activation+0.000
,
Token,
Feature activation+4.735
which
Token which
Feature activation+2.505
has
Token has
Feature activation+1.383
fluct
Token fluct
Feature activation+0.000
uated
Tokenuated
Feature activation+0.046
as
Token as
Feature activation+0.000
hosts
Token hosts
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
guests
Token guests
Feature activation+1.480
are
Token are
Feature activation+5.183
the
Token the
Feature activation+2.553
real
Token real
Feature activation+0.845
protagonists
Token protagonists
Feature activation+0.363
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 4.147 - 4.665
CONTAINS 0.000%

droid
Token droid
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+1.207
a
Token a
Feature activation+0.947
humanoid
Token humanoid
Feature activation+0.733
,
Token,
Feature activation+4.427
who
Token who
Feature activation+2.364
refers
Token refers
Feature activation+0.185
to
Token to
Feature activation+0.193
a
Token a
Feature activation+0.000
supreme
Token supreme
Feature activation+0.000

INTERVAL 3.628 - 4.147
CONTAINS 0.000%

A
Token A
Feature activation+0.000
doctor
Token doctor
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
legislators
Token legislators
Feature activation+0.093
,
Token,
Feature activation+3.652
should
Token should
Feature activation+2.361
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
ability
Token ability
Feature activation+0.198
to
Token to
Feature activation+0.404

INTERVAL 3.110 - 3.628
CONTAINS 0.000%

U
TokenU
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
Premiership
Token Premiership
Feature activation+0.000
Rugby
Token Rugby
Feature activation+0.000
,
Token,
Feature activation+3.448
and
Token and
Feature activation+0.063
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
't
Token't
Feature activation+0.000
just
Token just
Feature activation+0.000
said
Token said
Feature activation+0.000
Wang
Token Wang
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
Bo
Token Bo
Feature activation+0.000
,
Token,
Feature activation+3.185
"
Token "
Feature activation+0.223
is
Tokenis
Feature activation+1.472
probably
Token probably
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
building
Token building
Feature activation+0.000
bridges
Token bridges
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
walls
Token walls
Feature activation+0.384
,
Token,
Feature activation+3.601
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
his
Token his
Feature activation+0.000
remark
Token remark
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 2.592 - 3.110
CONTAINS 0.001%

policy
Token policy
Feature activation+0.000
improvements
Token improvements
Feature activation+0.000
from
Token from
Feature activation+0.000
federal
Token federal
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+2.869
has
Token has
Feature activation+0.639
provided
Token provided
Feature activation+0.000
the
Token the
Feature activation+0.000
vast
Token vast
Feature activation+0.000
majority
Token majority
Feature activation+0.000
,
Token,
Feature activation+0.227
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
carrot
Token carrot
Feature activation+0.000
,
Token,
Feature activation+2.839
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.020
demand
Token demand
Feature activation+0.000
that
Token that
Feature activation+0.000
those
Token those
Feature activation+0.000
are
Token are
Feature activation+0.000
flexible
Token flexible
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
rigid
Token rigid
Feature activation+0.487
,
Token,
Feature activation+2.758
so
Token so
Feature activation+0.000
their
Token their
Feature activation+0.000
shape
Token shape
Feature activation+0.000
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+0.000
to
Token to
Feature activation+0.179
help
Token help
Feature activation+0.099
make
Token make
Feature activation+0.000
it
Token it
Feature activation+0.092
right
Token right
Feature activation+0.071
,
Token,
Feature activation+3.080
has
Token has
Feature activation+1.017
become
Token become
Feature activation+1.135
all
Token all
Feature activation+0.000
too
Token too
Feature activation+0.000
common
Token common
Feature activation+0.000

INTERVAL 2.073 - 2.592
CONTAINS 0.001%

doctor
Token doctor
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
legislators
Token legislators
Feature activation+0.093
,
Token,
Feature activation+3.652
should
Token should
Feature activation+2.361
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
ability
Token ability
Feature activation+0.198
to
Token to
Feature activation+0.404
prescribe
Token prescribe
Feature activation+0.000
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+0.000
just
Token just
Feature activation+0.000
specific
Token specific
Feature activation+0.000
parts
Token parts
Feature activation+0.000
,
Token,
Feature activation+2.150
so
Token so
Feature activation+0.000
they
Token they
Feature activation+0.000
both
Token both
Feature activation+0.000
have
Token have
Feature activation+0.000
their
Token their
Feature activation+0.000
Idaho
Token Idaho
Feature activation+0.000
and
Token and
Feature activation+0.000
Alaska
Token Alaska
Feature activation+0.000
and
Token and
Feature activation+0.000
Arizona
Token Arizona
Feature activation+0.000
,
Token,
Feature activation+2.228
which
Token which
Feature activation+0.125
are
Token are
Feature activation+0.267
also
Token also
Feature activation+0.000
covered
Token covered
Feature activation+0.000
by
Token by
Feature activation+0.000
,
Token,
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+0.026
the
Token the
Feature activation+0.000
tumor
Token tumor
Feature activation+0.000
,
Token,
Feature activation+2.438
in
Token in
Feature activation+0.636
the
Token the
Feature activation+0.640
hopes
Token hopes
Feature activation+0.000
of
Token of
Feature activation+0.000
generating
Token generating
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
guests
Token guests
Feature activation+1.480
are
Token are
Feature activation+5.183
the
Token the
Feature activation+2.553
real
Token real
Feature activation+0.845
protagonists
Token protagonists
Feature activation+0.363
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.555 - 2.073
CONTAINS 0.001%

as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
personal
Token personal
Feature activation+0.000
vend
Token vend
Feature activation+0.000
etta
Tokenetta
Feature activation+0.000
,
Token,
Feature activation+1.603
but
Token but
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
shrew
Token shrew
Feature activation+0.000
d
Tokend
Feature activation+0.000
sitting
Token sitting
Feature activation+0.527
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
back
Token back
Feature activation+0.047
room
Token room
Feature activation+0.205
,
Token,
Feature activation+1.892
monitoring
Token monitoring
Feature activation+0.000
the
Token the
Feature activation+0.000
security
Token security
Feature activation+0.000
cameras
Token cameras
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
right
Token right
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.185
a
Token a
Feature activation+0.469
privilege
Token privilege
Feature activation+1.889
.
Token.
Feature activation+0.371
And
Token And
Feature activation+0.104
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
for
Token for
Feature activation+0.000
security
Token security
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
groceries
Token groceries
Feature activation+0.000
,
Token,
Feature activation+2.065
so
Token so
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
be
Token be
Feature activation+0.000
your
Token your
Feature activation+0.000
ally
Token ally
Feature activation+0.000
not
Token not
Feature activation+0.172
your
Token your
Feature activation+0.341
enemy
Token enemy
Feature activation+1.818
.
Token.
Feature activation+0.087
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ref
TokenRef
Feature activation+0.000
use
Tokenuse
Feature activation+0.000

INTERVAL 1.037 - 1.555
CONTAINS 0.003%

instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
core
Token core
Feature activation+0.000
muscles
Token muscles
Feature activation+0.004
,
Token,
Feature activation+1.190
to
Token to
Feature activation+0.191
support
Token support
Feature activation+0.000
their
Token their
Feature activation+0.000
weight
Token weight
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
goal
Token goal
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
mandate
Token mandate
Feature activation+1.123
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
lines
Token lines
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
not
Token not
Feature activation+0.000
immediately
Token immediately
Feature activation+0.000
,
Token,
Feature activation+1.496
said
Token said
Feature activation+0.000
Byron
Token Byron
Feature activation+0.000
Call
Token Call
Feature activation+0.000
an
Tokenan
Feature activation+0.000
,
Token,
Feature activation+0.000
suggestion
Token suggestion
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
not
Token not
Feature activation+0.098
an
Token an
Feature activation+0.148
instruction
Token instruction
Feature activation+0.022
,
Token,
Feature activation+1.328
nor
Token nor
Feature activation+0.000
an
Token an
Feature activation+0.000
order
Token order
Feature activation+0.000
or
Token or
Feature activation+0.000
a
Token a
Feature activation+0.000
an
Token an
Feature activation+0.000
order
Token order
Feature activation+0.000
or
Token or
Feature activation+0.000
a
Token a
Feature activation+0.000
directive
Token directive
Feature activation+0.000
,
Token,
Feature activation+1.047
much
Token much
Feature activation+0.030
less
Token less
Feature activation+0.000
three
Token three
Feature activation+0.000
directives
Token directives
Feature activation+0.000
.
Token.
Feature activation+0.676

INTERVAL 0.518 - 1.037
CONTAINS 0.014%

over
Token over
Feature activation+0.000
one
Token one
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+0.592
,
Token,
Feature activation+1.346
but
Token but
Feature activation+0.205
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.215
a
Tokena
Feature activation+0.000
improvements
Token improvements
Feature activation+0.000
from
Token from
Feature activation+0.000
federal
Token federal
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+2.869
has
Token has
Feature activation+0.639
provided
Token provided
Feature activation+0.000
the
Token the
Feature activation+0.000
vast
Token vast
Feature activation+0.000
majority
Token majority
Feature activation+0.000
of
Token of
Feature activation+0.000
individuals
Token individuals
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+0.525
banks
Token banks
Feature activation+0.000
,
Token,
Feature activation+0.864
are
Token are
Feature activation+0.567
lim
Token lim
Feature activation+0.000
ping
Tokenping
Feature activation+0.000
along
Token along
Feature activation+0.000
at
Token at
Feature activation+0.000
an
Token an
Feature activation+0.000
:
Token:
Feature activation+0.000
Russia
Token Russia
Feature activation+0.000
,
Token,
Feature activation+0.000
US
Token US
Feature activation+0.000
not
Token not
Feature activation+0.418
on
Token on
Feature activation+0.601
brink
Token brink
Feature activation+0.030
of
Token of
Feature activation+0.000
war
Token war
Feature activation+0.082
https
Token https
Feature activation+0.000
://
Token://
Feature activation+0.000
help
Token help
Feature activation+0.099
make
Token make
Feature activation+0.000
it
Token it
Feature activation+0.092
right
Token right
Feature activation+0.071
,
Token,
Feature activation+3.080
has
Token has
Feature activation+1.017
become
Token become
Feature activation+1.135
all
Token all
Feature activation+0.000
too
Token too
Feature activation+0.000
common
Token common
Feature activation+0.000
,"
Token,"
Feature activation+0.000

INTERVAL 0.000 - 0.518
CONTAINS 99.979%

an
Token an
Feature activation+0.000
emotionally
Token emotionally
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
subject
Token subject
Feature activation+0.000
under
Token under
Feature activation+0.000
cross
Token cross
Feature activation+0.000
-
Token-
Feature activation+0.000
examination
Tokenexamination
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
packed
Token packed
Feature activation+0.000
lack
Token lack
Feature activation+0.000
of
Token of
Feature activation+0.000
funds
Token funds
Feature activation+0.000
that
Token that
Feature activation+0.000
mass
Token mass
Feature activation+0.000
fish
Token fish
Feature activation+0.000
die
Token die
Feature activation+0.000
-
Token-
Feature activation+0.000
offs
Tokenoffs
Feature activation+0.000
are
Token are
Feature activation+0.000
a
Token a
Feature activation+0.000
redited
Tokenredited
Feature activation+0.000
production
Token production
Feature activation+0.000
from
Token from
Feature activation+0.000
Sv
Token Sv
Feature activation+0.000
idden
Tokenidden
Feature activation+0.000
and
Token and
Feature activation+0.000
unc
Token unc
Feature activation+0.000
redited
Tokenredited
Feature activation+0.000
vocals
Token vocals
Feature activation+0.000
from
Token from
Feature activation+0.000
Cathy
Token Cathy
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
protest
Token protest
Feature activation+0.000
appears
Token appears
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
struck
Token struck
Feature activation+0.000
a
Token a
Feature activation+0.000
nerve
Token nerve
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
most
Token most
Feature activation+0.000
critically
Token critically
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
he
Token he
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
believe
Token believe
Feature activation+0.000
special
Token special
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 H7.3: (feature 33412)

TOP ACTIVATIONS
MAX = 2.303

much
Token much
Feature activation+0.000
ridicule
Token ridicule
Feature activation+0.925
on
Token on
Feature activation+0.899
social
Token social
Feature activation+0.366
media
Token media
Feature activation+1.120
for
Token for
Feature activation+2.303
the
Token the
Feature activation+1.315
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
red
Token red
Feature activation+0.000
act
Tokenact
Feature activation+0.000
massive
Token massive
Feature activation+0.000
public
Token public
Feature activation+0.000
opposition
Token opposition
Feature activation+0.459
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.570
so
Token so
Feature activation+2.286
Netflix
Token Netflix
Feature activation+0.000
is
Token is
Feature activation+0.103
introducing
Token introducing
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
activist
Token activist
Feature activation+0.000
group
Token group
Feature activation+0.000
No
Token No
Feature activation+0.000
Red
Token Red
Feature activation+0.000
Tape
Token Tape
Feature activation+0.000
,
Token,
Feature activation+2.277
administrators
Token administrators
Feature activation+0.275
continue
Token continue
Feature activation+0.752
to
Token to
Feature activation+0.591
stand
Token stand
Feature activation+0.000
by
Token by
Feature activation+0.000
huge
Token huge
Feature activation+0.000
,
Token,
Feature activation+0.000
mostly
Token mostly
Feature activation+0.000
positive
Token positive
Feature activation+0.074
reaction
Token reaction
Feature activation+0.479
to
Token to
Feature activation+2.214
online
Token online
Feature activation+0.472
reports
Token reports
Feature activation+0.326
regarding
Token regarding
Feature activation+0.556
the
Token the
Feature activation+0.408
incorporation
Token incorporation
Feature activation+0.000
reports
Token reports
Feature activation+0.000
.
Token.
Feature activation+0.000
Amid
Token Amid
Feature activation+0.000
sustained
Token sustained
Feature activation+0.000
protests
Token protests
Feature activation+0.000
,
Token,
Feature activation+2.126
the
Token the
Feature activation+1.334
North
Token North
Feature activation+0.000
Eastern
Token Eastern
Feature activation+0.000
Electric
Token Electric
Feature activation+0.000
Power
Token Power
Feature activation+0.000
Top
Token Top
Feature activation+0.000
eka
Tokeneka
Feature activation+0.000
ball
Token ball
Feature activation+0.000
room
Tokenroom
Feature activation+0.059
Kob
Token Kob
Feature activation+0.000
ach
Tokenach
Feature activation+1.916
promised
Token promised
Feature activation+0.000
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
We
TokenWe
Feature activation+0.000
are
Token are
Feature activation+0.000
opposition
Token opposition
Feature activation+0.144
from
Token from
Feature activation+0.000
right
Token right
Feature activation+0.000
and
Token and
Feature activation+0.000
left
Token left
Feature activation+0.000
to
Token to
Feature activation+1.689
some
Token some
Feature activation+0.600
of
Token of
Feature activation+0.371
the
Token the
Feature activation+0.131
more
Token more
Feature activation+0.000
unpopular
Token unpopular
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.169
among
Token among
Feature activation+0.289
its
Token its
Feature activation+0.047
members
Token members
Feature activation+0.231
despite
Token despite
Feature activation+1.575
promising
Token promising
Feature activation+0.000
its
Token its
Feature activation+0.000
support
Token support
Feature activation+0.000
to
Token to
Feature activation+0.025
the
Token the
Feature activation+0.000
you
Token you
Feature activation+0.000
imagine
Token imagine
Feature activation+0.000
the
Token the
Feature activation+0.000
reaction
Token reaction
Feature activation+0.000
if
Token if
Feature activation+1.034
we
Token we
Feature activation+1.560
told
Token told
Feature activation+0.404
the
Token the
Feature activation+0.060
students
Token students
Feature activation+0.034
of
Token of
Feature activation+0.000
Chicago
Token Chicago
Feature activation+0.000
from
Token from
Feature activation+0.169
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.120
my
Token my
Feature activation+0.266
colleagues
Token colleagues
Feature activation+0.291
,
Token,
Feature activation+1.509
I
Token I
Feature activation+1.288
started
Token started
Feature activation+0.331
to
Token to
Feature activation+0.295
cheer
Token cheer
Feature activation+0.000
you
Token you
Feature activation+0.000
crowd
Token crowd
Feature activation+0.214
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.177
s
Tokens
Feature activation+0.150
reactions
Token reactions
Feature activation+0.775
to
Token to
Feature activation+1.468
certain
Token certain
Feature activation+0.818
key
Token key
Feature activation+0.067
moments
Token moments
Feature activation+0.382
of
Token of
Feature activation+0.146
the
Token the
Feature activation+0.142
of
Token of
Feature activation+0.003
pressure
Token pressure
Feature activation+0.137
had
Token had
Feature activation+0.275
been
Token been
Feature activation+0.262
placed
Token placed
Feature activation+0.055
on
Token on
Feature activation+1.467
Obama
Token Obama
Feature activation+0.092
to
Token to
Feature activation+0.625
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
political
Token political
Feature activation+0.000
to
Token to
Feature activation+0.000
red
Token red
Feature activation+0.000
act
Tokenact
Feature activation+0.000
the
Token the
Feature activation+0.000
transcripts
Token transcripts
Feature activation+0.000
,
Token,
Feature activation+1.443
the
Token the
Feature activation+0.503
Justice
Token Justice
Feature activation+0.000
Department
Token Department
Feature activation+0.000
rel
Token rel
Feature activation+0.000
ented
Tokenented
Feature activation+0.000
of
Token of
Feature activation+0.000
cheering
Token cheering
Feature activation+0.020
and
Token and
Feature activation+0.075
cl
Token cl
Feature activation+0.000
apping
Tokenapping
Feature activation+0.300
as
Token as
Feature activation+1.392
creepy
Token creepy
Feature activation+0.446
Todd
Token Todd
Feature activation+0.000
met
Token met
Feature activation+0.000
his
Token his
Feature activation+0.000
demise
Token demise
Feature activation+0.000
many
Token many
Feature activation+0.000
positive
Token positive
Feature activation+0.000
comments
Token comments
Feature activation+0.114
received
Token received
Feature activation+0.656
as
Token as
Feature activation+1.114
to
Token to
Feature activation+1.391
the
Token the
Feature activation+0.512
quality
Token quality
Feature activation+0.088
of
Token of
Feature activation+0.574
the
Token the
Feature activation+0.121
service
Token service
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Despite
TokenDespite
Feature activation+0.000
the
Token the
Feature activation+0.000
criticism
Token criticism
Feature activation+0.221
,
Token,
Feature activation+1.359
a
Token a
Feature activation+0.445
study
Token study
Feature activation+0.000
by
Token by
Feature activation+0.000
management
Token management
Feature activation+0.000
consultancy
Token consultancy
Feature activation+0.000
The
Token The
Feature activation+0.000
anger
Token anger
Feature activation+0.000
turned
Token turned
Feature activation+1.253
to
Token to
Feature activation+0.394
disbelief
Token disbelief
Feature activation+0.842
when
Token when
Feature activation+1.335
the
Token the
Feature activation+0.769
ghost
Token ghost
Feature activation+0.000
writer
Tokenwriter
Feature activation+0.000
himself
Token himself
Feature activation+0.000
came
Token came
Feature activation+0.000
.
Token.
Feature activation+0.000
Amid
Token Amid
Feature activation+0.000
sustained
Token sustained
Feature activation+0.000
protests
Token protests
Feature activation+0.000
,
Token,
Feature activation+2.126
the
Token the
Feature activation+1.334
North
Token North
Feature activation+0.000
Eastern
Token Eastern
Feature activation+0.000
Electric
Token Electric
Feature activation+0.000
Power
Token Power
Feature activation+0.000
Corporation
Token Corporation
Feature activation+0.000
ridicule
Token ridicule
Feature activation+0.925
on
Token on
Feature activation+0.899
social
Token social
Feature activation+0.366
media
Token media
Feature activation+1.120
for
Token for
Feature activation+2.303
the
Token the
Feature activation+1.315
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
red
Token red
Feature activation+0.000
act
Tokenact
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
universal
Token universal
Feature activation+0.000
reaction
Token reaction
Feature activation+0.002
to
Token to
Feature activation+1.298
the
Token the
Feature activation+0.782
specifics
Token specifics
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
thumbs
Token thumbs
Feature activation+0.000

Top DFA by src position
MAX = 2.541

Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
After
TokenAfter
Feature activation+0.018
Top resid features:
receiving
Token receiving
Feature activation+0.012
Top resid features:
much
Token much
Feature activation+0.123
Top resid features:
ridicule
Token ridicule
Feature activation+1.948
Top resid features:
on
Token on
Feature activation+0.159
Top resid features:
social
Token social
Feature activation+0.047
Top resid features:
media
Token media
Feature activation+0.252
Top resid features:
for
Token for
Feature activation-0.015
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
proposal
Token proposal
Feature activation-0.010
Top resid features:
has
Token has
Feature activation+0.011
Top resid features:
faced
Token faced
Feature activation+0.086
Top resid features:
massive
Token massive
Feature activation+0.050
Top resid features:
public
Token public
Feature activation+0.078
Top resid features:
opposition
Token opposition
Feature activation+2.309
Top resid features:
,
Token,
Feature activation+0.076
Top resid features:
and
Token and
Feature activation+0.059
Top resid features:
so
Token so
Feature activation+0.014
Top resid features:
Netflix
Token Netflix
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
stories
Token stories
Feature activation-0.000
Top resid features:
.)
Token.)
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.045
Top resid features:
Despite
TokenDespite
Feature activation+0.029
Top resid features:
push
Token push
Feature activation+0.086
Top resid features:
back
Tokenback
Feature activation+1.939
Top resid features:
from
Token from
Feature activation+0.309
Top resid features:
student
Token student
Feature activation+0.009
Top resid features:
activist
Token activist
Feature activation+0.119
Top resid features:
group
Token group
Feature activation+0.079
Top resid features:
No
Token No
Feature activation-0.011
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
huge
Token huge
Feature activation+0.051
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
mostly
Token mostly
Feature activation+0.005
Top resid features:
positive
Token positive
Feature activation+0.280
Top resid features:
reaction
Token reaction
Feature activation+1.945
Top resid features:
to
Token to
Feature activation+0.192
Top resid features:
online
Token online
Feature activation+0.000
Top resid features:
reports
Token reports
Feature activation+0.000
Top resid features:
regarding
Token regarding
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
confirmed
Tokenconfirmed
Feature activation-0.002
Top resid features:
reports
Token reports
Feature activation+0.013
Top resid features:
.
Token.
Feature activation-0.068
Top resid features:
Amid
Token Amid
Feature activation+0.006
Top resid features:
sustained
Token sustained
Feature activation+0.031
Top resid features:
protests
Token protests
Feature activation+2.541
Top resid features:
,
Token,
Feature activation+0.063
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
North
Token North
Feature activation+0.000
Top resid features:
Eastern
Token Eastern
Feature activation+0.000
Top resid features:
Electric
Token Electric
Feature activation+0.000
Top resid features:
system
Token system
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.051
Top resid features:
Ans
Token Ans
Feature activation+0.012
Top resid features:
wered
Tokenwered
Feature activation-0.029
Top resid features:
with
Token with
Feature activation+0.041
Top resid features:
cheers
Token cheers
Feature activation+1.868
Top resid features:
in
Token in
Feature activation+0.113
Top resid features:
the
Token the
Feature activation+0.067
Top resid features:
Top
Token Top
Feature activation+0.003
Top resid features:
eka
Tokeneka
Feature activation+0.003
Top resid features:
ball
Token ball
Feature activation+0.019
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
But
Token But
Feature activation-0.012
Top resid features:
he
Token he
Feature activation+0.012
Top resid features:
could
Token could
Feature activation-0.001
Top resid features:
face
Token face
Feature activation-0.045
Top resid features:
opposition
Token opposition
Feature activation+1.687
Top resid features:
from
Token from
Feature activation+0.368
Top resid features:
right
Token right
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+0.029
Top resid features:
left
Token left
Feature activation+0.034
Top resid features:
to
Token to
Feature activation+0.023
Top resid features:
there
Token there
Feature activation-0.001
Top resid features:
was
Token was
Feature activation+0.011
Top resid features:
âĢ
Token âĢ
Feature activation+0.003
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
huge
Tokenhuge
Feature activation+0.020
Top resid features:
opposition
Token opposition
Feature activation+1.631
Top resid features:
âĢ
TokenâĢ
Feature activation+0.010
Top resid features:
Ŀ
TokenĿ
Feature activation+0.002
Top resid features:
among
Token among
Feature activation+0.091
Top resid features:
its
Token its
Feature activation+0.019
Top resid features:
members
Token members
Feature activation+0.008
Top resid features:
ľ
Tokenľ
Feature activation+0.002
Top resid features:
Can
TokenCan
Feature activation+0.000
Top resid features:
you
Token you
Feature activation-0.004
Top resid features:
imagine
Token imagine
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.046
Top resid features:
reaction
Token reaction
Feature activation+1.681
Top resid features:
if
Token if
Feature activation+0.101
Top resid features:
we
Token we
Feature activation+0.008
Top resid features:
told
Token told
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
students
Token students
Feature activation+0.000
Top resid features:
face
Token face
Feature activation+0.036
Top resid features:
of
Token of
Feature activation+0.046
Top resid features:
a
Token a
Feature activation+0.037
Top resid features:
lot
Token lot
Feature activation+0.069
Top resid features:
of
Token of
Feature activation+0.072
Top resid features:
skepticism
Token skepticism
Feature activation+0.873
Top resid features:
from
Token from
Feature activation+0.212
Top resid features:
my
Token my
Feature activation+0.002
Top resid features:
readers
Token readers
Feature activation+0.099
Top resid features:
and
Token and
Feature activation+0.022
Top resid features:
even
Token even
Feature activation+0.057
Top resid features:
the
Token the
Feature activation+0.052
Top resid features:
crowd
Token crowd
Feature activation+0.515
Top resid features:
âĢ
TokenâĢ
Feature activation+0.060
Top resid features:
Ļ
TokenĻ
Feature activation+0.020
Top resid features:
s
Tokens
Feature activation+0.076
Top resid features:
reactions
Token reactions
Feature activation+0.841
Top resid features:
to
Token to
Feature activation+0.169
Top resid features:
certain
Token certain
Feature activation+0.000
Top resid features:
key
Token key
Feature activation+0.000
Top resid features:
moments
Token moments
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
consciousness
Token consciousness
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.042
Top resid features:
swat
Token swat
Feature activation+0.007
Top resid features:
hes
Tokenhes
Feature activation+0.018
Top resid features:
of
Token of
Feature activation+0.020
Top resid features:
pressure
Token pressure
Feature activation+1.114
Top resid features:
had
Token had
Feature activation+0.101
Top resid features:
been
Token been
Feature activation+0.042
Top resid features:
placed
Token placed
Feature activation+0.205
Top resid features:
on
Token on
Feature activation+0.063
Top resid features:
Obama
Token Obama
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.042
Top resid features:
After
TokenAfter
Feature activation+0.044
Top resid features:
receiving
Token receiving
Feature activation+0.006
Top resid features:
much
Token much
Feature activation+0.024
Top resid features:
ridicule
Token ridicule
Feature activation+1.276
Top resid features:
on
Token on
Feature activation+0.071
Top resid features:
social
Token social
Feature activation+0.053
Top resid features:
media
Token media
Feature activation+0.247
Top resid features:
for
Token for
Feature activation-0.005
Top resid features:
the
Token the
Feature activation-0.011
Top resid features:
(
Token (
Feature activation-0.025
Top resid features:
see
Tokensee
Feature activation-0.001
Top resid features:
:
Token:
Feature activation+0.001
Top resid features:
lots
Token lots
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.032
Top resid features:
cheering
Token cheering
Feature activation+0.766
Top resid features:
and
Token and
Feature activation+0.141
Top resid features:
cl
Token cl
Feature activation+0.021
Top resid features:
apping
Tokenapping
Feature activation+0.615
Top resid features:
as
Token as
Feature activation+0.103
Top resid features:
creepy
Token creepy
Feature activation+0.000
Top resid features:
service
Token service
Feature activation-0.014
Top resid features:
and
Token and
Feature activation+0.045
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
many
Token many
Feature activation+0.003
Top resid features:
positive
Token positive
Feature activation+0.206
Top resid features:
comments
Token comments
Feature activation+0.929
Top resid features:
received
Token received
Feature activation+0.246
Top resid features:
as
Token as
Feature activation+0.093
Top resid features:
to
Token to
Feature activation+0.029
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
quality
Token quality
Feature activation+0.000
Top resid features:
."
Token."
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Despite
TokenDespite
Feature activation+0.013
Top resid features:
the
Token the
Feature activation-0.013
Top resid features:
criticism
Token criticism
Feature activation+1.549
Top resid features:
,
Token,
Feature activation+0.050
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
study
Token study
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
management
Token management
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
his
Token his
Feature activation-0.001
Top resid features:
music
Token music
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.077
Top resid features:
The
Token The
Feature activation+0.018
Top resid features:
anger
Token anger
Feature activation+0.725
Top resid features:
turned
Token turned
Feature activation+0.165
Top resid features:
to
Token to
Feature activation+0.366
Top resid features:
disbelief
Token disbelief
Feature activation+0.250
Top resid features:
when
Token when
Feature activation+0.039
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
confirmed
Tokenconfirmed
Feature activation-0.002
Top resid features:
reports
Token reports
Feature activation+0.018
Top resid features:
.
Token.
Feature activation-0.049
Top resid features:
Amid
Token Amid
Feature activation+0.012
Top resid features:
sustained
Token sustained
Feature activation+0.029
Top resid features:
protests
Token protests
Feature activation+1.683
Top resid features:
,
Token,
Feature activation+0.111
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
North
Token North
Feature activation+0.000
Top resid features:
Eastern
Token Eastern
Feature activation+0.000
Top resid features:
Electric
Token Electric
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
After
TokenAfter
Feature activation+0.027
Top resid features:
receiving
Token receiving
Feature activation+0.012
Top resid features:
much
Token much
Feature activation+0.053
Top resid features:
ridicule
Token ridicule
Feature activation+1.133
Top resid features:
on
Token on
Feature activation+0.195
Top resid features:
social
Token social
Feature activation+0.048
Top resid features:
media
Token media
Feature activation+0.151
Top resid features:
for
Token for
Feature activation+0.005
Top resid features:
the
Token the
Feature activation-0.048
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
but
Token but
Feature activation-0.012
Top resid features:
the
Token the
Feature activation-0.022
Top resid features:
universal
Token universal
Feature activation+0.035
Top resid features:
reaction
Token reaction
Feature activation+1.322
Top resid features:
to
Token to
Feature activation+0.155
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
specifics
Token specifics
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.02

Head 3: 0.44

Head 4: 0.04

Head 5: 0.11

Head 6: 0.05

Head 7: 0.03

Head 8: 0.13

Head 9: 0.07

Head 10: 0.01

Head 11: 0.01

Positive logits

eff1.87

drafting1.85

signings1.82

4141.68

Payton1.63

translating1.59

renovation1.59

1.56

)|1.55

pite1.55

gery1.55

02001.54

Osw1.53

McDonnell1.51

Galileo1.50

DAY1.48

products1.47

7871.46

recordings1.46

exit1.45

Negative logits

sidx-2.18

yip-2.16

partName-2.04

Interstitial-1.83

untled-1.78

itch-1.77

*/(-1.71

licts-1.70

attract-1.69

OUP-1.67

neigh-1.66

uyomi-1.65

spons-1.65

-1.65

arcity-1.65

society-1.60

Crit-1.59

hawk-1.56

oreal-1.56

assian-1.55

INTERVAL 2.072 - 2.303
CONTAINS 0.001%

massive
Token massive
Feature activation+0.000
public
Token public
Feature activation+0.000
opposition
Token opposition
Feature activation+0.459
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.570
so
Token so
Feature activation+2.286
Netflix
Token Netflix
Feature activation+0.000
is
Token is
Feature activation+0.103
introducing
Token introducing
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
much
Token much
Feature activation+0.000
ridicule
Token ridicule
Feature activation+0.925
on
Token on
Feature activation+0.899
social
Token social
Feature activation+0.366
media
Token media
Feature activation+1.120
for
Token for
Feature activation+2.303
the
Token the
Feature activation+1.315
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
red
Token red
Feature activation+0.000
act
Tokenact
Feature activation+0.000
reports
Token reports
Feature activation+0.000
.
Token.
Feature activation+0.000
Amid
Token Amid
Feature activation+0.000
sustained
Token sustained
Feature activation+0.000
protests
Token protests
Feature activation+0.000
,
Token,
Feature activation+2.126
the
Token the
Feature activation+1.334
North
Token North
Feature activation+0.000
Eastern
Token Eastern
Feature activation+0.000
Electric
Token Electric
Feature activation+0.000
Power
Token Power
Feature activation+0.000
huge
Token huge
Feature activation+0.000
,
Token,
Feature activation+0.000
mostly
Token mostly
Feature activation+0.000
positive
Token positive
Feature activation+0.074
reaction
Token reaction
Feature activation+0.479
to
Token to
Feature activation+2.214
online
Token online
Feature activation+0.472
reports
Token reports
Feature activation+0.326
regarding
Token regarding
Feature activation+0.556
the
Token the
Feature activation+0.408
incorporation
Token incorporation
Feature activation+0.000
activist
Token activist
Feature activation+0.000
group
Token group
Feature activation+0.000
No
Token No
Feature activation+0.000
Red
Token Red
Feature activation+0.000
Tape
Token Tape
Feature activation+0.000
,
Token,
Feature activation+2.277
administrators
Token administrators
Feature activation+0.275
continue
Token continue
Feature activation+0.752
to
Token to
Feature activation+0.591
stand
Token stand
Feature activation+0.000
by
Token by
Feature activation+0.000

INTERVAL 1.842 - 2.072
CONTAINS 0.000%

Top
Token Top
Feature activation+0.000
eka
Tokeneka
Feature activation+0.000
ball
Token ball
Feature activation+0.000
room
Tokenroom
Feature activation+0.059
Kob
Token Kob
Feature activation+0.000
ach
Tokenach
Feature activation+1.916
promised
Token promised
Feature activation+0.000
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
We
TokenWe
Feature activation+0.000
are
Token are
Feature activation+0.000

INTERVAL 1.612 - 1.842
CONTAINS 0.000%

opposition
Token opposition
Feature activation+0.144
from
Token from
Feature activation+0.000
right
Token right
Feature activation+0.000
and
Token and
Feature activation+0.000
left
Token left
Feature activation+0.000
to
Token to
Feature activation+1.689
some
Token some
Feature activation+0.600
of
Token of
Feature activation+0.371
the
Token the
Feature activation+0.131
more
Token more
Feature activation+0.000
unpopular
Token unpopular
Feature activation+0.000

INTERVAL 1.382 - 1.612
CONTAINS 0.001%

from
Token from
Feature activation+0.169
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.120
my
Token my
Feature activation+0.266
colleagues
Token colleagues
Feature activation+0.291
,
Token,
Feature activation+1.509
I
Token I
Feature activation+1.288
started
Token started
Feature activation+0.331
to
Token to
Feature activation+0.295
cheer
Token cheer
Feature activation+0.000
you
Token you
Feature activation+0.000
of
Token of
Feature activation+0.003
pressure
Token pressure
Feature activation+0.137
had
Token had
Feature activation+0.275
been
Token been
Feature activation+0.262
placed
Token placed
Feature activation+0.055
on
Token on
Feature activation+1.467
Obama
Token Obama
Feature activation+0.092
to
Token to
Feature activation+0.625
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
political
Token political
Feature activation+0.000
to
Token to
Feature activation+0.000
red
Token red
Feature activation+0.000
act
Tokenact
Feature activation+0.000
the
Token the
Feature activation+0.000
transcripts
Token transcripts
Feature activation+0.000
,
Token,
Feature activation+1.443
the
Token the
Feature activation+0.503
Justice
Token Justice
Feature activation+0.000
Department
Token Department
Feature activation+0.000
rel
Token rel
Feature activation+0.000
ented
Tokenented
Feature activation+0.000
many
Token many
Feature activation+0.000
positive
Token positive
Feature activation+0.000
comments
Token comments
Feature activation+0.114
received
Token received
Feature activation+0.656
as
Token as
Feature activation+1.114
to
Token to
Feature activation+1.391
the
Token the
Feature activation+0.512
quality
Token quality
Feature activation+0.088
of
Token of
Feature activation+0.574
the
Token the
Feature activation+0.121
service
Token service
Feature activation+0.000
crowd
Token crowd
Feature activation+0.214
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.177
s
Tokens
Feature activation+0.150
reactions
Token reactions
Feature activation+0.775
to
Token to
Feature activation+1.468
certain
Token certain
Feature activation+0.818
key
Token key
Feature activation+0.067
moments
Token moments
Feature activation+0.382
of
Token of
Feature activation+0.146
the
Token the
Feature activation+0.142

INTERVAL 1.151 - 1.382
CONTAINS 0.002%

ered
Tokenered
Feature activation+0.035
an
Token an
Feature activation+0.161
atmosphere
Token atmosphere
Feature activation+0.157
of
Token of
Feature activation+0.250
hostility
Token hostility
Feature activation+0.235
to
Token to
Feature activation+1.208
any
Token any
Feature activation+1.100
women
Token women
Feature activation+0.000
who
Token who
Feature activation+0.412
had
Token had
Feature activation+0.000
the
Token the
Feature activation+0.000
okes
Tokenokes
Feature activation+0.000
anger
Token anger
Feature activation+0.000
and
Token and
Feature activation+0.000
der
Token der
Feature activation+0.000
ision
Tokenision
Feature activation+0.243
with
Token with
Feature activation+1.181
suggestion
Token suggestion
Feature activation+0.149
we
Token we
Feature activation+0.000
should
Token should
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
his
Token his
Feature activation+0.000
music
Token music
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
anger
Token anger
Feature activation+0.000
turned
Token turned
Feature activation+1.253
to
Token to
Feature activation+0.394
disbelief
Token disbelief
Feature activation+0.842
when
Token when
Feature activation+1.335
the
Token the
Feature activation+0.769
ghost
Token ghost
Feature activation+0.000
increased
Token increased
Feature activation+0.000
the
Token the
Feature activation+0.322
noise
Token noise
Feature activation+0.476
levels
Token levels
Feature activation+0.388
,
Token,
Feature activation+0.954
the
Token the
Feature activation+1.165
Celtic
Token Celtic
Feature activation+0.000
players
Token players
Feature activation+0.000
responded
Token responded
Feature activation+0.089
and
Token and
Feature activation+0.000
u
Token u
Feature activation+0.000
ridicule
Token ridicule
Feature activation+0.925
on
Token on
Feature activation+0.899
social
Token social
Feature activation+0.366
media
Token media
Feature activation+1.120
for
Token for
Feature activation+2.303
the
Token the
Feature activation+1.315
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
red
Token red
Feature activation+0.000
act
Tokenact
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.921 - 1.151
CONTAINS 0.005%

the
Token the
Feature activation+0.000
many
Token many
Feature activation+0.000
positive
Token positive
Feature activation+0.000
comments
Token comments
Feature activation+0.114
received
Token received
Feature activation+0.656
as
Token as
Feature activation+1.114
to
Token to
Feature activation+1.391
the
Token the
Feature activation+0.512
quality
Token quality
Feature activation+0.088
of
Token of
Feature activation+0.574
the
Token the
Feature activation+0.121
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
backlash
Token backlash
Feature activation+0.608
.
Token.
Feature activation+0.506
And
Token And
Feature activation+0.983
this
Token this
Feature activation+0.181
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
thing
Token thing
Feature activation+0.000
there
Token there
Feature activation+0.000
really
Token really
Feature activation+0.000
a
Token a
Feature activation+0.000
public
Token public
Feature activation+0.000
appetite
Token appetite
Feature activation+0.241
for
Token for
Feature activation+0.996
divisive
Token divisive
Feature activation+0.133
gender
Token gender
Feature activation+0.000
identity
Token identity
Feature activation+0.000
politics
Token politics
Feature activation+0.000
in
Token in
Feature activation+0.000
people
Token people
Feature activation+0.240
to
Token to
Feature activation+0.589
toss
Token toss
Feature activation+0.000
vitri
Token vitri
Feature activation+0.000
ol
Tokenol
Feature activation+0.051
towards
Token towards
Feature activation+1.025
V
Token V
Feature activation+0.000
ilyn
Tokenilyn
Feature activation+0.000
,
Token,
Feature activation+0.000
someone
Token someone
Feature activation+0.000
that
Token that
Feature activation+0.000
ouring
Tokenouring
Feature activation+0.000
of
Token of
Feature activation+0.000
support
Token support
Feature activation+0.242
and
Token and
Feature activation+0.339
grief
Token grief
Feature activation+0.269
would
Token would
Feature activation+0.957
measure
Token measure
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
what
Token what
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 0.691 - 0.921
CONTAINS 0.013%

osition
Tokenosition
Feature activation+0.000
from
Token from
Feature activation+0.000
regulated
Token regulated
Feature activation+0.000
utilities
Token utilities
Feature activation+0.000
could
Token could
Feature activation+0.580
stop
Token stop
Feature activation+0.914
a
Token a
Feature activation+0.460
solar
Token solar
Feature activation+0.000
boom
Token boom
Feature activation+0.000
before
Token before
Feature activation+0.237
it
Token it
Feature activation+0.000
ESPN
Token ESPN
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
website
Token website
Feature activation+0.000
for
Token for
Feature activation+0.750
a
Token a
Feature activation+0.558
while
Token while
Feature activation+0.034
last
Token last
Feature activation+0.056
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
rare
Token rare
Feature activation+0.000
threat
Token threat
Feature activation+0.019
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
after
Token after
Feature activation+0.722
Mr
Token Mr
Feature activation+0.101
.
Token.
Feature activation+0.024
Sam
Token Sam
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
ago
Tokenago
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.093
people
Token people
Feature activation+0.406
online
Token online
Feature activation+0.421
from
Token from
Feature activation+0.679
93
Token 93
Feature activation+0.837
different
Token different
Feature activation+0.628
countries
Token countries
Feature activation+0.164
.[
Token.[
Feature activation+0.000
13
Token13
Feature activation+0.000
]
Token]
Feature activation+0.000
to
Token to
Feature activation+0.000
join
Token join
Feature activation+0.000
chorus
Token chorus
Feature activation+0.000
of
Token of
Feature activation+0.003
opposition
Token opposition
Feature activation+0.417
to
Token to
Feature activation+0.799
bill
Token bill
Feature activation+0.000
allowing
Token allowing
Feature activation+0.000
for
Token for
Feature activation+0.000
indefinite
Token indefinite
Feature activation+0.000
detention
Token detention
Feature activation+0.000

INTERVAL 0.461 - 0.691
CONTAINS 0.036%

or
Token or
Feature activation+0.000
court
Token court
Feature activation+0.000
ruling
Token ruling
Feature activation+0.000
has
Token has
Feature activation+0.307
led
Token led
Feature activation+0.421
to
Token to
Feature activation+0.478
a
Token a
Feature activation+0.275
flurry
Token flurry
Feature activation+0.212
of
Token of
Feature activation+0.189
legislative
Token legislative
Feature activation+0.000
proposals
Token proposals
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
the
Token the
Feature activation+0.000
protests
Token protests
Feature activation+0.000
began
Token began
Feature activation+0.128
,
Token,
Feature activation+0.499
Ernest
Token Ernest
Feature activation+0.000
o
Tokeno
Feature activation+0.000
Vil
Token Vil
Feature activation+0.000
leg
Tokenleg
Feature activation+0.000
as
Tokenas
Feature activation+0.000
to
Token to
Feature activation+0.000
drum
Token drum
Feature activation+0.000
up
Token up
Feature activation+0.000
pressure
Token pressure
Feature activation+0.000
to
Token to
Feature activation+0.746
force
Token force
Feature activation+0.566
the
Token the
Feature activation+0.094
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
debate
Token debate
Feature activation+0.000
could
Token could
Feature activation+0.000
also
Token also
Feature activation+0.000
further
Token further
Feature activation+0.288
motivate
Token motivate
Feature activation+0.610
Beijing
Token Beijing
Feature activation+0.000
city
Token city
Feature activation+0.000
officials
Token officials
Feature activation+0.000
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
future
Token future
Feature activation+0.000
demand
Token demand
Feature activation+0.035
and
Token and
Feature activation+1.076
the
Token the
Feature activation+0.884
reduction
Token reduction
Feature activation+0.143
in
Token in
Feature activation+0.480
demand
Token demand
Feature activation+0.458
that
Token that
Feature activation+0.135
conservation
Token conservation
Feature activation+0.000
effort
Token effort
Feature activation+0.000
etc
Token etc
Feature activation+0.000

INTERVAL 0.230 - 0.461
CONTAINS 0.139%

Facebook
Token Facebook
Feature activation+0.000
pages
Token pages
Feature activation+0.000
are
Token are
Feature activation+0.000
ab
Token ab
Feature activation+0.000
uzz
Tokenuzz
Feature activation+0.000
with
Token with
Feature activation+0.266
activity
Token activity
Feature activation+0.251
,
Token,
Feature activation+0.039
ahead
Token ahead
Feature activation+0.062
of
Token of
Feature activation+0.693
the
Token the
Feature activation+0.466
fights
Token fights
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
PA
TokenPA
Feature activation+0.000
,
Token,
Feature activation+0.246
the
Token the
Feature activation+0.065
average
Token average
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
player
Token player
Feature activation+0.000
salary
Token salary
Feature activation+0.000
a
Token a
Feature activation+0.000
xen
Token xen
Feature activation+0.000
ophobic
Tokenophobic
Feature activation+0.000
backlash
Token backlash
Feature activation+0.093
against
Token against
Feature activation+0.551
the
Token the
Feature activation+0.277
more
Token more
Feature activation+0.422
than
Token than
Feature activation+0.000
1
Token 1
Feature activation+0.000
million
Token million
Feature activation+0.000
refugees
Token refugees
Feature activation+0.000
His
Token His
Feature activation+0.100
voice
Token voice
Feature activation+0.000
will
Token will
Feature activation+0.000
carry
Token carry
Feature activation+0.243
weight
Token weight
Feature activation+0.193
in
Token in
Feature activation+0.241
free
Token free
Feature activation+0.025
agent
Token agent
Feature activation+0.000
pitches
Token pitches
Feature activation+0.170
;
Token;
Feature activation+0.000
far
Token far
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
fans
Token fans
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.589
then
Token then
Feature activation+0.375
in
Token in
Feature activation+0.125
between
Token between
Feature activation+0.000
this
Token this
Feature activation+0.350
record
Token record
Feature activation+0.089
and
Token and
Feature activation+0.000

INTERVAL 0.000 - 0.230
CONTAINS 99.804%

Street
Token Street
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sunday
TokenSunday
Feature activation+0.000
Only
Token Only
Feature activation+0.000
,
Token,
Feature activation+0.000
$
Token $
Feature activation+0.000
1
Token1
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
www
Tokenwww
Feature activation+0.000
The
TokenThe
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Cr
TokenCr
Feature activation+0.000
ude
Tokenude
Feature activation+0.000
oil
Token oil
Feature activation+0.000
invent
Token invent
Feature activation+0.000
ories
Tokenories
Feature activation+0.000
climbed
Token climbed
Feature activation+0.000
by
Token by
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Congress
Token Congress
Feature activation+0.000
can
Token can
Feature activation+0.000
raise
Token raise
Feature activation+0.000
.
Token.
Feature activation+0.000
Many
Token Many
Feature activation+0.000
states
Token states
Feature activation+0.000
and
Token and
Feature activation+0.000
even
Token even
Feature activation+0.000
local
Token local
Feature activation+0.000
governments
Token governments
Feature activation+0.000
oru
Tokenoru
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
N
TokenN
Feature activation+0.000
ed
Tokened
Feature activation+0.000
á
Tokená
Feature activation+0.000
v
Tokenv
Feature activation+0.000
n
Tokenn
Feature activation+0.000
é
Tokené
Feature activation+0.000
Ã
Token Ã
Feature activation+0.000
Apps
Token Apps
Feature activation+0.000
like
Token like
Feature activation+0.000
Task
Token Task
Feature activation+0.000
er
Tokener
Feature activation+0.000
can
Token can
Feature activation+0.000
do
Token do
Feature activation+0.000
similar
Token similar
Feature activation+0.000
things
Token things
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
location
Token location
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 H7.3: (feature 46209)

TOP ACTIVATIONS
MAX = 3.506

ilia
Tokenilia
Feature activation+1.354
,
Token,
Feature activation+1.554
Brazil
Token Brazil
Feature activation+1.403
July
Token July
Feature activation+0.756
14
Token 14
Feature activation+2.891
,
Token,
Feature activation+3.506
2016
Token 2016
Feature activation+2.381
.
Token.
Feature activation+0.142
REUTERS
Token REUTERS
Feature activation+0.000
/
Token/
Feature activation+0.000
U
TokenU
Feature activation+0.000
a
Token a
Feature activation+0.000
rural
Token rural
Feature activation+0.189
Oregon
Token Oregon
Feature activation+0.000
blue
Token blue
Feature activation+0.264
berry
Tokenberry
Feature activation+0.268
farm
Token farm
Feature activation+3.348
had
Token had
Feature activation+0.242
been
Token been
Feature activation+0.141
deported
Token deported
Feature activation+0.000
six
Token six
Feature activation+0.095
times
Token times
Feature activation+0.019
Santa
Token Santa
Feature activation+0.000
Rosa
Token Rosa
Feature activation+0.000
,
Token,
Feature activation+0.000
CA
Token CA
Feature activation+0.000
elementary
Token elementary
Feature activation+0.293
school
Token school
Feature activation+3.264
district
Token district
Feature activation+2.696
is
Token is
Feature activation+0.792
mat
Token mat
Feature activation+0.000
uring
Tokenuring
Feature activation+0.530
robust
Token robust
Feature activation+0.162
born
Tokenborn
Feature activation+0.000
,
Token,
Feature activation+0.000
Michigan
Token Michigan
Feature activation+0.000
,
Token,
Feature activation+0.000
assembly
Token assembly
Feature activation+0.172
plant
Token plant
Feature activation+3.209
located
Token located
Feature activation+0.770
12
Token 12
Feature activation+0.743
miles
Token miles
Feature activation+0.000
southwest
Token southwest
Feature activation+0.238
of
Token of
Feature activation+0.566
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
Dallas
Token Dallas
Feature activation+0.000
Kara
Token Kara
Feature activation+0.000
oke
Tokenoke
Feature activation+0.640
bar
Token bar
Feature activation+3.012
while
Token while
Feature activation+0.000
he
Token he
Feature activation+0.000
and
Token and
Feature activation+0.000
American
Token American
Feature activation+0.000
white
Token white
Feature activation+0.000
Bras
Token Bras
Feature activation+0.000
ilia
Tokenilia
Feature activation+1.354
,
Token,
Feature activation+1.554
Brazil
Token Brazil
Feature activation+1.403
July
Token July
Feature activation+0.756
14
Token 14
Feature activation+2.891
,
Token,
Feature activation+3.506
2016
Token 2016
Feature activation+2.381
.
Token.
Feature activation+0.142
REUTERS
Token REUTERS
Feature activation+0.000
/
Token/
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
south
Token south
Feature activation+0.000
London
Token London
Feature activation+0.000
police
Token police
Feature activation+0.000
station
Token station
Feature activation+2.872
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
arrested
Token arrested
Feature activation+0.000
women
Token women
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
health
Token health
Feature activation+0.000
clinic
Token clinic
Feature activation+2.816
called
Token called
Feature activation+0.136
Aid
Token Aid
Feature activation+0.000
for
Token for
Feature activation+0.000
Women
Token Women
Feature activation+0.000
on
Token on
Feature activation+0.370
that
Token that
Feature activation+0.000
salaries
Token salaries
Feature activation+0.000
in
Token in
Feature activation+0.000
Detroit
Token Detroit
Feature activation+1.229
are
Token are
Feature activation+0.781
higher
Token higher
Feature activation+2.714
than
Token than
Feature activation+0.206
the
Token the
Feature activation+0.191
national
Token national
Feature activation+0.000
average
Token average
Feature activation+0.336
.
Token.
Feature activation+0.052
Rosa
Token Rosa
Feature activation+0.000
,
Token,
Feature activation+0.000
CA
Token CA
Feature activation+0.000
elementary
Token elementary
Feature activation+0.293
school
Token school
Feature activation+3.264
district
Token district
Feature activation+2.696
is
Token is
Feature activation+0.792
mat
Token mat
Feature activation+0.000
uring
Tokenuring
Feature activation+0.530
robust
Token robust
Feature activation+0.162
ly
Tokenly
Feature activation+0.396
Wichita
Token Wichita
Feature activation+0.000
Re
Token Re
Feature activation+0.000
formation
Tokenformation
Feature activation+0.000
Lutheran
Token Lutheran
Feature activation+0.000
Church
Token Church
Feature activation+2.297
in
Token in
Feature activation+2.684
Kansas
Token Kansas
Feature activation+0.042
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
New
TokenNew
Feature activation+0.000
,
Token,
Feature activation+2.138
Nov
Token Nov
Feature activation+0.159
.
Token.
Feature activation+0.052
13
Token 13
Feature activation+2.155
,
Token,
Feature activation+2.032
2014
Token 2014
Feature activation+2.546
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.078
Dave
TokenDave
Feature activation+0.000
Releases
Token Releases
Feature activation+0.000
R
Token R
Feature activation+0.000
have
Token have
Feature activation+0.000
eroded
Token eroded
Feature activation+0.000
from
Token from
Feature activation+0.000
Wisconsin
Token Wisconsin
Feature activation+0.000
fields
Token fields
Feature activation+1.140
in
Token in
Feature activation+2.536
2003
Token 2003
Feature activation+0.681
,
Token,
Feature activation+0.018
amount
Token amount
Feature activation+0.000
ing
Tokening
Feature activation+0.000
to
Token to
Feature activation+0.000
San
Token San
Feature activation+0.000
Francisco
Token Francisco
Feature activation+0.000
's
Token's
Feature activation+0.295
So
Token So
Feature activation+0.000
Ma
TokenMa
Feature activation+0.498
neighborhood
Token neighborhood
Feature activation+2.527
on
Token on
Feature activation+0.545
suspicion
Token suspicion
Feature activation+0.000
of
Token of
Feature activation+0.000
resisting
Token resisting
Feature activation+0.000
arrest
Token arrest
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
annual
Token annual
Feature activation+0.000
Tokyo
Token Tokyo
Feature activation+0.000
Toy
Token Toy
Feature activation+0.053
Show
Token Show
Feature activation+2.514
2009
Token 2009
Feature activation+0.964
.
Token.
Feature activation+0.000
Tom
Token Tom
Feature activation+0.000
y
Tokeny
Feature activation+0.000
claims
Token claims
Feature activation+0.000
iversity
Tokeniversity
Feature activation+0.000
in
Token in
Feature activation+0.000
Montreal
Token Montreal
Feature activation+0.687
's
Token's
Feature activation+0.402
east
Token east
Feature activation+1.146
end
Token end
Feature activation+2.403
.
Token.
Feature activation+0.132
Four
Token Four
Feature activation+0.156
of
Token of
Feature activation+0.010
the
Token the
Feature activation+0.000
people
Token people
Feature activation+0.000
,
Token,
Feature activation+1.554
Brazil
Token Brazil
Feature activation+1.403
July
Token July
Feature activation+0.756
14
Token 14
Feature activation+2.891
,
Token,
Feature activation+3.506
2016
Token 2016
Feature activation+2.381
.
Token.
Feature activation+0.142
REUTERS
Token REUTERS
Feature activation+0.000
/
Token/
Feature activation+0.000
U
TokenU
Feature activation+0.000
es
Tokenes
Feature activation+0.000
North
Token North
Feature activation+0.000
Stafford
Token Stafford
Feature activation+0.000
shire
Tokenshire
Feature activation+0.064
,
Token,
Feature activation+0.573
UK
Token UK
Feature activation+0.169
from
Token from
Feature activation+2.341
1998
Token 1998
Feature activation+0.680
.
Token.
Feature activation+0.017
Eth
Token Eth
Feature activation+0.000
ical
Tokenical
Feature activation+0.000
approval
Token approval
Feature activation+0.000
the
Token the
Feature activation+0.000
North
Token North
Feature activation+0.000
Baltimore
Token Baltimore
Feature activation+0.000
Aqu
Token Aqu
Feature activation+0.000
atic
Tokenatic
Feature activation+0.000
Club
Token Club
Feature activation+2.304
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
still
Token still
Feature activation+0.000
no
Token no
Feature activation+0.000
his
Token his
Feature activation+0.000
Wichita
Token Wichita
Feature activation+0.000
Re
Token Re
Feature activation+0.000
formation
Tokenformation
Feature activation+0.000
Lutheran
Token Lutheran
Feature activation+0.000
Church
Token Church
Feature activation+2.297
in
Token in
Feature activation+2.684
Kansas
Token Kansas
Feature activation+0.042
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 3.657

Palace
Token Palace
Feature activation-0.024
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
Bras
Token Bras
Feature activation+0.333
Top resid features:
ilia
Tokenilia
Feature activation+0.112
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
Brazil
Token Brazil
Feature activation+3.521
Top resid features:
July
Token July
Feature activation-0.016
Top resid features:
14
Token 14
Feature activation+0.010
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
2016
Token 2016
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
three
Token three
Feature activation-0.015
Top resid features:
people
Token people
Feature activation-0.008
Top resid features:
at
Token at
Feature activation-0.039
Top resid features:
a
Token a
Feature activation-0.050
Top resid features:
rural
Token rural
Feature activation+0.231
Top resid features:
Oregon
Token Oregon
Feature activation+3.657
Top resid features:
blue
Token blue
Feature activation+0.034
Top resid features:
berry
Tokenberry
Feature activation+0.014
Top resid features:
farm
Token farm
Feature activation+0.037
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
Linux
Token Linux
Feature activation+0.034
Top resid features:
deployment
Token deployment
Feature activation+0.015
Top resid features:
in
Token in
Feature activation-0.011
Top resid features:
a
Token a
Feature activation-0.052
Top resid features:
Santa
Token Santa
Feature activation+0.065
Top resid features:
Rosa
Token Rosa
Feature activation+1.671
Top resid features:
,
Token,
Feature activation+0.629
Top resid features:
CA
Token CA
Feature activation+1.156
Top resid features:
elementary
Token elementary
Feature activation+0.064
Top resid features:
school
Token school
Feature activation+0.105
Top resid features:
district
Token district
Feature activation+0.000
Top resid features:
1964
Token 1964
Feature activation+0.038
Top resid features:
at
Token at
Feature activation-0.025
Top resid features:
Ford
Token Ford
Feature activation+0.020
Top resid features:
's
Token's
Feature activation-0.010
Top resid features:
Dear
Token Dear
Feature activation+0.038
Top resid features:
born
Tokenborn
Feature activation+1.395
Top resid features:
,
Token,
Feature activation+0.684
Top resid features:
Michigan
Token Michigan
Feature activation+0.865
Top resid features:
,
Token,
Feature activation+0.610
Top resid features:
assembly
Token assembly
Feature activation+0.022
Top resid features:
plant
Token plant
Feature activation-0.004
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
patriotic
Token patriotic
Feature activation+0.008
Top resid features:
song
Token song
Feature activation+0.004
Top resid features:
at
Token at
Feature activation-0.030
Top resid features:
a
Token a
Feature activation-0.043
Top resid features:
Dallas
Token Dallas
Feature activation+3.469
Top resid features:
Kara
Token Kara
Feature activation+0.018
Top resid features:
oke
Tokenoke
Feature activation+0.003
Top resid features:
bar
Token bar
Feature activation+0.068
Top resid features:
while
Token while
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
Palace
Token Palace
Feature activation-0.009
Top resid features:
in
Token in
Feature activation+0.048
Top resid features:
Bras
Token Bras
Feature activation+0.184
Top resid features:
ilia
Tokenilia
Feature activation+0.277
Top resid features:
,
Token,
Feature activation+0.078
Top resid features:
Brazil
Token Brazil
Feature activation+2.887
Top resid features:
July
Token July
Feature activation-0.047
Top resid features:
14
Token 14
Feature activation-0.014
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
2016
Token 2016
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.035
Top resid features:
appointment
Token appointment
Feature activation+0.005
Top resid features:
at
Token at
Feature activation-0.054
Top resid features:
a
Token a
Feature activation-0.038
Top resid features:
south
Token south
Feature activation+0.176
Top resid features:
London
Token London
Feature activation+3.003
Top resid features:
police
Token police
Feature activation+0.107
Top resid features:
station
Token station
Feature activation+0.125
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
He
Token He
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
seen
Token seen
Feature activation+0.004
Top resid features:
vandal
Token vandal
Feature activation-0.024
Top resid features:
izing
Tokenizing
Feature activation-0.045
Top resid features:
a
Token a
Feature activation-0.023
Top resid features:
Kansas
Token Kansas
Feature activation+1.276
Top resid features:
City
Token City
Feature activation+1.810
Top resid features:
women
Token women
Feature activation+0.040
Top resid features:
âĢ
TokenâĢ
Feature activation+0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.009
Top resid features:
s
Tokens
Feature activation+0.060
Top resid features:
health
Token health
Feature activation+0.043
Top resid features:
report
Token report
Feature activation-0.002
Top resid features:
acknowledges
Token acknowledges
Feature activation-0.018
Top resid features:
that
Token that
Feature activation+0.019
Top resid features:
salaries
Token salaries
Feature activation-0.036
Top resid features:
in
Token in
Feature activation+0.115
Top resid features:
Detroit
Token Detroit
Feature activation+2.847
Top resid features:
are
Token are
Feature activation+0.032
Top resid features:
higher
Token higher
Feature activation-0.014
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
national
Token national
Feature activation+0.000
Top resid features:
Linux
Token Linux
Feature activation+0.036
Top resid features:
deployment
Token deployment
Feature activation+0.012
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
a
Token a
Feature activation-0.042
Top resid features:
Santa
Token Santa
Feature activation+0.045
Top resid features:
Rosa
Token Rosa
Feature activation+1.365
Top resid features:
,
Token,
Feature activation+0.464
Top resid features:
CA
Token CA
Feature activation+0.950
Top resid features:
elementary
Token elementary
Feature activation+0.064
Top resid features:
school
Token school
Feature activation+0.082
Top resid features:
district
Token district
Feature activation+0.128
Top resid features:
he
Token he
Feature activation-0.002
Top resid features:
attended
Token attended
Feature activation-0.019
Top resid features:
services
Token services
Feature activation-0.000
Top resid features:
at
Token at
Feature activation-0.014
Top resid features:
his
Token his
Feature activation+0.006
Top resid features:
Wichita
Token Wichita
Feature activation+2.973
Top resid features:
Re
Token Re
Feature activation+0.012
Top resid features:
formation
Tokenformation
Feature activation+0.011
Top resid features:
Lutheran
Token Lutheran
Feature activation+0.014
Top resid features:
Church
Token Church
Feature activation+0.027
Top resid features:
in
Token in
Feature activation+0.042
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
Fer
Token Fer
Feature activation-0.006
Top resid features:
nd
Tokennd
Feature activation+0.001
Top resid features:
ale
Tokenale
Feature activation+0.229
Top resid features:
,
Token,
Feature activation+0.471
Top resid features:
Michigan
Token Michigan
Feature activation+1.866
Top resid features:
,
Token,
Feature activation+0.410
Top resid features:
Nov
Token Nov
Feature activation+0.015
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
13
Token 13
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.030
Top resid features:
estimated
Token estimated
Feature activation+0.019
Top resid features:
to
Token to
Feature activation-0.006
Top resid features:
have
Token have
Feature activation-0.010
Top resid features:
eroded
Token eroded
Feature activation-0.031
Top resid features:
from
Token from
Feature activation-0.006
Top resid features:
Wisconsin
Token Wisconsin
Feature activation+2.626
Top resid features:
fields
Token fields
Feature activation+0.193
Top resid features:
in
Token in
Feature activation+0.047
Top resid features:
2003
Token 2003
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
amount
Token amount
Feature activation+0.000
Top resid features:
arrested
Token arrested
Feature activation-0.062
Top resid features:
Sunday
Token Sunday
Feature activation-0.015
Top resid features:
in
Token in
Feature activation-0.004
Top resid features:
San
Token San
Feature activation+0.120
Top resid features:
Francisco
Token Francisco
Feature activation+1.020
Top resid features:
's
Token's
Feature activation+1.680
Top resid features:
So
Token So
Feature activation+0.018
Top resid features:
Ma
TokenMa
Feature activation+0.038
Top resid features:
neighborhood
Token neighborhood
Feature activation+0.124
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
suspicion
Token suspicion
Feature activation+0.000
Top resid features:
emotions
Token emotions
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.003
Top resid features:
the
Token the
Feature activation-0.059
Top resid features:
annual
Token annual
Feature activation-0.061
Top resid features:
Tokyo
Token Tokyo
Feature activation+2.958
Top resid features:
Toy
Token Toy
Feature activation+0.023
Top resid features:
Show
Token Show
Feature activation+0.082
Top resid features:
2009
Token 2009
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Tom
Token Tom
Feature activation+0.000
Top resid features:
pre
Token pre
Feature activation+0.001
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
un
Tokenun
Feature activation-0.004
Top resid features:
iversity
Tokeniversity
Feature activation+0.020
Top resid features:
in
Token in
Feature activation+0.026
Top resid features:
Montreal
Token Montreal
Feature activation+1.353
Top resid features:
's
Token's
Feature activation+0.972
Top resid features:
east
Token east
Feature activation+0.250
Top resid features:
end
Token end
Feature activation+0.163
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Four
Token Four
Feature activation+0.000
Top resid features:
Palace
Token Palace
Feature activation+0.006
Top resid features:
in
Token in
Feature activation+0.080
Top resid features:
Bras
Token Bras
Feature activation+0.284
Top resid features:
ilia
Tokenilia
Feature activation+0.464
Top resid features:
,
Token,
Feature activation+0.162
Top resid features:
Brazil
Token Brazil
Feature activation+1.889
Top resid features:
July
Token July
Feature activation-0.042
Top resid features:
14
Token 14
Feature activation-0.018
Top resid features:
,
Token,
Feature activation-0.052
Top resid features:
2016
Token 2016
Feature activation-0.050
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.060
Top resid features:
North
Token North
Feature activation+0.160
Top resid features:
Stafford
Token Stafford
Feature activation+0.107
Top resid features:
shire
Tokenshire
Feature activation+0.745
Top resid features:
,
Token,
Feature activation+0.241
Top resid features:
UK
Token UK
Feature activation+1.352
Top resid features:
from
Token from
Feature activation+0.018
Top resid features:
1998
Token 1998
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Eth
Token Eth
Feature activation+0.000
Top resid features:
ical
Tokenical
Feature activation+0.000
Top resid features:
enthal
Tokenenthal
Feature activation-0.001
Top resid features:
drowned
Token drowned
Feature activation-0.023
Top resid features:
at
Token at
Feature activation-0.055
Top resid features:
the
Token the
Feature activation-0.031
Top resid features:
North
Token North
Feature activation+0.186
Top resid features:
Baltimore
Token Baltimore
Feature activation+2.490
Top resid features:
Aqu
Token Aqu
Feature activation+0.085
Top resid features:
atic
Tokenatic
Feature activation+0.047
Top resid features:
Club
Token Club
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
There
Token There
Feature activation+0.000
Top resid features:
he
Token he
Feature activation-0.004
Top resid features:
attended
Token attended
Feature activation-0.038
Top resid features:
services
Token services
Feature activation-0.001
Top resid features:
at
Token at
Feature activation-0.059
Top resid features:
his
Token his
Feature activation+0.017
Top resid features:
Wichita
Token Wichita
Feature activation+2.731
Top resid features:
Re
Token Re
Feature activation+0.020
Top resid features:
formation
Tokenformation
Feature activation+0.005
Top resid features:
Lutheran
Token Lutheran
Feature activation+0.012
Top resid features:
Church
Token Church
Feature activation+0.029
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.07

Head 2: 0.02

Head 3: 0.44

Head 4: 0.05

Head 5: 0.08

Head 6: 0.06

Head 7: 0.03

Head 8: 0.09

Head 9: 0.08

Head 10: 0.01

Head 11: 0.02

Positive logits

GOODMAN1.91

ambassador1.80

��1.76

largeDownload1.71

edged1.66

idable1.65

DragonMagazine1.62

Ebola1.60

Ambassador1.60

Gears1.57

ember1.57

Examiner1.57

Composite1.55

Week1.54

isodes1.53

andise1.53

Citation1.53

SIGN1.53

istries1.53

Registrar1.52

Negative logits

Chennai-2.50

Atlanta-2.22

Colorado-2.20

NYC-2.14

phis-2.10

Alaska-2.06

Mumbai-2.01

celona-2.00

Colorado-1.99

Denver-1.98

NSW-1.97

Brooklyn-1.96

Amsterdam-1.96

Kazakhstan-1.95

Norwich-1.95

insk-1.93

ampa-1.92

Tucson-1.90

Montreal-1.90

Tasmania-1.89

INTERVAL 3.156 - 3.506
CONTAINS 0.000%

ilia
Tokenilia
Feature activation+1.354
,
Token,
Feature activation+1.554
Brazil
Token Brazil
Feature activation+1.403
July
Token July
Feature activation+0.756
14
Token 14
Feature activation+2.891
,
Token,
Feature activation+3.506
2016
Token 2016
Feature activation+2.381
.
Token.
Feature activation+0.142
REUTERS
Token REUTERS
Feature activation+0.000
/
Token/
Feature activation+0.000
U
TokenU
Feature activation+0.000
a
Token a
Feature activation+0.000
rural
Token rural
Feature activation+0.189
Oregon
Token Oregon
Feature activation+0.000
blue
Token blue
Feature activation+0.264
berry
Tokenberry
Feature activation+0.268
farm
Token farm
Feature activation+3.348
had
Token had
Feature activation+0.242
been
Token been
Feature activation+0.141
deported
Token deported
Feature activation+0.000
six
Token six
Feature activation+0.095
times
Token times
Feature activation+0.019
born
Tokenborn
Feature activation+0.000
,
Token,
Feature activation+0.000
Michigan
Token Michigan
Feature activation+0.000
,
Token,
Feature activation+0.000
assembly
Token assembly
Feature activation+0.172
plant
Token plant
Feature activation+3.209
located
Token located
Feature activation+0.770
12
Token 12
Feature activation+0.743
miles
Token miles
Feature activation+0.000
southwest
Token southwest
Feature activation+0.238
of
Token of
Feature activation+0.566
Santa
Token Santa
Feature activation+0.000
Rosa
Token Rosa
Feature activation+0.000
,
Token,
Feature activation+0.000
CA
Token CA
Feature activation+0.000
elementary
Token elementary
Feature activation+0.293
school
Token school
Feature activation+3.264
district
Token district
Feature activation+2.696
is
Token is
Feature activation+0.792
mat
Token mat
Feature activation+0.000
uring
Tokenuring
Feature activation+0.530
robust
Token robust
Feature activation+0.162

INTERVAL 2.805 - 3.156
CONTAINS 0.000%

women
Token women
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
health
Token health
Feature activation+0.000
clinic
Token clinic
Feature activation+2.816
called
Token called
Feature activation+0.136
Aid
Token Aid
Feature activation+0.000
for
Token for
Feature activation+0.000
Women
Token Women
Feature activation+0.000
on
Token on
Feature activation+0.370
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
south
Token south
Feature activation+0.000
London
Token London
Feature activation+0.000
police
Token police
Feature activation+0.000
station
Token station
Feature activation+2.872
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
arrested
Token arrested
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
Dallas
Token Dallas
Feature activation+0.000
Kara
Token Kara
Feature activation+0.000
oke
Tokenoke
Feature activation+0.640
bar
Token bar
Feature activation+3.012
while
Token while
Feature activation+0.000
he
Token he
Feature activation+0.000
and
Token and
Feature activation+0.000
American
Token American
Feature activation+0.000
white
Token white
Feature activation+0.000
Bras
Token Bras
Feature activation+0.000
ilia
Tokenilia
Feature activation+1.354
,
Token,
Feature activation+1.554
Brazil
Token Brazil
Feature activation+1.403
July
Token July
Feature activation+0.756
14
Token 14
Feature activation+2.891
,
Token,
Feature activation+3.506
2016
Token 2016
Feature activation+2.381
.
Token.
Feature activation+0.142
REUTERS
Token REUTERS
Feature activation+0.000
/
Token/
Feature activation+0.000

INTERVAL 2.454 - 2.805
CONTAINS 0.001%

have
Token have
Feature activation+0.000
eroded
Token eroded
Feature activation+0.000
from
Token from
Feature activation+0.000
Wisconsin
Token Wisconsin
Feature activation+0.000
fields
Token fields
Feature activation+1.140
in
Token in
Feature activation+2.536
2003
Token 2003
Feature activation+0.681
,
Token,
Feature activation+0.018
amount
Token amount
Feature activation+0.000
ing
Tokening
Feature activation+0.000
to
Token to
Feature activation+0.000
Wichita
Token Wichita
Feature activation+0.000
Re
Token Re
Feature activation+0.000
formation
Tokenformation
Feature activation+0.000
Lutheran
Token Lutheran
Feature activation+0.000
Church
Token Church
Feature activation+2.297
in
Token in
Feature activation+2.684
Kansas
Token Kansas
Feature activation+0.042
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
New
TokenNew
Feature activation+0.000
,
Token,
Feature activation+2.138
Nov
Token Nov
Feature activation+0.159
.
Token.
Feature activation+0.052
13
Token 13
Feature activation+2.155
,
Token,
Feature activation+2.032
2014
Token 2014
Feature activation+2.546
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.078
Dave
TokenDave
Feature activation+0.000
Releases
Token Releases
Feature activation+0.000
R
Token R
Feature activation+0.000
Rosa
Token Rosa
Feature activation+0.000
,
Token,
Feature activation+0.000
CA
Token CA
Feature activation+0.000
elementary
Token elementary
Feature activation+0.293
school
Token school
Feature activation+3.264
district
Token district
Feature activation+2.696
is
Token is
Feature activation+0.792
mat
Token mat
Feature activation+0.000
uring
Tokenuring
Feature activation+0.530
robust
Token robust
Feature activation+0.162
ly
Tokenly
Feature activation+0.396
San
Token San
Feature activation+0.000
Francisco
Token Francisco
Feature activation+0.000
's
Token's
Feature activation+0.295
So
Token So
Feature activation+0.000
Ma
TokenMa
Feature activation+0.498
neighborhood
Token neighborhood
Feature activation+2.527
on
Token on
Feature activation+0.545
suspicion
Token suspicion
Feature activation+0.000
of
Token of
Feature activation+0.000
resisting
Token resisting
Feature activation+0.000
arrest
Token arrest
Feature activation+0.000

INTERVAL 2.104 - 2.454
CONTAINS 0.002%

he
Tokenhe
Feature activation+0.000
jiang
Tokenjiang
Feature activation+0.000
province
Token province
Feature activation+0.227
,
Token,
Feature activation+0.460
China
Token China
Feature activation+0.546
,
Token,
Feature activation+2.183
September
Token September
Feature activation+0.000
5
Token 5
Feature activation+1.530
,
Token,
Feature activation+2.263
2016
Token 2016
Feature activation+2.013
.
Token.
Feature activation+0.000
laundry
Token laundry
Feature activation+0.000
hanging
Token hanging
Feature activation+0.000
from
Token from
Feature activation+0.000
Shanghai
Token Shanghai
Feature activation+0.000
residences
Token residences
Feature activation+0.927
in
Token in
Feature activation+2.209
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Mission
TokenMission
Feature activation+0.000
Impossible
Token Impossible
Feature activation+0.000
3
Token 3
Feature activation+0.000
to
Token to
Feature activation+0.000
inmates
Token inmates
Feature activation+0.000
at
Token at
Feature activation+0.000
Philadelphia
Token Philadelphia
Feature activation+0.000
correctional
Token correctional
Feature activation+0.000
facility
Token facility
Feature activation+2.141
-
Token -
Feature activation+0.000
live
Token live
Feature activation+0.000
Read
Token Read
Feature activation+0.000
more
Token more
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.460
China
Token China
Feature activation+0.546
,
Token,
Feature activation+2.183
September
Token September
Feature activation+0.000
5
Token 5
Feature activation+1.530
,
Token,
Feature activation+2.263
2016
Token 2016
Feature activation+2.013
.
Token.
Feature activation+0.000
REUTERS
Token REUTERS
Feature activation+0.000
/
Token/
Feature activation+0.000
E
TokenE
Feature activation+0.000
North
Token North
Feature activation+0.000
Stafford
Token Stafford
Feature activation+0.000
shire
Tokenshire
Feature activation+0.064
,
Token,
Feature activation+0.573
UK
Token UK
Feature activation+0.169
from
Token from
Feature activation+2.341
1998
Token 1998
Feature activation+0.680
.
Token.
Feature activation+0.017
Eth
Token Eth
Feature activation+0.000
ical
Tokenical
Feature activation+0.000
approval
Token approval
Feature activation+0.000

INTERVAL 1.753 - 2.104
CONTAINS 0.004%

High
Token High
Feature activation+0.000
School
Token School
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.175
Chicago
Token Chicago
Feature activation+0.000
suburb
Token suburb
Feature activation+1.904
between
Token between
Feature activation+0.642
1965
Token 1965
Feature activation+0.519
and
Token and
Feature activation+0.000
1981
Token 1981
Feature activation+0.280
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.431
across
Token across
Feature activation+0.180
the
Token the
Feature activation+0.149
COUN
Token COUN
Feature activation+0.000
TRY
TokenTRY
Feature activation+0.751
-
Token-
Feature activation+1.831
if
Token if
Feature activation+0.385
George
Token George
Feature activation+0.000
Zimmerman
Token Zimmerman
Feature activation+0.000
is
Token is
Feature activation+0.000
acquitted
Token acquitted
Feature activation+0.000
to
Token to
Feature activation+0.443
46
Token 46
Feature activation+0.142
.
Token.
Feature activation+0.000
6
Token6
Feature activation+0.000
percent
Token percent
Feature activation+0.393
in
Token in
Feature activation+1.820
the
Token the
Feature activation+1.045
summer
Token summer
Feature activation+0.161
quarter
Token quarter
Feature activation+0.137
,
Token,
Feature activation+0.000
second
Token second
Feature activation+0.000
Tel
Token Tel
Feature activation+0.000
Aviv
Token Aviv
Feature activation+0.000
's
Token's
Feature activation+0.000
Sar
Token Sar
Feature activation+0.391
ona
Tokenona
Feature activation+0.434
Market
Token Market
Feature activation+1.883
Wednesday
Token Wednesday
Feature activation+0.855
night
Token night
Feature activation+1.012
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
16
Token 16
Feature activation+0.071
people
Token people
Feature activation+0.399
in
Token in
Feature activation+0.786
two
Token two
Feature activation+0.217
nearby
Token nearby
Feature activation+0.324
villages
Token villages
Feature activation+1.844
.
Token.
Feature activation+0.017
His
Token His
Feature activation+0.000
victims
Token victims
Feature activation+0.172
,
Token,
Feature activation+0.001
mostly
Token mostly
Feature activation+0.000

INTERVAL 1.403 - 1.753
CONTAINS 0.008%

surfaced
Token surfaced
Feature activation+0.000
anew
Token anew
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
Munich
Token Munich
Feature activation+0.000
conference
Token conference
Feature activation+1.429
where
Token where
Feature activation+0.000
Russia
Token Russia
Feature activation+0.000
rejected
Token rejected
Feature activation+0.000
French
Token French
Feature activation+0.000
charges
Token charges
Feature activation+0.000
opening
Token opening
Feature activation+0.000
a
Token a
Feature activation+0.000
Riverside
Token Riverside
Feature activation+0.000
County
Token County
Feature activation+0.000
location
Token location
Feature activation+0.970
in
Token in
Feature activation+1.588
Mur
Token Mur
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
eta
Tokeneta
Feature activation+0.304
,
Token,
Feature activation+0.578
according
Token according
Feature activation+0.000
Philadelphia
Token Philadelphia
Feature activation+0.524
,
Token,
Feature activation+0.828
the
Token the
Feature activation+0.612
leading
Token leading
Feature activation+0.000
cities
Token cities
Feature activation+0.303
of
Token of
Feature activation+1.496
colonial
Token colonial
Feature activation+0.324
America
Token America
Feature activation+0.259
,
Token,
Feature activation+0.505
though
Token though
Feature activation+0.000
Richmond
Token Richmond
Feature activation+0.033
YPG
Token YPG
Feature activation+0.000
headquarters
Token headquarters
Feature activation+0.000
in
Token in
Feature activation+0.000
northern
Token northern
Feature activation+0.000
Syria
Token Syria
Feature activation+0.722
in
Token in
Feature activation+1.427
2015
Token 2015
Feature activation+0.301
,
Token,
Feature activation+0.000
particularly
Token particularly
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Trends
Token Trends
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
Denver
Token Denver
Feature activation+0.000
research
Token research
Feature activation+0.000
group
Token group
Feature activation+1.450
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
real
Token real
Feature activation+0.000

INTERVAL 1.052 - 1.403
CONTAINS 0.028%

had
Token had
Feature activation+0.028
nothing
Token nothing
Feature activation+0.399
to
Token to
Feature activation+0.257
do
Token do
Feature activation+0.839
with
Token with
Feature activation+1.652
the
Token the
Feature activation+1.138
matter
Token matter
Feature activation+0.118
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
According
TokenAccording
Feature activation+0.000
in
Token in
Feature activation+0.000
Fall
Token Fall
Feature activation+0.000
ujah
Tokenujah
Feature activation+0.075
on
Token on
Feature activation+0.504
Thursday
Token Thursday
Feature activation+0.217
in
Token in
Feature activation+1.255
protest
Token protest
Feature activation+0.091
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
attack
Token attack
Feature activation+0.000
that
Token that
Feature activation+0.000
al
Tokenal
Feature activation+0.000
Pradesh
Token Pradesh
Feature activation+0.000
and
Token and
Feature activation+0.000
Punjab
Token Punjab
Feature activation+0.000
in
Token in
Feature activation+0.755
the
Token the
Feature activation+1.085
north
Token north
Feature activation+1.053
.
Token.
Feature activation+0.107
As
Token As
Feature activation+0.000
parties
Token parties
Feature activation+0.000
compete
Token compete
Feature activation+0.000
care
Token care
Feature activation+0.000
what
Token what
Feature activation+0.000
state
Token state
Feature activation+0.000
you
Token you
Feature activation+0.000
live
Token live
Feature activation+0.000
in
Token in
Feature activation+1.136
,
Token,
Feature activation+0.645
take
Token take
Feature activation+0.000
me
Token me
Feature activation+0.014
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.032
Takes
Token Takes
Feature activation+0.000
h
Tokenh
Feature activation+0.000
ima
Tokenima
Feature activation+0.000
in
Token in
Feature activation+0.833
Japan
Token Japan
Feature activation+0.844
,
Token,
Feature activation+1.191
and
Token and
Feature activation+0.121
claimed
Token claimed
Feature activation+0.163
by
Token by
Feature activation+0.000
both
Token both
Feature activation+0.000
countries
Token countries
Feature activation+0.018

INTERVAL 0.701 - 1.052
CONTAINS 0.089%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
offshore
Token offshore
Feature activation+0.000
oil
Token oil
Feature activation+0.000
fields
Token fields
Feature activation+0.968
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.007
Shell
Token Shell
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
to
Token to
Feature activation+0.099
be
Token be
Feature activation+0.141
the
Token the
Feature activation+0.079
county
Token county
Feature activation+0.112
's
Token's
Feature activation+0.273
first
Token first
Feature activation+0.844
representative
Token representative
Feature activation+1.275
to
Token to
Feature activation+0.595
the
Token the
Feature activation+0.661
Missouri
Token Missouri
Feature activation+0.143
State
Token State
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.002
largest
Token largest
Feature activation+0.000
city
Token city
Feature activation+0.495
in
Token in
Feature activation+0.949
eastern
Token eastern
Feature activation+0.768
Ukraine
Token Ukraine
Feature activation+0.771
held
Token held
Feature activation+0.146
by
Token by
Feature activation+0.302
pro
Token pro
Feature activation+0.338
-
Token-
Feature activation+0.000
statewide
Token statewide
Feature activation+0.000
cleanup
Token cleanup
Feature activation+0.389
.
Token.
Feature activation+0.000
Nation
Token Nation
Feature activation+0.000
ally
Tokenally
Feature activation+0.000
,
Token,
Feature activation+0.707
all
Token all
Feature activation+0.524
the
Token the
Feature activation+0.342
cigarette
Token cigarette
Feature activation+0.000
but
Token but
Feature activation+0.000
ts
Tokents
Feature activation+0.157
at
Token at
Feature activation+0.000
deepening
Token deepening
Feature activation+0.000
ÂŃ
Token ÂŃ
Feature activation+0.000
reg
Tokenreg
Feature activation+0.000
ional
Tokenional
Feature activation+0.000
alliances
Token alliances
Feature activation+0.787
to
Token to
Feature activation+0.138
confront
Token confront
Feature activation+0.000
China
Token China
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 0.351 - 0.701
CONTAINS 0.333%

hall
Tokenhall
Feature activation+0.000
o
Tokeno
Feature activation+0.000
Berlin
Token Berlin
Feature activation+0.000
!)
Token!)
Feature activation+0.844
tend
Token tend
Feature activation+0.467
to
Token to
Feature activation+0.543
speak
Token speak
Feature activation+0.000
English
Token English
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.073
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.,
Token.,
Feature activation+0.367
there
Token there
Feature activation+0.347
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.274
time
Tokentime
Feature activation+0.000
Ohio
Token Ohio
Feature activation+0.000
State
Token State
Feature activation+0.000
All
Token All
Feature activation+0.000
-
Token-
Feature activation+0.025
American
TokenAmerican
Feature activation+0.352
and
Token and
Feature activation+0.000
World
Token World
Feature activation+0.000
Series
Token Series
Feature activation+0.000
of
Token of
Feature activation+0.000
Fighting
Token Fighting
Feature activation+0.000
2011
Token 2011
Feature activation+0.009
and
Token and
Feature activation+0.000
worked
Token worked
Feature activation+0.000
with
Token with
Feature activation+0.000
him
Token him
Feature activation+0.000
there
Token there
Feature activation+0.685
for
Token for
Feature activation+0.319
one
Token one
Feature activation+0.070
season
Token season
Feature activation+0.414
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
fourth
Token fourth
Feature activation+0.000
-
Token-
Feature activation+0.000
low
Tokenlow
Feature activation+0.000
est
Tokenest
Feature activation+0.000
level
Token level
Feature activation+0.000
nationwide
Token nationwide
Feature activation+0.634
behind
Token behind
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
,
Token,
Feature activation+0.000
D
Token D
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.351
CONTAINS 99.534%

bles
Tokenbles
Feature activation+0.000
who
Token who
Feature activation+0.000
live
Token live
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
trailer
Token trailer
Feature activation+0.000
park
Token park
Feature activation+0.382
and
Token and
Feature activation+0.278
are
Token are
Feature activation+0.195
constantly
Token constantly
Feature activation+0.000
annoyed
Token annoyed
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
B
TokenB
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
health
Token health
Feature activation+0.000
department
Token department
Feature activation+0.000
set
Token set
Feature activation+0.000
it
Token it
Feature activation+0.000
into
Token into
Feature activation+0.000
memory
Token memory
Feature activation+0.000
.
Token.
Feature activation+0.000
Once
Token Once
Feature activation+0.000
there
Token there
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
control
Token control
Feature activation+0.000
the
Token the
Feature activation+0.000
taken
Token taken
Feature activation+0.000
over
Token over
Feature activation+0.000
by
Token by
Feature activation+0.000
Google
Token Google
Feature activation+0.000
-
Token -
Feature activation+0.000
disputes
Token disputes
Feature activation+0.000
the
Token the
Feature activation+0.000
figure
Token figure
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
why
Token why
Feature activation+0.000
defence
Token defence
Feature activation+0.000
analysts
Token analysts
Feature activation+0.000
think
Token think
Feature activation+0.000
that
Token that
Feature activation+0.000
Kim
Token Kim
Feature activation+0.000
Jong
Token Jong
Feature activation+0.000
-
Token-
Feature activation+0.000
un
Tokenun
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000

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 H7.3: (feature 13711)

TOP ACTIVATIONS
MAX = 3.150

as
Token as
Feature activation+0.000
long
Token long
Feature activation+0.649
as
Token as
Feature activation+0.133
I
Token I
Feature activation+0.800
can
Token can
Feature activation+0.980
remember
Token remember
Feature activation+3.150
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
Andy
Token Andy
Feature activation+0.000
Buc
Token Buc
Feature activation+0.000
z
Tokenz
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
seven
Token seven
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
,
Token,
Feature activation+2.930
$
Token $
Feature activation+0.000
42
Token42
Feature activation+0.581
-
Token-
Feature activation+0.110
million
Tokenmillion
Feature activation+0.000
contract
Token contract
Feature activation+0.000
researching
Token researching
Feature activation+0.000
for
Token for
Feature activation+0.000
15
Token 15
Feature activation+0.000
years
Token years
Feature activation+0.057
covering
Token covering
Feature activation+1.274
over
Token over
Feature activation+2.705
200
Token 200
Feature activation+1.936
years
Token years
Feature activation+0.675
of
Token of
Feature activation+0.526
wealth
Token wealth
Feature activation+0.519
and
Token and
Feature activation+0.107
signed
Token signed
Feature activation+0.000
a
Token a
Feature activation+0.000
three
Token three
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
,
Token,
Feature activation+2.635
$
Token $
Feature activation+0.000
4
Token4
Feature activation+0.031
.
Token.
Feature activation+0.000
05
Token05
Feature activation+0.000
million
Token million
Feature activation+0.000
sign
Token sign
Feature activation+0.031
a
Token a
Feature activation+0.000
1
Token 1
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
,
Token,
Feature activation+2.478
minor
Token minor
Feature activation+0.000
league
Token league
Feature activation+0.000
contract
Token contract
Feature activation+0.005
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
months
Token months
Feature activation+0.094
-
Token-
Feature activation+0.000
long
Tokenlong
Feature activation+0.727
conflict
Token conflict
Feature activation+2.376
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
M
TokenM
Feature activation+0.000
ilit
Tokenilit
Feature activation+0.000
Enhanced
Token Enhanced
Feature activation+0.000
Edition
Token Edition
Feature activation+0.000
for
Token for
Feature activation+0.000
some
Token some
Feature activation+0.000
time
Token time
Feature activation+0.801
now
Token now
Feature activation+2.367
,
Token,
Feature activation+0.019
but
Token but
Feature activation+0.198
until
Token until
Feature activation+0.000
all
Token all
Feature activation+0.000
issues
Token issues
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
four
Token four
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
,
Token,
Feature activation+2.328
$
Token $
Feature activation+0.000
50
Token50
Feature activation+0.000
million
Token million
Feature activation+0.000
offer
Token offer
Feature activation+0.000
sheet
Token sheet
Feature activation+0.000
in
Token in
Feature activation+0.000
court
Token court
Feature activation+0.000
for
Token for
Feature activation+0.000
several
Token several
Feature activation+0.000
years
Token years
Feature activation+0.387
over
Token over
Feature activation+2.317
the
Token the
Feature activation+2.057
controversial
Token controversial
Feature activation+0.000
practice
Token practice
Feature activation+0.000
of
Token of
Feature activation+0.000
killing
Token killing
Feature activation+0.000
been
Token been
Feature activation+0.000
in
Token in
Feature activation+0.000
trouble
Token trouble
Feature activation+0.000
for
Token for
Feature activation+0.000
years
Token years
Feature activation+0.745
now
Token now
Feature activation+2.275
.
Token.
Feature activation+0.000
Sales
Token Sales
Feature activation+0.000
have
Token have
Feature activation+0.000
fallen
Token fallen
Feature activation+0.000
every
Token every
Feature activation+0.000
tunes
Token tunes
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
time
Token time
Feature activation+0.193
now
Token now
Feature activation+2.087
,
Token,
Feature activation+0.103
but
Token but
Feature activation+0.067
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
his
Token his
Feature activation+0.000
three
Token three
Feature activation+0.000
-
Token-
Feature activation+0.000
month
Tokenmonth
Feature activation+0.000
,
Token,
Feature activation+1.111
3
Token 3
Feature activation+2.082
,
Token,
Feature activation+0.000
312
Token312
Feature activation+0.000
-
Token-
Feature activation+0.000
mile
Tokenmile
Feature activation+0.000
run
Token run
Feature activation+0.000
Kid
Token Kid
Feature activation+0.000
commission
Token commission
Feature activation+0.000
for
Token for
Feature activation+0.296
a
Token a
Feature activation+0.068
while
Token while
Feature activation+0.533
now
Token now
Feature activation+2.074
,
Token,
Feature activation+0.332
and
Token and
Feature activation+0.240
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
court
Token court
Feature activation+0.000
for
Token for
Feature activation+0.000
several
Token several
Feature activation+0.000
years
Token years
Feature activation+0.387
over
Token over
Feature activation+2.317
the
Token the
Feature activation+2.057
controversial
Token controversial
Feature activation+0.000
practice
Token practice
Feature activation+0.000
of
Token of
Feature activation+0.000
killing
Token killing
Feature activation+0.000
sea
Token sea
Feature activation+0.000
the
Token the
Feature activation+0.000
three
Token three
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.006
civil
Token civil
Feature activation+0.231
war
Token war
Feature activation+2.047
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
tricky
Token tricky
Feature activation+0.000
thing
Token thing
Feature activation+0.000
threats
Token threats
Feature activation+0.000
that
Token that
Feature activation+0.000
previously
Token previously
Feature activation+0.000
had
Token had
Feature activation+0.184
not
Token not
Feature activation+1.023
existed
Token existed
Feature activation+2.001
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
city
Token city
Feature activation+0.000
was
Token was
Feature activation+0.000
slowly
Token slowly
Feature activation+0.000
for
Token for
Feature activation+0.000
as
Token as
Feature activation+0.000
long
Token long
Feature activation+0.936
as
Token as
Feature activation+0.300
there
Token there
Feature activation+0.956
have
Token have
Feature activation+1.998
been
Token been
Feature activation+1.080
humans
Token humans
Feature activation+0.214
.
Token.
Feature activation+0.009
Ne
Token Ne
Feature activation+0.000
olithic
Tokenolithic
Feature activation+0.000
for
Token for
Feature activation+0.000
15
Token 15
Feature activation+0.000
years
Token years
Feature activation+0.057
covering
Token covering
Feature activation+1.274
over
Token over
Feature activation+2.705
200
Token 200
Feature activation+1.936
years
Token years
Feature activation+0.675
of
Token of
Feature activation+0.526
wealth
Token wealth
Feature activation+0.519
and
Token and
Feature activation+0.107
income
Token income
Feature activation+0.190
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
setting
Token setting
Feature activation+0.000
for
Token for
Feature activation+0.000
decades
Token decades
Feature activation+0.339
for
Token for
Feature activation+1.908
AM
Token AM
Feature activation+0.000
and
Token and
Feature activation+0.000
FM
Token FM
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
od
Tokenod
Feature activation+0.000
af
Tokenaf
Feature activation+0.000
one
Tokenone
Feature activation+0.000
had
Token had
Feature activation+0.000
long
Token long
Feature activation+0.000
argued
Token argued
Feature activation+1.904
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
ultimate
Token ultimate
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
of
Token of
Feature activation+0.000

Top DFA by src position
MAX = 3.210

that
Token that
Feature activation+0.032
Top resid features:
way
Token way
Feature activation+0.019
Top resid features:
for
Token for
Feature activation+0.090
Top resid features:
as
Token as
Feature activation+0.072
Top resid features:
long
Token long
Feature activation+1.496
Top resid features:
as
Token as
Feature activation+1.593
Top resid features:
I
Token I
Feature activation+0.100
Top resid features:
can
Token can
Feature activation+0.162
Top resid features:
remember
Token remember
Feature activation+0.164
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
This
Token This
Feature activation+0.000
Top resid features:
ig
Tokenig
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.007
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
seven
Token seven
Feature activation+0.002
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
year
Tokenyear
Feature activation+3.210
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
42
Token42
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
million
Tokenmillion
Feature activation+0.000
Top resid features:
scholars
Token scholars
Feature activation+0.009
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
researching
Token researching
Feature activation+0.011
Top resid features:
for
Token for
Feature activation+0.008
Top resid features:
15
Token 15
Feature activation+0.019
Top resid features:
years
Token years
Feature activation+3.102
Top resid features:
covering
Token covering
Feature activation+0.062
Top resid features:
over
Token over
Feature activation+0.010
Top resid features:
200
Token 200
Feature activation+0.000
Top resid features:
years
Token years
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
recently
Token recently
Feature activation+0.083
Top resid features:
signed
Token signed
Feature activation+0.011
Top resid features:
a
Token a
Feature activation+0.011
Top resid features:
three
Token three
Feature activation+0.016
Top resid features:
-
Token-
Feature activation-0.005
Top resid features:
year
Tokenyear
Feature activation+3.112
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
4
Token4
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
05
Token05
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
sign
Token sign
Feature activation-0.023
Top resid features:
a
Token a
Feature activation+0.019
Top resid features:
1
Token 1
Feature activation-0.008
Top resid features:
-
Token-
Feature activation-0.016
Top resid features:
year
Tokenyear
Feature activation+3.046
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
minor
Token minor
Feature activation+0.000
Top resid features:
league
Token league
Feature activation+0.000
Top resid features:
contract
Token contract
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
s
Tokens
Feature activation+0.136
Top resid features:
months
Token months
Feature activation+0.451
Top resid features:
-
Token-
Feature activation+0.065
Top resid features:
long
Tokenlong
Feature activation+1.913
Top resid features:
conflict
Token conflict
Feature activation+0.089
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:
M
TokenM
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.005
Top resid features:
Enhanced
Token Enhanced
Feature activation+0.007
Top resid features:
Edition
Token Edition
Feature activation+0.011
Top resid features:
for
Token for
Feature activation+0.129
Top resid features:
some
Token some
Feature activation+0.125
Top resid features:
time
Token time
Feature activation+2.106
Top resid features:
now
Token now
Feature activation+0.550
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
until
Token until
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.010
Top resid features:
Ļ
TokenĻ
Feature activation+0.007
Top resid features:
s
Tokens
Feature activation+0.017
Top resid features:
four
Token four
Feature activation-0.016
Top resid features:
-
Token-
Feature activation-0.027
Top resid features:
year
Tokenyear
Feature activation+2.911
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
50
Token50
Feature activation+0.000
Top resid features:
million
Token million
Feature activation+0.000
Top resid features:
offer
Token offer
Feature activation+0.000
Top resid features:
service
Token service
Feature activation-0.005
Top resid features:
in
Token in
Feature activation+0.016
Top resid features:
court
Token court
Feature activation-0.037
Top resid features:
for
Token for
Feature activation+0.024
Top resid features:
several
Token several
Feature activation+0.225
Top resid features:
years
Token years
Feature activation+2.404
Top resid features:
over
Token over
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
controversial
Token controversial
Feature activation+0.000
Top resid features:
practice
Token practice
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.006
Top resid features:
been
Token been
Feature activation+0.027
Top resid features:
in
Token in
Feature activation+0.007
Top resid features:
trouble
Token trouble
Feature activation+0.208
Top resid features:
for
Token for
Feature activation+0.048
Top resid features:
years
Token years
Feature activation+2.219
Top resid features:
now
Token now
Feature activation+0.327
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Sales
Token Sales
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
fallen
Token fallen
Feature activation+0.000
Top resid features:
sounding
Tokensounding
Feature activation-0.000
Top resid features:
tunes
Token tunes
Feature activation+0.003
Top resid features:
for
Token for
Feature activation+0.033
Top resid features:
a
Token a
Feature activation+0.027
Top resid features:
long
Token long
Feature activation+0.336
Top resid features:
time
Token time
Feature activation+1.560
Top resid features:
now
Token now
Feature activation+0.603
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
after
Token after
Feature activation+0.002
Top resid features:
finishing
Token finishing
Feature activation-0.018
Top resid features:
his
Token his
Feature activation-0.019
Top resid features:
three
Token three
Feature activation+0.012
Top resid features:
-
Token-
Feature activation+0.033
Top resid features:
month
Tokenmonth
Feature activation+2.609
Top resid features:
,
Token,
Feature activation+0.040
Top resid features:
3
Token 3
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
312
Token312
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
ate
Tokenate
Feature activation+0.001
Top resid features:
Kid
Token Kid
Feature activation+0.003
Top resid features:
commission
Token commission
Feature activation+0.022
Top resid features:
for
Token for
Feature activation+0.107
Top resid features:
a
Token a
Feature activation+0.090
Top resid features:
while
Token while
Feature activation+1.576
Top resid features:
now
Token now
Feature activation+0.552
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
service
Token service
Feature activation-0.004
Top resid features:
in
Token in
Feature activation+0.019
Top resid features:
court
Token court
Feature activation-0.020
Top resid features:
for
Token for
Feature activation+0.024
Top resid features:
several
Token several
Feature activation+0.138
Top resid features:
years
Token years
Feature activation+2.216
Top resid features:
over
Token over
Feature activation+0.082
Top resid features:
the
Token the
Feature activation+0.034
Top resid features:
controversial
Token controversial
Feature activation+0.000
Top resid features:
practice
Token practice
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
civilians
Token civilians
Feature activation-0.001
Top resid features:
during
Token during
Feature activation+0.063
Top resid features:
the
Token the
Feature activation+0.042
Top resid features:
three
Token three
Feature activation+0.049
Top resid features:
-
Token-
Feature activation+0.006
Top resid features:
year
Tokenyear
Feature activation+2.086
Top resid features:
civil
Token civil
Feature activation+0.049
Top resid features:
war
Token war
Feature activation+0.083
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
But
Token But
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
evidence
Token evidence
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:
external
Token external
Feature activation+0.002
Top resid features:
threats
Token threats
Feature activation+0.114
Top resid features:
that
Token that
Feature activation+0.025
Top resid features:
previously
Token previously
Feature activation+2.033
Top resid features:
had
Token had
Feature activation+0.255
Top resid features:
not
Token not
Feature activation+0.042
Top resid features:
existed
Token existed
Feature activation+0.030
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
likely
Token likely
Feature activation-0.005
Top resid features:
been
Token been
Feature activation-0.002
Top resid features:
asked
Token asked
Feature activation+0.027
Top resid features:
for
Token for
Feature activation+0.035
Top resid features:
as
Token as
Feature activation+0.041
Top resid features:
long
Token long
Feature activation+1.306
Top resid features:
as
Token as
Feature activation+1.195
Top resid features:
there
Token there
Feature activation-0.094
Top resid features:
have
Token have
Feature activation-0.007
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
humans
Token humans
Feature activation+0.000
Top resid features:
scholars
Token scholars
Feature activation+0.034
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
researching
Token researching
Feature activation+0.036
Top resid features:
for
Token for
Feature activation+0.017
Top resid features:
15
Token 15
Feature activation+0.005
Top resid features:
years
Token years
Feature activation+2.162
Top resid features:
covering
Token covering
Feature activation+0.172
Top resid features:
over
Token over
Feature activation+0.013
Top resid features:
200
Token 200
Feature activation-0.004
Top resid features:
years
Token years
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
FCC
Token FCC
Feature activation+0.017
Top resid features:
has
Token has
Feature activation-0.008
Top resid features:
been
Token been
Feature activation+0.024
Top resid features:
setting
Token setting
Feature activation-0.071
Top resid features:
for
Token for
Feature activation+0.047
Top resid features:
decades
Token decades
Feature activation+2.401
Top resid features:
for
Token for
Feature activation+0.049
Top resid features:
AM
Token AM
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
FM
Token FM
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
V
Token V
Feature activation-0.063
Top resid features:
od
Tokenod
Feature activation-0.010
Top resid features:
af
Tokenaf
Feature activation-0.002
Top resid features:
one
Tokenone
Feature activation-0.019
Top resid features:
had
Token had
Feature activation+0.003
Top resid features:
long
Token long
Feature activation+2.374
Top resid features:
argued
Token argued
Feature activation+0.130
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
ultimate
Token ultimate
Feature activation+0.000
Top resid features:
benefit
Token benefit
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.01

Head 3: 0.43

Head 4: 0.10

Head 5: 0.11

Head 6: 0.04

Head 7: 0.02

Head 8: 0.10

Head 9: 0.07

Head 10: 0.01

Head 11: 0.01

Positive logits

Reviewer2.72

iasis1.87

orescence1.81

iosyncr1.71

parasitic1.69

umni1.66

raq1.65

oyal1.62

shedding1.62

nostalgia1.58

ULTS1.58

nance1.57

marvel1.56

ividual1.56

perty1.56

commodity1.55

ellectual1.54

efficients1.54

graft1.53

Knot1.51

Negative logits

tomorrow-2.59

ASAP-2.35

Thursday-2.30

Friday-2.22

yesterday-2.19

terday-2.14

sooner-2.13

beforehand-2.11

nesday-2.10

Seconds-2.09

immediately-2.09

Thursday-2.08

earlier-2.07

Immediately-2.07

Tuesday-2.05

Monday-2.03

Wednesday-2.03

timeout-2.02

Wednesday-2.01

Friday-2.01

INTERVAL 2.835 - 3.150
CONTAINS 0.000%

as
Token as
Feature activation+0.000
long
Token long
Feature activation+0.649
as
Token as
Feature activation+0.133
I
Token I
Feature activation+0.800
can
Token can
Feature activation+0.980
remember
Token remember
Feature activation+3.150
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
Andy
Token Andy
Feature activation+0.000
Buc
Token Buc
Feature activation+0.000
z
Tokenz
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
seven
Token seven
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
,
Token,
Feature activation+2.930
$
Token $
Feature activation+0.000
42
Token42
Feature activation+0.581
-
Token-
Feature activation+0.110
million
Tokenmillion
Feature activation+0.000
contract
Token contract
Feature activation+0.000

INTERVAL 2.520 - 2.835
CONTAINS 0.000%

researching
Token researching
Feature activation+0.000
for
Token for
Feature activation+0.000
15
Token 15
Feature activation+0.000
years
Token years
Feature activation+0.057
covering
Token covering
Feature activation+1.274
over
Token over
Feature activation+2.705
200
Token 200
Feature activation+1.936
years
Token years
Feature activation+0.675
of
Token of
Feature activation+0.526
wealth
Token wealth
Feature activation+0.519
and
Token and
Feature activation+0.107
signed
Token signed
Feature activation+0.000
a
Token a
Feature activation+0.000
three
Token three
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
,
Token,
Feature activation+2.635
$
Token $
Feature activation+0.000
4
Token4
Feature activation+0.031
.
Token.
Feature activation+0.000
05
Token05
Feature activation+0.000
million
Token million
Feature activation+0.000

INTERVAL 2.205 - 2.520
CONTAINS 0.001%

in
Token in
Feature activation+0.000
court
Token court
Feature activation+0.000
for
Token for
Feature activation+0.000
several
Token several
Feature activation+0.000
years
Token years
Feature activation+0.387
over
Token over
Feature activation+2.317
the
Token the
Feature activation+2.057
controversial
Token controversial
Feature activation+0.000
practice
Token practice
Feature activation+0.000
of
Token of
Feature activation+0.000
killing
Token killing
Feature activation+0.000
been
Token been
Feature activation+0.000
in
Token in
Feature activation+0.000
trouble
Token trouble
Feature activation+0.000
for
Token for
Feature activation+0.000
years
Token years
Feature activation+0.745
now
Token now
Feature activation+2.275
.
Token.
Feature activation+0.000
Sales
Token Sales
Feature activation+0.000
have
Token have
Feature activation+0.000
fallen
Token fallen
Feature activation+0.000
every
Token every
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
four
Token four
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
,
Token,
Feature activation+2.328
$
Token $
Feature activation+0.000
50
Token50
Feature activation+0.000
million
Token million
Feature activation+0.000
offer
Token offer
Feature activation+0.000
sheet
Token sheet
Feature activation+0.000
Enhanced
Token Enhanced
Feature activation+0.000
Edition
Token Edition
Feature activation+0.000
for
Token for
Feature activation+0.000
some
Token some
Feature activation+0.000
time
Token time
Feature activation+0.801
now
Token now
Feature activation+2.367
,
Token,
Feature activation+0.019
but
Token but
Feature activation+0.198
until
Token until
Feature activation+0.000
all
Token all
Feature activation+0.000
issues
Token issues
Feature activation+0.000
sign
Token sign
Feature activation+0.031
a
Token a
Feature activation+0.000
1
Token 1
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
,
Token,
Feature activation+2.478
minor
Token minor
Feature activation+0.000
league
Token league
Feature activation+0.000
contract
Token contract
Feature activation+0.005
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.890 - 2.205
CONTAINS 0.001%

his
Token his
Feature activation+0.000
three
Token three
Feature activation+0.000
-
Token-
Feature activation+0.000
month
Tokenmonth
Feature activation+0.000
,
Token,
Feature activation+1.111
3
Token 3
Feature activation+2.082
,
Token,
Feature activation+0.000
312
Token312
Feature activation+0.000
-
Token-
Feature activation+0.000
mile
Tokenmile
Feature activation+0.000
run
Token run
Feature activation+0.000
for
Token for
Feature activation+0.000
15
Token 15
Feature activation+0.000
years
Token years
Feature activation+0.057
covering
Token covering
Feature activation+1.274
over
Token over
Feature activation+2.705
200
Token 200
Feature activation+1.936
years
Token years
Feature activation+0.675
of
Token of
Feature activation+0.526
wealth
Token wealth
Feature activation+0.519
and
Token and
Feature activation+0.107
income
Token income
Feature activation+0.190
threats
Token threats
Feature activation+0.000
that
Token that
Feature activation+0.000
previously
Token previously
Feature activation+0.000
had
Token had
Feature activation+0.184
not
Token not
Feature activation+1.023
existed
Token existed
Feature activation+2.001
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
city
Token city
Feature activation+0.000
was
Token was
Feature activation+0.000
slowly
Token slowly
Feature activation+0.000
court
Token court
Feature activation+0.000
for
Token for
Feature activation+0.000
several
Token several
Feature activation+0.000
years
Token years
Feature activation+0.387
over
Token over
Feature activation+2.317
the
Token the
Feature activation+2.057
controversial
Token controversial
Feature activation+0.000
practice
Token practice
Feature activation+0.000
of
Token of
Feature activation+0.000
killing
Token killing
Feature activation+0.000
sea
Token sea
Feature activation+0.000
the
Token the
Feature activation+0.000
three
Token three
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.006
civil
Token civil
Feature activation+0.231
war
Token war
Feature activation+2.047
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
tricky
Token tricky
Feature activation+0.000
thing
Token thing
Feature activation+0.000

INTERVAL 1.575 - 1.890
CONTAINS 0.002%

films
Token films
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
years
Token years
Feature activation+0.220
now
Token now
Feature activation+1.587
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
while
Token while
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
how
Token how
Feature activation+0.000
long
Token long
Feature activation+0.000
the
Token the
Feature activation+0.000
effects
Token effects
Feature activation+0.000
last
Token last
Feature activation+1.735
and
Token and
Feature activation+0.000
whether
Token whether
Feature activation+0.000
skin
Token skin
Feature activation+0.000
condition
Token condition
Feature activation+0.000
reaches
Token reaches
Feature activation+0.000
L
Token L
Feature activation+0.000
NG
TokenNG
Feature activation+0.000
demand
Token demand
Feature activation+0.000
over
Token over
Feature activation+0.000
time
Token time
Feature activation+0.224
will
Token will
Feature activation+1.855
grow
Token grow
Feature activation+1.171
faster
Token faster
Feature activation+1.013
than
Token than
Feature activation+0.000
oil
Token oil
Feature activation+0.000
,
Token,
Feature activation+0.000
two
Token two
Feature activation+0.000
centuries
Token centuries
Feature activation+0.000
infantry
Token infantry
Feature activation+0.000
had
Token had
Feature activation+0.045
advanced
Token advanced
Feature activation+1.143
in
Token in
Feature activation+1.805
close
Token close
Feature activation+0.000
-
Token-
Feature activation+0.000
order
Tokenorder
Feature activation+0.000
formations
Token formations
Feature activation+0.284
,
Token,
Feature activation+0.000
fought
Token fought
Feature activation+0.000
the
Token the
Feature activation+0.000
worst
Token worst
Feature activation+0.000
clashes
Token clashes
Feature activation+0.000
in
Token in
Feature activation+0.000
years
Token years
Feature activation+1.612
in
Token in
Feature activation+0.282
Yemen
Token Yemen
Feature activation+0.688
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.082

INTERVAL 1.260 - 1.575
CONTAINS 0.005%

the
Token the
Feature activation+0.195
years
Token years
Feature activation+0.026
since
Token since
Feature activation+0.957
Vatican
Token Vatican
Feature activation+0.000
II
Token II
Feature activation+0.553
in
Token in
Feature activation+1.553
the
Token the
Feature activation+1.150
relationship
Token relationship
Feature activation+0.266
between
Token between
Feature activation+0.000
Catholicism
Token Catholicism
Feature activation+0.000
and
Token and
Feature activation+0.000
took
Token took
Feature activation+0.000
me
Token me
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
time
Token time
Feature activation+0.305
to
Token to
Feature activation+1.546
throw
Token throw
Feature activation+0.146
caution
Token caution
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
wind
Token wind
Feature activation+0.000
AOL
Token AOL
Feature activation+0.000
has
Token has
Feature activation+0.000
become
Token become
Feature activation+0.000
fashionable
Token fashionable
Feature activation+0.000
of
Token of
Feature activation+0.000
late
Token late
Feature activation+1.405
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
addition
Token addition
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
I
Token I
Feature activation+0.000
possibly
Token possibly
Feature activation+0.000
go
Token go
Feature activation+0.000
so
Token so
Feature activation+0.000
long
Token long
Feature activation+0.233
without
Token without
Feature activation+1.334
ever
Token ever
Feature activation+0.460
trying
Token trying
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
products
Token products
Feature activation+0.000
for
Token for
Feature activation+0.000
over
Token over
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.720
now
Token now
Feature activation+1.464
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
of
Token of
Feature activation+0.000
today
Token today
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.945 - 1.260
CONTAINS 0.012%

concepts
Token concepts
Feature activation+0.000
that
Token that
Feature activation+0.000
had
Token had
Feature activation+0.000
long
Token long
Feature activation+0.000
been
Token been
Feature activation+0.229
viewed
Token viewed
Feature activation+1.073
as
Token as
Feature activation+0.000
witchcraft
Token witchcraft
Feature activation+0.000
or
Token or
Feature activation+0.000
sorcery
Token sorcery
Feature activation+0.000
were
Token were
Feature activation+0.397
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
six
Token six
Feature activation+0.726
World
Token World
Feature activation+0.000
Series
Token Series
Feature activation+0.682
titles
Token titles
Feature activation+0.949
,
Token,
Feature activation+0.000
Ba
Token Ba
Feature activation+0.000
er
Tokener
Feature activation+0.000
sees
Token sees
Feature activation+0.000
the
Token the
Feature activation+0.000
career
Token career
Feature activation+0.000
played
Token played
Feature activation+0.203
any
Token any
Feature activation+0.000
role
Token role
Feature activation+0.103
in
Token in
Feature activation+0.557
his
Token his
Feature activation+0.961
father
Token father
Feature activation+0.000
's
Token's
Feature activation+0.583
murder
Token murder
Feature activation+0.000
,
Token,
Feature activation+0.000
police
Token police
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
However
TokenHowever
Feature activation+0.000
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
late
Token late
Feature activation+1.121
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.405
been
Token been
Feature activation+1.359
at
Token at
Feature activation+0.529
the
Token the
Feature activation+0.060
ages
Token ages
Feature activation+0.245
since
Token since
Feature activation+1.328
I
Token I
Feature activation+1.238
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.973
stuck
Token stuck
Feature activation+0.931
my
Token my
Feature activation+0.000
nose
Token nose
Feature activation+0.000
in
Token in
Feature activation+0.000
Bob
Token Bob
Feature activation+0.000

INTERVAL 0.630 - 0.945
CONTAINS 0.030%

,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
has
Token has
Feature activation+0.000
long
Token long
Feature activation+0.000
spar
Token spar
Feature activation+0.164
red
Tokenred
Feature activation+0.918
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000
em
Tokenem
Feature activation+0.000
pire
Tokenpire
Feature activation+0.048
retrospect
Token retrospect
Feature activation+0.000
ives
Tokenives
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.053
past
Token past
Feature activation+0.462
decade
Token decade
Feature activation+0.815
,
Token,
Feature activation+0.438
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
Met
TokenMet
Feature activation+0.000
amorph
Tokenamorph
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
a
Token a
Feature activation+0.000
week
Token week
Feature activation+0.000
goes
Token goes
Feature activation+0.000
by
Token by
Feature activation+0.101
when
Token when
Feature activation+0.704
malware
Token malware
Feature activation+0.000
,
Token,
Feature activation+0.000
zero
Token zero
Feature activation+0.000
-
Token-
Feature activation+0.000
day
Tokenday
Feature activation+0.000
proxy
Token proxy
Feature activation+0.000
skirm
Token skirm
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
long
Token long
Feature activation+0.664
-
Token-
Feature activation+0.559
running
Tokenrunning
Feature activation+1.146
feud
Token feud
Feature activation+0.924
between
Token between
Feature activation+0.256
outgoing
Token outgoing
Feature activation+0.000
.
Token.
Feature activation+0.138
For
Token For
Feature activation+0.110
a
Token a
Feature activation+0.040
decade
Token decade
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.673
's
Token's
Feature activation+0.341
been
Token been
Feature activation+0.302
their
Token their
Feature activation+0.000
policy
Token policy
Feature activation+0.199
,
Token,
Feature activation+0.077

INTERVAL 0.315 - 0.630
CONTAINS 0.101%

the
Token the
Feature activation+0.000
1950
Token 1950
Feature activation+0.000
s
Tokens
Feature activation+0.000
and
Token and
Feature activation+0.000
1960
Token 1960
Feature activation+0.000
s
Tokens
Feature activation+0.317
.
Token.
Feature activation+0.005
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Law
TokenLaw
Feature activation+0.000
yer
Tokenyer
Feature activation+0.000
rookie
Token rookie
Feature activation+0.000
season
Token season
Feature activation+0.359
with
Token with
Feature activation+0.088
the
Token the
Feature activation+0.000
Denver
Token Denver
Feature activation+0.000
Nuggets
Token Nuggets
Feature activation+0.344
in
Token in
Feature activation+0.093
2008
Token 2008
Feature activation+0.000
-
Token-
Feature activation+0.000
09
Token09
Feature activation+0.000
.
Token.
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.000
history
Token history
Feature activation+0.000
was
Token was
Feature activation+0.018
made
Token made
Feature activation+0.000
in
Token in
Feature activation+0.424
perhaps
Token perhaps
Feature activation+0.302
the
Token the
Feature activation+0.219
most
Token most
Feature activation+0.175
compelling
Token compelling
Feature activation+0.386
of
Token of
Feature activation+0.069
report
Token report
Feature activation+0.000
,
Token,
Feature activation+0.351
the
Token the
Feature activation+0.163
IRS
Token IRS
Feature activation+0.000
has
Token has
Feature activation+0.495
made
Token made
Feature activation+0.564
significant
Token significant
Feature activation+0.000
changes
Token changes
Feature activation+0.996
in
Token in
Feature activation+0.328
the
Token the
Feature activation+0.087
way
Token way
Feature activation+0.000
years
Token years
Feature activation+0.000
of
Token of
Feature activation+0.036
public
Token public
Feature activation+0.000
service
Token service
Feature activation+0.083
in
Token in
Feature activation+0.438
the
Token the
Feature activation+0.439
Pennsylvania
Token Pennsylvania
Feature activation+0.000
House
Token House
Feature activation+0.000
and
Token and
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.315
CONTAINS 99.848%

worked
Token worked
Feature activation+0.209
with
Token with
Feature activation+0.113
Dr
Token Dr
Feature activation+0.000
van
Token van
Feature activation+0.000
E
Token E
Feature activation+0.000
el
Tokenel
Feature activation+0.000
en
Tokenen
Feature activation+0.000
's
Token's
Feature activation+0.000
colleagues
Token colleagues
Feature activation+0.155
,
Token,
Feature activation+0.211
and
Token and
Feature activation+0.082
of
Token of
Feature activation+0.000
her
Token her
Feature activation+0.000
own
Token own
Feature activation+0.000
observations
Token observations
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
portal
Token portal
Feature activation+0.000
between
Token between
Feature activation+0.000
her
Token her
Feature activation+0.000
and
Token and
Feature activation+0.000
Pl
Token Pl
Feature activation+0.000
days
Token days
Feature activation+0.000
in
Token in
Feature activation+0.000
jail
Token jail
Feature activation+0.000
in
Token in
Feature activation+0.037
April
Token April
Feature activation+0.000
for
Token for
Feature activation+0.263
violating
Token violating
Feature activation+0.000
his
Token his
Feature activation+0.000
probation
Token probation
Feature activation+0.000
in
Token in
Feature activation+0.000
relation
Token relation
Feature activation+0.000
ership
Tokenership
Feature activation+0.000
of
Token of
Feature activation+0.000
patents
Token patents
Feature activation+0.000
among
Token among
Feature activation+0.000
Chinese
Token Chinese
Feature activation+0.000
nationals
Token nationals
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
increasing
Token increasing
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
starting
Token starting
Feature activation+0.000
quarterback
Token quarterback
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
're
Token're
Feature activation+0.000
typically
Token typically
Feature activation+0.000
the
Token the
Feature activation+0.000
face
Token face
Feature activation+0.000
and
Token and
Feature activation+0.000
leader
Token leader
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 H7.3: (feature 26757)

TOP ACTIVATIONS
MAX = 3.248

.
Token.
Feature activation+0.142
On
Token On
Feature activation+0.000
Friday
Token Friday
Feature activation+0.145
September
Token September
Feature activation+0.065
8
Token 8
Feature activation+1.563
th
Tokenth
Feature activation+3.248
there
Token there
Feature activation+0.653
will
Token will
Feature activation+0.386
be
Token be
Feature activation+0.484
a
Token a
Feature activation+0.824
hack
Token hack
Feature activation+0.023
full
Token full
Feature activation+0.000
moon
Token moon
Feature activation+0.000
in
Token in
Feature activation+0.000
August
Token August
Feature activation+0.000
took
Token took
Feature activation+1.659
place
Token place
Feature activation+2.913
the
Token the
Feature activation+1.135
night
Token night
Feature activation+0.354
of
Token of
Feature activation+0.701
the
Token the
Feature activation+0.288
1
Token 1
Feature activation+0.289
Ab
TokenAb
Feature activation+0.000
dullah
Tokendullah
Feature activation+0.000
died
Token died
Feature activation+0.000
in
Token in
Feature activation+0.000
January
Token January
Feature activation+0.245
this
Token this
Feature activation+2.486
year
Token year
Feature activation+0.111
after
Token after
Feature activation+0.110
almost
Token almost
Feature activation+0.000
20
Token 20
Feature activation+0.000
years
Token years
Feature activation+0.000
the
Token the
Feature activation+0.000
September
Token September
Feature activation+0.000
26
Token 26
Feature activation+0.091
th
Tokenth
Feature activation+0.000
release
Token release
Feature activation+0.506
date
Token date
Feature activation+2.463
without
Token without
Feature activation+0.045
severely
Token severely
Feature activation+0.000
compromising
Token compromising
Feature activation+0.095
the
Token the
Feature activation+0.000
alpha
Token alpha
Feature activation+0.000
-
Token -
Feature activation+0.327
November
Token November
Feature activation+0.473
15
Token 15
Feature activation+0.520
,
Token,
Feature activation+0.722
2016
Token 2016
Feature activation+1.503
covering
Token covering
Feature activation+2.389
16
Token 16
Feature activation+0.273
billion
Token billion
Feature activation+0.384
unique
Token unique
Feature activation+0.468
Twe
Token Twe
Feature activation+0.000
ets
Tokenets
Feature activation+0.884
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
February
Token February
Feature activation+0.000
BMC
Token BMC
Feature activation+0.000
polls
Token polls
Feature activation+2.321
held
Token held
Feature activation+1.138
this
Token this
Feature activation+0.800
year
Token year
Feature activation+0.271
when
Token when
Feature activation+0.058
the
Token the
Feature activation+0.000
will
Token will
Feature activation+0.000
officially
Token officially
Feature activation+0.000
start
Token start
Feature activation+0.108
at
Token at
Feature activation+0.000
midnight
Token midnight
Feature activation+0.000
at
Token at
Feature activation+2.302
select
Token select
Feature activation+0.000
Disney
Token Disney
Feature activation+0.000
stores
Token stores
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
Panama
Token Panama
Feature activation+0.000
on
Token on
Feature activation+0.329
Oct
Token Oct
Feature activation+0.000
.
Token.
Feature activation+0.470
5
Token 5
Feature activation+1.204
,
Token,
Feature activation+2.279
with
Token with
Feature activation+0.583
all
Token all
Feature activation+0.081
games
Token games
Feature activation+0.228
played
Token played
Feature activation+0.000
at
Token at
Feature activation+0.000
told
Token told
Feature activation+0.000
CBS
Token CBS
Feature activation+0.000
in
Token in
Feature activation+0.000
August
Token August
Feature activation+0.000
of
Token of
Feature activation+0.332
last
Token last
Feature activation+2.214
year
Token year
Feature activation+0.037
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.000
exchange
Token exchange
Feature activation+0.000
businesses
Token businesses
Feature activation+0.000
on
Token on
Feature activation+0.000
September
Token September
Feature activation+0.000
30
Token 30
Feature activation+0.126
th
Tokenth
Feature activation+2.162
,
Token,
Feature activation+0.748
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
Tower
Token Tower
Feature activation+0.004
in
Token in
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.646
City
Token City
Feature activation+2.162
that
Token that
Feature activation+0.408
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
seeking
Token seeking
Feature activation+0.000
the
Token the
Feature activation+0.000
decide
Token decide
Feature activation+0.000
on
Token on
Feature activation+0.000
May
Token May
Feature activation+0.000
22
Token 22
Feature activation+0.073
nd
Tokennd
Feature activation+1.242
on
Token on
Feature activation+2.151
whether
Token whether
Feature activation+0.937
to
Token to
Feature activation+0.361
make
Token make
Feature activation+0.058
their
Token their
Feature activation+0.013
country
Token country
Feature activation+0.000
reads
Token reads
Feature activation+0.000
an
Token an
Feature activation+0.000
editorial
Token editorial
Feature activation+0.000
published
Token published
Feature activation+0.000
Sunday
Token Sunday
Feature activation+0.455
on
Token on
Feature activation+2.139
AL
Token AL
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.627
,
Token,
Feature activation+0.176
which
Token which
Feature activation+1.180
1959
Token 1959
Feature activation+0.000
Annual
Token Annual
Feature activation+0.000
Tropical
Token Tropical
Feature activation+0.000
Cy
Token Cy
Feature activation+0.000
clone
Tokenclone
Feature activation+0.000
Conference
Token Conference
Feature activation+2.137
,
Token,
Feature activation+0.034
the
Token the
Feature activation+0.000
Joint
Token Joint
Feature activation+0.000
Meteor
Token Meteor
Feature activation+0.000
ology
Tokenology
Feature activation+0.000
in
Token in
Feature activation+0.000
remarks
Token remarks
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
January
Token January
Feature activation+0.000
conference
Token conference
Feature activation+2.042
of
Token of
Feature activation+0.000
European
Token European
Feature activation+0.000
and
Token and
Feature activation+0.000
Latin
Token Latin
Feature activation+0.000
American
Token American
Feature activation+0.000
in
Token in
Feature activation+0.000
theaters
Token theaters
Feature activation+0.005
on
Token on
Feature activation+0.000
May
Token May
Feature activation+0.000
3
Token 3
Feature activation+0.933
,
Token,
Feature activation+2.031
2019
Token 2019
Feature activation+1.004
.
Token.
Feature activation+0.199
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ed
TokenEd
Feature activation+0.000
Or
Token Or
Feature activation+0.000
dialogue
Token dialogue
Feature activation+0.000
on
Token on
Feature activation+0.000
October
Token October
Feature activation+0.014
7
Token 7
Feature activation+0.833
in
Token in
Feature activation+0.927
Madrid
Token Madrid
Feature activation+2.004
.
Token.
Feature activation+0.538
Neither
Token Neither
Feature activation+0.000
the
Token the
Feature activation+0.000
Catalan
Token Catalan
Feature activation+0.000
regional
Token regional
Feature activation+0.000
In
TokenIn
Feature activation+0.000
a
Token a
Feature activation+0.000
March
Token March
Feature activation+0.000
5
Token 5
Feature activation+0.000
address
Token address
Feature activation+0.566
that
Token that
Feature activation+1.889
was
Token was
Feature activation+1.499
an
Token an
Feature activation+0.000
exercise
Token exercise
Feature activation+0.000
in
Token in
Feature activation+0.000
un
Token un
Feature activation+0.000
59
Token59
Feature activation+0.000
p
Token p
Feature activation+0.042
.
Token.
Feature activation+0.000
m
Tokenm
Feature activation+0.356
.
Token.
Feature activation+0.331
at
Token at
Feature activation+1.887
the
Token the
Feature activation+0.613
latest
Token latest
Feature activation+0.584
for
Token for
Feature activation+0.302
a
Token a
Feature activation+0.000
vote
Token vote
Feature activation+0.000
the
Token the
Feature activation+0.000
House
Token House
Feature activation+0.000
to
Token to
Feature activation+0.000
vote
Token vote
Feature activation+0.000
Friday
Token Friday
Feature activation+0.715
on
Token on
Feature activation+1.837
the
Token the
Feature activation+0.809
legislation
Token legislation
Feature activation+0.596
to
Token to
Feature activation+0.000
begin
Token begin
Feature activation+0.266
dismantling
Token dismantling
Feature activation+0.000

Top DFA by src position
MAX = 3.391

Thursday
Token Thursday
Feature activation+0.047
Top resid features:
afternoon
Token afternoon
Feature activation+0.026
Top resid features:
.
Token.
Feature activation-0.028
Top resid features:
On
Token On
Feature activation+0.011
Top resid features:
Friday
Token Friday
Feature activation+0.137
Top resid features:
September
Token September
Feature activation+3.354
Top resid features:
8
Token 8
Feature activation+0.038
Top resid features:
th
Tokenth
Feature activation+0.151
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation-0.011
Top resid features:
first
Token first
Feature activation-0.006
Top resid features:
full
Token full
Feature activation-0.010
Top resid features:
moon
Token moon
Feature activation-0.007
Top resid features:
in
Token in
Feature activation-0.006
Top resid features:
August
Token August
Feature activation+3.391
Top resid features:
took
Token took
Feature activation+0.008
Top resid features:
place
Token place
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
night
Token night
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Ab
TokenAb
Feature activation-0.002
Top resid features:
dullah
Tokendullah
Feature activation+0.000
Top resid features:
died
Token died
Feature activation-0.068
Top resid features:
in
Token in
Feature activation-0.019
Top resid features:
January
Token January
Feature activation+2.916
Top resid features:
this
Token this
Feature activation+0.046
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
after
Token after
Feature activation+0.000
Top resid features:
almost
Token almost
Feature activation+0.000
Top resid features:
20
Token 20
Feature activation+0.000
Top resid features:
most
Token most
Feature activation-0.003
Top resid features:
likely
Token likely
Feature activation-0.009
Top resid features:
cannot
Token cannot
Feature activation-0.009
Top resid features:
make
Token make
Feature activation+0.018
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
September
Token September
Feature activation+1.216
Top resid features:
26
Token 26
Feature activation+0.772
Top resid features:
th
Tokenth
Feature activation+0.901
Top resid features:
release
Token release
Feature activation+0.040
Top resid features:
date
Token date
Feature activation+0.020
Top resid features:
without
Token without
Feature activation+0.000
Top resid features:
studied
Token studied
Feature activation-0.007
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
time
Token time
Feature activation+0.012
Top resid features:
period
Token period
Feature activation+0.032
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
September
Token September
Feature activation+0.989
Top resid features:
1
Token 1
Feature activation+0.416
Top resid features:
-
Token -
Feature activation+0.022
Top resid features:
November
Token November
Feature activation+0.446
Top resid features:
15
Token 15
Feature activation+0.450
Top resid features:
,
Token,
Feature activation+0.086
Top resid features:
For
Token For
Feature activation-0.004
Top resid features:
instance
Token instance
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.023
Top resid features:
the
Token the
Feature activation-0.059
Top resid features:
February
Token February
Feature activation+2.810
Top resid features:
BMC
Token BMC
Feature activation+0.078
Top resid features:
polls
Token polls
Feature activation+0.009
Top resid features:
held
Token held
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:
Sales
Token Sales
Feature activation+0.006
Top resid features:
will
Token will
Feature activation+0.004
Top resid features:
officially
Token officially
Feature activation-0.084
Top resid features:
start
Token start
Feature activation-0.037
Top resid features:
at
Token at
Feature activation-0.010
Top resid features:
midnight
Token midnight
Feature activation+2.713
Top resid features:
at
Token at
Feature activation+0.046
Top resid features:
select
Token select
Feature activation+0.000
Top resid features:
Disney
Token Disney
Feature activation+0.000
Top resid features:
stores
Token stores
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
3
Token 3
Feature activation+0.045
Top resid features:
and
Token and
Feature activation+0.078
Top resid features:
host
Token host
Feature activation+0.010
Top resid features:
Panama
Token Panama
Feature activation-0.039
Top resid features:
on
Token on
Feature activation+0.226
Top resid features:
Oct
Token Oct
Feature activation+1.347
Top resid features:
.
Token.
Feature activation+0.311
Top resid features:
5
Token 5
Feature activation+0.311
Top resid features:
,
Token,
Feature activation+0.065
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation-0.003
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
told
Token told
Feature activation-0.047
Top resid features:
CBS
Token CBS
Feature activation-0.003
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
August
Token August
Feature activation+2.594
Top resid features:
of
Token of
Feature activation+0.032
Top resid features:
last
Token last
Feature activation+0.082
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
down
Token down
Feature activation-0.035
Top resid features:
its
Token its
Feature activation-0.020
Top resid features:
exchange
Token exchange
Feature activation-0.042
Top resid features:
businesses
Token businesses
Feature activation+0.010
Top resid features:
on
Token on
Feature activation+0.004
Top resid features:
September
Token September
Feature activation+2.187
Top resid features:
30
Token 30
Feature activation+0.253
Top resid features:
th
Tokenth
Feature activation+0.322
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:
man
Tokenman
Feature activation-0.002
Top resid features:
Donald
Token Donald
Feature activation-0.001
Top resid features:
Trump
Token Trump
Feature activation+0.001
Top resid features:
announced
Token announced
Feature activation-0.114
Top resid features:
June
Token June
Feature activation+1.227
Top resid features:
16
Token 16
Feature activation+1.453
Top resid features:
at
Token at
Feature activation+0.213
Top resid features:
his
Token his
Feature activation-0.016
Top resid features:
Trump
Token Trump
Feature activation+0.004
Top resid features:
Tower
Token Tower
Feature activation-0.002
Top resid features:
in
Token in
Feature activation-0.093
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
Ireland
Token Ireland
Feature activation-0.032
Top resid features:
will
Token will
Feature activation-0.010
Top resid features:
decide
Token decide
Feature activation-0.007
Top resid features:
on
Token on
Feature activation-0.016
Top resid features:
May
Token May
Feature activation+1.164
Top resid features:
22
Token 22
Feature activation+1.041
Top resid features:
nd
Tokennd
Feature activation+0.565
Top resid features:
on
Token on
Feature activation+0.021
Top resid features:
whether
Token whether
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation-0.003
Top resid features:
reads
Token reads
Feature activation-0.013
Top resid features:
an
Token an
Feature activation-0.014
Top resid features:
editorial
Token editorial
Feature activation-0.035
Top resid features:
published
Token published
Feature activation-0.074
Top resid features:
Sunday
Token Sunday
Feature activation+2.637
Top resid features:
on
Token on
Feature activation+0.040
Top resid features:
AL
Token AL
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
com
Tokencom
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
conclusions
Token conclusions
Feature activation-0.001
Top resid features:
reached
Token reached
Feature activation-0.007
Top resid features:
at
Token at
Feature activation+0.004
Top resid features:
the
Token the
Feature activation-0.015
Top resid features:
March
Token March
Feature activation+0.928
Top resid features:
1959
Token 1959
Feature activation+1.777
Top resid features:
Annual
Token Annual
Feature activation-0.043
Top resid features:
Tropical
Token Tropical
Feature activation+0.007
Top resid features:
Cy
Token Cy
Feature activation+0.002
Top resid features:
clone
Tokenclone
Feature activation-0.001
Top resid features:
Conference
Token Conference
Feature activation+0.024
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
in
Token in
Feature activation-0.055
Top resid features:
remarks
Token remarks
Feature activation-0.037
Top resid features:
at
Token at
Feature activation-0.045
Top resid features:
a
Token a
Feature activation-0.031
Top resid features:
January
Token January
Feature activation+2.559
Top resid features:
conference
Token conference
Feature activation+0.094
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
European
Token European
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Latin
Token Latin
Feature activation+0.000
Top resid features:
II
Token II
Feature activation-0.027
Top resid features:
opening
Token opening
Feature activation+0.056
Top resid features:
in
Token in
Feature activation+0.021
Top resid features:
theaters
Token theaters
Feature activation+0.016
Top resid features:
on
Token on
Feature activation+0.101
Top resid features:
May
Token May
Feature activation+2.230
Top resid features:
3
Token 3
Feature activation+0.116
Top resid features:
,
Token,
Feature activation+0.290
Top resid features:
2019
Token 2019
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
demonstration
Token demonstration
Feature activation-0.039
Top resid features:
urging
Token urging
Feature activation+0.036
Top resid features:
dialogue
Token dialogue
Feature activation-0.001
Top resid features:
on
Token on
Feature activation-0.002
Top resid features:
October
Token October
Feature activation+1.441
Top resid features:
7
Token 7
Feature activation+0.661
Top resid features:
in
Token in
Feature activation+0.269
Top resid features:
Madrid
Token Madrid
Feature activation+0.052
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Neither
Token Neither
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
In
TokenIn
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.011
Top resid features:
March
Token March
Feature activation+1.629
Top resid features:
5
Token 5
Feature activation+0.902
Top resid features:
address
Token address
Feature activation-0.194
Top resid features:
that
Token that
Feature activation+0.028
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
11
Token 11
Feature activation+0.099
Top resid features:
:
Token:
Feature activation+0.090
Top resid features:
59
Token59
Feature activation+0.090
Top resid features:
p
Token p
Feature activation+0.060
Top resid features:
.
Token.
Feature activation+0.110
Top resid features:
m
Tokenm
Feature activation+0.977
Top resid features:
.
Token.
Feature activation+0.348
Top resid features:
at
Token at
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
latest
Token latest
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
wants
Token wants
Feature activation-0.052
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
House
Token House
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.040
Top resid features:
vote
Token vote
Feature activation+0.057
Top resid features:
Friday
Token Friday
Feature activation+2.052
Top resid features:
on
Token on
Feature activation+0.051
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
legislation
Token legislation
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
begin
Token begin
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.02

Head 3: 0.43

Head 4: 0.04

Head 5: 0.12

Head 6: 0.07

Head 7: 0.04

Head 8: 0.09

Head 9: 0.05

Head 10: 0.02

Head 11: 0.02

Positive logits

Reviewer2.62

feat1.91

Interested1.88

vernment1.80

phabet1.74

METHOD1.71

listed1.71

roup1.63

ARGET1.62

mark1.62

earch1.61

gress1.61

athing1.61

OSS1.60

rious1.59

quest1.58

iphate1.58

Zig1.57

owship1.57

vik1.57

Negative logits

Mondays-3.03

Saturdays-2.83

onday-2.77

sooner-2.75

Tues-2.73

Sundays-2.64

Tuesday-2.61

summers-2.56

uesday-2.51

Wednesday-2.48

yesterday-2.47

Fridays-2.46

terday-2.39

Monday-2.36

winters-2.30

tomorrow-2.27

Thursday-2.26

Cooldown-2.25

lately-2.24

Tuesday-2.23

INTERVAL 2.923 - 3.248
CONTAINS 0.000%

.
Token.
Feature activation+0.142
On
Token On
Feature activation+0.000
Friday
Token Friday
Feature activation+0.145
September
Token September
Feature activation+0.065
8
Token 8
Feature activation+1.563
th
Tokenth
Feature activation+3.248
there
Token there
Feature activation+0.653
will
Token will
Feature activation+0.386
be
Token be
Feature activation+0.484
a
Token a
Feature activation+0.824
hack
Token hack
Feature activation+0.023

INTERVAL 2.599 - 2.923
CONTAINS 0.000%

full
Token full
Feature activation+0.000
moon
Token moon
Feature activation+0.000
in
Token in
Feature activation+0.000
August
Token August
Feature activation+0.000
took
Token took
Feature activation+1.659
place
Token place
Feature activation+2.913
the
Token the
Feature activation+1.135
night
Token night
Feature activation+0.354
of
Token of
Feature activation+0.701
the
Token the
Feature activation+0.288
1
Token 1
Feature activation+0.289

INTERVAL 2.274 - 2.599
CONTAINS 0.001%

will
Token will
Feature activation+0.000
officially
Token officially
Feature activation+0.000
start
Token start
Feature activation+0.108
at
Token at
Feature activation+0.000
midnight
Token midnight
Feature activation+0.000
at
Token at
Feature activation+2.302
select
Token select
Feature activation+0.000
Disney
Token Disney
Feature activation+0.000
stores
Token stores
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
September
Token September
Feature activation+0.000
26
Token 26
Feature activation+0.091
th
Tokenth
Feature activation+0.000
release
Token release
Feature activation+0.506
date
Token date
Feature activation+2.463
without
Token without
Feature activation+0.045
severely
Token severely
Feature activation+0.000
compromising
Token compromising
Feature activation+0.095
the
Token the
Feature activation+0.000
alpha
Token alpha
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
February
Token February
Feature activation+0.000
BMC
Token BMC
Feature activation+0.000
polls
Token polls
Feature activation+2.321
held
Token held
Feature activation+1.138
this
Token this
Feature activation+0.800
year
Token year
Feature activation+0.271
when
Token when
Feature activation+0.058
the
Token the
Feature activation+0.000
Ab
TokenAb
Feature activation+0.000
dullah
Tokendullah
Feature activation+0.000
died
Token died
Feature activation+0.000
in
Token in
Feature activation+0.000
January
Token January
Feature activation+0.245
this
Token this
Feature activation+2.486
year
Token year
Feature activation+0.111
after
Token after
Feature activation+0.110
almost
Token almost
Feature activation+0.000
20
Token 20
Feature activation+0.000
years
Token years
Feature activation+0.000
-
Token -
Feature activation+0.327
November
Token November
Feature activation+0.473
15
Token 15
Feature activation+0.520
,
Token,
Feature activation+0.722
2016
Token 2016
Feature activation+1.503
covering
Token covering
Feature activation+2.389
16
Token 16
Feature activation+0.273
billion
Token billion
Feature activation+0.384
unique
Token unique
Feature activation+0.468
Twe
Token Twe
Feature activation+0.000
ets
Tokenets
Feature activation+0.884

INTERVAL 1.949 - 2.274
CONTAINS 0.001%

told
Token told
Feature activation+0.000
CBS
Token CBS
Feature activation+0.000
in
Token in
Feature activation+0.000
August
Token August
Feature activation+0.000
of
Token of
Feature activation+0.332
last
Token last
Feature activation+2.214
year
Token year
Feature activation+0.037
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.000
in
Token in
Feature activation+0.000
remarks
Token remarks
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
January
Token January
Feature activation+0.000
conference
Token conference
Feature activation+2.042
of
Token of
Feature activation+0.000
European
Token European
Feature activation+0.000
and
Token and
Feature activation+0.000
Latin
Token Latin
Feature activation+0.000
American
Token American
Feature activation+0.000
decide
Token decide
Feature activation+0.000
on
Token on
Feature activation+0.000
May
Token May
Feature activation+0.000
22
Token 22
Feature activation+0.073
nd
Tokennd
Feature activation+1.242
on
Token on
Feature activation+2.151
whether
Token whether
Feature activation+0.937
to
Token to
Feature activation+0.361
make
Token make
Feature activation+0.058
their
Token their
Feature activation+0.013
country
Token country
Feature activation+0.000
dialogue
Token dialogue
Feature activation+0.000
on
Token on
Feature activation+0.000
October
Token October
Feature activation+0.014
7
Token 7
Feature activation+0.833
in
Token in
Feature activation+0.927
Madrid
Token Madrid
Feature activation+2.004
.
Token.
Feature activation+0.538
Neither
Token Neither
Feature activation+0.000
the
Token the
Feature activation+0.000
Catalan
Token Catalan
Feature activation+0.000
regional
Token regional
Feature activation+0.000
exchange
Token exchange
Feature activation+0.000
businesses
Token businesses
Feature activation+0.000
on
Token on
Feature activation+0.000
September
Token September
Feature activation+0.000
30
Token 30
Feature activation+0.126
th
Tokenth
Feature activation+2.162
,
Token,
Feature activation+0.748
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000

INTERVAL 1.624 - 1.949
CONTAINS 0.002%

s
Tokens
Feature activation+0.000
defence
Token defence
Feature activation+0.000
attorney
Token attorney
Feature activation+0.000
,
Token,
Feature activation+0.000
told
Token told
Feature activation+0.000
reporters
Token reporters
Feature activation+1.812
after
Token after
Feature activation+0.463
the
Token the
Feature activation+0.000
13
Token 13
Feature activation+0.000
-
Token-
Feature activation+0.000
hour
Tokenhour
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
6
Token 6
Feature activation+0.344
September
Token September
Feature activation+0.700
]
Token]
Feature activation+1.753
18
Token 18
Feature activation+1.266
85
Token85
Feature activation+0.250
,
Token,
Feature activation+0.239
Bulgaria
Token Bulgaria
Feature activation+0.108
and
Token and
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
September
Token September
Feature activation+0.000
last
Token last
Feature activation+1.648
year
Token year
Feature activation+0.000
an
Token an
Feature activation+0.000
aspiring
Token aspiring
Feature activation+0.000
chef
Token chef
Feature activation+0.000
died
Token died
Feature activation+0.029
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
23
Token 23
Feature activation+0.010
-
Token-
Feature activation+0.000
9
Token9
Feature activation+0.050
vote
Token vote
Feature activation+1.794
legislation
Token legislation
Feature activation+0.176
out
Token out
Feature activation+0.008
-
Token-
Feature activation+0.000
of
Tokenof
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Token and
Feature activation+0.000
ending
Token ending
Feature activation+0.000
May
Token May
Feature activation+0.000
31
Token 31
Feature activation+0.457
,
Token,
Feature activation+0.717
will
Token will
Feature activation+1.673
be
Token be
Feature activation+1.233
released
Token released
Feature activation+0.465
b
Token b
Feature activation+0.000
iann
Tokeniann
Feature activation+0.000
ually
Tokenually
Feature activation+0.057

INTERVAL 1.299 - 1.624
CONTAINS 0.006%

in
Token in
Feature activation+0.363
Spring
Token Spring
Feature activation+0.584
Hill
Token Hill
Feature activation+0.715
,
Token,
Feature activation+0.431
Tennessee
Token Tennessee
Feature activation+1.200
,
Token,
Feature activation+1.520
and
Token and
Feature activation+0.171
was
Token was
Feature activation+0.242
attended
Token attended
Feature activation+0.000
by
Token by
Feature activation+0.000
family
Token family
Feature activation+0.000
afternoon
Token afternoon
Feature activation+0.831
.
Token.
Feature activation+0.142
On
Token On
Feature activation+0.000
Friday
Token Friday
Feature activation+0.145
September
Token September
Feature activation+0.065
8
Token 8
Feature activation+1.563
th
Tokenth
Feature activation+3.248
there
Token there
Feature activation+0.653
will
Token will
Feature activation+0.386
be
Token be
Feature activation+0.484
a
Token a
Feature activation+0.824
and
Token and
Feature activation+0.209
diagnosed
Token diagnosed
Feature activation+0.032
in
Token in
Feature activation+0.200
April
Token April
Feature activation+0.336
and
Token and
Feature activation+0.098
May
Token May
Feature activation+1.581
.
Token.
Feature activation+0.163
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Tenn
TokenTenn
Feature activation+0.000
essee
Tokenessee
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
January
Token January
Feature activation+0.000
of
Token of
Feature activation+0.021
this
Token this
Feature activation+1.444
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
Reuters
Token Reuters
Feature activation+0.000
reported
Token reported
Feature activation+0.684
on
Token on
Feature activation+0.697
15
Token 15
Feature activation+0.935
.
Token.
Feature activation+0.000
Aug
Token Aug
Feature activation+0.000
.
Token.
Feature activation+0.000
15
Token 15
Feature activation+1.104
,
Token,
Feature activation+1.354
2011
Token 2011
Feature activation+0.821
:
Token :
Feature activation+0.065
Bal
Token Bal
Feature activation+0.000
cor
Tokencor
Feature activation+0.000
p
Tokenp
Feature activation+0.062

INTERVAL 0.974 - 1.299
CONTAINS 0.017%

28
Token 28
Feature activation+0.626
âĢĵ
Token âĢĵ
Feature activation+0.000
October
Token October
Feature activation+0.124
1
Token 1
Feature activation+0.723
Ċ
TokenĊ
Feature activation+0.433
Ċ
TokenĊ
Feature activation+1.031
Here
TokenHere
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
at
Token at
Feature activation+0.015
Saturday
Token Saturday
Feature activation+0.000
,
Token,
Feature activation+0.000
Chomsky
Token Chomsky
Feature activation+0.000
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000
deliver
Token deliver
Feature activation+1.041
a
Token a
Feature activation+0.000
speech
Token speech
Feature activation+0.389
on
Token on
Feature activation+0.465
the
Token the
Feature activation+0.000
Arab
Token Arab
Feature activation+0.000
,
Token,
Feature activation+0.104
James
Token James
Feature activation+0.000
K
Token K
Feature activation+0.000
.
Token.
Feature activation+0.000
Polk
Token Polk
Feature activation+0.000
,
Token,
Feature activation+1.098
with
Token with
Feature activation+0.000
Vice
Token Vice
Feature activation+0.000
-
Token-
Feature activation+0.000
President
TokenPresident
Feature activation+0.000
George
Token George
Feature activation+0.000
participated
Token participated
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
second
Token second
Feature activation+0.000
strike
Token strike
Feature activation+0.000
,
Token,
Feature activation+0.977
followed
Token followed
Feature activation+0.054
by
Token by
Feature activation+0.000
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
day
Tokenday
Feature activation+0.000
at
Token at
Feature activation+0.000
an
Token an
Feature activation+0.000
April
Token April
Feature activation+0.000
22
Token 22
Feature activation+0.000
joint
Token joint
Feature activation+0.476
presentation
Token presentation
Feature activation+1.029
by
Token by
Feature activation+0.000
ID
Token ID
Feature activation+0.000
OT
TokenOT
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.650 - 0.974
CONTAINS 0.041%

before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
January
Token January
Feature activation+0.000
trade
Token trade
Feature activation+0.000
deadline
Token deadline
Feature activation+0.441
last
Token last
Feature activation+0.680
season
Token season
Feature activation+0.200
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
world
Token world
Feature activation+0.000
junior
Token junior
Feature activation+0.000
Saturday
Token Saturday
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+0.820
a
Token a
Feature activation+0.222
video
Token video
Feature activation+0.125
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
mountain
Token mountain
Feature activation+0.000
days
Token days
Feature activation+0.000
after
Token after
Feature activation+0.000
the
Token the
Feature activation+0.000
incident
Token incident
Feature activation+0.223
,
Token,
Feature activation+0.205
which
Token which
Feature activation+0.762
involved
Token involved
Feature activation+0.000
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
most
Token most
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
of
Token of
Feature activation+0.000
each
Token each
Feature activation+0.000
month
Token month
Feature activation+0.366
from
Token from
Feature activation+0.947
6
Token 6
Feature activation+0.305
:
Token:
Feature activation+0.000
00
Token00
Feature activation+0.000
-
Token -
Feature activation+0.000
7
Token 7
Feature activation+0.000
was
Token was
Feature activation+0.000
arrested
Token arrested
Feature activation+0.000
Sunday
Token Sunday
Feature activation+0.531
in
Token in
Feature activation+0.000
San
Token San
Feature activation+0.000
Francisco
Token Francisco
Feature activation+0.846
's
Token's
Feature activation+0.000
So
Token So
Feature activation+0.000
Ma
TokenMa
Feature activation+0.000
neighborhood
Token neighborhood
Feature activation+0.204
on
Token on
Feature activation+0.247

INTERVAL 0.325 - 0.650
CONTAINS 0.140%

of
Token of
Feature activation+0.000
Rs
Token Rs
Feature activation+0.000
3
Token 3
Feature activation+0.000
,
Token,
Feature activation+0.000
200
Token200
Feature activation+0.000
crore
Token crore
Feature activation+0.387
and
Token and
Feature activation+0.000
Rs
Token Rs
Feature activation+0.000
39
Token 39
Feature activation+0.000
00
Token00
Feature activation+0.000
crore
Token crore
Feature activation+0.000
Reserve
Token Reserve
Feature activation+0.000
warning
Token warning
Feature activation+0.000
late
Token late
Feature activation+0.000
the
Token the
Feature activation+0.130
previous
Token previous
Feature activation+0.000
day
Token day
Feature activation+0.503
about
Token about
Feature activation+0.193
the
Token the
Feature activation+0.000
outlook
Token outlook
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
visit
Token visit
Feature activation+0.000
on
Token on
Feature activation+0.000
Monday
Token Monday
Feature activation+0.149
and
Token and
Feature activation+0.110
Tuesday
Token Tuesday
Feature activation+0.419
will
Token will
Feature activation+0.480
be
Token be
Feature activation+0.159
mainly
Token mainly
Feature activation+0.000
focused
Token focused
Feature activation+0.227
on
Token on
Feature activation+0.216
the
Token the
Feature activation+0.199
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
motion
Token motion
Feature activation+0.000
on
Token on
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
afternoon
Token afternoon
Feature activation+0.362
,
Token,
Feature activation+0.304
but
Token but
Feature activation+0.000
Hanson
Token Hanson
Feature activation+0.000
got
Token got
Feature activation+0.000
there
Token there
Feature activation+0.000
with
Token with
Feature activation+0.005
West
Token West
Feature activation+0.000
Brom
Token Brom
Feature activation+0.211
(
Token (
Feature activation+0.126
10
Token10
Feature activation+0.000
36
Token36
Feature activation+0.356
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
also
Token also
Feature activation+0.000

INTERVAL 0.000 - 0.325
CONTAINS 99.793%

otide
Tokenotide
Feature activation+0.000
pl
Token pl
Feature activation+0.000
asm
Tokenasm
Feature activation+0.000
id
Tokenid
Feature activation+0.000
target
Token target
Feature activation+0.000
sequence
Token sequence
Feature activation+0.000
of
Token of
Feature activation+0.000
which
Token which
Feature activation+0.000
the
Token the
Feature activation+0.000
nucle
Token nucle
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
com
Token com
Feature activation+0.000
Score
TokenScore
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
equal
Token equal
Feature activation+0.000
company
Token company
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
SUP
TokenSUP
Feature activation+0.000
ER
TokenER
Feature activation+0.000
HY
TokenHY
Feature activation+0.000
PER
TokenPER
Feature activation+0.000
C
TokenC
Feature activation+0.000
UB
TokenUB
Feature activation+0.000
E
TokenE
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
serve
Token serve
Feature activation+0.000
85
Token 85
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
sentence
Token sentence
Feature activation+0.000
before
Token before
Feature activation+0.000
getting
Token getting
Feature activation+0.000
released
Token released
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
midst
Token midst
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Everyone
TokenEveryone
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
city
Token city
Feature activation+0.000
and
Token and
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 H7.3: (feature 26620)

TOP ACTIVATIONS
MAX = 3.687

victory
Token victory
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
1908
Token 1908
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
election
Token election
Feature activation+3.687
,
Token,
Feature activation+0.000
Roosevelt
Token Roosevelt
Feature activation+0.000
was
Token was
Feature activation+0.000
succeeded
Token succeeded
Feature activation+0.000
by
Token by
Feature activation+0.000
demonstrations
Token demonstrations
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
1961
Token 1961
Feature activation+0.000
Gallup
Token Gallup
Feature activation+0.639
poll
Token poll
Feature activation+3.604
revealed
Token revealed
Feature activation+1.337
that
Token that
Feature activation+0.572
57
Token 57
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
1959
Token 1959
Feature activation+0.000
Annual
Token Annual
Feature activation+0.025
Tropical
Token Tropical
Feature activation+0.000
Cy
Token Cy
Feature activation+0.000
clone
Tokenclone
Feature activation+0.114
Conference
Token Conference
Feature activation+3.139
,
Token,
Feature activation+0.438
the
Token the
Feature activation+0.000
Joint
Token Joint
Feature activation+0.000
Meteor
Token Meteor
Feature activation+0.000
ology
Tokenology
Feature activation+0.000
30
Token30
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
in
Token in
Feature activation+0.000
1989
Token 1989
Feature activation+0.804
dollars
Token dollars
Feature activation+2.769
according
Token according
Feature activation+0.395
to
Token to
Feature activation+0.185
the
Token the
Feature activation+0.257
Bureau
Token Bureau
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
specific
Token specific
Feature activation+0.000
episode
Token episode
Feature activation+0.000
from
Token from
Feature activation+0.000
1940
Token 1940
Feature activation+0.329
from
Token from
Feature activation+2.740
Winnipeg
Token Winnipeg
Feature activation+0.456
where
Token where
Feature activation+0.000
young
Token young
Feature activation+0.000
people
Token people
Feature activation+0.000
were
Token were
Feature activation+0.000
inally
Tokeninally
Feature activation+0.000
enacted
Token enacted
Feature activation+0.024
in
Token in
Feature activation+0.103
2001
Token 2001
Feature activation+0.643
(
Token (
Feature activation+2.162
in
Tokenin
Feature activation+2.535
the
Token the
Feature activation+2.376
Economic
Token Economic
Feature activation+0.000
Growth
Token Growth
Feature activation+0.000
and
Token and
Feature activation+0.000
Tax
Token Tax
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
passed
Token passed
Feature activation+0.000
a
Token a
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
law
Token law
Feature activation+2.474
that
Token that
Feature activation+0.606
specifically
Token specifically
Feature activation+0.000
directs
Token directs
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
20
Token 20
Feature activation+0.000
40
Token40
Feature activation+0.000
time
Token time
Feature activation+0.000
-
Token-
Feature activation+0.000
frame
Tokenframe
Feature activation+2.433
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
goal
Token goal
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
000
Token000
Feature activation+0.552
cars
Token cars
Feature activation+0.627
were
Token were
Feature activation+0.590
reported
Token reported
Feature activation+1.225
stolen
Token stolen
Feature activation+0.868
in
Token in
Feature activation+2.387
England
Token England
Feature activation+0.924
and
Token and
Feature activation+0.000
Wales
Token Wales
Feature activation+1.936
:
Token:
Feature activation+0.000
in
Token in
Feature activation+0.000
enacted
Token enacted
Feature activation+0.024
in
Token in
Feature activation+0.103
2001
Token 2001
Feature activation+0.643
(
Token (
Feature activation+2.162
in
Tokenin
Feature activation+2.535
the
Token the
Feature activation+2.376
Economic
Token Economic
Feature activation+0.000
Growth
Token Growth
Feature activation+0.000
and
Token and
Feature activation+0.000
Tax
Token Tax
Feature activation+0.000
Relief
Token Relief
Feature activation+0.000
sel
Tokensel
Feature activation+0.000
1929
Token 1929
Feature activation+0.026
Tony
Token Tony
Feature activation+0.000
L
Token L
Feature activation+0.000
azz
Tokenazz
Feature activation+0.000
eri
Tokeneri
Feature activation+2.347
1930
Token 1930
Feature activation+0.356
-
Token-
Feature activation+0.000
19
Token19
Feature activation+0.000
31
Token31
Feature activation+0.698
Frank
Token Frank
Feature activation+0.000
a
Token a
Feature activation+0.000
1993
Token 1993
Feature activation+0.067
-
Token-
Feature activation+0.000
2006
Token2006
Feature activation+0.418
civil
Token civil
Feature activation+0.000
war
Token war
Feature activation+2.340
between
Token between
Feature activation+0.242
the
Token the
Feature activation+0.147
Hut
Token Hut
Feature activation+0.000
u
Tokenu
Feature activation+0.000
and
Token and
Feature activation+0.000
for
Token for
Feature activation+0.000
drug
Token drug
Feature activation+0.000
-
Token-
Feature activation+0.000
related
Tokenrelated
Feature activation+0.000
crimes
Token crimes
Feature activation+0.000
-
Token -
Feature activation+2.320
compared
Token compared
Feature activation+0.000
with
Token with
Feature activation+0.000
7
Token 7
Feature activation+0.000
43
Token43
Feature activation+0.000
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
recent
Token recent
Feature activation+0.000
study
Token study
Feature activation+0.218
from
Token from
Feature activation+0.038
2013
Token 2013
Feature activation+0.719
,
Token,
Feature activation+2.227
led
Token led
Feature activation+1.421
by
Token by
Feature activation+0.386
a
Token a
Feature activation+0.355
Boston
Token Boston
Feature activation+0.000
University
Token University
Feature activation+0.178
2013
Token 2013
Feature activation+1.004
state
Token state
Feature activation+0.185
defense
Token defense
Feature activation+0.066
order
Token order
Feature activation+1.915
,
Token,
Feature activation+1.651
which
Token which
Feature activation+2.214
Med
Token Med
Feature activation+0.000
ved
Tokenved
Feature activation+0.000
ev
Tokenev
Feature activation+0.000
said
Token said
Feature activation+0.000
was
Token was
Feature activation+0.279
month
Token month
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
general
Token general
Feature activation+0.000
election
Token election
Feature activation+2.210
,
Token,
Feature activation+0.340
provided
Token provided
Feature activation+0.000
they
Token they
Feature activation+0.000
returned
Token returned
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Femin
Token Femin
Feature activation+0.000
ine
Tokenine
Feature activation+0.000
Myst
Token Myst
Feature activation+0.000
ique
Tokenique
Feature activation+0.183
,
Token,
Feature activation+2.209
which
Token which
Feature activation+1.208
is
Token is
Feature activation+0.845
broadly
Token broadly
Feature activation+0.000
credited
Token credited
Feature activation+0.000
with
Token with
Feature activation+0.338
orig
Tokenorig
Feature activation+0.000
inally
Tokeninally
Feature activation+0.000
enacted
Token enacted
Feature activation+0.024
in
Token in
Feature activation+0.103
2001
Token 2001
Feature activation+0.643
(
Token (
Feature activation+2.162
in
Tokenin
Feature activation+2.535
the
Token the
Feature activation+2.376
Economic
Token Economic
Feature activation+0.000
Growth
Token Growth
Feature activation+0.000
and
Token and
Feature activation+0.000
early
Token early
Feature activation+0.000
1940
Token 1940
Feature activation+0.000
s
Tokens
Feature activation+0.000
film
Token film
Feature activation+0.000
criticism
Token criticism
Feature activation+0.339
from
Token from
Feature activation+2.088
novelist
Token novelist
Feature activation+0.000
James
Token James
Feature activation+0.000
Age
Token Age
Feature activation+0.000
e
Tokene
Feature activation+1.148
when
Token when
Feature activation+0.274
in
Token in
Feature activation+0.801
The
Token The
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Times
Token Times
Feature activation+0.995
,
Token,
Feature activation+2.067
under
Token under
Feature activation+0.276
the
Token the
Feature activation+0.003
headline
Token headline
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000

Top DFA by src position
MAX = 4.125

the
Token the
Feature activation-0.008
Top resid features:
Republican
Token Republican
Feature activation-0.036
Top resid features:
victory
Token victory
Feature activation-0.026
Top resid features:
in
Token in
Feature activation+0.074
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
1908
Token 1908
Feature activation+4.125
Top resid features:
presidential
Token presidential
Feature activation+0.039
Top resid features:
election
Token election
Feature activation+0.036
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Roosevelt
Token Roosevelt
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
marches
Token marches
Feature activation+0.001
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
demonstrations
Token demonstrations
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
A
Token A
Feature activation-0.006
Top resid features:
1961
Token 1961
Feature activation+3.841
Top resid features:
Gallup
Token Gallup
Feature activation+0.148
Top resid features:
poll
Token poll
Feature activation+0.055
Top resid features:
revealed
Token revealed
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
57
Token 57
Feature activation+0.000
Top resid features:
conclusions
Token conclusions
Feature activation-0.017
Top resid features:
reached
Token reached
Feature activation-0.003
Top resid features:
at
Token at
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
March
Token March
Feature activation+0.397
Top resid features:
1959
Token 1959
Feature activation+3.063
Top resid features:
Annual
Token Annual
Feature activation+0.070
Top resid features:
Tropical
Token Tropical
Feature activation+0.004
Top resid features:
Cy
Token Cy
Feature activation+0.001
Top resid features:
clone
Tokenclone
Feature activation+0.008
Top resid features:
Conference
Token Conference
Feature activation+0.032
Top resid features:
$
Token $
Feature activation+0.027
Top resid features:
30
Token30
Feature activation+0.030
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
000
Token000
Feature activation+0.028
Top resid features:
in
Token in
Feature activation+0.084
Top resid features:
1989
Token 1989
Feature activation+2.968
Top resid features:
dollars
Token dollars
Feature activation+0.031
Top resid features:
according
Token according
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:
Bureau
Token Bureau
Feature activation+0.000
Top resid features:
into
Token into
Feature activation-0.025
Top resid features:
a
Token a
Feature activation-0.008
Top resid features:
specific
Token specific
Feature activation-0.006
Top resid features:
episode
Token episode
Feature activation+0.032
Top resid features:
from
Token from
Feature activation+0.013
Top resid features:
1940
Token 1940
Feature activation+3.252
Top resid features:
from
Token from
Feature activation+0.055
Top resid features:
Winnipeg
Token Winnipeg
Feature activation+0.000
Top resid features:
where
Token where
Feature activation+0.000
Top resid features:
young
Token young
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.014
Top resid features:
orig
Tokenorig
Feature activation+0.003
Top resid features:
inally
Tokeninally
Feature activation-0.007
Top resid features:
enacted
Token enacted
Feature activation+0.031
Top resid features:
in
Token in
Feature activation+0.031
Top resid features:
2001
Token 2001
Feature activation+2.775
Top resid features:
(
Token (
Feature activation+0.102
Top resid features:
in
Tokenin
Feature activation+0.030
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Economic
Token Economic
Feature activation+0.000
Top resid features:
Growth
Token Growth
Feature activation+0.000
Top resid features:
courts
Token courts
Feature activation+0.000
Top resid features:
when
Token when
Feature activation+0.032
Top resid features:
it
Token it
Feature activation-0.007
Top resid features:
passed
Token passed
Feature activation+0.009
Top resid features:
a
Token a
Feature activation-0.007
Top resid features:
2012
Token 2012
Feature activation+2.881
Top resid features:
law
Token law
Feature activation+0.070
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
specifically
Token specifically
Feature activation+0.000
Top resid features:
directs
Token directs
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
be
Token be
Feature activation-0.002
Top resid features:
operational
Token operational
Feature activation-0.036
Top resid features:
in
Token in
Feature activation+0.027
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
20
Token 20
Feature activation+0.100
Top resid features:
40
Token40
Feature activation+2.681
Top resid features:
time
Token time
Feature activation+0.110
Top resid features:
-
Token-
Feature activation-0.003
Top resid features:
frame
Tokenframe
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
all
Token all
Feature activation-0.002
Top resid features:
but
Token but
Feature activation-0.002
Top resid features:
disappearing
Token disappearing
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
In
Token In
Feature activation+0.011
Top resid features:
1997
Token 1997
Feature activation+2.620
Top resid features:
,
Token,
Feature activation+0.261
Top resid features:
some
Token some
Feature activation-0.010
Top resid features:
400
Token 400
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
000
Token000
Feature activation+0.023
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.005
Top resid features:
orig
Tokenorig
Feature activation+0.004
Top resid features:
inally
Tokeninally
Feature activation-0.003
Top resid features:
enacted
Token enacted
Feature activation+0.058
Top resid features:
in
Token in
Feature activation+0.024
Top resid features:
2001
Token 2001
Feature activation+2.618
Top resid features:
(
Token (
Feature activation+0.058
Top resid features:
in
Tokenin
Feature activation+0.026
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
Economic
Token Economic
Feature activation+0.000
Top resid features:
Growth
Token Growth
Feature activation+0.000
Top resid features:
io
Tokenio
Feature activation-0.002
Top resid features:
Bob
Token Bob
Feature activation-0.002
Top resid features:
Me
Token Me
Feature activation-0.012
Top resid features:
u
Tokenu
Feature activation-0.003
Top resid features:
sel
Tokensel
Feature activation-0.001
Top resid features:
1929
Token 1929
Feature activation+2.776
Top resid features:
Tony
Token Tony
Feature activation+0.112
Top resid features:
L
Token L
Feature activation-0.035
Top resid features:
azz
Tokenazz
Feature activation-0.011
Top resid features:
eri
Tokeneri
Feature activation+0.017
Top resid features:
1930
Token 1930
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.002
Top resid features:
still
Token still
Feature activation-0.005
Top resid features:
reeling
Token reeling
Feature activation-0.010
Top resid features:
from
Token from
Feature activation-0.030
Top resid features:
a
Token a
Feature activation-0.021
Top resid features:
1993
Token 1993
Feature activation+1.517
Top resid features:
-
Token-
Feature activation+0.168
Top resid features:
2006
Token2006
Feature activation+1.101
Top resid features:
civil
Token civil
Feature activation+0.012
Top resid features:
war
Token war
Feature activation+0.056
Top resid features:
between
Token between
Feature activation+0.000
Top resid features:
least
Token least
Feature activation-0.006
Top resid features:
9
Token 9
Feature activation+0.000
Top resid features:
77
Token77
Feature activation+0.031
Top resid features:
people
Token people
Feature activation-0.030
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
2015
Token 2015
Feature activation+2.678
Top resid features:
-
Token -
Feature activation+0.069
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
vast
Token vast
Feature activation-0.006
Top resid features:
majority
Token majority
Feature activation+0.006
Top resid features:
for
Token for
Feature activation+0.010
Top resid features:
A
TokenA
Feature activation+0.003
Top resid features:
more
Token more
Feature activation-0.005
Top resid features:
recent
Token recent
Feature activation-0.003
Top resid features:
study
Token study
Feature activation+0.107
Top resid features:
from
Token from
Feature activation+0.169
Top resid features:
2013
Token 2013
Feature activation+2.117
Top resid features:
,
Token,
Feature activation+0.164
Top resid features:
led
Token led
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
Boston
Token Boston
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
large
Token large
Feature activation+0.003
Top resid features:
increase
Token increase
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
2013
Token 2013
Feature activation+2.584
Top resid features:
state
Token state
Feature activation+0.013
Top resid features:
defense
Token defense
Feature activation+0.027
Top resid features:
order
Token order
Feature activation-0.029
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
which
Token which
Feature activation+0.014
Top resid features:
weeks
Token weeks
Feature activation-0.005
Top resid features:
to
Token to
Feature activation+0.017
Top resid features:
vote
Token vote
Feature activation+0.019
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
last
Token last
Feature activation+0.039
Top resid features:
month
Token month
Feature activation+1.864
Top resid features:
âĢ
TokenâĢ
Feature activation+0.010
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.740
Top resid features:
general
Token general
Feature activation+0.043
Top resid features:
election
Token election
Feature activation+0.008
Top resid features:
an
Tokenan
Feature activation-0.005
Top resid features:
âĢ
TokenâĢ
Feature activation-0.009
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation-0.017
Top resid features:
seminal
Token seminal
Feature activation-0.002
Top resid features:
1963
Token 1963
Feature activation+2.318
Top resid features:
work
Token work
Feature activation+0.114
Top resid features:
,
Token,
Feature activation+0.112
Top resid features:
The
Token The
Feature activation+0.019
Top resid features:
Femin
Token Femin
Feature activation-0.003
Top resid features:
ine
Tokenine
Feature activation-0.001
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.012
Top resid features:
orig
Tokenorig
Feature activation+0.013
Top resid features:
inally
Tokeninally
Feature activation-0.094
Top resid features:
enacted
Token enacted
Feature activation+0.022
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
2001
Token 2001
Feature activation+2.535
Top resid features:
(
Token (
Feature activation+0.053
Top resid features:
in
Tokenin
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Economic
Token Economic
Feature activation+0.000
Top resid features:
Growth
Token Growth
Feature activation+0.000
Top resid features:
some
Token some
Feature activation-0.022
Top resid features:
of
Token of
Feature activation-0.020
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
early
Token early
Feature activation+0.517
Top resid features:
1940
Token 1940
Feature activation+0.957
Top resid features:
s
Tokens
Feature activation+1.111
Top resid features:
film
Token film
Feature activation+0.079
Top resid features:
criticism
Token criticism
Feature activation-0.023
Top resid features:
from
Token from
Feature activation+0.019
Top resid features:
novelist
Token novelist
Feature activation+0.000
Top resid features:
James
Token James
Feature activation+0.000
Top resid features:
results
Token results
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.015
Top resid features:
A
TokenA
Feature activation-0.002
Top resid features:
1910
Token 1910
Feature activation+2.149
Top resid features:
article
Token article
Feature activation+0.063
Top resid features:
in
Token in
Feature activation+0.151
Top resid features:
The
Token The
Feature activation+0.037
Top resid features:
New
Token New
Feature activation+0.000
Top resid features:
York
Token York
Feature activation+0.019
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.04

Head 2: 0.02

Head 3: 0.43

Head 4: 0.07

Head 5: 0.10

Head 6: 0.05

Head 7: 0.04

Head 8: 0.09

Head 9: 0.06

Head 10: 0.02

Head 11: 0.03

Positive logits

Reviewer2.95

schild1.86

ryu1.82

Citation1.74

ッド1.72

SPONSORED1.72

1.70

oslov1.70

vernment1.66

Gram1.64

osi1.61

ocol1.60

erion1.60

ruction1.57

ozyg1.57

1.53

incorrectly1.52

efficients1.51

wrongly1.49

guiIcon1.49

Negative logits

Tuesday-2.92

recent-2.84

Wednesday-2.81

2016-2.72

Thursday-2.72

Thursday-2.70

Tuesday-2.70

Monday-2.66

tomorrow-2.62

Friday-2.61

Friday-2.57

yesterday-2.56

tonight-2.55

Wednesday-2.53

onday-2.46

2017-2.45

2015-2.45

lately-2.44

Mondays-2.43

2015-2.43

INTERVAL 3.318 - 3.687
CONTAINS 0.000%

victory
Token victory
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
1908
Token 1908
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
election
Token election
Feature activation+3.687
,
Token,
Feature activation+0.000
Roosevelt
Token Roosevelt
Feature activation+0.000
was
Token was
Feature activation+0.000
succeeded
Token succeeded
Feature activation+0.000
by
Token by
Feature activation+0.000
demonstrations
Token demonstrations
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
1961
Token 1961
Feature activation+0.000
Gallup
Token Gallup
Feature activation+0.639
poll
Token poll
Feature activation+3.604
revealed
Token revealed
Feature activation+1.337
that
Token that
Feature activation+0.572
57
Token 57
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 2.949 - 3.318
CONTAINS 0.000%

1959
Token 1959
Feature activation+0.000
Annual
Token Annual
Feature activation+0.025
Tropical
Token Tropical
Feature activation+0.000
Cy
Token Cy
Feature activation+0.000
clone
Tokenclone
Feature activation+0.114
Conference
Token Conference
Feature activation+3.139
,
Token,
Feature activation+0.438
the
Token the
Feature activation+0.000
Joint
Token Joint
Feature activation+0.000
Meteor
Token Meteor
Feature activation+0.000
ology
Tokenology
Feature activation+0.000

INTERVAL 2.581 - 2.949
CONTAINS 0.000%

30
Token30
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
in
Token in
Feature activation+0.000
1989
Token 1989
Feature activation+0.804
dollars
Token dollars
Feature activation+2.769
according
Token according
Feature activation+0.395
to
Token to
Feature activation+0.185
the
Token the
Feature activation+0.257
Bureau
Token Bureau
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
specific
Token specific
Feature activation+0.000
episode
Token episode
Feature activation+0.000
from
Token from
Feature activation+0.000
1940
Token 1940
Feature activation+0.329
from
Token from
Feature activation+2.740
Winnipeg
Token Winnipeg
Feature activation+0.456
where
Token where
Feature activation+0.000
young
Token young
Feature activation+0.000
people
Token people
Feature activation+0.000
were
Token were
Feature activation+0.000

INTERVAL 2.212 - 2.581
CONTAINS 0.001%

inally
Tokeninally
Feature activation+0.000
enacted
Token enacted
Feature activation+0.024
in
Token in
Feature activation+0.103
2001
Token 2001
Feature activation+0.643
(
Token (
Feature activation+2.162
in
Tokenin
Feature activation+2.535
the
Token the
Feature activation+2.376
Economic
Token Economic
Feature activation+0.000
Growth
Token Growth
Feature activation+0.000
and
Token and
Feature activation+0.000
Tax
Token Tax
Feature activation+0.000
a
Token a
Feature activation+0.000
1993
Token 1993
Feature activation+0.067
-
Token-
Feature activation+0.000
2006
Token2006
Feature activation+0.418
civil
Token civil
Feature activation+0.000
war
Token war
Feature activation+2.340
between
Token between
Feature activation+0.242
the
Token the
Feature activation+0.147
Hut
Token Hut
Feature activation+0.000
u
Tokenu
Feature activation+0.000
and
Token and
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
passed
Token passed
Feature activation+0.000
a
Token a
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
law
Token law
Feature activation+2.474
that
Token that
Feature activation+0.606
specifically
Token specifically
Feature activation+0.000
directs
Token directs
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
sel
Tokensel
Feature activation+0.000
1929
Token 1929
Feature activation+0.026
Tony
Token Tony
Feature activation+0.000
L
Token L
Feature activation+0.000
azz
Tokenazz
Feature activation+0.000
eri
Tokeneri
Feature activation+2.347
1930
Token 1930
Feature activation+0.356
-
Token-
Feature activation+0.000
19
Token19
Feature activation+0.000
31
Token31
Feature activation+0.698
Frank
Token Frank
Feature activation+0.000
000
Token000
Feature activation+0.552
cars
Token cars
Feature activation+0.627
were
Token were
Feature activation+0.590
reported
Token reported
Feature activation+1.225
stolen
Token stolen
Feature activation+0.868
in
Token in
Feature activation+2.387
England
Token England
Feature activation+0.924
and
Token and
Feature activation+0.000
Wales
Token Wales
Feature activation+1.936
:
Token:
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 1.843 - 2.212
CONTAINS 0.002%

month
Token month
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
general
Token general
Feature activation+0.000
election
Token election
Feature activation+2.210
,
Token,
Feature activation+0.340
provided
Token provided
Feature activation+0.000
they
Token they
Feature activation+0.000
returned
Token returned
Feature activation+0.000
.
Token.
Feature activation+0.000
orig
Tokenorig
Feature activation+0.000
inally
Tokeninally
Feature activation+0.000
enacted
Token enacted
Feature activation+0.024
in
Token in
Feature activation+0.103
2001
Token 2001
Feature activation+0.643
(
Token (
Feature activation+2.162
in
Tokenin
Feature activation+2.535
the
Token the
Feature activation+2.376
Economic
Token Economic
Feature activation+0.000
Growth
Token Growth
Feature activation+0.000
and
Token and
Feature activation+0.000
spent
Token spent
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
$
Token $
Feature activation+0.021
84
Token84
Feature activation+0.504
bn
Tokenbn
Feature activation+2.043
worldwide
Token worldwide
Feature activation+0.000
to
Token to
Feature activation+0.000
improve
Token improve
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
1960
Token 1960
Feature activation+0.000
s
Tokens
Feature activation+0.032
in
Token in
Feature activation+1.319
the
Token the
Feature activation+1.849
United
Token United
Feature activation+0.201
States
Token States
Feature activation+0.853
.
Token.
Feature activation+0.000
Self
Token Self
Feature activation+0.000
-
Token-
Feature activation+0.000
].
Token].
Feature activation+0.000
In
Token In
Feature activation+0.000
a
Token a
Feature activation+0.000
2007
Token 2007
Feature activation+0.000
survey
Token survey
Feature activation+0.744
in
Token in
Feature activation+1.944
the
Token the
Feature activation+1.940
United
Token United
Feature activation+0.225
States
Token States
Feature activation+0.680
,
Token,
Feature activation+0.664
although
Token although
Feature activation+0.011

INTERVAL 1.475 - 1.843
CONTAINS 0.004%

in
Token in
Feature activation+0.000
1981
Token 1981
Feature activation+0.000
to
Token to
Feature activation+0.000
auto
Token auto
Feature activation+0.000
workers
Token workers
Feature activation+0.234
in
Token in
Feature activation+1.799
Detroit
Token Detroit
Feature activation+0.797
,
Token,
Feature activation+0.166
Reagan
Token Reagan
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
in
Token in
Feature activation+0.000
Bolivia
Token Bolivia
Feature activation+0.000
in
Token in
Feature activation+0.000
1967
Token 1967
Feature activation+0.335
that
Token that
Feature activation+2.023
ended
Token ended
Feature activation+1.560
in
Token in
Feature activation+0.000
G
Token G
Feature activation+0.000
ue
Tokenue
Feature activation+0.000
v
Tokenv
Feature activation+0.000
ara
Tokenara
Feature activation+0.000
8
Token8
Feature activation+0.000
%
Token%
Feature activation+0.866
(
Token (
Feature activation+0.311
30
Token30
Feature activation+0.000
th
Tokenth
Feature activation+0.338
)
Token)
Feature activation+1.530
Ċ
TokenĊ
Feature activation+0.422
Ċ
TokenĊ
Feature activation+0.000
2011
Token2011
Feature activation+0.000
:
Token:
Feature activation+1.177
17
Token 17
Feature activation+0.000
2025
Token 2025
Feature activation+0.015
,
Token,
Feature activation+0.000
compared
Token compared
Feature activation+0.000
with
Token with
Feature activation+0.000
2005
Token 2005
Feature activation+0.453
levels
Token levels
Feature activation+1.521
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
China
TokenChina
Feature activation+0.000
did
Token did
Feature activation+0.000
termed
Token termed
Feature activation+0.000
this
Token this
Feature activation+0.000
mid
Token mid
Feature activation+0.000
century
Tokencentury
Feature activation+0.000
era
Token era
Feature activation+0.789
the
Token the
Feature activation+1.559
"
Token "
Feature activation+0.400
Great
TokenGreat
Feature activation+0.298
Comp
Token Comp
Feature activation+0.000
ression
Tokenression
Feature activation+0.217
."
Token."
Feature activation+0.000

INTERVAL 1.106 - 1.475
CONTAINS 0.012%

restoration
Token restoration
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
1956
Token 1956
Feature activation+0.000
American
Token American
Feature activation+0.000
adaptation
Token adaptation
Feature activation+1.131
of
Token of
Feature activation+0.449
the
Token the
Feature activation+0.648
film
Token film
Feature activation+0.099
,
Token,
Feature activation+0.278
Godzilla
Token Godzilla
Feature activation+0.000
2014
Token2014
Feature activation+0.000
:
Token:
Feature activation+1.137
17
Token 17
Feature activation+0.325
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
%
Token%
Feature activation+1.235
(
Token (
Feature activation+0.000
20
Token20
Feature activation+0.000
th
Tokenth
Feature activation+0.000
)
Token)
Feature activation+0.935
Ċ
TokenĊ
Feature activation+0.279
large
Token large
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
estimate
Token estimate
Feature activation+0.420
was
Token was
Feature activation+1.134
that
Token that
Feature activation+0.934
each
Token each
Feature activation+0.000
higher
Token higher
Feature activation+0.000
-
Token-
Feature activation+0.000
skill
Tokenskill
Feature activation+0.000
a
Token a
Feature activation+0.052
total
Token total
Feature activation+0.012
of
Token of
Feature activation+0.025
1966
Token 1966
Feature activation+0.000
films
Token films
Feature activation+0.959
were
Token were
Feature activation+1.292
made
Token made
Feature activation+1.580
in
Token in
Feature activation+0.788
India
Token India
Feature activation+0.586
.
Token.
Feature activation+0.000
Out
Token Out
Feature activation+0.000
D
TokenD
Feature activation+0.000
research
Token research
Feature activation+0.000
project
Token project
Feature activation+0.000
in
Token in
Feature activation+0.000
1965
Token 1965
Feature activation+0.388
,
Token,
Feature activation+1.396
a
Token a
Feature activation+0.000
literature
Token literature
Feature activation+0.000
review
Token review
Feature activation+0.000
published
Token published
Feature activation+0.650
in
Token in
Feature activation+0.042

INTERVAL 0.737 - 1.106
CONTAINS 0.040%

ani
Tokenani
Feature activation+0.000
during
Token during
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
-
Token-
Feature activation+0.000
15
Token15
Feature activation+0.543
,
Token,
Feature activation+1.092
killing
Token killing
Feature activation+0.000
and
Token and
Feature activation+0.000
injuring
Token injuring
Feature activation+0.000
many
Token many
Feature activation+0.000
civilians
Token civilians
Feature activation+0.209
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
years
Token years
Feature activation+0.568
China
Token China
Feature activation+0.000
will
Token will
Feature activation+1.048
have
Token have
Feature activation+0.000
more
Token more
Feature activation+0.000
Christians
Token Christians
Feature activation+0.000
than
Token than
Feature activation+0.000
Communist
Token Communist
Feature activation+0.000
Cat
Token Cat
Feature activation+0.000
lin
Tokenlin
Feature activation+0.000
Kind
Token Kind
Feature activation+0.000
ness
Tokenness
Feature activation+0.110
Offensive
Token Offensive
Feature activation+0.911
event
Token event
Feature activation+0.944
resulted
Token resulted
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
events
Token events
Feature activation+0.000
organ
Token organ
Feature activation+0.000
most
Token most
Feature activation+0.000
popular
Token popular
Feature activation+0.000
articles
Token articles
Feature activation+0.000
in
Token in
Feature activation+0.000
recent
Token recent
Feature activation+0.000
months
Token months
Feature activation+1.025
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
Between
TokenBetween
Feature activation+0.000
2008
Token 2008
Feature activation+0.000
and
Token and
Feature activation+0.000
July
Token July
Feature activation+0.141
2013
Token 2013
Feature activation+0.000
(
Token (
Feature activation+0.952
under
Tokenunder
Feature activation+0.000
Labor
Token Labor
Feature activation+0.000
),
Token),
Feature activation+0.233
8
Token 8
Feature activation+0.000
77
Token77
Feature activation+0.276

INTERVAL 0.369 - 0.737
CONTAINS 0.117%

financing
Token financing
Feature activation+0.000
system
Token system
Feature activation+0.000
back
Token back
Feature activation+0.000
in
Token in
Feature activation+0.000
2003
Token 2003
Feature activation+0.000
,
Token,
Feature activation+0.414
but
Token but
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.000
refused
Token refused
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
January
Token January
Feature activation+0.000
10
Token 10
Feature activation+0.000
,
Token,
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
.
Token.
Feature activation+0.380
REUTERS
Token REUTERS
Feature activation+0.000
/
Token/
Feature activation+0.000
L
TokenL
Feature activation+0.000
isi
Tokenisi
Feature activation+0.000
N
Token N
Feature activation+0.000
riel
Tokenriel
Feature activation+0.000
losses
Token losses
Feature activation+0.000
in
Token in
Feature activation+0.066
World
Token World
Feature activation+0.000
War
Token War
Feature activation+0.000
II
Token II
Feature activation+0.587
refers
Token refers
Feature activation+0.000
to
Token to
Feature activation+0.000
military
Token military
Feature activation+0.000
equipment
Token equipment
Feature activation+0.000
destroyed
Token destroyed
Feature activation+0.000
in
Token in
Feature activation+0.000
Brooklyn
Token Brooklyn
Feature activation+0.000
,
Token,
Feature activation+0.003
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.466
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
a
Tokena
Feature activation+0.000
strong
Token strong
Feature activation+0.000
movement
Token movement
Feature activation+0.000
was
Token was
Feature activation+0.000
passed
Token passed
Feature activation+0.000
in
Token in
Feature activation+0.000
1984
Token 1984
Feature activation+0.161
,
Token,
Feature activation+0.377
which
Token which
Feature activation+0.537
severely
Token severely
Feature activation+0.000
limited
Token limited
Feature activation+0.000
the
Token the
Feature activation+0.000
religious
Token religious
Feature activation+0.000
freedom
Token freedom
Feature activation+0.000

INTERVAL 0.000 - 0.369
CONTAINS 99.824%

of
Token of
Feature activation+0.000
Major
Token Major
Feature activation+0.000
League
Token League
Feature activation+0.000
Baseball
Token Baseball
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
state
Token state
Feature activation+0.000
of
Token of
Feature activation+0.000
Fior
Token Fior
Feature activation+0.000
future
Token future
Feature activation+0.000
use
Token use
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
parliamentary
Token parliamentary
Feature activation+0.000
committee
Token committee
Feature activation+0.000
tasked
Token tasked
Feature activation+0.000
with
Token with
Feature activation+0.000
find
Token find
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Isa
TokenIsa
Feature activation+0.000
ac
Tokenac
Feature activation+0.000
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
actor
Token actor
Feature activation+0.000
from
Token from
Feature activation+0.000
The
Token The
Feature activation+0.000
Force
Token Force
Feature activation+0.000
figures
Token figures
Feature activation+0.000
are
Token are
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
cumulative
Token cumulative
Feature activation+0.000
revenue
Token revenue
Feature activation+0.000
from
Token from
Feature activation+0.000
Ent
Token Ent
Feature activation+0.000
group
Tokengroup
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
question
Token question
Feature activation+0.000
about
Token about
Feature activation+0.000
whether
Token whether
Feature activation+0.000
he
Token he
Feature activation+0.000
might
Token might
Feature activation+0.000
help
Token help
Feature activation+0.000
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
mayors
Token mayors
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
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 H7.3: (feature 40384)

TOP ACTIVATIONS
MAX = 1.675

away
Token away
Feature activation+0.000
that
Token that
Feature activation+0.000
opponents
Token opponents
Feature activation+0.000
can
Token can
Feature activation+0.164
not
Token not
Feature activation+0.627
touch
Token touch
Feature activation+1.675
him
Token him
Feature activation+0.677
with
Token with
Feature activation+0.000
strikes
Token strikes
Feature activation+0.000
.
Token.
Feature activation+0.000
Mas
Token Mas
Feature activation+0.000
that
Token that
Feature activation+0.315
were
Token were
Feature activation+0.538
supposedly
Token supposedly
Feature activation+0.235
there
Token there
Feature activation+0.892
to
Token to
Feature activation+0.638
protect
Token protect
Feature activation+1.558
her
Token her
Feature activation+0.853
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
to
Token to
Feature activation+0.000
beat
Token beat
Feature activation+0.514
the
Token the
Feature activation+0.626
crap
Token crap
Feature activation+0.000
out
Token out
Feature activation+0.588
of
Token of
Feature activation+1.473
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
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
superiors
Token superiors
Feature activation+0.000
recognize
Token recognize
Feature activation+0.370
his
Token his
Feature activation+1.432
undeniable
Token undeniable
Feature activation+0.000
skill
Token skill
Feature activation+0.000
and
Token and
Feature activation+0.000
tolerate
Token tolerate
Feature activation+0.363
his
Token his
Feature activation+1.169
allowed
Token allowed
Feature activation+0.298
female
Token female
Feature activation+0.000
sum
Token sum
Feature activation+0.000
o
Tokeno
Feature activation+0.000
wrestlers
Token wrestlers
Feature activation+0.000
,
Token,
Feature activation+1.367
they
Token they
Feature activation+0.246
competed
Token competed
Feature activation+0.000
nude
Token nude
Feature activation+0.000
,
Token,
Feature activation+0.000
without
Token without
Feature activation+0.000
completely
Token completely
Feature activation+0.278
turning
Token turning
Feature activation+0.485
a
Token a
Feature activation+0.540
blind
Token blind
Feature activation+0.000
eye
Token eye
Feature activation+0.841
to
Token to
Feature activation+1.276
what
Token what
Feature activation+0.822
they
Token they
Feature activation+0.220
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
They
TokenThey
Feature activation+0.000
liked
Token liked
Feature activation+0.663
what
Token what
Feature activation+1.268
they
Token they
Feature activation+0.638
saw
Token saw
Feature activation+0.293
,"
Token,"
Feature activation+0.432
Robinson
Token Robinson
Feature activation+0.000
said
Token said
Feature activation+0.000
Boston
Token Boston
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
know
Token know
Feature activation+0.000
they
Token they
Feature activation+0.023
love
Token love
Feature activation+1.259
me
Token me
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
actually
Token actually
Feature activation+0.000
wanted
Token wanted
Feature activation+0.611
to
Token to
Feature activation+0.257
sit
Token sit
Feature activation+0.476
next
Token next
Feature activation+0.366
to
Token to
Feature activation+1.231
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.183
my
Token my
Feature activation+0.000
walk
Token walk
Feature activation+0.000
man
Tokenman
Feature activation+0.000
US
Token US
Feature activation+0.000
won
Token won
Feature activation+0.001
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
support
Token support
Feature activation+1.230
him
Token him
Feature activation+0.242
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
're
Token're
Feature activation+0.132
going
Token going
Feature activation+0.121
to
Token to
Feature activation+0.268
be
Token be
Feature activation+0.424
leaning
Token leaning
Feature activation+0.053
on
Token on
Feature activation+1.200
me
Token me
Feature activation+0.115
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
But
Token But
Feature activation+0.000
nobody
Token nobody
Feature activation+0.000
ever
Token ever
Feature activation+0.000
asked
Token asked
Feature activation+0.561
,
Token,
Feature activation+0.368
and
Token and
Feature activation+1.178
I
Token I
Feature activation+0.108
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
paid
Token paid
Feature activation+0.000
anything
Token anything
Feature activation+0.000
his
Token his
Feature activation+1.432
undeniable
Token undeniable
Feature activation+0.000
skill
Token skill
Feature activation+0.000
and
Token and
Feature activation+0.000
tolerate
Token tolerate
Feature activation+0.363
his
Token his
Feature activation+1.169
ego
Token ego
Feature activation+0.000
.
Token.
Feature activation+0.000
Springer
Token Springer
Feature activation+0.000
has
Token has
Feature activation+0.000
nicknamed
Token nicknamed
Feature activation+0.000
Grow
Token Grow
Feature activation+0.004
Up
Token Up
Feature activation+0.000
cassette
Token cassette
Feature activation+0.000
were
Token were
Feature activation+0.143
waiting
Token waiting
Feature activation+0.132
for
Token for
Feature activation+1.164
me
Token me
Feature activation+0.134
.
Token.
Feature activation+0.333
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Jack
TokenJack
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
They
TokenThey
Feature activation+0.000
threw
Token threw
Feature activation+0.000
meat
Token meat
Feature activation+0.000
at
Token at
Feature activation+1.156
him
Token him
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
cant
Token cant
Feature activation+0.000
een
Tokeneen
Feature activation+0.000
friends
Token friends
Feature activation+0.000
list
Token list
Feature activation+0.000
.
Token.
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
reb
Token reb
Feature activation+0.000
uffed
Tokenuffed
Feature activation+1.114
him
Token him
Feature activation+0.487
in
Token in
Feature activation+0.178
return
Token return
Feature activation+0.000
emails
Token emails
Feature activation+0.044
and
Token and
Feature activation+0.048
officer
Token officer
Feature activation+0.000
then
Token then
Feature activation+0.000
jumped
Token jumped
Feature activation+0.000
on
Token on
Feature activation+0.833
top
Token top
Feature activation+0.406
of
Token of
Feature activation+1.082
them
Token them
Feature activation+0.110
.
Token.
Feature activation+0.580
"
Token "
Feature activation+0.000
And
TokenAnd
Feature activation+0.108
there
Token there
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
se
Tokense
Feature activation+0.000
emed
Tokenemed
Feature activation+0.000
pumped
Token pumped
Feature activation+0.056
up
Token up
Feature activation+0.385
about
Token about
Feature activation+1.078
killing
Token killing
Feature activation+0.426
Arabs
Token Arabs
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
that
Token that
Feature activation+0.000
her
Token her
Feature activation+0.000
teacher
Token teacher
Feature activation+0.000
had
Token had
Feature activation+0.000
asked
Token asked
Feature activation+0.892
the
Token the
Feature activation+1.067
whole
Token whole
Feature activation+0.487
class
Token class
Feature activation+0.260
to
Token to
Feature activation+0.394
write
Token write
Feature activation+0.271
an
Token an
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
think
Token think
Feature activation+0.160
es
Tokenes
Feature activation+0.141
that
Token that
Feature activation+1.063
I
Token I
Feature activation+0.211
was
Token was
Feature activation+0.000
very
Token very
Feature activation+0.000
rich
Token rich
Feature activation+0.000
.
Token.
Feature activation+0.000

Top DFA by src position
MAX = 1.477

or
Token or
Feature activation+0.010
Top resid features:
far
Token far
Feature activation+0.002
Top resid features:
enough
Token enough
Feature activation-0.000
Top resid features:
away
Token away
Feature activation-0.004
Top resid features:
that
Token that
Feature activation+0.019
Top resid features:
opponents
Token opponents
Feature activation+1.405
Top resid features:
can
Token can
Feature activation+0.274
Top resid features:
not
Token not
Feature activation+0.237
Top resid features:
touch
Token touch
Feature activation+0.050
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.012
Top resid features:
all
Token all
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
institutions
Token institutions
Feature activation+0.344
Top resid features:
that
Token that
Feature activation+0.312
Top resid features:
were
Token were
Feature activation+0.473
Top resid features:
supposedly
Token supposedly
Feature activation+0.171
Top resid features:
there
Token there
Feature activation+0.153
Top resid features:
to
Token to
Feature activation+0.255
Top resid features:
protect
Token protect
Feature activation+0.126
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
against
Token against
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
wall
Token wall
Feature activation-0.004
Top resid features:
and
Token and
Feature activation+0.047
Top resid features:
proceeded
Token proceeded
Feature activation+0.541
Top resid features:
to
Token to
Feature activation+0.709
Top resid features:
beat
Token beat
Feature activation+0.112
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
crap
Token crap
Feature activation+0.001
Top resid features:
out
Token out
Feature activation+0.011
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
length
Token length
Feature activation-0.020
Top resid features:
.
Token.
Feature activation-0.024
Top resid features:
However
Token However
Feature activation-0.019
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
his
Token his
Feature activation-0.030
Top resid features:
superiors
Token superiors
Feature activation+1.341
Top resid features:
recognize
Token recognize
Feature activation+0.526
Top resid features:
his
Token his
Feature activation-0.067
Top resid features:
undeniable
Token undeniable
Feature activation+0.000
Top resid features:
skill
Token skill
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
competed
Token competed
Feature activation+0.001
Top resid features:
nude
Token nude
Feature activation-0.002
Top resid features:
;
Token;
Feature activation+0.104
Top resid features:
when
Token when
Feature activation+0.089
Top resid features:
Japan
Token Japan
Feature activation+0.084
Top resid features:
allowed
Token allowed
Feature activation+1.477
Top resid features:
female
Token female
Feature activation-0.012
Top resid features:
sum
Token sum
Feature activation-0.000
Top resid features:
o
Tokeno
Feature activation+0.001
Top resid features:
wrestlers
Token wrestlers
Feature activation-0.025
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
importantly
Token importantly
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
how
Token how
Feature activation+0.024
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
media
Token media
Feature activation+0.476
Top resid features:
is
Token is
Feature activation+0.602
Top resid features:
completely
Token completely
Feature activation+0.180
Top resid features:
turning
Token turning
Feature activation+0.159
Top resid features:
a
Token a
Feature activation+0.014
Top resid features:
blind
Token blind
Feature activation+0.018
Top resid features:
eye
Token eye
Feature activation+0.116
Top resid features:
development
Token development
Feature activation-0.000
Top resid features:
camp
Token camp
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
"
Token"
Feature activation+0.016
Top resid features:
They
TokenThey
Feature activation+1.072
Top resid features:
liked
Token liked
Feature activation+0.439
Top resid features:
what
Token what
Feature activation+0.010
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
saw
Token saw
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
love
Token love
Feature activation-0.006
Top resid features:
Boston
Token Boston
Feature activation+0.062
Top resid features:
and
Token and
Feature activation+0.022
Top resid features:
I
Token I
Feature activation-0.089
Top resid features:
know
Token know
Feature activation+0.023
Top resid features:
they
Token they
Feature activation+1.422
Top resid features:
love
Token love
Feature activation+0.159
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
We
Token We
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
I
Token I
Feature activation-0.003
Top resid features:
was
Token was
Feature activation-0.009
Top resid features:
weird
Token weird
Feature activation-0.003
Top resid features:
ly
Tokenly
Feature activation-0.000
Top resid features:
excited
Token excited
Feature activation-0.010
Top resid features:
someone
Token someone
Feature activation+1.067
Top resid features:
actually
Token actually
Feature activation+0.156
Top resid features:
wanted
Token wanted
Feature activation+0.106
Top resid features:
to
Token to
Feature activation+0.224
Top resid features:
sit
Token sit
Feature activation-0.025
Top resid features:
next
Token next
Feature activation+0.016
Top resid features:
US
Token US
Feature activation+0.362
Top resid features:
won
Token won
Feature activation+0.181
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.007
Top resid features:
t
Tokent
Feature activation+0.330
Top resid features:
support
Token support
Feature activation+0.703
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
going
Token going
Feature activation+0.043
Top resid features:
to
Token to
Feature activation+0.091
Top resid features:
need
Token need
Feature activation+0.057
Top resid features:
me
Token me
Feature activation-0.058
Top resid features:
and
Token and
Feature activation-0.032
Top resid features:
they
Token they
Feature activation+0.293
Top resid features:
're
Token're
Feature activation+0.141
Top resid features:
going
Token going
Feature activation+0.081
Top resid features:
to
Token to
Feature activation+0.157
Top resid features:
be
Token be
Feature activation+0.146
Top resid features:
leaning
Token leaning
Feature activation+0.223
Top resid features:
table
Token table
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
But
Token But
Feature activation+0.009
Top resid features:
nobody
Token nobody
Feature activation+0.341
Top resid features:
ever
Token ever
Feature activation+0.223
Top resid features:
asked
Token asked
Feature activation+0.859
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.022
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
length
Token length
Feature activation-0.008
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
However
Token However
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
his
Token his
Feature activation-0.013
Top resid features:
superiors
Token superiors
Feature activation+0.972
Top resid features:
recognize
Token recognize
Feature activation+0.207
Top resid features:
his
Token his
Feature activation-0.017
Top resid features:
undeniable
Token undeniable
Feature activation-0.015
Top resid features:
skill
Token skill
Feature activation-0.124
Top resid features:
and
Token and
Feature activation-0.032
Top resid features:
To
Token To
Feature activation+0.001
Top resid features:
Grow
Token Grow
Feature activation+0.001
Top resid features:
Up
Token Up
Feature activation+0.002
Top resid features:
cassette
Token cassette
Feature activation+0.106
Top resid features:
were
Token were
Feature activation+0.335
Top resid features:
waiting
Token waiting
Feature activation+0.840
Top resid features:
for
Token for
Feature activation+0.132
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
'
Token'
Feature activation+0.022
Top resid features:
They
TokenThey
Feature activation+0.533
Top resid features:
threw
Token threw
Feature activation+1.069
Top resid features:
meat
Token meat
Feature activation-0.038
Top resid features:
at
Token at
Feature activation+0.007
Top resid features:
him
Token him
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:
friends
Token friends
Feature activation+0.001
Top resid features:
list
Token list
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.020
Top resid features:
Facebook
Token Facebook
Feature activation+0.326
Top resid features:
reb
Token reb
Feature activation+0.379
Top resid features:
uffed
Tokenuffed
Feature activation+0.802
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
return
Token return
Feature activation+0.000
Top resid features:
emails
Token emails
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.001
Top resid features:
."
Token."
Feature activation+0.042
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
An
TokenAn
Feature activation+0.075
Top resid features:
officer
Token officer
Feature activation+0.533
Top resid features:
then
Token then
Feature activation+0.337
Top resid features:
jumped
Token jumped
Feature activation+0.293
Top resid features:
on
Token on
Feature activation+0.051
Top resid features:
top
Token top
Feature activation+0.054
Top resid features:
of
Token of
Feature activation+0.023
Top resid features:
his
Token his
Feature activation-0.081
Top resid features:
commanders
Token commanders
Feature activation+0.326
Top resid features:
âĢ
Token âĢ
Feature activation+0.029
Top resid features:
ľ
Tokenľ
Feature activation+0.011
Top resid features:
se
Tokense
Feature activation+0.031
Top resid features:
emed
Tokenemed
Feature activation+0.336
Top resid features:
pumped
Token pumped
Feature activation+0.212
Top resid features:
up
Token up
Feature activation+0.312
Top resid features:
about
Token about
Feature activation+0.178
Top resid features:
killing
Token killing
Feature activation+0.000
Top resid features:
Arabs
Token Arabs
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
she
Token she
Feature activation+0.024
Top resid features:
said
Token said
Feature activation+0.020
Top resid features:
that
Token that
Feature activation+0.022
Top resid features:
her
Token her
Feature activation-0.027
Top resid features:
teacher
Token teacher
Feature activation+0.655
Top resid features:
had
Token had
Feature activation+0.361
Top resid features:
asked
Token asked
Feature activation+0.380
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
whole
Token whole
Feature activation+0.000
Top resid features:
class
Token class
Feature activation+0.000
Top resid features:
many
Token many
Feature activation-0.012
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
for
Token for
Feature activation+0.042
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
world
Token world
Feature activation+0.235
Top resid features:
think
Token think
Feature activation+0.720
Top resid features:
es
Tokenes
Feature activation+0.076
Top resid features:
that
Token that
Feature activation+0.306
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
very
Token very
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.05

Head 2: 0.02

Head 3: 0.42

Head 4: 0.04

Head 5: 0.09

Head 6: 0.05

Head 7: 0.02

Head 8: 0.11

Head 9: 0.10

Head 10: 0.02

Head 11: 0.02

Positive logits

him2.64

theirs2.15

''.2.12

.''1.92

%%1.91

thee1.90

Vaugh1.90

Whedon1.90

Solution1.85

002000001.85

anza1.85

\.1.84

Simone1.83

him1.79

addon1.78

Runner1.77

Herrera1.77

arthed1.75

yours1.75

bish1.74

Negative logits

pione-2.46

subur-2.45

覚醒-2.36

arcity-2.25

-2.22

-2.22

rawdownload-2.22

earthqu-2.22

-2.21

-2.21

-2.21

-2.20

oreAndOnline-2.20

-2.20

-2.19

-2.19

-2.19

quickShip-2.19

-2.19

-2.19

INTERVAL 1.507 - 1.675
CONTAINS 0.000%

away
Token away
Feature activation+0.000
that
Token that
Feature activation+0.000
opponents
Token opponents
Feature activation+0.000
can
Token can
Feature activation+0.164
not
Token not
Feature activation+0.627
touch
Token touch
Feature activation+1.675
him
Token him
Feature activation+0.677
with
Token with
Feature activation+0.000
strikes
Token strikes
Feature activation+0.000
.
Token.
Feature activation+0.000
Mas
Token Mas
Feature activation+0.000
that
Token that
Feature activation+0.315
were
Token were
Feature activation+0.538
supposedly
Token supposedly
Feature activation+0.235
there
Token there
Feature activation+0.892
to
Token to
Feature activation+0.638
protect
Token protect
Feature activation+1.558
her
Token her
Feature activation+0.853
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

INTERVAL 1.340 - 1.507
CONTAINS 0.000%

allowed
Token allowed
Feature activation+0.298
female
Token female
Feature activation+0.000
sum
Token sum
Feature activation+0.000
o
Tokeno
Feature activation+0.000
wrestlers
Token wrestlers
Feature activation+0.000
,
Token,
Feature activation+1.367
they
Token they
Feature activation+0.246
competed
Token competed
Feature activation+0.000
nude
Token nude
Feature activation+0.000
,
Token,
Feature activation+0.000
without
Token without
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
superiors
Token superiors
Feature activation+0.000
recognize
Token recognize
Feature activation+0.370
his
Token his
Feature activation+1.432
undeniable
Token undeniable
Feature activation+0.000
skill
Token skill
Feature activation+0.000
and
Token and
Feature activation+0.000
tolerate
Token tolerate
Feature activation+0.363
his
Token his
Feature activation+1.169
to
Token to
Feature activation+0.000
beat
Token beat
Feature activation+0.514
the
Token the
Feature activation+0.626
crap
Token crap
Feature activation+0.000
out
Token out
Feature activation+0.588
of
Token of
Feature activation+1.473
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

INTERVAL 1.172 - 1.340
CONTAINS 0.001%

're
Token're
Feature activation+0.132
going
Token going
Feature activation+0.121
to
Token to
Feature activation+0.268
be
Token be
Feature activation+0.424
leaning
Token leaning
Feature activation+0.053
on
Token on
Feature activation+1.200
me
Token me
Feature activation+0.115
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
actually
Token actually
Feature activation+0.000
wanted
Token wanted
Feature activation+0.611
to
Token to
Feature activation+0.257
sit
Token sit
Feature activation+0.476
next
Token next
Feature activation+0.366
to
Token to
Feature activation+1.231
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.183
my
Token my
Feature activation+0.000
walk
Token walk
Feature activation+0.000
man
Tokenman
Feature activation+0.000
US
Token US
Feature activation+0.000
won
Token won
Feature activation+0.001
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
support
Token support
Feature activation+1.230
him
Token him
Feature activation+0.242
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
They
TokenThey
Feature activation+0.000
liked
Token liked
Feature activation+0.663
what
Token what
Feature activation+1.268
they
Token they
Feature activation+0.638
saw
Token saw
Feature activation+0.293
,"
Token,"
Feature activation+0.432
Robinson
Token Robinson
Feature activation+0.000
said
Token said
Feature activation+0.000
completely
Token completely
Feature activation+0.278
turning
Token turning
Feature activation+0.485
a
Token a
Feature activation+0.540
blind
Token blind
Feature activation+0.000
eye
Token eye
Feature activation+0.841
to
Token to
Feature activation+1.276
what
Token what
Feature activation+0.822
they
Token they
Feature activation+0.220
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000

INTERVAL 1.005 - 1.172
CONTAINS 0.001%

officer
Token officer
Feature activation+0.000
then
Token then
Feature activation+0.000
jumped
Token jumped
Feature activation+0.000
on
Token on
Feature activation+0.833
top
Token top
Feature activation+0.406
of
Token of
Feature activation+1.082
them
Token them
Feature activation+0.110
.
Token.
Feature activation+0.580
"
Token "
Feature activation+0.000
And
TokenAnd
Feature activation+0.108
there
Token there
Feature activation+0.000
his
Token his
Feature activation+1.432
undeniable
Token undeniable
Feature activation+0.000
skill
Token skill
Feature activation+0.000
and
Token and
Feature activation+0.000
tolerate
Token tolerate
Feature activation+0.363
his
Token his
Feature activation+1.169
ego
Token ego
Feature activation+0.000
.
Token.
Feature activation+0.000
Springer
Token Springer
Feature activation+0.000
has
Token has
Feature activation+0.000
nicknamed
Token nicknamed
Feature activation+0.000
Grow
Token Grow
Feature activation+0.004
Up
Token Up
Feature activation+0.000
cassette
Token cassette
Feature activation+0.000
were
Token were
Feature activation+0.143
waiting
Token waiting
Feature activation+0.132
for
Token for
Feature activation+1.164
me
Token me
Feature activation+0.134
.
Token.
Feature activation+0.333
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Jack
TokenJack
Feature activation+0.000
friends
Token friends
Feature activation+0.000
list
Token list
Feature activation+0.000
.
Token.
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
reb
Token reb
Feature activation+0.000
uffed
Tokenuffed
Feature activation+1.114
him
Token him
Feature activation+0.487
in
Token in
Feature activation+0.178
return
Token return
Feature activation+0.000
emails
Token emails
Feature activation+0.044
and
Token and
Feature activation+0.048
will
Token will
Feature activation+0.000
send
Token send
Feature activation+0.052
a
Token a
Feature activation+0.040
letter
Token letter
Feature activation+0.000
to
Token to
Feature activation+0.773
the
Token the
Feature activation+1.052
company
Token company
Feature activation+0.000
.[
Token.[
Feature activation+0.000
4
Token4
Feature activation+0.000
]
Token]
Feature activation+0.000
While
Token While
Feature activation+0.000

INTERVAL 0.837 - 1.005
CONTAINS 0.006%

point
Token point
Feature activation+0.000
they
Token they
Feature activation+0.000
're
Token're
Feature activation+0.002
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.030
need
Token need
Feature activation+0.965
me
Token me
Feature activation+0.000
and
Token and
Feature activation+0.063
they
Token they
Feature activation+0.351
're
Token're
Feature activation+0.132
going
Token going
Feature activation+0.121
to
Token to
Feature activation+0.000
secure
Token secure
Feature activation+0.000
the
Token the
Feature activation+0.000
facility
Token facility
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.874
as
Token as
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
anybody
Token anybody
Feature activation+0.000
stun
Token stun
Feature activation+0.000
gun
Token gun
Feature activation+0.000
,
Token,
Feature activation+0.000
T
Token T
Feature activation+0.000
asing
Tokenasing
Feature activation+0.000
the
Token the
Feature activation+0.858
Oklahoma
Token Oklahoma
Feature activation+0.000
man
Token man
Feature activation+0.000
.
Token.
Feature activation+0.000
Shelby
Token Shelby
Feature activation+0.000
fired
Token fired
Feature activation+0.000
neighbouring
Token neighbouring
Feature activation+0.000
Iraq
Token Iraq
Feature activation+0.000
"
Token "
Feature activation+0.000
to
Tokento
Feature activation+0.000
back
Token back
Feature activation+0.614
us
Token us
Feature activation+0.856
in
Token in
Feature activation+0.000
our
Token our
Feature activation+0.000
struggle
Token struggle
Feature activation+0.000
to
Token to
Feature activation+0.000
liberate
Token liberate
Feature activation+0.000
s
Tokens
Feature activation+0.272
requests
Token requests
Feature activation+0.223
for
Token for
Feature activation+0.000
help
Token help
Feature activation+0.000
even
Token even
Feature activation+0.300
though
Token though
Feature activation+0.848
he
Token he
Feature activation+0.054
was
Token was
Feature activation+0.000
vomiting
Token vomiting
Feature activation+0.000
and
Token and
Feature activation+0.000
unable
Token unable
Feature activation+0.000

INTERVAL 0.670 - 0.837
CONTAINS 0.012%

the
Token the
Feature activation+0.002
powers
Token powers
Feature activation+0.000
that
Token that
Feature activation+0.000
oppress
Token oppress
Feature activation+0.131
us
Token us
Feature activation+0.158
expect
Token expect
Feature activation+0.790
us
Token us
Feature activation+0.455
to
Token to
Feature activation+0.285
do
Token do
Feature activation+0.056
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
partner
Token partner
Feature activation+0.000
that
Token that
Feature activation+0.000
supported
Token supported
Feature activation+0.544
my
Token my
Feature activation+0.706
vision
Token vision
Feature activation+0.000
and
Token and
Feature activation+0.000
helped
Token helped
Feature activation+0.528
me
Token me
Feature activation+0.417
bring
Token bring
Feature activation+0.000
French
Token French
Feature activation+0.069
had
Token had
Feature activation+0.153
closed
Token closed
Feature activation+0.113
their
Token their
Feature activation+0.000
curtains
Token curtains
Feature activation+0.331
to
Token to
Feature activation+0.721
disguise
Token disguise
Feature activation+0.285
the
Token the
Feature activation+0.072
city
Token city
Feature activation+0.000
),
Token),
Feature activation+0.000
and
Token and
Feature activation+0.000
parents
Token parents
Feature activation+0.000
who
Token who
Feature activation+0.104
tried
Token tried
Feature activation+0.051
to
Token to
Feature activation+0.110
keep
Token keep
Feature activation+0.826
their
Token their
Feature activation+0.777
custody
Token custody
Feature activation+0.309
battle
Token battle
Feature activation+0.029
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.111
the
Token the
Feature activation+0.000
signals
Token signals
Feature activation+0.000
.
Token.
Feature activation+0.000
Imagine
Token Imagine
Feature activation+0.000
if
Token if
Feature activation+0.000
somebody
Token somebody
Feature activation+0.137
grabbed
Token grabbed
Feature activation+0.720
you
Token you
Feature activation+0.000
and
Token and
Feature activation+0.407
put
Token put
Feature activation+0.096
a
Token a
Feature activation+0.000
blind
Token blind
Feature activation+0.000

INTERVAL 0.502 - 0.670
CONTAINS 0.030%

v
Tokenv
Feature activation+0.000
idal
Tokenidal
Feature activation+0.000
was
Token was
Feature activation+0.063
able
Token able
Feature activation+0.004
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.653
him
Token him
Feature activation+0.000
problems
Token problems
Feature activation+0.000
by
Token by
Feature activation+0.000
scoring
Token scoring
Feature activation+0.021
with
Token with
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
won
Token won
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.398
share
Token share
Feature activation+0.633
them
Token them
Feature activation+0.349
,
Token,
Feature activation+0.545
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
have
Token have
Feature activation+0.836
any
Token any
Feature activation+0.791
good
Token good
Feature activation+0.614
Nintendo
Token Nintendo
Feature activation+0.175
games
Token games
Feature activation+0.628
in
Token in
Feature activation+0.579
stock
Token stock
Feature activation+0.686
that
Token that
Feature activation+0.619
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.131
I
Token I
Feature activation+0.000
,
Token,
Feature activation+0.000
prompting
Token prompting
Feature activation+0.000
the
Token the
Feature activation+0.000
EU
Token EU
Feature activation+0.000
and
Token and
Feature activation+0.401
the
Token the
Feature activation+0.610
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
to
Token to
Feature activation+0.000
impose
Token impose
Feature activation+0.000
a
Token a
Feature activation+0.000
end
Token end
Feature activation+0.000
up
Token up
Feature activation+0.000
facing
Token facing
Feature activation+0.000
opponents
Token opponents
Feature activation+0.000
who
Token who
Feature activation+0.000
know
Token know
Feature activation+0.590
all
Token all
Feature activation+0.618
your
Token your
Feature activation+0.669
tricks
Token tricks
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000

INTERVAL 0.335 - 0.502
CONTAINS 0.077%

also
Token also
Feature activation+0.000
sure
Token sure
Feature activation+0.000
that
Token that
Feature activation+0.000
prospects
Token prospects
Feature activation+0.000
know
Token know
Feature activation+0.081
where
Token where
Feature activation+0.377
the
Token the
Feature activation+0.363
best
Token best
Feature activation+0.170
opportunities
Token opportunities
Feature activation+0.179
are
Token are
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
community
Token community
Feature activation+0.000
member
Token member
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
benefit
Token benefit
Feature activation+0.347
from
Token from
Feature activation+0.443
your
Token your
Feature activation+0.152
unique
Token unique
Feature activation+0.000
perspective
Token perspective
Feature activation+0.000
&
Token &
Feature activation+0.000
-
Token-
Feature activation+0.000
run
Tokenrun
Feature activation+0.000
news
Token news
Feature activation+0.000
agency
Token agency
Feature activation+0.000
claims
Token claims
Feature activation+0.225
the
Token the
Feature activation+0.409
man
Token man
Feature activation+0.000
who
Token who
Feature activation+0.000
stabbed
Token stabbed
Feature activation+0.000
and
Token and
Feature activation+0.000
wounded
Token wounded
Feature activation+0.000
the
Token the
Feature activation+0.000
spot
Token spot
Feature activation+0.000
against
Token against
Feature activation+0.000
Bayern
Token Bayern
Feature activation+0.000
Munich
Token Munich
Feature activation+0.000
at
Token at
Feature activation+0.377
Wembley
Token Wembley
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
2
Token 2
Feature activation+0.000
-
Token-
Feature activation+0.000
Uber
Token Uber
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
They
TokenThey
Feature activation+0.000
blame
Token blame
Feature activation+0.387
everything
Token everything
Feature activation+0.087
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
life
Token life
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 0.167 - 0.335
CONTAINS 0.214%

appointment
Token appointment
Feature activation+0.181
because
Token because
Feature activation+0.196
they
Token they
Feature activation+0.223
'll
Token'll
Feature activation+0.429
need
Token need
Feature activation+0.583
to
Token to
Feature activation+0.261
get
Token get
Feature activation+0.479
on
Token on
Feature activation+0.230
some
Token some
Feature activation+0.030
special
Token special
Feature activation+0.000
medications
Token medications
Feature activation+0.373
aro
Tokenaro
Feature activation+0.000
,
Token,
Feature activation+0.000
whose
Token whose
Feature activation+0.000
Howard
Token Howard
Feature activation+0.000
County
Token County
Feature activation+0.000
roots
Token roots
Feature activation+0.255
(
Token (
Feature activation+0.000
River
TokenRiver
Feature activation+0.000
Hill
Token Hill
Feature activation+0.000
)
Token)
Feature activation+0.000
have
Token have
Feature activation+0.059
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
swept
Token swept
Feature activation+0.000
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
rug
Token rug
Feature activation+0.276
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
nearby
Token nearby
Feature activation+0.000
For
Token For
Feature activation+0.000
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
interested
Token interested
Feature activation+0.087
in
Token in
Feature activation+0.273
me
Token me
Feature activation+0.000
is
Token is
Feature activation+0.000
what
Token what
Feature activation+0.000
you
Token you
Feature activation+0.000
play
Token play
Feature activation+0.000
G
Token G
Feature activation+0.000
amed
Tokenamed
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
also
Token also
Feature activation+0.000
received
Token received
Feature activation+0.372
a
Token a
Feature activation+0.192
bank
Token bank
Feature activation+0.000
loan
Token loan
Feature activation+0.567
with
Token with
Feature activation+0.815
what
Token what
Feature activation+0.226
Duncan
Token Duncan
Feature activation+0.000

INTERVAL 0.000 - 0.167
CONTAINS 99.659%

Lady
Token Lady
Feature activation+0.000
Susan
Token Susan
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
jumped
Token jumped
Feature activation+0.000
in
Token in
Feature activation+0.000
without
Token without
Feature activation+0.000
hesitation
Token hesitation
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
didn
Token didn
Feature activation+0.000
Spain
Token Spain
Feature activation+0.000
's
Token's
Feature activation+0.000
northwest
Token northwest
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
F
Token F
Feature activation+0.000
CO
TokenCO
Feature activation+0.000
has
Token has
Feature activation+0.000
advised
Token advised
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
Intel
Token Intel
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Dell
Token Dell
Feature activation+0.000
Computer
Token Computer
Feature activation+0.000
;
Token;
Feature activation+0.000
the
Token the
Feature activation+0.000
1990
Token 1990
Feature activation+0.000
s
Tokens
Feature activation+0.000
from
Token from
Feature activation+0.000
become
Token become
Feature activation+0.000
emperor
Token emperor
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Image
TokenImage
Feature activation+0.000
copyright
Token copyright
Feature activation+0.000
AFP
Token AFP
Feature activation+0.000
/
Token/
Feature activation+0.000
Getty
TokenGetty
Feature activation+0.000
Images
Token Images
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
It
Token It
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
cause
Token cause
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
support
Token support
Feature activation+0.000
on
Token on
Feature activation+0.000
its
Token its
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 H7.3: (feature 36450)

TOP ACTIVATIONS
MAX = 2.395

immigrants
Token immigrants
Feature activation+0.000
arrived
Token arrived
Feature activation+0.263
in
Token in
Feature activation+0.665
their
Token their
Feature activation+0.960
millions
Token millions
Feature activation+1.112
and
Token and
Feature activation+2.395
the
Token the
Feature activation+1.202
rich
Token rich
Feature activation+0.224
coined
Token coined
Feature activation+0.000
it
Token it
Feature activation+0.000
in
Token in
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
Some
TokenSome
Feature activation+0.000
body
Tokenbody
Feature activation+0.000
showed
Token showed
Feature activation+0.000
up
Token up
Feature activation+0.668
at
Token at
Feature activation+1.784
the
Token the
Feature activation+1.421
Penguins
Token Penguins
Feature activation+0.000
'
Token'
Feature activation+0.013
parade
Token parade
Feature activation+0.039
with
Token with
Feature activation+0.653
folks
Token folks
Feature activation+0.000
now
Token now
Feature activation+0.000
can
Token can
Feature activation+0.000
show
Token show
Feature activation+0.000
up
Token up
Feature activation+0.373
to
Token to
Feature activation+1.627
the
Token the
Feature activation+1.123
verbal
Token verbal
Feature activation+0.060
brawl
Token brawl
Feature activation+0.633
with
Token with
Feature activation+0.884
facts
Token facts
Feature activation+0.168
to
Token to
Feature activation+0.000
arrive
Token arrive
Feature activation+0.269
at
Token at
Feature activation+0.630
the
Token the
Feature activation+0.904
location
Token location
Feature activation+0.221
and
Token and
Feature activation+1.560
encounter
Token encounter
Feature activation+1.018
a
Token a
Feature activation+0.151
well
Token well
Feature activation+0.000
-
Token-
Feature activation+0.000
planned
Tokenplanned
Feature activation+0.000
coming
Token coming
Feature activation+0.000
in
Token in
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
middle
Token middle
Feature activation+0.000
to
Token to
Feature activation+1.478
intercept
Token intercept
Feature activation+0.284
a
Token a
Feature activation+0.000
pass
Token pass
Feature activation+0.000
.
Token.
Feature activation+0.000
Petty
Token Petty
Feature activation+0.000
I
TokenI
Feature activation+0.000
would
Token would
Feature activation+0.000
love
Token love
Feature activation+0.000
to
Token to
Feature activation+0.000
come
Token come
Feature activation+0.036
and
Token and
Feature activation+1.456
play
Token play
Feature activation+0.550
in
Token in
Feature activation+0.281
his
Token his
Feature activation+0.000
offense
Token offense
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
Dennis
Token Dennis
Feature activation+0.000
Mickey
Token Mickey
Feature activation+0.000
came
Token came
Feature activation+0.000
over
Token over
Feature activation+0.270
and
Token and
Feature activation+1.455
Ed
Token Ed
Feature activation+0.000
Arm
Token Arm
Feature activation+0.000
br
Tokenbr
Feature activation+0.000
ister
Tokenister
Feature activation+0.264
.
Token.
Feature activation+0.000
Mo
Token Mo
Feature activation+0.000
a
Tokena
Feature activation+0.000
will
Token will
Feature activation+0.000
come
Token come
Feature activation+0.000
in
Token in
Feature activation+0.131
to
Token to
Feature activation+1.451
start
Token start
Feature activation+0.979
at
Token at
Feature activation+0.107
prop
Token prop
Feature activation+0.000
with
Token with
Feature activation+0.427
Dylan
Token Dylan
Feature activation+0.000
Ramsey
Token Ramsey
Feature activation+0.000
could
Token could
Feature activation+0.000
come
Token come
Feature activation+0.000
in
Token in
Feature activation+0.303
and
Token and
Feature activation+0.914
be
Token be
Feature activation+1.439
the
Token the
Feature activation+0.431
best
Token best
Feature activation+0.050
player
Token player
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
distribution
Token distribution
Feature activation+0.000
,
Token,
Feature activation+0.000
arrived
Token arrived
Feature activation+0.000
at
Token at
Feature activation+0.098
Oslo
Token Oslo
Feature activation+0.000
and
Token and
Feature activation+1.433
changed
Token changed
Feature activation+0.987
the
Token the
Feature activation+0.927
life
Token life
Feature activation+0.017
of
Token of
Feature activation+0.129
Ash
Token Ash
Feature activation+0.000
Some
TokenSome
Feature activation+0.000
body
Tokenbody
Feature activation+0.000
showed
Token showed
Feature activation+0.000
up
Token up
Feature activation+0.668
at
Token at
Feature activation+1.784
the
Token the
Feature activation+1.421
Penguins
Token Penguins
Feature activation+0.000
'
Token'
Feature activation+0.013
parade
Token parade
Feature activation+0.039
with
Token with
Feature activation+0.653
copy
Token copy
Feature activation+0.065
had
Token had
Feature activation+0.000
stopped
Token stopped
Feature activation+0.000
stepped
Token stepped
Feature activation+0.000
in
Token in
Feature activation+0.265
to
Token to
Feature activation+0.824
help
Token help
Feature activation+1.360
.
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
what
Token what
Feature activation+0.000
the
Token the
Feature activation+0.000
two
Token two
Feature activation+0.000
players
Token players
Feature activation+0.000
bring
Token bring
Feature activation+0.000
to
Token to
Feature activation+1.330
the
Token the
Feature activation+0.355
game
Token game
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.428
Baker
Token Baker
Feature activation+0.000
Plant
Token Plant
Feature activation+0.000
ation
Tokenation
Feature activation+0.000
to
Token to
Feature activation+1.054
find
Token find
Feature activation+1.324
his
Token his
Feature activation+0.612
wife
Token wife
Feature activation+0.000
long
Token long
Feature activation+0.000
thought
Token thought
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
people
Token people
Feature activation+0.000
come
Token come
Feature activation+0.000
in
Token in
Feature activation+0.048
and
Token and
Feature activation+1.313
buy
Token buy
Feature activation+0.731
,
Token,
Feature activation+0.271
say
Token say
Feature activation+0.131
,
Token,
Feature activation+0.035
two
Token two
Feature activation+0.361
when
Token when
Feature activation+0.000
I
Token I
Feature activation+0.000
came
Token came
Feature activation+0.000
back
Token back
Feature activation+0.138
,
Token,
Feature activation+1.258
I
Token I
Feature activation+1.292
was
Token was
Feature activation+0.462
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
I
Token I
Feature activation+0.000
,
Token,
Feature activation+0.593
two
Token two
Feature activation+0.183
hours
Token hours
Feature activation+0.628
late
Token late
Feature activation+0.382
,
Token,
Feature activation+0.833
they
Token they
Feature activation+1.270
stayed
Token stayed
Feature activation+0.000
downstairs
Token downstairs
Feature activation+0.000
until
Token until
Feature activation+0.023
the
Token the
Feature activation+0.308
people
Token people
Feature activation+0.099
em
Tokenem
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
ogre
Token ogre
Feature activation+0.000
shows
Token shows
Feature activation+0.000
up
Token up
Feature activation+0.067
to
Token to
Feature activation+1.261
rescue
Token rescue
Feature activation+0.975
a
Token a
Feature activation+0.562
fe
Token fe
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
y
Tokeny
Feature activation+0.158
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
I
Token I
Feature activation+0.000
came
Token came
Feature activation+0.000
back
Token back
Feature activation+0.138
,
Token,
Feature activation+1.258
I
Token I
Feature activation+1.292
was
Token was
Feature activation+0.462
not
Token not
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
grown
Token grown
Feature activation+0.000
up
Tokenup
Feature activation+0.000
who
Token who
Feature activation+0.000
would
Token would
Feature activation+0.000
come
Token come
Feature activation+0.000
get
Token get
Feature activation+1.253
him
Token him
Feature activation+1.039
out
Token out
Feature activation+0.357
of
Token of
Feature activation+0.684
the
Token the
Feature activation+0.257
tub
Token tub
Feature activation+0.000

Top DFA by src position
MAX = 2.003

country
Token country
Feature activation-0.002
Top resid features:
bo
Token bo
Feature activation+0.002
Top resid features:
omed
Tokenomed
Feature activation+0.169
Top resid features:
,
Token,
Feature activation+0.053
Top resid features:
immigrants
Token immigrants
Feature activation+0.111
Top resid features:
arrived
Token arrived
Feature activation+2.003
Top resid features:
in
Token in
Feature activation+0.390
Top resid features:
their
Token their
Feature activation+0.044
Top resid features:
millions
Token millions
Feature activation+0.091
Top resid features:
and
Token and
Feature activation+0.050
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
fan
Token fan
Feature activation+0.020
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.047
Top resid features:
Some
TokenSome
Feature activation-0.007
Top resid features:
body
Tokenbody
Feature activation+0.026
Top resid features:
showed
Token showed
Feature activation+0.063
Top resid features:
up
Token up
Feature activation+1.849
Top resid features:
at
Token at
Feature activation+0.260
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Penguins
Token Penguins
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
parade
Token parade
Feature activation+0.000
Top resid features:
12
Token12
Feature activation-0.010
Top resid features:
folks
Token folks
Feature activation-0.001
Top resid features:
now
Token now
Feature activation+0.034
Top resid features:
can
Token can
Feature activation+0.006
Top resid features:
show
Token show
Feature activation+0.023
Top resid features:
up
Token up
Feature activation+1.937
Top resid features:
to
Token to
Feature activation+0.158
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
verbal
Token verbal
Feature activation+0.000
Top resid features:
brawl
Token brawl
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
ab
Tokenab
Feature activation+0.002
Top resid features:
ari
Tokenari
Feature activation+0.003
Top resid features:
was
Token was
Feature activation-0.006
Top resid features:
expected
Token expected
Feature activation-0.022
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
arrive
Token arrive
Feature activation+1.627
Top resid features:
at
Token at
Feature activation+0.298
Top resid features:
the
Token the
Feature activation+0.096
Top resid features:
location
Token location
Feature activation-0.019
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
encounter
Token encounter
Feature activation+0.000
Top resid features:
there
Token there
Feature activation-0.007
Top resid features:
is
Token is
Feature activation-0.016
Top resid features:
middle
Token middle
Feature activation-0.019
Top resid features:
linebacker
Token linebacker
Feature activation-0.017
Top resid features:
coming
Token coming
Feature activation+0.409
Top resid features:
in
Token in
Feature activation+1.181
Top resid features:
from
Token from
Feature activation+0.428
Top resid features:
the
Token the
Feature activation+0.038
Top resid features:
middle
Token middle
Feature activation-0.007
Top resid features:
to
Token to
Feature activation+0.037
Top resid features:
intercept
Token intercept
Feature activation+0.000
Top resid features:
"
Token "
Feature activation-0.009
Top resid features:
I
TokenI
Feature activation-0.026
Top resid features:
would
Token would
Feature activation-0.014
Top resid features:
love
Token love
Feature activation-0.026
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
come
Token come
Feature activation+1.663
Top resid features:
and
Token and
Feature activation+0.423
Top resid features:
play
Token play
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
offense
Token offense
Feature activation+0.000
Top resid features:
Bill
Token Bill
Feature activation+0.005
Top resid features:
ingham
Tokeningham
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Dennis
Token Dennis
Feature activation-0.005
Top resid features:
Mickey
Token Mickey
Feature activation+0.019
Top resid features:
came
Token came
Feature activation+1.031
Top resid features:
over
Token over
Feature activation+0.645
Top resid features:
and
Token and
Feature activation+0.189
Top resid features:
Ed
Token Ed
Feature activation+0.000
Top resid features:
Arm
Token Arm
Feature activation+0.000
Top resid features:
br
Tokenbr
Feature activation+0.000
Top resid features:
Sam
Token Sam
Feature activation+0.002
Top resid features:
Mo
Token Mo
Feature activation+0.005
Top resid features:
a
Tokena
Feature activation+0.003
Top resid features:
will
Token will
Feature activation+0.068
Top resid features:
come
Token come
Feature activation+0.523
Top resid features:
in
Token in
Feature activation+1.106
Top resid features:
to
Token to
Feature activation+0.231
Top resid features:
start
Token start
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
prop
Token prop
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.013
Top resid features:
Jal
Token Jal
Feature activation+0.046
Top resid features:
en
Tokenen
Feature activation-0.004
Top resid features:
Ramsey
Token Ramsey
Feature activation+0.028
Top resid features:
could
Token could
Feature activation+0.015
Top resid features:
come
Token come
Feature activation+0.774
Top resid features:
in
Token in
Feature activation+0.773
Top resid features:
and
Token and
Feature activation+0.285
Top resid features:
be
Token be
Feature activation+0.063
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
best
Token best
Feature activation+0.000
Top resid features:
irk
Tokenirk
Feature activation-0.003
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
cinema
Token cinema
Feature activation-0.002
Top resid features:
distribution
Token distribution
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
arrived
Token arrived
Feature activation+1.061
Top resid features:
at
Token at
Feature activation+0.466
Top resid features:
Oslo
Token Oslo
Feature activation+0.114
Top resid features:
and
Token and
Feature activation+0.223
Top resid features:
changed
Token changed
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
fan
Token fan
Feature activation+0.015
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.036
Top resid features:
Some
TokenSome
Feature activation-0.021
Top resid features:
body
Tokenbody
Feature activation+0.027
Top resid features:
showed
Token showed
Feature activation+0.039
Top resid features:
up
Token up
Feature activation+1.321
Top resid features:
at
Token at
Feature activation+0.371
Top resid features:
the
Token the
Feature activation+0.097
Top resid features:
Penguins
Token Penguins
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
parade
Token parade
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.047
Top resid features:
who
Token who
Feature activation+0.010
Top resid features:
had
Token had
Feature activation+0.003
Top resid features:
stopped
Token stopped
Feature activation+0.017
Top resid features:
stepped
Token stepped
Feature activation+0.552
Top resid features:
in
Token in
Feature activation+0.754
Top resid features:
to
Token to
Feature activation+0.553
Top resid features:
help
Token help
Feature activation+0.020
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:
about
Token about
Feature activation-0.009
Top resid features:
what
Token what
Feature activation+0.006
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
two
Token two
Feature activation+0.003
Top resid features:
players
Token players
Feature activation-0.047
Top resid features:
bring
Token bring
Feature activation+1.857
Top resid features:
to
Token to
Feature activation+0.084
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
game
Token game
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
tit
Token tit
Feature activation-0.006
Top resid features:
ular
Tokenular
Feature activation+0.005
Top resid features:
character
Token character
Feature activation+0.005
Top resid features:
Ethan
Token Ethan
Feature activation+0.030
Top resid features:
coming
Token coming
Feature activation+0.588
Top resid features:
to
Token to
Feature activation+0.835
Top resid features:
the
Token the
Feature activation+0.265
Top resid features:
Baker
Token Baker
Feature activation+0.014
Top resid features:
Plant
Token Plant
Feature activation-0.005
Top resid features:
ation
Tokenation
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.037
Top resid features:
unusual
Token unusual
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
have
Token have
Feature activation+0.022
Top resid features:
people
Token people
Feature activation+0.007
Top resid features:
come
Token come
Feature activation+0.667
Top resid features:
in
Token in
Feature activation+0.770
Top resid features:
and
Token and
Feature activation+0.366
Top resid features:
buy
Token buy
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
say
Token say
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
when
Token when
Feature activation-0.012
Top resid features:
I
Token I
Feature activation-0.003
Top resid features:
came
Token came
Feature activation+0.606
Top resid features:
back
Token back
Feature activation+1.130
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
I
Token I
Feature activation-0.028
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
When
TokenWhen
Feature activation-0.014
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
police
Token police
Feature activation+0.026
Top resid features:
showed
Token showed
Feature activation+0.442
Top resid features:
up
Token up
Feature activation+1.278
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
two
Token two
Feature activation+0.002
Top resid features:
hours
Token hours
Feature activation-0.002
Top resid features:
late
Token late
Feature activation+0.084
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
unse
Token unse
Feature activation+0.003
Top resid features:
em
Tokenem
Feature activation+0.008
Top resid features:
ly
Tokenly
Feature activation+0.003
Top resid features:
ogre
Token ogre
Feature activation+0.087
Top resid features:
shows
Token shows
Feature activation+0.196
Top resid features:
up
Token up
Feature activation+1.289
Top resid features:
to
Token to
Feature activation+0.125
Top resid features:
rescue
Token rescue
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
fe
Token fe
Feature activation+0.000
Top resid features:
ist
Tokenist
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
when
Token when
Feature activation-0.047
Top resid features:
I
Token I
Feature activation-0.029
Top resid features:
came
Token came
Feature activation+0.747
Top resid features:
back
Token back
Feature activation+1.003
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
some
Token some
Feature activation+0.017
Top resid features:
grown
Token grown
Feature activation+0.021
Top resid features:
up
Tokenup
Feature activation+0.022
Top resid features:
who
Token who
Feature activation+0.086
Top resid features:
would
Token would
Feature activation+0.087
Top resid features:
come
Token come
Feature activation+1.206
Top resid features:
get
Token get
Feature activation+0.513
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
out
Token out
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:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.06

Head 2: 0.01

Head 3: 0.42

Head 4: 0.04

Head 5: 0.11

Head 6: 0.03

Head 7: 0.02

Head 8: 0.16

Head 9: 0.07

Head 10: 0.02

Head 11: 0.02

Positive logits

mayhem1.99

pandemonium1.93

unsuspecting1.76

Mix1.72

));1.70

{{1.68

bounty1.68

DPS1.66

1.66

chaotic1.65

tit1.64

tac1.63

everybody1.62

puzzle1.62

us1.61

vacated1.60

devast1.60

Bounty1.59

puzzles1.59

Mash1.59

Negative logits

interstitial-2.60

eatures-2.18

ongyang-2.16

Downloadha-2.11

��-2.03

immune-1.96

reys-1.95

isexual-1.94

ributed-1.93

CTV-1.92

agos-1.92

ortality-1.83

eren-1.82

istle-1.82

raltar-1.82

lucent-1.82

ike-1.81

mberg-1.80

olesc-1.77

ymph-1.77

INTERVAL 2.155 - 2.395
CONTAINS 0.000%

immigrants
Token immigrants
Feature activation+0.000
arrived
Token arrived
Feature activation+0.263
in
Token in
Feature activation+0.665
their
Token their
Feature activation+0.960
millions
Token millions
Feature activation+1.112
and
Token and
Feature activation+2.395
the
Token the
Feature activation+1.202
rich
Token rich
Feature activation+0.224
coined
Token coined
Feature activation+0.000
it
Token it
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 1.916 - 2.155
CONTAINS 0.000%

INTERVAL 1.676 - 1.916
CONTAINS 0.000%

âĢĶ
TokenâĢĶ
Feature activation+0.000
Some
TokenSome
Feature activation+0.000
body
Tokenbody
Feature activation+0.000
showed
Token showed
Feature activation+0.000
up
Token up
Feature activation+0.668
at
Token at
Feature activation+1.784
the
Token the
Feature activation+1.421
Penguins
Token Penguins
Feature activation+0.000
'
Token'
Feature activation+0.013
parade
Token parade
Feature activation+0.039
with
Token with
Feature activation+0.653

INTERVAL 1.437 - 1.676
CONTAINS 0.001%

coming
Token coming
Feature activation+0.000
in
Token in
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
middle
Token middle
Feature activation+0.000
to
Token to
Feature activation+1.478
intercept
Token intercept
Feature activation+0.284
a
Token a
Feature activation+0.000
pass
Token pass
Feature activation+0.000
.
Token.
Feature activation+0.000
Petty
Token Petty
Feature activation+0.000
.
Token.
Feature activation+0.000
Dennis
Token Dennis
Feature activation+0.000
Mickey
Token Mickey
Feature activation+0.000
came
Token came
Feature activation+0.000
over
Token over
Feature activation+0.270
and
Token and
Feature activation+1.455
Ed
Token Ed
Feature activation+0.000
Arm
Token Arm
Feature activation+0.000
br
Tokenbr
Feature activation+0.000
ister
Tokenister
Feature activation+0.264
.
Token.
Feature activation+0.000
Mo
Token Mo
Feature activation+0.000
a
Tokena
Feature activation+0.000
will
Token will
Feature activation+0.000
come
Token come
Feature activation+0.000
in
Token in
Feature activation+0.131
to
Token to
Feature activation+1.451
start
Token start
Feature activation+0.979
at
Token at
Feature activation+0.107
prop
Token prop
Feature activation+0.000
with
Token with
Feature activation+0.427
Dylan
Token Dylan
Feature activation+0.000
folks
Token folks
Feature activation+0.000
now
Token now
Feature activation+0.000
can
Token can
Feature activation+0.000
show
Token show
Feature activation+0.000
up
Token up
Feature activation+0.373
to
Token to
Feature activation+1.627
the
Token the
Feature activation+1.123
verbal
Token verbal
Feature activation+0.060
brawl
Token brawl
Feature activation+0.633
with
Token with
Feature activation+0.884
facts
Token facts
Feature activation+0.168
to
Token to
Feature activation+0.000
arrive
Token arrive
Feature activation+0.269
at
Token at
Feature activation+0.630
the
Token the
Feature activation+0.904
location
Token location
Feature activation+0.221
and
Token and
Feature activation+1.560
encounter
Token encounter
Feature activation+1.018
a
Token a
Feature activation+0.151
well
Token well
Feature activation+0.000
-
Token-
Feature activation+0.000
planned
Tokenplanned
Feature activation+0.000

INTERVAL 1.197 - 1.437
CONTAINS 0.002%

there
Token there
Feature activation+0.334
with
Token with
Feature activation+0.402
his
Token his
Feature activation+0.000
two
Token two
Feature activation+0.000
monkeys
Token monkeys
Feature activation+0.000
,
Token,
Feature activation+1.233
the
Token the
Feature activation+0.710
two
Token two
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.042
have
Token have
Feature activation+0.000
says
Token says
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
comes
Token comes
Feature activation+0.000
into
Token into
Feature activation+0.236
his
Token his
Feature activation+0.158
head
Token head
Feature activation+1.235
at
Token at
Feature activation+0.280
the
Token the
Feature activation+0.202
moment
Token moment
Feature activation+0.630
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
em
Tokenem
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
ogre
Token ogre
Feature activation+0.000
shows
Token shows
Feature activation+0.000
up
Token up
Feature activation+0.067
to
Token to
Feature activation+1.261
rescue
Token rescue
Feature activation+0.975
a
Token a
Feature activation+0.562
fe
Token fe
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
y
Tokeny
Feature activation+0.158
warts
Tokenwarts
Feature activation+0.000
who
Token who
Feature activation+0.000
show
Token show
Feature activation+0.000
up
Token up
Feature activation+0.379
for
Token for
Feature activation+0.763
every
Token every
Feature activation+1.228
election
Token election
Feature activation+0.000
are
Token are
Feature activation+0.413
finding
Token finding
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
to
Token to
Feature activation+0.000
Some
TokenSome
Feature activation+0.000
body
Tokenbody
Feature activation+0.000
showed
Token showed
Feature activation+0.000
up
Token up
Feature activation+0.668
at
Token at
Feature activation+1.784
the
Token the
Feature activation+1.421
Penguins
Token Penguins
Feature activation+0.000
'
Token'
Feature activation+0.013
parade
Token parade
Feature activation+0.039
with
Token with
Feature activation+0.653
copy
Token copy
Feature activation+0.065

INTERVAL 0.958 - 1.197
CONTAINS 0.005%

the
Token the
Feature activation+0.000
legislature
Token legislature
Feature activation+0.000
grounds
Token grounds
Feature activation+0.000
Friday
Token Friday
Feature activation+0.122
,
Token,
Feature activation+0.733
she
Token she
Feature activation+1.077
was
Token was
Feature activation+0.297
all
Token all
Feature activation+0.000
smiles
Token smiles
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
around
Token around
Feature activation+0.000
Austin
Token Austin
Feature activation+0.000
stepped
Token stepped
Feature activation+0.000
forward
Token forward
Feature activation+0.000
to
Token to
Feature activation+0.492
help
Token help
Feature activation+1.081
him
Token him
Feature activation+0.460
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Copyright
TokenCopyright
Feature activation+0.000
and
Token and
Feature activation+0.260
three
Token three
Feature activation+0.000
people
Token people
Feature activation+0.000
got
Token got
Feature activation+0.000
out
Token out
Feature activation+0.000
and
Token and
Feature activation+0.999
said
Token said
Feature activation+0.000
they
Token they
Feature activation+0.117
could
Token could
Feature activation+0.135
push
Token push
Feature activation+0.000
the
Token the
Feature activation+0.000
think
Token think
Feature activation+0.000
she
Token she
Feature activation+0.000
should
Token should
Feature activation+0.000
come
Token come
Feature activation+0.065
out
Token out
Feature activation+0.183
and
Token and
Feature activation+1.055
continue
Token continue
Feature activation+1.236
her
Token her
Feature activation+0.600
dominance
Token dominance
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
dead
Token dead
Feature activation+0.000
come
Token come
Feature activation+0.282
back
Token back
Feature activation+0.450
to
Token to
Feature activation+0.733
life
Token life
Feature activation+1.144
with
Token with
Feature activation+0.948
a
Token a
Feature activation+1.053
craving
Token craving
Feature activation+0.455
to
Token to
Feature activation+0.533
gn
Token gn
Feature activation+0.000

INTERVAL 0.718 - 0.958
CONTAINS 0.012%

the
Token the
Feature activation+0.023
dark
Token dark
Feature activation+0.155
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
night
Token night
Feature activation+0.181
and
Token and
Feature activation+0.904
sc
Token sc
Feature activation+0.000
raw
Tokenraw
Feature activation+0.000
ls
Tokenls
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
ving
Tokenving
Feature activation+0.000
to
Token to
Feature activation+0.590
the
Token the
Feature activation+0.152
presidency
Token presidency
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.781
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.624
not
Token not
Feature activation+0.465
only
Token only
Feature activation+0.066
y
Tokeny
Feature activation+0.000
arrived
Token arrived
Feature activation+0.241
two
Token two
Feature activation+0.000
hours
Token hours
Feature activation+0.312
late
Token late
Feature activation+0.085
for
Token for
Feature activation+0.777
this
Token this
Feature activation+0.243
week
Token week
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
he
Token he
Feature activation+0.000
came
Token came
Feature activation+0.000
onboard
Token onboard
Feature activation+0.622
,
Token,
Feature activation+0.154
and
Token and
Feature activation+0.917
then
Token then
Feature activation+0.895
Matt
Token Matt
Feature activation+0.000
George
Token George
Feature activation+0.000
representing
Token representing
Feature activation+0.037
Surf
Token Surf
Feature activation+0.000
zone
Tokenzone
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
come
Token come
Feature activation+0.000
on
Token on
Feature activation+0.000
out
Token out
Feature activation+0.151
and
Token and
Feature activation+0.730
celebrate
Token celebrate
Feature activation+0.108
our
Token our
Feature activation+0.000
sport
Token sport
Feature activation+0.000
,
Token,
Feature activation+0.083
our
Token our
Feature activation+0.000

INTERVAL 0.479 - 0.718
CONTAINS 0.032%

,
Token,
Feature activation+0.000
Hegel
Token Hegel
Feature activation+0.000
also
Token also
Feature activation+0.000
looms
Token looms
Feature activation+0.000
large
Token large
Feature activation+0.000
in
Token in
Feature activation+0.632
Canada
Token Canada
Feature activation+0.000
.
Token.
Feature activation+0.000
Certain
Token Certain
Feature activation+0.000
broad
Token broad
Feature activation+0.000
Hegel
Token Hegel
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
Goodman
Token Goodman
Feature activation+0.000
arrived
Token arrived
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.495
scene
Token scene
Feature activation+0.045
to
Token to
Feature activation+0.634
do
Token do
Feature activation+0.105
a
Token a
Feature activation+0.000
special
Token special
Feature activation+0.000
the
Token the
Feature activation+0.000
armed
Token armed
Feature activation+0.000
assailants
Token assailants
Feature activation+0.000
emerging
Token emerging
Feature activation+0.000
to
Token to
Feature activation+0.515
attack
Token attack
Feature activation+0.564
from
Token from
Feature activation+0.157
within
Token within
Feature activation+0.389
the
Token the
Feature activation+0.389
sacred
Token sacred
Feature activation+0.000
compound
Token compound
Feature activation+0.000
the
Token the
Feature activation+0.000
caravan
Token caravan
Feature activation+0.000
crossed
Token crossed
Feature activation+0.000
through
Token through
Feature activation+0.000
Illinois
Token Illinois
Feature activation+0.000
it
Token it
Feature activation+0.641
also
Token also
Feature activation+0.000
left
Token left
Feature activation+0.000
behind
Token behind
Feature activation+0.000
paved
Token paved
Feature activation+0.000
sections
Token sections
Feature activation+0.000
said
Token said
Feature activation+0.000
their
Token their
Feature activation+0.000
adult
Token adult
Feature activation+0.000
children
Token children
Feature activation+0.000
returned
Token returned
Feature activation+0.085
home
Token home
Feature activation+0.556
within
Token within
Feature activation+0.411
the
Token the
Feature activation+0.368
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.113
,
Token,
Feature activation+0.000

INTERVAL 0.239 - 0.479
CONTAINS 0.110%

the
Token the
Feature activation+0.000
moon
Token moon
Feature activation+0.000
.
Token.
Feature activation+0.000
Religion
Token Religion
Feature activation+0.000
flies
Token flies
Feature activation+0.052
you
Token you
Feature activation+0.341
into
Token into
Feature activation+0.296
buildings
Token buildings
Feature activation+0.000
"
Token"
Feature activation+0.000
-
Token -
Feature activation+0.000
what
Token what
Feature activation+0.000
gets
Token gets
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
throat
Token throat
Feature activation+0.000
and
Token and
Feature activation+0.043
then
Token then
Feature activation+0.382
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
back
Token back
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Data
Token Data
Feature activation+0.000
returned
Token returned
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
mission
Token mission
Feature activation+0.000
will
Token will
Feature activation+0.367
help
Token help
Feature activation+0.000
Nasa
Token Nasa
Feature activation+0.000
identify
Token identify
Feature activation+0.000
safe
Token safe
Feature activation+0.000
landing
Token landing
Feature activation+0.000
awfully
Token awfully
Feature activation+0.000
tough
Token tough
Feature activation+0.000
to
Token to
Feature activation+0.000
come
Token come
Feature activation+0.000
back
Token back
Feature activation+0.000
without
Token without
Feature activation+0.450
your
Token your
Feature activation+0.046
goalie
Token goalie
Feature activation+0.006
pulling
Token pulling
Feature activation+0.000
off
Token off
Feature activation+0.000
at
Token at
Feature activation+0.000
arrived
Token arrived
Feature activation+0.000
,
Token,
Feature activation+0.107
Dev
Token Dev
Feature activation+0.000
inc
Tokeninc
Feature activation+0.000
en
Tokenen
Feature activation+0.000
zi
Tokenzi
Feature activation+0.426
stood
Token stood
Feature activation+0.000
and
Token and
Feature activation+0.000
watched
Token watched
Feature activation+0.000
as
Token as
Feature activation+0.000
flames
Token flames
Feature activation+0.000

INTERVAL 0.000 - 0.239
CONTAINS 99.839%

Cover
Token Cover
Feature activation+0.000
:
Token:
Feature activation+0.000
They
Token They
Feature activation+0.000
'
Token '
Feature activation+0.000
Par
TokenPar
Feature activation+0.000
rot
Tokenrot
Feature activation+0.000
the
Token the
Feature activation+0.000
Administration
Token Administration
Feature activation+0.000
's
Token's
Feature activation+0.000
Obamacare
Token Obamacare
Feature activation+0.000
Talking
Token Talking
Feature activation+0.000
from
Token from
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
show
Token show
Feature activation+0.000
came
Token came
Feature activation+0.000
the
Token the
Feature activation+0.000
day
Token day
Feature activation+0.449
IS
TokenIS
Feature activation+0.000
IN
Token IN
Feature activation+0.208
A
Token A
Feature activation+0.000
L
Token L
Feature activation+0.000
AD
TokenAD
Feature activation+0.000
Y
TokenY
Feature activation+0.000
THERE
Token THERE
Feature activation+0.000
IS
Token IS
Feature activation+0.000
A
Token A
Feature activation+0.000
CH
Token CH
Feature activation+0.000
ANCE
TokenANCE
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
suspected
Token suspected
Feature activation+0.000
terrorists
Token terrorists
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
deported
Token deported
Feature activation+0.000
and
Token and
Feature activation+0.000
53
Token 53
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
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+0.000
own
Token own
Feature activation+0.000
policies
Token policies
Feature activation+0.000
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
argue
Token argue
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 H7.3: (feature 2460)

TOP ACTIVATIONS
MAX = 4.165

were
Token were
Feature activation+0.000
creating
Token creating
Feature activation+0.000
a
Token a
Feature activation+0.000
larger
Token larger
Feature activation+0.000
global
Token global
Feature activation+0.593
presence
Token presence
Feature activation+4.165
for
Token for
Feature activation+2.052
themselves
Token themselves
Feature activation+1.491
with
Token with
Feature activation+0.234
the
Token the
Feature activation+0.372
American
Token American
Feature activation+0.000
the
Token the
Feature activation+0.000
global
Token global
Feature activation+0.000
economic
Token economic
Feature activation+0.000
centre
Token centre
Feature activation+0.766
of
Token of
Feature activation+0.236
gravity
Token gravity
Feature activation+3.271
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
changes
Token changes
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.027
issued
Token issued
Feature activation+0.000
a
Token a
Feature activation+0.000
rare
Token rare
Feature activation+0.000
worldwide
Token worldwide
Feature activation+0.000
travel
Token travel
Feature activation+1.113
alert
Token alert
Feature activation+3.106
on
Token on
Feature activation+1.031
Monday
Token Monday
Feature activation+0.000
,
Token,
Feature activation+0.000
warning
Token warning
Feature activation+0.301
American
Token American
Feature activation+0.041
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
a
Tokena
Feature activation+0.000
major
Token major
Feature activation+0.000
global
Token global
Feature activation+0.000
threat
Token threat
Feature activation+2.818
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Dr
Token Dr
Feature activation+0.000
.
Token.
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
global
Token global
Feature activation+0.000
PR
Token PR
Feature activation+0.000
and
Token and
Feature activation+0.000
communications
Token communications
Feature activation+0.140
groups
Token groups
Feature activation+2.758
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
10
Token 10
Feature activation+0.000
global
Token global
Feature activation+0.000
economies
Token economies
Feature activation+2.745
by
Token by
Feature activation+0.456
the
Token the
Feature activation+1.009
time
Token time
Feature activation+0.000
its
Token its
Feature activation+0.000
cent
Token cent
Feature activation+0.000
of
Token of
Feature activation+0.000
one
Token one
Feature activation+0.000
the
Token the
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
international
Token international
Feature activation+0.000
operations
Token operations
Feature activation+2.450
to
Token to
Feature activation+1.508
date
Token date
Feature activation+0.373
against
Token against
Feature activation+0.725
al
Token al
Feature activation+0.010
-
Token-
Feature activation+0.000
expected
Token expected
Feature activation+0.109
rate
Token rate
Feature activation+0.032
of
Token of
Feature activation+0.000
global
Token global
Feature activation+0.305
warming
Token warming
Feature activation+1.464
in
Token in
Feature activation+2.421
half
Token half
Feature activation+1.184
by
Token by
Feature activation+0.200
2050
Token 2050
Feature activation+0.000
,
Token,
Feature activation+0.000
save
Token save
Feature activation+0.000
its
Token its
Feature activation+0.000
position
Token position
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
global
Token global
Feature activation+0.543
leader
Token leader
Feature activation+2.401
in
Token in
Feature activation+1.709
the
Token the
Feature activation+2.041
semic
Token semic
Feature activation+0.000
onductor
Tokenonductor
Feature activation+0.000
industry
Token industry
Feature activation+1.027
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
globe
Token globe
Feature activation+0.761
non
Token non
Feature activation+0.980
-
Token-
Feature activation+1.500
stop
Tokenstop
Feature activation+2.242
on
Token on
Feature activation+0.887
our
Token our
Feature activation+0.839
world
Token world
Feature activation+0.011
tour
Token tour
Feature activation+0.902
,"
Token,"
Feature activation+0.000
top
Token top
Feature activation+0.000
5
Token 5
Feature activation+0.000
global
Token global
Feature activation+0.000
antiv
Token antiv
Feature activation+0.000
irus
Tokenirus
Feature activation+0.000
players
Token players
Feature activation+2.189
)
Token)
Feature activation+0.157
and
Token and
Feature activation+0.000
cart
Token cart
Feature activation+0.000
ech
Tokenech
Feature activation+0.000
(
Token (
Feature activation+0.000
's
Token's
Feature activation+0.000
gone
Token gone
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
nationwide
Token nationwide
Feature activation+0.000
hunt
Token hunt
Feature activation+2.183
to
Token to
Feature activation+0.629
find
Token find
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
business
Token business
Feature activation+0.000
owners
Token owners
Feature activation+0.000
the
Token the
Feature activation+0.000
direction
Token direction
Feature activation+0.000
of
Token of
Feature activation+0.000
international
Token international
Feature activation+0.358
development
Token development
Feature activation+0.739
in
Token in
Feature activation+2.180
a
Token a
Feature activation+0.165
global
Token global
Feature activation+0.195
vacuum
Token vacuum
Feature activation+1.098
of
Token of
Feature activation+0.557
accountability
Token accountability
Feature activation+1.017
rem
Tokenrem
Feature activation+0.000
ake
Tokenake
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.101
in
Token in
Feature activation+0.872
our
Token our
Feature activation+2.158
image
Token image
Feature activation+0.154
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
,
Token,
Feature activation+0.000
seeking
Token seeking
Feature activation+0.000
to
Token to
Feature activation+0.000
enhance
Token enhance
Feature activation+0.000
global
Token global
Feature activation+0.201
solidarity
Token solidarity
Feature activation+2.089
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
foremost
Token foremost
Feature activation+0.000
guiding
Token guiding
Feature activation+0.000
principles
Token principles
Feature activation+0.000
a
Token a
Feature activation+0.000
spike
Token spike
Feature activation+0.000
in
Token in
Feature activation+0.000
global
Token global
Feature activation+0.120
methane
Token methane
Feature activation+0.018
concentrations
Token concentrations
Feature activation+2.059
in
Token in
Feature activation+1.513
the
Token the
Feature activation+1.053
atmosphere
Token atmosphere
Feature activation+0.776
seen
Token seen
Feature activation+0.128
since
Token since
Feature activation+0.214
creating
Token creating
Feature activation+0.000
a
Token a
Feature activation+0.000
larger
Token larger
Feature activation+0.000
global
Token global
Feature activation+0.593
presence
Token presence
Feature activation+4.165
for
Token for
Feature activation+2.052
themselves
Token themselves
Feature activation+1.491
with
Token with
Feature activation+0.234
the
Token the
Feature activation+0.372
American
Token American
Feature activation+0.000
breakthrough
Token breakthrough
Feature activation+0.086
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
global
Token global
Feature activation+0.543
leader
Token leader
Feature activation+2.401
in
Token in
Feature activation+1.709
the
Token the
Feature activation+2.041
semic
Token semic
Feature activation+0.000
onductor
Tokenonductor
Feature activation+0.000
industry
Token industry
Feature activation+1.027
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
all
Token all
Feature activation+0.178
global
Token global
Feature activation+0.104
grain
Token grain
Feature activation+0.000
exp
Token exp
Feature activation+0.000
orters
Tokenorters
Feature activation+2.036
that
Token that
Feature activation+0.189
have
Token have
Feature activation+0.000
struggled
Token struggled
Feature activation+0.000
recently
Token recently
Feature activation+0.000
with
Token with
Feature activation+0.000
called
Token called
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
international
Token international
Feature activation+0.180
political
Token political
Feature activation+0.203
unification
Token unification
Feature activation+1.978
of
Token of
Feature activation+1.675
the
Token the
Feature activation+1.309
European
Token European
Feature activation+0.096
working
Token working
Feature activation+0.100
classes
Token classes
Feature activation+0.638

Top DFA by src position
MAX = 4.600

Who
Token Who
Feature activation+0.014
Top resid features:
were
Token were
Feature activation+0.013
Top resid features:
creating
Token creating
Feature activation+0.064
Top resid features:
a
Token a
Feature activation+0.031
Top resid features:
larger
Token larger
Feature activation+0.223
Top resid features:
global
Token global
Feature activation+4.600
Top resid features:
presence
Token presence
Feature activation+0.079
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
themselves
Token themselves
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
shift
Token shift
Feature activation-0.006
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.028
Top resid features:
global
Token global
Feature activation+3.809
Top resid features:
economic
Token economic
Feature activation+0.091
Top resid features:
centre
Token centre
Feature activation-0.029
Top resid features:
of
Token of
Feature activation+0.034
Top resid features:
gravity
Token gravity
Feature activation+0.044
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
State
Token State
Feature activation+0.003
Top resid features:
Department
Token Department
Feature activation+0.039
Top resid features:
issued
Token issued
Feature activation-0.037
Top resid features:
a
Token a
Feature activation-0.043
Top resid features:
rare
Token rare
Feature activation+0.080
Top resid features:
worldwide
Token worldwide
Feature activation+3.662
Top resid features:
travel
Token travel
Feature activation+0.074
Top resid features:
alert
Token alert
Feature activation+0.028
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Monday
Token Monday
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.014
Top resid features:
âĢ
Token âĢ
Feature activation+0.002
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
a
Tokena
Feature activation+0.003
Top resid features:
major
Token major
Feature activation+0.066
Top resid features:
global
Token global
Feature activation+3.437
Top resid features:
threat
Token threat
Feature activation+0.073
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:
Dr
Token Dr
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.010
Top resid features:
one
Token one
Feature activation-0.012
Top resid features:
of
Token of
Feature activation-0.011
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
biggest
Token biggest
Feature activation-0.002
Top resid features:
global
Token global
Feature activation+3.433
Top resid features:
PR
Token PR
Feature activation+0.027
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
communications
Token communications
Feature activation+0.019
Top resid features:
groups
Token groups
Feature activation+0.040
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
one
Token one
Feature activation-0.015
Top resid features:
of
Token of
Feature activation-0.007
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
top
Token top
Feature activation+0.043
Top resid features:
10
Token 10
Feature activation-0.054
Top resid features:
global
Token global
Feature activation+3.480
Top resid features:
economies
Token economies
Feature activation+0.069
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
part
Token part
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
one
Token one
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
biggest
Token biggest
Feature activation+0.098
Top resid features:
international
Token international
Feature activation+3.161
Top resid features:
operations
Token operations
Feature activation+0.045
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
date
Token date
Feature activation+0.000
Top resid features:
against
Token against
Feature activation+0.000
Top resid features:
al
Token al
Feature activation+0.000
Top resid features:
cut
Token cut
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
expected
Token expected
Feature activation+0.065
Top resid features:
rate
Token rate
Feature activation+0.041
Top resid features:
of
Token of
Feature activation+0.012
Top resid features:
global
Token global
Feature activation+2.017
Top resid features:
warming
Token warming
Feature activation+0.167
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
half
Token half
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
2050
Token 2050
Feature activation+0.000
Top resid features:
maintain
Token maintain
Feature activation+0.026
Top resid features:
its
Token its
Feature activation+0.012
Top resid features:
position
Token position
Feature activation+0.008
Top resid features:
as
Token as
Feature activation+0.065
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
global
Token global
Feature activation+2.689
Top resid features:
leader
Token leader
Feature activation+0.101
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
semic
Token semic
Feature activation+0.000
Top resid features:
onductor
Tokenonductor
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.055
Top resid features:
been
Token been
Feature activation+0.053
Top resid features:
racing
Token racing
Feature activation+0.233
Top resid features:
across
Token across
Feature activation+0.172
Top resid features:
the
Token the
Feature activation+0.215
Top resid features:
globe
Token globe
Feature activation+2.054
Top resid features:
non
Token non
Feature activation+0.087
Top resid features:
-
Token-
Feature activation+0.008
Top resid features:
stop
Tokenstop
Feature activation+0.134
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.000
Top resid features:
3
Token3
Feature activation-0.013
Top resid features:
out
Token out
Feature activation-0.024
Top resid features:
of
Token of
Feature activation-0.100
Top resid features:
top
Token top
Feature activation+0.007
Top resid features:
5
Token 5
Feature activation-0.129
Top resid features:
global
Token global
Feature activation+3.144
Top resid features:
antiv
Token antiv
Feature activation+0.006
Top resid features:
irus
Tokenirus
Feature activation-0.019
Top resid features:
players
Token players
Feature activation+0.033
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
He
Token He
Feature activation+0.004
Top resid features:
's
Token's
Feature activation-0.022
Top resid features:
gone
Token gone
Feature activation+0.016
Top resid features:
on
Token on
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.042
Top resid features:
nationwide
Token nationwide
Feature activation+2.999
Top resid features:
hunt
Token hunt
Feature activation+0.078
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
find
Token find
Feature activation+0.000
Top resid features:
Republican
Token Republican
Feature activation+0.000
Top resid features:
business
Token business
Feature activation+0.000
Top resid features:
dist
Token dist
Feature activation-0.001
Top resid features:
orting
Tokenorting
Feature activation+0.098
Top resid features:
the
Token the
Feature activation-0.017
Top resid features:
direction
Token direction
Feature activation+0.053
Top resid features:
of
Token of
Feature activation+0.017
Top resid features:
international
Token international
Feature activation+2.482
Top resid features:
development
Token development
Feature activation+0.183
Top resid features:
in
Token in
Feature activation+0.082
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
global
Token global
Feature activation+0.000
Top resid features:
vacuum
Token vacuum
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.017
Top resid features:
"
Token "
Feature activation+0.044
Top resid features:
rem
Tokenrem
Feature activation+0.005
Top resid features:
ake
Tokenake
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
world
Token world
Feature activation+2.300
Top resid features:
in
Token in
Feature activation+0.436
Top resid features:
our
Token our
Feature activation+0.006
Top resid features:
image
Token image
Feature activation+0.000
Top resid features:
."
Token."
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
international
Token international
Feature activation+0.133
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
seeking
Token seeking
Feature activation+0.154
Top resid features:
to
Token to
Feature activation+0.064
Top resid features:
enhance
Token enhance
Feature activation+0.116
Top resid features:
global
Token global
Feature activation+2.243
Top resid features:
solidarity
Token solidarity
Feature activation+0.060
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
foremost
Token foremost
Feature activation+0.000
Top resid features:
guiding
Token guiding
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
But
TokenBut
Feature activation+0.009
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
spike
Token spike
Feature activation-0.005
Top resid features:
in
Token in
Feature activation+0.145
Top resid features:
global
Token global
Feature activation+2.680
Top resid features:
methane
Token methane
Feature activation-0.129
Top resid features:
concentrations
Token concentrations
Feature activation+0.007
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
atmosphere
Token atmosphere
Feature activation+0.000
Top resid features:
Who
Token Who
Feature activation+0.039
Top resid features:
were
Token were
Feature activation+0.008
Top resid features:
creating
Token creating
Feature activation-0.025
Top resid features:
a
Token a
Feature activation-0.029
Top resid features:
larger
Token larger
Feature activation+0.195
Top resid features:
global
Token global
Feature activation+2.431
Top resid features:
presence
Token presence
Feature activation+0.167
Top resid features:
for
Token for
Feature activation+0.041
Top resid features:
themselves
Token themselves
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
maintain
Token maintain
Feature activation+0.019
Top resid features:
its
Token its
Feature activation-0.002
Top resid features:
position
Token position
Feature activation+0.014
Top resid features:
as
Token as
Feature activation+0.109
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
global
Token global
Feature activation+2.038
Top resid features:
leader
Token leader
Feature activation+0.197
Top resid features:
in
Token in
Feature activation+0.109
Top resid features:
the
Token the
Feature activation+0.041
Top resid features:
semic
Token semic
Feature activation+0.000
Top resid features:
onductor
Tokenonductor
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation-0.023
Top resid features:
action
Token action
Feature activation-0.009
Top resid features:
would
Token would
Feature activation+0.013
Top resid features:
benefit
Token benefit
Feature activation+0.001
Top resid features:
all
Token all
Feature activation+0.214
Top resid features:
global
Token global
Feature activation+2.439
Top resid features:
grain
Token grain
Feature activation-0.017
Top resid features:
exp
Token exp
Feature activation+0.026
Top resid features:
orters
Tokenorters
Feature activation+0.001
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
Engels
Token Engels
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
called
Token called
Feature activation+0.010
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.054
Top resid features:
international
Token international
Feature activation+2.225
Top resid features:
political
Token political
Feature activation+0.281
Top resid features:
unification
Token unification
Feature activation+0.122
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
European
Token European
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.06

Head 2: 0.01

Head 3: 0.41

Head 4: 0.06

Head 5: 0.11

Head 6: 0.05

Head 7: 0.02

Head 8: 0.09

Head 9: 0.07

Head 10: 0.01

Head 11: 0.02

Positive logits

765612.28

icter1.88

cryptoc1.81

omic1.78

ascript1.75

Bahá1.74

19511.73

embryonic1.73

bacter1.72

culosis1.71

19871.69

organism1.65

icable1.65

19471.65

urable1.64

transact1.64

subscribing1.61

phenomenon1.61

cybersecurity1.60

��1.58

Negative logits

esville-2.38

ander-2.18

District-2.16

downstairs-1.94

etsk-1.93

emo-1.90

intendent-1.90

ema-1.89

suburban-1.85

gow-1.82

veland-1.82

Score-1.82

upstairs-1.80

Meter-1.77

Titus-1.74

Range-1.74

city-1.74

ederal-1.73

zon-1.72

aukee-1.72

INTERVAL 3.748 - 4.165
CONTAINS 0.000%

were
Token were
Feature activation+0.000
creating
Token creating
Feature activation+0.000
a
Token a
Feature activation+0.000
larger
Token larger
Feature activation+0.000
global
Token global
Feature activation+0.593
presence
Token presence
Feature activation+4.165
for
Token for
Feature activation+2.052
themselves
Token themselves
Feature activation+1.491
with
Token with
Feature activation+0.234
the
Token the
Feature activation+0.372
American
Token American
Feature activation+0.000

INTERVAL 3.332 - 3.748
CONTAINS 0.000%

INTERVAL 2.915 - 3.332
CONTAINS 0.000%

issued
Token issued
Feature activation+0.000
a
Token a
Feature activation+0.000
rare
Token rare
Feature activation+0.000
worldwide
Token worldwide
Feature activation+0.000
travel
Token travel
Feature activation+1.113
alert
Token alert
Feature activation+3.106
on
Token on
Feature activation+1.031
Monday
Token Monday
Feature activation+0.000
,
Token,
Feature activation+0.000
warning
Token warning
Feature activation+0.301
American
Token American
Feature activation+0.041
the
Token the
Feature activation+0.000
global
Token global
Feature activation+0.000
economic
Token economic
Feature activation+0.000
centre
Token centre
Feature activation+0.766
of
Token of
Feature activation+0.236
gravity
Token gravity
Feature activation+3.271
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
changes
Token changes
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.027

INTERVAL 2.499 - 2.915
CONTAINS 0.000%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
10
Token 10
Feature activation+0.000
global
Token global
Feature activation+0.000
economies
Token economies
Feature activation+2.745
by
Token by
Feature activation+0.456
the
Token the
Feature activation+1.009
time
Token time
Feature activation+0.000
its
Token its
Feature activation+0.000
cent
Token cent
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
global
Token global
Feature activation+0.000
PR
Token PR
Feature activation+0.000
and
Token and
Feature activation+0.000
communications
Token communications
Feature activation+0.140
groups
Token groups
Feature activation+2.758
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
a
Tokena
Feature activation+0.000
major
Token major
Feature activation+0.000
global
Token global
Feature activation+0.000
threat
Token threat
Feature activation+2.818
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Dr
Token Dr
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 2.082 - 2.499
CONTAINS 0.001%

expected
Token expected
Feature activation+0.109
rate
Token rate
Feature activation+0.032
of
Token of
Feature activation+0.000
global
Token global
Feature activation+0.305
warming
Token warming
Feature activation+1.464
in
Token in
Feature activation+2.421
half
Token half
Feature activation+1.184
by
Token by
Feature activation+0.200
2050
Token 2050
Feature activation+0.000
,
Token,
Feature activation+0.000
save
Token save
Feature activation+0.000
rem
Tokenrem
Feature activation+0.000
ake
Tokenake
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.101
in
Token in
Feature activation+0.872
our
Token our
Feature activation+2.158
image
Token image
Feature activation+0.154
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
its
Token its
Feature activation+0.000
position
Token position
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
global
Token global
Feature activation+0.543
leader
Token leader
Feature activation+2.401
in
Token in
Feature activation+1.709
the
Token the
Feature activation+2.041
semic
Token semic
Feature activation+0.000
onductor
Tokenonductor
Feature activation+0.000
industry
Token industry
Feature activation+1.027
's
Token's
Feature activation+0.000
gone
Token gone
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
nationwide
Token nationwide
Feature activation+0.000
hunt
Token hunt
Feature activation+2.183
to
Token to
Feature activation+0.629
find
Token find
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
business
Token business
Feature activation+0.000
owners
Token owners
Feature activation+0.000
,
Token,
Feature activation+0.000
seeking
Token seeking
Feature activation+0.000
to
Token to
Feature activation+0.000
enhance
Token enhance
Feature activation+0.000
global
Token global
Feature activation+0.201
solidarity
Token solidarity
Feature activation+2.089
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
foremost
Token foremost
Feature activation+0.000
guiding
Token guiding
Feature activation+0.000
principles
Token principles
Feature activation+0.000

INTERVAL 1.666 - 2.082
CONTAINS 0.002%

people
Token people
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.000
Worldwide
Token Worldwide
Feature activation+0.130
,
Token,
Feature activation+1.681
60
Token 60
Feature activation+1.008
percent
Token percent
Feature activation+1.454
of
Token of
Feature activation+1.219
all
Token all
Feature activation+0.800
cancer
Token cancer
Feature activation+0.000
communities
Token communities
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.000
a
Token a
Feature activation+0.000
global
Token global
Feature activation+0.000
and
Token and
Feature activation+1.959
local
Token local
Feature activation+0.000
scale
Token scale
Feature activation+0.165
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
a
Token a
Feature activation+0.000
spike
Token spike
Feature activation+0.000
in
Token in
Feature activation+0.000
global
Token global
Feature activation+0.120
methane
Token methane
Feature activation+0.018
concentrations
Token concentrations
Feature activation+2.059
in
Token in
Feature activation+1.513
the
Token the
Feature activation+1.053
atmosphere
Token atmosphere
Feature activation+0.776
seen
Token seen
Feature activation+0.128
since
Token since
Feature activation+0.214
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
global
Token global
Feature activation+0.543
leader
Token leader
Feature activation+2.401
in
Token in
Feature activation+1.709
the
Token the
Feature activation+2.041
semic
Token semic
Feature activation+0.000
onductor
Tokenonductor
Feature activation+0.000
industry
Token industry
Feature activation+1.027
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
years
Token years
Feature activation+0.000
ago
Token ago
Feature activation+0.000
and
Token and
Feature activation+0.000
tell
Token tell
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+1.695
we
Token we
Feature activation+1.535
need
Token need
Feature activation+0.056
your
Token your
Feature activation+0.000
capital
Token capital
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.249 - 1.666
CONTAINS 0.005%

's
Token's
Feature activation+0.000
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.000
worldwide
Token worldwide
Feature activation+0.000
standard
Token standard
Feature activation+0.608
for
Token for
Feature activation+1.377
fast
Token fast
Feature activation+0.000
rail
Token rail
Feature activation+0.000
is
Token is
Feature activation+0.615
the
Token the
Feature activation+0.888
1
Token 1
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+0.000
Around
Token Around
Feature activation+0.000
the
Token the
Feature activation+0.000
World
Token World
Feature activation+0.000
in
Token in
Feature activation+1.485
4
Token 4
Feature activation+0.088
K
TokenK
Feature activation+0.000
and
Token and
Feature activation+0.000
Amazing
Token Amazing
Feature activation+0.000
Places
Token Places
Feature activation+0.268
her
Token her
Feature activation+0.000
performances
Token performances
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
worldwide
Token worldwide
Feature activation+0.000
stage
Token stage
Feature activation+1.496
.
Token.
Feature activation+0.000
Watching
Token Watching
Feature activation+0.000
Amy
Token Amy
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
has
Token has
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000
a
Token a
Feature activation+0.000
world
Token world
Feature activation+0.000
more
Token more
Feature activation+0.007
intertwined
Token intertwined
Feature activation+1.365
than
Token than
Feature activation+0.326
at
Token at
Feature activation+0.000
any
Token any
Feature activation+0.081
time
Token time
Feature activation+0.000
in
Token in
Feature activation+0.074
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.061
biggest
Token biggest
Feature activation+0.000
charitable
Token charitable
Feature activation+0.000
group
Token group
Feature activation+1.279
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
viewed
Token viewed
Feature activation+0.000
by
Token by
Feature activation+0.000

INTERVAL 0.833 - 1.249
CONTAINS 0.010%

linked
Token linked
Feature activation+0.000
to
Token to
Feature activation+0.000
numerous
Token numerous
Feature activation+0.000
international
Token international
Feature activation+0.000
parcel
Token parcel
Feature activation+0.000
shipments
Token shipments
Feature activation+1.221
from
Token from
Feature activation+0.736
China
Token China
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
one
Token one
Feature activation+0.000
ering
Tokenering
Feature activation+0.000
the
Token the
Feature activation+0.000
direction
Token direction
Feature activation+0.000
of
Token of
Feature activation+0.296
international
Token international
Feature activation+0.769
development
Token development
Feature activation+0.907
in
Token in
Feature activation+1.639
an
Token an
Feature activation+0.000
und
Token und
Feature activation+0.000
em
Tokenem
Feature activation+0.000
ocratic
Tokenocratic
Feature activation+0.000
and
Token and
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
displaced
Token displaced
Feature activation+0.000
by
Token by
Feature activation+0.000
global
Token global
Feature activation+0.000
competition
Token competition
Feature activation+0.863
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
knew
Token knew
Feature activation+0.000
how
Token how
Feature activation+0.000
to
Token to
Feature activation+0.000
emergency
Token emergency
Feature activation+0.000
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
brought
Token brought
Feature activation+0.000
international
Token international
Feature activation+0.138
attention
Token attention
Feature activation+1.099
to
Token to
Feature activation+0.858
Flint
Token Flint
Feature activation+0.000
's
Token's
Feature activation+0.000
troubles
Token troubles
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
Unlike
Token Unlike
Feature activation+0.000
the
Token the
Feature activation+0.000
uniform
Token uniform
Feature activation+0.000
global
Token global
Feature activation+0.140
increase
Token increase
Feature activation+0.897
in
Token in
Feature activation+1.435
carbon
Token carbon
Feature activation+0.000
dioxide
Token dioxide
Feature activation+0.152
levels
Token levels
Feature activation+1.919
caused
Token caused
Feature activation+0.000

INTERVAL 0.416 - 0.833
CONTAINS 0.041%

say
Token say
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
safe
Token safe
Feature activation+0.818
from
Token from
Feature activation+0.807
Iran
Token Iran
Feature activation+0.000
's
Token's
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
ambitions
Token ambitions
Feature activation+0.000
the
Token the
Feature activation+0.000
national
Token national
Feature activation+0.000
data
Token data
Feature activation+0.050
suggest
Token suggest
Feature activation+0.037
about
Token about
Feature activation+0.243
the
Token the
Feature activation+0.474
productivity
Token productivity
Feature activation+0.000
of
Token of
Feature activation+0.093
our
Token our
Feature activation+0.097
education
Token education
Feature activation+0.000
system
Token system
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
largest
Token largest
Feature activation+0.000
money
Token money
Feature activation+0.000
managers
Token managers
Feature activation+0.686
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
sympathetic
Token sympathetic
Feature activation+0.000
to
Token to
Feature activation+0.000
aspects
Token aspects
Feature activation+0.000
Maurice
Token Maurice
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
second
Token second
Feature activation+0.000
international
Token international
Feature activation+0.085
goal
Token goal
Feature activation+0.802
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
still
Token still
Feature activation+0.000
relevant
Token relevant
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.085
today
Token today
Feature activation+0.587
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Spanish
Token Spanish
Feature activation+0.000

INTERVAL 0.000 - 0.416
CONTAINS 99.941%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
How
TokenHow
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
contemporary
Token contemporary
Feature activation+0.000
food
Token food
Feature activation+0.000
magazines
Token magazines
Feature activation+0.000
use
Token use
Feature activation+0.000
photography
Token photography
Feature activation+0.000
?
Token?
Feature activation+0.000
BJP
Token BJP
Feature activation+0.000
collection
Tokencollection
Feature activation+0.000
,
Token,
Feature activation+0.000
Fashion
Token Fashion
Feature activation+0.000
Crimes
Token Crimes
Feature activation+0.000
Against
Token Against
Feature activation+0.000
Male
Token Male
Feature activation+0.000
Kn
Token Kn
Feature activation+0.000
it
Tokenit
Feature activation+0.000
wear
Tokenwear
Feature activation+0.000
Models
Token Models
Feature activation+0.000
,
Token,
Feature activation+0.000
smart
Token smart
Feature activation+0.000
and
Token and
Feature activation+0.000
tact
Token tact
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
quotation
Token quotation
Feature activation+0.000
exists
Token exists
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
finale
Token finale
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Of
TokenOf
Feature activation+0.000
D
TokenD
Feature activation+0.000
ork
Tokenork
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
(@
Token (@
Feature activation+0.000
L
TokenL
Feature activation+0.000
ard
Tokenard
Feature activation+0.000
FD
TokenFD
Feature activation+0.000
ork
Tokenork
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
)
Token)
Feature activation+0.000
he
Token he
Feature activation+0.000
explains
Token explains
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
we
Tokenwe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
still
Token still
Feature activation+0.000
trying
Token trying
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 H7.3: (feature 48504)

TOP ACTIVATIONS
MAX = 1.646

any
Token any
Feature activation+0.000
band
Token band
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
district
Token district
Feature activation+0.450
that
Token that
Feature activation+1.646
had
Token had
Feature activation+0.983
applied
Token applied
Feature activation+0.171
to
Token to
Feature activation+0.000
participate
Token participate
Feature activation+0.079
in
Token in
Feature activation+0.000
standard
Token standard
Feature activation+0.000
cos
Token cos
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ological
Tokenological
Feature activation+0.000
model
Token model
Feature activation+0.268
that
Token that
Feature activation+1.566
we
Token we
Feature activation+0.755
don
Token don
Feature activation+0.427
't
Token't
Feature activation+0.467
understand
Token understand
Feature activation+0.110
,"
Token,"
Feature activation+0.000
apps
Token apps
Feature activation+0.000
in
Token in
Feature activation+0.008
the
Token the
Feature activation+0.022
Windows
Token Windows
Feature activation+0.000
Store
Token Store
Feature activation+0.059
are
Token are
Feature activation+1.461
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
universal
Tokenuniversal
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
bacteria
Token bacteria
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
fungus
Token fungus
Feature activation+0.000
gardens
Token gardens
Feature activation+0.667
that
Token that
Feature activation+1.460
are
Token are
Feature activation+1.420
capable
Token capable
Feature activation+0.163
of
Token of
Feature activation+0.516
breaking
Token breaking
Feature activation+0.000
down
Token down
Feature activation+0.000
figure
Token figure
Feature activation+0.000
out
Token out
Feature activation+0.000
where
Token where
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
space
Token space
Feature activation+1.425
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
supposed
Token supposed
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
fungus
Token fungus
Feature activation+0.000
gardens
Token gardens
Feature activation+0.667
that
Token that
Feature activation+1.460
are
Token are
Feature activation+1.420
capable
Token capable
Feature activation+0.163
of
Token of
Feature activation+0.516
breaking
Token breaking
Feature activation+0.000
down
Token down
Feature activation+0.000
cellul
Token cellul
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
in
Token in
Feature activation+0.000
life
Token life
Feature activation+0.038
that
Token that
Feature activation+1.378
is
Token is
Feature activation+0.870
certain
Token certain
Feature activation+0.240
,"
Token,"
Feature activation+0.000
Joe
Token Joe
Feature activation+0.000
shared
Token shared
Feature activation+0.000
service
Token service
Feature activation+0.000
bots
Token bots
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
place
Token place
Feature activation+0.143
that
Token that
Feature activation+1.322
will
Token will
Feature activation+0.291
...
Token...
Feature activation+0.000
a
Token a
Feature activation+0.000
hm
Tokenhm
Feature activation+0.000
...
Token...
Feature activation+0.000
What
Token What
Feature activation+0.000
words
Token words
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
English
Token English
Feature activation+0.000
language
Token language
Feature activation+1.279
contain
Token contain
Feature activation+0.813
two
Token two
Feature activation+0.000
u
Token u
Feature activation+0.000
's
Token's
Feature activation+0.000
in
Token in
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
pressures
Token pressures
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
system
Token system
Feature activation+0.319
that
Token that
Feature activation+1.270
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
never
Token never
Feature activation+0.000
experienced
Token experienced
Feature activation+0.000
before
Token before
Feature activation+0.000
only
Token only
Feature activation+0.000
graphic
Token graphic
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.031
presentation
Token presentation
Feature activation+0.521
in
Token in
Feature activation+1.210
Metro
Token Metro
Feature activation+0.000
lin
Tokenlin
Feature activation+0.000
x
Tokenx
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
top
Token top
Feature activation+0.018
of
Token of
Feature activation+0.432
the
Token the
Feature activation+0.000
jelly
Token jelly
Feature activation+0.000
fish
Token fish
Feature activation+0.000
created
Token created
Feature activation+1.179
by
Token by
Feature activation+0.540
its
Token its
Feature activation+0.000
gon
Token gon
Feature activation+0.000
ads
Tokenads
Feature activation+0.000
which
Token which
Feature activation+0.647
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
of
Token of
Feature activation+0.000
Philadelphia
Token Philadelphia
Feature activation+0.000
that
Token that
Feature activation+1.175
operate
Token operate
Feature activation+0.000
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000
same
Token same
Feature activation+0.000
neighborhoods
Token neighborhoods
Feature activation+0.000
Part
Token Part
Feature activation+0.000
icles
Tokenicles
Feature activation+0.000
suspended
Token suspended
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
water
Token water
Feature activation+1.174
bumped
Token bumped
Feature activation+0.491
the
Token the
Feature activation+0.069
laser
Token laser
Feature activation+0.000
light
Token light
Feature activation+0.000
and
Token and
Feature activation+0.000
The
TokenThe
Feature activation+0.000
particles
Token particles
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.138
coma
Token coma
Feature activation+0.000
are
Token are
Feature activation+1.168
ejected
Token ejected
Feature activation+0.481
away
Token away
Feature activation+0.166
from
Token from
Feature activation+0.086
the
Token the
Feature activation+0.000
comet
Token comet
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000
other
Token other
Feature activation+0.000
receptors
Token receptors
Feature activation+0.000
in
Token in
Feature activation+0.100
the
Token the
Feature activation+0.041
body
Token body
Feature activation+1.118
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.281
have
Token have
Feature activation+0.729
a
Token a
Feature activation+0.000
wide
Token wide
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Koran
Token Koran
Feature activation+1.114
saying
Token saying
Feature activation+0.674
women
Token women
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
play
Token play
Feature activation+0.000
a
Token a
Feature activation+0.000
standard
Token standard
Feature activation+0.000
model
Token model
Feature activation+0.000
of
Token of
Feature activation+0.000
particle
Token particle
Feature activation+0.000
physics
Token physics
Feature activation+0.000
has
Token has
Feature activation+1.113
to
Token to
Feature activation+0.679
change
Token change
Feature activation+0.449
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.056
registry
Token registry
Feature activation+0.000
in
Token in
Feature activation+0.397
order
Token order
Feature activation+0.597
to
Token to
Feature activation+1.096
download
Token download
Feature activation+0.065
Meter
Token Meter
Feature activation+0.000
pret
Tokenpret
Feature activation+0.000
or
Tokenor
Feature activation+0.000
and
Token and
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
surfaces
Token surfaces
Feature activation+0.291
of
Token of
Feature activation+0.000
cells
Token cells
Feature activation+0.381
are
Token are
Feature activation+1.052
organized
Token organized
Feature activation+0.327
like
Token like
Feature activation+0.000
this
Token this
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

Top DFA by src position
MAX = 1.085

not
Token not
Feature activation-0.008
Top resid features:
aware
Token aware
Feature activation-0.013
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
any
Token any
Feature activation-0.033
Top resid features:
band
Token band
Feature activation+0.124
Top resid features:
in
Token in
Feature activation+1.034
Top resid features:
the
Token the
Feature activation+0.670
Top resid features:
district
Token district
Feature activation+0.335
Top resid features:
that
Token that
Feature activation-0.004
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
applied
Token applied
Feature activation+0.000
Top resid features:
think
Token think
Feature activation+0.024
Top resid features:
that
Token that
Feature activation+0.013
Top resid features:
there
Token there
Feature activation+0.011
Top resid features:
is
Token is
Feature activation-0.042
Top resid features:
something
Token something
Feature activation+0.003
Top resid features:
in
Token in
Feature activation+0.911
Top resid features:
the
Token the
Feature activation+0.523
Top resid features:
standard
Token standard
Feature activation+0.262
Top resid features:
cos
Token cos
Feature activation+0.001
Top resid features:
m
Tokenm
Feature activation+0.003
Top resid features:
ological
Tokenological
Feature activation+0.029
Top resid features:
A
TokenA
Feature activation-0.017
Top resid features:
number
Token number
Feature activation-0.009
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
new
Token new
Feature activation-0.033
Top resid features:
apps
Token apps
Feature activation+0.086
Top resid features:
in
Token in
Feature activation+0.770
Top resid features:
the
Token the
Feature activation+0.463
Top resid features:
Windows
Token Windows
Feature activation+0.078
Top resid features:
Store
Token Store
Feature activation+0.498
Top resid features:
are
Token are
Feature activation+0.041
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
are
Token are
Feature activation-0.049
Top resid features:
many
Token many
Feature activation-0.095
Top resid features:
species
Token species
Feature activation+0.306
Top resid features:
of
Token of
Feature activation+0.091
Top resid features:
bacteria
Token bacteria
Feature activation+0.146
Top resid features:
in
Token in
Feature activation+0.689
Top resid features:
the
Token the
Feature activation+0.367
Top resid features:
fungus
Token fungus
Feature activation+0.224
Top resid features:
gardens
Token gardens
Feature activation+0.303
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
constantly
Token constantly
Feature activation-0.016
Top resid features:
figure
Token figure
Feature activation-0.025
Top resid features:
out
Token out
Feature activation-0.070
Top resid features:
where
Token where
Feature activation-0.080
Top resid features:
in
Token in
Feature activation+0.729
Top resid features:
that
Token that
Feature activation+0.841
Top resid features:
space
Token space
Feature activation+0.748
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
re
Tokenre
Feature activation+0.000
Top resid features:
are
Token are
Feature activation-0.020
Top resid features:
many
Token many
Feature activation-0.081
Top resid features:
species
Token species
Feature activation+0.211
Top resid features:
of
Token of
Feature activation+0.080
Top resid features:
bacteria
Token bacteria
Feature activation+0.238
Top resid features:
in
Token in
Feature activation+0.659
Top resid features:
the
Token the
Feature activation+0.228
Top resid features:
fungus
Token fungus
Feature activation+0.252
Top resid features:
gardens
Token gardens
Feature activation+0.347
Top resid features:
that
Token that
Feature activation+0.042
Top resid features:
are
Token are
Feature activation-0.002
Top resid features:
know
Token know
Feature activation-0.020
Top resid features:
?
Token?
Feature activation-0.020
Top resid features:
There
Token There
Feature activation+0.025
Top resid features:
is
Token is
Feature activation-0.038
Top resid features:
nothing
Token nothing
Feature activation+0.086
Top resid features:
in
Token in
Feature activation+0.975
Top resid features:
life
Token life
Feature activation+0.880
Top resid features:
that
Token that
Feature activation+0.101
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
certain
Token certain
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
There
Token There
Feature activation+0.058
Top resid features:
are
Token are
Feature activation+0.014
Top resid features:
also
Token also
Feature activation-0.001
Top resid features:
service
Token service
Feature activation+0.022
Top resid features:
bots
Token bots
Feature activation+0.172
Top resid features:
around
Token around
Feature activation+0.837
Top resid features:
the
Token the
Feature activation+0.463
Top resid features:
place
Token place
Feature activation+0.287
Top resid features:
that
Token that
Feature activation+0.021
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
...
Token...
Feature activation+0.000
Top resid features:
look
Token look
Feature activation-0.001
Top resid features:
at
Token at
Feature activation-0.001
Top resid features:
:
Token:
Feature activation+0.007
Top resid features:
What
Token What
Feature activation+0.055
Top resid features:
words
Token words
Feature activation+0.283
Top resid features:
in
Token in
Feature activation+0.934
Top resid features:
the
Token the
Feature activation+0.288
Top resid features:
English
Token English
Feature activation+0.251
Top resid features:
language
Token language
Feature activation+0.184
Top resid features:
contain
Token contain
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
"
Token "
Feature activation-0.001
Top resid features:
I
TokenI
Feature activation+0.011
Top resid features:
'm
Token'm
Feature activation-0.001
Top resid features:
seeing
Token seeing
Feature activation-0.050
Top resid features:
pressures
Token pressures
Feature activation+0.222
Top resid features:
in
Token in
Feature activation+0.850
Top resid features:
the
Token the
Feature activation+0.386
Top resid features:
system
Token system
Feature activation+0.423
Top resid features:
that
Token that
Feature activation+0.040
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.012
Top resid features:
the
Token the
Feature activation-0.011
Top resid features:
only
Token only
Feature activation+0.012
Top resid features:
graphic
Token graphic
Feature activation+0.016
Top resid features:
in
Token in
Feature activation+0.555
Top resid features:
this
Token this
Feature activation+1.085
Top resid features:
presentation
Token presentation
Feature activation+0.099
Top resid features:
in
Token in
Feature activation+0.202
Top resid features:
Metro
Token Metro
Feature activation+0.000
Top resid features:
lin
Tokenlin
Feature activation+0.000
Top resid features:
x
Tokenx
Feature activation+0.000
Top resid features:
recognizable
Token recognizable
Feature activation+0.002
Top resid features:
by
Token by
Feature activation+0.029
Top resid features:
the
Token the
Feature activation+0.044
Top resid features:
pattern
Token pattern
Feature activation+0.033
Top resid features:
on
Token on
Feature activation+0.458
Top resid features:
the
Token the
Feature activation+0.506
Top resid features:
top
Token top
Feature activation+0.138
Top resid features:
of
Token of
Feature activation+0.189
Top resid features:
the
Token the
Feature activation+0.105
Top resid features:
jelly
Token jelly
Feature activation+0.163
Top resid features:
fish
Token fish
Feature activation+0.146
Top resid features:
thousands
Token thousands
Feature activation-0.039
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
thousands
Token thousands
Feature activation-0.012
Top resid features:
of
Token of
Feature activation-0.012
Top resid features:
businesses
Token businesses
Feature activation+0.231
Top resid features:
in
Token in
Feature activation+0.646
Top resid features:
the
Token the
Feature activation+0.475
Top resid features:
city
Token city
Feature activation+0.276
Top resid features:
of
Token of
Feature activation+0.038
Top resid features:
Philadelphia
Token Philadelphia
Feature activation+0.050
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
ods
Tokenods
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Part
Token Part
Feature activation-0.002
Top resid features:
icles
Tokenicles
Feature activation+0.368
Top resid features:
suspended
Token suspended
Feature activation-0.021
Top resid features:
in
Token in
Feature activation+0.689
Top resid features:
the
Token the
Feature activation+0.534
Top resid features:
water
Token water
Feature activation+0.249
Top resid features:
bumped
Token bumped
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
laser
Token laser
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.032
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
The
TokenThe
Feature activation+0.013
Top resid features:
particles
Token particles
Feature activation+0.245
Top resid features:
in
Token in
Feature activation+0.740
Top resid features:
the
Token the
Feature activation+0.395
Top resid features:
coma
Token coma
Feature activation+0.355
Top resid features:
are
Token are
Feature activation-0.012
Top resid features:
ejected
Token ejected
Feature activation+0.000
Top resid features:
away
Token away
Feature activation+0.000
Top resid features:
implications
Token implications
Feature activation-0.011
Top resid features:
for
Token for
Feature activation-0.013
Top resid features:
understanding
Token understanding
Feature activation+0.021
Top resid features:
other
Token other
Feature activation+0.011
Top resid features:
receptors
Token receptors
Feature activation+0.254
Top resid features:
in
Token in
Feature activation+0.771
Top resid features:
the
Token the
Feature activation+0.626
Top resid features:
body
Token body
Feature activation+0.231
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
ques
Tokenques
Feature activation+0.003
Top resid features:
claims
Token claims
Feature activation-0.009
Top resid features:
there
Token there
Feature activation+0.013
Top resid features:
is
Token is
Feature activation-0.008
Top resid features:
nothing
Token nothing
Feature activation+0.051
Top resid features:
in
Token in
Feature activation+0.645
Top resid features:
the
Token the
Feature activation+0.573
Top resid features:
Koran
Token Koran
Feature activation+0.480
Top resid features:
saying
Token saying
Feature activation+0.000
Top resid features:
women
Token women
Feature activation+0.000
Top resid features:
cannot
Token cannot
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.027
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
means
Token means
Feature activation-0.155
Top resid features:
something
Token something
Feature activation+0.032
Top resid features:
in
Token in
Feature activation+0.809
Top resid features:
the
Token the
Feature activation+0.525
Top resid features:
standard
Token standard
Feature activation+0.089
Top resid features:
model
Token model
Feature activation+0.201
Top resid features:
of
Token of
Feature activation+0.025
Top resid features:
particle
Token particle
Feature activation+0.014
Top resid features:
use
Token use
Feature activation+0.030
Top resid features:
in
Token in
Feature activation+0.215
Top resid features:
embed
Token embed
Feature activation+0.008
Top resid features:
ding
Tokending
Feature activation+0.108
Top resid features:
PowerShell
Token PowerShell
Feature activation+0.033
Top resid features:
into
Token into
Feature activation+0.707
Top resid features:
the
Token the
Feature activation+0.348
Top resid features:
registry
Token registry
Feature activation+0.072
Top resid features:
in
Token in
Feature activation+0.133
Top resid features:
order
Token order
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
We
TokenWe
Feature activation-0.003
Top resid features:
think
Token think
Feature activation+0.001
Top resid features:
that
Token that
Feature activation-0.004
Top resid features:
most
Token most
Feature activation-0.033
Top resid features:
receptors
Token receptors
Feature activation+0.251
Top resid features:
on
Token on
Feature activation+0.489
Top resid features:
the
Token the
Feature activation+0.091
Top resid features:
surfaces
Token surfaces
Feature activation+0.454
Top resid features:
of
Token of
Feature activation+0.134
Top resid features:
cells
Token cells
Feature activation+0.092
Top resid features:
are
Token are
Feature activation-0.032
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.05

Head 2: 0.01

Head 3: 0.41

Head 4: 0.09

Head 5: 0.04

Head 6: 0.04

Head 7: 0.02

Head 8: 0.15

Head 9: 0.06

Head 10: 0.02

Head 11: 0.02

Positive logits

sidx2.26

Exc1.98

otonin1.96

1.96

icidal1.90

��1.87

Charges1.87

reacted1.83

Enlarge1.80

Were1.78

Oracle1.74

deceive1.74

aughed1.73

ertodd1.73

Imp1.73

avascript1.73

finger1.72

udicrous1.72

screams1.72

Exception1.71

Negative logits

Berm-2.20

Mongolia-2.20

backstage-2.08

Ukrain-2.06

Ribbon-2.04

Westminster-2.02

onstage-2.00

Guantanamo-1.98

mats-1.93

elsewhere-1.92

laun-1.90

Aberdeen-1.90

canvas-1.88

tabletop-1.87

worldwide-1.86

Helsinki-1.84

henko-1.84

Okinawa-1.83

battleground-1.82

enegger-1.82

INTERVAL 1.481 - 1.646
CONTAINS 0.000%

standard
Token standard
Feature activation+0.000
cos
Token cos
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ological
Tokenological
Feature activation+0.000
model
Token model
Feature activation+0.268
that
Token that
Feature activation+1.566
we
Token we
Feature activation+0.755
don
Token don
Feature activation+0.427
't
Token't
Feature activation+0.467
understand
Token understand
Feature activation+0.110
,"
Token,"
Feature activation+0.000
any
Token any
Feature activation+0.000
band
Token band
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
district
Token district
Feature activation+0.450
that
Token that
Feature activation+1.646
had
Token had
Feature activation+0.983
applied
Token applied
Feature activation+0.171
to
Token to
Feature activation+0.000
participate
Token participate
Feature activation+0.079
in
Token in
Feature activation+0.000

INTERVAL 1.317 - 1.481
CONTAINS 0.001%

figure
Token figure
Feature activation+0.000
out
Token out
Feature activation+0.000
where
Token where
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
space
Token space
Feature activation+1.425
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
supposed
Token supposed
Feature activation+0.000
bacteria
Token bacteria
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
fungus
Token fungus
Feature activation+0.000
gardens
Token gardens
Feature activation+0.667
that
Token that
Feature activation+1.460
are
Token are
Feature activation+1.420
capable
Token capable
Feature activation+0.163
of
Token of
Feature activation+0.516
breaking
Token breaking
Feature activation+0.000
down
Token down
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
fungus
Token fungus
Feature activation+0.000
gardens
Token gardens
Feature activation+0.667
that
Token that
Feature activation+1.460
are
Token are
Feature activation+1.420
capable
Token capable
Feature activation+0.163
of
Token of
Feature activation+0.516
breaking
Token breaking
Feature activation+0.000
down
Token down
Feature activation+0.000
cellul
Token cellul
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
in
Token in
Feature activation+0.000
life
Token life
Feature activation+0.038
that
Token that
Feature activation+1.378
is
Token is
Feature activation+0.870
certain
Token certain
Feature activation+0.240
,"
Token,"
Feature activation+0.000
Joe
Token Joe
Feature activation+0.000
shared
Token shared
Feature activation+0.000
service
Token service
Feature activation+0.000
bots
Token bots
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
place
Token place
Feature activation+0.143
that
Token that
Feature activation+1.322
will
Token will
Feature activation+0.291
...
Token...
Feature activation+0.000
a
Token a
Feature activation+0.000
hm
Tokenhm
Feature activation+0.000
...
Token...
Feature activation+0.000

INTERVAL 1.152 - 1.317
CONTAINS 0.001%

Part
Token Part
Feature activation+0.000
icles
Tokenicles
Feature activation+0.000
suspended
Token suspended
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
water
Token water
Feature activation+1.174
bumped
Token bumped
Feature activation+0.491
the
Token the
Feature activation+0.069
laser
Token laser
Feature activation+0.000
light
Token light
Feature activation+0.000
and
Token and
Feature activation+0.000
top
Token top
Feature activation+0.018
of
Token of
Feature activation+0.432
the
Token the
Feature activation+0.000
jelly
Token jelly
Feature activation+0.000
fish
Token fish
Feature activation+0.000
created
Token created
Feature activation+1.179
by
Token by
Feature activation+0.540
its
Token its
Feature activation+0.000
gon
Token gon
Feature activation+0.000
ads
Tokenads
Feature activation+0.000
which
Token which
Feature activation+0.647
seeing
Token seeing
Feature activation+0.000
pressures
Token pressures
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
system
Token system
Feature activation+0.319
that
Token that
Feature activation+1.270
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
never
Token never
Feature activation+0.000
experienced
Token experienced
Feature activation+0.000
before
Token before
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
of
Token of
Feature activation+0.000
Philadelphia
Token Philadelphia
Feature activation+0.000
that
Token that
Feature activation+1.175
operate
Token operate
Feature activation+0.000
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000
same
Token same
Feature activation+0.000
neighborhoods
Token neighborhoods
Feature activation+0.000
only
Token only
Feature activation+0.000
graphic
Token graphic
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.031
presentation
Token presentation
Feature activation+0.521
in
Token in
Feature activation+1.210
Metro
Token Metro
Feature activation+0.000
lin
Tokenlin
Feature activation+0.000
x
Tokenx
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 0.988 - 1.152
CONTAINS 0.001%

into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.056
registry
Token registry
Feature activation+0.000
in
Token in
Feature activation+0.397
order
Token order
Feature activation+0.597
to
Token to
Feature activation+1.096
download
Token download
Feature activation+0.065
Meter
Token Meter
Feature activation+0.000
pret
Tokenpret
Feature activation+0.000
or
Tokenor
Feature activation+0.000
and
Token and
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Koran
Token Koran
Feature activation+1.114
saying
Token saying
Feature activation+0.674
women
Token women
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
play
Token play
Feature activation+0.000
a
Token a
Feature activation+0.000
thing
Token thing
Feature activation+0.000
inside
Token inside
Feature activation+0.147
our
Token our
Feature activation+0.000
skulls
Token skulls
Feature activation+0.683
is
Token is
Feature activation+0.970
even
Token even
Feature activation+1.040
more
Token more
Feature activation+0.397
complicated
Token complicated
Feature activation+0.557
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.000
looks
Token looks
Feature activation+0.000
"
Token "
Feature activation+0.000
sub
Tokensub
Feature activation+0.000
so
Tokenso
Feature activation+0.000
il
Tokenil
Feature activation+0.527
"
Token"
Feature activation+0.099
is
Token is
Feature activation+1.026
more
Token more
Feature activation+0.662
stable
Token stable
Feature activation+0.417
to
Token to
Feature activation+0.000
warming
Token warming
Feature activation+0.000
than
Token than
Feature activation+0.000
standard
Token standard
Feature activation+0.000
model
Token model
Feature activation+0.000
of
Token of
Feature activation+0.000
particle
Token particle
Feature activation+0.000
physics
Token physics
Feature activation+0.000
has
Token has
Feature activation+1.113
to
Token to
Feature activation+0.679
change
Token change
Feature activation+0.449
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.823 - 0.988
CONTAINS 0.003%

spew
Token spew
Feature activation+0.000
ed
Tokened
Feature activation+0.000
on
Token on
Feature activation+0.159
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.081
were
Token were
Feature activation+0.899
unimaginable
Token unimaginable
Feature activation+0.233
.
Token.
Feature activation+0.000
Though
Token Though
Feature activation+0.000
the
Token the
Feature activation+0.000
comments
Token comments
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
chip
Token chip
Feature activation+0.000
inside
Token inside
Feature activation+0.459
it
Token it
Feature activation+0.876
will
Token will
Feature activation+0.927
still
Token still
Feature activation+0.164
work
Token work
Feature activation+0.668
.
Token.
Feature activation+0.000
Problem
Token Problem
Feature activation+0.000
ishy
Tokenishy
Feature activation+0.000
thing
Token thing
Feature activation+0.000
inside
Token inside
Feature activation+0.147
our
Token our
Feature activation+0.000
skulls
Token skulls
Feature activation+0.683
is
Token is
Feature activation+0.970
even
Token even
Feature activation+1.040
more
Token more
Feature activation+0.397
complicated
Token complicated
Feature activation+0.557
than
Token than
Feature activation+0.000
it
Token it
Feature activation+0.000
second
Token second
Feature activation+0.000
card
Token card
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
pack
Token pack
Feature activation+0.000
is
Token is
Feature activation+0.828
absent
Token absent
Feature activation+0.491
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
plugins
Token plugins
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.290
menu
Token menu
Feature activation+0.000
must
Token must
Feature activation+0.617
be
Token be
Feature activation+0.845
better
Token better
Feature activation+0.403
.
Token.
Feature activation+0.000
Remember
Token Remember
Feature activation+0.000
that
Token that
Feature activation+0.000
sometimes
Token sometimes
Feature activation+0.000

INTERVAL 0.658 - 0.823
CONTAINS 0.005%

information
Token information
Feature activation+0.000
out
Token out
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.211
to
Token to
Feature activation+0.712
reach
Token reach
Feature activation+0.407
conscious
Token conscious
Feature activation+0.000
awareness
Token awareness
Feature activation+0.000
:
Token:
Feature activation+0.000
Because
Token Because
Feature activation+0.000
scene
Token scene
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
movie
Token movie
Feature activation+0.611
that
Token that
Feature activation+0.549
was
Token was
Feature activation+0.669
downright
Token downright
Feature activation+0.308
disturbing
Token disturbing
Feature activation+0.152
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
.
Token.
Feature activation+0.000
model
Token model
Feature activation+0.000
of
Token of
Feature activation+0.000
particle
Token particle
Feature activation+0.000
physics
Token physics
Feature activation+0.000
has
Token has
Feature activation+1.113
to
Token to
Feature activation+0.679
change
Token change
Feature activation+0.449
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
the
Token the
Feature activation+0.000
baskets
Token baskets
Feature activation+0.000
it
Token it
Feature activation+0.000
rests
Token rests
Feature activation+0.004
in
Token in
Feature activation+0.065
are
Token are
Feature activation+0.736
strong
Token strong
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
structure
Token structure
Feature activation+0.000
achieves
Token achieves
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
people
Token people
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
audience
Token audience
Feature activation+0.691
b
Token b
Feature activation+0.000
owing
Tokenowing
Feature activation+0.000
their
Token their
Feature activation+0.000
heads
Token heads
Feature activation+0.000
:
Token:
Feature activation+0.000

INTERVAL 0.494 - 0.658
CONTAINS 0.012%

the
Token the
Feature activation+0.000
sentiment
Token sentiment
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
ground
Token ground
Feature activation+0.000
is
Token is
Feature activation+0.530
not
Token not
Feature activation+0.180
matching
Token matching
Feature activation+0.000
what
Token what
Feature activation+0.000
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
statute
Token statute
Feature activation+0.519
required
Token required
Feature activation+0.599
movement
Token movement
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
word
Token word
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
when
Token when
Feature activation+0.000
a
Token a
Feature activation+0.000
script
Token script
Feature activation+0.000
on
Token on
Feature activation+0.008
their
Token their
Feature activation+0.000
desks
Token desks
Feature activation+0.510
contain
Token contain
Feature activation+0.294
a
Token a
Feature activation+0.503
slur
Token slur
Feature activation+0.153
,
Token,
Feature activation+0.000
reports
Token reports
Feature activation+0.000
by
Token by
Feature activation+0.540
its
Token its
Feature activation+0.000
gon
Token gon
Feature activation+0.000
ads
Tokenads
Feature activation+0.000
which
Token which
Feature activation+0.647
are
Token are
Feature activation+0.634
visible
Token visible
Feature activation+0.462
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
transparent
Token transparent
Feature activation+0.000
bell
Token bell
Feature activation+0.000
structures
Token structures
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
sl
Token sl
Feature activation+0.000
ums
Tokenums
Feature activation+0.834
will
Token will
Feature activation+0.523
be
Token be
Feature activation+0.282
removed
Token removed
Feature activation+0.271
by
Token by
Feature activation+0.000
10
Token 10
Feature activation+0.000
bulldo
Token bulldo
Feature activation+0.000

INTERVAL 0.329 - 0.494
CONTAINS 0.025%

modules
Token modules
Feature activation+0.000
sold
Token sold
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
market
Token market
Feature activation+0.017
are
Token are
Feature activation+0.485
meant
Token meant
Feature activation+0.057
to
Token to
Feature activation+0.019
be
Token be
Feature activation+0.000
used
Token used
Feature activation+0.000
with
Token with
Feature activation+0.000
receptors
Token receptors
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
surfaces
Token surfaces
Feature activation+0.291
of
Token of
Feature activation+0.000
cells
Token cells
Feature activation+0.381
are
Token are
Feature activation+1.052
organized
Token organized
Feature activation+0.327
like
Token like
Feature activation+0.000
this
Token this
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Y
Token Y
Feature activation+0.000
onge
Tokenonge
Feature activation+0.000
subway
Token subway
Feature activation+0.000
line
Token line
Feature activation+0.000
will
Token will
Feature activation+0.349
be
Token be
Feature activation+0.115
over
Token over
Feature activation+0.000
capacity
Tokencapacity
Feature activation+0.000
by
Token by
Feature activation+0.000
20
Token 20
Feature activation+0.000
"
Token "
Feature activation+0.000
def
Tokendef
Feature activation+0.000
eat
Tokeneat
Feature activation+0.000
devices
Token devices
Feature activation+0.000
"
Token"
Feature activation+0.000
were
Token were
Feature activation+0.336
registered
Token registered
Feature activation+0.000
in
Token in
Feature activation+0.000
London
Token London
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
roster
Token roster
Feature activation+0.143
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
area
Token area
Feature activation+0.078
to
Token to
Feature activation+0.464
start
Token start
Feature activation+0.000
challenging
Token challenging
Feature activation+0.000
for
Token for
Feature activation+0.000
trophies
Token trophies
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.165 - 0.329
CONTAINS 0.060%

powder
Token powder
Feature activation+0.000
that
Token that
Feature activation+0.000
stick
Token stick
Feature activation+0.000
to
Token to
Feature activation+0.108
their
Token their
Feature activation+0.000
limbs
Token limbs
Feature activation+0.192
can
Token can
Feature activation+0.325
leap
Token leap
Feature activation+0.000
down
Token down
Feature activation+0.000
and
Token and
Feature activation+0.000
start
Token start
Feature activation+0.000
-
Token-
Feature activation+0.000
San
TokenSan
Feature activation+0.000
Jose
Token Jose
Feature activation+0.000
urban
Token urban
Feature activation+0.000
areas
Token areas
Feature activation+0.263
have
Token have
Feature activation+0.265
already
Token already
Feature activation+0.225
grown
Token grown
Feature activation+0.000
by
Token by
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
60
Token 60
Feature activation+0.000
happened
Token happened
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
10
Token 10
Feature activation+0.000
minutes
Token minutes
Feature activation+0.683
I
Token I
Feature activation+0.165
was
Token was
Feature activation+0.000
gone
Token gone
Feature activation+0.000
?
Token?
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
element
Token element
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
array
Token array
Feature activation+0.000
appears
Token appears
Feature activation+0.471
to
Token to
Feature activation+0.181
be
Token be
Feature activation+0.132
null
Token null
Feature activation+0.000
,
Token ,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
columns
Token columns
Feature activation+0.000
on
Token on
Feature activation+0.080
one
Token one
Feature activation+0.000
side
Token side
Feature activation+0.000
could
Token could
Feature activation+0.195
be
Token be
Feature activation+0.219
cut
Token cut
Feature activation+0.000
,
Token,
Feature activation+0.000
along
Token along
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.165
CONTAINS 99.892%

Great
Token Great
Feature activation+0.000
Leap
Token Leap
Feature activation+0.000
Forward
Token Forward
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
thought
Token thought
Feature activation+0.000
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
could
Token could
Feature activation+0.000
accomplish
Token accomplish
Feature activation+0.000
anything
Token anything
Feature activation+0.000
get
Token get
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Stay
TokenStay
Feature activation+0.000
Tun
Token Tun
Feature activation+0.000
ed
Tokened
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
as
Token as
Feature activation+0.000
shotgun
Token shotgun
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
FBI
Token FBI
Feature activation+0.000
told
Token told
Feature activation+0.000
us
Token us
Feature activation+0.000
the
Token the
Feature activation+0.000
ban
Token ban
Feature activation+0.000
had
Token had
Feature activation+0.000
on
Token on
Feature activation+0.000
spending
Token spending
Feature activation+0.000
,
Token,
Feature activation+0.000
resulting
Token resulting
Feature activation+0.000
in
Token in
Feature activation+0.000
more
Token more
Feature activation+0.000
layoffs
Token layoffs
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
in
Token in
Feature activation+0.000
turn
Token turn
Feature activation+0.000
:
Token:
Feature activation+0.000
Not
Token Not
Feature activation+0.000
Just
Token Just
Feature activation+0.000
Religious
Token Religious
Feature activation+0.000
Music
Token Music
Feature activation+0.000
(
Token (
Feature activation+0.000
United
TokenUnited
Feature activation+0.000
States
Token States
Feature activation+0.000
)
Token)
Feature activation+0.000
/
Token /
Feature activation+0.000
NJ
Token NJ
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