H2.10 top features

Top feature 0 in H2.10: (feature 5121)

TOP ACTIVATIONS
MAX = 0.831

is
Token is
Feature activation+0.000
only
Token only
Feature activation+0.180
once
Token once
Feature activation+0.436
they
Token they
Feature activation+0.586
lost
Token lost
Feature activation+0.445
access
Token access
Feature activation+0.775
to
Token to
Feature activation+0.776
land
Token land
Feature activation+0.720
through
Token through
Feature activation+0.524
encl
Token encl
Feature activation+0.759
osures
Tokenosures
Feature activation+0.717
.
Token.
Feature activation+0.069
The
Token The
Feature activation+0.000
ash
Token ash
Feature activation+0.060
seemed
Token seemed
Feature activation+0.321
to
Token to
Feature activation+0.642
be
Token be
Feature activation+0.752
moving
Token moving
Feature activation+0.693
toward
Token toward
Feature activation+0.708
him
Token him
Feature activation+0.806
.
Token.
Feature activation+0.386
Downtown
Token Downtown
Feature activation+0.234
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+0.000
lethal
Token lethal
Feature activation+0.000
bite
Token bite
Feature activation+0.155
caused
Token caused
Feature activation+0.414
crew
Token crew
Feature activation+0.746
man
Tokenman
Feature activation+0.552
to
Token to
Feature activation+0.556
die
Token die
Feature activation+0.500
suddenly
Token suddenly
Feature activation+0.623
,
Token,
Feature activation+0.272
way
Token way
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
could
Token could
Feature activation+0.048
rise
Token rise
Feature activation+0.315
through
Token through
Feature activation+0.713
the
Token the
Feature activation+0.543
ranks
Token ranks
Feature activation+0.403
,
Token,
Feature activation+0.214
but
Token but
Feature activation+0.083
because
Token because
Feature activation+0.021
inspectors
Token inspectors
Feature activation+0.000
will
Token will
Feature activation+0.172
be
Token be
Feature activation+0.302
out
Token out
Feature activation+0.444
sourced
Token sourced
Feature activation+0.580
as
Token as
Feature activation+0.712
will
Token will
Feature activation+0.658
city
Token city
Feature activation+0.484
plan
Token plan
Feature activation+0.594
check
Token check
Feature activation+0.579
ers
Tokeners
Feature activation+0.608
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
asked
Token asked
Feature activation+0.000
him
Token him
Feature activation+0.369
whom
Token whom
Feature activation+0.555
he
Token he
Feature activation+0.710
will
Token will
Feature activation+0.537
cast
Token cast
Feature activation+0.492
if
Token if
Feature activation+0.500
she
Token she
Feature activation+0.418
denies
Token denies
Feature activation+0.385
.
Token.
Feature activation+0.000
FDR
Token FDR
Feature activation+0.000
was
Token was
Feature activation+0.138
measured
Token measured
Feature activation+0.214
by
Token by
Feature activation+0.651
two
Token two
Feature activation+0.708
scales
Token scales
Feature activation+0.618
:
Token:
Feature activation+0.416
harsh
Token harsh
Feature activation+0.418
-
Token-
Feature activation+0.417
co
Tokenco
Feature activation+0.417
Opp
Token Opp
Feature activation+0.000
onents
Tokenonents
Feature activation+0.000
can
Token can
Feature activation+0.063
easily
Token easily
Feature activation+0.342
whip
Token whip
Feature activation+0.488
up
Token up
Feature activation+0.684
fears
Token fears
Feature activation+0.530
about
Token about
Feature activation+0.550
grid
Token grid
Feature activation+0.477
out
Token out
Feature activation+0.440
ages
Tokenages
Feature activation+0.314
audience
Token audience
Feature activation+0.000
are
Token are
Feature activation+0.139
people
Token people
Feature activation+0.245
who
Token who
Feature activation+0.282
feel
Token feel
Feature activation+0.449
like
Token like
Feature activation+0.677
outsiders
Token outsiders
Feature activation+0.674
trying
Token trying
Feature activation+0.345
to
Token to
Feature activation+0.274
become
Token become
Feature activation+0.262
Dan
Token Dan
Feature activation+0.228
are
Token are
Feature activation+0.139
people
Token people
Feature activation+0.245
who
Token who
Feature activation+0.282
feel
Token feel
Feature activation+0.449
like
Token like
Feature activation+0.677
outsiders
Token outsiders
Feature activation+0.674
trying
Token trying
Feature activation+0.345
to
Token to
Feature activation+0.274
become
Token become
Feature activation+0.262
Dan
Token Dan
Feature activation+0.228
Harmon
Token Harmon
Feature activation+0.151
.
Token.
Feature activation+0.000
Epstein
Token Epstein
Feature activation+0.000
was
Token was
Feature activation+0.000
convicted
Token convicted
Feature activation+0.083
on
Token on
Feature activation+0.572
relatively
Token relatively
Feature activation+0.673
minor
Token minor
Feature activation+0.638
state
Token state
Feature activation+0.532
charges
Token charges
Feature activation+0.462
and
Token and
Feature activation+0.309
served
Token served
Feature activation+0.247
experience
Token experience
Feature activation+0.067
.
Token.
Feature activation+0.051
Theory
Token Theory
Feature activation+0.049
has
Token has
Feature activation+0.314
become
Token become
Feature activation+0.517
practice
Token practice
Feature activation+0.672
.
Token.
Feature activation+0.389
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
how
Token how
Feature activation+0.000
crystals
Token crystals
Feature activation+0.294
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.056
's
Token's
Feature activation+0.087
labelled
Token labelled
Feature activation+0.340
as
Token as
Feature activation+0.666
a
Token a
Feature activation+0.587
rare
Token rare
Feature activation+0.637
cartel
Token cartel
Feature activation+0.624
market
Token market
Feature activation+0.523
item
Token item
Feature activation+0.582
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
also
Token also
Feature activation+0.130
try
Token try
Feature activation+0.273
looking
Token looking
Feature activation+0.492
for
Token for
Feature activation+0.664
Pokémon
Token Pokémon
Feature activation+0.563
near
Token near
Feature activation+0.462
sources
Token sources
Feature activation+0.499
of
Token of
Feature activation+0.380
water
Token water
Feature activation+0.422
will
Token will
Feature activation+0.172
be
Token be
Feature activation+0.302
out
Token out
Feature activation+0.444
sourced
Token sourced
Feature activation+0.580
as
Token as
Feature activation+0.712
will
Token will
Feature activation+0.658
city
Token city
Feature activation+0.484
plan
Token plan
Feature activation+0.594
check
Token check
Feature activation+0.579
ers
Tokeners
Feature activation+0.608
,
Token,
Feature activation+0.348
CS
Token CS
Feature activation+0.000
KA
TokenKA
Feature activation+0.090
have
Token have
Feature activation+0.195
him
Token him
Feature activation+0.501
under
Token under
Feature activation+0.530
contract
Token contract
Feature activation+0.655
until
Token until
Feature activation+0.655
2018
Token 2018
Feature activation+0.428
so
Token so
Feature activation+0.421
they
Token they
Feature activation+0.452
do
Token do
Feature activation+0.399
KA
TokenKA
Feature activation+0.090
have
Token have
Feature activation+0.195
him
Token him
Feature activation+0.501
under
Token under
Feature activation+0.530
contract
Token contract
Feature activation+0.655
until
Token until
Feature activation+0.655
2018
Token 2018
Feature activation+0.428
so
Token so
Feature activation+0.421
they
Token they
Feature activation+0.452
do
Token do
Feature activation+0.399
not
Token not
Feature activation+0.298
turns
Token turns
Feature activation+0.109
his
Token his
Feature activation+0.384
head
Token head
Feature activation+0.413
to
Token to
Feature activation+0.625
locate
Token locate
Feature activation+0.640
the
Token the
Feature activation+0.651
ball
Token ball
Feature activation+0.483
while
Token while
Feature activation+0.517
keeping
Token keeping
Feature activation+0.322
a
Token a
Feature activation+0.202
hand
Token hand
Feature activation+0.052
adolescence
Token adolescence
Feature activation+0.000
.
Token.
Feature activation+0.000
FDR
Token FDR
Feature activation+0.000
was
Token was
Feature activation+0.138
measured
Token measured
Feature activation+0.214
by
Token by
Feature activation+0.651
two
Token two
Feature activation+0.708
scales
Token scales
Feature activation+0.618
:
Token:
Feature activation+0.416
harsh
Token harsh
Feature activation+0.418
-
Token-
Feature activation+0.417
They
Token They
Feature activation+0.000
said
Token said
Feature activation+0.049
there
Token there
Feature activation+0.532
were
Token were
Feature activation+0.639
weapons
Token weapons
Feature activation+0.601
of
Token of
Feature activation+0.643
mass
Token mass
Feature activation+0.689
destruction
Token destruction
Feature activation+0.620
,
Token,
Feature activation+0.442
there
Token there
Feature activation+0.384
were
Token were
Feature activation+0.168

Top DFA by src position
MAX = 0.277

It
Token It
Feature activation+0.085
Top resid features:
is
Token is
Feature activation+0.060
Top resid features:
only
Token only
Feature activation+0.024
Top resid features:
once
Token once
Feature activation+0.025
Top resid features:
they
Token they
Feature activation-0.021
Top resid features:
lost
Token lost
Feature activation+0.140
Top resid features:
access
Token access
Feature activation+0.036
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
land
Token land
Feature activation+0.000
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
encl
Token encl
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.012
Top resid features:
ash
Token ash
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
The
Token The
Feature activation-0.087
Top resid features:
ash
Token ash
Feature activation+0.024
Top resid features:
seemed
Token seemed
Feature activation+0.215
Top resid features:
to
Token to
Feature activation+0.118
Top resid features:
be
Token be
Feature activation+0.037
Top resid features:
moving
Token moving
Feature activation+0.000
Top resid features:
toward
Token toward
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
banana
Token banana
Feature activation-0.003
Top resid features:
bun
Token bun
Feature activation-0.006
Top resid features:
ches
Tokenches
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.087
Top resid features:
Their
Token Their
Feature activation+0.077
Top resid features:
lethal
Token lethal
Feature activation+0.116
Top resid features:
bite
Token bite
Feature activation+0.038
Top resid features:
caused
Token caused
Feature activation+0.074
Top resid features:
crew
Token crew
Feature activation+0.033
Top resid features:
man
Tokenman
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
This
Token This
Feature activation+0.051
Top resid features:
way
Token way
Feature activation+0.002
Top resid features:
a
Token a
Feature activation-0.041
Top resid features:
man
Token man
Feature activation-0.033
Top resid features:
could
Token could
Feature activation+0.085
Top resid features:
rise
Token rise
Feature activation+0.191
Top resid features:
through
Token through
Feature activation+0.115
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
ranks
Token ranks
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
unsustainable
Token unsustainable
Feature activation-0.006
Top resid features:
pensions
Token pensions
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.113
Top resid features:
Building
Token Building
Feature activation+0.048
Top resid features:
inspectors
Token inspectors
Feature activation+0.050
Top resid features:
will
Token will
Feature activation+0.136
Top resid features:
be
Token be
Feature activation+0.053
Top resid features:
out
Token out
Feature activation+0.065
Top resid features:
sourced
Token sourced
Feature activation+0.025
Top resid features:
as
Token as
Feature activation+0.022
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.007
Top resid features:
brief
Token brief
Feature activation-0.011
Top resid features:
flashback
Token flashback
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.110
Top resid features:
She
Token She
Feature activation+0.124
Top resid features:
asked
Token asked
Feature activation+0.277
Top resid features:
him
Token him
Feature activation+0.080
Top resid features:
whom
Token whom
Feature activation-0.156
Top resid features:
he
Token he
Feature activation+0.020
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
cast
Token cast
Feature activation+0.000
Top resid features:
fathers
Token fathers
Feature activation+0.019
Top resid features:
during
Token during
Feature activation+0.015
Top resid features:
adolescence
Token adolescence
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.117
Top resid features:
FDR
Token FDR
Feature activation+0.012
Top resid features:
was
Token was
Feature activation+0.127
Top resid features:
measured
Token measured
Feature activation+0.054
Top resid features:
by
Token by
Feature activation+0.088
Top resid features:
two
Token two
Feature activation+0.017
Top resid features:
scales
Token scales
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
phased
Token phased
Feature activation+0.021
Top resid features:
out
Token out
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.050
Top resid features:
Opp
Token Opp
Feature activation+0.016
Top resid features:
onents
Tokenonents
Feature activation-0.022
Top resid features:
can
Token can
Feature activation+0.122
Top resid features:
easily
Token easily
Feature activation+0.085
Top resid features:
whip
Token whip
Feature activation-0.008
Top resid features:
up
Token up
Feature activation+0.115
Top resid features:
fears
Token fears
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.009
Top resid features:
make
Token make
Feature activation-0.010
Top resid features:
his
Token his
Feature activation+0.001
Top resid features:
money
Token money
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.122
Top resid features:
His
Token His
Feature activation+0.064
Top resid features:
audience
Token audience
Feature activation+0.027
Top resid features:
are
Token are
Feature activation+0.114
Top resid features:
people
Token people
Feature activation-0.008
Top resid features:
who
Token who
Feature activation-0.074
Top resid features:
audience
Token audience
Feature activation+0.020
Top resid features:
are
Token are
Feature activation+0.080
Top resid features:
people
Token people
Feature activation+0.039
Top resid features:
who
Token who
Feature activation-0.014
Top resid features:
feel
Token feel
Feature activation+0.030
Top resid features:
like
Token like
Feature activation+0.122
Top resid features:
outsiders
Token outsiders
Feature activation-0.067
Top resid features:
trying
Token trying
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
become
Token become
Feature activation+0.000
Top resid features:
Dan
Token Dan
Feature activation+0.000
Top resid features:
underage
Token underage
Feature activation-0.001
Top resid features:
girls
Token girls
Feature activation-0.010
Top resid features:
.
Token.
Feature activation+0.099
Top resid features:
Epstein
Token Epstein
Feature activation+0.023
Top resid features:
was
Token was
Feature activation+0.111
Top resid features:
convicted
Token convicted
Feature activation+0.125
Top resid features:
on
Token on
Feature activation+0.108
Top resid features:
relatively
Token relatively
Feature activation-0.016
Top resid features:
minor
Token minor
Feature activation+0.000
Top resid features:
state
Token state
Feature activation+0.000
Top resid features:
charges
Token charges
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.009
Top resid features:
authentic
Token authentic
Feature activation+0.018
Top resid features:
experience
Token experience
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Theory
Token Theory
Feature activation-0.002
Top resid features:
has
Token has
Feature activation+0.102
Top resid features:
become
Token become
Feature activation+0.030
Top resid features:
practice
Token practice
Feature activation+0.061
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:
crystals
Token crystals
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
It
Token It
Feature activation+0.035
Top resid features:
's
Token's
Feature activation+0.041
Top resid features:
labelled
Token labelled
Feature activation-0.051
Top resid features:
as
Token as
Feature activation+0.219
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
rare
Token rare
Feature activation+0.000
Top resid features:
cartel
Token cartel
Feature activation+0.000
Top resid features:
market
Token market
Feature activation+0.000
Top resid features:
item
Token item
Feature activation+0.000
Top resid features:
You
Token You
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.100
Top resid features:
also
Token also
Feature activation+0.038
Top resid features:
try
Token try
Feature activation+0.082
Top resid features:
looking
Token looking
Feature activation+0.033
Top resid features:
for
Token for
Feature activation+0.137
Top resid features:
Pokémon
Token Pokémon
Feature activation+0.000
Top resid features:
near
Token near
Feature activation+0.000
Top resid features:
sources
Token sources
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
water
Token water
Feature activation+0.000
Top resid features:
unsustainable
Token unsustainable
Feature activation-0.007
Top resid features:
pensions
Token pensions
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.058
Top resid features:
Building
Token Building
Feature activation+0.042
Top resid features:
inspectors
Token inspectors
Feature activation+0.039
Top resid features:
will
Token will
Feature activation+0.104
Top resid features:
be
Token be
Feature activation+0.086
Top resid features:
out
Token out
Feature activation+0.073
Top resid features:
sourced
Token sourced
Feature activation+0.076
Top resid features:
as
Token as
Feature activation-0.105
Top resid features:
will
Token will
Feature activation+0.002
Top resid features:
both
Token both
Feature activation+0.006
Top resid features:
,
Token,
Feature activation-0.041
Top resid features:
making
Token making
Feature activation+0.003
Top resid features:
him
Token him
Feature activation+0.024
Top resid features:
ideal
Token ideal
Feature activation-0.018
Top resid features:
.
Token.
Feature activation+0.160
Top resid features:
CS
Token CS
Feature activation+0.003
Top resid features:
KA
TokenKA
Feature activation-0.024
Top resid features:
have
Token have
Feature activation+0.086
Top resid features:
him
Token him
Feature activation+0.024
Top resid features:
under
Token under
Feature activation+0.109
Top resid features:
both
Token both
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.020
Top resid features:
making
Token making
Feature activation-0.005
Top resid features:
him
Token him
Feature activation+0.026
Top resid features:
ideal
Token ideal
Feature activation-0.019
Top resid features:
.
Token.
Feature activation+0.119
Top resid features:
CS
Token CS
Feature activation+0.031
Top resid features:
KA
TokenKA
Feature activation-0.007
Top resid features:
have
Token have
Feature activation+0.103
Top resid features:
him
Token him
Feature activation+0.059
Top resid features:
under
Token under
Feature activation+0.109
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
He
Token He
Feature activation+0.087
Top resid features:
turns
Token turns
Feature activation+0.097
Top resid features:
his
Token his
Feature activation+0.055
Top resid features:
head
Token head
Feature activation+0.025
Top resid features:
to
Token to
Feature activation+0.143
Top resid features:
locate
Token locate
Feature activation-0.047
Top resid features:
the
Token the
Feature activation-0.059
Top resid features:
ball
Token ball
Feature activation+0.000
Top resid features:
while
Token while
Feature activation+0.000
Top resid features:
keeping
Token keeping
Feature activation+0.000
Top resid features:
adolescence
Token adolescence
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.072
Top resid features:
FDR
Token FDR
Feature activation+0.028
Top resid features:
was
Token was
Feature activation+0.041
Top resid features:
measured
Token measured
Feature activation+0.043
Top resid features:
by
Token by
Feature activation+0.166
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
scales
Token scales
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
harsh
Token harsh
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.035
Top resid features:
They
Token They
Feature activation+0.046
Top resid features:
lied
Token lied
Feature activation+0.080
Top resid features:
.
Token.
Feature activation+0.064
Top resid features:
They
Token They
Feature activation+0.081
Top resid features:
said
Token said
Feature activation+0.106
Top resid features:
there
Token there
Feature activation+0.003
Top resid features:
were
Token were
Feature activation+0.080
Top resid features:
weapons
Token weapons
Feature activation-0.158
Top resid features:
of
Token of
Feature activation+0.095
Top resid features:
mass
Token mass
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.03

Head 2: 0.04

Head 3: 0.06

Head 4: 0.02

Head 5: 0.07

Head 6: 0.10

Head 7: 0.12

Head 8: 0.06

Head 9: 0.06

Head 10: 0.26

Head 11: 0.12

Positive logits

disob0.65

veter0.64

though0.63

-+-+0.63

Palest0.61

ItemLevel0.61

Pandora0.59

Lazarus0.59

mog0.59

Tact0.59

Mell0.58

Mayweather0.57

Ment0.56

Shap0.56

Rothschild0.56

Skull0.55

Mol0.55

—"0.55

Mahjong0.55

ecause0.55

Negative logits

onga-0.80

astered-0.75

enture-0.74

opsis-0.72

esian-0.71

cci-0.70

rame-0.70

artment-0.69

anse-0.69

-0.69

wic-0.67

ieu-0.66

reviewed-0.66

esse-0.66

billed-0.65

proclaimed-0.65

-0.64

anth-0.64

ibling-0.64

weeney-0.64

INTERVAL 0.748 - 0.831
CONTAINS 0.002%

.
Token.
Feature activation+0.069
The
Token The
Feature activation+0.000
ash
Token ash
Feature activation+0.060
seemed
Token seemed
Feature activation+0.321
to
Token to
Feature activation+0.642
be
Token be
Feature activation+0.752
moving
Token moving
Feature activation+0.693
toward
Token toward
Feature activation+0.708
him
Token him
Feature activation+0.806
.
Token.
Feature activation+0.386
Downtown
Token Downtown
Feature activation+0.234
is
Token is
Feature activation+0.000
only
Token only
Feature activation+0.180
once
Token once
Feature activation+0.436
they
Token they
Feature activation+0.586
lost
Token lost
Feature activation+0.445
access
Token access
Feature activation+0.775
to
Token to
Feature activation+0.776
land
Token land
Feature activation+0.720
through
Token through
Feature activation+0.524
encl
Token encl
Feature activation+0.759
osures
Tokenosures
Feature activation+0.717

INTERVAL 0.665 - 0.748
CONTAINS 0.005%

inspectors
Token inspectors
Feature activation+0.000
will
Token will
Feature activation+0.172
be
Token be
Feature activation+0.302
out
Token out
Feature activation+0.444
sourced
Token sourced
Feature activation+0.580
as
Token as
Feature activation+0.712
will
Token will
Feature activation+0.658
city
Token city
Feature activation+0.484
plan
Token plan
Feature activation+0.594
check
Token check
Feature activation+0.579
ers
Tokeners
Feature activation+0.608
are
Token are
Feature activation+0.139
people
Token people
Feature activation+0.245
who
Token who
Feature activation+0.282
feel
Token feel
Feature activation+0.449
like
Token like
Feature activation+0.677
outsiders
Token outsiders
Feature activation+0.674
trying
Token trying
Feature activation+0.345
to
Token to
Feature activation+0.274
become
Token become
Feature activation+0.262
Dan
Token Dan
Feature activation+0.228
Harmon
Token Harmon
Feature activation+0.151
Opp
Token Opp
Feature activation+0.000
onents
Tokenonents
Feature activation+0.000
can
Token can
Feature activation+0.063
easily
Token easily
Feature activation+0.342
whip
Token whip
Feature activation+0.488
up
Token up
Feature activation+0.684
fears
Token fears
Feature activation+0.530
about
Token about
Feature activation+0.550
grid
Token grid
Feature activation+0.477
out
Token out
Feature activation+0.440
ages
Tokenages
Feature activation+0.314
crystals
Token crystals
Feature activation+0.294
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.056
's
Token's
Feature activation+0.087
labelled
Token labelled
Feature activation+0.340
as
Token as
Feature activation+0.666
a
Token a
Feature activation+0.587
rare
Token rare
Feature activation+0.637
cartel
Token cartel
Feature activation+0.624
market
Token market
Feature activation+0.523
item
Token item
Feature activation+0.582
.
Token.
Feature activation+0.000
FDR
Token FDR
Feature activation+0.000
was
Token was
Feature activation+0.138
measured
Token measured
Feature activation+0.214
by
Token by
Feature activation+0.651
two
Token two
Feature activation+0.708
scales
Token scales
Feature activation+0.618
:
Token:
Feature activation+0.416
harsh
Token harsh
Feature activation+0.418
-
Token-
Feature activation+0.417
co
Tokenco
Feature activation+0.417

INTERVAL 0.582 - 0.665
CONTAINS 0.016%

permit
Token permit
Feature activation+0.000
regime
Token regime
Feature activation+0.000
was
Token was
Feature activation+0.194
formal
Token formal
Feature activation+0.296
ized
Tokenized
Feature activation+0.484
as
Token as
Feature activation+0.615
a
Token a
Feature activation+0.470
part
Token part
Feature activation+0.418
of
Token of
Feature activation+0.419
the
Token the
Feature activation+0.410
Oslo
Token Oslo
Feature activation+0.295
man
Token man
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
ashamed
Token ashamed
Feature activation+0.074
of
Token of
Feature activation+0.527
himself
Token himself
Feature activation+0.588
beyond
Token beyond
Feature activation+0.466
the
Token the
Feature activation+0.563
scope
Token scope
Feature activation+0.301
of
Token of
Feature activation+0.284
his
Token his
Feature activation+0.253
will
Token will
Feature activation+0.172
be
Token be
Feature activation+0.302
out
Token out
Feature activation+0.444
sourced
Token sourced
Feature activation+0.580
as
Token as
Feature activation+0.712
will
Token will
Feature activation+0.658
city
Token city
Feature activation+0.484
plan
Token plan
Feature activation+0.594
check
Token check
Feature activation+0.579
ers
Tokeners
Feature activation+0.608
,
Token,
Feature activation+0.348
orders
Token orders
Feature activation+0.000
must
Token must
Feature activation+0.178
be
Token be
Feature activation+0.369
shipped
Token shipped
Feature activation+0.453
overnight
Token overnight
Feature activation+0.610
via
Token via
Feature activation+0.615
UPS
Token UPS
Feature activation+0.497
or
Token or
Feature activation+0.379
F
Token F
Feature activation+0.215
ED
TokenED
Feature activation+0.217
EX
TokenEX
Feature activation+0.244
The
Token The
Feature activation+0.000
cover
Token cover
Feature activation+0.000
will
Token will
Feature activation+0.000
remain
Token remain
Feature activation+0.251
forward
Token forward
Feature activation+0.566
during
Token during
Feature activation+0.636
firing
Token firing
Feature activation+0.643
since
Token since
Feature activation+0.527
it
Token it
Feature activation+0.553
does
Token does
Feature activation+0.476
not
Token not
Feature activation+0.349

INTERVAL 0.499 - 0.582
CONTAINS 0.038%

The
Token The
Feature activation+0.000
decision
Token decision
Feature activation+0.000
arose
Token arose
Feature activation+0.029
from
Token from
Feature activation+0.436
cases
Token cases
Feature activation+0.529
in
Token in
Feature activation+0.517
Seattle
Token Seattle
Feature activation+0.324
,
Token,
Feature activation+0.319
Wash
Token Wash
Feature activation+0.026
.,
Token.,
Feature activation+0.237
and
Token and
Feature activation+0.163
bons
Tokenbons
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
spark
Token spark
Feature activation+0.151
ly
Tokenly
Feature activation+0.500
,
Token,
Feature activation+0.343
soft
Token soft
Feature activation+0.123
,
Token,
Feature activation+0.156
and
Token and
Feature activation+0.000
suff
Token suff
Feature activation+0.000
lethal
Token lethal
Feature activation+0.000
bite
Token bite
Feature activation+0.155
caused
Token caused
Feature activation+0.414
crew
Token crew
Feature activation+0.746
man
Tokenman
Feature activation+0.552
to
Token to
Feature activation+0.556
die
Token die
Feature activation+0.500
suddenly
Token suddenly
Feature activation+0.623
,
Token,
Feature activation+0.272
height
Token height
Feature activation+0.118
ening
Tokenening
Feature activation+0.175
reported
Token reported
Feature activation+0.023
that
Token that
Feature activation+0.302
she
Token she
Feature activation+0.356
had
Token had
Feature activation+0.412
been
Token been
Feature activation+0.478
filmed
Token filmed
Feature activation+0.512
,
Token,
Feature activation+0.372
and
Token and
Feature activation+0.124
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
assault
Token assault
Feature activation+0.000
felt
Token felt
Feature activation+0.000
he
Token he
Feature activation+0.355
was
Token was
Feature activation+0.503
already
Token already
Feature activation+0.402
stretched
Token stretched
Feature activation+0.450
with
Token with
Feature activation+0.525
3
Token 3
Feature activation+0.523
roles
Token roles
Feature activation+0.425
and
Token and
Feature activation+0.158
was
Token was
Feature activation+0.121
eventually
Token eventually
Feature activation+0.005

INTERVAL 0.416 - 0.499
CONTAINS 0.074%

Of
Token Of
Feature activation+0.000
Fame
Token Fame
Feature activation+0.000
case
Token case
Feature activation+0.078
was
Token was
Feature activation+0.226
over
Token over
Feature activation+0.230
before
Token before
Feature activation+0.417
it
Token it
Feature activation+0.574
ever
Token ever
Feature activation+0.331
started
Token started
Feature activation+0.298
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
is
Token is
Feature activation+0.137
stored
Token stored
Feature activation+0.299
as
Token as
Feature activation+0.350
data
Token data
Feature activation+0.477
which
Token which
Feature activation+0.400
is
Token is
Feature activation+0.438
retri
Token retri
Feature activation+0.323
ev
Tokenev
Feature activation+0.367
able
Tokenable
Feature activation+0.344
and
Token and
Feature activation+0.267
analys
Token analys
Feature activation+0.152
Jay
Token Jay
Feature activation+0.000
len
Tokenlen
Feature activation+0.000
has
Token has
Feature activation+0.019
played
Token played
Feature activation+0.303
well
Token well
Feature activation+0.484
at
Token at
Feature activation+0.441
safety
Token safety
Feature activation+0.353
for
Token for
Feature activation+0.414
us
Token us
Feature activation+0.235
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
They
TokenThey
Feature activation+0.000
were
Token were
Feature activation+0.000
able
Token able
Feature activation+0.041
to
Token to
Feature activation+0.416
come
Token come
Feature activation+0.366
in
Token in
Feature activation+0.480
early
Token early
Feature activation+0.506
on
Token on
Feature activation+0.545
with
Token with
Feature activation+0.373
people
Token people
Feature activation+0.144
would
Token would
Feature activation+0.297
take
Token take
Feature activation+0.437
a
Token a
Feature activation+0.405
chance
Token chance
Feature activation+0.416
on
Token on
Feature activation+0.485
dying
Token dying
Feature activation+0.553
to
Token to
Feature activation+0.509
escape
Token escape
Feature activation+0.441
the
Token the
Feature activation+0.408
never
Token never
Feature activation+0.278

INTERVAL 0.332 - 0.416
CONTAINS 0.130%

may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.117
important
Token important
Feature activation+0.181
to
Token to
Feature activation+0.303
future
Token future
Feature activation+0.318
Mars
Token Mars
Feature activation+0.392
explorers
Token explorers
Feature activation+0.276
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
surface
Token surface
Feature activation+0.000
of
Token of
Feature activation+0.000
rd
Tokenrd
Feature activation+0.000
District
Token District
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
will
Token will
Feature activation+0.006
go
Token go
Feature activation+0.170
ahead
Token ahead
Feature activation+0.333
with
Token with
Feature activation+0.431
their
Token their
Feature activation+0.354
candidates
Token candidates
Feature activation+0.284
'
Token'
Feature activation+0.279
forum
Token forum
Feature activation+0.218
And
Token And
Feature activation+0.000
it
Token it
Feature activation+0.000
likely
Token likely
Feature activation+0.000
will
Token will
Feature activation+0.043
be
Token be
Feature activation+0.034
for
Token for
Feature activation+0.387
some
Token some
Feature activation+0.392
time
Token time
Feature activation+0.390
.
Token.
Feature activation+0.000
Veget
Token Veget
Feature activation+0.000
arians
Tokenarians
Feature activation+0.127
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
collision
Token collision
Feature activation+0.000
remains
Token remains
Feature activation+0.000
under
Token under
Feature activation+0.172
investigation
Token investigation
Feature activation+0.350
.
Token.
Feature activation+0.007
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Reading
TokenReading
Feature activation+0.000
this
Token this
Feature activation+0.000
It
Token It
Feature activation+0.000
also
Token also
Feature activation+0.000
reported
Token reported
Feature activation+0.023
that
Token that
Feature activation+0.302
she
Token she
Feature activation+0.356
had
Token had
Feature activation+0.412
been
Token been
Feature activation+0.478
filmed
Token filmed
Feature activation+0.512
,
Token,
Feature activation+0.372
and
Token and
Feature activation+0.124
that
Token that
Feature activation+0.000

INTERVAL 0.249 - 0.332
CONTAINS 0.222%

.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
these
Token these
Feature activation+0.000
problems
Token problems
Feature activation+0.000
seem
Token seem
Feature activation+0.071
relatively
Token relatively
Feature activation+0.256
simple
Token simple
Feature activation+0.248
to
Token to
Feature activation+0.296
address
Token address
Feature activation+0.322
âĢĶ
Token âĢĶ
Feature activation+0.405
not
Token not
Feature activation+0.129
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
tom
Token tom
Feature activation+0.059
f
Tokenf
Feature activation+0.395
ool
Tokenool
Feature activation+0.342
ery
Tokenery
Feature activation+0.256
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.040
goes
Token goes
Feature activation+0.149
to
Token to
Feature activation+0.395
Outer
Token Outer
Feature activation+0.507
.
Token.
Feature activation+0.000
See
Token See
Feature activation+0.000
,
Token,
Feature activation+0.000
everybody
Token everybody
Feature activation+0.000
blames
Token blames
Feature activation+0.000
the
Token the
Feature activation+0.295
kids
Token kids
Feature activation+0.254
as
Token as
Feature activation+0.227
fucking
Token fucking
Feature activation+0.106
crazy
Token crazy
Feature activation+0.109
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
marks
Token marks
Feature activation+0.000
a
Token a
Feature activation+0.000
change
Token change
Feature activation+0.000
from
Token from
Feature activation+0.146
season
Token season
Feature activation+0.271
one
Token one
Feature activation+0.216
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
does
Token does
Feature activation+0.000
.
Token.
Feature activation+0.000
Everything
Token Everything
Feature activation+0.000
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
reverber
Token reverber
Feature activation+0.298
ates
Tokenates
Feature activation+0.450
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
doesn
Token doesn
Feature activation+0.024
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 0.166 - 0.249
CONTAINS 0.344%

We
TokenWe
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.043
ĺ
Tokenĺ
Feature activation+0.192
No
TokenNo
Feature activation+0.176
âĢ
TokenâĢ
Feature activation+0.148
Ļ
TokenĻ
Feature activation+0.063
to
Token to
Feature activation+0.156
a
Token a
Feature activation+0.037
nation
Token nation
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.002
think
Token think
Feature activation+0.000
about
Token about
Feature activation+0.176
commercial
Token commercial
Feature activation+0.222
attractiveness
Token attractiveness
Feature activation+0.193
,
Token,
Feature activation+0.000
how
Token how
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
Col
Token Col
Feature activation+0.000
ton
Tokenton
Feature activation+0.000
told
Token told
Feature activation+0.000
his
Token his
Feature activation+0.195
parents
Token parents
Feature activation+0.168
that
Token that
Feature activation+0.123
he
Token he
Feature activation+0.010
had
Token had
Feature activation+0.071
met
Token met
Feature activation+0.118
his
Token his
Feature activation+0.262
within
Token within
Feature activation+0.000
others
Token others
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
imagined
Token imagined
Feature activation+0.000
what
Token what
Feature activation+0.168
it
Token it
Feature activation+0.312
would
Token would
Feature activation+0.268
have
Token have
Feature activation+0.312
been
Token been
Feature activation+0.386
like
Token like
Feature activation+0.499
We
TokenWe
Feature activation+0.000
did
Token did
Feature activation+0.000
go
Token go
Feature activation+0.000
through
Token through
Feature activation+0.000
records
Token records
Feature activation+0.000
after
Token after
Feature activation+0.170
fingerprint
Token fingerprint
Feature activation+0.015
ing
Tokening
Feature activation+0.001
her
Token her
Feature activation+0.000
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000

INTERVAL 0.083 - 0.166
CONTAINS 0.504%

protecting
Token protecting
Feature activation+0.000
his
Token his
Feature activation+0.100
reputation
Token reputation
Feature activation+0.000
was
Token was
Feature activation+0.154
only
Token only
Feature activation+0.000
one
Token one
Feature activation+0.099
reason
Token reason
Feature activation+0.000
he
Token he
Feature activation+0.051
sued
Token sued
Feature activation+0.000
the
Token the
Feature activation+0.011
ABC
Token ABC
Feature activation+0.000
he
Token he
Feature activation+0.000
were
Token were
Feature activation+0.000
white
Token white
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
are
Token are
Feature activation+0.139
selfish
Token selfish
Feature activation+0.200
,
Token,
Feature activation+0.255
neuro
Token neuro
Feature activation+0.169
tic
Tokentic
Feature activation+0.148
thoughts
Token thoughts
Feature activation+0.274
voiced
Token voiced
Feature activation+0.000
doubts
Token doubts
Feature activation+0.353
that
Token that
Feature activation+0.288
technology
Token technology
Feature activation+0.158
would
Token would
Feature activation+0.228
be
Token be
Feature activation+0.166
able
Token able
Feature activation+0.152
to
Token to
Feature activation+0.336
revolution
Token revolution
Feature activation+0.276
ize
Tokenize
Feature activation+0.426
mineral
Token mineral
Feature activation+0.299
).
Token).
Feature activation+0.000
Then
Token Then
Feature activation+0.000
it
Token it
Feature activation+0.000
can
Token can
Feature activation+0.000
use
Token use
Feature activation+0.000
that
Token that
Feature activation+0.100
information
Token information
Feature activation+0.000
to
Token to
Feature activation+0.145
match
Token match
Feature activation+0.078
potential
Token potential
Feature activation+0.147
advertisers
Token advertisers
Feature activation+0.005
The
TokenThe
Feature activation+0.000
weights
Token weights
Feature activation+0.000
have
Token have
Feature activation+0.000
almost
Token almost
Feature activation+0.000
half
Token half
Feature activation+0.000
the
Token the
Feature activation+0.112
height
Token height
Feature activation+0.000
of
Token of
Feature activation+0.120
the
Token the
Feature activation+0.117
tower
Token tower
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.000 - 0.083
CONTAINS 98.664%

due
Tokendue
Feature activation+0.000
process
Token process
Feature activation+0.000
"
Token"
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
't
Token't
Feature activation+0.000
require
Token require
Feature activation+0.000
"
Token "
Feature activation+0.000
judicial
Tokenjudicial
Feature activation+0.000
process
Token process
Feature activation+0.000
."
Token."
Feature activation+0.000
During
Token During
Feature activation+0.000
and
Token and
Feature activation+0.000
Marty
Token Marty
Feature activation+0.000
Alexander
Token Alexander
Feature activation+0.000
cast
Token cast
Feature activation+0.000
a
Token a
Feature activation+0.000
broader
Token broader
Feature activation+0.000
net
Token net
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
suggested
Token suggested
Feature activation+0.000
that
Token that
Feature activation+0.000
possibly
Token possibly
Feature activation+0.000
including
Token including
Feature activation+0.000
trim
Token trim
Feature activation+0.000
ming
Tokenming
Feature activation+0.000
their
Token their
Feature activation+0.000
size
Token size
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
warned
Token warned
Feature activation+0.000
that
Token that
Feature activation+0.000
and
Token and
Feature activation+0.000
risen
Token risen
Feature activation+0.000
among
Token among
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
.
Token.
Feature activation+0.000
About
Token About
Feature activation+0.000
9
Token 9
Feature activation+0.000
in
Token in
Feature activation+0.000
10
Token 10
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
think
Token think
Feature activation+0.000
iod
Tokeniod
Feature activation+0.000
as
Tokenas
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
others
Token others
Feature activation+0.000
.
Token.
Feature activation+0.000
Back
Token Back
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
capital
Token capital
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H2.10: (feature 16311)

TOP ACTIVATIONS
MAX = 2.111

(
Token (
Feature activation+1.820
4
Token4
Feature activation+1.720
)
Token)
Feature activation+1.765
June
Token June
Feature activation+1.638
2006
Token 2006
Feature activation+1.877
(
Token (
Feature activation+1.959
5
Token5
Feature activation+1.855
)
Token)
Feature activation+2.004
May
Token May
Feature activation+1.799
2006
Token 2006
Feature activation+2.016
(
Token (
Feature activation+2.046
(
Token (
Feature activation+1.731
15
Token15
Feature activation+1.562
)
Token)
Feature activation+1.787
Apr
Token Apr
Feature activation+1.667
2009
Token 2009
Feature activation+1.908
(
Token (
Feature activation+1.920
24
Token24
Feature activation+1.832
)
Token)
Feature activation+1.915
Mar
Token Mar
Feature activation+1.830
2009
Token 2009
Feature activation+2.049
(
Token (
Feature activation+2.111
2009
Token 2009
Feature activation+1.692
(
Token (
Feature activation+1.731
15
Token15
Feature activation+1.562
)
Token)
Feature activation+1.787
Apr
Token Apr
Feature activation+1.667
2009
Token 2009
Feature activation+1.908
(
Token (
Feature activation+1.920
24
Token24
Feature activation+1.832
)
Token)
Feature activation+1.915
Mar
Token Mar
Feature activation+1.830
2009
Token 2009
Feature activation+2.049
2006
Token 2006
Feature activation+1.742
(
Token (
Feature activation+1.820
4
Token4
Feature activation+1.720
)
Token)
Feature activation+1.765
June
Token June
Feature activation+1.638
2006
Token 2006
Feature activation+1.877
(
Token (
Feature activation+1.959
5
Token5
Feature activation+1.855
)
Token)
Feature activation+2.004
May
Token May
Feature activation+1.799
2006
Token 2006
Feature activation+2.016
15
Token15
Feature activation+1.562
)
Token)
Feature activation+1.787
Apr
Token Apr
Feature activation+1.667
2009
Token 2009
Feature activation+1.908
(
Token (
Feature activation+1.920
24
Token24
Feature activation+1.832
)
Token)
Feature activation+1.915
Mar
Token Mar
Feature activation+1.830
2009
Token 2009
Feature activation+2.049
(
Token (
Feature activation+2.111
25
Token25
Feature activation+2.063
(
Token (
Feature activation+1.586
5
Token5
Feature activation+1.494
)
Token)
Feature activation+1.645
July
Token July
Feature activation+1.492
2006
Token 2006
Feature activation+1.742
(
Token (
Feature activation+1.820
4
Token4
Feature activation+1.720
)
Token)
Feature activation+1.765
June
Token June
Feature activation+1.638
2006
Token 2006
Feature activation+1.877
(
Token (
Feature activation+1.959
)
Token)
Feature activation+1.623
May
Token May
Feature activation+1.483
2009
Token 2009
Feature activation+1.692
(
Token (
Feature activation+1.731
15
Token15
Feature activation+1.562
)
Token)
Feature activation+1.787
Apr
Token Apr
Feature activation+1.667
2009
Token 2009
Feature activation+1.908
(
Token (
Feature activation+1.920
24
Token24
Feature activation+1.832
)
Token)
Feature activation+1.915
)
Token)
Feature activation+1.645
July
Token July
Feature activation+1.492
2006
Token 2006
Feature activation+1.742
(
Token (
Feature activation+1.820
4
Token4
Feature activation+1.720
)
Token)
Feature activation+1.765
June
Token June
Feature activation+1.638
2006
Token 2006
Feature activation+1.877
(
Token (
Feature activation+1.959
5
Token5
Feature activation+1.855
)
Token)
Feature activation+2.004
2006
Token 2006
Feature activation+1.535
(
Token (
Feature activation+1.586
5
Token5
Feature activation+1.494
)
Token)
Feature activation+1.645
July
Token July
Feature activation+1.492
2006
Token 2006
Feature activation+1.742
(
Token (
Feature activation+1.820
4
Token4
Feature activation+1.720
)
Token)
Feature activation+1.765
June
Token June
Feature activation+1.638
2006
Token 2006
Feature activation+1.877
(
Token (
Feature activation+1.596
13
Token13
Feature activation+1.549
)
Token)
Feature activation+1.623
May
Token May
Feature activation+1.483
2009
Token 2009
Feature activation+1.692
(
Token (
Feature activation+1.731
15
Token15
Feature activation+1.562
)
Token)
Feature activation+1.787
Apr
Token Apr
Feature activation+1.667
2009
Token 2009
Feature activation+1.908
(
Token (
Feature activation+1.920
5
Token5
Feature activation+1.494
)
Token)
Feature activation+1.645
July
Token July
Feature activation+1.492
2006
Token 2006
Feature activation+1.742
(
Token (
Feature activation+1.820
4
Token4
Feature activation+1.720
)
Token)
Feature activation+1.765
June
Token June
Feature activation+1.638
2006
Token 2006
Feature activation+1.877
(
Token (
Feature activation+1.959
5
Token5
Feature activation+1.855
2009
Token 2009
Feature activation+1.541
(
Token (
Feature activation+1.596
13
Token13
Feature activation+1.549
)
Token)
Feature activation+1.623
May
Token May
Feature activation+1.483
2009
Token 2009
Feature activation+1.692
(
Token (
Feature activation+1.731
15
Token15
Feature activation+1.562
)
Token)
Feature activation+1.787
Apr
Token Apr
Feature activation+1.667
2009
Token 2009
Feature activation+1.908
May
Token May
Feature activation+1.483
2009
Token 2009
Feature activation+1.692
(
Token (
Feature activation+1.731
15
Token15
Feature activation+1.562
)
Token)
Feature activation+1.787
Apr
Token Apr
Feature activation+1.667
2009
Token 2009
Feature activation+1.908
(
Token (
Feature activation+1.920
24
Token24
Feature activation+1.832
)
Token)
Feature activation+1.915
Mar
Token Mar
Feature activation+1.830
)
Token)
Feature activation+1.472
August
Token August
Feature activation+1.330
2006
Token 2006
Feature activation+1.535
(
Token (
Feature activation+1.586
5
Token5
Feature activation+1.494
)
Token)
Feature activation+1.645
July
Token July
Feature activation+1.492
2006
Token 2006
Feature activation+1.742
(
Token (
Feature activation+1.820
4
Token4
Feature activation+1.720
)
Token)
Feature activation+1.765
July
Token July
Feature activation+1.492
2006
Token 2006
Feature activation+1.742
(
Token (
Feature activation+1.820
4
Token4
Feature activation+1.720
)
Token)
Feature activation+1.765
June
Token June
Feature activation+1.638
2006
Token 2006
Feature activation+1.877
(
Token (
Feature activation+1.959
5
Token5
Feature activation+1.855
)
Token)
Feature activation+2.004
May
Token May
Feature activation+1.799
)
Token)
Feature activation+1.470
Jun
Token Jun
Feature activation+1.246
2009
Token 2009
Feature activation+1.541
(
Token (
Feature activation+1.596
13
Token13
Feature activation+1.549
)
Token)
Feature activation+1.623
May
Token May
Feature activation+1.483
2009
Token 2009
Feature activation+1.692
(
Token (
Feature activation+1.731
15
Token15
Feature activation+1.562
)
Token)
Feature activation+1.787
(
Token (
Feature activation+1.519
28
Token28
Feature activation+1.265
)
Token)
Feature activation+1.470
Jun
Token Jun
Feature activation+1.246
2009
Token 2009
Feature activation+1.541
(
Token (
Feature activation+1.596
13
Token13
Feature activation+1.549
)
Token)
Feature activation+1.623
May
Token May
Feature activation+1.483
2009
Token 2009
Feature activation+1.692
(
Token (
Feature activation+1.731
(
Token (
Feature activation+1.325
6
Token6
Feature activation+1.349
)
Token)
Feature activation+1.472
August
Token August
Feature activation+1.330
2006
Token 2006
Feature activation+1.535
(
Token (
Feature activation+1.586
5
Token5
Feature activation+1.494
)
Token)
Feature activation+1.645
July
Token July
Feature activation+1.492
2006
Token 2006
Feature activation+1.742
(
Token (
Feature activation+1.820
13
Token13
Feature activation+1.549
)
Token)
Feature activation+1.623
May
Token May
Feature activation+1.483
2009
Token 2009
Feature activation+1.692
(
Token (
Feature activation+1.731
15
Token15
Feature activation+1.562
)
Token)
Feature activation+1.787
Apr
Token Apr
Feature activation+1.667
2009
Token 2009
Feature activation+1.908
(
Token (
Feature activation+1.920
24
Token24
Feature activation+1.832
28
Token28
Feature activation+1.265
)
Token)
Feature activation+1.470
Jun
Token Jun
Feature activation+1.246
2009
Token 2009
Feature activation+1.541
(
Token (
Feature activation+1.596
13
Token13
Feature activation+1.549
)
Token)
Feature activation+1.623
May
Token May
Feature activation+1.483
2009
Token 2009
Feature activation+1.692
(
Token (
Feature activation+1.731
15
Token15
Feature activation+1.562

Top DFA by src position
MAX = 0.987

July
Token July
Feature activation+0.244
Top resid features:
2006
Token 2006
Feature activation+0.186
Top resid features:
(
Token (
Feature activation+0.141
Top resid features:
4
Token4
Feature activation+0.263
Top resid features:
)
Token)
Feature activation+0.442
Top resid features:
June
Token June
Feature activation+0.793
Top resid features:
2006
Token 2006
Feature activation+0.654
Top resid features:
(
Token (
Feature activation+0.463
Top resid features:
5
Token5
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.217
Top resid features:
2009
Token 2009
Feature activation+0.163
Top resid features:
(
Token (
Feature activation+0.135
Top resid features:
15
Token15
Feature activation+0.270
Top resid features:
)
Token)
Feature activation+0.460
Top resid features:
Apr
Token Apr
Feature activation+0.822
Top resid features:
2009
Token 2009
Feature activation+0.602
Top resid features:
(
Token (
Feature activation+0.472
Top resid features:
24
Token24
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
Mar
Token Mar
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.232
Top resid features:
2009
Token 2009
Feature activation+0.167
Top resid features:
(
Token (
Feature activation+0.300
Top resid features:
15
Token15
Feature activation+0.338
Top resid features:
)
Token)
Feature activation+0.550
Top resid features:
Apr
Token Apr
Feature activation+0.979
Top resid features:
2009
Token 2009
Feature activation+0.553
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
24
Token24
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
Mar
Token Mar
Feature activation+0.000
Top resid features:
July
Token July
Feature activation+0.269
Top resid features:
2006
Token 2006
Feature activation+0.181
Top resid features:
(
Token (
Feature activation+0.315
Top resid features:
4
Token4
Feature activation+0.297
Top resid features:
)
Token)
Feature activation+0.529
Top resid features:
June
Token June
Feature activation+0.905
Top resid features:
2006
Token 2006
Feature activation+0.602
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
5
Token5
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.125
Top resid features:
15
Token15
Feature activation+0.220
Top resid features:
)
Token)
Feature activation+0.380
Top resid features:
Apr
Token Apr
Feature activation+0.592
Top resid features:
2009
Token 2009
Feature activation+0.432
Top resid features:
(
Token (
Feature activation+0.608
Top resid features:
24
Token24
Feature activation+0.552
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
Mar
Token Mar
Feature activation+0.000
Top resid features:
2009
Token 2009
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
August
Token August
Feature activation+0.211
Top resid features:
2006
Token 2006
Feature activation+0.174
Top resid features:
(
Token (
Feature activation+0.131
Top resid features:
5
Token5
Feature activation+0.246
Top resid features:
)
Token)
Feature activation+0.423
Top resid features:
July
Token July
Feature activation+0.859
Top resid features:
2006
Token 2006
Feature activation+0.644
Top resid features:
(
Token (
Feature activation+0.460
Top resid features:
4
Token4
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
June
Token June
Feature activation+0.000
Top resid features:
Jun
Token Jun
Feature activation+0.177
Top resid features:
2009
Token 2009
Feature activation+0.114
Top resid features:
(
Token (
Feature activation+0.106
Top resid features:
13
Token13
Feature activation+0.144
Top resid features:
)
Token)
Feature activation+0.218
Top resid features:
May
Token May
Feature activation+0.614
Top resid features:
2009
Token 2009
Feature activation+0.336
Top resid features:
(
Token (
Feature activation+0.408
Top resid features:
15
Token15
Feature activation+0.591
Top resid features:
)
Token)
Feature activation+0.600
Top resid features:
Apr
Token Apr
Feature activation+0.000
Top resid features:
August
Token August
Feature activation+0.180
Top resid features:
2006
Token 2006
Feature activation+0.135
Top resid features:
(
Token (
Feature activation+0.113
Top resid features:
5
Token5
Feature activation+0.159
Top resid features:
)
Token)
Feature activation+0.212
Top resid features:
July
Token July
Feature activation+0.650
Top resid features:
2006
Token 2006
Feature activation+0.378
Top resid features:
(
Token (
Feature activation+0.413
Top resid features:
4
Token4
Feature activation+0.515
Top resid features:
)
Token)
Feature activation+0.548
Top resid features:
June
Token June
Feature activation+0.000
Top resid features:
August
Token August
Feature activation+0.230
Top resid features:
2006
Token 2006
Feature activation+0.167
Top resid features:
(
Token (
Feature activation+0.295
Top resid features:
5
Token5
Feature activation+0.298
Top resid features:
)
Token)
Feature activation+0.508
Top resid features:
July
Token July
Feature activation+0.987
Top resid features:
2006
Token 2006
Feature activation+0.584
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:
June
Token June
Feature activation+0.000
Top resid features:
Jun
Token Jun
Feature activation+0.219
Top resid features:
2009
Token 2009
Feature activation+0.158
Top resid features:
(
Token (
Feature activation+0.128
Top resid features:
13
Token13
Feature activation+0.237
Top resid features:
)
Token)
Feature activation+0.432
Top resid features:
May
Token May
Feature activation+0.759
Top resid features:
2009
Token 2009
Feature activation+0.600
Top resid features:
(
Token (
Feature activation+0.473
Top resid features:
15
Token15
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
Apr
Token Apr
Feature activation+0.000
Top resid features:
August
Token August
Feature activation+0.179
Top resid features:
2006
Token 2006
Feature activation+0.164
Top resid features:
(
Token (
Feature activation+0.122
Top resid features:
5
Token5
Feature activation+0.174
Top resid features:
)
Token)
Feature activation+0.325
Top resid features:
July
Token July
Feature activation+0.612
Top resid features:
2006
Token 2006
Feature activation+0.505
Top resid features:
(
Token (
Feature activation+0.588
Top resid features:
4
Token4
Feature activation+0.530
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
June
Token June
Feature activation+0.000
Top resid features:
Jun
Token Jun
Feature activation+0.248
Top resid features:
2009
Token 2009
Feature activation+0.159
Top resid features:
(
Token (
Feature activation+0.298
Top resid features:
13
Token13
Feature activation+0.292
Top resid features:
)
Token)
Feature activation+0.518
Top resid features:
May
Token May
Feature activation+0.872
Top resid features:
2009
Token 2009
Feature activation+0.574
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
15
Token15
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
Apr
Token Apr
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.260
Top resid features:
2009
Token 2009
Feature activation+0.221
Top resid features:
(
Token (
Feature activation+0.328
Top resid features:
15
Token15
Feature activation+0.422
Top resid features:
)
Token)
Feature activation+0.650
Top resid features:
Apr
Token Apr
Feature activation+0.709
Top resid features:
2009
Token 2009
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
24
Token24
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
Mar
Token Mar
Feature activation+0.000
Top resid features:
September
Token September
Feature activation+0.171
Top resid features:
2006
Token 2006
Feature activation+0.125
Top resid features:
(
Token (
Feature activation+0.106
Top resid features:
6
Token6
Feature activation+0.130
Top resid features:
)
Token)
Feature activation+0.206
Top resid features:
August
Token August
Feature activation+0.647
Top resid features:
2006
Token 2006
Feature activation+0.358
Top resid features:
(
Token (
Feature activation+0.383
Top resid features:
5
Token5
Feature activation+0.544
Top resid features:
)
Token)
Feature activation+0.540
Top resid features:
July
Token July
Feature activation+0.000
Top resid features:
July
Token July
Feature activation+0.293
Top resid features:
2006
Token 2006
Feature activation+0.242
Top resid features:
(
Token (
Feature activation+0.316
Top resid features:
4
Token4
Feature activation+0.359
Top resid features:
)
Token)
Feature activation+0.652
Top resid features:
June
Token June
Feature activation+0.776
Top resid features:
2006
Token 2006
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
5
Token5
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.209
Top resid features:
Jun
Token Jun
Feature activation+0.584
Top resid features:
2009
Token 2009
Feature activation+0.342
Top resid features:
(
Token (
Feature activation+0.403
Top resid features:
13
Token13
Feature activation+0.522
Top resid features:
)
Token)
Feature activation+0.589
Top resid features:
May
Token May
Feature activation+0.000
Top resid features:
2009
Token 2009
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
15
Token15
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
Jul
Token Jul
Feature activation+0.220
Top resid features:
2009
Token 2009
Feature activation+0.145
Top resid features:
(
Token (
Feature activation+0.119
Top resid features:
28
Token28
Feature activation+0.202
Top resid features:
)
Token)
Feature activation+0.423
Top resid features:
Jun
Token Jun
Feature activation+0.759
Top resid features:
2009
Token 2009
Feature activation+0.609
Top resid features:
(
Token (
Feature activation+0.467
Top resid features:
13
Token13
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.000
Top resid features:
September
Token September
Feature activation+0.198
Top resid features:
2006
Token 2006
Feature activation+0.161
Top resid features:
(
Token (
Feature activation+0.125
Top resid features:
6
Token6
Feature activation+0.214
Top resid features:
)
Token)
Feature activation+0.411
Top resid features:
August
Token August
Feature activation+0.791
Top resid features:
2006
Token 2006
Feature activation+0.606
Top resid features:
(
Token (
Feature activation+0.442
Top resid features:
5
Token5
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
July
Token July
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.120
Top resid features:
13
Token13
Feature activation+0.163
Top resid features:
)
Token)
Feature activation+0.354
Top resid features:
May
Token May
Feature activation+0.493
Top resid features:
2009
Token 2009
Feature activation+0.437
Top resid features:
(
Token (
Feature activation+0.616
Top resid features:
15
Token15
Feature activation+0.510
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
Apr
Token Apr
Feature activation+0.000
Top resid features:
2009
Token 2009
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.119
Top resid features:
28
Token28
Feature activation+0.156
Top resid features:
)
Token)
Feature activation+0.337
Top resid features:
Jun
Token Jun
Feature activation+0.578
Top resid features:
2009
Token 2009
Feature activation+0.435
Top resid features:
(
Token (
Feature activation+0.618
Top resid features:
13
Token13
Feature activation+0.502
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.000
Top resid features:
2009
Token 2009
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.03

Head 2: 0.05

Head 3: 0.07

Head 4: 0.03

Head 5: 0.06

Head 6: 0.09

Head 7: 0.13

Head 8: 0.05

Head 9: 0.05

Head 10: 0.26

Head 11: 0.12

Positive logits

etheus0.73

MpServer0.66

redo0.61

leon0.58

)0.58

Runtime0.54

anamo0.54

Cmd0.54

thora0.54

Bonus0.53

"/>0.53

elin0.52

cknow0.52

odus0.51

orah0.51

nington0.51

uncle0.51

Corp0.51

irin0.50

Cooldown0.50

Negative logits

oulos-0.49

vape-0.49

''-0.49

esides-0.47

rather-0.47

-0.47

Democr-0.46

GMO-0.46

Obesity-0.46

lithium-0.46

-0.46

yrim-0.45

Zika-0.45

Filip-0.45

Chev-0.45

Nissan-0.45

Kos-0.44

CAS-0.44

Nicotine-0.43

itaire-0.43

INTERVAL 1.900 - 2.111
CONTAINS 0.001%

2009
Token 2009
Feature activation+1.692
(
Token (
Feature activation+1.731
15
Token15
Feature activation+1.562
)
Token)
Feature activation+1.787
Apr
Token Apr
Feature activation+1.667
2009
Token 2009
Feature activation+1.908
(
Token (
Feature activation+1.920
24
Token24
Feature activation+1.832
)
Token)
Feature activation+1.915
Mar
Token Mar
Feature activation+1.830
2009
Token 2009
Feature activation+2.049
(
Token (
Feature activation+1.731
15
Token15
Feature activation+1.562
)
Token)
Feature activation+1.787
Apr
Token Apr
Feature activation+1.667
2009
Token 2009
Feature activation+1.908
(
Token (
Feature activation+1.920
24
Token24
Feature activation+1.832
)
Token)
Feature activation+1.915
Mar
Token Mar
Feature activation+1.830
2009
Token 2009
Feature activation+2.049
(
Token (
Feature activation+2.111
(
Token (
Feature activation+1.820
4
Token4
Feature activation+1.720
)
Token)
Feature activation+1.765
June
Token June
Feature activation+1.638
2006
Token 2006
Feature activation+1.877
(
Token (
Feature activation+1.959
5
Token5
Feature activation+1.855
)
Token)
Feature activation+2.004
May
Token May
Feature activation+1.799
2006
Token 2006
Feature activation+2.016
(
Token (
Feature activation+2.046

INTERVAL 1.689 - 1.900
CONTAINS 0.001%

(
Token (
Feature activation+1.586
5
Token5
Feature activation+1.494
)
Token)
Feature activation+1.645
July
Token July
Feature activation+1.492
2006
Token 2006
Feature activation+1.742
(
Token (
Feature activation+1.820
4
Token4
Feature activation+1.720
)
Token)
Feature activation+1.765
June
Token June
Feature activation+1.638
2006
Token 2006
Feature activation+1.877
(
Token (
Feature activation+1.959
)
Token)
Feature activation+1.623
May
Token May
Feature activation+1.483
2009
Token 2009
Feature activation+1.692
(
Token (
Feature activation+1.731
15
Token15
Feature activation+1.562
)
Token)
Feature activation+1.787
Apr
Token Apr
Feature activation+1.667
2009
Token 2009
Feature activation+1.908
(
Token (
Feature activation+1.920
24
Token24
Feature activation+1.832
)
Token)
Feature activation+1.915
)
Token)
Feature activation+1.645
July
Token July
Feature activation+1.492
2006
Token 2006
Feature activation+1.742
(
Token (
Feature activation+1.820
4
Token4
Feature activation+1.720
)
Token)
Feature activation+1.765
June
Token June
Feature activation+1.638
2006
Token 2006
Feature activation+1.877
(
Token (
Feature activation+1.959
5
Token5
Feature activation+1.855
)
Token)
Feature activation+2.004
5
Token5
Feature activation+1.494
)
Token)
Feature activation+1.645
July
Token July
Feature activation+1.492
2006
Token 2006
Feature activation+1.742
(
Token (
Feature activation+1.820
4
Token4
Feature activation+1.720
)
Token)
Feature activation+1.765
June
Token June
Feature activation+1.638
2006
Token 2006
Feature activation+1.877
(
Token (
Feature activation+1.959
5
Token5
Feature activation+1.855
2006
Token 2006
Feature activation+1.742
(
Token (
Feature activation+1.820
4
Token4
Feature activation+1.720
)
Token)
Feature activation+1.765
June
Token June
Feature activation+1.638
2006
Token 2006
Feature activation+1.877
(
Token (
Feature activation+1.959
5
Token5
Feature activation+1.855
)
Token)
Feature activation+2.004
May
Token May
Feature activation+1.799
2006
Token 2006
Feature activation+2.016

INTERVAL 1.478 - 1.689
CONTAINS 0.004%

(
Token (
Feature activation+1.325
6
Token6
Feature activation+1.349
)
Token)
Feature activation+1.472
August
Token August
Feature activation+1.330
2006
Token 2006
Feature activation+1.535
(
Token (
Feature activation+1.586
5
Token5
Feature activation+1.494
)
Token)
Feature activation+1.645
July
Token July
Feature activation+1.492
2006
Token 2006
Feature activation+1.742
(
Token (
Feature activation+1.820
(
Token (
Feature activation+1.237
18
Token18
Feature activation+1.062
)
Token)
Feature activation+1.150
Jul
Token Jul
Feature activation+1.078
2009
Token 2009
Feature activation+1.523
(
Token (
Feature activation+1.519
28
Token28
Feature activation+1.265
)
Token)
Feature activation+1.470
Jun
Token Jun
Feature activation+1.246
2009
Token 2009
Feature activation+1.541
(
Token (
Feature activation+1.596
ogie
Tokenogie
Feature activation+0.817
Ball
Token Ball
Feature activation+0.739
in
Tokenin
Feature activation+0.518
'
Token'
Feature activation+0.693
bonus
Token bonus
Feature activation+0.869
-
Token -
Feature activation+1.478
ind
Token ind
Feature activation+1.266
y
Tokeny
Feature activation+0.818
track
Token track
Feature activation+0.950
-
Token -
Feature activation+1.449
Pink
Token Pink
Feature activation+1.566
July
Token July
Feature activation+1.492
2006
Token 2006
Feature activation+1.742
(
Token (
Feature activation+1.820
4
Token4
Feature activation+1.720
)
Token)
Feature activation+1.765
June
Token June
Feature activation+1.638
2006
Token 2006
Feature activation+1.877
(
Token (
Feature activation+1.959
5
Token5
Feature activation+1.855
)
Token)
Feature activation+2.004
May
Token May
Feature activation+1.799
6
Token6
Feature activation+1.349
)
Token)
Feature activation+1.472
August
Token August
Feature activation+1.330
2006
Token 2006
Feature activation+1.535
(
Token (
Feature activation+1.586
5
Token5
Feature activation+1.494
)
Token)
Feature activation+1.645
July
Token July
Feature activation+1.492
2006
Token 2006
Feature activation+1.742
(
Token (
Feature activation+1.820
4
Token4
Feature activation+1.720

INTERVAL 1.266 - 1.478
CONTAINS 0.005%

6
Token6
Feature activation+1.105
)
Token)
Feature activation+1.280
September
Token September
Feature activation+1.123
2006
Token 2006
Feature activation+1.293
(
Token (
Feature activation+1.325
6
Token6
Feature activation+1.349
)
Token)
Feature activation+1.472
August
Token August
Feature activation+1.330
2006
Token 2006
Feature activation+1.535
(
Token (
Feature activation+1.586
5
Token5
Feature activation+1.494
5
Token 5
Feature activation+1.328
2000
Token 2000
Feature activation+1.343
Astros
Token Astros
Feature activation+1.228
30
Token 30
Feature activation+1.196
57
Token 57
Feature activation+1.226
.
Token .
Feature activation+1.430
345
Token345
Feature activation+1.500
6
Token 6
Feature activation+1.638
42
Token 42
Feature activation+1.648
33
Token 33
Feature activation+1.470
.
Token .
Feature activation+1.555
46
Token 46
Feature activation+1.165
Mississippi
Token Mississippi
Feature activation+1.201
13
Token 13
Feature activation+1.470
Arizona
Token Arizona
Feature activation+1.390
30
Token 30
Feature activation+1.462
Maryland
Token Maryland
Feature activation+1.409
47
Token 47
Feature activation+1.426
New
Token New
Feature activation+1.284
Jersey
Token Jersey
Feature activation+1.200
14
Token 14
Feature activation+1.491
Louisiana
Token Louisiana
Feature activation+1.408
7
Token 7
Feature activation+1.028
:
Token:
Feature activation+1.098
00
Token00
Feature activation+1.261
AM
Token AM
Feature activation+1.254
8
Token 8
Feature activation+1.424
:
Token:
Feature activation+1.461
00
Token00
Feature activation+1.546
AM
Token AM
Feature activation+1.519
359
Token 359
Feature activation+1.536
214
Token 214
Feature activation+1.519
LIVE
Token LIVE
Feature activation+1.534
Arizona
Token Arizona
Feature activation+0.689
State
Token State
Feature activation+0.599
6
Token 6
Feature activation+1.009
-
Token-
Feature activation+1.120
1
Token1
Feature activation+1.264
14
Token 14
Feature activation+1.285
15
Token 15
Feature activation+1.113
18
Token 18
Feature activation+1.022
9
Token 9
Feature activation+1.136
.
Token.
Feature activation+1.140
82
Token82
Feature activation+1.082

INTERVAL 1.055 - 1.266
CONTAINS 0.010%

6
Token6
Feature activation+0.835
)
Token)
Feature activation+1.068
October
Token October
Feature activation+0.955
2006
Token 2006
Feature activation+1.092
(
Token (
Feature activation+1.103
6
Token6
Feature activation+1.105
)
Token)
Feature activation+1.280
September
Token September
Feature activation+1.123
2006
Token 2006
Feature activation+1.293
(
Token (
Feature activation+1.325
6
Token6
Feature activation+1.349
Ohio
Token Ohio
Feature activation+0.728
45
Token 45
Feature activation+0.846
Oklahoma
Token Oklahoma
Feature activation+0.898
12
Token 12
Feature activation+1.026
Connecticut
Token Connecticut
Feature activation+1.041
29
Token 29
Feature activation+1.209
Montana
Token Montana
Feature activation+1.167
46
Token 46
Feature activation+1.165
Mississippi
Token Mississippi
Feature activation+1.201
13
Token 13
Feature activation+1.470
Arizona
Token Arizona
Feature activation+1.390
Jul
Token Jul
Feature activation+1.078
2009
Token 2009
Feature activation+1.523
(
Token (
Feature activation+1.519
28
Token28
Feature activation+1.265
)
Token)
Feature activation+1.470
Jun
Token Jun
Feature activation+1.246
2009
Token 2009
Feature activation+1.541
(
Token (
Feature activation+1.596
13
Token13
Feature activation+1.549
)
Token)
Feature activation+1.623
May
Token May
Feature activation+1.483
4
Token4
Feature activation+0.103
d
Tokend
Feature activation+0.243
Tue
Token Tue
Feature activation+0.569
Sep
Token Sep
Feature activation+0.925
24
Token 24
Feature activation+0.999
03
Token 03
Feature activation+1.116
:
Token:
Feature activation+1.087
21
Token21
Feature activation+1.095
:
Token:
Feature activation+1.007
13
Token13
Feature activation+1.010
2013
Token 2013
Feature activation+0.956
State
Token State
Feature activation+0.599
6
Token 6
Feature activation+1.009
-
Token-
Feature activation+1.120
1
Token1
Feature activation+1.264
14
Token 14
Feature activation+1.285
15
Token 15
Feature activation+1.113
18
Token 18
Feature activation+1.022
9
Token 9
Feature activation+1.136
.
Token.
Feature activation+1.140
82
Token82
Feature activation+1.082
Nebraska
Token Nebraska
Feature activation+1.048

INTERVAL 0.844 - 1.055
CONTAINS 0.018%

OL
TokenOL
Feature activation+0.668
F
TokenF
Feature activation+0.640
CH
Token CH
Feature activation+0.593
ANN
TokenANN
Feature activation+0.629
EL
TokenEL
Feature activation+0.739
12
Token 12
Feature activation+0.866
:
Token:
Feature activation+0.885
00
Token00
Feature activation+1.142
PM
Token PM
Feature activation+1.211
1
Token 1
Feature activation+1.425
:
Token:
Feature activation+1.366
\
Token\
Feature activation+0.665
alpha
Tokenalpha
Feature activation+0.699
^{
Token^{
Feature activation+0.604
2
Token2
Feature activation+0.687
^{
Token^{
Feature activation+0.779
k
Tokenk
Feature activation+0.876
+
Token+
Feature activation+0.874
j
Tokenj
Feature activation+1.038
}
Token}
Feature activation+1.038
-
Token-
Feature activation+0.926
2
Token2
Feature activation+0.950
Devil
Token Devil
Feature activation+0.528
Rays
Token Rays
Feature activation+0.526
28
Token 28
Feature activation+0.716
61
Token 61
Feature activation+0.632
.
Token .
Feature activation+0.849
315
Token315
Feature activation+1.020
5
Token 5
Feature activation+1.101
39
Token 39
Feature activation+1.070
34
Token 34
Feature activation+0.931
.
Token .
Feature activation+0.981
5
Token5
Feature activation+1.194
.
Token.
Feature activation+0.218
Virginia
Token Virginia
Feature activation+0.408
:
Token:
Feature activation+0.394
10
Token 10
Feature activation+0.765
.
Token.
Feature activation+0.822
9
Token9
Feature activation+0.941
17
Token 17
Feature activation+0.750
.
Token.
Feature activation+0.558
Delaware
Token Delaware
Feature activation+0.661
:
Token:
Feature activation+0.623
11
Token 11
Feature activation+0.900
azz
Tokenazz
Feature activation+0.521
eri
Tokeneri
Feature activation+0.577
1929
Token 1929
Feature activation+0.670
,
Token,
Feature activation+0.886
1934
Token 1934
Feature activation+0.769
-
Token-
Feature activation+0.854
19
Token19
Feature activation+0.962
37
Token37
Feature activation+1.026
Dust
Token Dust
Feature activation+0.909
y
Tokeny
Feature activation+0.779
Cooke
Token Cooke
Feature activation+0.762

INTERVAL 0.633 - 0.844
CONTAINS 0.037%

,
Token,
Feature activation+0.359
04
Token 04
Feature activation+0.559
/
Token/
Feature activation+0.643
03
Token03
Feature activation+0.781
/
Token/
Feature activation+0.857
2017
Token2017
Feature activation+0.831
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.772
âĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.860
âĢĶ-
TokenâĢĶ-
Feature activation+0.992
1
Token1
Feature activation+1.063
st
Tokenst
Feature activation+1.090
I
Token I
Feature activation+0.546
ker
Tokenker
Feature activation+0.504
Cas
Token Cas
Feature activation+0.335
illas
Tokenillas
Feature activation+0.549
Getty
Token Getty
Feature activation+0.596
2
Token 2
Feature activation+0.793
/
Token/
Feature activation+0.632
11
Token11
Feature activation+0.736
Che
Token Che
Feature activation+0.742
nd
Tokennd
Feature activation+0.830
o
Tokeno
Feature activation+0.720
https
Token https
Feature activation+0.815
://
Token://
Feature activation+0.960
twitter
Tokentwitter
Feature activation+1.070
.
Token.
Feature activation+0.817
com
Tokencom
Feature activation+0.817
/
Token/
Feature activation+0.769
i
Tokeni
Feature activation+0.817
ST
TokenST
Feature activation+0.722
ubby
Tokenubby
Feature activation+0.555
_
Token_
Feature activation+0.549
<|endoftext|>
Token<|endoftext|>
Feature activation+0.006
illas
Tokenillas
Feature activation+0.549
Getty
Token Getty
Feature activation+0.596
2
Token 2
Feature activation+0.793
/
Token/
Feature activation+0.632
11
Token11
Feature activation+0.736
Che
Token Che
Feature activation+0.742
nd
Tokennd
Feature activation+0.830
o
Tokeno
Feature activation+0.720
Getty
Token Getty
Feature activation+0.835
3
Token 3
Feature activation+0.985
/
Token/
Feature activation+0.880
âĢĶ-
TokenâĢĶ-
Feature activation+0.541
4
Token4
Feature activation+0.791
th
Tokenth
Feature activation+0.813
Place
Token Place
Feature activation+0.701
,
Token,
Feature activation+0.693
Player
Token Player
Feature activation+0.643
C
Token C
Feature activation+0.627
:
Token:
Feature activation+0.695
Dem
Token Dem
Feature activation+0.575
ise
Tokenise
Feature activation+0.000
True
Token True
Feature activation+0.413

INTERVAL 0.422 - 0.633
CONTAINS 0.064%

15
Token 15
Feature activation+0.143
.
Token.
Feature activation+0.016
Michigan
Token Michigan
Feature activation+0.163
:
Token:
Feature activation+0.109
10
Token 10
Feature activation+0.482
.
Token.
Feature activation+0.499
8
Token8
Feature activation+0.598
16
Token 16
Feature activation+0.375
.
Token.
Feature activation+0.218
Virginia
Token Virginia
Feature activation+0.408
:
Token:
Feature activation+0.394
\/
Token\/
Feature activation+0.000
th
Tokenth
Feature activation+0.274
umb
Tokenumb
Feature activation+0.000
\/
Token\/
Feature activation+0.000
0
Token0
Feature activation+0.254
\/
Token\/
Feature activation+0.456
0
Token0
Feature activation+0.490
f
Tokenf
Feature activation+0.497
\/
Token\/
Feature activation+0.615
H
TokenH
Feature activation+0.567
ang
Tokenang
Feature activation+0.455
5
Token 5
Feature activation+0.462
14
Token14
Feature activation+0.578
-
Token-
Feature activation+0.392
419
Token419
Feature activation+0.382
-
Token-
Feature activation+0.290
88
Token88
Feature activation+0.463
01
Token01
Feature activation+0.459
Ċ
TokenĊ
Feature activation+0.023
Ċ
TokenĊ
Feature activation+0.000
Toronto
TokenToronto
Feature activation+0.024
:
Token:
Feature activation+0.043
Ċ
TokenĊ
Feature activation+0.354
Ċ
TokenĊ
Feature activation+0.306
Morgan
TokenMorgan
Feature activation+0.282
Anne
Token Anne
Feature activation+0.320
Brooks
Token Brooks
Feature activation+0.226
,
Token,
Feature activation+0.602
25
Token 25
Feature activation+0.982
,
Token,
Feature activation+0.964
of
Token of
Feature activation+1.002
Raleigh
Token Raleigh
Feature activation+0.868
Ċ
TokenĊ
Feature activation+0.728
(
Token (
Feature activation+0.227
t
Token t
Feature activation+0.376
sv
Tokensv
Feature activation+0.291
@@
Token @@
Feature activation+0.215
q
Token q
Feature activation+0.324
)
Token )
Feature activation+0.458
)
Token )
Feature activation+0.438
AS
Token AS
Feature activation+0.430
t
Token t
Feature activation+0.775
1
Token1
Feature activation+0.711
ORDER
Token ORDER
Feature activation+0.631

INTERVAL 0.211 - 0.422
CONTAINS 0.111%

umber
Tokenumber
Feature activation+0.000
College
Token College
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Tue
TokenTue
Feature activation+0.000
Aug
Token Aug
Feature activation+0.368
11
Token 11
Feature activation+0.700
:
Token:
Feature activation+0.558
S
Token S
Feature activation+0.441
agin
Tokenagin
Feature activation+0.320
aw
Tokenaw
Feature activation+0.284
to
Token to
Feature activation+0.000
#
Token #
Feature activation+0.000
{
Token{
Feature activation+0.000
value
Tokenvalue
Feature activation+0.000
}"
Token}"
Feature activation+0.000
#
Token #
Feature activation+0.239
Print
Token Print
Feature activation+0.261
out
Token out
Feature activation+0.322
details
Token details
Feature activation+0.052
of
Token of
Feature activation+0.009
posts
Token posts
Feature activation+0.000
ors
Tokenors
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
9
Token9
Feature activation+0.000
p
Token p
Feature activation+0.043
.
Token.
Feature activation+0.341
m
Tokenm
Feature activation+0.371
.
Token.
Feature activation+0.304
âĢĶ
Token âĢĶ
Feature activation+0.250
Mom
Token Mom
Feature activation+0.180
Ċ
TokenĊ
Feature activation+0.000
57
Token57
Feature activation+0.000
900
Token900
Feature activation+0.000
27
Token27
Feature activation+0.000
&
Token&
Feature activation+0.292
sr
Tokensr
Feature activation+0.607
=
Token=
Feature activation+0.345
1
Token1
Feature activation+0.496
-
Token-
Feature activation+0.506
18
Token18
Feature activation+0.425
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Port
Token Port
Feature activation+0.439
Chester
Token Chester
Feature activation+0.534
,
Token,
Feature activation+0.371
N
Token N
Feature activation+0.493
.
Token.
Feature activation+0.305
Y
TokenY
Feature activation+0.341
.),
Token.),
Feature activation+0.463
McKin
Token McKin
Feature activation+0.823
ze
Tokenze
Feature activation+0.467
Gain
Token Gain
Feature activation+0.546
es
Tokenes
Feature activation+0.514

INTERVAL 0.000 - 0.211
CONTAINS 99.749%

Dylan
Token Dylan
Feature activation+0.000
Roof
Token Roof
Feature activation+0.000
shot
Token shot
Feature activation+0.000
and
Token and
Feature activation+0.000
killed
Token killed
Feature activation+0.000
nine
Token nine
Feature activation+0.000
African
Token African
Feature activation+0.000
American
Token American
Feature activation+0.000
Bible
Token Bible
Feature activation+0.000
class
Token class
Feature activation+0.000
students
Token students
Feature activation+0.000
-
Token-
Feature activation+0.000
election
Tokenelection
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
she
Token she
Feature activation+0.000
denies
Token denies
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
It
TokenIt
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
stored
Token stored
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
bank
Token bank
Feature activation+0.000
server
Token server
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
adds
Token adds
Feature activation+0.000
an
Token an
Feature activation+0.000
revenues
Token revenues
Feature activation+0.000
,
Token,
Feature activation+0.000
Western
Token Western
Feature activation+0.000
sanctions
Token sanctions
Feature activation+0.000
did
Token did
Feature activation+0.000
have
Token have
Feature activation+0.000
an
Token an
Feature activation+0.000
impact
Token impact
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
industry
Token industry
Feature activation+0.000
firms
Token firms
Feature activation+0.000
than
Token than
Feature activation+0.000
drive
Token drive
Feature activation+0.000
socioeconomic
Token socioeconomic
Feature activation+0.000
injust
Token injust
Feature activation+0.000
ices
Tokenices
Feature activation+0.000
.
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
this
Token this
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H2.10: (feature 23423)

TOP ACTIVATIONS
MAX = 1.641

products
Token products
Feature activation+1.130
are
Token are
Feature activation+1.373
not
Token not
Feature activation+1.577
fully
Token fully
Feature activation+1.637
paid
Token paid
Feature activation+1.495
for
Token for
Feature activation+1.641
or
Token or
Feature activation+1.572
are
Token are
Feature activation+1.522
being
Token being
Feature activation+1.257
sold
Token sold
Feature activation+1.305
on
Token on
Feature activation+0.981
,
Token,
Feature activation+0.790
the
Token the
Feature activation+0.955
products
Token products
Feature activation+1.130
are
Token are
Feature activation+1.373
not
Token not
Feature activation+1.577
fully
Token fully
Feature activation+1.637
paid
Token paid
Feature activation+1.495
for
Token for
Feature activation+1.641
or
Token or
Feature activation+1.572
are
Token are
Feature activation+1.522
being
Token being
Feature activation+1.257
12
Token12
Feature activation+0.841
-
Token-
Feature activation+1.089
2
Token2
Feature activation+1.086
:
Token:
Feature activation+1.263
2015
Token2015
Feature activation+1.471
âĢ
TokenâĢ
Feature activation+1.620
Ŀ
TokenĿ
Feature activation+1.568
)
Token)
Feature activation+0.562
international
Token international
Feature activation+0.033
safety
Token safety
Feature activation+0.000
standards
Token standards
Feature activation+0.000
example
Token example
Feature activation+0.071
,
Token,
Feature activation+0.790
the
Token the
Feature activation+0.955
products
Token products
Feature activation+1.130
are
Token are
Feature activation+1.373
not
Token not
Feature activation+1.577
fully
Token fully
Feature activation+1.637
paid
Token paid
Feature activation+1.495
for
Token for
Feature activation+1.641
or
Token or
Feature activation+1.572
are
Token are
Feature activation+1.522
are
Token are
Feature activation+1.373
not
Token not
Feature activation+1.577
fully
Token fully
Feature activation+1.637
paid
Token paid
Feature activation+1.495
for
Token for
Feature activation+1.641
or
Token or
Feature activation+1.572
are
Token are
Feature activation+1.522
being
Token being
Feature activation+1.257
sold
Token sold
Feature activation+1.305
on
Token on
Feature activation+0.981
cons
Token cons
Feature activation+0.931
-
Token-
Feature activation+1.089
2
Token2
Feature activation+1.086
:
Token:
Feature activation+1.263
2015
Token2015
Feature activation+1.471
âĢ
TokenâĢ
Feature activation+1.620
Ŀ
TokenĿ
Feature activation+1.568
)
Token)
Feature activation+0.562
international
Token international
Feature activation+0.033
safety
Token safety
Feature activation+0.000
standards
Token standards
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+1.577
fully
Token fully
Feature activation+1.637
paid
Token paid
Feature activation+1.495
for
Token for
Feature activation+1.641
or
Token or
Feature activation+1.572
are
Token are
Feature activation+1.522
being
Token being
Feature activation+1.257
sold
Token sold
Feature activation+1.305
on
Token on
Feature activation+0.981
cons
Token cons
Feature activation+0.931
ignment
Tokenignment
Feature activation+0.765
the
Token the
Feature activation+0.955
products
Token products
Feature activation+1.130
are
Token are
Feature activation+1.373
not
Token not
Feature activation+1.577
fully
Token fully
Feature activation+1.637
paid
Token paid
Feature activation+1.495
for
Token for
Feature activation+1.641
or
Token or
Feature activation+1.572
are
Token are
Feature activation+1.522
being
Token being
Feature activation+1.257
sold
Token sold
Feature activation+1.305
123
Token 123
Feature activation+0.814
12
Token12
Feature activation+0.841
-
Token-
Feature activation+1.089
2
Token2
Feature activation+1.086
:
Token:
Feature activation+1.263
2015
Token2015
Feature activation+1.471
âĢ
TokenâĢ
Feature activation+1.620
Ŀ
TokenĿ
Feature activation+1.568
)
Token)
Feature activation+0.562
international
Token international
Feature activation+0.033
safety
Token safety
Feature activation+0.000
ew
Tokenew
Feature activation+0.053
.
Token.
Feature activation+0.543
Chem
Token Chem
Feature activation+0.699
.
Token.
Feature activation+1.077
Int
Token Int
Feature activation+1.092
.
Token.
Feature activation+1.435
Ed
Token Ed
Feature activation+1.165
.
Token.
Feature activation+1.198
2015
Token 2015
Feature activation+0.809
,
Token,
Feature activation+0.801
DOI
Token DOI
Feature activation+0.167
July
Token July
Feature activation+0.730
18
Token 18
Feature activation+0.856
53
Token53
Feature activation+0.768
âĢĵ
Token âĢĵ
Feature activation+1.364
4
Token 4
Feature activation+1.254
February
Token February
Feature activation+1.434
1928
Token 1928
Feature activation+1.234
)
Token)
Feature activation+0.374
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
Dutch
Token Dutch
Feature activation+0.000
the
Token the
Feature activation+0.525
select
Token select
Feature activation+0.857
few
Token few
Feature activation+1.200
who
Token who
Feature activation+0.878
have
Token have
Feature activation+1.126
not
Token not
Feature activation+1.421
read
Token read
Feature activation+1.268
the
Token the
Feature activation+1.268
books
Token books
Feature activation+1.223
,
Token,
Feature activation+1.335
a
Token a
Feature activation+1.069
spoke
Token spoke
Feature activation+0.751
the
Token the
Feature activation+0.871
other
Token other
Feature activation+1.080
's
Token's
Feature activation+1.071
mother
Token mother
Feature activation+1.101
tongue
Token tongue
Feature activation+1.402
confidently
Token confidently
Feature activation+1.345
)
Token)
Feature activation+0.196
about
Token about
Feature activation+0.000
everything
Token everything
Feature activation+0.000
under
Token under
Feature activation+0.000
to
Token to
Feature activation+0.747
see
Token see
Feature activation+0.795
Season
Token Season
Feature activation+0.773
11
Token 11
Feature activation+0.849
âĢ
TokenâĢ
Feature activation+1.024
Ļ
TokenĻ
Feature activation+1.398
s
Tokens
Feature activation+1.032
Tape
Token Tape
Feature activation+1.084
Face
Token Face
Feature activation+0.976
do
Token do
Feature activation+1.093
his
Token his
Feature activation+0.998
up
Token up
Feature activation+0.998
the
Token the
Feature activation+1.083
tab
Token tab
Feature activation+1.278
for
Token for
Feature activation+1.088
any
Token any
Feature activation+1.246
employee
Token employee
Feature activation+1.395
that
Token that
Feature activation+1.176
opt
Token opt
Feature activation+1.036
s
Tokens
Feature activation+0.960
in
Token in
Feature activation+0.980
).
Token).
Feature activation+0.253
for
Tokenfor
Feature activation+0.000
example
Token example
Feature activation+0.071
,
Token,
Feature activation+0.790
the
Token the
Feature activation+0.955
products
Token products
Feature activation+1.130
are
Token are
Feature activation+1.373
not
Token not
Feature activation+1.577
fully
Token fully
Feature activation+1.637
paid
Token paid
Feature activation+1.495
for
Token for
Feature activation+1.641
or
Token or
Feature activation+1.572
;
Token;
Feature activation+0.000
18
Token 18
Feature activation+0.000
July
Token July
Feature activation+0.730
18
Token 18
Feature activation+0.856
53
Token53
Feature activation+0.768
âĢĵ
Token âĢĵ
Feature activation+1.364
4
Token 4
Feature activation+1.254
February
Token February
Feature activation+1.434
1928
Token 1928
Feature activation+1.234
)
Token)
Feature activation+0.374
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.871
other
Token other
Feature activation+1.080
's
Token's
Feature activation+1.071
mother
Token mother
Feature activation+1.101
tongue
Token tongue
Feature activation+1.402
confidently
Token confidently
Feature activation+1.345
)
Token)
Feature activation+0.196
about
Token about
Feature activation+0.000
everything
Token everything
Feature activation+0.000
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
being
Token being
Feature activation+0.920
around
Token around
Feature activation+0.877
other
Token other
Feature activation+1.108
people
Token people
Feature activation+1.011
âĢ
TokenâĢ
Feature activation+1.157
Ŀ
TokenĿ
Feature activation+1.336
)
Token)
Feature activation+0.386
we
Token we
Feature activation+0.000
presented
Token presented
Feature activation+0.000
each
Token each
Feature activation+0.000
item
Token item
Feature activation+0.000
have
Token have
Feature activation+1.126
not
Token not
Feature activation+1.421
read
Token read
Feature activation+1.268
the
Token the
Feature activation+1.268
books
Token books
Feature activation+1.223
,
Token,
Feature activation+1.335
a
Token a
Feature activation+1.069
spoiler
Token spoiler
Feature activation+1.121
is
Token is
Feature activation+1.002
coming
Token coming
Feature activation+1.047
).
Token).
Feature activation+0.083

Top DFA by src position
MAX = 0.784

an
Token an
Feature activation-0.004
Top resid features:
interest
Token interest
Feature activation-0.029
Top resid features:
(
Token (
Feature activation+0.243
Top resid features:
for
Tokenfor
Feature activation+0.119
Top resid features:
example
Token example
Feature activation+0.274
Top resid features:
,
Token,
Feature activation+0.316
Top resid features:
the
Token the
Feature activation+0.205
Top resid features:
products
Token products
Feature activation+0.065
Top resid features:
are
Token are
Feature activation+0.224
Top resid features:
not
Token not
Feature activation+0.164
Top resid features:
fully
Token fully
Feature activation+0.141
Top resid features:
has
Token has
Feature activation-0.016
Top resid features:
an
Token an
Feature activation-0.003
Top resid features:
interest
Token interest
Feature activation-0.041
Top resid features:
(
Token (
Feature activation+0.175
Top resid features:
for
Tokenfor
Feature activation+0.120
Top resid features:
example
Token example
Feature activation+0.460
Top resid features:
,
Token,
Feature activation+0.390
Top resid features:
the
Token the
Feature activation+0.232
Top resid features:
products
Token products
Feature activation+0.111
Top resid features:
are
Token are
Feature activation+0.308
Top resid features:
not
Token not
Feature activation+0.216
Top resid features:
ISO
TokenISO
Feature activation+0.055
Top resid features:
123
Token 123
Feature activation+0.119
Top resid features:
12
Token12
Feature activation+0.116
Top resid features:
-
Token-
Feature activation+0.098
Top resid features:
2
Token2
Feature activation+0.112
Top resid features:
:
Token:
Feature activation+0.469
Top resid features:
2015
Token2015
Feature activation+0.315
Top resid features:
âĢ
TokenâĢ
Feature activation+0.260
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
international
Token international
Feature activation+0.000
Top resid features:
has
Token has
Feature activation-0.022
Top resid features:
an
Token an
Feature activation-0.003
Top resid features:
interest
Token interest
Feature activation-0.039
Top resid features:
(
Token (
Feature activation+0.229
Top resid features:
for
Tokenfor
Feature activation+0.153
Top resid features:
example
Token example
Feature activation+0.441
Top resid features:
,
Token,
Feature activation+0.379
Top resid features:
the
Token the
Feature activation+0.224
Top resid features:
products
Token products
Feature activation+0.097
Top resid features:
are
Token are
Feature activation+0.324
Top resid features:
not
Token not
Feature activation+0.245
Top resid features:
has
Token has
Feature activation-0.015
Top resid features:
an
Token an
Feature activation-0.005
Top resid features:
interest
Token interest
Feature activation-0.029
Top resid features:
(
Token (
Feature activation+0.201
Top resid features:
for
Tokenfor
Feature activation+0.079
Top resid features:
example
Token example
Feature activation+0.284
Top resid features:
,
Token,
Feature activation+0.272
Top resid features:
the
Token the
Feature activation+0.163
Top resid features:
products
Token products
Feature activation+0.080
Top resid features:
are
Token are
Feature activation+0.190
Top resid features:
not
Token not
Feature activation+0.141
Top resid features:
12
Token12
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
2
Token2
Feature activation-0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ŀ
TokenĿ
Feature activation-0.010
Top resid features:
(
Token (
Feature activation+0.443
Top resid features:
sometimes
Tokensometimes
Feature activation+0.072
Top resid features:
written
Token written
Feature activation+0.045
Top resid features:
as
Token as
Feature activation+0.069
Top resid features:
âĢ
Token âĢ
Feature activation+0.088
Top resid features:
ľ
Tokenľ
Feature activation+0.054
Top resid features:
are
Token are
Feature activation+0.140
Top resid features:
not
Token not
Feature activation+0.133
Top resid features:
fully
Token fully
Feature activation+0.081
Top resid features:
paid
Token paid
Feature activation+0.125
Top resid features:
for
Token for
Feature activation+0.134
Top resid features:
or
Token or
Feature activation+0.250
Top resid features:
are
Token are
Feature activation+0.235
Top resid features:
being
Token being
Feature activation+0.000
Top resid features:
sold
Token sold
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
cons
Token cons
Feature activation+0.000
Top resid features:
has
Token has
Feature activation-0.018
Top resid features:
an
Token an
Feature activation-0.002
Top resid features:
interest
Token interest
Feature activation-0.040
Top resid features:
(
Token (
Feature activation+0.198
Top resid features:
for
Tokenfor
Feature activation+0.141
Top resid features:
example
Token example
Feature activation+0.429
Top resid features:
,
Token,
Feature activation+0.349
Top resid features:
the
Token the
Feature activation+0.208
Top resid features:
products
Token products
Feature activation+0.078
Top resid features:
are
Token are
Feature activation+0.254
Top resid features:
not
Token not
Feature activation+0.180
Top resid features:
ISO
TokenISO
Feature activation+0.080
Top resid features:
123
Token 123
Feature activation+0.122
Top resid features:
12
Token12
Feature activation+0.128
Top resid features:
-
Token-
Feature activation+0.104
Top resid features:
2
Token2
Feature activation+0.127
Top resid features:
:
Token:
Feature activation+0.405
Top resid features:
2015
Token2015
Feature activation+0.197
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
international
Token international
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.165
Top resid features:
Ang
TokenAng
Feature activation+0.095
Top resid features:
ew
Tokenew
Feature activation+0.102
Top resid features:
.
Token.
Feature activation+0.433
Top resid features:
Chem
Token Chem
Feature activation+0.098
Top resid features:
.
Token.
Feature activation+0.499
Top resid features:
Int
Token Int
Feature activation+0.174
Top resid features:
.
Token.
Feature activation+0.412
Top resid features:
Ed
Token Ed
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
2015
Token 2015
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.325
Top resid features:
18
Token 18
Feature activation+0.130
Top resid features:
July
Token July
Feature activation+0.178
Top resid features:
18
Token 18
Feature activation+0.136
Top resid features:
53
Token53
Feature activation+0.151
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.371
Top resid features:
4
Token 4
Feature activation+0.335
Top resid features:
February
Token February
Feature activation+0.238
Top resid features:
1928
Token 1928
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
Lord
Token Lord
Feature activation-0.012
Top resid features:
Voldemort
Token Voldemort
Feature activation-0.014
Top resid features:
(
Token (
Feature activation+0.198
Top resid features:
al
Tokenal
Feature activation+0.048
Top resid features:
as
Tokenas
Feature activation+0.074
Top resid features:
,
Token,
Feature activation+0.353
Top resid features:
for
Token for
Feature activation+0.148
Top resid features:
the
Token the
Feature activation+0.136
Top resid features:
select
Token select
Feature activation+0.124
Top resid features:
few
Token few
Feature activation+0.165
Top resid features:
who
Token who
Feature activation+0.207
Top resid features:
heated
Token heated
Feature activation-0.000
Top resid features:
discussion
Token discussion
Feature activation-0.007
Top resid features:
with
Token with
Feature activation-0.023
Top resid features:
one
Token one
Feature activation-0.003
Top resid features:
another
Token another
Feature activation-0.022
Top resid features:
(
Token (
Feature activation+0.407
Top resid features:
in
Tokenin
Feature activation+0.086
Top resid features:
English
Token English
Feature activation+0.069
Top resid features:
,
Token,
Feature activation+0.316
Top resid features:
for
Token for
Feature activation+0.196
Top resid features:
neither
Token neither
Feature activation+0.111
Top resid features:
âĢ
TokenâĢ
Feature activation-0.005
Top resid features:
Ļ
TokenĻ
Feature activation-0.008
Top resid features:
t
Tokent
Feature activation-0.006
Top resid features:
be
Token be
Feature activation-0.009
Top resid features:
attending
Token attending
Feature activation-0.012
Top resid features:
(
Token (
Feature activation+0.366
Top resid features:
though
Tokenthough
Feature activation+0.140
Top resid features:
I
Token I
Feature activation+0.118
Top resid features:
did
Token did
Feature activation+0.128
Top resid features:
get
Token get
Feature activation+0.082
Top resid features:
to
Token to
Feature activation+0.134
Top resid features:
run
Token run
Feature activation-0.021
Top resid features:
about
Token about
Feature activation+0.002
Top resid features:
$
Token $
Feature activation+0.002
Top resid features:
300
Token300
Feature activation+0.001
Top resid features:
each
Token each
Feature activation-0.013
Top resid features:
(
Token (
Feature activation+0.406
Top resid features:
the
Tokenthe
Feature activation+0.120
Top resid features:
company
Token company
Feature activation+0.101
Top resid features:
âĢ
TokenâĢ
Feature activation+0.241
Top resid features:
Ļ
TokenĻ
Feature activation+0.065
Top resid features:
s
Tokens
Feature activation+0.063
Top resid features:
has
Token has
Feature activation-0.020
Top resid features:
an
Token an
Feature activation-0.001
Top resid features:
interest
Token interest
Feature activation-0.039
Top resid features:
(
Token (
Feature activation+0.215
Top resid features:
for
Tokenfor
Feature activation+0.219
Top resid features:
example
Token example
Feature activation+0.419
Top resid features:
,
Token,
Feature activation+0.364
Top resid features:
the
Token the
Feature activation+0.221
Top resid features:
products
Token products
Feature activation+0.116
Top resid features:
are
Token are
Feature activation+0.327
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
oon
Tokenoon
Feature activation-0.012
Top resid features:
Lore
Token Lore
Feature activation-0.065
Top resid features:
nt
Tokennt
Feature activation+0.003
Top resid features:
z
Tokenz
Feature activation-0.012
Top resid features:
(
Token (
Feature activation+0.101
Top resid features:
;
Token;
Feature activation+0.784
Top resid features:
18
Token 18
Feature activation+0.240
Top resid features:
July
Token July
Feature activation+0.234
Top resid features:
18
Token 18
Feature activation+0.216
Top resid features:
53
Token53
Feature activation+0.180
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.251
Top resid features:
heated
Token heated
Feature activation-0.001
Top resid features:
discussion
Token discussion
Feature activation-0.008
Top resid features:
with
Token with
Feature activation-0.023
Top resid features:
one
Token one
Feature activation-0.002
Top resid features:
another
Token another
Feature activation-0.023
Top resid features:
(
Token (
Feature activation+0.442
Top resid features:
in
Tokenin
Feature activation+0.075
Top resid features:
English
Token English
Feature activation+0.054
Top resid features:
,
Token,
Feature activation+0.283
Top resid features:
for
Token for
Feature activation+0.137
Top resid features:
neither
Token neither
Feature activation+0.096
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
context
Tokencontext
Feature activation-0.011
Top resid features:
ual
Tokenual
Feature activation-0.000
Top resid features:
ized
Tokenized
Feature activation-0.010
Top resid features:
form
Token form
Feature activation-0.016
Top resid features:
(
Token (
Feature activation+0.393
Top resid features:
e
Tokene
Feature activation+0.050
Top resid features:
.
Token.
Feature activation+0.098
Top resid features:
g
Tokeng
Feature activation+0.053
Top resid features:
.,
Token.,
Feature activation+0.205
Top resid features:
âĢ
Token âĢ
Feature activation+0.108
Top resid features:
have
Token have
Feature activation+0.112
Top resid features:
not
Token not
Feature activation+0.126
Top resid features:
read
Token read
Feature activation+0.098
Top resid features:
the
Token the
Feature activation+0.157
Top resid features:
books
Token books
Feature activation+0.108
Top resid features:
,
Token,
Feature activation+0.365
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
spoiler
Token spoiler
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
coming
Token coming
Feature activation+0.000
Top resid features:
).
Token).
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.03

Head 2: 0.05

Head 3: 0.08

Head 4: 0.02

Head 5: 0.09

Head 6: 0.14

Head 7: 0.06

Head 8: 0.06

Head 9: 0.07

Head 10: 0.26

Head 11: 0.07

Positive logits

…)3.34

)."3.28

.)3.18

.).3.14

).3.10

?).3.04

.")3.03

)}3.03

),"3.02

...)2.96

!).2.95

)]2.95

?)2.92

").2.91

})2.90

)!2.90

.)2.90

.),2.90

)"2.85

),2.84

Negative logits

guiName-1.49

etheless-1.41

wcs-1.31

sequ-1.30

":[{"-1.29

agnetic-1.22

mining-1.18

415-1.15

brid-1.15

20439-1.15

stri-1.15

Listen-1.14

ween-1.12

patient-1.09

leeve-1.08

stru-1.08

odcast-1.08

................................-1.06

ItemTracker-1.06

-1.05

INTERVAL 1.477 - 1.641
CONTAINS 0.001%

12
Token12
Feature activation+0.841
-
Token-
Feature activation+1.089
2
Token2
Feature activation+1.086
:
Token:
Feature activation+1.263
2015
Token2015
Feature activation+1.471
âĢ
TokenâĢ
Feature activation+1.620
Ŀ
TokenĿ
Feature activation+1.568
)
Token)
Feature activation+0.562
international
Token international
Feature activation+0.033
safety
Token safety
Feature activation+0.000
standards
Token standards
Feature activation+0.000
are
Token are
Feature activation+1.373
not
Token not
Feature activation+1.577
fully
Token fully
Feature activation+1.637
paid
Token paid
Feature activation+1.495
for
Token for
Feature activation+1.641
or
Token or
Feature activation+1.572
are
Token are
Feature activation+1.522
being
Token being
Feature activation+1.257
sold
Token sold
Feature activation+1.305
on
Token on
Feature activation+0.981
cons
Token cons
Feature activation+0.931
example
Token example
Feature activation+0.071
,
Token,
Feature activation+0.790
the
Token the
Feature activation+0.955
products
Token products
Feature activation+1.130
are
Token are
Feature activation+1.373
not
Token not
Feature activation+1.577
fully
Token fully
Feature activation+1.637
paid
Token paid
Feature activation+1.495
for
Token for
Feature activation+1.641
or
Token or
Feature activation+1.572
are
Token are
Feature activation+1.522
products
Token products
Feature activation+1.130
are
Token are
Feature activation+1.373
not
Token not
Feature activation+1.577
fully
Token fully
Feature activation+1.637
paid
Token paid
Feature activation+1.495
for
Token for
Feature activation+1.641
or
Token or
Feature activation+1.572
are
Token are
Feature activation+1.522
being
Token being
Feature activation+1.257
sold
Token sold
Feature activation+1.305
on
Token on
Feature activation+0.981
,
Token,
Feature activation+0.790
the
Token the
Feature activation+0.955
products
Token products
Feature activation+1.130
are
Token are
Feature activation+1.373
not
Token not
Feature activation+1.577
fully
Token fully
Feature activation+1.637
paid
Token paid
Feature activation+1.495
for
Token for
Feature activation+1.641
or
Token or
Feature activation+1.572
are
Token are
Feature activation+1.522
being
Token being
Feature activation+1.257

INTERVAL 1.313 - 1.477
CONTAINS 0.002%

for
Tokenfor
Feature activation+0.000
example
Token example
Feature activation+0.071
,
Token,
Feature activation+0.790
the
Token the
Feature activation+0.955
products
Token products
Feature activation+1.130
are
Token are
Feature activation+1.373
not
Token not
Feature activation+1.577
fully
Token fully
Feature activation+1.637
paid
Token paid
Feature activation+1.495
for
Token for
Feature activation+1.641
or
Token or
Feature activation+1.572
The
TokenThe
Feature activation+0.813
Euro
Token Euro
Feature activation+0.749
v
Tokenv
Feature activation+0.978
ish
Tokenish
Feature activation+0.927
âĢ
TokenâĢ
Feature activation+1.117
Ŀ
TokenĿ
Feature activation+1.327
in
Token in
Feature activation+1.024
the
Token the
Feature activation+1.005
press
Token press
Feature activation+0.988
release
Token release
Feature activation+1.146
is
Token is
Feature activation+1.046
July
Token July
Feature activation+0.730
18
Token 18
Feature activation+0.856
53
Token53
Feature activation+0.768
âĢĵ
Token âĢĵ
Feature activation+1.364
4
Token 4
Feature activation+1.254
February
Token February
Feature activation+1.434
1928
Token 1928
Feature activation+1.234
)
Token)
Feature activation+0.374
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
Dutch
Token Dutch
Feature activation+0.000
;
Token;
Feature activation+0.000
18
Token 18
Feature activation+0.000
July
Token July
Feature activation+0.730
18
Token 18
Feature activation+0.856
53
Token53
Feature activation+0.768
âĢĵ
Token âĢĵ
Feature activation+1.364
4
Token 4
Feature activation+1.254
February
Token February
Feature activation+1.434
1928
Token 1928
Feature activation+1.234
)
Token)
Feature activation+0.374
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.525
select
Token select
Feature activation+0.857
few
Token few
Feature activation+1.200
who
Token who
Feature activation+0.878
have
Token have
Feature activation+1.126
not
Token not
Feature activation+1.421
read
Token read
Feature activation+1.268
the
Token the
Feature activation+1.268
books
Token books
Feature activation+1.223
,
Token,
Feature activation+1.335
a
Token a
Feature activation+1.069

INTERVAL 1.149 - 1.313
CONTAINS 0.011%

chicken
Token chicken
Feature activation+0.655
,
Token,
Feature activation+0.608
21
Token 21
Feature activation+0.815
.
Token.
Feature activation+0.862
9
Token9
Feature activation+1.005
kg
Token kg
Feature activation+1.220
of
Token of
Feature activation+0.986
pork
Token pork
Feature activation+0.963
and
Token and
Feature activation+0.837
14
Token 14
Feature activation+0.955
kg
Token kg
Feature activation+1.129
they
Token they
Feature activation+0.832
've
Token've
Feature activation+0.946
had
Token had
Feature activation+0.973
to
Token to
Feature activation+0.859
set
Token set
Feature activation+0.931
up
Token up
Feature activation+1.218
"
Token "
Feature activation+0.911
san
Tokensan
Feature activation+0.707
ct
Tokenct
Feature activation+0.568
u
Tokenu
Feature activation+0.782
aries
Tokenaries
Feature activation+0.701
shared
Token shared
Feature activation+1.040
_
Token_
Feature activation+0.912
ptr
Tokenptr
Feature activation+0.923
instances
Token instances
Feature activation+0.936
pointing
Token pointing
Feature activation+1.061
to
Token to
Feature activation+1.169
this
Token this
Feature activation+1.090
object
Token object
Feature activation+0.957
),
Token),
Feature activation+0.033
then
Token then
Feature activation+0.000
that
Token that
Feature activation+0.000
B
TokenB
Feature activation+0.224
inary
Tokeninary
Feature activation+0.315
star
Token star
Feature activation+0.681
apocalypse
Token apocalypse
Feature activation+0.889
âĢ
TokenâĢ
Feature activation+1.066
ľ
Tokenľ
Feature activation+1.264
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
that
Token that
Feature activation+0.000
5
Token 5
Feature activation+0.005
5
Token 5
Feature activation+0.372
5
Token 5
Feature activation+0.721
5
Token 5
Feature activation+0.997
2
Token 2
Feature activation+1.010
3
Token 3
Feature activation+1.191
4
Token 4
Feature activation+1.280
5
Token 5
Feature activation+1.299
In
Token In
Feature activation+1.053
this
Token this
Feature activation+0.544
study
Token study
Feature activation+0.343

INTERVAL 0.985 - 1.149
CONTAINS 0.028%

ish
Tokenish
Feature activation+0.927
âĢ
TokenâĢ
Feature activation+1.117
Ŀ
TokenĿ
Feature activation+1.327
in
Token in
Feature activation+1.024
the
Token the
Feature activation+1.005
press
Token press
Feature activation+0.988
release
Token release
Feature activation+1.146
is
Token is
Feature activation+1.046
painful
Token painful
Feature activation+0.965
).
Token).
Feature activation+0.219
There
Token There
Feature activation+0.000
you
Token you
Feature activation+0.339
can
Token can
Feature activation+0.483
call
Token call
Feature activation+0.602
them
Token them
Feature activation+0.794
âĢ
Token âĢ
Feature activation+0.804
ľ
Tokenľ
Feature activation+0.992
The
TokenThe
Feature activation+0.697
sis
Tokensis
Feature activation+0.536
Statements
Token Statements
Feature activation+0.606
âĢ
TokenâĢ
Feature activation+0.703
Ŀ
TokenĿ
Feature activation+0.717
see
Tokensee
Feature activation+0.000
:
Token:
Feature activation+0.000
lots
Token lots
Feature activation+0.303
of
Token of
Feature activation+0.569
cheering
Token cheering
Feature activation+0.642
and
Token and
Feature activation+0.998
cl
Token cl
Feature activation+0.924
apping
Tokenapping
Feature activation+1.194
as
Token as
Feature activation+1.059
creepy
Token creepy
Feature activation+1.113
Todd
Token Todd
Feature activation+1.085
ľ
Tokenľ
Feature activation+0.691
I
TokenI
Feature activation+0.586
like
Token like
Feature activation+0.671
being
Token being
Feature activation+0.920
around
Token around
Feature activation+0.877
other
Token other
Feature activation+1.108
people
Token people
Feature activation+1.011
âĢ
TokenâĢ
Feature activation+1.157
Ŀ
TokenĿ
Feature activation+1.336
)
Token)
Feature activation+0.386
we
Token we
Feature activation+0.000
around
Token around
Feature activation+0.364
38
Token 38
Feature activation+0.759
years
Token years
Feature activation+0.934
because
Token because
Feature activation+0.955
of
Token of
Feature activation+1.071
child
Token child
Feature activation+1.068
mortality
Token mortality
Feature activation+0.944
,
Token,
Feature activation+1.109
but
Token but
Feature activation+0.980
only
Token only
Feature activation+1.024
another
Token another
Feature activation+0.816

INTERVAL 0.820 - 0.985
CONTAINS 0.052%

Nine
TokenNine
Feature activation+0.982
Fish
Token Fish
Feature activation+0.992
With
Token With
Feature activation+1.032
'
Token '
Feature activation+0.891
H
TokenH
Feature activation+0.820
ands
Tokenands
Feature activation+0.954
'
Token'
Feature activation+0.743
Found
Token Found
Feature activation+0.789
to
Token to
Feature activation+0.936
Be
Token Be
Feature activation+0.892
New
Token New
Feature activation+0.858
6
Token6
Feature activation+0.757
F
TokenF
Feature activation+0.882
12
Token 12
Feature activation+0.810
/
Token/
Feature activation+0.978
24
Token24
Feature activation+0.884
V
TokenV
Feature activation+0.954
,
Token,
Feature activation+0.867
6
Token 6
Feature activation+0.864
A
TokenA
Feature activation+0.862
)
Token)
Feature activation+0.200
Ċ
TokenĊ
Feature activation+0.048
don
Token don
Feature activation+0.467
âĢ
TokenâĢ
Feature activation+0.637
Ļ
TokenĻ
Feature activation+1.069
t
Tokent
Feature activation+0.819
quite
Token quite
Feature activation+0.924
have
Token have
Feature activation+0.968
the
Token the
Feature activation+0.995
money
Token money
Feature activation+0.756
for
Token for
Feature activation+0.841
that
Token that
Feature activation+1.003
),
Token),
Feature activation+0.000
¯
Token¯
Feature activation+0.446
ر
Tokenر
Feature activation+0.478
ÙĪ
TokenÙĪ
Feature activation+0.729
اØ
TokenاØ
Feature activation+0.657
²
Token²
Feature activation+0.693
Ùĩ
TokenÙĩ
Feature activation+0.919
âĢİ
TokenâĢİ
Feature activation+0.729
,
Token,
Feature activation+0.766
literally
Token literally
Feature activation+0.807
"
Token "
Feature activation+0.800
gate
Tokengate
Feature activation+0.487
most
Token most
Feature activation+0.000
cases
Token cases
Feature activation+0.032
of
Token of
Feature activation+0.336
real
Token real
Feature activation+0.418
life
Token life
Feature activation+0.735
examples
Token examples
Feature activation+0.827
).
Token).
Feature activation+0.194
If
Token If
Feature activation+0.000
anything
Token anything
Feature activation+0.000
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.000

INTERVAL 0.656 - 0.820
CONTAINS 0.079%

should
Token should
Feature activation+0.064
probably
Token probably
Feature activation+0.481
have
Token have
Feature activation+0.432
his
Token his
Feature activation+0.609
deck
Token deck
Feature activation+0.539
bought
Token bought
Feature activation+0.814
)
Token)
Feature activation+0.000
An
Token An
Feature activation+0.000
cano
Tokencano
Feature activation+0.000
for
Token for
Feature activation+0.000
...
Token...
Feature activation+0.000
(
Token (
Feature activation+0.000
though
Tokenthough
Feature activation+0.000
I
Token I
Feature activation+0.064
did
Token did
Feature activation+0.288
get
Token get
Feature activation+0.353
to
Token to
Feature activation+0.747
see
Token see
Feature activation+0.795
Season
Token Season
Feature activation+0.773
11
Token 11
Feature activation+0.849
âĢ
TokenâĢ
Feature activation+1.024
Ļ
TokenĻ
Feature activation+1.398
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.115
ve
Tokenve
Feature activation+0.086
named
Token named
Feature activation+0.311
mine
Token mine
Feature activation+0.590
âĢ
Token âĢ
Feature activation+0.812
ľ
Tokenľ
Feature activation+0.941
av
Tokenav
Feature activation+0.614
g
Tokeng
Feature activation+0.635
_
Token_
Feature activation+0.805
color
Tokencolor
Feature activation+0.701
launch
Token launch
Feature activation+0.495
and
Token and
Feature activation+0.709
view
Token view
Feature activation+0.777
Tactics
Token Tactics
Feature activation+0.756
as
Token as
Feature activation+0.744
a
Token a
Feature activation+0.795
separate
Token separate
Feature activation+0.766
game
Token game
Feature activation+0.810
),
Token),
Feature activation+0.000
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
(
Token (
Feature activation+0.000
even
Tokeneven
Feature activation+0.000
if
Token if
Feature activation+0.018
the
Token the
Feature activation+0.209
raids
Token raids
Feature activation+0.724
were
Token were
Feature activation+0.691
often
Token often
Feature activation+1.058
carried
Token carried
Feature activation+0.918
out
Token out
Feature activation+0.793
on
Token on
Feature activation+0.930
smart
Token smart
Feature activation+0.942

INTERVAL 0.492 - 0.656
CONTAINS 0.096%

1
Token1
Feature activation+0.353
,
Token,
Feature activation+0.554
a
Tokena
Feature activation+0.516
_
Token_
Feature activation+0.510
1
Token1
Feature activation+0.417
,
Token,
Feature activation+0.559
r
Tokenr
Feature activation+0.526
_
Token_
Feature activation+0.472
2
Token2
Feature activation+0.395
,
Token,
Feature activation+0.594
s
Tokens
Feature activation+0.496
al
Tokenal
Feature activation+0.000
vo
Tokenvo
Feature activation+0.000
-
Token-
Feature activation+0.000
Or
TokenOr
Feature activation+0.229
t
Tokent
Feature activation+0.440
iz
Tokeniz
Feature activation+0.528
et
Token et
Feature activation+0.702
al
Token al
Feature activation+0.744
.
Token.
Feature activation+0.751
2014
Token 2014
Feature activation+0.620
)
Token)
Feature activation+0.092
Credit
TokenCredit
Feature activation+0.000
:
Token:
Feature activation+0.000
F
Token F
Feature activation+0.195
ot
Tokenot
Feature activation+0.338
ose
Tokenose
Feature activation+0.416
arch
Tokenarch
Feature activation+0.497
/
Token/
Feature activation+0.814
Getty
TokenGetty
Feature activation+0.886
Images
Token Images
Feature activation+0.761
).
Token).
Feature activation+0.047
Ċ
TokenĊ
Feature activation+0.000
ve
Tokenve
Feature activation+0.086
named
Token named
Feature activation+0.311
mine
Token mine
Feature activation+0.590
âĢ
Token âĢ
Feature activation+0.812
ľ
Tokenľ
Feature activation+0.941
av
Tokenav
Feature activation+0.614
g
Tokeng
Feature activation+0.635
_
Token_
Feature activation+0.805
color
Tokencolor
Feature activation+0.701
.
Token.
Feature activation+0.865
py
Tokenpy
Feature activation+0.873
also
Token also
Feature activation+0.000
why
Token why
Feature activation+0.217
there
Token there
Feature activation+0.335
will
Token will
Feature activation+0.399
be
Token be
Feature activation+0.532
a
Token a
Feature activation+0.597
major
Token major
Feature activation+0.768
shoe
Token shoe
Feature activation+0.786
shopping
Token shopping
Feature activation+0.803
spree
Token spree
Feature activation+0.673
in
Token in
Feature activation+0.644

INTERVAL 0.328 - 0.492
CONTAINS 0.105%

ized
Tokenized
Feature activation+0.000
the
Token the
Feature activation+0.000
red
Token red
Feature activation+0.114
flags
Token flags
Feature activation+0.266
I
Token I
Feature activation+0.428
see
Token see
Feature activation+0.419
):
Token):
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
H
TokenH
Feature activation+0.000
.
Token.
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
(
Token (
Feature activation+0.000
any
Tokenany
Feature activation+0.000
existing
Token existing
Feature activation+0.062
weapons
Token weapons
Feature activation+0.218
would
Token would
Feature activation+0.396
be
Token be
Feature activation+0.587
transferred
Token transferred
Feature activation+0.710
to
Token to
Feature activation+0.943
the
Token the
Feature activation+0.888
equipment
Token equipment
Feature activation+0.924
progress
Token progress
Feature activation+0.142
in
Token in
Feature activation+0.440
your
Token your
Feature activation+0.451
game
Token game
Feature activation+0.321
profile
Token profile
Feature activation+0.620
âĢĶ
Token âĢĶ
Feature activation+0.468
achievements
Token achievements
Feature activation+0.505
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
the
Token the
Feature activation+0.000
Pill
Token Pill
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.007
Ļ
TokenĻ
Feature activation+0.245
s
Tokens
Feature activation+0.333
1
Token 1
Feature activation+0.335
in
Token in
Feature activation+0.587
11
Token 11
Feature activation+0.419
;
Token;
Feature activation+0.508
with
Token with
Feature activation+0.628
(
Token (
Feature activation+0.000
balance
Tokenbalance
Feature activation+0.000
valid
Token valid
Feature activation+0.000
for
Token for
Feature activation+0.000
6
Token 6
Feature activation+0.000
months
Token months
Feature activation+0.358
).
Token).
Feature activation+0.000
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
total
Token total
Feature activation+0.000
inv
Token inv
Feature activation+0.000

INTERVAL 0.164 - 0.328
CONTAINS 0.125%

any
Token any
Feature activation+0.000
ecosystem
Token ecosystem
Feature activation+0.000
(
Token (
Feature activation+0.000
present
Tokenpresent
Feature activation+0.000
or
Token or
Feature activation+0.000
past
Token past
Feature activation+0.210
[
Token[
Feature activation+0.349
2
Token2
Feature activation+0.084
])
Token])
Feature activation+0.000
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
pounds
Token pounds
Feature activation+0.000
(
Token (
Feature activation+0.000
just
Tokenjust
Feature activation+0.000
as
Token as
Feature activation+0.194
the
Token the
Feature activation+0.225
S
Token S
Feature activation+0.253
RT
TokenRT
Feature activation+0.447
8
Token8
Feature activation+0.569
can
Token can
Feature activation+0.607
).
Token).
Feature activation+0.000
The
Token The
Feature activation+0.000
victory
Token victory
Feature activation+0.303
regardless
Token regardless
Feature activation+0.344
of
Token of
Feature activation+0.389
the
Token the
Feature activation+0.399
score
Token score
Feature activation+0.109
of
Token of
Feature activation+0.214
either
Token either
Feature activation+0.355
match
Token match
Feature activation+0.067
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
happen
Token happen
Feature activation+0.000
until
Token until
Feature activation+0.000
after
Token after
Feature activation+0.099
Britain
Token Britain
Feature activation+0.004
official
Token official
Feature activation+0.439
leaves
Token leaves
Feature activation+0.271
the
Token the
Feature activation+0.305
EU
Token EU
Feature activation+0.287
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.438
Ŀ
TokenĿ
Feature activation+0.232
changing
Token changing
Feature activation+0.371
the
Token the
Feature activation+0.436
internal
Token internal
Feature activation+0.374
state
Token state
Feature activation+0.307
of
Token of
Feature activation+0.161
the
Token the
Feature activation+0.243
RT
Token RT
Feature activation+0.233
L
TokenL
Feature activation+0.097
component
Token component
Feature activation+0.187

INTERVAL 0.000 - 0.164
CONTAINS 99.501%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
performance
Token performance
Feature activation+0.000
presented
Token presented
Feature activation+0.000
here
Token here
Feature activation+0.000
ranges
Token ranges
Feature activation+0.000
widely
Token widely
Feature activation+0.000
over
Token over
Feature activation+0.000
terrain
Token terrain
Feature activation+0.000
both
Token both
Feature activation+0.000
new
Token new
Feature activation+0.000
and
Token and
Feature activation+0.000
off
Token off
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
has
Token has
Feature activation+0.000
thrown
Token thrown
Feature activation+0.000
the
Token the
Feature activation+0.000
Global
Token Global
Feature activation+0.000
Fund
Token Fund
Feature activation+0.000
a
Token a
Feature activation+0.000
lif
Token lif
Feature activation+0.000
eline
Tokeneline
Feature activation+0.000
2001
Token 2001
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
.
Token.
Feature activation+0.000
@
Token@
Feature activation+0.000
Pl
TokenPl
Feature activation+0.000
ano
Tokenano
Feature activation+0.000
Police
TokenPolice
Feature activation+0.000
De
TokenDe
Feature activation+0.000
pt
Tokenpt
Feature activation+0.000
looking
Token looking
Feature activation+0.000
The
Token The
Feature activation+0.000
Two
Token Two
Feature activation+0.000
Ron
Token Ron
Feature activation+0.000
n
Tokenn
Feature activation+0.000
ies
Tokenies
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+0.000
Vampire
Token Vampire
Feature activation+0.000
Lo
Token Lo
Feature activation+0.000
vers
Tokenvers
Feature activation+0.052
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
span
Token span
Feature activation+0.000
that
Token that
Feature activation+0.000
saw
Token saw
Feature activation+0.000
the
Token the
Feature activation+0.000
secretive
Token secretive
Feature activation+0.000
company
Token company
Feature activation+0.000
embarrassed
Token embarrassed
Feature activation+0.000
when
Token when
Feature activation+0.000
important
Token important
Feature activation+0.000
trade
Token trade
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 3 in H2.10: (feature 12139)

TOP ACTIVATIONS
MAX = 0.831

a
Tokena
Feature activation+0.012
ub
Tokenub
Feature activation+0.000
ol
Tokenol
Feature activation+0.057
was
Token was
Feature activation+0.415
suppose
Token suppose
Feature activation+0.655
to
Token to
Feature activation+0.791
give
Token give
Feature activation+0.684
the
Token the
Feature activation+0.494
soccer
Token soccer
Feature activation+0.307
team
Token team
Feature activation+0.228
,
Token,
Feature activation+0.348
Peters
Token Peters
Feature activation+0.200
St
Token St
Feature activation+0.156
.
Token.
Feature activation+0.206
If
Token If
Feature activation+0.453
you
Token you
Feature activation+0.684
're
Token're
Feature activation+0.712
driving
Token driving
Feature activation+0.588
,
Token,
Feature activation+0.549
parking
Token parking
Feature activation+0.260
will
Token will
Feature activation+0.175
be
Token be
Feature activation+0.123
211
Token 211
Feature activation+0.150
Peters
Token Peters
Feature activation+0.200
St
Token St
Feature activation+0.156
.
Token.
Feature activation+0.206
If
Token If
Feature activation+0.453
you
Token you
Feature activation+0.684
're
Token're
Feature activation+0.712
driving
Token driving
Feature activation+0.588
,
Token,
Feature activation+0.549
parking
Token parking
Feature activation+0.260
will
Token will
Feature activation+0.175
ub
Tokenub
Feature activation+0.000
ol
Tokenol
Feature activation+0.057
was
Token was
Feature activation+0.415
suppose
Token suppose
Feature activation+0.655
to
Token to
Feature activation+0.791
give
Token give
Feature activation+0.684
the
Token the
Feature activation+0.494
soccer
Token soccer
Feature activation+0.307
team
Token team
Feature activation+0.228
,
Token,
Feature activation+0.348
"
Token "
Feature activation+0.305
INC
TokenINC
Feature activation+0.069
.
Token.
Feature activation+0.140
COM
TokenCOM
Feature activation+0.009
<
Token <
Feature activation+0.289
javascript
Tokenjavascript
Feature activation+0.602
:
Token:
Feature activation+0.677
_
Token_
Feature activation+0.611
e
Tokene
Feature activation+0.467
(
Token(
Feature activation+0.410
%
Token%
Feature activation+0.322
7
Token7
Feature activation+0.372
.
Token.
Feature activation+0.000
Stan
Token Stan
Feature activation+0.000
Monte
Token Monte
Feature activation+0.000
ith
Tokenith
Feature activation+0.000
likes
Token likes
Feature activation+0.245
to
Token to
Feature activation+0.670
say
Token say
Feature activation+0.618
as
Token as
Feature activation+0.490
he
Token he
Feature activation+0.330
starts
Token starts
Feature activation+0.390
each
Token each
Feature activation+0.356
ech
Tokenech
Feature activation+0.116
a
Tokena
Feature activation+0.012
ub
Tokenub
Feature activation+0.000
ol
Tokenol
Feature activation+0.057
was
Token was
Feature activation+0.415
suppose
Token suppose
Feature activation+0.655
to
Token to
Feature activation+0.791
give
Token give
Feature activation+0.684
the
Token the
Feature activation+0.494
soccer
Token soccer
Feature activation+0.307
team
Token team
Feature activation+0.228
sh
Tokensh
Feature activation+0.303
an
Tokenan
Feature activation+0.194
Workers
Token Workers
Feature activation+0.250
'
Token'
Feature activation+0.497
Party
Token Party
Feature activation+0.522
(
Token (
Feature activation+0.650
WP
TokenWP
Feature activation+0.620
)
Token)
Feature activation+0.592
Hong
Token Hong
Feature activation+0.535
Kah
Token Kah
Feature activation+0.298
North
Token North
Feature activation+0.223
and
Token and
Feature activation+0.039
G
Token G
Feature activation+0.057
illing
Tokenilling
Feature activation+0.046
ham
Tokenham
Feature activation+0.005
during
Token during
Feature activation+0.418
his
Token his
Feature activation+0.630
career
Token career
Feature activation+0.494
,
Token,
Feature activation+0.454
said
Token said
Feature activation+0.308
:
Token:
Feature activation+0.348
"
Token "
Feature activation+0.422
Hastings
Token Hastings
Feature activation+0.115
Rd
Token Rd
Feature activation+0.067
.,
Token.,
Feature activation+0.345
in
Token in
Feature activation+0.518
late
Token late
Feature activation+0.533
November
Token November
Feature activation+0.613
.
Token.
Feature activation+0.309
With
Token With
Feature activation+0.268
a
Token a
Feature activation+0.182
sports
Token sports
Feature activation+0.114
bar
Token bar
Feature activation+0.018
ARS
TokenARS
Feature activation+0.110
INC
TokenINC
Feature activation+0.069
.
Token.
Feature activation+0.140
COM
TokenCOM
Feature activation+0.009
<
Token <
Feature activation+0.289
javascript
Tokenjavascript
Feature activation+0.602
:
Token:
Feature activation+0.677
_
Token_
Feature activation+0.611
e
Tokene
Feature activation+0.467
(
Token(
Feature activation+0.410
%
Token%
Feature activation+0.322
St
Token St
Feature activation+0.156
.
Token.
Feature activation+0.206
If
Token If
Feature activation+0.453
you
Token you
Feature activation+0.684
're
Token're
Feature activation+0.712
driving
Token driving
Feature activation+0.588
,
Token,
Feature activation+0.549
parking
Token parking
Feature activation+0.260
will
Token will
Feature activation+0.175
be
Token be
Feature activation+0.123
available
Token available
Feature activation+0.090
,
Token,
Feature activation+0.110
5
Token 5
Feature activation+0.034
SF
Token SF
Feature activation+0.000
M
TokenM
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.393
the
Tokenthe
Feature activation+0.575
list
Token list
Feature activation+0.464
just
Token just
Feature activation+0.536
goes
Token goes
Feature activation+0.330
on
Token on
Feature activation+0.235
with
Token with
Feature activation+0.126
Joint
Token Joint
Feature activation+0.000
Task
Token Task
Feature activation+0.000
Force
Token Force
Feature activation+0.000
101
Token 101
Feature activation+0.000
fills
Token fills
Feature activation+0.180
out
Token out
Feature activation+0.574
an
Token an
Feature activation+0.461
absentee
Token absentee
Feature activation+0.285
ballot
Token ballot
Feature activation+0.075
at
Token at
Feature activation+0.159
a
Token a
Feature activation+0.199
Europe
Token Europe
Feature activation+0.219
&
Token &
Feature activation+0.164
Asia
Token Asia
Feature activation+0.066
with
Token with
Feature activation+0.177
support
Token support
Feature activation+0.284
from
Token from
Feature activation+0.570
1000
Token 1000
Feature activation+0.294
more
Token more
Feature activation+0.223
scientific
Token scientific
Feature activation+0.227
societies
Token societies
Feature activation+0.183
and
Token and
Feature activation+0.108
ski
Tokenski
Feature activation+0.068
crystals
Token crystals
Feature activation+0.057
,
Token,
Feature activation+0.219
I
Token I
Feature activation+0.218
found
Token found
Feature activation+0.401
myself
Token myself
Feature activation+0.566
front
Token front
Feature activation+0.369
row
Token row
Feature activation+0.199
and
Token and
Feature activation+0.211
buzzing
Token buzzing
Feature activation+0.071
.
Token.
Feature activation+0.000
MOR
Token MOR
Feature activation+0.078
AL
TokenAL
Feature activation+0.075
ITY
TokenITY
Feature activation+0.000
There
Token There
Feature activation+0.217
are
Token are
Feature activation+0.408
,
Token,
Feature activation+0.565
then
Token then
Feature activation+0.420
,
Token,
Feature activation+0.281
significant
Token significant
Feature activation+0.022
practical
Token practical
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
Native
Token Native
Feature activation+0.000
American
Token American
Feature activation+0.000
tribes
Token tribes
Feature activation+0.000
who
Token who
Feature activation+0.188
rely
Token rely
Feature activation+0.340
on
Token on
Feature activation+0.563
the
Token the
Feature activation+0.340
river
Token river
Feature activation+0.103
âĢ
TokenâĢ
Feature activation+0.140
Ļ
TokenĻ
Feature activation+0.154
s
Tokens
Feature activation+0.165
Jerry
Token Jerry
Feature activation+0.304
Fal
Token Fal
Feature activation+0.081
well
Tokenwell
Feature activation+0.000
and
Token and
Feature activation+0.218
went
Token went
Feature activation+0.342
after
Token after
Feature activation+0.562
John
Token John
Feature activation+0.419
McCain
Token McCain
Feature activation+0.283
in
Token in
Feature activation+0.410
2000
Token 2000
Feature activation+0.398
,
Token,
Feature activation+0.486
where
Token where
Feature activation+0.230
her
Token her
Feature activation+0.465
colleagues
Token colleagues
Feature activation+0.305
have
Token have
Feature activation+0.458
fallen
Token fallen
Feature activation+0.500
in
Token in
Feature activation+0.561
love
Token love
Feature activation+0.404
with
Token with
Feature activation+0.581
him
Token him
Feature activation+0.342
.
Token.
Feature activation+0.173
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 0.167

Ta
Token Ta
Feature activation+0.014
Top resid features:
ech
Tokenech
Feature activation+0.017
Top resid features:
a
Tokena
Feature activation+0.011
Top resid features:
ub
Tokenub
Feature activation+0.011
Top resid features:
ol
Tokenol
Feature activation+0.008
Top resid features:
was
Token was
Feature activation+0.065
Top resid features:
suppose
Token suppose
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
give
Token give
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
soccer
Token soccer
Feature activation+0.000
Top resid features:
Gran
Token Gran
Feature activation+0.017
Top resid features:
ite
Tokenite
Feature activation+0.029
Top resid features:
Room
Token Room
Feature activation+0.029
Top resid features:
at
Token at
Feature activation+0.012
Top resid features:
211
Token 211
Feature activation+0.021
Top resid features:
Peters
Token Peters
Feature activation+0.030
Top resid features:
St
Token St
Feature activation-0.016
Top resid features:
.
Token.
Feature activation-0.016
Top resid features:
If
Token If
Feature activation-0.000
Top resid features:
you
Token you
Feature activation-0.052
Top resid features:
're
Token're
Feature activation+0.007
Top resid features:
at
Token at
Feature activation+0.015
Top resid features:
211
Token 211
Feature activation+0.016
Top resid features:
Peters
Token Peters
Feature activation+0.014
Top resid features:
St
Token St
Feature activation-0.059
Top resid features:
.
Token.
Feature activation-0.025
Top resid features:
If
Token If
Feature activation+0.042
Top resid features:
you
Token you
Feature activation+0.011
Top resid features:
're
Token're
Feature activation+0.000
Top resid features:
driving
Token driving
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
parking
Token parking
Feature activation+0.000
Top resid features:
Ta
Token Ta
Feature activation+0.011
Top resid features:
ech
Tokenech
Feature activation+0.014
Top resid features:
a
Tokena
Feature activation+0.013
Top resid features:
ub
Tokenub
Feature activation+0.008
Top resid features:
ol
Tokenol
Feature activation+0.011
Top resid features:
was
Token was
Feature activation+0.046
Top resid features:
suppose
Token suppose
Feature activation+0.044
Top resid features:
to
Token to
Feature activation-0.035
Top resid features:
give
Token give
Feature activation-0.034
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
soccer
Token soccer
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.046
Top resid features:
you
Token you
Feature activation+0.011
Top resid features:
are
Token are
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
I
Token I
Feature activation-0.002
Top resid features:
apologize
Token apologize
Feature activation-0.002
Top resid features:
Dr
Token Dr
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Stan
Token Stan
Feature activation+0.005
Top resid features:
Monte
Token Monte
Feature activation-0.013
Top resid features:
ith
Tokenith
Feature activation-0.000
Top resid features:
likes
Token likes
Feature activation+0.121
Top resid features:
to
Token to
Feature activation+0.045
Top resid features:
say
Token say
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
starts
Token starts
Feature activation+0.000
Top resid features:
ech
Tokenech
Feature activation+0.018
Top resid features:
a
Tokena
Feature activation+0.012
Top resid features:
ub
Tokenub
Feature activation+0.005
Top resid features:
ol
Tokenol
Feature activation+0.004
Top resid features:
was
Token was
Feature activation+0.061
Top resid features:
suppose
Token suppose
Feature activation+0.088
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
give
Token give
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
soccer
Token soccer
Feature activation+0.000
Top resid features:
team
Token team
Feature activation+0.000
Top resid features:
S
Token S
Feature activation+0.020
Top resid features:
DP
TokenDP
Feature activation+0.027
Top resid features:
Feng
Token Feng
Feature activation+0.031
Top resid features:
sh
Tokensh
Feature activation+0.027
Top resid features:
an
Tokenan
Feature activation+0.026
Top resid features:
Workers
Token Workers
Feature activation+0.045
Top resid features:
'
Token'
Feature activation-0.027
Top resid features:
Party
Token Party
Feature activation-0.112
Top resid features:
(
Token (
Feature activation-0.060
Top resid features:
WP
TokenWP
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
Town
Token Town
Feature activation+0.019
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
G
Token G
Feature activation-0.020
Top resid features:
illing
Tokenilling
Feature activation-0.014
Top resid features:
ham
Tokenham
Feature activation-0.044
Top resid features:
during
Token during
Feature activation+0.110
Top resid features:
his
Token his
Feature activation-0.103
Top resid features:
career
Token career
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
415
Token 415
Feature activation-0.017
Top resid features:
W
Token W
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
Hastings
Token Hastings
Feature activation+0.010
Top resid features:
Rd
Token Rd
Feature activation-0.003
Top resid features:
.,
Token.,
Feature activation+0.109
Top resid features:
in
Token in
Feature activation-0.110
Top resid features:
late
Token late
Feature activation-0.108
Top resid features:
November
Token November
Feature activation-0.012
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
With
Token With
Feature activation+0.000
Top resid features:
EST
TokenEST
Feature activation+0.005
Top resid features:
ARS
TokenARS
Feature activation-0.004
Top resid features:
INC
TokenINC
Feature activation-0.050
Top resid features:
.
Token.
Feature activation-0.098
Top resid features:
COM
TokenCOM
Feature activation-0.102
Top resid features:
<
Token <
Feature activation+0.136
Top resid features:
javascript
Tokenjavascript
Feature activation+0.020
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
_
Token_
Feature activation+0.000
Top resid features:
e
Tokene
Feature activation+0.000
Top resid features:
(
Token(
Feature activation+0.000
Top resid features:
ed
Tokened
Feature activation+0.009
Top resid features:
at
Token at
Feature activation+0.004
Top resid features:
The
Token The
Feature activation+0.019
Top resid features:
Gran
Token Gran
Feature activation+0.014
Top resid features:
ite
Tokenite
Feature activation+0.023
Top resid features:
Room
Token Room
Feature activation+0.027
Top resid features:
at
Token at
Feature activation+0.012
Top resid features:
211
Token 211
Feature activation+0.023
Top resid features:
Peters
Token Peters
Feature activation+0.015
Top resid features:
St
Token St
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
MS
TokenMS
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
5
Token 5
Feature activation-0.042
Top resid features:
SF
Token SF
Feature activation-0.021
Top resid features:
M
TokenM
Feature activation-0.035
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.164
Top resid features:
the
Tokenthe
Feature activation-0.144
Top resid features:
list
Token list
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
goes
Token goes
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
ained
Tokenained
Feature activation+0.027
Top resid features:
Joint
Token Joint
Feature activation-0.025
Top resid features:
Task
Token Task
Feature activation+0.023
Top resid features:
Force
Token Force
Feature activation+0.015
Top resid features:
101
Token 101
Feature activation-0.018
Top resid features:
fills
Token fills
Feature activation+0.167
Top resid features:
out
Token out
Feature activation-0.013
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
absentee
Token absentee
Feature activation+0.000
Top resid features:
ballot
Token ballot
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
Europe
Token Europe
Feature activation-0.044
Top resid features:
&
Token &
Feature activation+0.002
Top resid features:
Asia
Token Asia
Feature activation-0.122
Top resid features:
with
Token with
Feature activation-0.023
Top resid features:
support
Token support
Feature activation+0.054
Top resid features:
from
Token from
Feature activation-0.049
Top resid features:
1000
Token 1000
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
scientific
Token scientific
Feature activation+0.000
Top resid features:
societies
Token societies
Feature activation+0.000
Top resid features:
arov
Tokenarov
Feature activation+0.003
Top resid features:
ski
Tokenski
Feature activation+0.014
Top resid features:
crystals
Token crystals
Feature activation-0.018
Top resid features:
,
Token,
Feature activation-0.025
Top resid features:
I
Token I
Feature activation-0.077
Top resid features:
found
Token found
Feature activation+0.160
Top resid features:
myself
Token myself
Feature activation-0.116
Top resid features:
front
Token front
Feature activation+0.000
Top resid features:
row
Token row
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
buzzing
Token buzzing
Feature activation+0.000
Top resid features:
ING
TokenING
Feature activation+0.006
Top resid features:
TR
Token TR
Feature activation-0.001
Top resid features:
AD
TokenAD
Feature activation+0.003
Top resid features:
ITION
TokenITION
Feature activation+0.007
Top resid features:
AL
TokenAL
Feature activation+0.005
Top resid features:
NOT
Token NOT
Feature activation+0.030
Top resid features:
IONS
TokenIONS
Feature activation-0.001
Top resid features:
OF
Token OF
Feature activation-0.001
Top resid features:
MOR
Token MOR
Feature activation-0.006
Top resid features:
AL
TokenAL
Feature activation-0.005
Top resid features:
ITY
TokenITY
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
Miller
Token Miller
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
who
Token who
Feature activation+0.008
Top resid features:
twice
Token twice
Feature activation+0.003
Top resid features:
surveyed
Token surveyed
Feature activation+0.030
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
area
Token area
Feature activation-0.003
Top resid features:
for
Token for
Feature activation+0.018
Top resid features:
local
Token local
Feature activation-0.006
Top resid features:
Native
Token Native
Feature activation+0.001
Top resid features:
Jerry
Token Jerry
Feature activation-0.012
Top resid features:
Fal
Token Fal
Feature activation-0.014
Top resid features:
well
Tokenwell
Feature activation+0.004
Top resid features:
and
Token and
Feature activation-0.069
Top resid features:
went
Token went
Feature activation-0.053
Top resid features:
after
Token after
Feature activation+0.037
Top resid features:
John
Token John
Feature activation+0.000
Top resid features:
McCain
Token McCain
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
2000
Token 2000
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Care
Token Care
Feature activation+0.017
Top resid features:
line
Tokenline
Feature activation+0.016
Top resid features:
in
Token in
Feature activation+0.030
Top resid features:
Black
Token Black
Feature activation+0.023
Top resid features:
wood
Tokenwood
Feature activation+0.024
Top resid features:
where
Token where
Feature activation+0.030
Top resid features:
her
Token her
Feature activation-0.041
Top resid features:
colleagues
Token colleagues
Feature activation-0.025
Top resid features:
have
Token have
Feature activation-0.008
Top resid features:
fallen
Token fallen
Feature activation-0.060
Top resid features:
in
Token in
Feature activation-0.050
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.03

Head 2: 0.05

Head 3: 0.08

Head 4: 0.02

Head 5: 0.08

Head 6: 0.08

Head 7: 0.10

Head 8: 0.06

Head 9: 0.08

Head 10: 0.26

Head 11: 0.11

Positive logits

]).1.15

]);1.06

}}1.03

]."0.99

respectively0.98

)).0.97

}}0.94

.).0.93

}.0.93

%).0.91

latter0.89

].0.88

});0.87

})0.83

]]0.83

]),0.82

>)0.82

cele0.81

paralle0.81

=]0.80

Negative logits

estern-0.95

Earthqu-0.78

udic-0.74

Decay-0.73

panic-0.72

minist-0.70

Cause-0.68

DRAG-0.68

vous-0.68

EFF-0.67

Detect-0.66

の�-0.66

itzer-0.66

Det-0.65

ccess-0.65

mos-0.64

oké-0.64

indeed-0.63

nsics-0.63

の�-0.63

INTERVAL 0.748 - 0.831
CONTAINS 0.000%

a
Tokena
Feature activation+0.012
ub
Tokenub
Feature activation+0.000
ol
Tokenol
Feature activation+0.057
was
Token was
Feature activation+0.415
suppose
Token suppose
Feature activation+0.655
to
Token to
Feature activation+0.791
give
Token give
Feature activation+0.684
the
Token the
Feature activation+0.494
soccer
Token soccer
Feature activation+0.307
team
Token team
Feature activation+0.228
,
Token,
Feature activation+0.348

INTERVAL 0.665 - 0.748
CONTAINS 0.001%

ub
Tokenub
Feature activation+0.000
ol
Tokenol
Feature activation+0.057
was
Token was
Feature activation+0.415
suppose
Token suppose
Feature activation+0.655
to
Token to
Feature activation+0.791
give
Token give
Feature activation+0.684
the
Token the
Feature activation+0.494
soccer
Token soccer
Feature activation+0.307
team
Token team
Feature activation+0.228
,
Token,
Feature activation+0.348
"
Token "
Feature activation+0.305
211
Token 211
Feature activation+0.150
Peters
Token Peters
Feature activation+0.200
St
Token St
Feature activation+0.156
.
Token.
Feature activation+0.206
If
Token If
Feature activation+0.453
you
Token you
Feature activation+0.684
're
Token're
Feature activation+0.712
driving
Token driving
Feature activation+0.588
,
Token,
Feature activation+0.549
parking
Token parking
Feature activation+0.260
will
Token will
Feature activation+0.175
Peters
Token Peters
Feature activation+0.200
St
Token St
Feature activation+0.156
.
Token.
Feature activation+0.206
If
Token If
Feature activation+0.453
you
Token you
Feature activation+0.684
're
Token're
Feature activation+0.712
driving
Token driving
Feature activation+0.588
,
Token,
Feature activation+0.549
parking
Token parking
Feature activation+0.260
will
Token will
Feature activation+0.175
be
Token be
Feature activation+0.123
INC
TokenINC
Feature activation+0.069
.
Token.
Feature activation+0.140
COM
TokenCOM
Feature activation+0.009
<
Token <
Feature activation+0.289
javascript
Tokenjavascript
Feature activation+0.602
:
Token:
Feature activation+0.677
_
Token_
Feature activation+0.611
e
Tokene
Feature activation+0.467
(
Token(
Feature activation+0.410
%
Token%
Feature activation+0.322
7
Token7
Feature activation+0.372
.
Token.
Feature activation+0.000
Stan
Token Stan
Feature activation+0.000
Monte
Token Monte
Feature activation+0.000
ith
Tokenith
Feature activation+0.000
likes
Token likes
Feature activation+0.245
to
Token to
Feature activation+0.670
say
Token say
Feature activation+0.618
as
Token as
Feature activation+0.490
he
Token he
Feature activation+0.330
starts
Token starts
Feature activation+0.390
each
Token each
Feature activation+0.356

INTERVAL 0.582 - 0.665
CONTAINS 0.003%

ARS
TokenARS
Feature activation+0.110
INC
TokenINC
Feature activation+0.069
.
Token.
Feature activation+0.140
COM
TokenCOM
Feature activation+0.009
<
Token <
Feature activation+0.289
javascript
Tokenjavascript
Feature activation+0.602
:
Token:
Feature activation+0.677
_
Token_
Feature activation+0.611
e
Tokene
Feature activation+0.467
(
Token(
Feature activation+0.410
%
Token%
Feature activation+0.322
and
Token and
Feature activation+0.039
G
Token G
Feature activation+0.057
illing
Tokenilling
Feature activation+0.046
ham
Tokenham
Feature activation+0.005
during
Token during
Feature activation+0.418
his
Token his
Feature activation+0.630
career
Token career
Feature activation+0.494
,
Token,
Feature activation+0.454
said
Token said
Feature activation+0.308
:
Token:
Feature activation+0.348
"
Token "
Feature activation+0.422
ech
Tokenech
Feature activation+0.116
a
Tokena
Feature activation+0.012
ub
Tokenub
Feature activation+0.000
ol
Tokenol
Feature activation+0.057
was
Token was
Feature activation+0.415
suppose
Token suppose
Feature activation+0.655
to
Token to
Feature activation+0.791
give
Token give
Feature activation+0.684
the
Token the
Feature activation+0.494
soccer
Token soccer
Feature activation+0.307
team
Token team
Feature activation+0.228
Hastings
Token Hastings
Feature activation+0.115
Rd
Token Rd
Feature activation+0.067
.,
Token.,
Feature activation+0.345
in
Token in
Feature activation+0.518
late
Token late
Feature activation+0.533
November
Token November
Feature activation+0.613
.
Token.
Feature activation+0.309
With
Token With
Feature activation+0.268
a
Token a
Feature activation+0.182
sports
Token sports
Feature activation+0.114
bar
Token bar
Feature activation+0.018
St
Token St
Feature activation+0.156
.
Token.
Feature activation+0.206
If
Token If
Feature activation+0.453
you
Token you
Feature activation+0.684
're
Token're
Feature activation+0.712
driving
Token driving
Feature activation+0.588
,
Token,
Feature activation+0.549
parking
Token parking
Feature activation+0.260
will
Token will
Feature activation+0.175
be
Token be
Feature activation+0.123
available
Token available
Feature activation+0.090

INTERVAL 0.499 - 0.582
CONTAINS 0.009%

of
Token of
Feature activation+0.427
State
Token State
Feature activation+0.150
Formation
Token Formation
Feature activation+0.088
--
Token--
Feature activation+0.403
Review
Token Review
Feature activation+0.464
of
Token of
Feature activation+0.522
Peter
Token Peter
Feature activation+0.245
Ge
Token Ge
Feature activation+0.000
lder
Tokenlder
Feature activation+0.000
lo
Tokenlo
Feature activation+0.000
os
Tokenos
Feature activation+0.000
Brent
Token Brent
Feature activation+0.000
Mus
Token Mus
Feature activation+0.000
bur
Tokenbur
Feature activation+0.000
ger
Tokenger
Feature activation+0.000
from
Token from
Feature activation+0.371
down
Token down
Feature activation+0.511
the
Token the
Feature activation+0.411
road
Token road
Feature activation+0.394
Hamilton
Token Hamilton
Feature activation+0.330
,
Token,
Feature activation+0.378
and
Token and
Feature activation+0.339
pl
Tokenpl
Feature activation+0.000
ir
Tokenir
Feature activation+0.000
sen
Tokensen
Feature activation+0.000
retracted
Token retracted
Feature activation+0.089
because
Token because
Feature activation+0.384
he
Token he
Feature activation+0.521
believes
Token believes
Feature activation+0.499
it
Token it
Feature activation+0.422
was
Token was
Feature activation+0.245
misleading
Token misleading
Feature activation+0.044
.
Token.
Feature activation+0.000
uppet
Tokenuppet
Feature activation+0.182
Show
Token Show
Feature activation+0.156
(
Token (
Feature activation+0.288
I
TokenI
Feature activation+0.434
once
Token once
Feature activation+0.457
almost
Token almost
Feature activation+0.536
owned
Token owned
Feature activation+0.444
a
Token a
Feature activation+0.381
ginger
Token ginger
Feature activation+0.357
cat
Token cat
Feature activation+0.276
with
Token with
Feature activation+0.380
Panic
Token Panic
Feature activation+0.000
lead
Token lead
Feature activation+0.000
guitarist
Token guitarist
Feature activation+0.110
who
Token who
Feature activation+0.364
died
Token died
Feature activation+0.441
of
Token of
Feature activation+0.546
pancreat
Token pancreat
Feature activation+0.375
ic
Tokenic
Feature activation+0.671
cancer
Token cancer
Feature activation+0.516
in
Token in
Feature activation+0.563
2002
Token 2002
Feature activation+0.525

INTERVAL 0.416 - 0.499
CONTAINS 0.021%

Black
Token Black
Feature activation+0.068
wood
Tokenwood
Feature activation+0.155
where
Token where
Feature activation+0.230
her
Token her
Feature activation+0.465
colleagues
Token colleagues
Feature activation+0.305
have
Token have
Feature activation+0.458
fallen
Token fallen
Feature activation+0.500
in
Token in
Feature activation+0.561
love
Token love
Feature activation+0.404
with
Token with
Feature activation+0.581
him
Token him
Feature activation+0.342
+
Token +
Feature activation+0.162
Sam
Token Sam
Feature activation+0.173
's
Token's
Feature activation+0.116
Club
Token Club
Feature activation+0.231
(
Token (
Feature activation+0.263
or
Tokenor
Feature activation+0.490
Costco
Token Costco
Feature activation+0.415
)
Token)
Feature activation+0.233
+
Token +
Feature activation+0.337
M
Token M
Feature activation+0.348
azz
Tokenazz
Feature activation+0.309
idespread
Tokenidespread
Feature activation+0.000
Panic
Token Panic
Feature activation+0.000
lead
Token lead
Feature activation+0.000
guitarist
Token guitarist
Feature activation+0.110
who
Token who
Feature activation+0.364
died
Token died
Feature activation+0.441
of
Token of
Feature activation+0.546
pancreat
Token pancreat
Feature activation+0.375
ic
Tokenic
Feature activation+0.671
cancer
Token cancer
Feature activation+0.516
in
Token in
Feature activation+0.563
Ch
Token Ch
Feature activation+0.000
airs
Tokenairs
Feature activation+0.000
:
Token:
Feature activation+0.000
While
Token While
Feature activation+0.260
moms
Token moms
Feature activation+0.434
also
Token also
Feature activation+0.438
swear
Token swear
Feature activation+0.262
that
Token that
Feature activation+0.305
baby
Token baby
Feature activation+0.244
exerc
Token exerc
Feature activation+0.150
isers
Tokenisers
Feature activation+0.335
ol
Tokenol
Feature activation+0.057
was
Token was
Feature activation+0.415
suppose
Token suppose
Feature activation+0.655
to
Token to
Feature activation+0.791
give
Token give
Feature activation+0.684
the
Token the
Feature activation+0.494
soccer
Token soccer
Feature activation+0.307
team
Token team
Feature activation+0.228
,
Token,
Feature activation+0.348
"
Token "
Feature activation+0.305
deep
Tokendeep
Feature activation+0.287

INTERVAL 0.332 - 0.416
CONTAINS 0.051%

ario
Tokenario
Feature activation+0.000
ball
Token ball
Feature activation+0.070
en
Tokenen
Feature activation+0.183
as
Tokenas
Feature activation+0.069
@
Token @
Feature activation+0.308
ball
Tokenball
Feature activation+0.404
en
Tokenen
Feature activation+0.302
as
Tokenas
Feature activation+0.215
uy
Tokenuy
Feature activation+0.090
âĢĶ
Token âĢĶ
Feature activation+0.492
L
Token L
Feature activation+0.385
ãģ§
Tokenãģ§
Feature activation+0.000
ãģĻ
TokenãģĻ
Feature activation+0.002
ãģĮ
TokenãģĮ
Feature activation+0.000
ãĥ»
Tokenãĥ»
Feature activation+0.197
ãĥ»
Tokenãĥ»
Feature activation+0.330
ãĥ»
Tokenãĥ»
Feature activation+0.361
ãģ
Tokenãģ
Feature activation+0.293
Ŀ
TokenĿ
Feature activation+0.139
ãģĨ
TokenãģĨ
Feature activation+0.000
ãģª
Tokenãģª
Feature activation+0.055
ãĤĵ
TokenãĤĵ
Feature activation+0.000
awkward
Token awkward
Feature activation+0.000
video
Token video
Feature activation+0.000
from
Token from
Feature activation+0.132
Politico
Token Politico
Feature activation+0.122
shows
Token shows
Feature activation+0.200
that
Token that
Feature activation+0.351
Sanders
Token Sanders
Feature activation+0.141
and
Token and
Feature activation+0.051
Alc
Token Alc
Feature activation+0.000
ind
Tokenind
Feature activation+0.000
or
Tokenor
Feature activation+0.000
Urban
Token Urban
Feature activation+0.000
Meyer
Token Meyer
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
't
Token't
Feature activation+0.072
sure
Token sure
Feature activation+0.164
of
Token of
Feature activation+0.344
what
Token what
Feature activation+0.313
he
Token he
Feature activation+0.091
had
Token had
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.007
F
TokenF
Feature activation+0.000
protection
Token protection
Feature activation+0.000
technique
Token technique
Feature activation+0.137
we
Token we
Feature activation+0.374
just
Token just
Feature activation+0.368
mentioned
Token mentioned
Feature activation+0.377
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 0.249 - 0.332
CONTAINS 0.098%

D
Token D
Feature activation+0.000
azz
Tokenazz
Feature activation+0.043
le
Tokenle
Feature activation+0.089
Name
TokenName
Feature activation+0.173
:
Token:
Feature activation+0.257
Beauty
Token Beauty
Feature activation+0.281
Brass
Token Brass
Feature activation+0.067
Prof
TokenProf
Feature activation+0.000
ession
Tokenession
Feature activation+0.058
:
Token:
Feature activation+0.146
Music
Token Music
Feature activation+0.197
Z
Token Z
Feature activation+0.000
avor
Tokenavor
Feature activation+0.000
anu
Tokenanu
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
handed
Token handed
Feature activation+0.093
over
Token over
Feature activation+0.265
âĤ¬
Token âĤ¬
Feature activation+0.107
450
Token450
Feature activation+0.175
,
Token,
Feature activation+0.180
000
Token000
Feature activation+0.158
(£
Token (£
Feature activation+0.158
Cairo
Token Cairo
Feature activation+0.000
treat
Token treat
Feature activation+0.062
their
Token their
Feature activation+0.237
women
Token women
Feature activation+0.143
-
Token-
Feature activation+0.154
not
Token not
Feature activation+0.297
a
Token a
Feature activation+0.283
single
Token single
Feature activation+0.233
case
Token case
Feature activation+0.152
of
Token of
Feature activation+0.237
harassment
Token harassment
Feature activation+0.077
particularly
Token particularly
Feature activation+0.378
interesting
Token interesting
Feature activation+0.263
articles
Token articles
Feature activation+0.295
over
Token over
Feature activation+0.378
at
Token at
Feature activation+0.318
The
Token The
Feature activation+0.328
Floating
Token Floating
Feature activation+0.180
Rum
Token Rum
Feature activation+0.144
Shack
Token Shack
Feature activation+0.190
in
Token in
Feature activation+0.477
June
Token June
Feature activation+0.623
Party
Token Party
Feature activation+0.000
,
Token ,
Feature activation+0.000
long
Token long
Feature activation+0.201
before
Token before
Feature activation+0.259
America
Token America
Feature activation+0.351
would
Token would
Feature activation+0.289
join
Token join
Feature activation+0.229
the
Token the
Feature activation+0.361
Allies
Token Allies
Feature activation+0.019
to
Token to
Feature activation+0.127
fight
Token fight
Feature activation+0.033

INTERVAL 0.166 - 0.249
CONTAINS 0.191%

Ryan
Token Ryan
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.020
member
Token member
Feature activation+0.005
of
Token of
Feature activation+0.251
the
Token the
Feature activation+0.190
communications
Token communications
Feature activation+0.000
committee
Token committee
Feature activation+0.000
.
Token.
Feature activation+0.000
Ryan
Token Ryan
Feature activation+0.000
,
Token,
Feature activation+0.000
coffee
Token coffee
Feature activation+0.160
shop
Token shop
Feature activation+0.207
was
Token was
Feature activation+0.132
directly
Token directly
Feature activation+0.113
across
Token across
Feature activation+0.168
the
Token the
Feature activation+0.168
street
Token street
Feature activation+0.030
from
Token from
Feature activation+0.077
my
Token my
Feature activation+0.000
comic
Token comic
Feature activation+0.000
book
Token book
Feature activation+0.000
Beauty
Token Beauty
Feature activation+0.281
Brass
Token Brass
Feature activation+0.067
Prof
TokenProf
Feature activation+0.000
ession
Tokenession
Feature activation+0.058
:
Token:
Feature activation+0.146
Music
Token Music
Feature activation+0.197
teacher
Token teacher
Feature activation+0.230
,
Token,
Feature activation+0.325
s
Token s
Feature activation+0.239
ous
Tokenous
Feature activation+0.307
a
Tokena
Feature activation+0.091
S
Token S
Feature activation+0.000
ars
Tokenars
Feature activation+0.000
our
Tokenour
Feature activation+0.000
is
Token is
Feature activation+0.000
backing
Token backing
Feature activation+0.033
Ye
Token Ye
Feature activation+0.185
ger
Tokenger
Feature activation+0.041
,
Token,
Feature activation+0.197
which
Token which
Feature activation+0.245
she
Token she
Feature activation+0.248
has
Token has
Feature activation+0.244
showcasing
Token showcasing
Feature activation+0.239
new
Token new
Feature activation+0.244
HP
Token HP
Feature activation+0.174
servers
Token servers
Feature activation+0.000
based
Token based
Feature activation+0.107
on
Token on
Feature activation+0.229
EP
Token EP
Feature activation+0.085
YC
TokenYC
Feature activation+0.076
and
Token and
Feature activation+0.148
specific
Token specific
Feature activation+0.203
strengths
Token strengths
Feature activation+0.209

INTERVAL 0.083 - 0.166
CONTAINS 0.349%

Connecticut
Token Connecticut
Feature activation+0.000
Economic
Token Economic
Feature activation+0.000
Resource
Token Resource
Feature activation+0.000
Center
Token Center
Feature activation+0.000
Inc
Token Inc
Feature activation+0.000
.,
Token.,
Feature activation+0.101
senior
Token senior
Feature activation+0.255
financial
Token financial
Feature activation+0.207
editor
Token editor
Feature activation+0.131
at
Token at
Feature activation+0.292
Ness
Token Ness
Feature activation+0.394
St
Token St
Feature activation+0.000
.
Token.
Feature activation+0.000
Louis
Token Louis
Feature activation+0.000
Cardinals
Token Cardinals
Feature activation+0.000
rallied
Token rallied
Feature activation+0.000
for
Token for
Feature activation+0.156
two
Token two
Feature activation+0.003
runs
Token runs
Feature activation+0.000
in
Token in
Feature activation+0.027
the
Token the
Feature activation+0.000
ninth
Token ninth
Feature activation+0.000
helmet
Token helmet
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
him
Token him
Feature activation+0.069
into
Token into
Feature activation+0.140
a
Token a
Feature activation+0.088
superhero
Token superhero
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.098
Mega
Token Mega
Feature activation+0.000
Man
Token Man
Feature activation+0.000
!
Token!
Feature activation+0.073
i
Tokeni
Feature activation+0.000
x
Token x
Feature activation+0.000
Drive
TokenDrive
Feature activation+0.000
variant
Token variant
Feature activation+0.000
and
Token and
Feature activation+0.131
has
Token has
Feature activation+0.124
a
Token a
Feature activation+0.136
distinct
Token distinct
Feature activation+0.061
cou
Token cou
Feature activation+0.000
pe
Tokenpe
Feature activation+0.000
-
Token-
Feature activation+0.000
,
Token,
Feature activation+0.022
linebacker
Token linebacker
Feature activation+0.000
Chad
Token Chad
Feature activation+0.054
Green
Token Green
Feature activation+0.000
way
Tokenway
Feature activation+0.000
,
Token,
Feature activation+0.087
kicker
Token kicker
Feature activation+0.272
Blair
Token Blair
Feature activation+0.269
Walsh
Token Walsh
Feature activation+0.244
and
Token and
Feature activation+0.234
tight
Token tight
Feature activation+0.437

INTERVAL 0.000 - 0.083
CONTAINS 99.277%

This
Token This
Feature activation+0.000
will
Token will
Feature activation+0.000
become
Token become
Feature activation+0.000
especially
Token especially
Feature activation+0.000
handy
Token handy
Feature activation+0.000
when
Token when
Feature activation+0.000
you
Token you
Feature activation+0.000
build
Token build
Feature activation+0.000
applications
Token applications
Feature activation+0.000
that
Token that
Feature activation+0.000
perform
Token perform
Feature activation+0.000
Ryan
Token Ryan
Feature activation+0.000
?
Token?
Feature activation+0.000
Comp
Token Comp
Feature activation+0.000
assion
Tokenassion
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Last
TokenLast
Feature activation+0.000
month
Token month
Feature activation+0.000
,
Token,
Feature activation+0.000
block
Token block
Feature activation+0.000
chains
Tokenchains
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
best
Token best
Feature activation+0.000
analogy
Token analogy
Feature activation+0.000
to
Token to
Feature activation+0.000
understand
Token understand
Feature activation+0.000
the
Token the
Feature activation+0.000
difference
Token difference
Feature activation+0.000
law
Token law
Feature activation+0.000
that
Token that
Feature activation+0.000
prohibits
Token prohibits
Feature activation+0.000
bringing
Token bringing
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
aliens
Token aliens
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
and
Token and
Feature activation+0.000
consider
Token consider
Feature activation+0.000
feeding
Token feeding
Feature activation+0.000
your
Token your
Feature activation+0.000
cat
Token cat
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
plate
Token plate
Feature activation+0.000
or
Token or
Feature activation+0.000
buying
Token buying
Feature activation+0.000
her
Token her
Feature activation+0.000
a
Token a
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H2.10: (feature 6299)

TOP ACTIVATIONS
MAX = 1.001

or
Token or
Feature activation+0.441
offer
Token offer
Feature activation+0.543
tie
Token tie
Feature activation+0.701
red
Tokenred
Feature activation+0.832
services
Token services
Feature activation+0.819
with
Token with
Feature activation+0.929
internet
Token internet
Feature activation+0.896
fast
Token fast
Feature activation+0.906
l
Tokenl
Feature activation+0.883
anes
Tokenanes
Feature activation+0.825
or
Token or
Feature activation+0.626
,
Token,
Feature activation+0.719
Newark
Token Newark
Feature activation+0.580
(
Token (
Feature activation+0.595
N
TokenN
Feature activation+0.558
.
Token.
Feature activation+0.655
J
TokenJ
Feature activation+0.842
.),
Token.),
Feature activation+0.619
Baltimore
Token Baltimore
Feature activation+0.439
,
Token,
Feature activation+0.561
Chicago
Token Chicago
Feature activation+0.650
--
Token --
Feature activation+0.752
content
Token content
Feature activation+0.653
,
Token,
Feature activation+0.515
or
Token or
Feature activation+0.441
offer
Token offer
Feature activation+0.543
tie
Token tie
Feature activation+0.701
red
Tokenred
Feature activation+0.832
services
Token services
Feature activation+0.819
with
Token with
Feature activation+0.929
internet
Token internet
Feature activation+0.896
fast
Token fast
Feature activation+0.906
l
Tokenl
Feature activation+0.883
,
Token,
Feature activation+0.515
or
Token or
Feature activation+0.441
offer
Token offer
Feature activation+0.543
tie
Token tie
Feature activation+0.701
red
Tokenred
Feature activation+0.832
services
Token services
Feature activation+0.819
with
Token with
Feature activation+0.929
internet
Token internet
Feature activation+0.896
fast
Token fast
Feature activation+0.906
l
Tokenl
Feature activation+0.883
anes
Tokenanes
Feature activation+0.825
,
Token,
Feature activation+0.431
it
Token it
Feature activation+0.106
Bit
TokenBit
Feature activation+0.453
,
Token,
Feature activation+0.465
Peer
Token Peer
Feature activation+0.363
N
TokenN
Feature activation+0.804
ova
Tokenova
Feature activation+0.709
,
Token,
Feature activation+0.523
Ripple
Token Ripple
Feature activation+0.420
,
Token,
Feature activation+0.457
Wave
Token Wave
Feature activation+0.385
how
Token how
Feature activation+0.259
it
Token it
Feature activation+0.434
made
Token made
Feature activation+0.472
her
Token her
Feature activation+0.629
extremely
Token extremely
Feature activation+0.667
frightened
Token frightened
Feature activation+0.797
.
Token.
Feature activation+0.141
Our
Token Our
Feature activation+0.034
sources
Token sources
Feature activation+0.000
say
Token say
Feature activation+0.057
DC
Token DC
Feature activation+0.067
position
Token position
Feature activation+0.268
,
Token,
Feature activation+0.379
they
Token they
Feature activation+0.274
live
Token live
Feature activation+0.389
more
Token more
Feature activation+0.632
off
Token off
Feature activation+0.790
of
Token of
Feature activation+0.795
sales
Token sales
Feature activation+0.625
of
Token of
Feature activation+0.733
stock
Token stock
Feature activation+0.608
,
Token,
Feature activation+0.681
pay
Token pay
Feature activation+0.358
fines
Token fines
Feature activation+0.465
,
Token,
Feature activation+0.340
being
Token being
Feature activation+0.110
convicted
Token convicted
Feature activation+0.345
of
Token of
Feature activation+0.779
drunken
Token drunken
Feature activation+0.614
driving
Token driving
Feature activation+0.625
and
Token and
Feature activation+0.529
driving
Token driving
Feature activation+0.261
a
Token a
Feature activation+0.247
activist
Token activist
Feature activation+0.307
judges
Token judges
Feature activation+0.489
,
Token,
Feature activation+0.484
a
Token a
Feature activation+0.299
power
Token power
Feature activation+0.452
-
Token-
Feature activation+0.773
hung
Tokenhung
Feature activation+0.683
ry
Tokenry
Feature activation+0.727
executive
Token executive
Feature activation+0.607
,
Token,
Feature activation+0.558
or
Token or
Feature activation+0.224
,
Token,
Feature activation+0.119
rather
Token rather
Feature activation+0.100
than
Token than
Feature activation+0.319
across
Token across
Feature activation+0.446
industries
Token industries
Feature activation+0.699
or
Token or
Feature activation+0.762
trades
Token trades
Feature activation+0.497
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
According
TokenAccording
Feature activation+0.000
his
Token his
Feature activation+0.031
leg
Token leg
Feature activation+0.126
,
Token,
Feature activation+0.067
answering
Token answering
Feature activation+0.054
every
Token every
Feature activation+0.364
single
Token single
Feature activation+0.761
question
Token question
Feature activation+0.639
put
Token put
Feature activation+0.596
to
Token to
Feature activation+0.453
him
Token him
Feature activation+0.351
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.323
display
Token display
Feature activation+0.483
that
Token that
Feature activation+0.540
emitted
Token emitted
Feature activation+0.552
light
Token light
Feature activation+0.689
uniformly
Token uniformly
Feature activation+0.752
would
Token would
Feature activation+0.703
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
in
Token in
Feature activation+0.000
principle
Token principle
Feature activation+0.000
,
Token,
Feature activation+0.080
along
Token along
Feature activation+0.153
with
Token with
Feature activation+0.380
two
Token two
Feature activation+0.537
American
Token American
Feature activation+0.572
servic
Token servic
Feature activation+0.743
emen
Tokenemen
Feature activation+0.769
.
Token.
Feature activation+0.169
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
or
Token or
Feature activation+0.037
throttle
Token throttle
Feature activation+0.100
or
Token or
Feature activation+0.433
block
Token block
Feature activation+0.300
access
Token access
Feature activation+0.626
to
Token to
Feature activation+0.743
specific
Token specific
Feature activation+0.580
content
Token content
Feature activation+0.653
,
Token,
Feature activation+0.515
or
Token or
Feature activation+0.441
offer
Token offer
Feature activation+0.543
,
Token,
Feature activation+0.090
which
Token which
Feature activation+0.124
reduces
Token reduces
Feature activation+0.197
conflicts
Token conflicts
Feature activation+0.431
between
Token between
Feature activation+0.602
left
Token left
Feature activation+0.736
-
Token-
Feature activation+0.649
turn
Tokenturn
Feature activation+0.664
ing
Tokening
Feature activation+0.618
cars
Token cars
Feature activation+0.600
and
Token and
Feature activation+0.386
,
Token,
Feature activation+0.484
a
Token a
Feature activation+0.299
power
Token power
Feature activation+0.452
-
Token-
Feature activation+0.773
hung
Tokenhung
Feature activation+0.683
ry
Tokenry
Feature activation+0.727
executive
Token executive
Feature activation+0.607
,
Token,
Feature activation+0.558
or
Token or
Feature activation+0.224
a
Token a
Feature activation+0.260
meddling
Token meddling
Feature activation+0.315
investors
Token investors
Feature activation+0.635
,
Token,
Feature activation+0.634
and
Token and
Feature activation+0.324
incentives
Token incentives
Feature activation+0.338
designed
Token designed
Feature activation+0.454
with
Token with
Feature activation+0.720
the
Token the
Feature activation+0.574
participation
Token participation
Feature activation+0.539
of
Token of
Feature activation+0.637
the
Token the
Feature activation+0.590
private
Token private
Feature activation+0.512
--
Token --
Feature activation+0.000
in
Token in
Feature activation+0.333
places
Token places
Feature activation+0.552
like
Token like
Feature activation+0.485
Cincinnati
Token Cincinnati
Feature activation+0.655
,
Token,
Feature activation+0.719
Newark
Token Newark
Feature activation+0.580
(
Token (
Feature activation+0.595
N
TokenN
Feature activation+0.558
.
Token.
Feature activation+0.655
J
TokenJ
Feature activation+0.842
handles
Token handles
Feature activation+0.223
,
Token,
Feature activation+0.227
build
Token build
Feature activation+0.163
a
Token a
Feature activation+0.341
lamp
Token lamp
Feature activation+0.425
to
Token to
Feature activation+0.704
cover
Token cover
Feature activation+0.656
your
Token your
Feature activation+0.552
head
Token head
Feature activation+0.488
,
Token,
Feature activation+0.419
and
Token and
Feature activation+0.241
display
Token display
Feature activation+0.483
that
Token that
Feature activation+0.540
emitted
Token emitted
Feature activation+0.552
light
Token light
Feature activation+0.689
uniformly
Token uniformly
Feature activation+0.752
would
Token would
Feature activation+0.703
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
in
Token in
Feature activation+0.000
principle
Token principle
Feature activation+0.000
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 0.331

block
Token block
Feature activation+0.023
Top resid features:
access
Token access
Feature activation+0.023
Top resid features:
to
Token to
Feature activation+0.032
Top resid features:
specific
Token specific
Feature activation+0.010
Top resid features:
content
Token content
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.276
Top resid features:
or
Token or
Feature activation+0.022
Top resid features:
offer
Token offer
Feature activation+0.080
Top resid features:
tie
Token tie
Feature activation+0.005
Top resid features:
red
Tokenred
Feature activation-0.012
Top resid features:
services
Token services
Feature activation+0.046
Top resid features:
Cincinnati
Token Cincinnati
Feature activation+0.045
Top resid features:
,
Token,
Feature activation+0.080
Top resid features:
Newark
Token Newark
Feature activation+0.113
Top resid features:
(
Token (
Feature activation-0.029
Top resid features:
N
TokenN
Feature activation+0.058
Top resid features:
.
Token.
Feature activation+0.165
Top resid features:
J
TokenJ
Feature activation+0.053
Top resid features:
.),
Token.),
Feature activation+0.000
Top resid features:
Baltimore
Token Baltimore
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Chicago
Token Chicago
Feature activation+0.000
Top resid features:
block
Token block
Feature activation+0.037
Top resid features:
access
Token access
Feature activation+0.032
Top resid features:
to
Token to
Feature activation+0.046
Top resid features:
specific
Token specific
Feature activation+0.009
Top resid features:
content
Token content
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.242
Top resid features:
or
Token or
Feature activation+0.051
Top resid features:
offer
Token offer
Feature activation+0.166
Top resid features:
tie
Token tie
Feature activation-0.064
Top resid features:
red
Tokenred
Feature activation+0.020
Top resid features:
services
Token services
Feature activation+0.000
Top resid features:
block
Token block
Feature activation+0.029
Top resid features:
access
Token access
Feature activation+0.029
Top resid features:
to
Token to
Feature activation+0.036
Top resid features:
specific
Token specific
Feature activation+0.010
Top resid features:
content
Token content
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.321
Top resid features:
or
Token or
Feature activation+0.013
Top resid features:
offer
Token offer
Feature activation+0.078
Top resid features:
tie
Token tie
Feature activation-0.001
Top resid features:
red
Tokenred
Feature activation-0.056
Top resid features:
services
Token services
Feature activation+0.073
Top resid features:
Coin
TokenCoin
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
it
Token it
Feature activation+0.057
Top resid features:
Bit
TokenBit
Feature activation+0.058
Top resid features:
,
Token,
Feature activation-0.028
Top resid features:
Peer
Token Peer
Feature activation+0.142
Top resid features:
N
TokenN
Feature activation+0.132
Top resid features:
ova
Tokenova
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ripple
Token Ripple
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
involving
Token involving
Feature activation+0.010
Top resid features:
him
Token him
Feature activation+0.008
Top resid features:
screaming
Token screaming
Feature activation+0.019
Top resid features:
at
Token at
Feature activation+0.009
Top resid features:
her
Token her
Feature activation+0.013
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.310
Top resid features:
and
Token and
Feature activation+0.056
Top resid features:
how
Token how
Feature activation+0.175
Top resid features:
it
Token it
Feature activation-0.032
Top resid features:
made
Token made
Feature activation+0.019
Top resid features:
her
Token her
Feature activation-0.008
Top resid features:
because
Token because
Feature activation+0.031
Top resid features:
in
Token in
Feature activation+0.042
Top resid features:
their
Token their
Feature activation+0.011
Top resid features:
privileged
Token privileged
Feature activation+0.003
Top resid features:
position
Token position
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.234
Top resid features:
they
Token they
Feature activation+0.057
Top resid features:
live
Token live
Feature activation+0.042
Top resid features:
more
Token more
Feature activation+0.042
Top resid features:
off
Token off
Feature activation+0.149
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
including
Token including
Feature activation+0.037
Top resid features:
failing
Token failing
Feature activation+0.032
Top resid features:
to
Token to
Feature activation+0.038
Top resid features:
pay
Token pay
Feature activation+0.022
Top resid features:
fines
Token fines
Feature activation+0.018
Top resid features:
,
Token,
Feature activation+0.161
Top resid features:
being
Token being
Feature activation+0.148
Top resid features:
convicted
Token convicted
Feature activation+0.011
Top resid features:
of
Token of
Feature activation+0.118
Top resid features:
drunken
Token drunken
Feature activation+0.000
Top resid features:
driving
Token driving
Feature activation+0.000
Top resid features:
activist
Token activist
Feature activation+0.022
Top resid features:
judges
Token judges
Feature activation+0.083
Top resid features:
,
Token,
Feature activation+0.096
Top resid features:
a
Token a
Feature activation+0.079
Top resid features:
power
Token power
Feature activation+0.039
Top resid features:
-
Token-
Feature activation+0.109
Top resid features:
hung
Tokenhung
Feature activation+0.000
Top resid features:
ry
Tokenry
Feature activation+0.000
Top resid features:
executive
Token executive
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.006
Top resid features:
organized
Token organized
Feature activation+0.013
Top resid features:
at
Token at
Feature activation+0.008
Top resid features:
individual
Token individual
Feature activation+0.003
Top resid features:
companies
Token companies
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.253
Top resid features:
rather
Token rather
Feature activation+0.094
Top resid features:
than
Token than
Feature activation+0.065
Top resid features:
across
Token across
Feature activation+0.224
Top resid features:
industries
Token industries
Feature activation-0.021
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.027
Top resid features:
his
Token his
Feature activation-0.004
Top resid features:
leg
Token leg
Feature activation+0.020
Top resid features:
,
Token,
Feature activation+0.133
Top resid features:
answering
Token answering
Feature activation+0.118
Top resid features:
every
Token every
Feature activation+0.246
Top resid features:
single
Token single
Feature activation+0.038
Top resid features:
question
Token question
Feature activation+0.000
Top resid features:
put
Token put
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
images
Token images
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.118
Top resid features:
as
Token as
Feature activation+0.078
Top resid features:
a
Token a
Feature activation+0.020
Top resid features:
display
Token display
Feature activation+0.029
Top resid features:
that
Token that
Feature activation+0.162
Top resid features:
emitted
Token emitted
Feature activation-0.021
Top resid features:
light
Token light
Feature activation+0.045
Top resid features:
uniformly
Token uniformly
Feature activation+0.037
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Libya
Token Libya
Feature activation+0.009
Top resid features:
and
Token and
Feature activation+0.017
Top resid features:
killed
Token killed
Feature activation+0.027
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
Stevens
Token Stevens
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.331
Top resid features:
along
Token along
Feature activation+0.061
Top resid features:
with
Token with
Feature activation+0.080
Top resid features:
two
Token two
Feature activation-0.011
Top resid features:
American
Token American
Feature activation+0.070
Top resid features:
servic
Token servic
Feature activation+0.024
Top resid features:
toll
Token toll
Feature activation+0.006
Top resid features:
s
Tokens
Feature activation-0.008
Top resid features:
from
Token from
Feature activation+0.014
Top resid features:
content
Token content
Feature activation+0.009
Top resid features:
providers
Token providers
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.304
Top resid features:
or
Token or
Feature activation+0.029
Top resid features:
throttle
Token throttle
Feature activation+0.037
Top resid features:
or
Token or
Feature activation-0.003
Top resid features:
block
Token block
Feature activation+0.064
Top resid features:
access
Token access
Feature activation+0.032
Top resid features:
lights
Token lights
Feature activation-0.004
Top resid features:
with
Token with
Feature activation+0.018
Top resid features:
left
Token left
Feature activation+0.010
Top resid features:
turn
Token turn
Feature activation-0.001
Top resid features:
signals
Token signals
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.213
Top resid features:
which
Token which
Feature activation+0.100
Top resid features:
reduces
Token reduces
Feature activation+0.013
Top resid features:
conflicts
Token conflicts
Feature activation-0.048
Top resid features:
between
Token between
Feature activation+0.159
Top resid features:
left
Token left
Feature activation+0.043
Top resid features:
,
Token,
Feature activation+0.097
Top resid features:
whether
Token whether
Feature activation+0.076
Top resid features:
by
Token by
Feature activation+0.056
Top resid features:
activist
Token activist
Feature activation+0.017
Top resid features:
judges
Token judges
Feature activation+0.053
Top resid features:
,
Token,
Feature activation+0.130
Top resid features:
a
Token a
Feature activation+0.067
Top resid features:
power
Token power
Feature activation+0.053
Top resid features:
-
Token-
Feature activation+0.074
Top resid features:
hung
Tokenhung
Feature activation-0.021
Top resid features:
ry
Tokenry
Feature activation+0.012
Top resid features:
investors
Token investors
Feature activation+0.025
Top resid features:
,
Token,
Feature activation+0.108
Top resid features:
and
Token and
Feature activation+0.031
Top resid features:
incentives
Token incentives
Feature activation+0.025
Top resid features:
designed
Token designed
Feature activation-0.008
Top resid features:
with
Token with
Feature activation+0.120
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
participation
Token participation
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:
private
Token private
Feature activation+0.000
Top resid features:
poverty
Token poverty
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
heavily
Token heavily
Feature activation+0.023
Top resid features:
concentrated
Token concentrated
Feature activation+0.018
Top resid features:
unemployment
Token unemployment
Feature activation+0.026
Top resid features:
--
Token --
Feature activation+0.268
Top resid features:
in
Token in
Feature activation+0.089
Top resid features:
places
Token places
Feature activation+0.057
Top resid features:
like
Token like
Feature activation+0.119
Top resid features:
Cincinnati
Token Cincinnati
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
handles
Token handles
Feature activation+0.034
Top resid features:
,
Token,
Feature activation+0.056
Top resid features:
build
Token build
Feature activation+0.118
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
lamp
Token lamp
Feature activation+0.026
Top resid features:
to
Token to
Feature activation+0.135
Top resid features:
cover
Token cover
Feature activation+0.000
Top resid features:
your
Token your
Feature activation+0.000
Top resid features:
head
Token head
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
viewers
Token viewers
Feature activation-0.005
Top resid features:
on
Token on
Feature activation+0.004
Top resid features:
both
Token both
Feature activation-0.001
Top resid features:
sides
Token sides
Feature activation+0.001
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.180
Top resid features:
not
Token not
Feature activation+0.019
Top resid features:
mirror
Token mirror
Feature activation+0.011
Top resid features:
images
Token images
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.115
Top resid features:
as
Token as
Feature activation+0.059
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.03

Head 2: 0.04

Head 3: 0.07

Head 4: 0.03

Head 5: 0.07

Head 6: 0.13

Head 7: 0.09

Head 8: 0.04

Head 9: 0.08

Head 10: 0.26

Head 11: 0.11

Positive logits

]."1.20

}.0.98

]).0.95

).[0.91

].0.88

)).0.88

.).0.88

)."0.86

))))0.84

}}0.82

"/>0.81

?).0.79

).0.78

��0.77

%).0.76

.''.0.76

etc0.75

'."0.73

]}0.71

NetMessage0.71

Negative logits

esides-0.72

Neville-0.65

Firstly-0.63

Ange-0.59

shire-0.58

ensional-0.58

soDeliveryDate-0.57

NX-0.57

arkable-0.57

Blazers-0.56

Gund-0.56

FTWARE-0.56

raltar-0.54

OOD-0.54

Anthropology-0.54

Xavier-0.54

podcast-0.53

Patreon-0.53

Abbey-0.52

FS-0.52

INTERVAL 0.901 - 1.001
CONTAINS 0.000%

or
Token or
Feature activation+0.441
offer
Token offer
Feature activation+0.543
tie
Token tie
Feature activation+0.701
red
Tokenred
Feature activation+0.832
services
Token services
Feature activation+0.819
with
Token with
Feature activation+0.929
internet
Token internet
Feature activation+0.896
fast
Token fast
Feature activation+0.906
l
Tokenl
Feature activation+0.883
anes
Tokenanes
Feature activation+0.825
or
Token or
Feature activation+0.626

INTERVAL 0.801 - 0.901
CONTAINS 0.002%

,
Token,
Feature activation+0.431
it
Token it
Feature activation+0.106
Bit
TokenBit
Feature activation+0.453
,
Token,
Feature activation+0.465
Peer
Token Peer
Feature activation+0.363
N
TokenN
Feature activation+0.804
ova
Tokenova
Feature activation+0.709
,
Token,
Feature activation+0.523
Ripple
Token Ripple
Feature activation+0.420
,
Token,
Feature activation+0.457
Wave
Token Wave
Feature activation+0.385
,
Token,
Feature activation+0.719
Newark
Token Newark
Feature activation+0.580
(
Token (
Feature activation+0.595
N
TokenN
Feature activation+0.558
.
Token.
Feature activation+0.655
J
TokenJ
Feature activation+0.842
.),
Token.),
Feature activation+0.619
Baltimore
Token Baltimore
Feature activation+0.439
,
Token,
Feature activation+0.561
Chicago
Token Chicago
Feature activation+0.650
--
Token --
Feature activation+0.752
content
Token content
Feature activation+0.653
,
Token,
Feature activation+0.515
or
Token or
Feature activation+0.441
offer
Token offer
Feature activation+0.543
tie
Token tie
Feature activation+0.701
red
Tokenred
Feature activation+0.832
services
Token services
Feature activation+0.819
with
Token with
Feature activation+0.929
internet
Token internet
Feature activation+0.896
fast
Token fast
Feature activation+0.906
l
Tokenl
Feature activation+0.883
,
Token,
Feature activation+0.515
or
Token or
Feature activation+0.441
offer
Token offer
Feature activation+0.543
tie
Token tie
Feature activation+0.701
red
Tokenred
Feature activation+0.832
services
Token services
Feature activation+0.819
with
Token with
Feature activation+0.929
internet
Token internet
Feature activation+0.896
fast
Token fast
Feature activation+0.906
l
Tokenl
Feature activation+0.883
anes
Tokenanes
Feature activation+0.825

INTERVAL 0.701 - 0.801
CONTAINS 0.007%

or
Token or
Feature activation+0.037
throttle
Token throttle
Feature activation+0.100
or
Token or
Feature activation+0.433
block
Token block
Feature activation+0.300
access
Token access
Feature activation+0.626
to
Token to
Feature activation+0.743
specific
Token specific
Feature activation+0.580
content
Token content
Feature activation+0.653
,
Token,
Feature activation+0.515
or
Token or
Feature activation+0.441
offer
Token offer
Feature activation+0.543
pay
Token pay
Feature activation+0.358
fines
Token fines
Feature activation+0.465
,
Token,
Feature activation+0.340
being
Token being
Feature activation+0.110
convicted
Token convicted
Feature activation+0.345
of
Token of
Feature activation+0.779
drunken
Token drunken
Feature activation+0.614
driving
Token driving
Feature activation+0.625
and
Token and
Feature activation+0.529
driving
Token driving
Feature activation+0.261
a
Token a
Feature activation+0.247
--
Token --
Feature activation+0.000
in
Token in
Feature activation+0.333
places
Token places
Feature activation+0.552
like
Token like
Feature activation+0.485
Cincinnati
Token Cincinnati
Feature activation+0.655
,
Token,
Feature activation+0.719
Newark
Token Newark
Feature activation+0.580
(
Token (
Feature activation+0.595
N
TokenN
Feature activation+0.558
.
Token.
Feature activation+0.655
J
TokenJ
Feature activation+0.842
,
Token,
Feature activation+0.090
which
Token which
Feature activation+0.124
reduces
Token reduces
Feature activation+0.197
conflicts
Token conflicts
Feature activation+0.431
between
Token between
Feature activation+0.602
left
Token left
Feature activation+0.736
-
Token-
Feature activation+0.649
turn
Tokenturn
Feature activation+0.664
ing
Tokening
Feature activation+0.618
cars
Token cars
Feature activation+0.600
and
Token and
Feature activation+0.386
position
Token position
Feature activation+0.268
,
Token,
Feature activation+0.379
they
Token they
Feature activation+0.274
live
Token live
Feature activation+0.389
more
Token more
Feature activation+0.632
off
Token off
Feature activation+0.790
of
Token of
Feature activation+0.795
sales
Token sales
Feature activation+0.625
of
Token of
Feature activation+0.733
stock
Token stock
Feature activation+0.608
,
Token,
Feature activation+0.681

INTERVAL 0.601 - 0.701
CONTAINS 0.023%

-
Token-
Feature activation+0.454
enabled
Tokenenabled
Feature activation+0.411
,
Token,
Feature activation+0.284
peer
Token peer
Feature activation+0.269
-
Token-
Feature activation+0.604
to
Tokento
Feature activation+0.652
-
Token-
Feature activation+0.587
peer
Tokenpeer
Feature activation+0.420
participation
Token participation
Feature activation+0.550
in
Token in
Feature activation+0.642
politics
Token politics
Feature activation+0.602
in
Token in
Feature activation+0.157
-
Token-
Feature activation+0.461
depth
Tokendepth
Feature activation+0.342
state
Token state
Feature activation+0.653
coverage
Token coverage
Feature activation+0.618
and
Token and
Feature activation+0.607
what
Token what
Feature activation+0.399
it
Token it
Feature activation+0.334
all
Token all
Feature activation+0.398
means
Token means
Feature activation+0.289
for
Token for
Feature activation+0.349
sailing
Token sailing
Feature activation+0.213
,
Token,
Feature activation+0.480
shooting
Token shooting
Feature activation+0.214
,
Token,
Feature activation+0.592
tennis
Token tennis
Feature activation+0.485
,
Token,
Feature activation+0.643
swimming
Token swimming
Feature activation+0.449
,
Token,
Feature activation+0.679
water
Token water
Feature activation+0.405
pol
Token pol
Feature activation+0.556
o
Tokeno
Feature activation+0.601
all
Token all
Feature activation+0.385
,
Token,
Feature activation+0.196
getting
Token getting
Feature activation+0.070
back
Token back
Feature activation+0.358
something
Token something
Feature activation+0.595
the
Token the
Feature activation+0.628
car
Token car
Feature activation+0.438
community
Token community
Feature activation+0.531
has
Token has
Feature activation+0.596
lost
Token lost
Feature activation+0.490
some
Token some
Feature activation+0.526
functional
Token functional
Feature activation+0.262
brain
Token brain
Feature activation+0.401
imaging
Token imaging
Feature activation+0.525
in
Token in
Feature activation+0.640
real
Token real
Feature activation+0.653
time
Token time
Feature activation+0.648
in
Token in
Feature activation+0.589
adolescents
Token adolescents
Feature activation+0.498
and
Token and
Feature activation+0.456
even
Token even
Feature activation+0.459
in
Token in
Feature activation+0.556

INTERVAL 0.500 - 0.601
CONTAINS 0.051%

how
Token how
Feature activation+0.096
,
Token,
Feature activation+0.377
as
Token as
Feature activation+0.194
the
Token the
Feature activation+0.360
result
Token result
Feature activation+0.411
of
Token of
Feature activation+0.542
so
Token so
Feature activation+0.569
doing
Token doing
Feature activation+0.509
,
Token,
Feature activation+0.397
civilization
Token civilization
Feature activation+0.341
may
Token may
Feature activation+0.553
and
Token and
Feature activation+0.097
harm
Token harm
Feature activation+0.176
the
Token the
Feature activation+0.257
public
Token public
Feature activation+0.314
perception
Token perception
Feature activation+0.400
of
Token of
Feature activation+0.530
those
Token those
Feature activation+0.514
who
Token who
Feature activation+0.443
believe
Token believe
Feature activation+0.485
in
Token in
Feature activation+0.607
traditional
Token traditional
Feature activation+0.623
play
Token play
Feature activation+0.029
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
hard
Token hard
Feature activation+0.233
-
Token-
Feature activation+0.525
hit
Tokenhit
Feature activation+0.547
single
Token single
Feature activation+0.555
were
Token were
Feature activation+0.418
the
Token the
Feature activation+0.334
only
Token only
Feature activation+0.328
the
Token the
Feature activation+0.178
finest
Token finest
Feature activation+0.151
,
Token,
Feature activation+0.115
nutrient
Token nutrient
Feature activation+0.161
-
Token-
Feature activation+0.501
rich
Tokenrich
Feature activation+0.572
compost
Token compost
Feature activation+0.477
.
Token.
Feature activation+0.000
Cedar
Token Cedar
Feature activation+0.003
Grove
Token Grove
Feature activation+0.000
has
Token has
Feature activation+0.000
,
Token,
Feature activation+0.020
as
Token as
Feature activation+0.000
amended
Token amended
Feature activation+0.162
,
Token,
Feature activation+0.469
known
Token known
Feature activation+0.324
as
Token as
Feature activation+0.588
the
Token the
Feature activation+0.580
Clayton
Token Clayton
Feature activation+0.392
Act
Token Act
Feature activation+0.485
,
Token,
Feature activation+0.478
and
Token and
Feature activation+0.286

INTERVAL 0.400 - 0.500
CONTAINS 0.118%

uncle
Token uncle
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.100
killed
Token killed
Feature activation+0.234
six
Token six
Feature activation+0.401
years
Token years
Feature activation+0.476
ago
Token ago
Feature activation+0.475
.
Token.
Feature activation+0.000
'
Token '
Feature activation+0.000
Safe
TokenSafe
Feature activation+0.000
they
Token they
Feature activation+0.407
have
Token have
Feature activation+0.255
been
Token been
Feature activation+0.288
summons
Token summons
Feature activation+0.400
ed
Tokened
Feature activation+0.603
as
Token as
Feature activation+0.479
witnesses
Token witnesses
Feature activation+0.420
or
Token or
Feature activation+0.390
defendants
Token defendants
Feature activation+0.271
,
Token,
Feature activation+0.457
solicit
Token solicit
Feature activation+0.455
and
Token and
Feature activation+0.438
people
Token people
Feature activation+0.377
who
Token who
Feature activation+0.438
aren
Token aren
Feature activation+0.413
't
Token't
Feature activation+0.529
there
Token there
Feature activation+0.441
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
They
TokenThey
Feature activation+0.000
are
Token are
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
many
Token many
Feature activation+0.043
outside
Token outside
Feature activation+0.353
responsibilities
Token responsibilities
Feature activation+0.412
as
Token as
Feature activation+0.391
well
Token well
Feature activation+0.290
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
do
Token do
Feature activation+0.000
turn
Token turn
Feature activation+0.265
signals
Token signals
Feature activation+0.282
,
Token,
Feature activation+0.090
which
Token which
Feature activation+0.124
reduces
Token reduces
Feature activation+0.197
conflicts
Token conflicts
Feature activation+0.431
between
Token between
Feature activation+0.602
left
Token left
Feature activation+0.736
-
Token-
Feature activation+0.649
turn
Tokenturn
Feature activation+0.664
ing
Tokening
Feature activation+0.618

INTERVAL 0.300 - 0.400
CONTAINS 0.227%

of
Token of
Feature activation+0.366
Abu
Token Abu
Feature activation+0.355
Dhabi
Token Dhabi
Feature activation+0.346
(
Token (
Feature activation+0.151
NB
TokenNB
Feature activation+0.187
AD
TokenAD
Feature activation+0.350
),
Token),
Feature activation+0.095
AT
Token AT
Feature activation+0.125
B
TokenB
Feature activation+0.339
Financial
Token Financial
Feature activation+0.489
,
Token,
Feature activation+0.324
ability
Token ability
Feature activation+0.317
to
Token to
Feature activation+0.339
keep
Token keep
Feature activation+0.395
children
Token children
Feature activation+0.427
on
Token on
Feature activation+0.577
their
Token their
Feature activation+0.337
policies
Token policies
Feature activation+0.318
until
Token until
Feature activation+0.366
age
Token age
Feature activation+0.437
26
Token 26
Feature activation+0.468
.
Token.
Feature activation+0.000
him
Token him
Feature activation+0.315
or
Token or
Feature activation+0.250
herself
Token herself
Feature activation+0.238
as
Token as
Feature activation+0.273
belonging
Token belonging
Feature activation+0.198
separate
Token separate
Feature activation+0.332
from
Token from
Feature activation+0.476
the
Token the
Feature activation+0.243
rest
Token rest
Feature activation+0.211
of
Token of
Feature activation+0.320
the
Token the
Feature activation+0.223
weird
Token weird
Feature activation+0.000
cyber
Token cyber
Feature activation+0.015
netic
Tokennetic
Feature activation+0.087
suit
Token suit
Feature activation+0.192
whose
Token whose
Feature activation+0.182
massive
Token massive
Feature activation+0.353
arms
Token arms
Feature activation+0.410
extend
Token extend
Feature activation+0.586
like
Token like
Feature activation+0.510
lim
Token lim
Feature activation+0.288
ber
Tokenber
Feature activation+0.382
and
Token and
Feature activation+0.087
Real
Token Real
Feature activation+0.042
Madrid
Token Madrid
Feature activation+0.135
destined
Token destined
Feature activation+0.176
only
Token only
Feature activation+0.276
to
Token to
Feature activation+0.307
cross
Token cross
Feature activation+0.190
paths
Token paths
Feature activation+0.234
if
Token if
Feature activation+0.155
both
Token both
Feature activation+0.148
reach
Token reach
Feature activation+0.119

INTERVAL 0.200 - 0.300
CONTAINS 0.392%

open
Token open
Feature activation+0.365
on
Token on
Feature activation+0.446
the
Token the
Feature activation+0.319
first
Token first
Feature activation+0.303
weekend
Token weekend
Feature activation+0.265
of
Token of
Feature activation+0.235
early
Token early
Feature activation+0.272
voting
Token voting
Feature activation+0.259
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
even
Token even
Feature activation+0.000
better
Token better
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
improving
Token improving
Feature activation+0.011
how
Token how
Feature activation+0.226
we
Token we
Feature activation+0.300
manage
Token manage
Feature activation+0.467
performance
Token performance
Feature activation+0.524
and
Token and
Feature activation+0.366
avoid
Token avoid
Feature activation+0.181
is
Token is
Feature activation+0.195
added
Token added
Feature activation+0.122
once
Token once
Feature activation+0.094
we
Token we
Feature activation+0.142
factor
Token factor
Feature activation+0.093
in
Token in
Feature activation+0.226
those
Token those
Feature activation+0.153
who
Token who
Feature activation+0.145
make
Token make
Feature activation+0.079
it
Token it
Feature activation+0.086
to
Token to
Feature activation+0.012
emer
Token emer
Feature activation+0.221
ald
Tokenald
Feature activation+0.330
hills
Token hills
Feature activation+0.303
with
Token with
Feature activation+0.234
scenic
Token scenic
Feature activation+0.075
views
Token views
Feature activation+0.261
of
Token of
Feature activation+0.265
the
Token the
Feature activation+0.108
C
Token C
Feature activation+0.000
asc
Tokenasc
Feature activation+0.000
ades
Tokenades
Feature activation+0.000
before
Token before
Feature activation+0.000
-
Token -
Feature activation+0.000
just
Token just
Feature activation+0.000
think
Token think
Feature activation+0.068
of
Token of
Feature activation+0.290
Almost
Token Almost
Feature activation+0.218
Human
Token Human
Feature activation+0.260
creator
Token creator
Feature activation+0.365
Joel
Token Joel
Feature activation+0.392
Wy
Token Wy
Feature activation+0.355
man
Tokenman
Feature activation+0.400

INTERVAL 0.100 - 0.200
CONTAINS 0.647%

security
Token security
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
sparked
Token sparked
Feature activation+0.000
by
Token by
Feature activation+0.000
Hamas
Token Hamas
Feature activation+0.029
rocket
Token rocket
Feature activation+0.191
attacks
Token attacks
Feature activation+0.173
from
Token from
Feature activation+0.188
Gaza
Token Gaza
Feature activation+0.168
.
Token .
Feature activation+0.018
Thousands
Token Thousands
Feature activation+0.000
potential
Token potential
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
those
Token those
Feature activation+0.000
in
Token in
Feature activation+0.105
the
Token the
Feature activation+0.000
environment
Token environment
Feature activation+0.029
and
Token and
Feature activation+0.145
he
Token he
Feature activation+0.000
ath
Tokenath
Feature activation+0.000
racing
Token racing
Feature activation+0.000
and
Token and
Feature activation+0.000
hon
Token hon
Feature activation+0.021
ing
Tokening
Feature activation+0.247
your
Token your
Feature activation+0.158
skills
Token skills
Feature activation+0.176
!
Token!
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
complete
Token complete
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
stage
Token stage
Feature activation+0.000
victory
Token victory
Feature activation+0.000
ahead
Token ahead
Feature activation+0.047
of
Token of
Feature activation+0.137
Sergio
Token Sergio
Feature activation+0.090
Hen
Token Hen
Feature activation+0.139
ao
Tokenao
Feature activation+0.183
and
Token and
Feature activation+0.000
Richie
Token Richie
Feature activation+0.000
street
Token street
Feature activation+0.000
,
Token,
Feature activation+0.000
city
Token city
Feature activation+0.000
,
Token,
Feature activation+0.018
province
Token province
Feature activation+0.000
and
Token and
Feature activation+0.142
post
Token post
Feature activation+0.194
code
Tokencode
Feature activation+0.400
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
my
Token my
Feature activation+0.000

INTERVAL 0.000 - 0.100
CONTAINS 98.533%

in
Token in
Feature activation+0.000
these
Token these
Feature activation+0.000
very
Token very
Feature activation+0.000
pages
Token pages
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
demise
Token demise
Feature activation+0.000
of
Token of
Feature activation+0.000
Pakistan
Token Pakistan
Feature activation+0.000
is
Token is
Feature activation+0.000
"
Token "
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
READ
TokenREAD
Feature activation+0.000
MORE
Token MORE
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
*
Token*
Feature activation+0.000
Victory
Token Victory
Feature activation+0.000
at
Token at
Feature activation+0.000
hand
Token hand
Feature activation+0.000
or
Token or
Feature activation+0.000
campaigns
Token campaigns
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
results
Token results
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
best
Token best
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
ability
Tokenability
Feature activation+0.000
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
.
Token.
Feature activation+0.000
Why
Token Why
Feature activation+0.000
do
Token do
Feature activation+0.000
some
Token some
Feature activation+0.000
built
Token built
Feature activation+0.000
forms
Token forms
Feature activation+0.000
resemble
Token resemble
Feature activation+0.000
biological
Token biological
Feature activation+0.000
pm
Tokenpm
Feature activation+0.000
The
Token The
Feature activation+0.000
Red
Token Red
Feature activation+0.000
Serpent
Token Serpent
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
10
Token10
Feature activation+0.000
pm
Tokenpm
Feature activation+0.000
Sacrament
Token Sacrament
Feature activation+0.000
um
Tokenum
Feature activation+0.000
Gladiator
Token Gladiator
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H2.10: (feature 15010)

TOP ACTIVATIONS
MAX = 2.553

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
background
Token background
Feature activation+0.000
check
Token check
Feature activation+0.000
measure
Token measure
Feature activation+0.000
--
Token --
Feature activation+1.958
painstaking
Token painstaking
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
crafted
Token crafted
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
power
Token power
Feature activation+0.000
grid
Token grid
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.896
an
Token an
Feature activation+0.064
event
Token event
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
dwarf
Token dwarf
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
the
Token the
Feature activation+0.000
ultimate
Token ultimate
Feature activation+0.000
political
Token political
Feature activation+0.000
survivor
Token survivor
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.862
but
Token but
Feature activation+0.142
he
Token he
Feature activation+0.000
emerges
Token emerges
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
hasn
Token hasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.790
the
Token the
Feature activation+0.000
Nin
Token Nin
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
are
Token are
Feature activation+0.000
2
Token 2
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
dis
Token dis
Feature activation+0.000
interest
Tokeninterest
Feature activation+0.000
in
Token in
Feature activation+0.000
subscription
Token subscription
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+1.718
and
Tokenand
Feature activation+0.000
Penguin
Token Penguin
Feature activation+0.000
Random
Token Random
Feature activation+0.000
House
Token House
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
or
Token or
Feature activation+0.000
college
Token college
Feature activation+0.000
in
Token in
Feature activation+0.000
Alberta
Token Alberta
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.715
especially
Token especially
Feature activation+0.374
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
oversee
Token oversee
Feature activation+0.000
one
Token one
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
To
TokenTo
Feature activation+0.000
do
Token do
Feature activation+0.000
this
Token this
Feature activation+0.000
well
Token well
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.715
and
Token and
Feature activation+0.000
foster
Token foster
Feature activation+0.000
it
Token it
Feature activation+0.000
in
Token in
Feature activation+0.000
places
Token places
Feature activation+0.000
pipe
Token pipe
Feature activation+0.000
yard
Token yard
Feature activation+0.000
in
Token in
Feature activation+0.000
C
Token C
Feature activation+0.000
ushing
Tokenushing
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.642
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
p
Tokenp
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
X
TokenX
Feature activation+0.000
e
Tokene
Feature activation+0.000
Ol
TokenOl
Feature activation+0.000
ORY
TokenORY
Feature activation+0.000
Ub
TokenUb
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.619
Nick
Token Nick
Feature activation+0.000
(@
Token (@
Feature activation+0.000
Nick
TokenNick
Feature activation+0.000
_
Token_
Feature activation+0.000
Fal
TokenFal
Feature activation+0.000
thereof
Token thereof
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
expert
Token expert
Feature activation+0.000
report
Token report
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.607
boiled
Token boiled
Feature activation+0.000
down
Token down
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
inter
Token inter
Feature activation+0.000
were
Token were
Feature activation+0.000
supposed
Token supposed
Feature activation+0.000
to
Token to
Feature activation+0.000
spend
Token spend
Feature activation+0.000
together
Token together
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.601
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
as
Token as
Feature activation+0.000
good
Token good
Feature activation+0.000
as
Token as
Feature activation+0.000
depicted
Token depicted
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+1.581
nor
Tokennor
Feature activation+0.000
as
Token as
Feature activation+0.000
bad
Token bad
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
BER
TokenBER
Feature activation+0.000
N
TokenN
Feature activation+0.000
ARDS
TokenARDS
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.574
The
Token The
Feature activation+0.339
17
Token 17
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
completing
Token completing
Feature activation+0.000
them
Token them
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+1.556
before
Tokenbefore
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
circles
Token circles
Feature activation+0.000
main
Token main
Feature activation+0.000
st
Tokenst
Feature activation+0.000
ays
Tokenays
Feature activation+0.000
Bore
Token Bore
Feature activation+0.000
ale
Tokenale
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.504
another
Token another
Feature activation+0.000
Quebec
Token Quebec
Feature activation+0.000
micro
Token micro
Feature activation+0.000
brew
Tokenbrew
Feature activation+0.000
ery
Tokenery
Feature activation+0.000
G
Token G
Feature activation+0.000
yan
Tokenyan
Feature activation+0.000
Sang
Token Sang
Feature activation+0.000
am
Tokenam
Feature activation+0.000
'
Token '
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.482
the
Token the
Feature activation+0.000
joint
Token joint
Feature activation+0.000
conference
Token conference
Feature activation+0.000
of
Token of
Feature activation+0.000
direct
Token direct
Feature activation+0.000
CA
Token CA
Feature activation+0.000
--
Token--
Feature activation+2.005
(
Token(
Feature activation+0.842
Market
TokenMarket
Feature activation+0.114
wired
Tokenwired
Feature activation+0.000
-
Token -
Feature activation+1.436
Jul
Token Jul
Feature activation+0.097
25
Token 25
Feature activation+0.000
,
Token,
Feature activation+0.031
2016
Token 2016
Feature activation+0.000
)
Token)
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
ar
Token ar
Feature activation+0.000
k
Tokenk
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+1.435
also
Tokenalso
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
men
Token men
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
,
Token,
Feature activation+0.000
Mitch
Token Mitch
Feature activation+0.000
McConnell
Token McConnell
Feature activation+0.000
was
Token was
Feature activation+0.000
right
Token right
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.423
in
Token in
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
MORE
Token MORE
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
best
Token best
Feature activation+0.000
days
Token days
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.389
are
Token are
Feature activation+0.000
actively
Token actively
Feature activation+0.000
trying
Token trying
Feature activation+0.000
just
Token just
Feature activation+0.000
about
Token about
Feature activation+0.000

Top DFA by src position
MAX = 3.046

<|endoftext|>
Token<|endoftext|>
Feature activation+0.503
Top resid features:
The
TokenThe
Feature activation-0.385
Top resid features:
background
Token background
Feature activation+0.240
Top resid features:
check
Token check
Feature activation+0.097
Top resid features:
measure
Token measure
Feature activation+0.505
Top resid features:
--
Token --
Feature activation+2.594
Top resid features:
painstaking
Token painstaking
Feature activation+0.000
Top resid features:
ly
Tokenly
Feature activation+0.000
Top resid features:
crafted
Token crafted
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.154
Top resid features:
S
TokenS
Feature activation-0.124
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
power
Token power
Feature activation+0.124
Top resid features:
grid
Token grid
Feature activation+0.437
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+2.632
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
event
Token event
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
dwarf
Token dwarf
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.588
Top resid features:
the
Token the
Feature activation-0.344
Top resid features:
ultimate
Token ultimate
Feature activation-0.213
Top resid features:
political
Token political
Feature activation+0.028
Top resid features:
survivor
Token survivor
Feature activation+0.405
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.992
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
emerges
Token emerges
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.581
Top resid features:
hasn
Token hasn
Feature activation-0.071
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.109
Top resid features:
t
Tokent
Feature activation-0.025
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+2.793
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Nin
Token Nin
Feature activation+0.000
Top resid features:
ers
Tokeners
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
2
Token 2
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.693
Top resid features:
dis
Token dis
Feature activation-0.200
Top resid features:
interest
Tokeninterest
Feature activation+0.087
Top resid features:
in
Token in
Feature activation-0.177
Top resid features:
subscription
Token subscription
Feature activation-0.050
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+2.960
Top resid features:
and
Tokenand
Feature activation+0.000
Top resid features:
Penguin
Token Penguin
Feature activation+0.000
Top resid features:
Random
Token Random
Feature activation+0.000
Top resid features:
House
Token House
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.559
Top resid features:
or
Token or
Feature activation-0.272
Top resid features:
college
Token college
Feature activation-0.184
Top resid features:
in
Token in
Feature activation-0.087
Top resid features:
Alberta
Token Alberta
Feature activation+0.248
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+3.046
Top resid features:
especially
Token especially
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
oversee
Token oversee
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.549
Top resid features:
To
TokenTo
Feature activation-0.231
Top resid features:
do
Token do
Feature activation-0.135
Top resid features:
this
Token this
Feature activation-0.142
Top resid features:
well
Token well
Feature activation+0.413
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+2.856
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
foster
Token foster
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
places
Token places
Feature activation+0.000
Top resid features:
pipe
Token pipe
Feature activation-0.033
Top resid features:
yard
Token yard
Feature activation+0.054
Top resid features:
in
Token in
Feature activation-0.103
Top resid features:
C
Token C
Feature activation-0.225
Top resid features:
ushing
Tokenushing
Feature activation+0.055
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+2.940
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
p
Tokenp
Feature activation+0.000
Top resid features:
ip
Tokenip
Feature activation+0.000
Top resid features:
X
TokenX
Feature activation-0.158
Top resid features:
e
Tokene
Feature activation-0.009
Top resid features:
Ol
TokenOl
Feature activation+0.009
Top resid features:
ORY
TokenORY
Feature activation+0.102
Top resid features:
Ub
TokenUb
Feature activation-0.065
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.755
Top resid features:
Nick
Token Nick
Feature activation+0.000
Top resid features:
(@
Token (@
Feature activation+0.000
Top resid features:
Nick
TokenNick
Feature activation+0.000
Top resid features:
_
Token_
Feature activation+0.000
Top resid features:
Fal
TokenFal
Feature activation+0.000
Top resid features:
thereof
Token thereof
Feature activation-0.112
Top resid features:
in
Token in
Feature activation-0.161
Top resid features:
my
Token my
Feature activation-0.178
Top resid features:
expert
Token expert
Feature activation+0.165
Top resid features:
report
Token report
Feature activation+0.323
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.665
Top resid features:
boiled
Token boiled
Feature activation+0.000
Top resid features:
down
Token down
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:
inter
Token inter
Feature activation+0.000
Top resid features:
were
Token were
Feature activation-0.057
Top resid features:
supposed
Token supposed
Feature activation-0.045
Top resid features:
to
Token to
Feature activation-0.037
Top resid features:
spend
Token spend
Feature activation+0.139
Top resid features:
together
Token together
Feature activation-0.090
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.797
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:
s
Tokens
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.697
Top resid features:
as
Token as
Feature activation-0.059
Top resid features:
good
Token good
Feature activation-0.021
Top resid features:
as
Token as
Feature activation-0.206
Top resid features:
depicted
Token depicted
Feature activation+0.112
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+2.654
Top resid features:
nor
Tokennor
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
bad
Token bad
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.075
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.378
Top resid features:
BER
TokenBER
Feature activation-0.118
Top resid features:
N
TokenN
Feature activation-0.045
Top resid features:
ARDS
TokenARDS
Feature activation+0.048
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.560
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
17
Token 17
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
year
Tokenyear
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.584
Top resid features:
to
Token to
Feature activation-0.051
Top resid features:
be
Token be
Feature activation-0.030
Top resid features:
completing
Token completing
Feature activation-0.292
Top resid features:
them
Token them
Feature activation+0.258
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+2.682
Top resid features:
before
Tokenbefore
Feature activation+0.000
Top resid features:
one
Token one
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:
circles
Token circles
Feature activation+0.000
Top resid features:
main
Token main
Feature activation-0.052
Top resid features:
st
Tokenst
Feature activation-0.010
Top resid features:
ays
Tokenays
Feature activation+0.187
Top resid features:
Bore
Token Bore
Feature activation-0.061
Top resid features:
ale
Tokenale
Feature activation+0.122
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+2.531
Top resid features:
another
Token another
Feature activation+0.000
Top resid features:
Quebec
Token Quebec
Feature activation+0.000
Top resid features:
micro
Token micro
Feature activation+0.000
Top resid features:
brew
Tokenbrew
Feature activation+0.000
Top resid features:
ery
Tokenery
Feature activation+0.000
Top resid features:
G
Token G
Feature activation-0.096
Top resid features:
yan
Tokenyan
Feature activation+0.026
Top resid features:
Sang
Token Sang
Feature activation+0.007
Top resid features:
am
Tokenam
Feature activation+0.101
Top resid features:
'
Token '
Feature activation+0.135
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.371
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
joint
Token joint
Feature activation+0.000
Top resid features:
conference
Token conference
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
direct
Token direct
Feature activation+0.000
Top resid features:
CA
Token CA
Feature activation+0.021
Top resid features:
--
Token--
Feature activation+1.024
Top resid features:
(
Token(
Feature activation-0.069
Top resid features:
Market
TokenMarket
Feature activation-0.070
Top resid features:
wired
Tokenwired
Feature activation+0.392
Top resid features:
-
Token -
Feature activation+1.193
Top resid features:
Jul
Token Jul
Feature activation+0.000
Top resid features:
25
Token 25
Feature activation+0.000
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:
out
Token out
Feature activation+0.045
Top resid features:
of
Token of
Feature activation-0.073
Top resid features:
the
Token the
Feature activation-0.238
Top resid features:
ar
Token ar
Feature activation-0.022
Top resid features:
k
Tokenk
Feature activation+0.129
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+2.723
Top resid features:
also
Tokenalso
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
men
Token men
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.111
Top resid features:
Mitch
Token Mitch
Feature activation-0.079
Top resid features:
McConnell
Token McConnell
Feature activation+0.139
Top resid features:
was
Token was
Feature activation-0.048
Top resid features:
right
Token right
Feature activation-0.444
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.801
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
2014
Token 2014
Feature activation+0.000
Top resid features:
MORE
Token MORE
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:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.604
Top resid features:
on
Token on
Feature activation-0.054
Top resid features:
his
Token his
Feature activation-0.295
Top resid features:
best
Token best
Feature activation-0.079
Top resid features:
days
Token days
Feature activation-0.049
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.858
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
actively
Token actively
Feature activation+0.000
Top resid features:
trying
Token trying
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.04

Head 2: 0.06

Head 3: 0.05

Head 4: 0.02

Head 5: 0.10

Head 6: 0.07

Head 7: 0.14

Head 8: 0.05

Head 9: 0.04

Head 10: 0.25

Head 11: 0.11

Positive logits

jri1.19

won1.08

��0.96

phas0.90

prus0.90

STD0.89

Sel0.87

ecided0.86

attled0.85

adv0.85

pha0.84

dated0.84

Labour0.83

carbohyd0.82

lled0.81

Bel0.81

Hutchinson0.81

foundland0.81

berra0.80

dom0.80

Negative logits

Magical-0.90

NM-0.84

((-0.83

Tycoon-0.81

assadors-0.80

Awesome-0.80

WOOD-0.79

Example-0.79

Ax-0.78

Lime-0.78

Metallic-0.77

Midnight-0.77

comparable-0.77

Auction-0.77

iro-0.76

Juice-0.76

Mutant-0.75

AW-0.75

""-0.75

ox-0.75

INTERVAL 2.298 - 2.553
CONTAINS 0.000%

INTERVAL 2.042 - 2.298
CONTAINS 0.001%

INTERVAL 1.787 - 2.042
CONTAINS 0.002%

.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
power
Token power
Feature activation+0.000
grid
Token grid
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.896
an
Token an
Feature activation+0.064
event
Token event
Feature activation+0.000
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
dwarf
Token dwarf
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
hasn
Token hasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.790
the
Token the
Feature activation+0.000
Nin
Token Nin
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
are
Token are
Feature activation+0.000
2
Token 2
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
background
Token background
Feature activation+0.000
check
Token check
Feature activation+0.000
measure
Token measure
Feature activation+0.000
--
Token --
Feature activation+1.958
painstaking
Token painstaking
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
crafted
Token crafted
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
the
Token the
Feature activation+0.000
ultimate
Token ultimate
Feature activation+0.000
political
Token political
Feature activation+0.000
survivor
Token survivor
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.862
but
Token but
Feature activation+0.142
he
Token he
Feature activation+0.000
emerges
Token emerges
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.532 - 1.787
CONTAINS 0.003%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
To
TokenTo
Feature activation+0.000
do
Token do
Feature activation+0.000
this
Token this
Feature activation+0.000
well
Token well
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.715
and
Token and
Feature activation+0.000
foster
Token foster
Feature activation+0.000
it
Token it
Feature activation+0.000
in
Token in
Feature activation+0.000
places
Token places
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
or
Token or
Feature activation+0.000
college
Token college
Feature activation+0.000
in
Token in
Feature activation+0.000
Alberta
Token Alberta
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.715
especially
Token especially
Feature activation+0.374
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
oversee
Token oversee
Feature activation+0.000
one
Token one
Feature activation+0.000
pipe
Token pipe
Feature activation+0.000
yard
Token yard
Feature activation+0.000
in
Token in
Feature activation+0.000
C
Token C
Feature activation+0.000
ushing
Tokenushing
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.642
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
p
Tokenp
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
BER
TokenBER
Feature activation+0.000
N
TokenN
Feature activation+0.000
ARDS
TokenARDS
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.574
The
Token The
Feature activation+0.339
17
Token 17
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
as
Token as
Feature activation+0.000
good
Token good
Feature activation+0.000
as
Token as
Feature activation+0.000
depicted
Token depicted
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+1.581
nor
Tokennor
Feature activation+0.000
as
Token as
Feature activation+0.000
bad
Token bad
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.277 - 1.532
CONTAINS 0.004%

CA
Token CA
Feature activation+0.000
--
Token--
Feature activation+2.005
(
Token(
Feature activation+0.842
Market
TokenMarket
Feature activation+0.114
wired
Tokenwired
Feature activation+0.000
-
Token -
Feature activation+1.436
Jul
Token Jul
Feature activation+0.097
25
Token 25
Feature activation+0.000
,
Token,
Feature activation+0.031
2016
Token 2016
Feature activation+0.000
)
Token)
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
best
Token best
Feature activation+0.000
days
Token days
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.389
are
Token are
Feature activation+0.000
actively
Token actively
Feature activation+0.000
trying
Token trying
Feature activation+0.000
just
Token just
Feature activation+0.000
about
Token about
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
long
Token long
Feature activation+0.000
worried
Token worried
Feature activation+0.000
by
Token by
Feature activation+0.000
Moscow
Token Moscow
Feature activation+0.000
-
Token -
Feature activation+1.280
had
Token had
Feature activation+0.067
assumed
Token assumed
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
itself
Token itself
Feature activation+0.000
faced
Token faced
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Start
TokenStart
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.329
Start
Token Start
Feature activation+0.000
/
Token/
Feature activation+0.000
Stop
TokenStop
Feature activation+0.000
&
Token &
Feature activation+0.000
shows
Token shows
Feature activation+0.000
main
Token main
Feature activation+0.000
st
Tokenst
Feature activation+0.000
ays
Tokenays
Feature activation+0.000
Bore
Token Bore
Feature activation+0.000
ale
Tokenale
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.504
another
Token another
Feature activation+0.000
Quebec
Token Quebec
Feature activation+0.000
micro
Token micro
Feature activation+0.000
brew
Tokenbrew
Feature activation+0.000
ery
Tokenery
Feature activation+0.000

INTERVAL 1.021 - 1.277
CONTAINS 0.003%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
,
Token,
Feature activation+0.000
30
Token 30
Feature activation+0.000
November
Token November
Feature activation+0.000
-
Token -
Feature activation+1.088
0001
Token0001
Feature activation+0.000
00
Token 00
Feature activation+0.000
:
Token:
Feature activation+0.000
00
Token00
Feature activation+0.000
Written
Token Written
Feature activation+0.000
four
Token four
Feature activation+0.000
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
s
Tokens
Feature activation+0.000
ales
Tokenales
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.243
the
Token the
Feature activation+0.000
limits
Token limits
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
based
Token based
Feature activation+0.000
man
Tokenman
Feature activation+0.000
Daniel
Token Daniel
Feature activation+0.000
O
Token O
Feature activation+0.000
'
Token'
Feature activation+0.000
Donnell
TokenDonnell
Feature activation+0.000
--
Token --
Feature activation+1.041
Ros
Token Ros
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
O
Token O
Feature activation+0.000
'
Token'
Feature activation+0.000
Donnell
TokenDonnell
Feature activation+0.000
,
Token,
Feature activation+0.000
two
Token two
Feature activation+0.000
walk
Token walk
Feature activation+0.000
-
Token-
Feature activation+0.000
ons
Tokenons
Feature activation+0.000
--
Token --
Feature activation+1.271
and
Token and
Feature activation+0.000
two
Token two
Feature activation+0.000
delet
Token delet
Feature activation+0.000
ions
Tokenions
Feature activation+0.000
.
Token.
Feature activation+0.000
launched
Token launched
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
permanent
Token permanent
Feature activation+0.000
CEO
Token CEO
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.049
a
Token a
Feature activation+0.000
move
Token move
Feature activation+0.000
cheered
Token cheered
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.766 - 1.021
CONTAINS 0.006%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
and
Token and
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
it
Token it
Feature activation+0.000
off
Token off
Feature activation+0.000
-
Token -
Feature activation+1.006
can
Token can
Feature activation+0.000
reduce
Token reduce
Feature activation+0.000
those
Token those
Feature activation+0.000
risks
Token risks
Feature activation+0.000
.
Token.
Feature activation+0.000
get
Token get
Feature activation+0.000
started
Token started
Feature activation+0.000
on
Token on
Feature activation+0.000
right
Token right
Feature activation+0.000
away
Token away
Feature activation+0.000
-
Token -
Feature activation+0.848
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
likely
Token likely
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
with
Token with
Feature activation+0.000
everybody
Token everybody
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
-
Token -
Feature activation+0.795
and
Token and
Feature activation+0.000
learned
Token learned
Feature activation+0.000
more
Token more
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
of
Token of
Feature activation+0.000
beating
Token beating
Feature activation+0.000
Mercedes
Token Mercedes
Feature activation+0.000
and
Token and
Feature activation+0.000
Ferrari
Token Ferrari
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.014
has
Token has
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
employ
Token employ
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
aroused
Token aroused
Feature activation+0.000
by
Token by
Feature activation+0.000
bisexual
Token bisexual
Feature activation+0.000
clips
Token clips
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.949
for
Tokenfor
Feature activation+0.000
example
Token example
Feature activation+0.000
,
Token,
Feature activation+0.000
two
Token two
Feature activation+0.000
men
Token men
Feature activation+0.000

INTERVAL 0.511 - 0.766
CONTAINS 0.007%

preserved
Token preserved
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
fossil
Token fossil
Feature activation+0.000
record
Token record
Feature activation+0.000
--
Token --
Feature activation+0.575
and
Token and
Feature activation+0.000
intriguing
Token intriguing
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
area
Token area
Feature activation+0.000
atop
Token atop
Feature activation+0.000
a
Token a
Feature activation+0.000
hill
Token hill
Feature activation+0.000
there
Token there
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.685
a
Token a
Feature activation+0.000
place
Token place
Feature activation+0.000
that
Token that
Feature activation+0.000
contains
Token contains
Feature activation+0.000
popular
Token popular
Feature activation+0.000
.
Token.
Feature activation+0.000
Inst
Token Inst
Feature activation+0.000
ance
Tokenance
Feature activation+0.000
Mot
Token Mot
Feature activation+0.000
if
Tokenif
Feature activation+0.000
-
Token -
Feature activation+0.707
Celestial
Token Celestial
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ch
TokenCh
Feature activation+0.000
apters
Tokenapters
Feature activation+0.000
stuff
Token stuff
Feature activation+0.000
we
Token we
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
need
Token need
Feature activation+0.000
--
Token --
Feature activation+0.623
but
Token but
Feature activation+0.000
certainly
Token certainly
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
want
Token want
Feature activation+0.000
Story
Token Story
Feature activation+0.000
,
Token,
Feature activation+0.000
book
Token book
Feature activation+0.000
and
Token and
Feature activation+0.000
film
Token film
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.516
"
Token "
Feature activation+0.000
Is
TokenIs
Feature activation+0.000
God
Token God
Feature activation+0.000
calling
Token calling
Feature activation+0.000
me
Token me
Feature activation+0.000

INTERVAL 0.255 - 0.511
CONTAINS 0.011%

Daily
Token Daily
Feature activation+0.000
Mirror
Token Mirror
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Sun
Token Sun
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.438
"
Token "
Feature activation+0.000
to
Tokento
Feature activation+0.000
do
Token do
Feature activation+0.000
what
Token what
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
consequences
Token consequences
Feature activation+0.000
of
Token of
Feature activation+0.000
your
Token your
Feature activation+0.000
actions
Token actions
Feature activation+0.000
-
Token -
Feature activation+0.487
be
Token be
Feature activation+0.000
it
Token it
Feature activation+0.000
self
Token self
Feature activation+0.000
-
Token-
Feature activation+0.000
all
Tokenall
Feature activation+0.000
loss
Token loss
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
Republican
TokenRepublican
Feature activation+0.000
values
Token values
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.339
strong
Token strong
Feature activation+0.000
families
Token families
Feature activation+0.000
,
Token,
Feature activation+0.000
faith
Token faith
Feature activation+0.000
,
Token,
Feature activation+0.000
Mer
Token Mer
Feature activation+0.000
ck
Tokenck
Feature activation+0.000
releases
Token releases
Feature activation+0.000
a
Token a
Feature activation+0.000
statement
Token statement
Feature activation+0.000
:
Token:
Feature activation+0.298
Mer
Token Mer
Feature activation+0.000
ck
Tokenck
Feature activation+0.000
Resp
Token Resp
Feature activation+0.000
onds
Tokenonds
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
check
Token check
Feature activation+0.000
-
Token-
Feature activation+0.000
in
Tokenin
Feature activation+0.000
deals
Token deals
Feature activation+0.000
:
Token:
Feature activation+0.482
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Once
TokenOnce
Feature activation+0.000
someone
Token someone
Feature activation+0.000
tags
Token tags
Feature activation+0.000

INTERVAL 0.000 - 0.255
CONTAINS 99.964%

PCs
Token PCs
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
affected
Token affected
Feature activation+0.000
Mac
Token Mac
Feature activation+0.000
sales
Token sales
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
simpler
Token simpler
Feature activation+0.000
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.000
accessible
Token accessible
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
So
TokenSo
Feature activation+0.000
a
Token a
Feature activation+0.000
reverse
Token reverse
Feature activation+0.000
,
Token,
Feature activation+0.000
give
Token give
Feature activation+0.000
your
Token your
Feature activation+0.000
local
Token local
Feature activation+0.000
vet
Token vet
Feature activation+0.000
a
Token a
Feature activation+0.000
call
Token call
Feature activation+0.000
and
Token and
Feature activation+0.000
schedule
Token schedule
Feature activation+0.000
an
Token an
Feature activation+0.000
appointment
Token appointment
Feature activation+0.000
or
Token or
Feature activation+0.000
forward
Token forward
Feature activation+0.000
movement
Token movement
Feature activation+0.000
on
Token on
Feature activation+0.000
strengthening
Token strengthening
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
defense
Token defense
Feature activation+0.000
charge
Token charge
Feature activation+0.000
F
Token F
Feature activation+0.000
of
Tokenof
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
.
Token.
Feature activation+0.000
Nor
Token Nor
Feature activation+0.000
are
Token are
Feature activation+0.000
they
Token they
Feature activation+0.000
expressing
Token expressing
Feature activation+0.000
a
Token a
Feature activation+0.000
sincerely
Token sincerely
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H2.10: (feature 23916)

TOP ACTIVATIONS
MAX = 0.804

ley
Tokenley
Feature activation+0.000
Cooper
Token Cooper
Feature activation+0.014
can
Token can
Feature activation+0.164
do
Token do
Feature activation+0.254
it
Token it
Feature activation+0.635
all
Token all
Feature activation+0.790
,
Token,
Feature activation+0.629
from
Token from
Feature activation+0.260
comedy
Token comedy
Feature activation+0.154
(
Token (
Feature activation+0.230
The
TokenThe
Feature activation+0.200
encourage
Token encourage
Feature activation+0.487
people
Token people
Feature activation+0.535
to
Token to
Feature activation+0.489
take
Token take
Feature activation+0.471
fewer
Token fewer
Feature activation+0.486
trips
Token trips
Feature activation+0.723
,
Token,
Feature activation+0.302
Hampshire
Token Hampshire
Feature activation+0.133
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Most
Token Most
Feature activation+0.000
items
Token items
Feature activation+0.156
could
Token could
Feature activation+0.308
have
Token have
Feature activation+0.393
been
Token been
Feature activation+0.483
used
Token used
Feature activation+0.514
to
Token to
Feature activation+0.696
make
Token make
Feature activation+0.573
an
Token an
Feature activation+0.582
improvised
Token improvised
Feature activation+0.381
explosive
Token explosive
Feature activation+0.488
device
Token device
Feature activation+0.602
IBM
Token IBM
Feature activation+0.239
made
Token made
Feature activation+0.418
decisions
Token decisions
Feature activation+0.454
so
Token so
Feature activation+0.395
slowly
Token slowly
Feature activation+0.633
that
Token that
Feature activation+0.691
,
Token,
Feature activation+0.311
when
Token when
Feature activation+0.156
tested
Token tested
Feature activation+0.030
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
income
Token income
Feature activation+0.407
taxes
Token taxes
Feature activation+0.479
for
Token for
Feature activation+0.665
at
Token at
Feature activation+0.676
least
Token least
Feature activation+0.540
two
Token two
Feature activation+0.690
years
Token years
Feature activation+0.646
in
Token in
Feature activation+0.585
the
Token the
Feature activation+0.446
late
Token late
Feature activation+0.242
1970
Token 1970
Feature activation+0.344
can
Token can
Feature activation+0.000
go
Token go
Feature activation+0.084
over
Token over
Feature activation+0.406
several
Token several
Feature activation+0.360
solutions
Token solutions
Feature activation+0.445
to
Token to
Feature activation+0.677
this
Token this
Feature activation+0.618
problem
Token problem
Feature activation+0.623
,
Token,
Feature activation+0.511
but
Token but
Feature activation+0.259
you
Token you
Feature activation+0.155
no
Token no
Feature activation+0.288
federal
Token federal
Feature activation+0.390
income
Token income
Feature activation+0.407
taxes
Token taxes
Feature activation+0.479
for
Token for
Feature activation+0.665
at
Token at
Feature activation+0.676
least
Token least
Feature activation+0.540
two
Token two
Feature activation+0.690
years
Token years
Feature activation+0.646
in
Token in
Feature activation+0.585
the
Token the
Feature activation+0.446
been
Token been
Feature activation+0.194
driving
Token driving
Feature activation+0.272
a
Token a
Feature activation+0.398
wedge
Token wedge
Feature activation+0.390
between
Token between
Feature activation+0.586
my
Token my
Feature activation+0.673
sister
Token sister
Feature activation+0.618
and
Token and
Feature activation+0.499
me
Token me
Feature activation+0.438
,
Token,
Feature activation+0.250
which
Token which
Feature activation+0.149
paid
Token paid
Feature activation+0.000
no
Token no
Feature activation+0.288
federal
Token federal
Feature activation+0.390
income
Token income
Feature activation+0.407
taxes
Token taxes
Feature activation+0.479
for
Token for
Feature activation+0.665
at
Token at
Feature activation+0.676
least
Token least
Feature activation+0.540
two
Token two
Feature activation+0.690
years
Token years
Feature activation+0.646
in
Token in
Feature activation+0.585
are
Token are
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.117
get
Token get
Feature activation+0.191
shipped
Token shipped
Feature activation+0.514
with
Token with
Feature activation+0.663
mistakes
Token mistakes
Feature activation+0.628
now
Token now
Feature activation+0.588
and
Token and
Feature activation+0.604
then
Token then
Feature activation+0.456
.
Token.
Feature activation+0.196
programmed
Token programmed
Feature activation+0.257
to
Token to
Feature activation+0.380
output
Token output
Feature activation+0.454
test
Token test
Feature activation+0.440
results
Token results
Feature activation+0.465
in
Token in
Feature activation+0.659
a
Token a
Feature activation+0.484
consistent
Token consistent
Feature activation+0.502
,
Token,
Feature activation+0.236
easily
Token easily
Feature activation+0.122
analyzed
Token analyzed
Feature activation+0.000
cafe
Token cafe
Feature activation+0.085
racer
Token racer
Feature activation+0.240
is
Token is
Feature activation+0.376
currently
Token currently
Feature activation+0.420
available
Token available
Feature activation+0.494
for
Token for
Feature activation+0.652
purchase
Token purchase
Feature activation+0.492
at
Token at
Feature activation+0.564
New
Token New
Feature activation+0.403
York
Token York
Feature activation+0.347
âĢ
TokenâĢ
Feature activation+0.315
taxes
Token taxes
Feature activation+0.479
for
Token for
Feature activation+0.665
at
Token at
Feature activation+0.676
least
Token least
Feature activation+0.540
two
Token two
Feature activation+0.690
years
Token years
Feature activation+0.646
in
Token in
Feature activation+0.585
the
Token the
Feature activation+0.446
late
Token late
Feature activation+0.242
1970
Token 1970
Feature activation+0.344
s
Tokens
Feature activation+0.391
of
Token of
Feature activation+0.000
Daniel
Token Daniel
Feature activation+0.011
is
Token is
Feature activation+0.155
divided
Token divided
Feature activation+0.338
between
Token between
Feature activation+0.605
the
Token the
Feature activation+0.645
court
Token court
Feature activation+0.354
tales
Token tales
Feature activation+0.423
of
Token of
Feature activation+0.490
chapters
Token chapters
Feature activation+0.522
1
Token 1
Feature activation+0.330
Blizzard
Token Blizzard
Feature activation+0.000
game
Token game
Feature activation+0.006
would
Token would
Feature activation+0.177
most
Token most
Feature activation+0.281
like
Token like
Feature activation+0.493
to
Token to
Feature activation+0.643
see
Token see
Feature activation+0.567
in
Token in
Feature activation+0.620
virtual
Token virtual
Feature activation+0.576
reality
Token reality
Feature activation+0.649
or
Token or
Feature activation+0.602
Neill
TokenNeill
Feature activation+0.101
is
Token is
Feature activation+0.173
a
Token a
Feature activation+0.124
main
Token main
Feature activation+0.231
character
Token character
Feature activation+0.397
in
Token in
Feature activation+0.642
the
Token the
Feature activation+0.544
TNT
Token TNT
Feature activation+0.407
movie
Token movie
Feature activation+0.456
Rough
Token Rough
Feature activation+0.473
Riders
Token Riders
Feature activation+0.467
nowadays
Token nowadays
Feature activation+0.025
consists
Token consists
Feature activation+0.298
of
Token of
Feature activation+0.569
wooden
Token wooden
Feature activation+0.516
cab
Token cab
Feature activation+0.525
ins
Tokenins
Feature activation+0.641
and
Token and
Feature activation+0.482
a
Token a
Feature activation+0.355
few
Token few
Feature activation+0.352
less
Token less
Feature activation+0.479
sturdy
Token sturdy
Feature activation+0.512
Brad
TokenBrad
Feature activation+0.000
ley
Tokenley
Feature activation+0.000
Cooper
Token Cooper
Feature activation+0.014
can
Token can
Feature activation+0.164
do
Token do
Feature activation+0.254
it
Token it
Feature activation+0.635
all
Token all
Feature activation+0.790
,
Token,
Feature activation+0.629
from
Token from
Feature activation+0.260
comedy
Token comedy
Feature activation+0.154
(
Token (
Feature activation+0.230
being
Token being
Feature activation+0.437
on
Token on
Feature activation+0.374
a
Token a
Feature activation+0.270
continual
Token continual
Feature activation+0.254
search
Token search
Feature activation+0.284
for
Token for
Feature activation+0.635
resp
Token resp
Feature activation+0.329
ite
Tokenite
Feature activation+0.618
.
Token.
Feature activation+0.182
The
Token The
Feature activation+0.000
laundry
Token laundry
Feature activation+0.000
tropical
Token tropical
Feature activation+0.000
storm
Token storm
Feature activation+0.000
warning
Token warning
Feature activation+0.136
has
Token has
Feature activation+0.395
since
Token since
Feature activation+0.406
been
Token been
Feature activation+0.633
lifted
Token lifted
Feature activation+0.578
,
Token,
Feature activation+0.323
many
Token many
Feature activation+0.028
parts
Token parts
Feature activation+0.044
of
Token of
Feature activation+0.123

Top DFA by src position
MAX = 0.227

17
Token17
Feature activation+0.025
Top resid features:
.
Token.
Feature activation+0.054
Top resid features:
Bradley
Token Bradley
Feature activation+0.014
Top resid features:
Cooper
Token Cooper
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.202
Top resid features:
Ċ
TokenĊ
Feature activation+0.203
Top resid features:
Brad
TokenBrad
Feature activation-0.013
Top resid features:
ley
Tokenley
Feature activation+0.004
Top resid features:
Cooper
Token Cooper
Feature activation+0.014
Top resid features:
can
Token can
Feature activation+0.044
Top resid features:
do
Token do
Feature activation+0.096
Top resid features:
may
Token may
Feature activation+0.026
Top resid features:
encourage
Token encourage
Feature activation+0.048
Top resid features:
people
Token people
Feature activation-0.014
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
take
Token take
Feature activation-0.063
Top resid features:
fewer
Token fewer
Feature activation+0.227
Top resid features:
trips
Token trips
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Hampshire
Token Hampshire
Feature activation+0.000
Top resid features:
said
Token said
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:
wooden
Token wooden
Feature activation-0.002
Top resid features:
matches
Token matches
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
Ċ
TokenĊ
Feature activation+0.158
Top resid features:
Ċ
TokenĊ
Feature activation+0.169
Top resid features:
Investigators
TokenInvestigators
Feature activation+0.000
Top resid features:
concluded
Token concluded
Feature activation+0.045
Top resid features:
these
Token these
Feature activation+0.068
Top resid features:
items
Token items
Feature activation+0.018
Top resid features:
could
Token could
Feature activation+0.051
Top resid features:
1980
Token 1980
Feature activation+0.001
Top resid features:
.[
Token.[
Feature activation+0.021
Top resid features:
14
Token14
Feature activation+0.009
Top resid features:
]
Token]
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.126
Top resid features:
Ċ
TokenĊ
Feature activation+0.138
Top resid features:
Another
TokenAnother
Feature activation+0.097
Top resid features:
observer
Token observer
Feature activation+0.025
Top resid features:
claimed
Token claimed
Feature activation+0.063
Top resid features:
that
Token that
Feature activation+0.072
Top resid features:
IBM
Token IBM
Feature activation+0.042
Top resid features:
ABC
TokenABC
Feature activation+0.000
Top resid features:
News
Token News
Feature activation+0.001
Top resid features:
reported
Token reported
Feature activation+0.011
Top resid features:
:
Token:
Feature activation+0.053
Top resid features:
Ċ
TokenĊ
Feature activation+0.155
Top resid features:
Ċ
TokenĊ
Feature activation+0.160
Top resid features:
Donald
TokenDonald
Feature activation+0.024
Top resid features:
Trump
Token Trump
Feature activation+0.032
Top resid features:
paid
Token paid
Feature activation+0.046
Top resid features:
no
Token no
Feature activation+0.025
Top resid features:
federal
Token federal
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.079
Top resid features:
Ċ
TokenĊ
Feature activation+0.082
Top resid features:
The
TokenThe
Feature activation+0.056
Top resid features:
solution
Token solution
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.164
Top resid features:
Ċ
TokenĊ
Feature activation+0.151
Top resid features:
You
TokenYou
Feature activation+0.086
Top resid features:
can
Token can
Feature activation+0.044
Top resid features:
go
Token go
Feature activation+0.067
Top resid features:
over
Token over
Feature activation+0.062
Top resid features:
ABC
TokenABC
Feature activation+0.003
Top resid features:
News
Token News
Feature activation+0.000
Top resid features:
reported
Token reported
Feature activation+0.013
Top resid features:
:
Token:
Feature activation+0.052
Top resid features:
Ċ
TokenĊ
Feature activation+0.136
Top resid features:
Ċ
TokenĊ
Feature activation+0.137
Top resid features:
Donald
TokenDonald
Feature activation+0.023
Top resid features:
Trump
Token Trump
Feature activation+0.036
Top resid features:
paid
Token paid
Feature activation+0.060
Top resid features:
no
Token no
Feature activation+0.037
Top resid features:
federal
Token federal
Feature activation+0.017
Top resid features:
Kim
Token Kim
Feature activation+0.007
Top resid features:
as
Token as
Feature activation+0.017
Top resid features:
jealousy
Token jealousy
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.062
Top resid features:
Ċ
TokenĊ
Feature activation+0.173
Top resid features:
Ċ
TokenĊ
Feature activation+0.173
Top resid features:
âĢ
TokenâĢ
Feature activation+0.043
Top resid features:
ľ
Tokenľ
Feature activation+0.005
Top resid features:
Br
TokenBr
Feature activation+0.004
Top resid features:
andi
Tokenandi
Feature activation+0.006
Top resid features:
clearly
Token clearly
Feature activation+0.033
Top resid features:
paid
Token paid
Feature activation+0.051
Top resid features:
no
Token no
Feature activation+0.070
Top resid features:
federal
Token federal
Feature activation+0.010
Top resid features:
income
Token income
Feature activation-0.007
Top resid features:
taxes
Token taxes
Feature activation-0.060
Top resid features:
for
Token for
Feature activation+0.156
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
least
Token least
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
years
Token years
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
apologize
Token apologize
Feature activation-0.005
Top resid features:
for
Token for
Feature activation+0.016
Top resid features:
this
Token this
Feature activation+0.005
Top resid features:
inconvenience
Token inconvenience
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.033
Top resid features:
Ċ
TokenĊ
Feature activation+0.221
Top resid features:
Ċ
TokenĊ
Feature activation+0.205
Top resid features:
Products
TokenProducts
Feature activation+0.038
Top resid features:
are
Token are
Feature activation+0.057
Top resid features:
going
Token going
Feature activation+0.033
Top resid features:
to
Token to
Feature activation+0.084
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.089
Top resid features:
Ċ
TokenĊ
Feature activation+0.084
Top resid features:
Test
TokenTest
Feature activation+0.006
Top resid features:
Value
Token Value
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.153
Top resid features:
Ċ
TokenĊ
Feature activation+0.150
Top resid features:
The
TokenThe
Feature activation+0.115
Top resid features:
computer
Token computer
Feature activation+0.014
Top resid features:
can
Token can
Feature activation+0.055
Top resid features:
be
Token be
Feature activation+0.043
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
smaller
Token smaller
Feature activation-0.003
Top resid features:
side
Token side
Feature activation-0.002
Top resid features:
covers
Token covers
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.035
Top resid features:
Ċ
TokenĊ
Feature activation+0.144
Top resid features:
Ċ
TokenĊ
Feature activation+0.143
Top resid features:
This
TokenThis
Feature activation+0.051
Top resid features:
âĢ
Token âĢ
Feature activation+0.020
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
71
Token71
Feature activation+0.019
Top resid features:
ABC
TokenABC
Feature activation+0.001
Top resid features:
News
Token News
Feature activation+0.001
Top resid features:
reported
Token reported
Feature activation+0.010
Top resid features:
:
Token:
Feature activation+0.050
Top resid features:
Ċ
TokenĊ
Feature activation+0.134
Top resid features:
Ċ
TokenĊ
Feature activation+0.139
Top resid features:
Donald
TokenDonald
Feature activation+0.022
Top resid features:
Trump
Token Trump
Feature activation+0.027
Top resid features:
paid
Token paid
Feature activation+0.045
Top resid features:
no
Token no
Feature activation+0.021
Top resid features:
federal
Token federal
Feature activation+0.022
Top resid features:
).
Token).
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.084
Top resid features:
Ċ
TokenĊ
Feature activation+0.082
Top resid features:
Div
TokenDiv
Feature activation+0.002
Top resid features:
isions
Tokenisions
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.128
Top resid features:
Ċ
TokenĊ
Feature activation+0.128
Top resid features:
The
TokenThe
Feature activation+0.086
Top resid features:
Book
Token Book
Feature activation+0.029
Top resid features:
of
Token of
Feature activation+0.049
Top resid features:
Daniel
Token Daniel
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.077
Top resid features:
Watch
TokenWatch
Feature activation+0.012
Top resid features:
:
Token:
Feature activation+0.020
Top resid features:
Overwatch
Token Overwatch
Feature activation+0.022
Top resid features:
gameplay
Token gameplay
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.159
Top resid features:
Ċ
TokenĊ
Feature activation+0.159
Top resid features:
Which
TokenWhich
Feature activation+0.069
Top resid features:
Blizzard
Token Blizzard
Feature activation-0.009
Top resid features:
game
Token game
Feature activation+0.038
Top resid features:
would
Token would
Feature activation+0.018
Top resid features:
Neill
TokenNeill
Feature activation+0.006
Top resid features:
is
Token is
Feature activation+0.080
Top resid features:
a
Token a
Feature activation-0.022
Top resid features:
main
Token main
Feature activation-0.009
Top resid features:
character
Token character
Feature activation-0.038
Top resid features:
in
Token in
Feature activation+0.153
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
TNT
Token TNT
Feature activation+0.000
Top resid features:
movie
Token movie
Feature activation+0.000
Top resid features:
Rough
Token Rough
Feature activation+0.000
Top resid features:
Riders
Token Riders
Feature activation+0.000
Top resid features:
ono
Tokenono
Feature activation-0.003
Top resid features:
today
Token today
Feature activation+0.020
Top resid features:
[
Token [
Feature activation+0.017
Top resid features:
edit
Token edit
Feature activation+0.003
Top resid features:
]
Token ]
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.156
Top resid features:
Ċ
TokenĊ
Feature activation+0.151
Top resid features:
The
TokenThe
Feature activation+0.081
Top resid features:
village
Token village
Feature activation+0.023
Top resid features:
nowadays
Token nowadays
Feature activation+0.075
Top resid features:
consists
Token consists
Feature activation+0.106
Top resid features:
Ċ
TokenĊ
Feature activation+0.110
Top resid features:
17
Token17
Feature activation+0.028
Top resid features:
.
Token.
Feature activation+0.051
Top resid features:
Bradley
Token Bradley
Feature activation+0.011
Top resid features:
Cooper
Token Cooper
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.189
Top resid features:
Ċ
TokenĊ
Feature activation+0.174
Top resid features:
Brad
TokenBrad
Feature activation-0.025
Top resid features:
ley
Tokenley
Feature activation-0.007
Top resid features:
Cooper
Token Cooper
Feature activation-0.026
Top resid features:
can
Token can
Feature activation+0.029
Top resid features:
looking
Token looking
Feature activation-0.001
Top resid features:
for
Token for
Feature activation+0.006
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
treatment
Token treatment
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.046
Top resid features:
Ċ
TokenĊ
Feature activation+0.156
Top resid features:
Ċ
TokenĊ
Feature activation+0.141
Top resid features:
Living
TokenLiving
Feature activation+0.003
Top resid features:
with
Token with
Feature activation+0.039
Top resid features:
cluster
Token cluster
Feature activation+0.014
Top resid features:
headaches
Token headaches
Feature activation+0.027
Top resid features:
To
Token To
Feature activation+0.005
Top resid features:
Ever
Token Ever
Feature activation+0.005
Top resid features:
Hit
Token Hit
Feature activation-0.002
Top resid features:
America
Token America
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.207
Top resid features:
Ċ
TokenĊ
Feature activation+0.211
Top resid features:
Though
TokenThough
Feature activation+0.032
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
tropical
Token tropical
Feature activation+0.001
Top resid features:
storm
Token storm
Feature activation+0.037
Top resid features:
warning
Token warning
Feature activation+0.034
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.03

Head 2: 0.04

Head 3: 0.06

Head 4: 0.03

Head 5: 0.07

Head 6: 0.12

Head 7: 0.13

Head 8: 0.05

Head 9: 0.06

Head 10: 0.25

Head 11: 0.11

Positive logits

Westminster0.68

Cardiff0.67

Cornwall0.61

Fighters0.59

Dover0.59

Gaddafi0.57

Founders0.56

Genetics0.55

Doctors0.55

Buckingham0.54

Picture0.54

cohol0.53

Pesh0.53

Converted0.53

Windsor0.52

Prin0.52

Kings0.52

antioxid0.52

Dragons0.52

Churchill0.52

Negative logits

!).-1.21

.).-1.16

)).-1.14

)."-1.13

?).-1.13

!".-1.09

]."-1.07

%).-1.05

).[-1.02

))))-0.96

).-0.94

").-0.94

'."-0.92

.'"-0.91

)!-0.91

?".-0.89

]).-0.89

.�-0.87

}.-0.85

.-0.83

INTERVAL 0.723 - 0.804
CONTAINS 0.002%

encourage
Token encourage
Feature activation+0.487
people
Token people
Feature activation+0.535
to
Token to
Feature activation+0.489
take
Token take
Feature activation+0.471
fewer
Token fewer
Feature activation+0.486
trips
Token trips
Feature activation+0.723
,
Token,
Feature activation+0.302
Hampshire
Token Hampshire
Feature activation+0.133
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Most
Token Most
Feature activation+0.000
ley
Tokenley
Feature activation+0.000
Cooper
Token Cooper
Feature activation+0.014
can
Token can
Feature activation+0.164
do
Token do
Feature activation+0.254
it
Token it
Feature activation+0.635
all
Token all
Feature activation+0.790
,
Token,
Feature activation+0.629
from
Token from
Feature activation+0.260
comedy
Token comedy
Feature activation+0.154
(
Token (
Feature activation+0.230
The
TokenThe
Feature activation+0.200

INTERVAL 0.643 - 0.723
CONTAINS 0.006%

of
Token of
Feature activation+0.000
Daniel
Token Daniel
Feature activation+0.011
is
Token is
Feature activation+0.155
divided
Token divided
Feature activation+0.338
between
Token between
Feature activation+0.605
the
Token the
Feature activation+0.645
court
Token court
Feature activation+0.354
tales
Token tales
Feature activation+0.423
of
Token of
Feature activation+0.490
chapters
Token chapters
Feature activation+0.522
1
Token 1
Feature activation+0.330
cafe
Token cafe
Feature activation+0.085
racer
Token racer
Feature activation+0.240
is
Token is
Feature activation+0.376
currently
Token currently
Feature activation+0.420
available
Token available
Feature activation+0.494
for
Token for
Feature activation+0.652
purchase
Token purchase
Feature activation+0.492
at
Token at
Feature activation+0.564
New
Token New
Feature activation+0.403
York
Token York
Feature activation+0.347
âĢ
TokenâĢ
Feature activation+0.315
IBM
Token IBM
Feature activation+0.239
made
Token made
Feature activation+0.418
decisions
Token decisions
Feature activation+0.454
so
Token so
Feature activation+0.395
slowly
Token slowly
Feature activation+0.633
that
Token that
Feature activation+0.691
,
Token,
Feature activation+0.311
when
Token when
Feature activation+0.156
tested
Token tested
Feature activation+0.030
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
can
Token can
Feature activation+0.000
go
Token go
Feature activation+0.084
over
Token over
Feature activation+0.406
several
Token several
Feature activation+0.360
solutions
Token solutions
Feature activation+0.445
to
Token to
Feature activation+0.677
this
Token this
Feature activation+0.618
problem
Token problem
Feature activation+0.623
,
Token,
Feature activation+0.511
but
Token but
Feature activation+0.259
you
Token you
Feature activation+0.155
paid
Token paid
Feature activation+0.000
no
Token no
Feature activation+0.288
federal
Token federal
Feature activation+0.390
income
Token income
Feature activation+0.407
taxes
Token taxes
Feature activation+0.479
for
Token for
Feature activation+0.665
at
Token at
Feature activation+0.676
least
Token least
Feature activation+0.540
two
Token two
Feature activation+0.690
years
Token years
Feature activation+0.646
in
Token in
Feature activation+0.585

INTERVAL 0.563 - 0.643
CONTAINS 0.020%

the
Token the
Feature activation+0.000
borough
Token borough
Feature activation+0.000
had
Token had
Feature activation+0.119
tried
Token tried
Feature activation+0.298
closing
Token closing
Feature activation+0.514
only
Token only
Feature activation+0.618
a
Token a
Feature activation+0.721
handful
Token handful
Feature activation+0.620
of
Token of
Feature activation+0.599
streets
Token streets
Feature activation+0.544
in
Token in
Feature activation+0.515
Blizzard
Token Blizzard
Feature activation+0.000
game
Token game
Feature activation+0.006
would
Token would
Feature activation+0.177
most
Token most
Feature activation+0.281
like
Token like
Feature activation+0.493
to
Token to
Feature activation+0.643
see
Token see
Feature activation+0.567
in
Token in
Feature activation+0.620
virtual
Token virtual
Feature activation+0.576
reality
Token reality
Feature activation+0.649
or
Token or
Feature activation+0.602
the
Token the
Feature activation+0.000
sixth
Token sixth
Feature activation+0.000
installment
Token installment
Feature activation+0.087
of
Token of
Feature activation+0.333
Resident
Token Resident
Feature activation+0.317
Evil
Token Evil
Feature activation+0.568
franchise
Token franchise
Feature activation+0.428
entitled
Token entitled
Feature activation+0.599
Resident
Token Resident
Feature activation+0.603
Evil
Token Evil
Feature activation+0.674
:
Token:
Feature activation+0.469
won
Token won
Feature activation+0.133
small
Token small
Feature activation+0.309
raises
Token raises
Feature activation+0.532
at
Token at
Feature activation+0.499
various
Token various
Feature activation+0.439
franchises
Token franchises
Feature activation+0.564
of
Token of
Feature activation+0.428
Little
Token Little
Feature activation+0.302
Ca
Token Ca
Feature activation+0.209
es
Tokenes
Feature activation+0.282
ars
Tokenars
Feature activation+0.206
s
Tokens
Feature activation+0.191
armed
Token armed
Feature activation+0.149
with
Token with
Feature activation+0.448
testing
Token testing
Feature activation+0.501
kits
Token kits
Feature activation+0.482
took
Token took
Feature activation+0.596
the
Token the
Feature activation+0.487
fish
Token fish
Feature activation+0.384
samples
Token samples
Feature activation+0.381
,
Token,
Feature activation+0.280
and
Token and
Feature activation+0.165

INTERVAL 0.482 - 0.563
CONTAINS 0.042%

look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
this
Token this
Feature activation+0.060
frog
Token frog
Feature activation+0.151
resting
Token resting
Feature activation+0.235
in
Token in
Feature activation+0.516
his
Token his
Feature activation+0.465
log
Token log
Feature activation+0.335
,
Token,
Feature activation+0.254
I
Token I
Feature activation+0.176
try
Token try
Feature activation+0.109
her
Token her
Feature activation+0.343
mom
Token mom
Feature activation+0.293
what
Token what
Feature activation+0.380
was
Token was
Feature activation+0.352
going
Token going
Feature activation+0.400
on
Token on
Feature activation+0.557
inside
Token inside
Feature activation+0.381
,
Token,
Feature activation+0.303
Jen
Token Jen
Feature activation+0.000
Morrow
Token Morrow
Feature activation+0.000
was
Token was
Feature activation+0.000
may
Token may
Feature activation+0.452
encourage
Token encourage
Feature activation+0.487
people
Token people
Feature activation+0.535
to
Token to
Feature activation+0.489
take
Token take
Feature activation+0.471
fewer
Token fewer
Feature activation+0.486
trips
Token trips
Feature activation+0.723
,
Token,
Feature activation+0.302
Hampshire
Token Hampshire
Feature activation+0.133
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.167
study
Token study
Feature activation+0.075
believed
Token believed
Feature activation+0.221
themselves
Token themselves
Feature activation+0.369
to
Token to
Feature activation+0.586
be
Token be
Feature activation+0.520
"
Token "
Feature activation+0.429
elect
Tokenelect
Feature activation+0.381
ros
Tokenros
Feature activation+0.244
ensitive
Tokenensitive
Feature activation+0.229
",
Token",
Feature activation+0.198
year
Token year
Feature activation+0.252
documenting
Token documenting
Feature activation+0.299
the
Token the
Feature activation+0.450
issues
Token issues
Feature activation+0.338
facing
Token facing
Feature activation+0.506
black
Token black
Feature activation+0.500
students
Token students
Feature activation+0.493
in
Token in
Feature activation+0.428
Oakland
Token Oakland
Feature activation+0.332
,
Token,
Feature activation+0.285
and
Token and
Feature activation+0.131

INTERVAL 0.402 - 0.482
CONTAINS 0.085%

-
Token-
Feature activation+0.011
en
Tokenen
Feature activation+0.000
's
Token's
Feature activation+0.080
classic
Token classic
Feature activation+0.175
Journey
Token Journey
Feature activation+0.288
to
Token to
Feature activation+0.403
the
Token the
Feature activation+0.264
West
Token West
Feature activation+0.000
tales
Token tales
Feature activation+0.129
--
Token --
Feature activation+0.140
Stephen
Token Stephen
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
incredibly
Token incredibly
Feature activation+0.000
vigilant
Token vigilant
Feature activation+0.092
due
Token due
Feature activation+0.159
to
Token to
Feature activation+0.428
lack
Token lack
Feature activation+0.241
of
Token of
Feature activation+0.212
criminals
Token criminals
Feature activation+0.083
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
consists
Token consists
Feature activation+0.298
of
Token of
Feature activation+0.569
wooden
Token wooden
Feature activation+0.516
cab
Token cab
Feature activation+0.525
ins
Tokenins
Feature activation+0.641
and
Token and
Feature activation+0.482
a
Token a
Feature activation+0.355
few
Token few
Feature activation+0.352
less
Token less
Feature activation+0.479
sturdy
Token sturdy
Feature activation+0.512
buildings
Token buildings
Feature activation+0.567
We
TokenWe
Feature activation+0.000
've
Token've
Feature activation+0.000
enjoyed
Token enjoyed
Feature activation+0.000
ourselves
Token ourselves
Feature activation+0.124
thanks
Token thanks
Feature activation+0.222
to
Token to
Feature activation+0.470
him
Token him
Feature activation+0.251
and
Token and
Feature activation+0.212
now
Token now
Feature activation+0.035
we
Token we
Feature activation+0.109
suffer
Token suffer
Feature activation+0.162
a
Token a
Feature activation+0.000
video
Token video
Feature activation+0.000
statement
Token statement
Feature activation+0.000
released
Token released
Feature activation+0.088
around
Token around
Feature activation+0.348
midnight
Token midnight
Feature activation+0.449
Friday
Token Friday
Feature activation+0.433
,
Token,
Feature activation+0.130
vowed
Token vowed
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.321 - 0.402
CONTAINS 0.159%

soldiers
Token soldiers
Feature activation+0.550
as
Token as
Feature activation+0.420
the
Token the
Feature activation+0.376
attack
Token attack
Feature activation+0.250
was
Token was
Feature activation+0.412
being
Token being
Feature activation+0.354
filmed
Token filmed
Feature activation+0.396
,
Token,
Feature activation+0.250
reports
Token reports
Feature activation+0.000
Israeli
Token Israeli
Feature activation+0.000
news
Token news
Feature activation+0.000
he
Token he
Feature activation+0.394
or
Token or
Feature activation+0.271
she
Token she
Feature activation+0.296
is
Token is
Feature activation+0.194
responsible
Token responsible
Feature activation+0.193
for
Token for
Feature activation+0.327
pollution
Token pollution
Feature activation+0.245
that
Token that
Feature activation+0.147
seriously
Token seriously
Feature activation+0.072
inj
Token inj
Feature activation+0.060
ures
Tokenures
Feature activation+0.109
Ċ
TokenĊ
Feature activation+0.097
The
TokenThe
Feature activation+0.083
billionaire
Token billionaire
Feature activation+0.084
businessman
Token businessman
Feature activation+0.174
has
Token has
Feature activation+0.423
voc
Token voc
Feature activation+0.357
ifer
Tokenifer
Feature activation+0.354
ously
Tokenously
Feature activation+0.406
defended
Token defended
Feature activation+0.609
Second
Token Second
Feature activation+0.670
Amendment
Token Amendment
Feature activation+0.655
Django
Token Django
Feature activation+0.000
is
Token is
Feature activation+0.226
still
Token still
Feature activation+0.181
not
Token not
Feature activation+0.288
aware
Token aware
Feature activation+0.205
of
Token of
Feature activation+0.370
it
Token it
Feature activation+0.369
,
Token,
Feature activation+0.206
you
Token you
Feature activation+0.010
will
Token will
Feature activation+0.000
need
Token need
Feature activation+0.000
the
Token the
Feature activation+0.000
Sh
Token Sh
Feature activation+0.000
ura
Tokenura
Feature activation+0.038
Council
Token Council
Feature activation+0.000
presented
Token presented
Feature activation+0.222
a
Token a
Feature activation+0.365
recommendation
Token recommendation
Feature activation+0.286
that
Token that
Feature activation+0.374
women
Token women
Feature activation+0.181
be
Token be
Feature activation+0.228
given
Token given
Feature activation+0.256

INTERVAL 0.241 - 0.321
CONTAINS 0.265%

says
Token says
Feature activation+0.000
his
Token his
Feature activation+0.000
agency
Token agency
Feature activation+0.000
will
Token will
Feature activation+0.135
do
Token do
Feature activation+0.082
a
Token a
Feature activation+0.299
"
Token "
Feature activation+0.189
com
Tokencom
Feature activation+0.101
pre
Tokenpre
Feature activation+0.002
hens
Tokenhens
Feature activation+0.000
ive
Tokenive
Feature activation+0.000
One
TokenOne
Feature activation+0.000
way
Token way
Feature activation+0.000
our
Token our
Feature activation+0.000
new
Token new
Feature activation+0.000
environment
Token environment
Feature activation+0.029
has
Token has
Feature activation+0.285
shaped
Token shaped
Feature activation+0.318
modern
Token modern
Feature activation+0.532
evolution
Token evolution
Feature activation+0.465
is
Token is
Feature activation+0.655
in
Token in
Feature activation+0.593
They
TokenThey
Feature activation+0.000
have
Token have
Feature activation+0.000
broken
Token broken
Feature activation+0.000
away
Token away
Feature activation+0.075
from
Token from
Feature activation+0.129
representing
Token representing
Feature activation+0.256
the
Token the
Feature activation+0.256
American
Token American
Feature activation+0.189
people
Token people
Feature activation+0.174
and
Token and
Feature activation+0.179
now
Token now
Feature activation+0.110
for
Token for
Feature activation+0.070
Cyber
Token Cyber
Feature activation+0.000
Intelligence
Token Intelligence
Feature activation+0.017
Europe
Token Europe
Feature activation+0.015
based
Token based
Feature activation+0.123
out
Token out
Feature activation+0.250
of
Token of
Feature activation+0.144
the
Token the
Feature activation+0.108
Frankfurt
Token Frankfurt
Feature activation+0.000
Cons
Token Cons
Feature activation+0.000
ulate
Tokenulate
Feature activation+0.000
signed
Token signed
Feature activation+0.000
a
Token a
Feature activation+0.000
5
Token 5
Feature activation+0.000
year
Token year
Feature activation+0.036
contract
Token contract
Feature activation+0.057
with
Token with
Feature activation+0.283
the
Token the
Feature activation+0.342
Washington
Token Washington
Feature activation+0.196
Redskins
Token Redskins
Feature activation+0.107
in
Token in
Feature activation+0.226
January
Token January
Feature activation+0.220

INTERVAL 0.161 - 0.241
CONTAINS 0.405%

dismissed
Token dismissed
Feature activation+0.000
arguments
Token arguments
Feature activation+0.000
from
Token from
Feature activation+0.081
British
Token British
Feature activation+0.217
government
Token government
Feature activation+0.347
lawyers
Token lawyers
Feature activation+0.230
that
Token that
Feature activation+0.323
declaring
Token declaring
Feature activation+0.347
travelling
Token travelling
Feature activation+0.355
time
Token time
Feature activation+0.404
as
Token as
Feature activation+0.398
in
Token in
Feature activation+0.193
the
Token the
Feature activation+0.091
singles
Token singles
Feature activation+0.061
chart
Token chart
Feature activation+0.028
with
Token with
Feature activation+0.169
their
Token their
Feature activation+0.186
dance
Token dance
Feature activation+0.064
track
Token track
Feature activation+0.206
Cold
Token Cold
Feature activation+0.224
Water
Token Water
Feature activation+0.210
,
Token,
Feature activation+0.000
Yorker
Token Yorker
Feature activation+0.000
could
Token could
Feature activation+0.000
tell
Token tell
Feature activation+0.000
you
Token you
Feature activation+0.010
why
Token why
Feature activation+0.038
Ċ
TokenĊ
Feature activation+0.202
Ċ
TokenĊ
Feature activation+0.214
Reuters
TokenReuters
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Democrats
TokenDemocrats
Feature activation+0.000
was
Token was
Feature activation+0.000
introduced
Token introduced
Feature activation+0.000
to
Token to
Feature activation+0.091
counter
Token counter
Feature activation+0.020
an
Token an
Feature activation+0.189
alarming
Token alarming
Feature activation+0.167
drop
Token drop
Feature activation+0.241
-
Token-
Feature activation+0.367
off
Tokenoff
Feature activation+0.398
in
Token in
Feature activation+0.355
the
Token the
Feature activation+0.213
which
Token which
Feature activation+0.070
we
Token we
Feature activation+0.111
love
Token love
Feature activation+0.196
and
Token and
Feature activation+0.151
care
Token care
Feature activation+0.000
for
Token for
Feature activation+0.166
yet
Token yet
Feature activation+0.019
,
Token,
Feature activation+0.000
once
Token once
Feature activation+0.000
separated
Token separated
Feature activation+0.000
from
Token from
Feature activation+0.000

INTERVAL 0.080 - 0.161
CONTAINS 0.572%

ee
Tokenee
Feature activation+0.000
oral
Token oral
Feature activation+0.000
tradition
Token tradition
Feature activation+0.000
identifies
Token identifies
Feature activation+0.169
the
Token the
Feature activation+0.160
original
Token original
Feature activation+0.142
elabor
Token elabor
Feature activation+0.150
ation
Tokenation
Feature activation+0.061
of
Token of
Feature activation+0.231
k
Token k
Feature activation+0.000
as
Tokenas
Feature activation+0.043
our
Token our
Feature activation+0.000
solar
Token solar
Feature activation+0.000
system
Token system
Feature activation+0.098
into
Token into
Feature activation+0.240
the
Token the
Feature activation+0.257
universe
Token universe
Feature activation+0.161
seeking
Token seeking
Feature activation+0.406
only
Token only
Feature activation+0.481
peace
Token peace
Feature activation+0.615
and
Token and
Feature activation+0.464
friendship
Token friendship
Feature activation+0.235
D
TokenD
Feature activation+0.000
owntown
Tokenowntown
Feature activation+0.000
Partnership
Token Partnership
Feature activation+0.000
of
Token of
Feature activation+0.012
Baltimore
Token Baltimore
Feature activation+0.000
has
Token has
Feature activation+0.093
partnered
Token partnered
Feature activation+0.145
with
Token with
Feature activation+0.341
Parking
Token Parking
Feature activation+0.276
Panda
Token Panda
Feature activation+0.117
,
Token,
Feature activation+0.010
the
Token the
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
area
Token area
Feature activation+0.000
has
Token has
Feature activation+0.000
many
Token many
Feature activation+0.000
fields
Token fields
Feature activation+0.131
that
Token that
Feature activation+0.000
could
Token could
Feature activation+0.004
be
Token be
Feature activation+0.030
used
Token used
Feature activation+0.032
.
Token.
Feature activation+0.000
itself
Token itself
Feature activation+0.182
at
Token at
Feature activation+0.259
the
Token the
Feature activation+0.164
center
Token center
Feature activation+0.000
of
Token of
Feature activation+0.268
a
Token a
Feature activation+0.159
dispute
Token dispute
Feature activation+0.047
between
Token between
Feature activation+0.255
its
Token its
Feature activation+0.255
current
Token current
Feature activation+0.171
owner
Token owner
Feature activation+0.239

INTERVAL 0.000 - 0.080
CONTAINS 98.445%

Z
Token Z
Feature activation+0.000
ander
Tokenander
Feature activation+0.000
Clark
Token Clark
Feature activation+0.000
to
Token to
Feature activation+0.000
secure
Token secure
Feature activation+0.000
the
Token the
Feature activation+0.000
lead
Token lead
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
amendment
Token amendment
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
Senate
Token Senate
Feature activation+0.000
committee
Token committee
Feature activation+0.000
approved
Token approved
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
to
Token to
Feature activation+0.000
restore
Token restore
Feature activation+0.000
older
Token older
Feature activation+0.000
rest
Token rest
Feature activation+0.000
also
Token also
Feature activation+0.000
finding
Token finding
Feature activation+0.000
common
Token common
Feature activation+0.000
cause
Token cause
Feature activation+0.000
with
Token with
Feature activation+0.000
Moment
Token Moment
Feature activation+0.000
um
Tokenum
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.000
wing
Tokenwing
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
question
Token question
Feature activation+0.000
of
Token of
Feature activation+0.000
whether
Token whether
Feature activation+0.000
a
Token a
Feature activation+0.000
country
Token country
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
reached
Token reached
Feature activation+0.000
him
Token him
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
zoo
Token zoo
Feature activation+0.000
remained
Token remained
Feature activation+0.000
open
Token open
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
afternoon
Token afternoon
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 7 in H2.10: (feature 20127)

TOP ACTIVATIONS
MAX = 0.939

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.070
Officers
TokenOfficers
Feature activation+0.325
use
Token use
Feature activation+0.625
deadly
Token deadly
Feature activation+0.793
force
Token force
Feature activation+0.796
to
Token to
Feature activation+0.706
save
Token save
Feature activation+0.571
the
Token the
Feature activation+0.605
lives
Token lives
Feature activation+0.605
of
Token of
Feature activation+0.486
.
Token.
Feature activation+0.118
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.070
Officers
TokenOfficers
Feature activation+0.325
use
Token use
Feature activation+0.625
deadly
Token deadly
Feature activation+0.793
force
Token force
Feature activation+0.796
to
Token to
Feature activation+0.706
save
Token save
Feature activation+0.571
the
Token the
Feature activation+0.605
lives
Token lives
Feature activation+0.605
Ċ
TokenĊ
Feature activation+0.037
Eight
TokenEight
Feature activation+0.369
teams
Token teams
Feature activation+0.597
will
Token will
Feature activation+0.519
fight
Token fight
Feature activation+0.649
for
Token for
Feature activation+0.786
the
Token the
Feature activation+0.693
bulk
Token bulk
Feature activation+0.593
of
Token of
Feature activation+0.670
$
Token $
Feature activation+0.604
1
Token1
Feature activation+0.506
.
Token.
Feature activation+0.011
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.028
Now
TokenNow
Feature activation+0.269
here
Tokenhere
Feature activation+0.558
is
Token is
Feature activation+0.785
this
Token this
Feature activation+0.580
more
Token more
Feature activation+0.492
evident
Token evident
Feature activation+0.538
than
Token than
Feature activation+0.596
at
Token at
Feature activation+0.679
signs
Token signs
Feature activation+0.497
suggest
Token suggest
Feature activation+0.538
he
Token he
Feature activation+0.733
would
Token would
Feature activation+0.602
like
Token like
Feature activation+0.646
to
Token to
Feature activation+0.772
make
Token make
Feature activation+0.569
a
Token a
Feature activation+0.510
bid
Token bid
Feature activation+0.477
for
Token for
Feature activation+0.422
the
Token the
Feature activation+0.355
them
Token them
Feature activation+0.546
.
Token.
Feature activation+0.332
Black
Token Black
Feature activation+0.446
balls
Token balls
Feature activation+0.615
everywhere
Token everywhere
Feature activation+0.741
,
Token,
Feature activation+0.766
bouncing
Token bouncing
Feature activation+0.699
,
Token,
Feature activation+0.662
swinging
Token swinging
Feature activation+0.656
,
Token,
Feature activation+0.598
cav
Token cav
Feature activation+0.472
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Article
TokenArticle
Feature activation+0.212
continues
Token continues
Feature activation+0.532
below
Token below
Feature activation+0.644
...
Token ...
Feature activation+0.750
Ċ
TokenĊ
Feature activation+0.451
Ċ
TokenĊ
Feature activation+0.377
S
TokenS
Feature activation+0.288
ear
Tokenear
Feature activation+0.394
ls
Tokenls
Feature activation+0.605
of
Token of
Feature activation+0.523
them
Token them
Feature activation+0.546
.
Token.
Feature activation+0.332
Black
Token Black
Feature activation+0.446
balls
Token balls
Feature activation+0.615
everywhere
Token everywhere
Feature activation+0.741
,
Token,
Feature activation+0.766
bouncing
Token bouncing
Feature activation+0.699
,
Token,
Feature activation+0.662
swinging
Token swinging
Feature activation+0.656
,
Token,
Feature activation+0.598
sometimes
Token sometimes
Feature activation+0.447
an
Token an
Feature activation+0.541
event
Token event
Feature activation+0.481
or
Token or
Feature activation+0.671
theme
Token theme
Feature activation+0.608
or
Token or
Feature activation+0.739
setting
Token setting
Feature activation+0.646
is
Token is
Feature activation+0.619
so
Token so
Feature activation+0.564
attractive
Token attractive
Feature activation+0.443
,
Token,
Feature activation+0.473
Ancients
Token Ancients
Feature activation+0.206
harvested
Token harvested
Feature activation+0.482
these
Token these
Feature activation+0.600
re
Token re
Feature activation+0.556
eds
Tokeneds
Feature activation+0.604
and
Token and
Feature activation+0.737
created
Token created
Feature activation+0.663
a
Token a
Feature activation+0.593
med
Token med
Feature activation+0.389
itative
Tokenitative
Feature activation+0.477
and
Token and
Feature activation+0.494
knows
Token knows
Feature activation+0.165
.
Token.
Feature activation+0.295
Early
Token Early
Feature activation+0.270
signs
Token signs
Feature activation+0.497
suggest
Token suggest
Feature activation+0.538
he
Token he
Feature activation+0.733
would
Token would
Feature activation+0.602
like
Token like
Feature activation+0.646
to
Token to
Feature activation+0.772
make
Token make
Feature activation+0.569
a
Token a
Feature activation+0.510
imperative
Token imperative
Feature activation+0.591
.
Token.
Feature activation+0.403
Taliban
Token Taliban
Feature activation+0.409
amb
Token amb
Feature activation+0.628
ushes
Tokenushes
Feature activation+0.660
of
Token of
Feature activation+0.730
supply
Token supply
Feature activation+0.763
conv
Token conv
Feature activation+0.715
oys
Tokenoys
Feature activation+0.638
are
Token are
Feature activation+0.678
a
Token a
Feature activation+0.627
measure
Token measure
Feature activation+0.632
,
Token,
Feature activation+0.713
household
Token household
Feature activation+0.593
credit
Token credit
Feature activation+0.657
market
Token market
Feature activation+0.527
debt
Token debt
Feature activation+0.719
to
Token to
Feature activation+0.610
disposable
Token disposable
Feature activation+0.587
income
Token income
Feature activation+0.647
,
Token,
Feature activation+0.585
climbed
Token climbed
Feature activation+0.579
The
TokenThe
Feature activation+0.287
fires
Token fires
Feature activation+0.412
pose
Token pose
Feature activation+0.584
too
Token too
Feature activation+0.687
big
Token big
Feature activation+0.626
of
Token of
Feature activation+0.719
a
Token a
Feature activation+0.665
safety
Token safety
Feature activation+0.558
threat
Token threat
Feature activation+0.678
for
Token for
Feature activation+0.613
the
Token the
Feature activation+0.502
.
Token.
Feature activation+0.054
Ċ
TokenĊ
Feature activation+0.039
Ċ
TokenĊ
Feature activation+0.174
That
TokenThat
Feature activation+0.343
measure
Token measure
Feature activation+0.632
,
Token,
Feature activation+0.713
household
Token household
Feature activation+0.593
credit
Token credit
Feature activation+0.657
market
Token market
Feature activation+0.527
debt
Token debt
Feature activation+0.719
to
Token to
Feature activation+0.610
.
Token.
Feature activation+0.123
Ċ
TokenĊ
Feature activation+0.039
Ċ
TokenĊ
Feature activation+0.131
Ryan
TokenRyan
Feature activation+0.436
Day
Token Day
Feature activation+0.577
takes
Token takes
Feature activation+0.712
over
Token over
Feature activation+0.696
for
Token for
Feature activation+0.643
Urban
Token Urban
Feature activation+0.574
Meyer
Token Meyer
Feature activation+0.486
,
Token,
Feature activation+0.575
.
Token.
Feature activation+0.479
29
Token 29
Feature activation+0.535
,
Token,
Feature activation+0.498
West
Token West
Feature activation+0.408
past
Token past
Feature activation+0.496
ed
Tokened
Feature activation+0.710
the
Token the
Feature activation+0.570
text
Token text
Feature activation+0.497
of
Token of
Feature activation+0.740
a
Token a
Feature activation+0.594
story
Token story
Feature activation+0.515
Ċ
TokenĊ
Feature activation+0.070
Officers
TokenOfficers
Feature activation+0.325
use
Token use
Feature activation+0.625
deadly
Token deadly
Feature activation+0.793
force
Token force
Feature activation+0.796
to
Token to
Feature activation+0.706
save
Token save
Feature activation+0.571
the
Token the
Feature activation+0.605
lives
Token lives
Feature activation+0.605
of
Token of
Feature activation+0.486
others
Token others
Feature activation+0.418
headlines
Token headlines
Feature activation+0.576
for
Token for
Feature activation+0.525
listing
Token listing
Feature activation+0.571
her
Token her
Feature activation+0.614
white
Token white
Feature activation+0.589
2006
Token 2006
Feature activation+0.705
J
Token J
Feature activation+0.572
etta
Tokenetta
Feature activation+0.473
for
Token for
Feature activation+0.510
just
Token just
Feature activation+0.486
eight
Token eight
Feature activation+0.408
.
Token.
Feature activation+0.332
Black
Token Black
Feature activation+0.446
balls
Token balls
Feature activation+0.615
everywhere
Token everywhere
Feature activation+0.741
,
Token,
Feature activation+0.766
bouncing
Token bouncing
Feature activation+0.699
,
Token,
Feature activation+0.662
swinging
Token swinging
Feature activation+0.656
,
Token,
Feature activation+0.598
cav
Token cav
Feature activation+0.472
orting
Tokenorting
Feature activation+0.546

Top DFA by src position
MAX = 0.345

<|endoftext|>
Token<|endoftext|>
Feature activation+0.165
Top resid features:
attributes
Token attributes
Feature activation-0.012
Top resid features:
required
Token required
Feature activation+0.002
Top resid features:
for
Token for
Feature activation+0.001
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
prem
Token prem
Feature activation-0.002
Top resid features:
it
Token it
Feature activation+0.017
Top resid features:
barbaric
Token barbaric
Feature activation+0.043
Top resid features:
.
Token.
Feature activation+0.132
Top resid features:
Ċ
TokenĊ
Feature activation+0.147
Top resid features:
Ċ
TokenĊ
Feature activation+0.158
Top resid features:
Officers
TokenOfficers
Feature activation+0.161
Top resid features:
use
Token use
Feature activation+0.129
Top resid features:
deadly
Token deadly
Feature activation+0.084
Top resid features:
force
Token force
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
save
Token save
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.119
Top resid features:
Eight
TokenEight
Feature activation+0.081
Top resid features:
teams
Token teams
Feature activation+0.115
Top resid features:
will
Token will
Feature activation+0.117
Top resid features:
fight
Token fight
Feature activation+0.102
Top resid features:
for
Token for
Feature activation+0.172
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
bulk
Token bulk
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
1
Token1
Feature activation+0.000
Top resid features:
atoms
Token atoms
Feature activation+0.036
Top resid features:
.
Token.
Feature activation+0.096
Top resid features:
Ċ
TokenĊ
Feature activation+0.105
Top resid features:
Ċ
TokenĊ
Feature activation+0.116
Top resid features:
Now
TokenNow
Feature activation+0.148
Top resid features:
here
Tokenhere
Feature activation+0.298
Top resid features:
is
Token is
Feature activation+0.158
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
evident
Token evident
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
question
Token question
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.036
Top resid features:
only
Token only
Feature activation+0.010
Top resid features:
Gray
Token Gray
Feature activation+0.017
Top resid features:
knows
Token knows
Feature activation+0.067
Top resid features:
.
Token.
Feature activation+0.183
Top resid features:
Early
Token Early
Feature activation+0.092
Top resid features:
signs
Token signs
Feature activation+0.092
Top resid features:
suggest
Token suggest
Feature activation+0.104
Top resid features:
he
Token he
Feature activation+0.029
Top resid features:
would
Token would
Feature activation+0.111
Top resid features:
400
Token 400
Feature activation+0.074
Top resid features:
,
Token,
Feature activation+0.041
Top resid features:
000
Token000
Feature activation+0.088
Top resid features:
of
Token of
Feature activation+0.049
Top resid features:
them
Token them
Feature activation+0.075
Top resid features:
.
Token.
Feature activation+0.268
Top resid features:
Black
Token Black
Feature activation+0.094
Top resid features:
balls
Token balls
Feature activation+0.100
Top resid features:
everywhere
Token everywhere
Feature activation+0.066
Top resid features:
,
Token,
Feature activation+0.052
Top resid features:
bouncing
Token bouncing
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.114
Top resid features:
Ċ
TokenĊ
Feature activation+0.131
Top resid features:
Ċ
TokenĊ
Feature activation+0.152
Top resid features:
Article
TokenArticle
Feature activation+0.139
Top resid features:
continues
Token continues
Feature activation+0.147
Top resid features:
below
Token below
Feature activation+0.266
Top resid features:
...
Token ...
Feature activation+0.074
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
S
TokenS
Feature activation+0.000
Top resid features:
ear
Tokenear
Feature activation+0.000
Top resid features:
aw
Token aw
Feature activation+0.008
Top resid features:
ing
Tokening
Feature activation+0.005
Top resid features:
over
Token over
Feature activation+0.016
Top resid features:
black
Token black
Feature activation+0.014
Top resid features:
balls
Token balls
Feature activation+0.018
Top resid features:
.
Token.
Feature activation+0.153
Top resid features:
400
Token 400
Feature activation+0.088
Top resid features:
,
Token,
Feature activation+0.050
Top resid features:
000
Token000
Feature activation+0.121
Top resid features:
of
Token of
Feature activation+0.073
Top resid features:
them
Token them
Feature activation+0.077
Top resid features:
from
Token from
Feature activation+0.016
Top resid features:
something
Token something
Feature activation+0.021
Top resid features:
that
Token that
Feature activation+0.019
Top resid features:
needs
Token needs
Feature activation+0.031
Top resid features:
celebrating
Token celebrating
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.249
Top resid features:
But
Token But
Feature activation+0.116
Top resid features:
sometimes
Token sometimes
Feature activation+0.092
Top resid features:
an
Token an
Feature activation+0.002
Top resid features:
event
Token event
Feature activation+0.143
Top resid features:
or
Token or
Feature activation+0.112
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
sound
Token sound
Feature activation+0.013
Top resid features:
frequency
Token frequency
Feature activation+0.023
Top resid features:
when
Token when
Feature activation+0.033
Top resid features:
touched
Token touched
Feature activation+0.036
Top resid features:
.
Token.
Feature activation+0.345
Top resid features:
The
Token The
Feature activation+0.122
Top resid features:
Ancients
Token Ancients
Feature activation+0.094
Top resid features:
harvested
Token harvested
Feature activation+0.123
Top resid features:
these
Token these
Feature activation-0.022
Top resid features:
re
Token re
Feature activation+0.026
Top resid features:
Gray
Token Gray
Feature activation+0.031
Top resid features:
knows
Token knows
Feature activation+0.111
Top resid features:
.
Token.
Feature activation+0.159
Top resid features:
Early
Token Early
Feature activation+0.140
Top resid features:
signs
Token signs
Feature activation+0.107
Top resid features:
suggest
Token suggest
Feature activation+0.172
Top resid features:
he
Token he
Feature activation+0.127
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
like
Token like
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
imperative
Token imperative
Feature activation+0.072
Top resid features:
.
Token.
Feature activation+0.161
Top resid features:
Taliban
Token Taliban
Feature activation+0.147
Top resid features:
amb
Token amb
Feature activation+0.058
Top resid features:
ushes
Tokenushes
Feature activation+0.071
Top resid features:
of
Token of
Feature activation+0.182
Top resid features:
supply
Token supply
Feature activation+0.000
Top resid features:
conv
Token conv
Feature activation+0.000
Top resid features:
oys
Tokenoys
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
debt
Token debt
Feature activation+0.011
Top resid features:
has
Token has
Feature activation+0.028
Top resid features:
hit
Token hit
Feature activation+0.024
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
record
Token record
Feature activation+0.030
Top resid features:
.
Token.
Feature activation+0.179
Top resid features:
Ċ
TokenĊ
Feature activation+0.110
Top resid features:
Ċ
TokenĊ
Feature activation+0.111
Top resid features:
That
TokenThat
Feature activation+0.077
Top resid features:
measure
Token measure
Feature activation+0.098
Top resid features:
,
Token,
Feature activation-0.029
Top resid features:
The
TokenThe
Feature activation+0.076
Top resid features:
fires
Token fires
Feature activation+0.091
Top resid features:
pose
Token pose
Feature activation+0.150
Top resid features:
too
Token too
Feature activation+0.089
Top resid features:
big
Token big
Feature activation+0.011
Top resid features:
of
Token of
Feature activation+0.157
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
safety
Token safety
Feature activation+0.000
Top resid features:
threat
Token threat
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.183
Top resid features:
getting
Token getting
Feature activation-0.002
Top resid features:
an
Token an
Feature activation-0.003
Top resid features:
hash
Token hash
Feature activation+0.002
Top resid features:
table
Token table
Feature activation+0.001
Top resid features:
implementation
Token implementation
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.082
Top resid features:
Ċ
TokenĊ
Feature activation+0.150
Top resid features:
Ċ
TokenĊ
Feature activation+0.157
Top resid features:
Ryan
TokenRyan
Feature activation+0.106
Top resid features:
Day
Token Day
Feature activation+0.039
Top resid features:
takes
Token takes
Feature activation+0.247
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Urban
Token Urban
Feature activation+0.000
Top resid features:
Meyer
Token Meyer
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Dec
Token Dec
Feature activation+0.059
Top resid features:
.
Token.
Feature activation+0.056
Top resid features:
29
Token 29
Feature activation+0.086
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
West
Token West
Feature activation+0.015
Top resid features:
past
Token past
Feature activation+0.165
Top resid features:
ed
Tokened
Feature activation+0.133
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
text
Token text
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.114
Top resid features:
Officers
TokenOfficers
Feature activation+0.119
Top resid features:
use
Token use
Feature activation+0.126
Top resid features:
deadly
Token deadly
Feature activation+0.041
Top resid features:
force
Token force
Feature activation+0.036
Top resid features:
to
Token to
Feature activation+0.181
Top resid features:
save
Token save
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
lives
Token lives
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
others
Token others
Feature activation+0.000
Top resid features:
online
Token online
Feature activation+0.020
Top resid features:
currency
Token currency
Feature activation+0.017
Top resid features:
known
Token known
Feature activation+0.010
Top resid features:
as
Token as
Feature activation+0.013
Top resid features:
Bitcoin
Token Bitcoin
Feature activation+0.031
Top resid features:
.
Token.
Feature activation+0.142
Top resid features:
Ċ
TokenĊ
Feature activation+0.079
Top resid features:
Ċ
TokenĊ
Feature activation+0.081
Top resid features:
Sarah
TokenSarah
Feature activation+0.051
Top resid features:
Yu
Token Yu
Feature activation+0.030
Top resid features:
is
Token is
Feature activation+0.075
Top resid features:
400
Token 400
Feature activation+0.060
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
000
Token000
Feature activation+0.065
Top resid features:
of
Token of
Feature activation+0.057
Top resid features:
them
Token them
Feature activation+0.058
Top resid features:
.
Token.
Feature activation+0.256
Top resid features:
Black
Token Black
Feature activation+0.080
Top resid features:
balls
Token balls
Feature activation+0.090
Top resid features:
everywhere
Token everywhere
Feature activation+0.069
Top resid features:
,
Token,
Feature activation-0.060
Top resid features:
bouncing
Token bouncing
Feature activation+0.123
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.09

Head 2: 0.03

Head 3: 0.06

Head 4: 0.02

Head 5: 0.05

Head 6: 0.09

Head 7: 0.12

Head 8: 0.03

Head 9: 0.06

Head 10: 0.25

Head 11: 0.12

Positive logits

NX0.69

CBD0.67

BMC0.67

ORY0.66

2000000.66

Pastebin0.65

Nerd0.63

however0.63

Torrent0.63

FANTASY0.62

Freddie0.62

Potion0.61

TMZ0.61

Generic0.60

Majesty0.60

AVG0.60

Miranda0.59

AUD0.59

OND0.58

standalone0.57

Negative logits

anthrop-0.81

thia-0.81

UNCLASSIFIED-0.80

terness-0.76

ourge-0.75

bara-0.75

ignty-0.74

ieties-0.72

gregation-0.72

]).-0.71

pit-0.71

flies-0.71

iferation-0.69

Joined-0.69

owsky-0.68

folios-0.67

herent-0.67

wings-0.66

illas-0.66

ocaust-0.66

INTERVAL 0.845 - 0.939
CONTAINS 0.000%

INTERVAL 0.751 - 0.845
CONTAINS 0.002%

.
Token.
Feature activation+0.118
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.070
Officers
TokenOfficers
Feature activation+0.325
use
Token use
Feature activation+0.625
deadly
Token deadly
Feature activation+0.793
force
Token force
Feature activation+0.796
to
Token to
Feature activation+0.706
save
Token save
Feature activation+0.571
the
Token the
Feature activation+0.605
lives
Token lives
Feature activation+0.605
Ċ
TokenĊ
Feature activation+0.037
Eight
TokenEight
Feature activation+0.369
teams
Token teams
Feature activation+0.597
will
Token will
Feature activation+0.519
fight
Token fight
Feature activation+0.649
for
Token for
Feature activation+0.786
the
Token the
Feature activation+0.693
bulk
Token bulk
Feature activation+0.593
of
Token of
Feature activation+0.670
$
Token $
Feature activation+0.604
1
Token1
Feature activation+0.506
them
Token them
Feature activation+0.546
.
Token.
Feature activation+0.332
Black
Token Black
Feature activation+0.446
balls
Token balls
Feature activation+0.615
everywhere
Token everywhere
Feature activation+0.741
,
Token,
Feature activation+0.766
bouncing
Token bouncing
Feature activation+0.699
,
Token,
Feature activation+0.662
swinging
Token swinging
Feature activation+0.656
,
Token,
Feature activation+0.598
cav
Token cav
Feature activation+0.472
signs
Token signs
Feature activation+0.497
suggest
Token suggest
Feature activation+0.538
he
Token he
Feature activation+0.733
would
Token would
Feature activation+0.602
like
Token like
Feature activation+0.646
to
Token to
Feature activation+0.772
make
Token make
Feature activation+0.569
a
Token a
Feature activation+0.510
bid
Token bid
Feature activation+0.477
for
Token for
Feature activation+0.422
the
Token the
Feature activation+0.355
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.070
Officers
TokenOfficers
Feature activation+0.325
use
Token use
Feature activation+0.625
deadly
Token deadly
Feature activation+0.793
force
Token force
Feature activation+0.796
to
Token to
Feature activation+0.706
save
Token save
Feature activation+0.571
the
Token the
Feature activation+0.605
lives
Token lives
Feature activation+0.605
of
Token of
Feature activation+0.486

INTERVAL 0.658 - 0.751
CONTAINS 0.010%

Ċ
TokenĊ
Feature activation+0.070
Officers
TokenOfficers
Feature activation+0.325
use
Token use
Feature activation+0.625
deadly
Token deadly
Feature activation+0.793
force
Token force
Feature activation+0.796
to
Token to
Feature activation+0.706
save
Token save
Feature activation+0.571
the
Token the
Feature activation+0.605
lives
Token lives
Feature activation+0.605
of
Token of
Feature activation+0.486
others
Token others
Feature activation+0.418
,
Token,
Feature activation+0.436
organizations
Token organizations
Feature activation+0.411
such
Token such
Feature activation+0.537
as
Token as
Feature activation+0.690
incub
Token incub
Feature activation+0.687
ators
Tokenators
Feature activation+0.673
,
Token,
Feature activation+0.596
acceler
Token acceler
Feature activation+0.455
ators
Tokenators
Feature activation+0.417
,
Token,
Feature activation+0.437
and
Token and
Feature activation+0.439
a
Token a
Feature activation+0.316
result
Token result
Feature activation+0.365
,
Token,
Feature activation+0.436
organizations
Token organizations
Feature activation+0.411
such
Token such
Feature activation+0.537
as
Token as
Feature activation+0.690
incub
Token incub
Feature activation+0.687
ators
Tokenators
Feature activation+0.673
,
Token,
Feature activation+0.596
acceler
Token acceler
Feature activation+0.455
ators
Tokenators
Feature activation+0.417
Ċ
TokenĊ
Feature activation+0.039
Ċ
TokenĊ
Feature activation+0.131
Ryan
TokenRyan
Feature activation+0.436
Day
Token Day
Feature activation+0.577
takes
Token takes
Feature activation+0.712
over
Token over
Feature activation+0.696
for
Token for
Feature activation+0.643
Urban
Token Urban
Feature activation+0.574
Meyer
Token Meyer
Feature activation+0.486
,
Token,
Feature activation+0.575
with
Token with
Feature activation+0.474
is
Token is
Feature activation+0.288
the
Token the
Feature activation+0.351
founding
Token founding
Feature activation+0.528
executive
Token executive
Feature activation+0.508
director
Token director
Feature activation+0.569
of
Token of
Feature activation+0.676
the
Token the
Feature activation+0.538
Da
Token Da
Feature activation+0.371
V
TokenV
Feature activation+0.232
in
Tokenin
Feature activation+0.353
ci
Tokenci
Feature activation+0.187

INTERVAL 0.564 - 0.658
CONTAINS 0.032%

Whatever
Token Whatever
Feature activation+0.230
you
Token you
Feature activation+0.410
want
Token want
Feature activation+0.559
to
Token to
Feature activation+0.580
call
Token call
Feature activation+0.564
it
Token it
Feature activation+0.574
.
Token.
Feature activation+0.255
The
Token The
Feature activation+0.234
mil
Token mil
Feature activation+0.386
ieu
Tokenieu
Feature activation+0.552
I
Token I
Feature activation+0.489
.
Token.
Feature activation+0.035
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.085
neighbors
Token neighbors
Feature activation+0.401
know
Token know
Feature activation+0.603
.
Token.
Feature activation+0.499
Ċ
TokenĊ
Feature activation+0.216
Ċ
TokenĊ
Feature activation+0.255
âĢ
TokenâĢ
Feature activation+0.438
ľ
Tokenľ
Feature activation+0.573
Ċ
TokenĊ
Feature activation+0.000
Update
TokenUpdate
Feature activation+0.119
12
Token 12
Feature activation+0.560
/
Token/
Feature activation+0.526
31
Token31
Feature activation+0.565
/
Token/
Feature activation+0.654
14
Token14
Feature activation+0.635
Ċ
TokenĊ
Feature activation+0.395
Ċ
TokenĊ
Feature activation+0.310
The
TokenThe
Feature activation+0.221
hole
Token hole
Feature activation+0.318
umber
Tokenumber
Feature activation+0.488
produced
Token produced
Feature activation+0.599
a
Token a
Feature activation+0.589
commercial
Token commercial
Feature activation+0.531
showing
Token showing
Feature activation+0.596
a
Token a
Feature activation+0.582
Mexican
Token Mexican
Feature activation+0.496
mother
Token mother
Feature activation+0.505
and
Token and
Feature activation+0.492
daughter
Token daughter
Feature activation+0.432
heading
Token heading
Feature activation+0.405
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
History
TokenHistory
Feature activation+0.152
[
Token [
Feature activation+0.612
edit
Token edit
Feature activation+0.615
]
Token ]
Feature activation+0.603
Ċ
TokenĊ
Feature activation+0.604
Ċ
TokenĊ
Feature activation+0.594
Counter
TokenCounter
Feature activation+0.448
fe
Tokenfe
Feature activation+0.371

INTERVAL 0.470 - 0.564
CONTAINS 0.062%

.
Token.
Feature activation+0.167
Ċ
TokenĊ
Feature activation+0.013
Ċ
TokenĊ
Feature activation+0.115
Police
TokenPolice
Feature activation+0.228
said
Token said
Feature activation+0.542
six
Token six
Feature activation+0.528
cars
Token cars
Feature activation+0.439
were
Token were
Feature activation+0.523
broken
Token broken
Feature activation+0.439
into
Token into
Feature activation+0.345
last
Token last
Feature activation+0.410
Times
Token Times
Feature activation+0.464
of
Token of
Feature activation+0.589
San
Token San
Feature activation+0.484
Diego
Token Diego
Feature activation+0.444
's
Token's
Feature activation+0.604
growth
Token growth
Feature activation+0.498
Ċ
TokenĊ
Feature activation+0.135
Ċ
TokenĊ
Feature activation+0.085
with
Tokenwith
Feature activation+0.225
a
Token a
Feature activation+0.355
small
Token small
Feature activation+0.356
less
Token less
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.294
getting
Tokengetting
Feature activation+0.528
the
Token the
Feature activation+0.643
vag
Token vag
Feature activation+0.529
aries
Tokenaries
Feature activation+0.632
of
Token of
Feature activation+0.636
nine
Token nine
Feature activation+0.561
V
TokenV
Feature activation+0.012
atican
Tokenatican
Feature activation+0.140
Influence
Token Influence
Feature activation+0.230
on
Token on
Feature activation+0.510
Policies
Token Policies
Feature activation+0.403
of
Token of
Feature activation+0.515
Other
Token Other
Feature activation+0.541
Nations
Token Nations
Feature activation+0.583
Ċ
TokenĊ
Feature activation+0.190
Ċ
TokenĊ
Feature activation+0.137
V
TokenV
Feature activation+0.184
is
Token is
Feature activation+0.327
important
Token important
Feature activation+0.203
.
Token.
Feature activation+0.237
The
Token The
Feature activation+0.236
more
Token more
Feature activation+0.491
alternatives
Token alternatives
Feature activation+0.524
we
Token we
Feature activation+0.634
see
Token see
Feature activation+0.680
,
Token,
Feature activation+0.729
the
Token the
Feature activation+0.555
healthier
Token healthier
Feature activation+0.511

INTERVAL 0.376 - 0.470
CONTAINS 0.113%

The
TokenThe
Feature activation+0.077
Higgins
Token Higgins
Feature activation+0.155
family
Token family
Feature activation+0.271
,
Token,
Feature activation+0.354
five
Token five
Feature activation+0.392
kids
Token kids
Feature activation+0.419
between
Token between
Feature activation+0.259
the
Token the
Feature activation+0.388
ages
Token ages
Feature activation+0.239
of
Token of
Feature activation+0.296
14
Token 14
Feature activation+0.399
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mc
TokenMc
Feature activation+0.026
L
TokenL
Feature activation+0.123
aren
Tokenaren
Feature activation+0.160
âĢĵ
Token âĢĵ
Feature activation+0.385
Je
Token Je
Feature activation+0.232
z
Tokenz
Feature activation+0.232
son
Tokenson
Feature activation+0.221
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Brian
Token Brian
Feature activation+0.000
Flynn
Token Flynn
Feature activation+0.209
,
Token,
Feature activation+0.174
a
Token a
Feature activation+0.160
spokesman
Token spokesman
Feature activation+0.124
for
Token for
Feature activation+0.390
Euro
Token Euro
Feature activation+0.235
control
Tokencontrol
Feature activation+0.143
,
Token,
Feature activation+0.164
which
Token which
Feature activation+0.136
directs
Token directs
Feature activation+0.140
update
Token update
Feature activation+0.105
will
Token will
Feature activation+0.221
bump
Token bump
Feature activation+0.243
the
Token the
Feature activation+0.332
OS
Token OS
Feature activation+0.327
to
Token to
Feature activation+0.390
version
Token version
Feature activation+0.314
8
Token 8
Feature activation+0.396
.
Token.
Feature activation+0.255
10
Token10
Feature activation+0.363
.
Token.
Feature activation+0.385
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.154
ľ
Tokenľ
Feature activation+0.333
We
TokenWe
Feature activation+0.315
went
Token went
Feature activation+0.401
back
Token back
Feature activation+0.422
to
Token to
Feature activation+0.440
her
Token her
Feature activation+0.612
place
Token place
Feature activation+0.581
and
Token and
Feature activation+0.492

INTERVAL 0.282 - 0.376
CONTAINS 0.202%

recently
Token recently
Feature activation+0.134
started
Token started
Feature activation+0.273
an
Token an
Feature activation+0.197
online
Token online
Feature activation+0.127
petition
Token petition
Feature activation+0.252
to
Token to
Feature activation+0.323
ban
Token ban
Feature activation+0.209
smoking
Token smoking
Feature activation+0.220
on
Token on
Feature activation+0.071
Massachusetts
Token Massachusetts
Feature activation+0.025
Street
Token Street
Feature activation+0.000
,
Token,
Feature activation+0.275
the
Token the
Feature activation+0.186
two
Token two
Feature activation+0.119
companies
Token companies
Feature activation+0.213
update
Token update
Feature activation+0.281
and
Token and
Feature activation+0.327
expand
Token expand
Feature activation+0.315
their
Token their
Feature activation+0.349
2011
Token 2011
Feature activation+0.301
arrangement
Token arrangement
Feature activation+0.363
to
Token to
Feature activation+0.415
of
Token of
Feature activation+0.229
top
Token top
Feature activation+0.245
quality
Token quality
Feature activation+0.326
scholarship
Token scholarship
Feature activation+0.367
has
Token has
Feature activation+0.337
demonstrated
Token demonstrated
Feature activation+0.358
that
Token that
Feature activation+0.272
Islam
Token Islam
Feature activation+0.208
,
Token,
Feature activation+0.155
Muslim
Token Muslim
Feature activation+0.037
societies
Token societies
Feature activation+0.135
ke
Tokenke
Feature activation+0.234
described
Token described
Feature activation+0.252
Spotify
Token Spotify
Feature activation+0.253
as
Token as
Feature activation+0.367
"
Token "
Feature activation+0.400
the
Tokenthe
Feature activation+0.301
last
Token last
Feature activation+0.190
desperate
Token desperate
Feature activation+0.268
fart
Token fart
Feature activation+0.238
of
Token of
Feature activation+0.176
a
Token a
Feature activation+0.168
nurse
Token nurse
Feature activation+0.000
.
Token.
Feature activation+0.000
After
Token After
Feature activation+0.000
the
Token the
Feature activation+0.000
description
Token description
Feature activation+0.031
of
Token of
Feature activation+0.333
the
Token the
Feature activation+0.215
character
Token character
Feature activation+0.000
was
Token was
Feature activation+0.171
originally
Token originally
Feature activation+0.166
leaked
Token leaked
Feature activation+0.169

INTERVAL 0.188 - 0.282
CONTAINS 0.274%

-
Token-
Feature activation+0.000
2
Token2
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
doing
Token doing
Feature activation+0.144
so
Token so
Feature activation+0.247
,
Token,
Feature activation+0.109
they
Token they
Feature activation+0.138
extended
Token extended
Feature activation+0.168
their
Token their
Feature activation+0.223
hopes
Token hopes
Feature activation+0.211
even
Token even
Feature activation+0.012
atoms
Token atoms
Feature activation+0.022
.
Token.
Feature activation+0.011
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.028
Now
TokenNow
Feature activation+0.269
here
Tokenhere
Feature activation+0.558
is
Token is
Feature activation+0.785
this
Token this
Feature activation+0.580
more
Token more
Feature activation+0.492
evident
Token evident
Feature activation+0.538
ass
Tokenass
Feature activation+0.000
é
Tokené
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
someone
Token someone
Feature activation+0.037
who
Token who
Feature activation+0.224
is
Token is
Feature activation+0.234
now
Token now
Feature activation+0.270
a
Token a
Feature activation+0.213
secular
Token secular
Feature activation+0.160
progressive
Token progressive
Feature activation+0.207
pund
Token pund
Feature activation+0.163
it
Tokenit
Feature activation+0.204
,
Token,
Feature activation+0.271
former
Token former
Feature activation+0.217
state
Token state
Feature activation+0.321
lawmaker
Token lawmaker
Feature activation+0.262
and
Token and
Feature activation+0.293
Flint
Token Flint
Feature activation+0.214
resident
Token resident
Feature activation+0.151
Bill
Token Bill
Feature activation+0.161
Ball
Token Ball
Feature activation+0.086
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Four
TokenFour
Feature activation+0.000
major
Token major
Feature activation+0.076
tobacco
Token tobacco
Feature activation+0.140
companies
Token companies
Feature activation+0.217
challenged
Token challenged
Feature activation+0.255
the
Token the
Feature activation+0.198
new
Token new
Feature activation+0.155
rules
Token rules
Feature activation+0.166
on
Token on
Feature activation+0.223

INTERVAL 0.094 - 0.188
CONTAINS 0.360%

and
Token and
Feature activation+0.000
steel
Token steel
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+0.104
fact
Token fact
Feature activation+0.163
,
Token,
Feature activation+0.348
the
Token the
Feature activation+0.244
Al
Token Al
Feature activation+0.270
ask
Tokenask
Feature activation+0.292
,
Token,
Feature activation+0.233
ther
Token ther
Feature activation+0.130
mos
Tokenmos
Feature activation+0.000
ets
Tokenets
Feature activation+0.032
represent
Token represent
Feature activation+0.170
an
Token an
Feature activation+0.128
engineer
Token engineer
Feature activation+0.055
's
Token's
Feature activation+0.086
point
Token point
Feature activation+0.175
of
Token of
Feature activation+0.240
no
Token no
Feature activation+0.194
Sun
Token Sun
Feature activation+0.203
ing
Tokening
Feature activation+0.240
,
Token,
Feature activation+0.245
an
Token an
Feature activation+0.168
electronics
Token electronics
Feature activation+0.119
retailer
Token retailer
Feature activation+0.113
that
Token that
Feature activation+0.223
owns
Token owns
Feature activation+0.251
65
Token 65
Feature activation+0.216
national
Token national
Feature activation+0.174
and
Token and
Feature activation+0.201
88
Token88
Feature activation+0.000
events
Token events
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
When
TokenWhen
Feature activation+0.119
not
Token not
Feature activation+0.411
possible
Token possible
Feature activation+0.363
for
Token for
Feature activation+0.360
a
Token a
Feature activation+0.338
Foundation
Token Foundation
Feature activation+0.378
major
Token major
Feature activation+0.076
tobacco
Token tobacco
Feature activation+0.140
companies
Token companies
Feature activation+0.217
challenged
Token challenged
Feature activation+0.255
the
Token the
Feature activation+0.198
new
Token new
Feature activation+0.155
rules
Token rules
Feature activation+0.166
on
Token on
Feature activation+0.223
the
Token the
Feature activation+0.186
grounds
Token grounds
Feature activation+0.061
that
Token that
Feature activation+0.201

INTERVAL 0.000 - 0.094
CONTAINS 98.945%

be
Token be
Feature activation+0.000
put
Token put
Feature activation+0.000
into
Token into
Feature activation+0.000
production
Token production
Feature activation+0.000
,
Token,
Feature activation+0.000
sooner
Token sooner
Feature activation+0.000
than
Token than
Feature activation+0.000
later
Token later
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
asked
Token asked
Feature activation+0.000
about
Token about
Feature activation+0.000
Eric
Token Eric
Feature activation+0.000
Holder
Token Holder
Feature activation+0.000
's
Token's
Feature activation+0.000
position
Token position
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
whether
Token whether
Feature activation+0.000
it
Token it
Feature activation+0.000
applied
Token applied
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
proposals
Token proposals
Feature activation+0.000
were
Token were
Feature activation+0.000
made
Token made
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
culture
Token culture
Feature activation+0.000
minister
Token minister
Feature activation+0.000
Ed
Token Ed
Feature activation+0.000
meets
Token meets
Feature activation+0.000
the
Token the
Feature activation+0.000
offensive
Token offensive
Feature activation+0.000
guard
Token guard
Feature activation+0.000
(
Token (
Feature activation+0.000
solid
Tokensolid
Feature activation+0.000
red
Token red
Feature activation+0.000
arrow
Token arrow
Feature activation+0.000
above
Token above
Feature activation+0.000
),
Token),
Feature activation+0.000
it
Token it
Feature activation+0.000
that
Token that
Feature activation+0.000
Roger
Token Roger
Feature activation+0.000
is
Token is
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
know
Token know
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
what
Token what
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
in
Token in
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 8 in H2.10: (feature 17112)

TOP ACTIVATIONS
MAX = 1.113

,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.004
.
Token.
Feature activation+0.230
But
Token But
Feature activation+0.318
insisting
Token insisting
Feature activation+0.423
on
Token on
Feature activation+0.916
absolute
Token absolute
Feature activation+0.773
proof
Token proof
Feature activation+0.669
of
Token of
Feature activation+0.625
causation
Token causation
Feature activation+0.455
is
Token is
Feature activation+0.357
happened
Token happened
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.020
,
Token,
Feature activation+0.427
according
Token according
Feature activation+0.369
to
Token to
Feature activation+0.812
a
Token a
Feature activation+0.782
report
Token report
Feature activation+0.641
from
Token from
Feature activation+0.666
the
Token the
Feature activation+0.445
Fort
Token Fort
Feature activation+0.324
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
,
Token,
Feature activation+0.387
you
Token you
Feature activation+0.185
know
Token know
Feature activation+0.482
,
Token,
Feature activation+0.788
nothing
Token nothing
Feature activation+0.525
to
Token to
Feature activation+0.814
complain
Token complain
Feature activation+0.723
about
Token about
Feature activation+0.815
,
Token,
Feature activation+0.731
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.020
,
Token,
Feature activation+0.427
according
Token according
Feature activation+0.369
to
Token to
Feature activation+0.812
a
Token a
Feature activation+0.782
report
Token report
Feature activation+0.641
from
Token from
Feature activation+0.666
the
Token the
Feature activation+0.445
Fort
Token Fort
Feature activation+0.324
Worth
Token Worth
Feature activation+0.078
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.098
as
Token as
Feature activation+0.294
discovered
Token discovered
Feature activation+0.531
through
Token through
Feature activation+0.778
profiling
Token profiling
Feature activation+0.478
,
Token,
Feature activation+0.438
that
Token that
Feature activation+0.365
a
Token a
Feature activation+0.332
process
Token process
Feature activation+0.232
as
Token as
Feature activation+0.000
,
Token,
Feature activation+0.000
well
Token well
Feature activation+0.206
,
Token,
Feature activation+0.502
good
Token good
Feature activation+0.473
news
Token news
Feature activation+0.776
,
Token,
Feature activation+0.480
it
Token it
Feature activation+0.365
âĢ
TokenâĢ
Feature activation+0.419
Ļ
TokenĻ
Feature activation+0.402
d
Tokend
Feature activation+0.509
?
Token?
Feature activation+0.000
Something
Token Something
Feature activation+0.000
like
Token like
Feature activation+0.144
,
Token,
Feature activation+0.274
say
Token say
Feature activation+0.368
,
Token,
Feature activation+0.769
Friends
Token Friends
Feature activation+0.516
?
Token?
Feature activation+0.343
Ċ
TokenĊ
Feature activation+0.330
Ċ
TokenĊ
Feature activation+0.332
Thankfully
TokenThankfully
Feature activation+0.342
,
Token,
Feature activation+0.000
somehow
Token somehow
Feature activation+0.001
,
Token,
Feature activation+0.320
even
Token even
Feature activation+0.419
worse
Token worse
Feature activation+0.446
than
Token than
Feature activation+0.767
Labour
Token Labour
Feature activation+0.513
âĢ
TokenâĢ
Feature activation+0.347
Ļ
TokenĻ
Feature activation+0.224
s
Tokens
Feature activation+0.362
media
Token media
Feature activation+0.287
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.000
,
Token,
Feature activation+0.178
amid
Token amid
Feature activation+0.291
reports
Token reports
Feature activation+0.764
of
Token of
Feature activation+0.630
discrepancies
Token discrepancies
Feature activation+0.439
in
Token in
Feature activation+0.405
its
Token its
Feature activation+0.114
record
Token record
Feature activation+0.126
note
Token note
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.601
that
Token that
Feature activation+0.760
,
Token,
Feature activation+0.545
it
Token it
Feature activation+0.389
did
Token did
Feature activation+0.480
not
Token not
Feature activation+0.633
expect
Token expect
Feature activation+0.600
who
Token who
Feature activation+0.064
was
Token was
Feature activation+0.045
,
Token,
Feature activation+0.065
in
Token in
Feature activation+0.226
fact
Token fact
Feature activation+0.527
,
Token,
Feature activation+0.752
the
Token the
Feature activation+0.451
best
Token best
Feature activation+0.587
within
Token within
Feature activation+0.730
a
Token a
Feature activation+0.956
division
Token division
Feature activation+0.731
,
Token,
Feature activation+0.000
indeed
Token indeed
Feature activation+0.000
,
Token,
Feature activation+0.231
during
Token during
Feature activation+0.250
periodic
Token periodic
Feature activation+0.710
den
Token den
Feature activation+0.750
unci
Tokenunci
Feature activation+0.692
ations
Tokenations
Feature activation+0.645
of
Token of
Feature activation+0.482
the
Token the
Feature activation+0.226
risks
Token risks
Feature activation+0.120
worried
Token worried
Feature activation+0.568
(
Token (
Feature activation+0.331
pdf
Tokenpdf
Feature activation+0.143
)âĢĶ
Token)âĢĶ
Feature activation+0.261
about
Tokenabout
Feature activation+0.464
lightly
Token lightly
Feature activation+0.749
regulated
Token regulated
Feature activation+0.639
mortgage
Token mortgage
Feature activation+0.280
finance
Token finance
Feature activation+0.042
specialists
Token specialists
Feature activation+0.112
taking
Token taking
Feature activation+0.183
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
However
TokenHowever
Feature activation+0.000
,
Token,
Feature activation+0.000
juggling
Token juggling
Feature activation+0.277
with
Token with
Feature activation+0.729
the
Token the
Feature activation+0.530
stack
Token stack
Feature activation+0.215
seems
Token seems
Feature activation+0.287
to
Token to
Feature activation+0.188
me
Token me
Feature activation+0.059
be
Token be
Feature activation+0.000
acceptable
Token acceptable
Feature activation+0.000
,
Token,
Feature activation+0.000
preferably
Token preferably
Feature activation+0.063
without
Token without
Feature activation+0.634
a
Token a
Feature activation+0.729
levy
Token levy
Feature activation+0.418
on
Token on
Feature activation+0.352
deposits
Token deposits
Feature activation+0.164
below
Token below
Feature activation+0.067
âĤ¬
Token âĤ¬
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.026
-
Token -
Feature activation+0.516
a
Token a
Feature activation+0.299
part
Token part
Feature activation+0.447
of
Token of
Feature activation+0.716
me
Token me
Feature activation+0.609
wished
Token wished
Feature activation+0.547
that
Token that
Feature activation+0.533
Sud
Token Sud
Feature activation+0.050
a
Tokena
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000
,
Token,
Feature activation+0.000
indeed
Token indeed
Feature activation+0.000
,
Token,
Feature activation+0.231
during
Token during
Feature activation+0.250
periodic
Token periodic
Feature activation+0.710
den
Token den
Feature activation+0.750
unci
Tokenunci
Feature activation+0.692
ations
Tokenations
Feature activation+0.645
of
Token of
Feature activation+0.482
the
Token the
Feature activation+0.226
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
example
Token example
Feature activation+0.000
,
Token,
Feature activation+0.349
imagine
Token imagine
Feature activation+0.504
I
Token I
Feature activation+0.706
said
Token said
Feature activation+0.508
to
Token to
Feature activation+0.639
a
Token a
Feature activation+0.510
friend
Token friend
Feature activation+0.340
âĢ
Token âĢ
Feature activation+0.069
eastern
Token eastern
Feature activation+0.000
halves
Token halves
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.047
duel
Token duel
Feature activation+0.377
ing
Tokening
Feature activation+0.700
capitals
Token capitals
Feature activation+0.431
at
Token at
Feature activation+0.245
Rome
Token Rome
Feature activation+0.198
and
Token and
Feature activation+0.030
Constantinople
Token Constantinople
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Finally
TokenFinally
Feature activation+0.000
,
Token,
Feature activation+0.018
after
Token after
Feature activation+0.063
long
Token long
Feature activation+0.567
time
Token time
Feature activation+0.700
and
Token and
Feature activation+0.365
a
Token a
Feature activation+0.195
lot
Token lot
Feature activation+0.261
of
Token of
Feature activation+0.229
tries
Token tries
Feature activation+0.235

Top DFA by src position
MAX = 0.731

alone
Token alone
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.079
Top resid features:
then
Token then
Feature activation+0.084
Top resid features:
.
Token.
Feature activation+0.129
Top resid features:
But
Token But
Feature activation+0.219
Top resid features:
insisting
Token insisting
Feature activation+0.297
Top resid features:
on
Token on
Feature activation+0.233
Top resid features:
absolute
Token absolute
Feature activation+0.000
Top resid features:
proof
Token proof
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
causation
Token causation
Feature activation+0.000
Top resid features:
happened
Token happened
Feature activation+0.060
Top resid features:
,
Token,
Feature activation+0.168
Top resid features:
however
Token however
Feature activation+0.209
Top resid features:
,
Token,
Feature activation+0.198
Top resid features:
according
Token according
Feature activation+0.151
Top resid features:
to
Token to
Feature activation+0.267
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
report
Token report
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Fort
Token Fort
Feature activation+0.000
Top resid features:
exchanged
Token exchanged
Feature activation+0.027
Top resid features:
,
Token,
Feature activation+0.056
Top resid features:
but
Token but
Feature activation+0.172
Top resid features:
,
Token,
Feature activation+0.106
Top resid features:
you
Token you
Feature activation+0.038
Top resid features:
know
Token know
Feature activation+0.394
Top resid features:
,
Token,
Feature activation+0.173
Top resid features:
nothing
Token nothing
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
complain
Token complain
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
happened
Token happened
Feature activation+0.065
Top resid features:
,
Token,
Feature activation+0.147
Top resid features:
however
Token however
Feature activation+0.166
Top resid features:
,
Token,
Feature activation+0.165
Top resid features:
according
Token according
Feature activation+0.195
Top resid features:
to
Token to
Feature activation+0.277
Top resid features:
a
Token a
Feature activation+0.028
Top resid features:
report
Token report
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Fort
Token Fort
Feature activation+0.000
Top resid features:
process
Token process
Feature activation-0.017
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
If
Token If
Feature activation+0.024
Top resid features:
you
Token you
Feature activation+0.010
Top resid features:
know
Token know
Feature activation+0.078
Top resid features:
,
Token,
Feature activation+0.318
Top resid features:
as
Token as
Feature activation+0.143
Top resid features:
discovered
Token discovered
Feature activation+0.255
Top resid features:
through
Token through
Feature activation+0.182
Top resid features:
profiling
Token profiling
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
certainly
Token certainly
Feature activation+0.015
Top resid features:
comes
Token comes
Feature activation+0.026
Top resid features:
as
Token as
Feature activation+0.047
Top resid features:
,
Token,
Feature activation+0.187
Top resid features:
well
Token well
Feature activation+0.123
Top resid features:
,
Token,
Feature activation+0.282
Top resid features:
good
Token good
Feature activation+0.267
Top resid features:
news
Token news
Feature activation+0.050
Top resid features:
,
Token,
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:
simpler
Token simpler
Feature activation+0.018
Top resid features:
?
Token?
Feature activation+0.075
Top resid features:
Something
Token Something
Feature activation-0.034
Top resid features:
like
Token like
Feature activation+0.140
Top resid features:
,
Token,
Feature activation+0.160
Top resid features:
say
Token say
Feature activation+0.374
Top resid features:
,
Token,
Feature activation+0.205
Top resid features:
Friends
Token Friends
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:
Yet
TokenYet
Feature activation+0.063
Top resid features:
,
Token,
Feature activation+0.115
Top resid features:
somehow
Token somehow
Feature activation+0.103
Top resid features:
,
Token,
Feature activation+0.173
Top resid features:
even
Token even
Feature activation+0.119
Top resid features:
worse
Token worse
Feature activation+0.257
Top resid features:
than
Token than
Feature activation+0.246
Top resid features:
Labour
Token Labour
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:
s
Tokens
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.017
Top resid features:
it
Token it
Feature activation-0.031
Top resid features:
,
Token,
Feature activation+0.064
Top resid features:
though
Token though
Feature activation+0.169
Top resid features:
,
Token,
Feature activation+0.122
Top resid features:
amid
Token amid
Feature activation+0.731
Top resid features:
reports
Token reports
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
discrepancies
Token discrepancies
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
research
Token research
Feature activation+0.029
Top resid features:
note
Token note
Feature activation+0.018
Top resid features:
that
Token that
Feature activation+0.027
Top resid features:
,
Token,
Feature activation+0.168
Top resid features:
because
Token because
Feature activation+0.350
Top resid features:
of
Token of
Feature activation+0.281
Top resid features:
that
Token that
Feature activation+0.108
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
did
Token did
Feature activation+0.000
Top resid features:
determine
Token determine
Feature activation+0.058
Top resid features:
who
Token who
Feature activation+0.008
Top resid features:
was
Token was
Feature activation+0.037
Top resid features:
,
Token,
Feature activation+0.140
Top resid features:
in
Token in
Feature activation+0.193
Top resid features:
fact
Token fact
Feature activation+0.261
Top resid features:
,
Token,
Feature activation+0.175
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
best
Token best
Feature activation+0.000
Top resid features:
within
Token within
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
only
Token only
Feature activation+0.020
Top resid features:
mentioned
Token mentioned
Feature activation+0.043
Top resid features:
,
Token,
Feature activation+0.113
Top resid features:
indeed
Token indeed
Feature activation+0.157
Top resid features:
,
Token,
Feature activation+0.129
Top resid features:
during
Token during
Feature activation+0.320
Top resid features:
periodic
Token periodic
Feature activation+0.258
Top resid features:
den
Token den
Feature activation+0.041
Top resid features:
unci
Tokenunci
Feature activation+0.000
Top resid features:
ations
Tokenations
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
too
Token too
Feature activation+0.017
Top resid features:
worried
Token worried
Feature activation+0.067
Top resid features:
(
Token (
Feature activation+0.027
Top resid features:
pdf
Tokenpdf
Feature activation+0.046
Top resid features:
)âĢĶ
Token)âĢĶ
Feature activation+0.263
Top resid features:
about
Tokenabout
Feature activation+0.344
Top resid features:
lightly
Token lightly
Feature activation+0.087
Top resid features:
regulated
Token regulated
Feature activation+0.000
Top resid features:
mortgage
Token mortgage
Feature activation+0.000
Top resid features:
finance
Token finance
Feature activation+0.000
Top resid features:
specialists
Token specialists
Feature activation+0.000
Top resid features:
bash
Token bash
Feature activation-0.019
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
However
TokenHowever
Feature activation+0.090
Top resid features:
,
Token,
Feature activation+0.303
Top resid features:
juggling
Token juggling
Feature activation+0.262
Top resid features:
with
Token with
Feature activation+0.249
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
stack
Token stack
Feature activation+0.000
Top resid features:
seems
Token seems
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.031
Top resid features:
be
Token be
Feature activation+0.018
Top resid features:
acceptable
Token acceptable
Feature activation-0.026
Top resid features:
,
Token,
Feature activation+0.147
Top resid features:
preferably
Token preferably
Feature activation+0.238
Top resid features:
without
Token without
Feature activation+0.509
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
levy
Token levy
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
deposits
Token deposits
Feature activation+0.000
Top resid features:
below
Token below
Feature activation+0.000
Top resid features:
something
Token something
Feature activation+0.051
Top resid features:
absent
Token absent
Feature activation+0.037
Top resid features:
there
Token there
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.123
Top resid features:
though
Token though
Feature activation+0.149
Top resid features:
-
Token -
Feature activation+0.229
Top resid features:
a
Token a
Feature activation+0.036
Top resid features:
part
Token part
Feature activation+0.209
Top resid features:
of
Token of
Feature activation+0.149
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
wished
Token wished
Feature activation+0.000
Top resid features:
only
Token only
Feature activation+0.029
Top resid features:
mentioned
Token mentioned
Feature activation+0.041
Top resid features:
,
Token,
Feature activation+0.136
Top resid features:
indeed
Token indeed
Feature activation+0.115
Top resid features:
,
Token,
Feature activation+0.149
Top resid features:
during
Token during
Feature activation+0.442
Top resid features:
periodic
Token periodic
Feature activation+0.131
Top resid features:
den
Token den
Feature activation+0.000
Top resid features:
unci
Tokenunci
Feature activation+0.000
Top resid features:
ations
Tokenations
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
speak
Token speak
Feature activation+0.022
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
For
Token For
Feature activation+0.055
Top resid features:
example
Token example
Feature activation+0.119
Top resid features:
,
Token,
Feature activation+0.264
Top resid features:
imagine
Token imagine
Feature activation+0.554
Top resid features:
I
Token I
Feature activation-0.031
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
friend
Token friend
Feature activation+0.000
Top resid features:
western
Token western
Feature activation-0.003
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
eastern
Token eastern
Feature activation-0.015
Top resid features:
halves
Token halves
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.210
Top resid features:
with
Token with
Feature activation+0.349
Top resid features:
duel
Token duel
Feature activation+0.232
Top resid features:
ing
Tokening
Feature activation+0.045
Top resid features:
capitals
Token capitals
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
Rome
Token Rome
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.046
Top resid features:
âĢ
Token âĢ
Feature activation+0.047
Top resid features:
ľ
Tokenľ
Feature activation+0.011
Top resid features:
Finally
TokenFinally
Feature activation+0.039
Top resid features:
,
Token,
Feature activation+0.179
Top resid features:
after
Token after
Feature activation+0.397
Top resid features:
long
Token long
Feature activation+0.134
Top resid features:
time
Token time
Feature activation+0.081
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
lot
Token lot
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.03

Head 2: 0.05

Head 3: 0.06

Head 4: 0.03

Head 5: 0.09

Head 6: 0.06

Head 7: 0.11

Head 8: 0.06

Head 9: 0.09

Head 10: 0.25

Head 11: 0.11

Positive logits

pmwiki0.95

hindsight0.93

caveats0.78

adject0.78

unanim0.75

acknowled0.74

pse0.73

causation0.72

obser0.71

nuance0.70

constants0.70

saturation0.70

specificity0.69

totality0.69

hiber0.68

inconsistency0.67

positives0.67

itudes0.66

disclaim0.66

syll0.65

Negative logits

rotein-0.68

vernight-0.66

iverpool-0.65

assador-0.64

razil-0.61

anwhile-0.61

LM-0.61

onga-0.61

Hussein-0.60

Sabha-0.60

christ-0.60

LTD-0.60

Leaders-0.59

Hass-0.58

him-0.58

allows-0.58

agos-0.58

also-0.58

Amen-0.57

Zh-0.57

INTERVAL 1.002 - 1.113
CONTAINS 0.000%

INTERVAL 0.891 - 1.002
CONTAINS 0.000%

,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.004
.
Token.
Feature activation+0.230
But
Token But
Feature activation+0.318
insisting
Token insisting
Feature activation+0.423
on
Token on
Feature activation+0.916
absolute
Token absolute
Feature activation+0.773
proof
Token proof
Feature activation+0.669
of
Token of
Feature activation+0.625
causation
Token causation
Feature activation+0.455
is
Token is
Feature activation+0.357

INTERVAL 0.779 - 0.891
CONTAINS 0.002%

,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
,
Token,
Feature activation+0.387
you
Token you
Feature activation+0.185
know
Token know
Feature activation+0.482
,
Token,
Feature activation+0.788
nothing
Token nothing
Feature activation+0.525
to
Token to
Feature activation+0.814
complain
Token complain
Feature activation+0.723
about
Token about
Feature activation+0.815
,
Token,
Feature activation+0.731
happened
Token happened
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.020
,
Token,
Feature activation+0.427
according
Token according
Feature activation+0.369
to
Token to
Feature activation+0.812
a
Token a
Feature activation+0.782
report
Token report
Feature activation+0.641
from
Token from
Feature activation+0.666
the
Token the
Feature activation+0.445
Fort
Token Fort
Feature activation+0.324
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.020
,
Token,
Feature activation+0.427
according
Token according
Feature activation+0.369
to
Token to
Feature activation+0.812
a
Token a
Feature activation+0.782
report
Token report
Feature activation+0.641
from
Token from
Feature activation+0.666
the
Token the
Feature activation+0.445
Fort
Token Fort
Feature activation+0.324
Worth
Token Worth
Feature activation+0.078

INTERVAL 0.668 - 0.779
CONTAINS 0.009%

,
Token,
Feature activation+0.000
indeed
Token indeed
Feature activation+0.000
,
Token,
Feature activation+0.231
during
Token during
Feature activation+0.250
periodic
Token periodic
Feature activation+0.710
den
Token den
Feature activation+0.750
unci
Tokenunci
Feature activation+0.692
ations
Tokenations
Feature activation+0.645
of
Token of
Feature activation+0.482
the
Token the
Feature activation+0.226
risks
Token risks
Feature activation+0.120
as
Token as
Feature activation+0.000
,
Token,
Feature activation+0.000
well
Token well
Feature activation+0.206
,
Token,
Feature activation+0.502
good
Token good
Feature activation+0.473
news
Token news
Feature activation+0.776
,
Token,
Feature activation+0.480
it
Token it
Feature activation+0.365
âĢ
TokenâĢ
Feature activation+0.419
Ļ
TokenĻ
Feature activation+0.402
d
Tokend
Feature activation+0.509
As
Token As
Feature activation+0.000
will
Token will
Feature activation+0.000
,
Token,
Feature activation+0.000
more
Token more
Feature activation+0.159
importantly
Token importantly
Feature activation+0.456
,
Token,
Feature activation+0.695
how
Token how
Feature activation+0.564
it
Token it
Feature activation+0.674
gets
Token gets
Feature activation+0.617
there
Token there
Feature activation+0.568
.
Token.
Feature activation+0.334
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
However
TokenHowever
Feature activation+0.000
,
Token,
Feature activation+0.000
juggling
Token juggling
Feature activation+0.277
with
Token with
Feature activation+0.729
the
Token the
Feature activation+0.530
stack
Token stack
Feature activation+0.215
seems
Token seems
Feature activation+0.287
to
Token to
Feature activation+0.188
me
Token me
Feature activation+0.059
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.098
as
Token as
Feature activation+0.294
discovered
Token discovered
Feature activation+0.531
through
Token through
Feature activation+0.778
profiling
Token profiling
Feature activation+0.478
,
Token,
Feature activation+0.438
that
Token that
Feature activation+0.365
a
Token a
Feature activation+0.332
process
Token process
Feature activation+0.232

INTERVAL 0.557 - 0.668
CONTAINS 0.024%

,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.114
,
Token,
Feature activation+0.355
cases
Token cases
Feature activation+0.286
of
Token of
Feature activation+0.612
complete
Token complete
Feature activation+0.563
treatment
Token treatment
Feature activation+0.424
failure
Token failure
Feature activation+0.308
have
Token have
Feature activation+0.274
been
Token been
Feature activation+0.276
reported
Token reported
Feature activation+0.219
,
Token,
Feature activation+0.000
too
Token too
Feature activation+0.000
,
Token,
Feature activation+0.078
needs
Token needs
Feature activation+0.135
to
Token to
Feature activation+0.543
be
Token be
Feature activation+0.560
recognized
Token recognized
Feature activation+0.340
as
Token as
Feature activation+0.313
an
Token an
Feature activation+0.151
intentional
Token intentional
Feature activation+0.060
act
Token act
Feature activation+0.040
last
Token last
Feature activation+0.215
Thursday
Token Thursday
Feature activation+0.302
,
Token,
Feature activation+0.205
when
Token when
Feature activation+0.236
ol
Token ol
Feature activation+0.460
'
Token'
Feature activation+0.640
Shake
Token Shake
Feature activation+0.523
y
Tokeny
Feature activation+0.335
and
Token and
Feature activation+0.505
his
Token his
Feature activation+0.247
golden
Token golden
Feature activation+0.324
,
Token,
Feature activation+0.000
meanwhile
Token meanwhile
Feature activation+0.000
,
Token,
Feature activation+0.140
to
Token to
Feature activation+0.328
strengthen
Token strengthen
Feature activation+0.479
evidence
Token evidence
Feature activation+0.589
on
Token on
Feature activation+0.680
the
Token the
Feature activation+0.469
links
Token links
Feature activation+0.290
between
Token between
Feature activation+0.236
extreme
Token extreme
Feature activation+0.000
black
Token black
Feature activation+0.003
market
Token market
Feature activation+0.353
will
Token will
Feature activation+0.055
,
Token,
Feature activation+0.180
too
Token too
Feature activation+0.206
,
Token,
Feature activation+0.564
he
Token he
Feature activation+0.379
argues
Token argues
Feature activation+0.565
.
Token.
Feature activation+0.668
Ċ
TokenĊ
Feature activation+0.429
Ċ
TokenĊ
Feature activation+0.350

INTERVAL 0.445 - 0.557
CONTAINS 0.066%

So
TokenSo
Feature activation+0.000
,
Token,
Feature activation+0.000
welcome
Token welcome
Feature activation+0.050
.
Token.
Feature activation+0.195
Make
Token Make
Feature activation+0.164
yourself
Token yourself
Feature activation+0.519
comfortable
Token comfortable
Feature activation+0.469
.
Token.
Feature activation+0.060
And
Token And
Feature activation+0.088
by
Token by
Feature activation+0.467
that
Token that
Feature activation+0.589
something
Token something
Feature activation+0.000
absent
Token absent
Feature activation+0.000
there
Token there
Feature activation+0.000
,
Token,
Feature activation+0.000
though
Token though
Feature activation+0.026
-
Token -
Feature activation+0.516
a
Token a
Feature activation+0.299
part
Token part
Feature activation+0.447
of
Token of
Feature activation+0.716
me
Token me
Feature activation+0.609
wished
Token wished
Feature activation+0.547
In
TokenIn
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.107
although
Token although
Feature activation+0.096
some
Token some
Feature activation+0.338
of
Token of
Feature activation+0.509
the
Token the
Feature activation+0.371
humor
Token humor
Feature activation+0.100
was
Token was
Feature activation+0.197
welcome
Token welcome
Feature activation+0.204
,
Token,
Feature activation+0.243
determine
Token determine
Feature activation+0.000
who
Token who
Feature activation+0.064
was
Token was
Feature activation+0.045
,
Token,
Feature activation+0.065
in
Token in
Feature activation+0.226
fact
Token fact
Feature activation+0.527
,
Token,
Feature activation+0.752
the
Token the
Feature activation+0.451
best
Token best
Feature activation+0.587
within
Token within
Feature activation+0.730
a
Token a
Feature activation+0.956
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
after
Token after
Feature activation+0.139
reading
Token reading
Feature activation+0.490
their
Token their
Feature activation+0.272
Facebook
Token Facebook
Feature activation+0.084
statement
Token statement
Feature activation+0.006
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000

INTERVAL 0.334 - 0.445
CONTAINS 0.157%

,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.093
followed
Token followed
Feature activation+0.321
by
Token by
Feature activation+0.478
a
Token a
Feature activation+0.352
900
Token 900
Feature activation+0.107
MW
Token MW
Feature activation+0.000
one
Token one
Feature activation+0.000
by
Token by
Feature activation+0.012
2016
Token 2016
Feature activation+0.000
a
Token a
Feature activation+0.000
result
Token result
Feature activation+0.000
,
Token,
Feature activation+0.121
organizations
Token organizations
Feature activation+0.050
such
Token such
Feature activation+0.081
as
Token as
Feature activation+0.411
incub
Token incub
Feature activation+0.468
ators
Tokenators
Feature activation+0.458
,
Token,
Feature activation+0.384
acceler
Token acceler
Feature activation+0.267
ators
Tokenators
Feature activation+0.375
Ed
Token Ed
Feature activation+0.000
Winter
Token Winter
Feature activation+0.107
,
Token,
Feature activation+0.027
assistant
Token assistant
Feature activation+0.000
chief
Token chief
Feature activation+0.025
of
Token of
Feature activation+0.341
the
Token the
Feature activation+0.187
Los
Token Los
Feature activation+0.000
Angeles
Token Angeles
Feature activation+0.000
coroner
Token coroner
Feature activation+0.027
âĢ
TokenâĢ
Feature activation+0.000
it
Token it
Feature activation+0.000
comes
Token comes
Feature activation+0.000
from
Token from
Feature activation+0.000
pin
Token pin
Feature activation+0.311
strip
Tokenstrip
Feature activation+0.392
ed
Tokened
Feature activation+0.439
apolog
Token apolog
Feature activation+0.202
ists
Tokenists
Feature activation+0.165
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
financial
Token financial
Feature activation+0.000
odd
Token odd
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
if
Token if
Feature activation+0.437
there
Token there
Feature activation+0.446
's
Token's
Feature activation+0.315
one
Token one
Feature activation+0.239
detail
Token detail
Feature activation+0.271
that
Token that
Feature activation+0.090

INTERVAL 0.223 - 0.334
CONTAINS 0.319%

.,
Token.,
Feature activation+0.000
1969
Token 1969
Feature activation+0.000
),
Token),
Feature activation+0.000
pp
Token pp
Feature activation+0.153
.
Token.
Feature activation+0.327
10
Token 10
Feature activation+0.278
65
Token65
Feature activation+0.215
-
Token-
Feature activation+0.211
10
Token10
Feature activation+0.186
71
Token71
Feature activation+0.101
Ċ
TokenĊ
Feature activation+0.000
biodiversity
Token biodiversity
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
addition
Token addition
Feature activation+0.055
to
Token to
Feature activation+0.269
being
Token being
Feature activation+0.323
influenced
Token influenced
Feature activation+0.278
by
Token by
Feature activation+0.307
grad
Token grad
Feature activation+0.198
ients
Tokenients
Feature activation+0.392
in
Token in
Feature activation+0.252
example
Token example
Feature activation+0.106
,
Token,
Feature activation+0.421
last
Token last
Feature activation+0.453
year
Token year
Feature activation+0.692
I
Token I
Feature activation+0.456
went
Token went
Feature activation+0.265
to
Token to
Feature activation+0.446
Cairo
Token Cairo
Feature activation+0.240
to
Token to
Feature activation+0.164
be
Token be
Feature activation+0.154
interviewed
Token interviewed
Feature activation+0.169
turns
Token turns
Feature activation+0.000
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.000
Of
Token Of
Feature activation+0.000
course
Token course
Feature activation+0.166
,
Token,
Feature activation+0.284
showing
Token showing
Feature activation+0.234
that
Token that
Feature activation+0.385
human
Token human
Feature activation+0.052
chromosome
Token chromosome
Feature activation+0.000
2
Token 2
Feature activation+0.000
priorities
Token priorities
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
little
Tokenlittle
Feature activation+0.000
more
Token more
Feature activation+0.253
than
Token than
Feature activation+0.299
ordering
Token ordering
Feature activation+0.241
a
Token a
Feature activation+0.113
list
Token list
Feature activation+0.000
of
Token of
Feature activation+0.000
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 0.111 - 0.223
CONTAINS 0.602%

tweets
Token tweets
Feature activation+0.000
from
Token from
Feature activation+0.000
today
Token today
Feature activation+0.000
are
Token are
Feature activation+0.000
any
Token any
Feature activation+0.000
indication
Token indication
Feature activation+0.149
:
Token:
Feature activation+0.053
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Tomorrow
TokenTomorrow
Feature activation+0.044
is
Token is
Feature activation+0.053
,
Token,
Feature activation+0.000
celebrating
Token celebrating
Feature activation+0.000
how
Token how
Feature activation+0.183
she
Token she
Feature activation+0.095
works
Token works
Feature activation+0.046
hard
Token hard
Feature activation+0.175
as
Token as
Feature activation+0.157
a
Token a
Feature activation+0.000
breastfeeding
Token breastfeeding
Feature activation+0.000
mom
Token mom
Feature activation+0.000
on
Token on
Feature activation+0.000
Currently
TokenCurrently
Feature activation+0.000
,
Token,
Feature activation+0.000
93
Token 93
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
of
Token of
Feature activation+0.120
chief
Token chief
Feature activation+0.048
executive
Token executive
Feature activation+0.000
officer
Token officer
Feature activation+0.000
positions
Token positions
Feature activation+0.000
in
Token in
Feature activation+0.000
older
Token older
Feature activation+0.000
demo
Token demo
Feature activation+0.014
likely
Token likely
Feature activation+0.000
is
Token is
Feature activation+0.007
under
Token under
Feature activation+0.000
represented
Tokenrepresented
Feature activation+0.216
,
Token,
Feature activation+0.194
2
Token 2
Feature activation+0.286
)
Token)
Feature activation+0.449
it
Token it
Feature activation+0.422
's
Token's
Feature activation+0.375
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.009
I
Token I
Feature activation+0.038
can
Token can
Feature activation+0.144
tell
Token tell
Feature activation+0.200
you
Token you
Feature activation+0.210
on
Token on
Feature activation+0.263
behalf
Token behalf
Feature activation+0.262
of
Token of
Feature activation+0.351
this
Token this
Feature activation+0.111
county
Token county
Feature activation+0.000

INTERVAL 0.000 - 0.111
CONTAINS 98.821%

system
Token system
Feature activation+0.000
and
Token and
Feature activation+0.000
carefully
Token carefully
Feature activation+0.000
designed
Token designed
Feature activation+0.000
water
Token water
Feature activation+0.000
flow
Token flow
Feature activation+0.000
are
Token are
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
well
Token well
Feature activation+0.000
makes
Token makes
Feature activation+0.000
a
Token a
Feature activation+0.000
variety
Token variety
Feature activation+0.000
of
Token of
Feature activation+0.000
bikes
Token bikes
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
kids
Token kids
Feature activation+0.000
'
Token'
Feature activation+0.000
bikes
Token bikes
Feature activation+0.000
,
Token,
Feature activation+0.000
pers
Tokenpers
Feature activation+0.000
ons
Tokenons
Feature activation+0.000
alert
Token alert
Feature activation+0.000
on
Token on
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
for
Token for
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Magn
Token Magn
Feature activation+0.000
otta
Tokenotta
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
saying
Token saying
Feature activation+0.000
that
Token that
Feature activation+0.000
"
Token "
Feature activation+0.000
our
Tokenour
Feature activation+0.000
posts
Token posts
Feature activation+0.000
seem
Token seem
Feature activation+0.000
provocative
Token provocative
Feature activation+0.000
mainly
Token mainly
Feature activation+0.000
because
Token because
Feature activation+0.000
they
Token they
Feature activation+0.000
and
Token and
Feature activation+0.000
back
Token back
Feature activation+0.000
-
Token-
Feature activation+0.000
ups
Tokenups
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Earlier
TokenEarlier
Feature activation+0.000
,
Token,
Feature activation+0.000
N
Token N
Feature activation+0.000
isa
Tokenisa
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H2.10: (feature 407)

TOP ACTIVATIONS
MAX = 1.403

The
Token The
Feature activation+0.000
founding
Token founding
Feature activation+0.000
fathers
Token fathers
Feature activation+0.000
of
Token of
Feature activation+0.000
Detroit
Token Detroit
Feature activation+0.000
--
Token --
Feature activation+1.403
and
Token and
Feature activation+0.117
Michigan
Token Michigan
Feature activation+0.000
--
Token --
Feature activation+0.766
are
Token are
Feature activation+0.000
buried
Token buried
Feature activation+0.000
out
Token out
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
bed
Token bed
Feature activation+0.000
really
Token really
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.334
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
honest
Token honest
Feature activation+0.000
,
Token,
Feature activation+0.000
since
Token since
Feature activation+0.000
on
Token on
Feature activation+0.000
and
Token and
Feature activation+0.000
forgiven
Token forgiven
Feature activation+0.000
in
Token in
Feature activation+0.000
advance
Token advance
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.272
lest
Token lest
Feature activation+0.000
Iran
Token Iran
Feature activation+0.000
walk
Token walk
Feature activation+0.000
away
Token away
Feature activation+0.000
.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
is
Token is
Feature activation+0.000
very
Token very
Feature activation+0.000
high
Token high
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.264
more
Token more
Feature activation+0.031
people
Token people
Feature activation+0.000
trust
Token trust
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000
Wild
TokenWild
Feature activation+0.000
"
Token"
Feature activation+0.000
crew
Token crew
Feature activation+0.000
--
Token --
Feature activation+1.260
which
Token which
Feature activation+0.168
shot
Token shot
Feature activation+0.000
all
Token all
Feature activation+0.000
but
Token but
Feature activation+0.000
seven
Token seven
Feature activation+0.000
brisk
Token brisk
Feature activation+0.000
et
Tokenet
Feature activation+0.000
has
Token has
Feature activation+0.000
different
Token different
Feature activation+0.000
parts
Token parts
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.238
the
Token the
Feature activation+0.105
fat
Token fat
Feature activation+0.000
cap
Token cap
Feature activation+0.000
,
Token,
Feature activation+0.151
the
Token the
Feature activation+0.000
celebrate
Token celebrate
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
American
Token American
Feature activation+0.000
appetite
Token appetite
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+1.202
but
Tokenbut
Feature activation+0.000
investors
Token investors
Feature activation+0.000
weren
Token weren
Feature activation+0.000
't
Token't
Feature activation+0.000
convinced
Token convinced
Feature activation+0.000
things
Token things
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
widely
Token widely
Feature activation+0.000
accepted
Token accepted
Feature activation+0.000
--
Token --
Feature activation+1.179
and
Token and
Feature activation+0.007
then
Token then
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
approach
Token approach
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.168
talking
Token talking
Feature activation+0.000
around
Token around
Feature activation+0.000
race
Token race
Feature activation+0.000
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+0.000
has
Token has
Feature activation+0.000
plenty
Token plenty
Feature activation+0.000
of
Token of
Feature activation+0.000
debt
Token debt
Feature activation+0.000
troubles
Token troubles
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+1.164
thanks
Tokenthanks
Feature activation+0.000
to
Token to
Feature activation+0.000
enormous
Token enormous
Feature activation+0.000
over
Token over
Feature activation+0.000
bor
Tokenbor
Feature activation+0.000
pointing
Token pointing
Feature activation+0.000
out
Token out
Feature activation+0.000
questionable
Token questionable
Feature activation+0.000
coding
Token coding
Feature activation+0.000
practices
Token practices
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+1.162
just
Tokenjust
Feature activation+0.000
like
Token like
Feature activation+0.000
good
Token good
Feature activation+0.000
old
Token old
Feature activation+0.000
-
Token -
Feature activation+0.738
Democrats
Token Democrats
Feature activation+0.000
should
Token should
Feature activation+0.000
pursue
Token pursue
Feature activation+0.000
Romney
Token Romney
Feature activation+0.000
voters
Token voters
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.155
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
comfortable
Token comfortable
Feature activation+0.000
suburban
Token suburban
Feature activation+0.000
has
Token has
Feature activation+0.000
spoken
Token spoken
Feature activation+0.000
out
Token out
Feature activation+0.000
against
Token against
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.144
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
prep
Token prep
Feature activation+0.000
oster
Tokenoster
Feature activation+0.000
ous
Tokenous
Feature activation+0.000
someone
Token someone
Feature activation+0.000
might
Token might
Feature activation+0.000
play
Token play
Feature activation+0.000
a
Token a
Feature activation+0.000
game
Token game
Feature activation+0.000
--
Token --
Feature activation+1.127
the
Token the
Feature activation+0.000
pride
Token pride
Feature activation+0.000
you
Token you
Feature activation+0.000
feel
Token feel
Feature activation+0.000
when
Token when
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
project
Token project
Feature activation+0.000
of
Token of
Feature activation+0.000
mine
Token mine
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.116
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
Step
Token Step
Feature activation+0.000
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+0.000
Cowboys
Token Cowboys
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
training
Token training
Feature activation+0.000
camp
Token camp
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.116
they
Token they
Feature activation+0.000
want
Token want
Feature activation+0.000
continuity
Token continuity
Feature activation+0.000
from
Token from
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
relaxed
Token relaxed
Feature activation+0.000
affair
Token affair
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.112
possibly
Token possibly
Feature activation+0.000
because
Token because
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
recorded
Token recorded
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
sophomore
Token sophomore
Feature activation+0.000
year
Token year
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.110
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
verge
Token verge
Feature activation+0.000
of
Token of
Feature activation+0.000
dropping
Token dropping
Feature activation+0.000
the
Token the
Feature activation+0.000
birth
Token birth
Feature activation+0.000
trauma
Token trauma
Feature activation+0.000
to
Token to
Feature activation+0.000
adulthood
Token adulthood
Feature activation+0.000
--
Token--
Feature activation+1.106
which
Tokenwhich
Feature activation+0.294
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
analogous
Token analogous
Feature activation+0.000
to
Token to
Feature activation+0.000
Confederate
Token Confederate
Feature activation+0.000
monuments
Token monuments
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.099
including
Token including
Feature activation+0.036
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Confederate
Token Confederate
Feature activation+0.000
President
Token President
Feature activation+0.000

Top DFA by src position
MAX = 2.268

The
Token The
Feature activation+0.139
Top resid features:
founding
Token founding
Feature activation+0.066
Top resid features:
fathers
Token fathers
Feature activation+0.146
Top resid features:
of
Token of
Feature activation-0.299
Top resid features:
Detroit
Token Detroit
Feature activation+0.200
Top resid features:
--
Token --
Feature activation+2.076
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Michigan
Token Michigan
Feature activation+0.000
Top resid features:
--
Token --
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
buried
Token buried
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.072
Top resid features:
out
Token out
Feature activation+0.064
Top resid features:
of
Token of
Feature activation-0.020
Top resid features:
bed
Token bed
Feature activation+0.182
Top resid features:
really
Token really
Feature activation+0.198
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+1.955
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
honest
Token honest
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+0.053
Top resid features:
forgiven
Token forgiven
Feature activation+0.108
Top resid features:
in
Token in
Feature activation-0.101
Top resid features:
advance
Token advance
Feature activation+0.252
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+1.960
Top resid features:
lest
Token lest
Feature activation+0.000
Top resid features:
Iran
Token Iran
Feature activation+0.000
Top resid features:
walk
Token walk
Feature activation+0.000
Top resid features:
away
Token away
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.146
Top resid features:
scientists
Token scientists
Feature activation+0.204
Top resid features:
is
Token is
Feature activation+0.154
Top resid features:
very
Token very
Feature activation+0.263
Top resid features:
high
Token high
Feature activation+0.079
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+2.042
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
trust
Token trust
Feature activation+0.000
Top resid features:
scientists
Token scientists
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.103
Top resid features:
"
Token "
Feature activation+0.326
Top resid features:
Wild
TokenWild
Feature activation-0.101
Top resid features:
"
Token"
Feature activation+0.090
Top resid features:
crew
Token crew
Feature activation+0.117
Top resid features:
--
Token --
Feature activation+1.730
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
shot
Token shot
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
seven
Token seven
Feature activation+0.000
Top resid features:
brisk
Token brisk
Feature activation-0.021
Top resid features:
et
Tokenet
Feature activation+0.061
Top resid features:
has
Token has
Feature activation+0.181
Top resid features:
different
Token different
Feature activation+0.023
Top resid features:
parts
Token parts
Feature activation+0.213
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.067
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
fat
Token fat
Feature activation+0.000
Top resid features:
cap
Token cap
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
celebrate
Token celebrate
Feature activation+0.082
Top resid features:
the
Token the
Feature activation+0.123
Top resid features:
new
Token new
Feature activation+0.173
Top resid features:
American
Token American
Feature activation-0.007
Top resid features:
appetite
Token appetite
Feature activation+0.229
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+1.711
Top resid features:
but
Tokenbut
Feature activation+0.000
Top resid features:
investors
Token investors
Feature activation+0.000
Top resid features:
weren
Token weren
Feature activation+0.000
Top resid features:
't
Token't
Feature activation+0.000
Top resid features:
convinced
Token convinced
Feature activation+0.000
Top resid features:
things
Token things
Feature activation+0.098
Top resid features:
that
Token that
Feature activation+0.223
Top resid features:
was
Token was
Feature activation+0.166
Top resid features:
widely
Token widely
Feature activation-0.072
Top resid features:
accepted
Token accepted
Feature activation+0.031
Top resid features:
--
Token --
Feature activation+2.101
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
then
Token then
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
lot
Token lot
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Democrats
Token Democrats
Feature activation+0.160
Top resid features:
that
Token that
Feature activation+0.269
Top resid features:
the
Token the
Feature activation+0.068
Top resid features:
current
Token current
Feature activation+0.019
Top resid features:
approach
Token approach
Feature activation+0.117
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+1.977
Top resid features:
talking
Token talking
Feature activation+0.000
Top resid features:
around
Token around
Feature activation+0.000
Top resid features:
race
Token race
Feature activation+0.000
Top resid features:
rather
Token rather
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.064
Top resid features:
plenty
Token plenty
Feature activation+0.029
Top resid features:
of
Token of
Feature activation-0.051
Top resid features:
debt
Token debt
Feature activation+0.063
Top resid features:
troubles
Token troubles
Feature activation+0.164
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+2.005
Top resid features:
thanks
Tokenthanks
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
enormous
Token enormous
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
bor
Tokenbor
Feature activation+0.000
Top resid features:
pointing
Token pointing
Feature activation+0.136
Top resid features:
out
Token out
Feature activation+0.039
Top resid features:
questionable
Token questionable
Feature activation+0.054
Top resid features:
coding
Token coding
Feature activation+0.243
Top resid features:
practices
Token practices
Feature activation+0.325
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+1.715
Top resid features:
just
Tokenjust
Feature activation+0.000
Top resid features:
like
Token like
Feature activation+0.000
Top resid features:
good
Token good
Feature activation+0.000
Top resid features:
old
Token old
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
Democrats
Token Democrats
Feature activation+0.060
Top resid features:
should
Token should
Feature activation-0.074
Top resid features:
pursue
Token pursue
Feature activation-0.084
Top resid features:
Romney
Token Romney
Feature activation+0.144
Top resid features:
voters
Token voters
Feature activation+0.264
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.012
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
comfortable
Token comfortable
Feature activation+0.000
Top resid features:
suburban
Token suburban
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.112
Top resid features:
spoken
Token spoken
Feature activation+0.073
Top resid features:
out
Token out
Feature activation-0.012
Top resid features:
against
Token against
Feature activation+0.072
Top resid features:
it
Token it
Feature activation+0.298
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+2.268
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
prep
Token prep
Feature activation+0.000
Top resid features:
oster
Tokenoster
Feature activation+0.000
Top resid features:
ous
Tokenous
Feature activation+0.000
Top resid features:
someone
Token someone
Feature activation+0.122
Top resid features:
might
Token might
Feature activation+0.081
Top resid features:
play
Token play
Feature activation+0.200
Top resid features:
a
Token a
Feature activation+0.065
Top resid features:
game
Token game
Feature activation+0.209
Top resid features:
--
Token --
Feature activation+1.822
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
pride
Token pride
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
feel
Token feel
Feature activation+0.000
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.016
Top resid features:
new
Token new
Feature activation+0.174
Top resid features:
project
Token project
Feature activation+0.204
Top resid features:
of
Token of
Feature activation-0.065
Top resid features:
mine
Token mine
Feature activation+0.446
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+1.755
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
Step
Token Step
Feature activation+0.000
Top resid features:
1
Token 1
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Cowboys
Token Cowboys
Feature activation+0.114
Top resid features:
go
Token go
Feature activation+0.082
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
training
Token training
Feature activation+0.046
Top resid features:
camp
Token camp
Feature activation+0.219
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+1.932
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
want
Token want
Feature activation+0.000
Top resid features:
continuity
Token continuity
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.088
Top resid features:
a
Token a
Feature activation-0.050
Top resid features:
more
Token more
Feature activation+0.107
Top resid features:
relaxed
Token relaxed
Feature activation+0.032
Top resid features:
affair
Token affair
Feature activation+0.333
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+1.663
Top resid features:
possibly
Token possibly
Feature activation+0.000
Top resid features:
because
Token because
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
recorded
Token recorded
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.355
Top resid features:
in
Token in
Feature activation-0.537
Top resid features:
her
Token her
Feature activation+0.113
Top resid features:
sophomore
Token sophomore
Feature activation+0.132
Top resid features:
year
Token year
Feature activation+0.253
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+2.090
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
verge
Token verge
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
dropping
Token dropping
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.153
Top resid features:
birth
Token birth
Feature activation+0.157
Top resid features:
trauma
Token trauma
Feature activation+0.132
Top resid features:
to
Token to
Feature activation+0.037
Top resid features:
adulthood
Token adulthood
Feature activation+0.252
Top resid features:
--
Token--
Feature activation+1.546
Top resid features:
which
Tokenwhich
Feature activation+0.000
Top resid features:
might
Token might
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
analogous
Token analogous
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Confederate
Token Confederate
Feature activation+0.082
Top resid features:
monuments
Token monuments
Feature activation+0.201
Top resid features:
in
Token in
Feature activation-0.056
Top resid features:
the
Token the
Feature activation+0.169
Top resid features:
Capitol
Token Capitol
Feature activation+0.236
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+1.874
Top resid features:
including
Token including
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Confederate
Token Confederate
Feature activation+0.000
Top resid features:
President
Token President
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.09

Head 3: 0.05

Head 4: 0.04

Head 5: 0.16

Head 6: 0.04

Head 7: 0.10

Head 8: 0.05

Head 9: 0.05

Head 10: 0.25

Head 11: 0.09

Positive logits

assic1.09

odder0.93

won0.93

glomer0.89

acteria0.89

Schr0.87

umbn0.87

phia0.87

atel0.86

lite0.85

iddled0.84

rather0.83

once0.82

allows0.82

sung0.82

self0.82

dating0.81

-)0.81

starting0.81

ocrats0.80

Negative logits

"]=>-0.92

Auction-0.84

ORE-0.83

respons-0.80

Interested-0.80

negro-0.79

Console-0.78

escort-0.78

":--0.78

":[{"-0.77

marvelous-0.77

Parameters-0.77

ocket-0.76

-0.75

EVENTS-0.74

Hemisphere-0.74

oval-0.73

Arms-0.73

android-0.73

inappropriate-0.72

INTERVAL 1.263 - 1.403
CONTAINS 0.000%

out
Token out
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
bed
Token bed
Feature activation+0.000
really
Token really
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.334
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
honest
Token honest
Feature activation+0.000
,
Token,
Feature activation+0.000
since
Token since
Feature activation+0.000
on
Token on
Feature activation+0.000
and
Token and
Feature activation+0.000
forgiven
Token forgiven
Feature activation+0.000
in
Token in
Feature activation+0.000
advance
Token advance
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.272
lest
Token lest
Feature activation+0.000
Iran
Token Iran
Feature activation+0.000
walk
Token walk
Feature activation+0.000
away
Token away
Feature activation+0.000
.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
is
Token is
Feature activation+0.000
very
Token very
Feature activation+0.000
high
Token high
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+1.264
more
Token more
Feature activation+0.031
people
Token people
Feature activation+0.000
trust
Token trust
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
to
Token to
Feature activation+0.000
The
Token The
Feature activation+0.000
founding
Token founding
Feature activation+0.000
fathers
Token fathers
Feature activation+0.000
of
Token of
Feature activation+0.000
Detroit
Token Detroit
Feature activation+0.000
--
Token --
Feature activation+1.403
and
Token and
Feature activation+0.117
Michigan
Token Michigan
Feature activation+0.000
--
Token --
Feature activation+0.766
are
Token are
Feature activation+0.000
buried
Token buried
Feature activation+0.000

INTERVAL 1.122 - 1.263
CONTAINS 0.001%

someone
Token someone
Feature activation+0.000
might
Token might
Feature activation+0.000
play
Token play
Feature activation+0.000
a
Token a
Feature activation+0.000
game
Token game
Feature activation+0.000
--
Token --
Feature activation+1.127
the
Token the
Feature activation+0.000
pride
Token pride
Feature activation+0.000
you
Token you
Feature activation+0.000
feel
Token feel
Feature activation+0.000
when
Token when
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
should
Token should
Feature activation+0.000
pursue
Token pursue
Feature activation+0.000
Romney
Token Romney
Feature activation+0.000
voters
Token voters
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.155
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
comfortable
Token comfortable
Feature activation+0.000
suburban
Token suburban
Feature activation+0.000
celebrate
Token celebrate
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
American
Token American
Feature activation+0.000
appetite
Token appetite
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+1.202
but
Tokenbut
Feature activation+0.000
investors
Token investors
Feature activation+0.000
weren
Token weren
Feature activation+0.000
't
Token't
Feature activation+0.000
convinced
Token convinced
Feature activation+0.000
has
Token has
Feature activation+0.000
spoken
Token spoken
Feature activation+0.000
out
Token out
Feature activation+0.000
against
Token against
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.144
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
prep
Token prep
Feature activation+0.000
oster
Tokenoster
Feature activation+0.000
ous
Tokenous
Feature activation+0.000
brisk
Token brisk
Feature activation+0.000
et
Tokenet
Feature activation+0.000
has
Token has
Feature activation+0.000
different
Token different
Feature activation+0.000
parts
Token parts
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.238
the
Token the
Feature activation+0.105
fat
Token fat
Feature activation+0.000
cap
Token cap
Feature activation+0.000
,
Token,
Feature activation+0.151
the
Token the
Feature activation+0.000

INTERVAL 0.982 - 1.122
CONTAINS 0.005%

be
Token be
Feature activation+0.000
aware
Token aware
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
risks
Token risks
Feature activation+0.000
--
Token --
Feature activation+1.056
current
Token current
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
public
Token public
Feature activation+0.000
health
Token health
Feature activation+0.000
guidelines
Token guidelines
Feature activation+0.000
forcing
Token forcing
Feature activation+0.000
the
Token the
Feature activation+0.000
O
Token O
Feature activation+0.000
sp
Tokensp
Feature activation+0.000
reys
Tokenreys
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.983
advanced
Token advanced
Feature activation+0.092
helicopter
Token helicopter
Feature activation+0.000
-
Token-
Feature activation+0.000
air
Tokenair
Feature activation+0.000
plane
Tokenplane
Feature activation+0.000
multicultural
Token multicultural
Feature activation+0.000
makeup
Token makeup
Feature activation+0.000
of
Token of
Feature activation+0.000
Hugo
Token Hugo
Feature activation+0.000
winners
Token winners
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+1.060
books
Tokenbooks
Feature activation+0.000
featuring
Token featuring
Feature activation+0.000
women
Token women
Feature activation+0.000
,
Token,
Feature activation+0.000
gay
Token gay
Feature activation+0.000
two
Token two
Feature activation+0.000
century
Token century
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
buildings
Token buildings
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.028
including
Token including
Feature activation+0.094
an
Token an
Feature activation+0.000
old
Token old
Feature activation+0.000
Bank
Token Bank
Feature activation+0.000
of
Token of
Feature activation+0.000
efficiency
Tokenefficiency
Feature activation+0.000
"
Token"
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
arrangement
Token arrangement
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.036
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+0.000
as
Token as
Feature activation+0.000

INTERVAL 0.842 - 0.982
CONTAINS 0.007%

cinema
Token cinema
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
art
Token art
Feature activation+0.000
form
Tokenform
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.977
the
Token the
Feature activation+0.000
use
Token use
Feature activation+0.000
of
Token of
Feature activation+0.000
shadows
Token shadows
Feature activation+0.000
for
Token for
Feature activation+0.000
phot
Token phot
Feature activation+0.000
ov
Tokenov
Feature activation+0.000
olt
Tokenolt
Feature activation+0.000
aic
Tokenaic
Feature activation+0.000
effect
Token effect
Feature activation+0.000
--
Token --
Feature activation+0.928
a
Token a
Feature activation+0.001
phenomenon
Token phenomenon
Feature activation+0.000
that
Token that
Feature activation+0.000
takes
Token takes
Feature activation+0.000
place
Token place
Feature activation+0.000
adult
Token adult
Feature activation+0.000
children
Token children
Feature activation+0.000
are
Token are
Feature activation+0.000
coming
Token coming
Feature activation+0.000
back
Token back
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.934
for
Token for
Feature activation+0.000
good
Token good
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
if
Token if
Feature activation+0.000
those
Token those
Feature activation+0.000
millions
Token millions
Feature activation+0.000
of
Token of
Feature activation+0.000
Americans
Token Americans
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.972
including
Token including
Feature activation+0.152
children
Token children
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
poor
Token poor
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
division
Token division
Feature activation+0.000
as
Token as
Feature activation+0.000
anticipated
Token anticipated
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.873
largely
Token largely
Feature activation+0.000
because
Token because
Feature activation+0.000
their
Token their
Feature activation+0.000
starting
Token starting
Feature activation+0.000
rotation
Token rotation
Feature activation+0.000

INTERVAL 0.701 - 0.842
CONTAINS 0.011%

profile
Token profile
Feature activation+0.000
we
Token we
Feature activation+0.000
were
Token were
Feature activation+0.000
looking
Token looking
Feature activation+0.000
for
Token for
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.740
some
Token some
Feature activation+0.000
beers
Token beers
Feature activation+0.000
and
Token and
Feature activation+0.000
styles
Token styles
Feature activation+0.000
don
Token don
Feature activation+0.000
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
two
Token two
Feature activation+0.000
Avengers
Token Avengers
Feature activation+0.000
films
Token films
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.711
soon
Token soon
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
ret
Token ret
Feature activation+0.000
itled
Tokenitled
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
free
Token free
Feature activation+0.000
press
Token press
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.727
along
Token along
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
elements
Token elements
Feature activation+0.000
but
Token but
Feature activation+0.000
civilian
Token civilian
Feature activation+0.000
Bal
Token Bal
Feature activation+0.000
och
Tokenoch
Feature activation+0.000
men
Token men
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.782
and
Tokenand
Feature activation+0.000
some
Token some
Feature activation+0.000
w
Token w
Feature activation+0.000
iz
Tokeniz
Feature activation+0.000
ened
Tokenened
Feature activation+0.000
ill
Tokenill
Feature activation+0.000
ain
Tokenain
Feature activation+0.000
we
Token we
Feature activation+0.000
know
Token know
Feature activation+0.000
today
Token today
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.818
brilliant
Token brilliant
Feature activation+0.000
,
Token,
Feature activation+0.000
cold
Token cold
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.561 - 0.701
CONTAINS 0.012%

been
Token been
Feature activation+0.000
a
Token a
Feature activation+0.000
hit
Token hit
Feature activation+0.000
with
Token with
Feature activation+0.000
visitors
Token visitors
Feature activation+0.000
-
Token -
Feature activation+0.574
but
Token but
Feature activation+0.000
has
Token has
Feature activation+0.000
left
Token left
Feature activation+0.000
keep
Token keep
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
DIS
TokenDIS
Feature activation+0.000
PLAY
TokenPLAY
Feature activation+0.000
S
TokenS
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.592
âĢĶ
TokenâĢĶ
Feature activation+0.184
âĢĵ
TokenâĢĵ
Feature activation+0.047
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Color
TokenColor
Feature activation+0.000
Car
Token Car
Feature activation+0.000
rey
Tokenrey
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
opposite
Token opposite
Feature activation+0.000
-
Token -
Feature activation+0.603
they
Token they
Feature activation+0.040
often
Token often
Feature activation+0.000
play
Token play
Feature activation+0.000
highly
Token highly
Feature activation+0.000
animated
Token animated
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
PS
TokenPS
Feature activation+0.000
4
Token4
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.685
Digital
Token Digital
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
free
Token free
Feature activation+0.000
if
Token if
Feature activation+0.000
he
Token he
Feature activation+0.000
did
Token did
Feature activation+0.000
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.684
he
Token he
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
't
Token't
Feature activation+0.000
trying
Token trying
Feature activation+0.000
too
Token too
Feature activation+0.000

INTERVAL 0.421 - 0.561
CONTAINS 0.011%

of
Token of
Feature activation+0.000
potential
Token potential
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+0.000
justice
Token justice
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.465
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
that
Token that
Feature activation+0.000
included
Token included
Feature activation+0.000
close
Token close
Feature activation+0.000
often
Token often
Feature activation+0.000
over
Token over
Feature activation+0.000
comes
Tokencomes
Feature activation+0.000
lesser
Token lesser
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.488
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
interests
Token interests
Feature activation+0.000
of
Token of
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
class
Token class
Feature activation+0.000
members
Token members
Feature activation+0.000
--
Token--
Feature activation+0.546
potentially
Token potentially
Feature activation+0.000
millions
Token millions
Feature activation+0.000
of
Token of
Feature activation+0.000
women
Token women
Feature activation+0.000
supervised
Token supervised
Feature activation+0.000
deadly
Token deadly
Feature activation+0.000
force
Token force
Feature activation+0.000
only
Token only
Feature activation+0.000
when
Token when
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
-
Token -
Feature activation+0.517
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.491
and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
clearly
Token clearly
Feature activation+0.000
wants
Token wants
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 0.281 - 0.421
CONTAINS 0.012%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
suggestion
Token suggestion
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.383
not
Token not
Feature activation+0.000
an
Token an
Feature activation+0.000
instruction
Token instruction
Feature activation+0.000
,
Token,
Feature activation+0.000
nor
Token nor
Feature activation+0.000
delivered
Token delivered
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
padded
Token padded
Feature activation+0.000
envelop
Token envelop
Feature activation+0.000
-
Token -
Feature activation+0.283
inside
Token inside
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
sea
Token sea
Feature activation+0.000
breeze
Token breeze
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
extreme
Token extreme
Feature activation+0.000
scenarios
Token scenarios
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.362
every
Tokenevery
Feature activation+0.000
where
Tokenwhere
Feature activation+0.000
outside
Token outside
Feature activation+0.000
of
Token of
Feature activation+0.000
repressive
Token repressive
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
manager
Token manager
Feature activation+0.000
said
Token said
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.377
plus
Tokenplus
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
second
Token second
Feature activation+0.000
Nice
TokenNice
Feature activation+0.000
view
Token view
Feature activation+0.000
of
Token of
Feature activation+0.000
M
Token M
Feature activation+0.000
EX
TokenEX
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.357
Click
Token Click
Feature activation+0.000
image
Token image
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
3
Token 3
Feature activation+0.000

INTERVAL 0.140 - 0.281
CONTAINS 0.015%

are
Token are
Feature activation+0.000
a
Token a
Feature activation+0.000
cover
Token cover
Feature activation+0.000
for
Token for
Feature activation+0.000
prejudice
Token prejudice
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.205
or
Tokenor
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
disregard
Token disregard
Feature activation+0.000
for
Token for
Feature activation+0.000
fields
Token fields
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.275
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
for
Token for
Feature activation+0.000
lack
Token lack
Feature activation+0.000
of
Token of
Feature activation+0.000
face
Token face
Feature activation+0.000
forward
Token forward
Feature activation+0.000
for
Token for
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.159
including
Token including
Feature activation+0.000
paying
Token paying
Feature activation+0.000
close
Token close
Feature activation+0.000
attention
Token attention
Feature activation+0.000
to
Token to
Feature activation+0.000
logging
Token logging
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
console
Token console
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.271
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
complex
Token complex
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
staying
Token staying
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.174
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
unreal
Token unreal
Feature activation+0.000

INTERVAL 0.000 - 0.140
CONTAINS 99.927%

bell
Token bell
Feature activation+0.000
es
Tokenes
Feature activation+0.000
to
Token to
Feature activation+0.000
iles
Tokeniles
Feature activation+0.000
de
Token de
Feature activation+0.000
fond
Token fond
Feature activation+0.000
de
Token de
Feature activation+0.000
la
Token la
Feature activation+0.000
v
Token v
Feature activation+0.000
ille
Tokenille
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
in
Token in
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
of
Token of
Feature activation+0.000
deceit
Token deceit
Feature activation+0.000
about
Token about
Feature activation+0.000
America
Token America
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Transit
Token Transit
Feature activation+0.000
train
Token train
Feature activation+0.000
derailed
Token derailed
Feature activation+0.000
just
Token just
Feature activation+0.000
outside
Token outside
Feature activation+0.000
the
Token the
Feature activation+0.000
station
Token station
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
morning
Token morning
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
some
Token some
Feature activation+0.000
real
Token real
Feature activation+0.000
effort
Token effort
Feature activation+0.000
.
Token.
Feature activation+0.000
Those
Token Those
Feature activation+0.000
who
Token who
Feature activation+0.000
want
Token want
Feature activation+0.000
even
Token even
Feature activation+0.000
a
Token a
Feature activation+0.000
remote
Token remote
Feature activation+0.000
shot
Token shot
Feature activation+0.000
in
Token in
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
three
Token three
Feature activation+0.000
teams
Token teams
Feature activation+0.000
formerly
Token formerly
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Premier
Token Premier
Feature activation+0.000
Basketball
Token Basketball
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