H8.8 top features

Top feature 0 in H8.8: (feature 6654)

TOP ACTIVATIONS
MAX = 6.008

replacements
Token replacements
Feature activation+0.000
,
Token,
Feature activation+0.000
either
Token either
Feature activation+0.000
alone
Token alone
Feature activation+0.000
or
Token or
Feature activation+5.858
in
Token in
Feature activation+6.008
combination
Token combination
Feature activation+1.699
,
Token,
Feature activation+0.690
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
with
Token with
Feature activation+0.000
meal
Token meal
Feature activation+0.000
replacements
Token replacements
Feature activation+0.000
,
Token,
Feature activation+0.000
either
Token either
Feature activation+0.000
alone
Token alone
Feature activation+0.000
or
Token or
Feature activation+5.858
in
Token in
Feature activation+6.008
combination
Token combination
Feature activation+1.699
,
Token,
Feature activation+0.690
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
distinct
Token distinct
Feature activation+0.000
zones
Token zones
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
solo
Token solo
Feature activation+0.000
or
Token or
Feature activation+3.646
first
Token first
Feature activation+0.949
and
Token and
Feature activation+0.333
second
Token second
Feature activation+0.000
player
Token player
Feature activation+0.000
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
our
Token our
Feature activation+0.000
own
Token own
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.788
need
Token need
Feature activation+3.506
to
Token to
Feature activation+2.546
strongly
Token strongly
Feature activation+0.800
call
Token call
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
map
Token map
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
a
Token a
Feature activation+0.000
solo
Token solo
Feature activation+0.000
or
Token or
Feature activation+3.287
guild
Token guild
Feature activation+0.000
survival
Token survival
Feature activation+0.000
arena
Token arena
Feature activation+0.000
on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
conventional
Token conventional
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000
alone
Token alone
Feature activation+0.000
and
Token and
Feature activation+2.029
conventional
Token conventional
Feature activation+0.977
treatment
Token treatment
Feature activation+3.113
plus
Token plus
Feature activation+0.864
fumes
Token fumes
Feature activation+0.000
of
Token of
Feature activation+0.016
tea
Token tea
Feature activation+0.000
tree
Token tree
Feature activation+0.000
on
Token on
Feature activation+0.000
its
Token its
Feature activation+0.000
own
Token own
Feature activation+0.000
.
Token.
Feature activation+0.141
But
Token But
Feature activation+3.099
it
Token it
Feature activation+3.107
creates
Token creates
Feature activation+2.057
a
Token a
Feature activation+1.022
situation
Token situation
Feature activation+0.051
where
Token where
Feature activation+0.000
electing
Token electing
Feature activation+0.000
support
Token support
Feature activation+0.000
on
Token on
Feature activation+0.000
its
Token its
Feature activation+0.000
own
Token own
Feature activation+0.000
.
Token.
Feature activation+0.141
But
Token But
Feature activation+3.099
it
Token it
Feature activation+3.107
creates
Token creates
Feature activation+2.057
a
Token a
Feature activation+1.022
situation
Token situation
Feature activation+0.051
where
Token where
Feature activation+0.000
clinics
Token clinics
Feature activation+0.000
by
Token by
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
but
Token but
Feature activation+1.203
they
Token they
Feature activation+1.427
can
Token can
Feature activation+2.979
't
Token't
Feature activation+2.444
always
Token always
Feature activation+2.806
articulate
Token articulate
Feature activation+0.572
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
however
Token however
Feature activation+0.095
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.035
'll
Token'll
Feature activation+1.184
need
Token need
Feature activation+2.061
to
Token to
Feature activation+2.932
pay
Token pay
Feature activation+2.122
the
Token the
Feature activation+0.975
costs
Token costs
Feature activation+0.540
to
Token to
Feature activation+0.910
list
Token list
Feature activation+0.297
themselves
Token themselves
Feature activation+0.000
but
Token but
Feature activation+1.203
they
Token they
Feature activation+1.427
can
Token can
Feature activation+2.979
't
Token't
Feature activation+2.444
always
Token always
Feature activation+2.806
articulate
Token articulate
Feature activation+0.572
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.000
our
Token our
Feature activation+0.000
own
Token own
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.788
need
Token need
Feature activation+3.506
to
Token to
Feature activation+2.546
strongly
Token strongly
Feature activation+0.800
call
Token call
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
by
Token by
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
but
Token but
Feature activation+1.203
they
Token they
Feature activation+1.427
can
Token can
Feature activation+2.979
't
Token't
Feature activation+2.444
always
Token always
Feature activation+2.806
articulate
Token articulate
Feature activation+0.572
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
on
Token on
Feature activation+0.255
my
Token my
Feature activation+0.000
own
Token own
Feature activation+0.000
terms
Token terms
Feature activation+0.709
instead
Token instead
Feature activation+0.516
of
Token of
Feature activation+2.314
being
Token being
Feature activation+1.778
stuck
Token stuck
Feature activation+1.845
in
Token in
Feature activation+1.886
the
Token the
Feature activation+1.358
house
Token house
Feature activation+1.051
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.035
'll
Token'll
Feature activation+1.184
need
Token need
Feature activation+2.061
to
Token to
Feature activation+2.932
pay
Token pay
Feature activation+2.122
the
Token the
Feature activation+0.975
costs
Token costs
Feature activation+0.540
to
Token to
Feature activation+0.910
list
Token list
Feature activation+0.297
your
Token your
Feature activation+0.000
they
Token they
Feature activation+1.642
think
Token think
Feature activation+1.935
the
Token the
Feature activation+1.221
context
Token context
Feature activation+0.000
for
Token for
Feature activation+0.000
being
Token being
Feature activation+2.106
alone
Token alone
Feature activation+0.000
is
Token is
Feature activation+0.000
while
Token while
Feature activation+0.488
they
Token they
Feature activation+1.358
âĢ
TokenâĢ
Feature activation+0.000
,
Token,
Feature activation+1.134
however
Token however
Feature activation+0.095
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.035
'll
Token'll
Feature activation+1.184
need
Token need
Feature activation+2.061
to
Token to
Feature activation+2.932
pay
Token pay
Feature activation+2.122
the
Token the
Feature activation+0.975
costs
Token costs
Feature activation+0.540
to
Token to
Feature activation+0.910
its
Token its
Feature activation+0.000
own
Token own
Feature activation+0.000
.
Token.
Feature activation+0.141
But
Token But
Feature activation+3.099
it
Token it
Feature activation+3.107
creates
Token creates
Feature activation+2.057
a
Token a
Feature activation+1.022
situation
Token situation
Feature activation+0.051
where
Token where
Feature activation+0.000
electing
Token electing
Feature activation+0.000
the
Token the
Feature activation+0.000
own
Token own
Feature activation+0.000
terms
Token terms
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.233
never
Token never
Feature activation+2.032
apolog
Token apolog
Feature activation+0.000
etic
Tokenetic
Feature activation+0.000
for
Token for
Feature activation+0.369
being
Token being
Feature activation+0.000
herself
Token herself
Feature activation+0.000
times
Token times
Feature activation+0.000
between
Token between
Feature activation+0.000
conventional
Token conventional
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000
alone
Token alone
Feature activation+0.000
and
Token and
Feature activation+2.029
conventional
Token conventional
Feature activation+0.977
treatment
Token treatment
Feature activation+3.113
plus
Token plus
Feature activation+0.864
fumes
Token fumes
Feature activation+0.000
of
Token of
Feature activation+0.016

Top DFA by src position
MAX = 7.240

and
Token and
Feature activation-0.002
Top resid features:
meal
Token meal
Feature activation-0.005
Top resid features:
replacements
Token replacements
Feature activation-0.026
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
either
Token either
Feature activation-0.002
Top resid features:
alone
Token alone
Feature activation+7.240
Top resid features:
or
Token or
Feature activation-0.143
Top resid features:
in
Token in
Feature activation-0.040
Top resid features:
combination
Token combination
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
meal
Token meal
Feature activation-0.007
Top resid features:
replacements
Token replacements
Feature activation-0.014
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
either
Token either
Feature activation+0.003
Top resid features:
alone
Token alone
Feature activation+7.020
Top resid features:
or
Token or
Feature activation-0.101
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
combination
Token combination
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.010
Top resid features:
distinct
Token distinct
Feature activation-0.012
Top resid features:
zones
Token zones
Feature activation-0.015
Top resid features:
for
Token for
Feature activation-0.014
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
solo
Token solo
Feature activation+4.763
Top resid features:
or
Token or
Feature activation-0.115
Top resid features:
first
Token first
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
second
Token second
Feature activation+0.000
Top resid features:
player
Token player
Feature activation+0.000
Top resid features:
Mexicans
Token Mexicans
Feature activation+0.017
Top resid features:
can
Token can
Feature activation+0.041
Top resid features:
solve
Token solve
Feature activation+0.068
Top resid features:
on
Token on
Feature activation+0.046
Top resid features:
our
Token our
Feature activation+0.017
Top resid features:
own
Token own
Feature activation+3.992
Top resid features:
.
Token.
Feature activation+0.075
Top resid features:
We
Token We
Feature activation+0.052
Top resid features:
need
Token need
Feature activation+0.076
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
strongly
Token strongly
Feature activation+0.000
Top resid features:
which
Token which
Feature activation-0.118
Top resid features:
map
Token map
Feature activation-0.043
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
start
Token start
Feature activation-0.030
Top resid features:
a
Token a
Feature activation-0.030
Top resid features:
solo
Token solo
Feature activation+4.648
Top resid features:
or
Token or
Feature activation-0.075
Top resid features:
guild
Token guild
Feature activation+0.000
Top resid features:
survival
Token survival
Feature activation+0.000
Top resid features:
arena
Token arena
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
healing
Token healing
Feature activation+0.003
Top resid features:
times
Token times
Feature activation-0.003
Top resid features:
between
Token between
Feature activation+0.024
Top resid features:
conventional
Token conventional
Feature activation+0.215
Top resid features:
treatment
Token treatment
Feature activation+0.007
Top resid features:
alone
Token alone
Feature activation+3.734
Top resid features:
and
Token and
Feature activation+0.137
Top resid features:
conventional
Token conventional
Feature activation-0.012
Top resid features:
treatment
Token treatment
Feature activation+0.022
Top resid features:
plus
Token plus
Feature activation+0.000
Top resid features:
fumes
Token fumes
Feature activation+0.000
Top resid features:
cause
Token cause
Feature activation-0.225
Top resid features:
Trump
Token Trump
Feature activation+0.007
Top resid features:
support
Token support
Feature activation+0.052
Top resid features:
on
Token on
Feature activation+0.006
Top resid features:
its
Token its
Feature activation+0.020
Top resid features:
own
Token own
Feature activation+4.078
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
But
Token But
Feature activation+0.131
Top resid features:
it
Token it
Feature activation+0.013
Top resid features:
creates
Token creates
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
cause
Token cause
Feature activation+0.021
Top resid features:
Trump
Token Trump
Feature activation+0.016
Top resid features:
support
Token support
Feature activation+0.048
Top resid features:
on
Token on
Feature activation+0.011
Top resid features:
its
Token its
Feature activation+0.051
Top resid features:
own
Token own
Feature activation+3.891
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
But
Token But
Feature activation+0.015
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
creates
Token creates
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
go
Token go
Feature activation+0.031
Top resid features:
to
Token to
Feature activation-0.031
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
clinics
Token clinics
Feature activation-0.006
Top resid features:
by
Token by
Feature activation-0.032
Top resid features:
themselves
Token themselves
Feature activation+4.002
Top resid features:
but
Token but
Feature activation-0.003
Top resid features:
they
Token they
Feature activation+0.028
Top resid features:
can
Token can
Feature activation-0.011
Top resid features:
't
Token't
Feature activation+0.000
Top resid features:
always
Token always
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.230
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
your
Token your
Feature activation-0.001
Top resid features:
own
Token own
Feature activation+3.583
Top resid features:
,
Token,
Feature activation+0.101
Top resid features:
however
Token however
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.044
Top resid features:
you
Token you
Feature activation+0.001
Top resid features:
'll
Token'll
Feature activation+0.032
Top resid features:
go
Token go
Feature activation+0.025
Top resid features:
to
Token to
Feature activation-0.046
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
clinics
Token clinics
Feature activation-0.008
Top resid features:
by
Token by
Feature activation-0.064
Top resid features:
themselves
Token themselves
Feature activation+3.865
Top resid features:
but
Token but
Feature activation+0.032
Top resid features:
they
Token they
Feature activation+0.004
Top resid features:
can
Token can
Feature activation+0.013
Top resid features:
't
Token't
Feature activation-0.020
Top resid features:
always
Token always
Feature activation-0.048
Top resid features:
Mexicans
Token Mexicans
Feature activation+0.028
Top resid features:
can
Token can
Feature activation+0.035
Top resid features:
solve
Token solve
Feature activation+0.070
Top resid features:
on
Token on
Feature activation+0.036
Top resid features:
our
Token our
Feature activation+0.016
Top resid features:
own
Token own
Feature activation+3.004
Top resid features:
.
Token.
Feature activation+0.073
Top resid features:
We
Token We
Feature activation+0.045
Top resid features:
need
Token need
Feature activation+0.076
Top resid features:
to
Token to
Feature activation+0.065
Top resid features:
strongly
Token strongly
Feature activation+0.000
Top resid features:
go
Token go
Feature activation+0.047
Top resid features:
to
Token to
Feature activation-0.079
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
clinics
Token clinics
Feature activation+0.001
Top resid features:
by
Token by
Feature activation-0.059
Top resid features:
themselves
Token themselves
Feature activation+3.522
Top resid features:
but
Token but
Feature activation+0.032
Top resid features:
they
Token they
Feature activation+0.019
Top resid features:
can
Token can
Feature activation+0.026
Top resid features:
't
Token't
Feature activation-0.048
Top resid features:
always
Token always
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
go
Token go
Feature activation-0.004
Top resid features:
out
Token out
Feature activation+0.059
Top resid features:
on
Token on
Feature activation+0.012
Top resid features:
my
Token my
Feature activation+0.011
Top resid features:
own
Token own
Feature activation+2.595
Top resid features:
terms
Token terms
Feature activation+0.133
Top resid features:
instead
Token instead
Feature activation+0.013
Top resid features:
of
Token of
Feature activation-0.029
Top resid features:
being
Token being
Feature activation+0.000
Top resid features:
stuck
Token stuck
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.270
Top resid features:
on
Token on
Feature activation-0.006
Top resid features:
your
Token your
Feature activation-0.012
Top resid features:
own
Token own
Feature activation+2.788
Top resid features:
,
Token,
Feature activation+0.085
Top resid features:
however
Token however
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
you
Token you
Feature activation-0.004
Top resid features:
'll
Token'll
Feature activation+0.027
Top resid features:
if
Token if
Feature activation+0.007
Top resid features:
they
Token they
Feature activation+0.004
Top resid features:
like
Token like
Feature activation+0.027
Top resid features:
to
Token to
Feature activation+0.017
Top resid features:
be
Token be
Feature activation-0.018
Top resid features:
alone
Token alone
Feature activation+3.035
Top resid features:
,
Token,
Feature activation-0.016
Top resid features:
they
Token they
Feature activation-0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation-0.001
Top resid features:
ll
Tokenll
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.266
Top resid features:
on
Token on
Feature activation-0.003
Top resid features:
your
Token your
Feature activation+0.003
Top resid features:
own
Token own
Feature activation+2.679
Top resid features:
,
Token,
Feature activation+0.105
Top resid features:
however
Token however
Feature activation+0.020
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
you
Token you
Feature activation-0.001
Top resid features:
'll
Token'll
Feature activation+0.027
Top resid features:
cause
Token cause
Feature activation+0.010
Top resid features:
Trump
Token Trump
Feature activation-0.034
Top resid features:
support
Token support
Feature activation+0.101
Top resid features:
on
Token on
Feature activation+0.013
Top resid features:
its
Token its
Feature activation+0.031
Top resid features:
own
Token own
Feature activation+2.712
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
But
Token But
Feature activation+0.050
Top resid features:
it
Token it
Feature activation+0.023
Top resid features:
creates
Token creates
Feature activation+0.048
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
Morrow
Token Morrow
Feature activation-0.021
Top resid features:
lived
Token lived
Feature activation+0.002
Top resid features:
life
Token life
Feature activation-0.013
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
her
Token her
Feature activation+0.004
Top resid features:
own
Token own
Feature activation+2.744
Top resid features:
terms
Token terms
Feature activation+0.148
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
was
Token was
Feature activation+0.013
Top resid features:
never
Token never
Feature activation-0.056
Top resid features:
healing
Token healing
Feature activation+0.031
Top resid features:
times
Token times
Feature activation+0.002
Top resid features:
between
Token between
Feature activation+0.068
Top resid features:
conventional
Token conventional
Feature activation+0.215
Top resid features:
treatment
Token treatment
Feature activation+0.103
Top resid features:
alone
Token alone
Feature activation+2.598
Top resid features:
and
Token and
Feature activation+0.078
Top resid features:
conventional
Token conventional
Feature activation+0.000
Top resid features:
treatment
Token treatment
Feature activation+0.000
Top resid features:
plus
Token plus
Feature activation+0.000
Top resid features:
fumes
Token fumes
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.05

Head 2: 0.04

Head 3: 0.05

Head 4: 0.04

Head 5: 0.05

Head 6: 0.05

Head 7: 0.03

Head 8: 0.49

Head 9: 0.06

Head 10: 0.07

Head 11: 0.03

Positive logits

solo3.55

alone3.20

duo2.82

companions2.77

communal2.70

loneliness2.69

Alone2.66

Duo2.64

Solo2.64

partner2.62

platoon2.62

lone2.62

trio2.54

teamwork2.54

isolated2.50

Partner2.49

companion2.49

individually2.48

partnered2.46

strangers2.46

Negative logits

icht-2.20

FFFF-2.17

typo-2.16

yy-2.12

expiration-2.10

quote-2.07

wikipedia-2.06

2020-2.05

terday-2.04

UTC-1.96

yrights-1.93

Fair-1.90

cens-1.90

Unicode-1.89

-1.89

wy-1.89

ffff-1.87

Blizz-1.87

expired-1.85

ueller-1.85

INTERVAL 5.407 - 6.008
CONTAINS 0.000%

meal
Token meal
Feature activation+0.000
replacements
Token replacements
Feature activation+0.000
,
Token,
Feature activation+0.000
either
Token either
Feature activation+0.000
alone
Token alone
Feature activation+0.000
or
Token or
Feature activation+5.858
in
Token in
Feature activation+6.008
combination
Token combination
Feature activation+1.699
,
Token,
Feature activation+0.690
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
replacements
Token replacements
Feature activation+0.000
,
Token,
Feature activation+0.000
either
Token either
Feature activation+0.000
alone
Token alone
Feature activation+0.000
or
Token or
Feature activation+5.858
in
Token in
Feature activation+6.008
combination
Token combination
Feature activation+1.699
,
Token,
Feature activation+0.690
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
with
Token with
Feature activation+0.000

INTERVAL 4.806 - 5.407
CONTAINS 0.000%

INTERVAL 4.206 - 4.806
CONTAINS 0.000%

INTERVAL 3.605 - 4.206
CONTAINS 0.000%

distinct
Token distinct
Feature activation+0.000
zones
Token zones
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
solo
Token solo
Feature activation+0.000
or
Token or
Feature activation+3.646
first
Token first
Feature activation+0.949
and
Token and
Feature activation+0.333
second
Token second
Feature activation+0.000
player
Token player
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 3.004 - 3.605
CONTAINS 0.001%

on
Token on
Feature activation+0.000
our
Token our
Feature activation+0.000
own
Token own
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.788
need
Token need
Feature activation+3.506
to
Token to
Feature activation+2.546
strongly
Token strongly
Feature activation+0.800
call
Token call
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
map
Token map
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
a
Token a
Feature activation+0.000
solo
Token solo
Feature activation+0.000
or
Token or
Feature activation+3.287
guild
Token guild
Feature activation+0.000
survival
Token survival
Feature activation+0.000
arena
Token arena
Feature activation+0.000
on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
conventional
Token conventional
Feature activation+0.000
treatment
Token treatment
Feature activation+0.000
alone
Token alone
Feature activation+0.000
and
Token and
Feature activation+2.029
conventional
Token conventional
Feature activation+0.977
treatment
Token treatment
Feature activation+3.113
plus
Token plus
Feature activation+0.864
fumes
Token fumes
Feature activation+0.000
of
Token of
Feature activation+0.016
tea
Token tea
Feature activation+0.000
tree
Token tree
Feature activation+0.000
support
Token support
Feature activation+0.000
on
Token on
Feature activation+0.000
its
Token its
Feature activation+0.000
own
Token own
Feature activation+0.000
.
Token.
Feature activation+0.141
But
Token But
Feature activation+3.099
it
Token it
Feature activation+3.107
creates
Token creates
Feature activation+2.057
a
Token a
Feature activation+1.022
situation
Token situation
Feature activation+0.051
where
Token where
Feature activation+0.000
on
Token on
Feature activation+0.000
its
Token its
Feature activation+0.000
own
Token own
Feature activation+0.000
.
Token.
Feature activation+0.141
But
Token But
Feature activation+3.099
it
Token it
Feature activation+3.107
creates
Token creates
Feature activation+2.057
a
Token a
Feature activation+1.022
situation
Token situation
Feature activation+0.051
where
Token where
Feature activation+0.000
electing
Token electing
Feature activation+0.000

INTERVAL 2.403 - 3.004
CONTAINS 0.001%

however
Token however
Feature activation+0.095
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.035
'll
Token'll
Feature activation+1.184
need
Token need
Feature activation+2.061
to
Token to
Feature activation+2.932
pay
Token pay
Feature activation+2.122
the
Token the
Feature activation+0.975
costs
Token costs
Feature activation+0.540
to
Token to
Feature activation+0.910
list
Token list
Feature activation+0.297
our
Token our
Feature activation+0.000
own
Token own
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.788
need
Token need
Feature activation+3.506
to
Token to
Feature activation+2.546
strongly
Token strongly
Feature activation+0.800
call
Token call
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
clinics
Token clinics
Feature activation+0.000
by
Token by
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
but
Token but
Feature activation+1.203
they
Token they
Feature activation+1.427
can
Token can
Feature activation+2.979
't
Token't
Feature activation+2.444
always
Token always
Feature activation+2.806
articulate
Token articulate
Feature activation+0.572
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
by
Token by
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
but
Token but
Feature activation+1.203
they
Token they
Feature activation+1.427
can
Token can
Feature activation+2.979
't
Token't
Feature activation+2.444
always
Token always
Feature activation+2.806
articulate
Token articulate
Feature activation+0.572
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
but
Token but
Feature activation+1.203
they
Token they
Feature activation+1.427
can
Token can
Feature activation+2.979
't
Token't
Feature activation+2.444
always
Token always
Feature activation+2.806
articulate
Token articulate
Feature activation+0.572
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.802 - 2.403
CONTAINS 0.002%

terms
Token terms
Feature activation+0.709
instead
Token instead
Feature activation+0.516
of
Token of
Feature activation+2.314
being
Token being
Feature activation+1.778
stuck
Token stuck
Feature activation+1.845
in
Token in
Feature activation+1.886
the
Token the
Feature activation+1.358
house
Token house
Feature activation+1.051
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
-
Token-
Feature activation+0.000
one
Tokenone
Feature activation+0.000
matchups
Token matchups
Feature activation+0.000
;
Token;
Feature activation+1.563
there
Token there
Feature activation+1.547
were
Token were
Feature activation+1.977
other
Token other
Feature activation+0.703
great
Token great
Feature activation+0.000
players
Token players
Feature activation+0.000
Jordan
Token Jordan
Feature activation+0.000
's
Token's
Feature activation+0.000
own
Token own
Feature activation+0.000
terms
Token terms
Feature activation+0.709
instead
Token instead
Feature activation+0.516
of
Token of
Feature activation+2.314
being
Token being
Feature activation+1.778
stuck
Token stuck
Feature activation+1.845
in
Token in
Feature activation+1.886
the
Token the
Feature activation+1.358
house
Token house
Feature activation+1.051
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
its
Token its
Feature activation+0.000
own
Token own
Feature activation+0.000
.
Token.
Feature activation+0.141
But
Token But
Feature activation+3.099
it
Token it
Feature activation+3.107
creates
Token creates
Feature activation+2.057
a
Token a
Feature activation+1.022
situation
Token situation
Feature activation+0.051
where
Token where
Feature activation+0.000
electing
Token electing
Feature activation+0.000
the
Token the
Feature activation+0.000
or
Token or
Feature activation+0.000
under
Token under
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
without
Token without
Feature activation+1.992
his
Token his
Feature activation+0.839
wife
Token wife
Feature activation+0.000
's
Token's
Feature activation+0.000
signature
Token signature
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.202 - 1.802
CONTAINS 0.003%

is
Token is
Feature activation+0.000
while
Token while
Feature activation+0.488
they
Token they
Feature activation+1.358
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+1.207
working
Token working
Feature activation+0.852
versus
Token versus
Feature activation+0.000
while
Token while
Feature activation+0.029
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+1.861
the
Token the
Feature activation+0.000
couple
Token couple
Feature activation+0.000
was
Token was
Feature activation+0.344
not
Token not
Feature activation+1.656
being
Token being
Feature activation+0.212
aud
Token aud
Feature activation+0.000
ited
Tokenited
Feature activation+0.000
or
Token or
Feature activation+0.000
under
Token under
Feature activation+0.000
for
Token for
Feature activation+0.000
being
Token being
Feature activation+2.106
alone
Token alone
Feature activation+0.000
is
Token is
Feature activation+0.000
while
Token while
Feature activation+0.488
they
Token they
Feature activation+1.358
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+1.207
working
Token working
Feature activation+0.852
versus
Token versus
Feature activation+0.000
protect
Token protect
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
yourself
Token yourself
Feature activation+0.000
,
Token,
Feature activation+1.300
historically
Token historically
Feature activation+0.000
your
Token your
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
enemy
Token enemy
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
"
Token "
Feature activation+0.555
Washington
TokenWashington
Feature activation+0.100
...
Token ...
Feature activation+0.000
must
Token must
Feature activation+1.658
also
Token also
Feature activation+0.370
continue
Token continue
Feature activation+0.248
to
Token to
Feature activation+0.065
exert
Token exert
Feature activation+0.000
its
Token its
Feature activation+0.000

INTERVAL 0.601 - 1.202
CONTAINS 0.011%

zones
Token zones
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
solo
Token solo
Feature activation+0.000
or
Token or
Feature activation+3.646
first
Token first
Feature activation+0.949
and
Token and
Feature activation+0.333
second
Token second
Feature activation+0.000
player
Token player
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
own
Token own
Feature activation+0.000
,
Token,
Feature activation+1.134
however
Token however
Feature activation+0.095
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.035
'll
Token'll
Feature activation+1.184
need
Token need
Feature activation+2.061
to
Token to
Feature activation+2.932
pay
Token pay
Feature activation+2.122
the
Token the
Feature activation+0.975
costs
Token costs
Feature activation+0.540
ľ
Tokenľ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
security
Token security
Feature activation+0.000
measures
Token measures
Feature activation+0.000
alone
Token alone
Feature activation+0.000
will
Token will
Feature activation+0.995
not
Token not
Feature activation+0.090
stop
Token stop
Feature activation+0.000
the
Token the
Feature activation+0.000
violence
Token violence
Feature activation+0.000
.
Token.
Feature activation+0.687
lets
Token lets
Feature activation+0.146
you
Token you
Feature activation+0.714
access
Token access
Feature activation+0.522
those
Token those
Feature activation+0.088
downloaded
Token downloaded
Feature activation+0.000
files
Token files
Feature activation+0.748
from
Token from
Feature activation+0.585
your
Token your
Feature activation+0.000
Box
Token Box
Feature activation+0.000
account
Token account
Feature activation+0.000
even
Token even
Feature activation+0.612
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
phone
Token phone
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.043
buy
Token buy
Feature activation+1.155
a
Token a
Feature activation+0.692
new
Token new
Feature activation+0.000
phone
Token phone
Feature activation+0.447
and
Token and
Feature activation+0.000
pay
Token pay
Feature activation+0.530

INTERVAL 0.000 - 0.601
CONTAINS 99.983%

subject
Token subject
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
privacy
Token privacy
Feature activation+0.000
and
Token and
Feature activation+0.000
access
Token access
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.000
information
Tokeninformation
Feature activation+0.000
justice
Tokenjustice
Feature activation+0.000
,
Token,
Feature activation+0.000
animals
Token animals
Feature activation+0.000
,
Token,
Feature activation+0.000
animal
Token animal
Feature activation+0.000
-
Token-
Feature activation+0.000
w
Tokenw
Feature activation+0.000
elfare
Tokenelfare
Feature activation+0.000
,
Token,
Feature activation+0.000
hum
Token hum
Feature activation+0.000
pty
Tokenpty
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
the
Token the
Feature activation+0.000
FEC
Token FEC
Feature activation+0.000
writes
Token writes
Feature activation+0.000
another
Token another
Feature activation+0.000
demand
Token demand
Feature activation+0.000
for
Token for
Feature activation+0.000
another
Token another
Feature activation+0.000
explanation
Token explanation
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
present
Token present
Feature activation+0.000
peers
Token peers
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
inevitably
Token inevitably
Feature activation+0.000
be
Token be
Feature activation+0.000
resisted
Token resisted
Feature activation+0.000
by
Token by
Feature activation+0.000
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
much
Token much
Feature activation+0.000
more
Token more
Feature activation+0.000
likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.000
support
Token support
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
as
Token as
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 H8.8: (feature 4326)

TOP ACTIVATIONS
MAX = 4.996

OK
Token OK
Feature activation+0.000
C
TokenC
Feature activation+0.000
is
Token is
Feature activation+0.000
better
Token better
Feature activation+0.000
now
Token now
Feature activation+0.000
than
Token than
Feature activation+4.996
it
Token it
Feature activation+4.859
used
Token used
Feature activation+2.119
to
Token to
Feature activation+0.560
be
Token be
Feature activation+0.980
,
Token,
Feature activation+0.779
C
TokenC
Feature activation+0.000
is
Token is
Feature activation+0.000
better
Token better
Feature activation+0.000
now
Token now
Feature activation+0.000
than
Token than
Feature activation+4.996
it
Token it
Feature activation+4.859
used
Token used
Feature activation+2.119
to
Token to
Feature activation+0.560
be
Token be
Feature activation+0.980
,
Token,
Feature activation+0.779
and
Token and
Feature activation+0.455
now
Token now
Feature activation+0.000
,
Token,
Feature activation+2.799
that
Token that
Feature activation+0.868
might
Token might
Feature activation+1.710
be
Token be
Feature activation+0.208
exploited
Token exploited
Feature activation+4.727
later
Token later
Feature activation+3.346
when
Token when
Feature activation+0.387
the
Token the
Feature activation+0.000
compiler
Token compiler
Feature activation+0.000
becomes
Token becomes
Feature activation+0.000
champions
Token champions
Feature activation+0.000
like
Token like
Feature activation+0.000
Katy
Token Katy
Feature activation+0.000
now
Token now
Feature activation+0.000
more
Token more
Feature activation+1.432
than
Token than
Feature activation+4.130
ever
Token ever
Feature activation+0.554
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.274
need
Token need
Feature activation+0.000
her
Token her
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
possible
Token possible
Feature activation+0.000
now
Token now
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+4.126
ever
Token ever
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
heard
Token heard
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.931
software
Token software
Feature activation+0.000
maintenance
Token maintenance
Feature activation+0.000
and
Token and
Feature activation+0.000
upkeep
Token upkeep
Feature activation+1.866
may
Token may
Feature activation+4.086
accumulate
Token accumulate
Feature activation+0.373
and
Token and
Feature activation+0.000
charge
Token charge
Feature activation+0.000
you
Token you
Feature activation+2.324
in
Token in
Feature activation+2.341
hydro
Token hydro
Feature activation+0.000
pl
Token pl
Feature activation+0.000
ights
Tokenights
Feature activation+0.000
of
Token of
Feature activation+0.000
today
Token today
Feature activation+0.000
and
Token and
Feature activation+3.993
tomorrow
Token tomorrow
Feature activation+0.000
,
Token,
Feature activation+0.000
many
Token many
Feature activation+0.000
past
Token past
Feature activation+0.000
articles
Token articles
Feature activation+0.000
may
Token may
Feature activation+0.000
not
Token not
Feature activation+0.000
pay
Token pay
Feature activation+0.000
upfront
Token upfront
Feature activation+0.000
now
Token now
Feature activation+0.136
,
Token,
Feature activation+3.821
the
Token the
Feature activation+1.874
expenses
Token expenses
Feature activation+1.770
for
Token for
Feature activation+1.563
the
Token the
Feature activation+0.931
software
Token software
Feature activation+0.000
Ant
Token Ant
Feature activation+0.000
im
Tokenim
Feature activation+0.000
atter
Tokenatter
Feature activation+0.000
:
Token:
Feature activation+0.000
Now
Token Now
Feature activation+0.000
and
Token and
Feature activation+3.502
Later
Token Later
Feature activation+0.000
-
Token -
Feature activation+0.000
B
Token B
Feature activation+0.000
ibliography
Tokenibliography
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+2.799
that
Token that
Feature activation+0.868
might
Token might
Feature activation+1.710
be
Token be
Feature activation+0.208
exploited
Token exploited
Feature activation+4.727
later
Token later
Feature activation+3.346
when
Token when
Feature activation+0.387
the
Token the
Feature activation+0.000
compiler
Token compiler
Feature activation+0.000
becomes
Token becomes
Feature activation+0.000
a
Token a
Feature activation+0.000
is
Token is
Feature activation+0.304
everyone
Token everyone
Feature activation+0.000
asking
Token asking
Feature activation+0.596
me
Token me
Feature activation+0.000
about
Token about
Feature activation+0.211
it
Token it
Feature activation+3.288
?
Token?
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
passion
Token passion
Feature activation+0.000
remains
Token remains
Feature activation+0.000
as
Token as
Feature activation+0.000
strong
Token strong
Feature activation+0.000
today
Token today
Feature activation+0.000
as
Token as
Feature activation+3.224
ever
Token ever
Feature activation+0.079
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hun
TokenHun
Feature activation+0.000
said
Token said
Feature activation+0.000
Journey
Token Journey
Feature activation+0.000
man
Tokenman
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+1.779
But
TokenBut
Feature activation+3.193
a
Token a
Feature activation+2.133
Siberian
Token Siberian
Feature activation+0.000
el
Token el
Feature activation+0.000
m
Tokenm
Feature activation+0.000
grew
Token grew
Feature activation+0.000
that
Token that
Feature activation+0.000
applies
Token applies
Feature activation+0.000
to
Token to
Feature activation+0.000
Yates
Token Yates
Feature activation+0.000
now
Token now
Feature activation+0.000
applies
Token applies
Feature activation+3.114
to
Token to
Feature activation+0.000
Bo
Token Bo
Feature activation+0.000
ente
Tokenente
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Josh
Token Josh
Feature activation+0.000
's
Token's
Feature activation+0.282
still
Token still
Feature activation+0.119
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
as
Token as
Feature activation+1.513
it
Token it
Feature activation+3.108
was
Token was
Feature activation+2.441
in
Token in
Feature activation+1.610
2012
Token 2012
Feature activation+0.059
."
Token."
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+2.296
It
TokenIt
Feature activation+3.095
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.800
all
Token all
Feature activation+0.000
about
Token about
Feature activation+0.803
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
times
Token times
Feature activation+0.000
higher
Token higher
Feature activation+0.000
today
Token today
Feature activation+0.000
than
Token than
Feature activation+2.918
it
Token it
Feature activation+2.795
was
Token was
Feature activation+1.485
in
Token in
Feature activation+1.498
1960
Token 1960
Feature activation+0.000
,
Token,
Feature activation+0.000
(
Token(
Feature activation+0.000
k
Tokenk
Feature activation+0.000
)
Token)
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.778
but
Token but
Feature activation+2.838
this
Token this
Feature activation+1.529
number
Token number
Feature activation+2.835
is
Token is
Feature activation+1.673
expected
Token expected
Feature activation+1.880
to
Token to
Feature activation+1.091
)
Token)
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.778
but
Token but
Feature activation+2.838
this
Token this
Feature activation+1.529
number
Token number
Feature activation+2.835
is
Token is
Feature activation+1.673
expected
Token expected
Feature activation+1.880
to
Token to
Feature activation+1.091
rapidly
Token rapidly
Feature activation+0.005
grow
Token grow
Feature activation+0.000
happen
Token happen
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
exploited
Token exploited
Feature activation+0.000
now
Token now
Feature activation+0.000
,
Token,
Feature activation+2.799
that
Token that
Feature activation+0.868
might
Token might
Feature activation+1.710
be
Token be
Feature activation+0.208
exploited
Token exploited
Feature activation+4.727
later
Token later
Feature activation+3.346

Top DFA by src position
MAX = 5.579

on
Token on
Feature activation+0.008
Top resid features:
OK
Token OK
Feature activation-0.012
Top resid features:
C
TokenC
Feature activation-0.002
Top resid features:
is
Token is
Feature activation+0.064
Top resid features:
better
Token better
Feature activation+0.050
Top resid features:
now
Token now
Feature activation+5.579
Top resid features:
than
Token than
Feature activation-0.034
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
used
Token used
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.008
Top resid features:
OK
Token OK
Feature activation-0.004
Top resid features:
C
TokenC
Feature activation-0.002
Top resid features:
is
Token is
Feature activation+0.037
Top resid features:
better
Token better
Feature activation+0.071
Top resid features:
now
Token now
Feature activation+5.428
Top resid features:
than
Token than
Feature activation+0.078
Top resid features:
it
Token it
Feature activation+0.040
Top resid features:
used
Token used
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation-0.005
Top resid features:
happen
Token happen
Feature activation-0.008
Top resid features:
to
Token to
Feature activation-0.009
Top resid features:
be
Token be
Feature activation+0.017
Top resid features:
exploited
Token exploited
Feature activation-0.018
Top resid features:
now
Token now
Feature activation+5.478
Top resid features:
,
Token,
Feature activation+0.080
Top resid features:
that
Token that
Feature activation+0.043
Top resid features:
might
Token might
Feature activation+0.028
Top resid features:
be
Token be
Feature activation+0.028
Top resid features:
exploited
Token exploited
Feature activation-0.069
Top resid features:
We
TokenWe
Feature activation+0.025
Top resid features:
need
Token need
Feature activation+0.096
Top resid features:
champions
Token champions
Feature activation-0.131
Top resid features:
like
Token like
Feature activation-0.053
Top resid features:
Katy
Token Katy
Feature activation+0.036
Top resid features:
now
Token now
Feature activation+4.579
Top resid features:
more
Token more
Feature activation+0.395
Top resid features:
than
Token than
Feature activation+0.083
Top resid features:
ever
Token ever
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
We
Token We
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.021
Top resid features:
âĢ
TokenâĢ
Feature activation+0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
s
Tokens
Feature activation+0.015
Top resid features:
possible
Token possible
Feature activation+0.062
Top resid features:
now
Token now
Feature activation+4.767
Top resid features:
more
Token more
Feature activation+0.362
Top resid features:
than
Token than
Feature activation-0.009
Top resid features:
ever
Token ever
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.003
Top resid features:
may
Token may
Feature activation+0.006
Top resid features:
not
Token not
Feature activation+0.002
Top resid features:
pay
Token pay
Feature activation-0.015
Top resid features:
upfront
Token upfront
Feature activation-0.036
Top resid features:
now
Token now
Feature activation+4.484
Top resid features:
,
Token,
Feature activation+0.089
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
expenses
Token expenses
Feature activation+0.080
Top resid features:
for
Token for
Feature activation+0.035
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
Ontario
Token Ontario
Feature activation+0.004
Top resid features:
hydro
Token hydro
Feature activation+0.009
Top resid features:
pl
Token pl
Feature activation+0.003
Top resid features:
ights
Tokenights
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
today
Token today
Feature activation+4.780
Top resid features:
and
Token and
Feature activation-0.016
Top resid features:
tomorrow
Token tomorrow
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
many
Token many
Feature activation+0.000
Top resid features:
past
Token past
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.024
Top resid features:
may
Token may
Feature activation+0.049
Top resid features:
not
Token not
Feature activation+0.038
Top resid features:
pay
Token pay
Feature activation+0.033
Top resid features:
upfront
Token upfront
Feature activation-0.039
Top resid features:
now
Token now
Feature activation+4.277
Top resid features:
,
Token,
Feature activation+0.092
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
expenses
Token expenses
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:
-
Token -
Feature activation-0.007
Top resid features:
Ant
Token Ant
Feature activation-0.001
Top resid features:
im
Tokenim
Feature activation+0.002
Top resid features:
atter
Tokenatter
Feature activation-0.008
Top resid features:
:
Token:
Feature activation+0.012
Top resid features:
Now
Token Now
Feature activation+4.457
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
Later
Token Later
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
B
Token B
Feature activation+0.000
Top resid features:
ibliography
Tokenibliography
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.002
Top resid features:
happen
Token happen
Feature activation-0.003
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
be
Token be
Feature activation+0.017
Top resid features:
exploited
Token exploited
Feature activation-0.007
Top resid features:
now
Token now
Feature activation+4.118
Top resid features:
,
Token,
Feature activation+0.064
Top resid features:
that
Token that
Feature activation+0.006
Top resid features:
might
Token might
Feature activation+0.016
Top resid features:
be
Token be
Feature activation+0.003
Top resid features:
exploited
Token exploited
Feature activation+0.041
Top resid features:
that
Token that
Feature activation+0.030
Top resid features:
homosexuality
Token homosexuality
Feature activation+0.014
Top resid features:
has
Token has
Feature activation+0.014
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
value
Token value
Feature activation-0.068
Top resid features:
now
Token now
Feature activation+3.582
Top resid features:
.
Token.
Feature activation+0.063
Top resid features:
Why
Token Why
Feature activation+0.066
Top resid features:
is
Token is
Feature activation+0.008
Top resid features:
everyone
Token everyone
Feature activation-0.000
Top resid features:
asking
Token asking
Feature activation-0.007
Top resid features:
's
Token's
Feature activation-0.008
Top resid features:
passion
Token passion
Feature activation+0.038
Top resid features:
remains
Token remains
Feature activation+0.206
Top resid features:
as
Token as
Feature activation-0.018
Top resid features:
strong
Token strong
Feature activation+0.059
Top resid features:
today
Token today
Feature activation+3.707
Top resid features:
as
Token as
Feature activation+0.003
Top resid features:
ever
Token ever
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:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
ľ
Tokenľ
Feature activation-0.005
Top resid features:
Not
TokenNot
Feature activation-0.004
Top resid features:
now
Token now
Feature activation+3.630
Top resid features:
,
Token,
Feature activation+0.087
Top resid features:
âĢ
TokenâĢ
Feature activation-0.008
Top resid features:
Ŀ
TokenĿ
Feature activation-0.005
Top resid features:
said
Token said
Feature activation-0.007
Top resid features:
Journey
Token Journey
Feature activation-0.039
Top resid features:
analysis
Token analysis
Feature activation-0.007
Top resid features:
that
Token that
Feature activation+0.011
Top resid features:
applies
Token applies
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.010
Top resid features:
Yates
Token Yates
Feature activation-0.013
Top resid features:
now
Token now
Feature activation+3.772
Top resid features:
applies
Token applies
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Bo
Token Bo
Feature activation+0.000
Top resid features:
ente
Tokenente
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
case
Token case
Feature activation+0.008
Top resid features:
:
Token:
Feature activation+0.006
Top resid features:
"
Token "
Feature activation+0.064
Top resid features:
It
TokenIt
Feature activation+0.043
Top resid features:
's
Token's
Feature activation+0.018
Top resid features:
still
Token still
Feature activation+3.331
Top resid features:
the
Token the
Feature activation+0.105
Top resid features:
same
Token same
Feature activation+0.207
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
it
Token it
Feature activation+0.009
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
doesn
Token doesn
Feature activation+0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+0.009
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
t
Tokent
Feature activation+0.010
Top resid features:
matter
Token matter
Feature activation+0.102
Top resid features:
now
Token now
Feature activation+3.598
Top resid features:
,"
Token,"
Feature activation-0.001
Top resid features:
he
Token he
Feature activation+0.003
Top resid features:
said
Token said
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
"
Token "
Feature activation+0.076
Top resid features:
1
Token 1
Feature activation-0.046
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
8
Token8
Feature activation-0.038
Top resid features:
times
Token times
Feature activation+0.024
Top resid features:
higher
Token higher
Feature activation-0.015
Top resid features:
today
Token today
Feature activation+3.752
Top resid features:
than
Token than
Feature activation-0.059
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
1960
Token 1960
Feature activation+0.000
Top resid features:
(
Token(
Feature activation-0.000
Top resid features:
k
Tokenk
Feature activation+0.001
Top resid features:
)
Token)
Feature activation+0.008
Top resid features:
option
Token option
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Currently
Token Currently
Feature activation+3.311
Top resid features:
only
Token only
Feature activation+0.133
Top resid features:
a
Token a
Feature activation+0.034
Top resid features:
third
Token third
Feature activation-0.022
Top resid features:
of
Token of
Feature activation+0.016
Top resid features:
employers
Token employers
Feature activation+0.006
Top resid features:
(
Token(
Feature activation-0.000
Top resid features:
k
Tokenk
Feature activation-0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
option
Token option
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
Currently
Token Currently
Feature activation+3.394
Top resid features:
only
Token only
Feature activation+0.215
Top resid features:
a
Token a
Feature activation+0.015
Top resid features:
third
Token third
Feature activation-0.051
Top resid features:
of
Token of
Feature activation+0.102
Top resid features:
employers
Token employers
Feature activation+0.003
Top resid features:
t
Tokent
Feature activation+0.028
Top resid features:
happen
Token happen
Feature activation-0.016
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
be
Token be
Feature activation+0.038
Top resid features:
exploited
Token exploited
Feature activation-0.017
Top resid features:
now
Token now
Feature activation+3.911
Top resid features:
,
Token,
Feature activation+0.048
Top resid features:
that
Token that
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:
exploited
Token exploited
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.04

Head 2: 0.03

Head 3: 0.05

Head 4: 0.05

Head 5: 0.06

Head 6: 0.06

Head 7: 0.04

Head 8: 0.48

Head 9: 0.06

Head 10: 0.09

Head 11: 0.02

Positive logits

tomorrow4.12

Tomorrow3.26

yesterday3.01

Tomorrow2.84

ago2.75

Yesterday2.73

morrow2.72

today2.63

earlier2.61

today2.59

sooner2.58

future2.56

earliest2.55

terday2.54

hereafter2.53

future2.51

catentry2.47

Ago2.47

Today2.44

Today2.42

Negative logits

-2.35

isu-2.02

obar-1.96

isy-1.91

gee-1.89

ortion-1.87

cipl-1.86

Gate-1.84

iquette-1.82

gore-1.82

clusive-1.79

hack-1.79

llah-1.78

ographed-1.73

ullah-1.71

POL-1.70

CLUD-1.69

complimentary-1.68

scored-1.68

SourceFile-1.66

INTERVAL 4.496 - 4.996
CONTAINS 0.000%

OK
Token OK
Feature activation+0.000
C
TokenC
Feature activation+0.000
is
Token is
Feature activation+0.000
better
Token better
Feature activation+0.000
now
Token now
Feature activation+0.000
than
Token than
Feature activation+4.996
it
Token it
Feature activation+4.859
used
Token used
Feature activation+2.119
to
Token to
Feature activation+0.560
be
Token be
Feature activation+0.980
,
Token,
Feature activation+0.779
C
TokenC
Feature activation+0.000
is
Token is
Feature activation+0.000
better
Token better
Feature activation+0.000
now
Token now
Feature activation+0.000
than
Token than
Feature activation+4.996
it
Token it
Feature activation+4.859
used
Token used
Feature activation+2.119
to
Token to
Feature activation+0.560
be
Token be
Feature activation+0.980
,
Token,
Feature activation+0.779
and
Token and
Feature activation+0.455
now
Token now
Feature activation+0.000
,
Token,
Feature activation+2.799
that
Token that
Feature activation+0.868
might
Token might
Feature activation+1.710
be
Token be
Feature activation+0.208
exploited
Token exploited
Feature activation+4.727
later
Token later
Feature activation+3.346
when
Token when
Feature activation+0.387
the
Token the
Feature activation+0.000
compiler
Token compiler
Feature activation+0.000
becomes
Token becomes
Feature activation+0.000

INTERVAL 3.997 - 4.496
CONTAINS 0.000%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
possible
Token possible
Feature activation+0.000
now
Token now
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+4.126
ever
Token ever
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
heard
Token heard
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.931
software
Token software
Feature activation+0.000
maintenance
Token maintenance
Feature activation+0.000
and
Token and
Feature activation+0.000
upkeep
Token upkeep
Feature activation+1.866
may
Token may
Feature activation+4.086
accumulate
Token accumulate
Feature activation+0.373
and
Token and
Feature activation+0.000
charge
Token charge
Feature activation+0.000
you
Token you
Feature activation+2.324
in
Token in
Feature activation+2.341
champions
Token champions
Feature activation+0.000
like
Token like
Feature activation+0.000
Katy
Token Katy
Feature activation+0.000
now
Token now
Feature activation+0.000
more
Token more
Feature activation+1.432
than
Token than
Feature activation+4.130
ever
Token ever
Feature activation+0.554
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.274
need
Token need
Feature activation+0.000
her
Token her
Feature activation+0.000

INTERVAL 3.497 - 3.997
CONTAINS 0.000%

hydro
Token hydro
Feature activation+0.000
pl
Token pl
Feature activation+0.000
ights
Tokenights
Feature activation+0.000
of
Token of
Feature activation+0.000
today
Token today
Feature activation+0.000
and
Token and
Feature activation+3.993
tomorrow
Token tomorrow
Feature activation+0.000
,
Token,
Feature activation+0.000
many
Token many
Feature activation+0.000
past
Token past
Feature activation+0.000
articles
Token articles
Feature activation+0.000
Ant
Token Ant
Feature activation+0.000
im
Tokenim
Feature activation+0.000
atter
Tokenatter
Feature activation+0.000
:
Token:
Feature activation+0.000
Now
Token Now
Feature activation+0.000
and
Token and
Feature activation+3.502
Later
Token Later
Feature activation+0.000
-
Token -
Feature activation+0.000
B
Token B
Feature activation+0.000
ibliography
Tokenibliography
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
may
Token may
Feature activation+0.000
not
Token not
Feature activation+0.000
pay
Token pay
Feature activation+0.000
upfront
Token upfront
Feature activation+0.000
now
Token now
Feature activation+0.136
,
Token,
Feature activation+3.821
the
Token the
Feature activation+1.874
expenses
Token expenses
Feature activation+1.770
for
Token for
Feature activation+1.563
the
Token the
Feature activation+0.931
software
Token software
Feature activation+0.000

INTERVAL 2.998 - 3.497
CONTAINS 0.001%

that
Token that
Feature activation+0.000
applies
Token applies
Feature activation+0.000
to
Token to
Feature activation+0.000
Yates
Token Yates
Feature activation+0.000
now
Token now
Feature activation+0.000
applies
Token applies
Feature activation+3.114
to
Token to
Feature activation+0.000
Bo
Token Bo
Feature activation+0.000
ente
Tokenente
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Josh
Token Josh
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+2.296
It
TokenIt
Feature activation+3.095
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.800
all
Token all
Feature activation+0.000
about
Token about
Feature activation+0.803
,
Token,
Feature activation+2.799
that
Token that
Feature activation+0.868
might
Token might
Feature activation+1.710
be
Token be
Feature activation+0.208
exploited
Token exploited
Feature activation+4.727
later
Token later
Feature activation+3.346
when
Token when
Feature activation+0.387
the
Token the
Feature activation+0.000
compiler
Token compiler
Feature activation+0.000
becomes
Token becomes
Feature activation+0.000
a
Token a
Feature activation+0.000
's
Token's
Feature activation+0.282
still
Token still
Feature activation+0.119
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
as
Token as
Feature activation+1.513
it
Token it
Feature activation+3.108
was
Token was
Feature activation+2.441
in
Token in
Feature activation+1.610
2012
Token 2012
Feature activation+0.059
."
Token."
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
passion
Token passion
Feature activation+0.000
remains
Token remains
Feature activation+0.000
as
Token as
Feature activation+0.000
strong
Token strong
Feature activation+0.000
today
Token today
Feature activation+0.000
as
Token as
Feature activation+3.224
ever
Token ever
Feature activation+0.079
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hun
TokenHun
Feature activation+0.000

INTERVAL 2.498 - 2.998
CONTAINS 0.002%

happen
Token happen
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
exploited
Token exploited
Feature activation+0.000
now
Token now
Feature activation+0.000
,
Token,
Feature activation+2.799
that
Token that
Feature activation+0.868
might
Token might
Feature activation+1.710
be
Token be
Feature activation+0.208
exploited
Token exploited
Feature activation+4.727
later
Token later
Feature activation+3.346
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.141
analogous
Token analogous
Feature activation+2.209
.
Token.
Feature activation+1.005
Unlike
Token Unlike
Feature activation+2.555
the
Token the
Feature activation+2.095
Asian
Token Asian
Feature activation+0.000
countries
Token countries
Feature activation+0.166
that
Token that
Feature activation+0.399
got
Token got
Feature activation+0.022
accumulate
Token accumulate
Feature activation+0.373
and
Token and
Feature activation+0.000
charge
Token charge
Feature activation+0.000
you
Token you
Feature activation+2.324
in
Token in
Feature activation+2.341
the
Token the
Feature activation+2.659
future
Token future
Feature activation+0.243
.
Token.
Feature activation+0.034
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
user
Token user
Feature activation+0.000
-
Token-
Feature activation+0.000
visible
Tokenvisible
Feature activation+0.000
today
Token today
Feature activation+0.000
,
Token,
Feature activation+2.755
it
Token it
Feature activation+2.626
p
Token p
Feature activation+0.000
aves
Tokenaves
Feature activation+0.287
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.077
for
Token for
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
times
Token times
Feature activation+0.000
higher
Token higher
Feature activation+0.000
today
Token today
Feature activation+0.000
than
Token than
Feature activation+2.918
it
Token it
Feature activation+2.795
was
Token was
Feature activation+1.485
in
Token in
Feature activation+1.498
1960
Token 1960
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.998 - 2.498
CONTAINS 0.002%

ist
Tokenist
Feature activation+0.000
and
Token and
Feature activation+0.000
extremist
Token extremist
Feature activation+0.000
narratives
Token narratives
Feature activation+0.000
today
Token today
Feature activation+0.000
,
Token,
Feature activation+2.189
the
Token the
Feature activation+0.677
preceding
Token preceding
Feature activation+0.878
war
Token war
Feature activation+0.000
was
Token was
Feature activation+0.000
potentially
Token potentially
Feature activation+0.000
in
Token in
Feature activation+1.243
the
Token the
Feature activation+0.000
95
Token 95
Feature activation+0.000
th
Tokenth
Feature activation+0.000
percentile
Token percentile
Feature activation+2.634
in
Token in
Feature activation+2.441
1982
Token 1982
Feature activation+0.091
,
Token,
Feature activation+0.067
whereas
Token whereas
Feature activation+1.932
someone
Token someone
Feature activation+0.392
in
Token in
Feature activation+0.573
US
Token US
Feature activation+0.000
either
Token either
Feature activation+0.000
still
Token still
Feature activation+0.000
getting
Token getting
Feature activation+0.000
now
Token now
Feature activation+0.000
or
Token or
Feature activation+2.254
digging
Token digging
Feature activation+0.181
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
stuff
Token stuff
Feature activation+0.000
still
Token still
Feature activation+0.119
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
as
Token as
Feature activation+1.513
it
Token it
Feature activation+3.108
was
Token was
Feature activation+2.441
in
Token in
Feature activation+1.610
2012
Token 2012
Feature activation+0.059
."
Token."
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
It
TokenIt
Feature activation+0.000
conservatives
Token conservatives
Feature activation+0.000
say
Token say
Feature activation+0.000
their
Token their
Feature activation+0.000
repeal
Token repeal
Feature activation+0.000
now
Token now
Feature activation+0.000
and
Token and
Feature activation+2.097
replace
Token replace
Feature activation+0.000
later
Token later
Feature activation+0.000
plan
Token plan
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 1.499 - 1.998
CONTAINS 0.004%

not
Token not
Feature activation+0.000
pay
Token pay
Feature activation+0.000
upfront
Token upfront
Feature activation+0.000
now
Token now
Feature activation+0.136
,
Token,
Feature activation+3.821
the
Token the
Feature activation+1.874
expenses
Token expenses
Feature activation+1.770
for
Token for
Feature activation+1.563
the
Token the
Feature activation+0.931
software
Token software
Feature activation+0.000
maintenance
Token maintenance
Feature activation+0.000
the
Token the
Feature activation+0.000
open
Token open
Feature activation+0.000
hubs
Token hubs
Feature activation+0.000
.
Token.
Feature activation+0.405
In
Token In
Feature activation+0.875
the
Token the
Feature activation+1.534
coming
Token coming
Feature activation+0.808
days
Token days
Feature activation+0.150
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
going
Token going
Feature activation+0.000
k
Tokenk
Feature activation+0.000
)
Token)
Feature activation+0.000
s
Tokens
Feature activation+0.000
,
Token,
Feature activation+0.778
but
Token but
Feature activation+2.838
this
Token this
Feature activation+1.529
number
Token number
Feature activation+2.835
is
Token is
Feature activation+1.673
expected
Token expected
Feature activation+1.880
to
Token to
Feature activation+1.091
rapidly
Token rapidly
Feature activation+0.005
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
value
Token value
Feature activation+0.000
now
Token now
Feature activation+0.000
.
Token.
Feature activation+0.920
Why
Token Why
Feature activation+1.779
is
Token is
Feature activation+0.304
everyone
Token everyone
Feature activation+0.000
asking
Token asking
Feature activation+0.596
me
Token me
Feature activation+0.000
about
Token about
Feature activation+0.211
,
Token,
Feature activation+0.778
but
Token but
Feature activation+2.838
this
Token this
Feature activation+1.529
number
Token number
Feature activation+2.835
is
Token is
Feature activation+1.673
expected
Token expected
Feature activation+1.880
to
Token to
Feature activation+1.091
rapidly
Token rapidly
Feature activation+0.005
grow
Token grow
Feature activation+0.000
with
Token with
Feature activation+0.000
most
Token most
Feature activation+0.000

INTERVAL 0.999 - 1.499
CONTAINS 0.009%

and
Token and
Feature activation+0.271
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
minor
Token minor
Feature activation+0.356
forces
Token forces
Feature activation+1.991
pulling
Token pulling
Feature activation+1.020
it
Token it
Feature activation+0.930
here
Token here
Feature activation+2.297
and
Token and
Feature activation+0.235
there
Token there
Feature activation+0.911
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
look
Token look
Feature activation+0.000
back
Token back
Feature activation+0.000
now
Token now
Feature activation+0.000
and
Token and
Feature activation+2.275
I
Token I
Feature activation+1.253
don
Token don
Feature activation+0.668
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.146
know
Token know
Feature activation+0.000
s
Tokens
Feature activation+0.000
these
Token these
Feature activation+0.000
days
Token days
Feature activation+0.000
,
Token,
Feature activation+0.031
but
Token but
Feature activation+1.280
he
Token he
Feature activation+1.083
started
Token started
Feature activation+0.266
changing
Token changing
Feature activation+0.000
the
Token the
Feature activation+0.000
business
Token business
Feature activation+0.000
when
Token when
Feature activation+0.000
ose
Tokenose
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
both
Token both
Feature activation+0.000
recently
Token recently
Feature activation+0.000
and
Token and
Feature activation+1.173
historically
Token historically
Feature activation+0.000
)
Token)
Feature activation+0.000
the
Token the
Feature activation+0.000
fans
Token fans
Feature activation+0.000
there
Token there
Feature activation+0.000
laws
Token laws
Feature activation+0.000
that
Token that
Feature activation+0.000
still
Token still
Feature activation+0.000
stand
Token stand
Feature activation+0.000
today
Token today
Feature activation+0.000
are
Token are
Feature activation+1.195
based
Token based
Feature activation+0.205
on
Token on
Feature activation+0.050
ancient
Token ancient
Feature activation+0.000
rulings
Token rulings
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 0.500 - 0.999
CONTAINS 0.026%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
further
Token further
Feature activation+0.000
back
Token back
Feature activation+0.590
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
1897
Token 1897
Feature activation+0.000
,
Token,
Feature activation+0.000
Scientific
Token Scientific
Feature activation+0.000
less
Token less
Feature activation+0.000
than
Token than
Feature activation+0.000
10
Token 10
Feature activation+0.000
percent
Token percent
Feature activation+0.000
volatility
Token volatility
Feature activation+0.000
.
Token.
Feature activation+0.645
While
Token While
Feature activation+0.000
the
Token the
Feature activation+0.000
power
Token power
Feature activation+0.000
station
Token station
Feature activation+0.000
reportedly
Token reportedly
Feature activation+0.000
now
Token now
Feature activation+0.000
.
Token.
Feature activation+0.920
Why
Token Why
Feature activation+1.779
is
Token is
Feature activation+0.304
everyone
Token everyone
Feature activation+0.000
asking
Token asking
Feature activation+0.596
me
Token me
Feature activation+0.000
about
Token about
Feature activation+0.211
it
Token it
Feature activation+3.288
?
Token?
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
most
Token most
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
defaults
Token defaults
Feature activation+0.000
are
Token are
Feature activation+0.000
fine
Token fine
Feature activation+0.557
for
Token for
Feature activation+1.131
us
Token us
Feature activation+0.000
.
Token.
Feature activation+0.144
I
Token I
Feature activation+0.417
will
Token will
Feature activation+1.516
are
Token are
Feature activation+0.000
widely
Token widely
Feature activation+0.000
no
Token no
Feature activation+0.000
longer
Token longer
Feature activation+0.000
Christian
Token Christian
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.508
but
Token but
Feature activation+0.385
Masonic
Token Masonic
Feature activation+0.000
Lucifer
Token Lucifer
Feature activation+0.000
ians
Tokenians
Feature activation+0.514
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.500
CONTAINS 99.955%

As
Token As
Feature activation+0.000
a
Token a
Feature activation+0.000
result
Token result
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
most
Token most
Feature activation+0.000
likely
Token likely
Feature activation+0.000
cannot
Token cannot
Feature activation+0.000
make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
September
Token September
Feature activation+0.000
70
Token 70
Feature activation+0.000
to
Token to
Feature activation+0.000
80
Token 80
Feature activation+0.000
percent
Token percent
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
De
Token De
Feature activation+0.000
ird
Tokenird
Feature activation+0.000
re
Tokenre
Feature activation+0.000
Mac
Token Mac
Feature activation+0.000
Man
TokenMan
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
moving
Token moving
Feature activation+0.000
car
Token car
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
the
Token the
Feature activation+0.000
fun
Token fun
Feature activation+0.000
was
Token was
Feature activation+0.000
produce
Token produce
Feature activation+0.000
sluggish
Token sluggish
Feature activation+0.000
modifications
Token modifications
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
ultimate
Token ultimate
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
these
Token these
Feature activation+0.000
variations
Token variations
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
gave
Token gave
Feature activation+0.000
elaborate
Token elaborate
Feature activation+0.000
speeches
Token speeches
Feature activation+0.000
,
Token,
Feature activation+0.000
Rahul
Token Rahul
Feature activation+0.000
,
Token,
Feature activation+0.000
dressed
Token dressed
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
trademark
Token trademark
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 H8.8: (feature 10464)

TOP ACTIVATIONS
MAX = 4.846

that
Token that
Feature activation+0.000
accounted
Token accounted
Feature activation+0.000
for
Token for
Feature activation+0.000
42
Token 42
Feature activation+0.000
of
Token of
Feature activation+4.826
the
Token the
Feature activation+4.846
78
Token 78
Feature activation+0.090
(
Token (
Feature activation+0.327
53
Token53
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
group
Token group
Feature activation+0.000
that
Token that
Feature activation+0.000
accounted
Token accounted
Feature activation+0.000
for
Token for
Feature activation+0.000
42
Token 42
Feature activation+0.000
of
Token of
Feature activation+4.826
the
Token the
Feature activation+4.846
78
Token 78
Feature activation+0.090
(
Token (
Feature activation+0.327
53
Token53
Feature activation+0.000
.
Token.
Feature activation+0.000
measure
Token measure
Feature activation+0.000
also
Token also
Feature activation+0.000
failed
Token failed
Feature activation+0.000
,
Token,
Feature activation+0.000
52
Token 52
Feature activation+0.113
to
Token to
Feature activation+3.951
48
Token 48
Feature activation+0.041
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
a
Token a
Feature activation+0.000
hospital
Token hospital
Feature activation+0.000
within
Token within
Feature activation+0.000
30
Token 30
Feature activation+0.000
miles
Token miles
Feature activation+0.000
(
Token (
Feature activation+3.818
48
Token48
Feature activation+0.000
k
Token k
Feature activation+0.000
ms
Tokenms
Feature activation+0.000
)
Token)
Feature activation+0.000
of
Token of
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
R
TokenR
Feature activation+0.000
ough
Tokenough
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
50
Token 50
Feature activation+0.000
to
Token to
Feature activation+3.634
60
Token 60
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
energy
Token energy
Feature activation+0.000
James
Token James
Feature activation+0.000
had
Token had
Feature activation+0.000
played
Token played
Feature activation+0.000
33
Token 33
Feature activation+0.000
of
Token of
Feature activation+2.485
the
Token the
Feature activation+3.500
40
Token 40
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.002
game
Token game
Feature activation+0.000
wounded
Token wounded
Feature activation+0.000
in
Token in
Feature activation+0.000
T
Token T
Feature activation+0.000
anta
Tokenanta
Feature activation+0.000
and
Token and
Feature activation+0.197
another
Token another
Feature activation+3.367
40
Token 40
Feature activation+0.381
wounded
Token wounded
Feature activation+0.000
in
Token in
Feature activation+0.000
Alexandria
Token Alexandria
Feature activation+0.000
,
Token,
Feature activation+0.000
playoff
Token playoff
Feature activation+0.000
games
Token games
Feature activation+0.000
he
Token he
Feature activation+0.000
won
Token won
Feature activation+0.000
71
Token 71
Feature activation+0.000
of
Token of
Feature activation+3.303
them
Token them
Feature activation+0.000
with
Token with
Feature activation+0.000
an
Token an
Feature activation+0.000
astounding
Token astounding
Feature activation+0.000
2
Token 2
Feature activation+0.000
son
Tokenson
Feature activation+0.000
has
Token has
Feature activation+0.000
made
Token made
Feature activation+0.000
30
Token 30
Feature activation+0.000
of
Token of
Feature activation+1.103
the
Token the
Feature activation+3.297
department
Token department
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.480
70
Token 70
Feature activation+0.000
will
Token will
Feature activation+0.000
throw
Token throw
Feature activation+0.000
anywhere
Token anywhere
Feature activation+0.000
from
Token from
Feature activation+0.000
92
Token 92
Feature activation+0.000
-
Token-
Feature activation+3.293
94
Token94
Feature activation+0.666
,
Token,
Feature activation+0.890
with
Token with
Feature activation+0.000
W
Token W
Feature activation+0.000
ahl
Tokenahl
Feature activation+0.384
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
amendment
Token amendment
Feature activation+0.000
failed
Token failed
Feature activation+0.000
54
Token 54
Feature activation+0.003
to
Token to
Feature activation+3.174
46
Token 46
Feature activation+0.000
,
Token,
Feature activation+0.198
falling
Token falling
Feature activation+0.134
short
Token short
Feature activation+0.148
of
Token of
Feature activation+0.368
at
Token at
Feature activation+0.000
times
Token times
Feature activation+0.000
,
Token,
Feature activation+0.000
moving
Token moving
Feature activation+0.000
60
Token 60
Feature activation+0.000
-
Token-
Feature activation+3.127
70
Token70
Feature activation+0.116
ft
Token ft
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
minute
Token minute
Feature activation+0.000
a
Token a
Feature activation+0.000
final
Token final
Feature activation+0.000
order
Token order
Feature activation+0.000
of
Token of
Feature activation+0.000
removal
Token removal
Feature activation+0.000
,
Token,
Feature activation+3.080
one
Token one
Feature activation+1.714
was
Token was
Feature activation+0.000
granted
Token granted
Feature activation+0.000
voluntary
Token voluntary
Feature activation+0.000
departure
Token departure
Feature activation+0.000
-
Token-
Feature activation+0.000
Sc
Token Sc
Feature activation+0.000
ored
Tokenored
Feature activation+0.000
28
Token 28
Feature activation+0.000
goals
Token goals
Feature activation+0.000
and
Token and
Feature activation+3.044
added
Token added
Feature activation+0.118
10
Token 10
Feature activation+0.000
assists
Token assists
Feature activation+0.000
during
Token during
Feature activation+0.000
his
Token his
Feature activation+0.000
shifted
Token shifted
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
40
Token 40
Feature activation+0.000
s
Tokens
Feature activation+0.000
and
Token and
Feature activation+3.030
50
Token 50
Feature activation+0.000
s
Tokens
Feature activation+0.000
to
Token to
Feature activation+0.000
include
Token include
Feature activation+0.000
more
Token more
Feature activation+0.000
increased
Token increased
Feature activation+0.000
the
Token the
Feature activation+0.000
risk
Token risk
Feature activation+0.000
by
Token by
Feature activation+0.000
70
Token 70
Feature activation+0.000
to
Token to
Feature activation+3.026
80
Token 80
Feature activation+0.000
percent
Token percent
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
De
Token De
Feature activation+0.000
cloudy
Token cloudy
Feature activation+0.000
.
Token.
Feature activation+0.000
L
Token L
Feature activation+0.000
ows
Tokenows
Feature activation+0.000
55
Token 55
Feature activation+0.183
-
Token-
Feature activation+3.002
60
Token60
Feature activation+0.200
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Saturday
TokenSaturday
Feature activation+0.000
Hat
Token Hat
Feature activation+0.000
only
Token only
Feature activation+0.000
renewed
Token renewed
Feature activation+0.000
24
Token 24
Feature activation+0.000
of
Token of
Feature activation+2.671
the
Token the
Feature activation+2.999
top
Token top
Feature activation+2.500
25
Token 25
Feature activation+0.000
deals
Token deals
Feature activation+0.000
that
Token that
Feature activation+0.000
came
Token came
Feature activation+0.000
bed
Token bed
Feature activation+0.000
for
Token for
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
40
Token 40
Feature activation+0.000
,
Token,
Feature activation+2.952
000
Token000
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
which
Token which
Feature activation+0.000
incidentally
Token incidentally
Feature activation+0.000
is
Token is
Feature activation+0.000
V
TokenV
Feature activation+0.000
oters
Tokenoters
Feature activation+0.000
raised
Token raised
Feature activation+0.000
the
Token the
Feature activation+0.000
threshold
Token threshold
Feature activation+0.000
to
Token to
Feature activation+2.926
60
Token 60
Feature activation+0.303
percent
Token percent
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+3.001
50
Token 50
Feature activation+0.000

Top DFA by src position
MAX = 5.726

a
Token a
Feature activation-0.001
Top resid features:
group
Token group
Feature activation+0.009
Top resid features:
that
Token that
Feature activation+0.020
Top resid features:
accounted
Token accounted
Feature activation+0.003
Top resid features:
for
Token for
Feature activation+0.012
Top resid features:
42
Token 42
Feature activation+5.726
Top resid features:
of
Token of
Feature activation-0.136
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
78
Token 78
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
53
Token53
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
group
Token group
Feature activation+0.013
Top resid features:
that
Token that
Feature activation+0.044
Top resid features:
accounted
Token accounted
Feature activation+0.014
Top resid features:
for
Token for
Feature activation+0.037
Top resid features:
42
Token 42
Feature activation+5.494
Top resid features:
of
Token of
Feature activation-0.007
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
78
Token 78
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
53
Token53
Feature activation+0.000
Top resid features:
That
Token That
Feature activation+0.002
Top resid features:
measure
Token measure
Feature activation-0.005
Top resid features:
also
Token also
Feature activation+0.001
Top resid features:
failed
Token failed
Feature activation+0.031
Top resid features:
,
Token,
Feature activation-0.026
Top resid features:
52
Token 52
Feature activation+4.712
Top resid features:
to
Token to
Feature activation-0.047
Top resid features:
48
Token 48
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:
affiliation
Token affiliation
Feature activation+0.002
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
hospital
Token hospital
Feature activation+0.002
Top resid features:
within
Token within
Feature activation+0.000
Top resid features:
30
Token 30
Feature activation+4.615
Top resid features:
miles
Token miles
Feature activation-0.040
Top resid features:
(
Token (
Feature activation-0.056
Top resid features:
48
Token48
Feature activation+0.000
Top resid features:
k
Token k
Feature activation+0.000
Top resid features:
ms
Tokenms
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.017
Top resid features:
Ċ
TokenĊ
Feature activation-0.039
Top resid features:
R
TokenR
Feature activation+0.018
Top resid features:
ough
Tokenough
Feature activation-0.010
Top resid features:
ly
Tokenly
Feature activation+0.020
Top resid features:
50
Token 50
Feature activation+4.672
Top resid features:
to
Token to
Feature activation-0.152
Top resid features:
60
Token 60
Feature activation+0.000
Top resid features:
percent
Token percent
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:
,
Token,
Feature activation+0.003
Top resid features:
but
Token but
Feature activation+0.003
Top resid features:
James
Token James
Feature activation-0.013
Top resid features:
had
Token had
Feature activation+0.010
Top resid features:
played
Token played
Feature activation+0.032
Top resid features:
33
Token 33
Feature activation+4.406
Top resid features:
of
Token of
Feature activation-0.205
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
40
Token 40
Feature activation+0.000
Top resid features:
minutes
Token minutes
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
At
TokenAt
Feature activation-0.002
Top resid features:
least
Token least
Feature activation+0.037
Top resid features:
78
Token 78
Feature activation+3.562
Top resid features:
people
Token people
Feature activation-0.000
Top resid features:
were
Token were
Feature activation+0.007
Top resid features:
wounded
Token wounded
Feature activation+0.078
Top resid features:
in
Token in
Feature activation+0.084
Top resid features:
T
Token T
Feature activation+0.029
Top resid features:
career
Token career
Feature activation+0.018
Top resid features:
playoff
Token playoff
Feature activation+0.012
Top resid features:
games
Token games
Feature activation+0.052
Top resid features:
he
Token he
Feature activation+0.054
Top resid features:
won
Token won
Feature activation+0.015
Top resid features:
71
Token 71
Feature activation+3.737
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
them
Token them
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
astounding
Token astounding
Feature activation+0.000
Top resid features:
Adam
Token Adam
Feature activation-0.004
Top resid features:
Jacob
Token Jacob
Feature activation-0.006
Top resid features:
son
Tokenson
Feature activation-0.002
Top resid features:
has
Token has
Feature activation+0.012
Top resid features:
made
Token made
Feature activation+0.021
Top resid features:
30
Token 30
Feature activation+3.996
Top resid features:
of
Token of
Feature activation-0.009
Top resid features:
the
Token the
Feature activation+0.046
Top resid features:
department
Token department
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:
ers
Tokeners
Feature activation-0.002
Top resid features:
will
Token will
Feature activation-0.004
Top resid features:
throw
Token throw
Feature activation-0.007
Top resid features:
anywhere
Token anywhere
Feature activation+0.007
Top resid features:
from
Token from
Feature activation-0.022
Top resid features:
92
Token 92
Feature activation+4.058
Top resid features:
-
Token-
Feature activation-0.011
Top resid features:
94
Token94
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
W
Token W
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
The
TokenThe
Feature activation-0.002
Top resid features:
amendment
Token amendment
Feature activation+0.001
Top resid features:
failed
Token failed
Feature activation+0.004
Top resid features:
54
Token 54
Feature activation+3.892
Top resid features:
to
Token to
Feature activation-0.108
Top resid features:
46
Token 46
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
falling
Token falling
Feature activation+0.000
Top resid features:
short
Token short
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
at
Token at
Feature activation+0.001
Top resid features:
times
Token times
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
moving
Token moving
Feature activation+0.108
Top resid features:
60
Token 60
Feature activation+3.460
Top resid features:
-
Token-
Feature activation-0.017
Top resid features:
70
Token70
Feature activation+0.000
Top resid features:
ft
Token ft
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
removal
Token removal
Feature activation+0.024
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
Of
Token Of
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
remaining
Token remaining
Feature activation+0.030
Top resid features:
38
Token 38
Feature activation+3.563
Top resid features:
aliens
Token aliens
Feature activation+0.014
Top resid features:
who
Token who
Feature activation-0.013
Top resid features:
have
Token have
Feature activation+0.026
Top resid features:
not
Token not
Feature activation+0.072
Top resid features:
been
Token been
Feature activation+0.093
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
Sc
Token Sc
Feature activation-0.015
Top resid features:
ored
Tokenored
Feature activation+0.079
Top resid features:
28
Token 28
Feature activation+3.558
Top resid features:
goals
Token goals
Feature activation+0.033
Top resid features:
and
Token and
Feature activation+0.012
Top resid features:
added
Token added
Feature activation+0.000
Top resid features:
10
Token 10
Feature activation+0.000
Top resid features:
assists
Token assists
Feature activation+0.000
Top resid features:
criticism
Token criticism
Feature activation-0.003
Top resid features:
also
Token also
Feature activation-0.018
Top resid features:
shifted
Token shifted
Feature activation-0.060
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
40
Token 40
Feature activation+4.140
Top resid features:
s
Tokens
Feature activation-0.277
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
50
Token 50
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
increased
Token increased
Feature activation+0.041
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
risk
Token risk
Feature activation-0.005
Top resid features:
by
Token by
Feature activation+0.011
Top resid features:
70
Token 70
Feature activation+3.997
Top resid features:
to
Token to
Feature activation-0.202
Top resid features:
80
Token 80
Feature activation+0.000
Top resid features:
percent
Token percent
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:
partly
Token partly
Feature activation+0.015
Top resid features:
cloudy
Token cloudy
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
L
Token L
Feature activation+0.017
Top resid features:
ows
Tokenows
Feature activation+0.103
Top resid features:
55
Token 55
Feature activation+3.393
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
60
Token60
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:
that
Token that
Feature activation-0.001
Top resid features:
Red
Token Red
Feature activation+0.006
Top resid features:
Hat
Token Hat
Feature activation-0.001
Top resid features:
only
Token only
Feature activation-0.005
Top resid features:
renewed
Token renewed
Feature activation+0.022
Top resid features:
24
Token 24
Feature activation+3.717
Top resid features:
of
Token of
Feature activation-0.008
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
top
Token top
Feature activation+0.000
Top resid features:
25
Token 25
Feature activation+0.000
Top resid features:
deals
Token deals
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
bed
Token bed
Feature activation-0.002
Top resid features:
for
Token for
Feature activation-0.007
Top resid features:
at
Token at
Feature activation+0.007
Top resid features:
least
Token least
Feature activation+0.091
Top resid features:
40
Token 40
Feature activation+3.533
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
000
Token000
Feature activation+0.000
Top resid features:
dollars
Token dollars
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
incidentally
Token incidentally
Feature activation+0.000
Top resid features:
than
Token than
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
current
Token current
Feature activation+0.001
Top resid features:
requirement
Token requirement
Feature activation+0.005
Top resid features:
that
Token that
Feature activation+0.006
Top resid features:
60
Token 60
Feature activation+3.545
Top resid features:
percent
Token percent
Feature activation+0.203
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
voters
Token voters
Feature activation+0.002
Top resid features:
need
Token need
Feature activation-0.005
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.03

Head 2: 0.03

Head 3: 0.07

Head 4: 0.02

Head 5: 0.05

Head 6: 0.05

Head 7: 0.03

Head 8: 0.46

Head 9: 0.05

Head 10: 0.11

Head 11: 0.07

Positive logits

653.63

683.60

713.59

703.59

723.57

743.55

613.55

663.53

563.53

463.52

443.52

633.52

473.51

593.51

573.50

403.50

733.50

533.49

433.48

773.48

Negative logits

EStreamFrame-1.98

Nanto-1.92

Scrib-1.77

:{-1.74

iosyncr-1.72

differe-1.71

rug-1.69

oppos-1.69

rice-1.66

chang-1.61

OnePlus-1.61

redress-1.60

hai-1.59

Router-1.59

Loyal-1.59

WCS-1.58

Benefits-1.57

��-1.57

hind-1.57

-1.56

INTERVAL 4.361 - 4.846
CONTAINS 0.000%

group
Token group
Feature activation+0.000
that
Token that
Feature activation+0.000
accounted
Token accounted
Feature activation+0.000
for
Token for
Feature activation+0.000
42
Token 42
Feature activation+0.000
of
Token of
Feature activation+4.826
the
Token the
Feature activation+4.846
78
Token 78
Feature activation+0.090
(
Token (
Feature activation+0.327
53
Token53
Feature activation+0.000
.
Token.
Feature activation+0.000
that
Token that
Feature activation+0.000
accounted
Token accounted
Feature activation+0.000
for
Token for
Feature activation+0.000
42
Token 42
Feature activation+0.000
of
Token of
Feature activation+4.826
the
Token the
Feature activation+4.846
78
Token 78
Feature activation+0.090
(
Token (
Feature activation+0.327
53
Token53
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000

INTERVAL 3.877 - 4.361
CONTAINS 0.000%

measure
Token measure
Feature activation+0.000
also
Token also
Feature activation+0.000
failed
Token failed
Feature activation+0.000
,
Token,
Feature activation+0.000
52
Token 52
Feature activation+0.113
to
Token to
Feature activation+3.951
48
Token 48
Feature activation+0.041
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000

INTERVAL 3.392 - 3.877
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
R
TokenR
Feature activation+0.000
ough
Tokenough
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
50
Token 50
Feature activation+0.000
to
Token to
Feature activation+3.634
60
Token 60
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
energy
Token energy
Feature activation+0.000
a
Token a
Feature activation+0.000
hospital
Token hospital
Feature activation+0.000
within
Token within
Feature activation+0.000
30
Token 30
Feature activation+0.000
miles
Token miles
Feature activation+0.000
(
Token (
Feature activation+3.818
48
Token48
Feature activation+0.000
k
Token k
Feature activation+0.000
ms
Tokenms
Feature activation+0.000
)
Token)
Feature activation+0.000
of
Token of
Feature activation+0.000
James
Token James
Feature activation+0.000
had
Token had
Feature activation+0.000
played
Token played
Feature activation+0.000
33
Token 33
Feature activation+0.000
of
Token of
Feature activation+2.485
the
Token the
Feature activation+3.500
40
Token 40
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.002
game
Token game
Feature activation+0.000

INTERVAL 2.907 - 3.392
CONTAINS 0.002%

son
Tokenson
Feature activation+0.000
has
Token has
Feature activation+0.000
made
Token made
Feature activation+0.000
30
Token 30
Feature activation+0.000
of
Token of
Feature activation+1.103
the
Token the
Feature activation+3.297
department
Token department
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.480
70
Token 70
Feature activation+0.000
shifted
Token shifted
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
40
Token 40
Feature activation+0.000
s
Tokens
Feature activation+0.000
and
Token and
Feature activation+3.030
50
Token 50
Feature activation+0.000
s
Tokens
Feature activation+0.000
to
Token to
Feature activation+0.000
include
Token include
Feature activation+0.000
more
Token more
Feature activation+0.000
a
Token a
Feature activation+0.000
final
Token final
Feature activation+0.000
order
Token order
Feature activation+0.000
of
Token of
Feature activation+0.000
removal
Token removal
Feature activation+0.000
,
Token,
Feature activation+3.080
one
Token one
Feature activation+1.714
was
Token was
Feature activation+0.000
granted
Token granted
Feature activation+0.000
voluntary
Token voluntary
Feature activation+0.000
departure
Token departure
Feature activation+0.000
bed
Token bed
Feature activation+0.000
for
Token for
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
40
Token 40
Feature activation+0.000
,
Token,
Feature activation+2.952
000
Token000
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
which
Token which
Feature activation+0.000
incidentally
Token incidentally
Feature activation+0.000
is
Token is
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
amendment
Token amendment
Feature activation+0.000
failed
Token failed
Feature activation+0.000
54
Token 54
Feature activation+0.003
to
Token to
Feature activation+3.174
46
Token 46
Feature activation+0.000
,
Token,
Feature activation+0.198
falling
Token falling
Feature activation+0.134
short
Token short
Feature activation+0.148
of
Token of
Feature activation+0.368

INTERVAL 2.423 - 2.907
CONTAINS 0.003%

netted
Token netted
Feature activation+0.000
72
Token 72
Feature activation+0.000
for
Token for
Feature activation+0.000
Bayern
Token Bayern
Feature activation+0.000
Munich
Token Munich
Feature activation+0.000
and
Token and
Feature activation+2.500
13
Token 13
Feature activation+0.320
for
Token for
Feature activation+0.000
West
Token West
Feature activation+0.000
Germany
Token Germany
Feature activation+0.000
when
Token when
Feature activation+0.000
possess
Token possess
Feature activation+0.000
the
Token the
Feature activation+0.000
football
Token football
Feature activation+0.000
in
Token in
Feature activation+0.000
overtime
Token overtime
Feature activation+0.000
,
Token,
Feature activation+2.480
22
Token 22
Feature activation+0.000
of
Token of
Feature activation+2.604
them
Token them
Feature activation+0.000
ended
Token ended
Feature activation+0.000
in
Token in
Feature activation+0.000
.
Token.
Feature activation+0.000
Bro
Token Bro
Feature activation+0.000
ome
Tokenome
Feature activation+0.000
stopped
Token stopped
Feature activation+0.000
36
Token 36
Feature activation+0.000
of
Token of
Feature activation+2.783
58
Token 58
Feature activation+0.000
shots
Token shots
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
season
Token season
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
Access
Token Access
Feature activation+0.000
Act
Token Act
Feature activation+0.000
was
Token was
Feature activation+0.000
29
Token 29
Feature activation+0.000
to
Token to
Feature activation+2.623
19
Token 19
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
voting
Token voting
Feature activation+0.000
the
Token the
Feature activation+0.000
17
Token 17
Feature activation+0.000
90
Token90
Feature activation+0.000
census
Token census
Feature activation+0.000
,
Token,
Feature activation+1.337
that
Token that
Feature activation+2.855
went
Token went
Feature activation+1.847
up
Token up
Feature activation+2.405
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 1.938 - 2.423
CONTAINS 0.007%

to
Token to
Feature activation+0.000
identify
Token identify
Feature activation+0.000
sharks
Token sharks
Feature activation+0.000
with
Token with
Feature activation+0.000
20
Token 20
Feature activation+0.000
to
Token to
Feature activation+1.939
30
Token 30
Feature activation+0.000
percent
Token percent
Feature activation+0.000
accuracy
Token accuracy
Feature activation+0.000
when
Token when
Feature activation+0.000
analyzing
Token analyzing
Feature activation+0.000
th
Tokenth
Feature activation+0.000
century
Token century
Feature activation+0.000
was
Token was
Feature activation+0.000
that
Token that
Feature activation+0.000
24
Token 24
Feature activation+0.000
to
Token to
Feature activation+2.176
42
Token 42
Feature activation+0.000
per
Token per
Feature activation+0.044
cent
Token cent
Feature activation+0.000
of
Token of
Feature activation+0.000
aboriginal
Token aboriginal
Feature activation+0.000
your
Token your
Feature activation+0.000
faith
Token faith
Feature activation+0.000
has
Token has
Feature activation+0.000
healed
Token healed
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+2.056
Go
Token Go
Feature activation+0.000
in
Token in
Feature activation+0.000
peace
Token peace
Feature activation+0.000
.
Token.
Feature activation+1.701
âĢ
TokenâĢ
Feature activation+0.000
and
Token and
Feature activation+0.000
reduce
Token reduce
Feature activation+0.000
nitrogen
Token nitrogen
Feature activation+0.000
ox
Token ox
Feature activation+0.000
ides
Tokenides
Feature activation+1.645
by
Token by
Feature activation+2.348
80
Token 80
Feature activation+0.000
percent
Token percent
Feature activation+0.000
,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.000
expanding
Token expanding
Feature activation+0.000
ability
Token ability
Feature activation+0.000
to
Token to
Feature activation+0.000
claim
Token claim
Feature activation+0.000
25
Token 25
Feature activation+0.000
of
Token of
Feature activation+1.869
their
Token their
Feature activation+2.026
last
Token last
Feature activation+1.887
30
Token 30
Feature activation+0.000
possible
Token possible
Feature activation+0.000
points
Token points
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000

INTERVAL 1.454 - 1.938
CONTAINS 0.012%

compared
Token compared
Feature activation+0.000
with
Token with
Feature activation+1.974
Clinton
Token Clinton
Feature activation+1.254
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.781
195
Token 195
Feature activation+0.642
delegates
Token delegates
Feature activation+0.278
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Check
TokenCheck
Feature activation+0.000
out
Token out
Feature activation+0.000
ca
Tokenca
Feature activation+0.000
ution
Tokenution
Feature activation+0.000
;
Token;
Feature activation+0.000
reckless
Token reckless
Feature activation+0.000
tackle
Token tackle
Feature activation+0.000
)
Token)
Feature activation+1.800
92
Token 92
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
SEA
TokenSEA
Feature activation+0.000
-
Token -
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
never
Token never
Feature activation+0.000
felt
Token felt
Feature activation+0.000
78
Token 78
Feature activation+0.251
,
Token,
Feature activation+1.534
and
Token and
Feature activation+0.420
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
feel
Token feel
Feature activation+1.694
the
Token the
Feature activation+0.350
22
Token 22
Feature activation+0.740
,
Token,
Feature activation+1.014
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.219
represent
Token represent
Feature activation+0.000
particular
Token particular
Feature activation+0.000
professions
Token professions
Feature activation+0.000
or
Token or
Feature activation+0.000
trades
Token trades
Feature activation+0.000
and
Token and
Feature activation+1.556
can
Token can
Feature activation+0.000
only
Token only
Feature activation+0.000
be
Token be
Feature activation+0.000
voted
Token voted
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 0.969 - 1.454
CONTAINS 0.018%

to
Token to
Feature activation+0.000
squeeze
Token squeeze
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
30
Token 30
Feature activation+0.000
-
Token-
Feature activation+1.139
minute
Tokenminute
Feature activation+0.000
lunch
Token lunch
Feature activation+0.000
by
Token by
Feature activation+0.000
12
Token 12
Feature activation+0.000
:
Token:
Feature activation+0.000
of
Token of
Feature activation+0.000
which
Token which
Feature activation+0.932
it
Token it
Feature activation+0.000
fully
Token fully
Feature activation+0.000
complied
Token complied
Feature activation+0.000
with
Token with
Feature activation+1.169
82
Token 82
Feature activation+0.000
percent
Token percent
Feature activation+0.000
;
Token;
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
school
Token school
Feature activation+0.000
.
Token.
Feature activation+0.000
Today
Token Today
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.981
has
Token has
Feature activation+1.194
reached
Token reached
Feature activation+1.640
45
Token 45
Feature activation+0.114
%
Token%
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
44
Token 44
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
veterans
Token veterans
Feature activation+0.000
as
Token as
Feature activation+0.000
opposed
Token opposed
Feature activation+1.343
to
Token to
Feature activation+2.566
John
Token John
Feature activation+0.000
F
Token F
Feature activation+0.000
.
Token.
Feature activation+0.000
Kerry
Token Kerry
Feature activation+0.410
After
Token After
Feature activation+0.000
the
Token the
Feature activation+0.000
17
Token 17
Feature activation+0.000
90
Token90
Feature activation+0.000
census
Token census
Feature activation+0.000
,
Token,
Feature activation+1.337
that
Token that
Feature activation+2.855
went
Token went
Feature activation+1.847
up
Token up
Feature activation+2.405
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000

INTERVAL 0.485 - 0.969
CONTAINS 0.039%

area
Token area
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
is
Token is
Feature activation+0.000
lets
Tokenlets
Feature activation+0.000
is
Token is
Feature activation+0.514
0
Token 0
Feature activation+0.000
.
Token.
Feature activation+0.000
18
Token18
Feature activation+0.000
75
Token75
Feature activation+0.000
54
Token54
Feature activation+0.000
club
Token club
Feature activation+0.000
,
Token,
Feature activation+0.000
scoring
Token scoring
Feature activation+0.000
11
Token 11
Feature activation+0.000
points
Token points
Feature activation+0.000
in
Token in
Feature activation+0.605
9
Token 9
Feature activation+0.000
games
Token games
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.214
a
Token a
Feature activation+0.000
:
Token:
Feature activation+0.000
43
Token 43
Feature activation+0.000
Hunter
Token Hunter
Feature activation+0.000
Joy
Token Joy
Feature activation+0.000
er
Tokener
Feature activation+0.000
,
Token,
Feature activation+0.945
25
Token 25
Feature activation+0.000
Gideon
Token Gideon
Feature activation+0.000
Aj
Token Aj
Feature activation+0.000
ag
Tokenag
Feature activation+0.000
be
Tokenbe
Feature activation+0.000
Power
Token Power
Feature activation+0.000
increased
Token increased
Feature activation+0.000
to
Token to
Feature activation+0.000
323
Token 323
Feature activation+0.000
(
Token (
Feature activation+0.179
from
Tokenfrom
Feature activation+0.720
300
Token 300
Feature activation+0.898
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Base
TokenBase
Feature activation+0.000
.
Token.
Feature activation+0.000
Samp
Token Samp
Feature activation+0.000
son
Tokenson
Feature activation+0.000
took
Token took
Feature activation+0.000
nine
Token nine
Feature activation+0.000
of
Token of
Feature activation+0.749
the
Token the
Feature activation+0.701
33
Token 33
Feature activation+0.000
points
Token points
Feature activation+0.000
available
Token available
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.000 - 0.485
CONTAINS 99.919%

18
Token18
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
to
Token to
Feature activation+0.000
$
Token $
Feature activation+0.000
30
Token30
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
in
Token in
Feature activation+0.000
India
Token India
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ms
TokenMs
Feature activation+0.000
Saunders
Token Saunders
Feature activation+0.000
added
Token added
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
new
Token new
Feature activation+0.000
action
Token action
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
case
Token case
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
limited
Token limited
Feature activation+0.000
workload
Token workload
Feature activation+0.000
s
Tokens
Feature activation+0.000
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
unexpected
Token unexpected
Feature activation+0.000
shutdown
Token shutdown
Feature activation+0.000
s
Tokens
Feature activation+0.000
on
Token on
Feature activation+0.000
iPhone
Token iPhone
Feature activation+0.000
6
Token 6
Feature activation+0.000
,
Token,
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
what
Token what
Feature activation+0.000
`
Token`
Feature activation+0.000
s
Tokens
Feature activation+0.000
happening
Token happening
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
a
Token a
Feature activation+0.000
half
Token half
Feature activation+0.000
hour
Token hour
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 H8.8: (feature 20012)

TOP ACTIVATIONS
MAX = 6.981

receive
Token receive
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
three
Token three
Feature activation+0.000
colors
Token colors
Feature activation+0.000
:
Token:
Feature activation+6.981
Ċ
TokenĊ
Feature activation+1.538
Ċ
TokenĊ
Feature activation+6.134
Select
TokenSelect
Feature activation+1.924
members
Token members
Feature activation+0.106
(
Token (
Feature activation+1.085
of
Token of
Feature activation+0.000
three
Token three
Feature activation+0.000
colors
Token colors
Feature activation+0.000
:
Token:
Feature activation+6.981
Ċ
TokenĊ
Feature activation+1.538
Ċ
TokenĊ
Feature activation+6.134
Select
TokenSelect
Feature activation+1.924
members
Token members
Feature activation+0.106
(
Token (
Feature activation+1.085
ann
Tokenann
Feature activation+0.519
ual
Tokenual
Feature activation+1.205
change
Token change
Feature activation+0.000
the
Token the
Feature activation+0.000
background
Token background
Feature activation+0.000
color
Token color
Feature activation+0.103
//
Token //
Feature activation+0.800
to
Token to
Feature activation+5.938
red
Token red
Feature activation+0.162
and
Token and
Feature activation+2.668
the
Token the
Feature activation+0.857
x
Token x
Feature activation+0.207
-
Token-
Feature activation+0.185
at
Token at
Feature activation+0.987
first
Token first
Feature activation+1.067
was
Token was
Feature activation+5.470
going
Token going
Feature activation+3.482
to
Token to
Feature activation+4.697
be
Token be
Feature activation+5.921
a
Token a
Feature activation+5.450
50
Token 50
Feature activation+1.875
s
Tokens
Feature activation+0.717
tv
Token tv
Feature activation+0.094
show
Token show
Feature activation+0.126
set
Token set
Feature activation+0.087
the
Token the
Feature activation+0.393
Fore
Token Fore
Feature activation+0.503
ground
Tokenground
Feature activation+0.705
color
Token color
Feature activation+0.608
to
Token to
Feature activation+5.616
black
Token black
Feature activation+1.278
.
Token.
Feature activation+1.152
In
Token In
Feature activation+1.325
the
Token the
Feature activation+0.977
Options
Token Options
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.936
game
Token game
Feature activation+0.918
at
Token at
Feature activation+0.987
first
Token first
Feature activation+1.067
was
Token was
Feature activation+5.470
going
Token going
Feature activation+3.482
to
Token to
Feature activation+4.697
be
Token be
Feature activation+5.921
a
Token a
Feature activation+5.450
50
Token 50
Feature activation+1.875
first
Token first
Feature activation+1.067
was
Token was
Feature activation+5.470
going
Token going
Feature activation+3.482
to
Token to
Feature activation+4.697
be
Token be
Feature activation+5.921
a
Token a
Feature activation+5.450
50
Token 50
Feature activation+1.875
s
Tokens
Feature activation+0.717
tv
Token tv
Feature activation+0.094
show
Token show
Feature activation+0.126
simulator
Token simulator
Feature activation+0.000
Comes
Token Comes
Feature activation+0.766
in
Token in
Feature activation+0.997
a
Token a
Feature activation+0.695
cool
Token cool
Feature activation+0.746
blue
Token blue
Feature activation+0.370
or
Token or
Feature activation+5.016
black
Token black
Feature activation+0.766
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.302
T
TokenT
Feature activation+0.940
game
Token game
Feature activation+0.918
at
Token at
Feature activation+0.987
first
Token first
Feature activation+1.067
was
Token was
Feature activation+5.470
going
Token going
Feature activation+3.482
to
Token to
Feature activation+4.697
be
Token be
Feature activation+5.921
a
Token a
Feature activation+5.450
50
Token 50
Feature activation+1.875
s
Tokens
Feature activation+0.717
tv
Token tv
Feature activation+0.094
a
Token a
Feature activation+1.008
particular
Token particular
Feature activation+1.180
color
Token color
Feature activation+0.377
standard
Token standard
Feature activation+0.323
,
Token,
Feature activation+0.733
like
Token like
Feature activation+4.683
Rec
Token Rec
Feature activation+1.494
.
Token.
Feature activation+0.787
709
Token709
Feature activation+0.399
(
Token (
Feature activation+2.352
HD
TokenHD
Feature activation+0.469
the
Token the
Feature activation+0.000
classic
Token classic
Feature activation+0.000
HL
Token HL
Feature activation+0.000
2
Token2
Feature activation+0.000
yellow
Token yellow
Feature activation+0.024
/
Token/
Feature activation+4.627
green
Tokengreen
Feature activation+0.836
toxic
Token toxic
Feature activation+0.609
sl
Token sl
Feature activation+0.707
udge
Tokenudge
Feature activation+0.000
must
Token must
Feature activation+0.252
edge
Token edge
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
plank
Token plank
Feature activation+0.000
(
Token (
Feature activation+4.185
red
Tokenred
Feature activation+0.000
arrow
Token arrow
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
so
Token so
Feature activation+0.000
Islam
Token Islam
Feature activation+0.000
i
Tokeni
Feature activation+0.000
Gul
Token Gul
Feature activation+0.000
b
Tokenb
Feature activation+0.000
uddin
Tokenuddin
Feature activation+0.000
(
Token (
Feature activation+4.147
dark
Tokendark
Feature activation+0.000
green
Token green
Feature activation+0.000
),
Token),
Feature activation+0.000
He
Token He
Feature activation+0.000
zb
Tokenzb
Feature activation+0.000
I
Token I
Feature activation+0.448
stained
Token stained
Feature activation+0.000
it
Token it
Feature activation+2.800
however
Token however
Feature activation+0.830
,
Token,
Feature activation+2.168
it
Token it
Feature activation+4.085
became
Token became
Feature activation+3.573
more
Token more
Feature activation+3.346
apparent
Token apparent
Feature activation+1.994
.
Token.
Feature activation+2.157
The
Token The
Feature activation+2.324
Color
TokenColor
Feature activation+0.165
=
Token =
Feature activation+1.977
U
Token U
Feature activation+0.872
IC
TokenIC
Feature activation+0.187
olor
Tokenolor
Feature activation+1.368
.
Token.
Feature activation+3.803
red
Tokenred
Feature activation+0.926
Color
TokenColor
Feature activation+0.425
()
Token()
Feature activation+0.000
//
Token //
Feature activation+1.732
for
Token for
Feature activation+1.624
,
Token,
Feature activation+0.431
with
Token with
Feature activation+3.561
pale
Token pale
Feature activation+2.624
red
Token red
Feature activation+1.919
s
Tokens
Feature activation+1.185
and
Token and
Feature activation+3.710
greens
Token greens
Feature activation+1.333
,
Token,
Feature activation+2.533
as
Token as
Feature activation+0.435
if
Token if
Feature activation+0.253
to
Token to
Feature activation+1.593
oise
Tokenoise
Feature activation+0.000
for
Token for
Feature activation+0.185
past
Token past
Feature activation+0.000
el
Tokenel
Feature activation+1.030
blue
Token blue
Feature activation+0.290
or
Token or
Feature activation+3.666
mint
Token mint
Feature activation+0.000
.
Token.
Feature activation+0.037
For
Token For
Feature activation+0.986
condition
Token condition
Feature activation+0.000
er
Tokener
Feature activation+0.000
are
Token are
Feature activation+2.529
using
Token using
Feature activation+2.987
color
Token color
Feature activation+1.111
,
Token,
Feature activation+1.028
add
Token add
Feature activation+2.674
a
Token a
Feature activation+3.642
dash
Token dash
Feature activation+1.385
of
Token of
Feature activation+3.019
food
Token food
Feature activation+1.088
coloring
Token coloring
Feature activation+0.258
to
Token to
Feature activation+1.262
the
Token the
Feature activation+1.778
Ward
Token Ward
Feature activation+0.239
robe
Tokenrobe
Feature activation+1.056
,
Token,
Feature activation+1.279
They
Token They
Feature activation+1.790
appear
Token appear
Feature activation+3.576
only
Token only
Feature activation+1.384
if
Token if
Feature activation+0.781
the
Token the
Feature activation+1.054
Sunset
Token Sunset
Feature activation+0.917
Orange
Token Orange
Feature activation+1.100
stained
Token stained
Feature activation+0.000
it
Token it
Feature activation+2.800
however
Token however
Feature activation+0.830
,
Token,
Feature activation+2.168
it
Token it
Feature activation+4.085
became
Token became
Feature activation+3.573
more
Token more
Feature activation+3.346
apparent
Token apparent
Feature activation+1.994
.
Token.
Feature activation+2.157
The
Token The
Feature activation+2.324
proper
Token proper
Feature activation+2.650

Top DFA by src position
MAX = 7.733

ll
Tokenll
Feature activation-0.037
Top resid features:
receive
Token receive
Feature activation+0.005
Top resid features:
one
Token one
Feature activation+0.003
Top resid features:
of
Token of
Feature activation-0.012
Top resid features:
three
Token three
Feature activation-0.034
Top resid features:
colors
Token colors
Feature activation+7.733
Top resid features:
:
Token:
Feature activation-0.160
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Select
TokenSelect
Feature activation+0.000
Top resid features:
members
Token members
Feature activation+0.000
Top resid features:
ll
Tokenll
Feature activation-0.051
Top resid features:
receive
Token receive
Feature activation+0.008
Top resid features:
one
Token one
Feature activation+0.004
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
three
Token three
Feature activation+0.005
Top resid features:
colors
Token colors
Feature activation+6.557
Top resid features:
:
Token:
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.058
Top resid features:
Ċ
TokenĊ
Feature activation+0.079
Top resid features:
Select
TokenSelect
Feature activation+0.000
Top resid features:
members
Token members
Feature activation+0.000
Top resid features:
animations
Token animations
Feature activation-0.010
Top resid features:
block
Token block
Feature activation+0.005
Top resid features:
change
Token change
Feature activation+0.017
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
background
Token background
Feature activation+0.094
Top resid features:
color
Token color
Feature activation+6.485
Top resid features:
//
Token //
Feature activation+0.049
Top resid features:
to
Token to
Feature activation-0.023
Top resid features:
red
Token red
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.003
Top resid features:
B
Token B
Feature activation+0.012
Top resid features:
&
Token&
Feature activation+0.004
Top resid features:
W
TokenW
Feature activation-0.012
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
color
Token color
Feature activation+6.159
Top resid features:
,
Token,
Feature activation+0.132
Top resid features:
the
Token the
Feature activation+0.028
Top resid features:
game
Token game
Feature activation+0.010
Top resid features:
at
Token at
Feature activation+0.007
Top resid features:
first
Token first
Feature activation+0.015
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
set
Token set
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
Fore
Token Fore
Feature activation-0.009
Top resid features:
ground
Tokenground
Feature activation+0.185
Top resid features:
color
Token color
Feature activation+5.668
Top resid features:
to
Token to
Feature activation-0.020
Top resid features:
black
Token black
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
In
Token In
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.007
Top resid features:
B
Token B
Feature activation+0.002
Top resid features:
&
Token&
Feature activation+0.006
Top resid features:
W
TokenW
Feature activation-0.015
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
color
Token color
Feature activation+5.771
Top resid features:
,
Token,
Feature activation+0.129
Top resid features:
the
Token the
Feature activation+0.038
Top resid features:
game
Token game
Feature activation-0.008
Top resid features:
at
Token at
Feature activation+0.007
Top resid features:
first
Token first
Feature activation-0.008
Top resid features:
from
Token from
Feature activation-0.003
Top resid features:
B
Token B
Feature activation+0.025
Top resid features:
&
Token&
Feature activation+0.007
Top resid features:
W
TokenW
Feature activation-0.015
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
color
Token color
Feature activation+5.701
Top resid features:
,
Token,
Feature activation+0.103
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
game
Token game
Feature activation+0.011
Top resid features:
at
Token at
Feature activation+0.007
Top resid features:
first
Token first
Feature activation-0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.022
Top resid features:
Comes
Token Comes
Feature activation+0.020
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.061
Top resid features:
cool
Token cool
Feature activation+0.080
Top resid features:
blue
Token blue
Feature activation+5.094
Top resid features:
or
Token or
Feature activation+0.036
Top resid features:
black
Token black
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:
from
Token from
Feature activation+0.008
Top resid features:
B
Token B
Feature activation+0.014
Top resid features:
&
Token&
Feature activation+0.002
Top resid features:
W
TokenW
Feature activation-0.006
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
color
Token color
Feature activation+4.803
Top resid features:
,
Token,
Feature activation+0.307
Top resid features:
the
Token the
Feature activation+0.043
Top resid features:
game
Token game
Feature activation-0.014
Top resid features:
at
Token at
Feature activation+0.001
Top resid features:
first
Token first
Feature activation-0.007
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
percentage
Token percentage
Feature activation+0.115
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
a
Token a
Feature activation+0.011
Top resid features:
particular
Token particular
Feature activation-0.007
Top resid features:
color
Token color
Feature activation+3.782
Top resid features:
standard
Token standard
Feature activation+0.029
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
like
Token like
Feature activation+0.010
Top resid features:
Rec
Token Rec
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.010
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
classic
Token classic
Feature activation+0.018
Top resid features:
HL
Token HL
Feature activation+0.029
Top resid features:
2
Token2
Feature activation-0.011
Top resid features:
yellow
Token yellow
Feature activation+4.931
Top resid features:
/
Token/
Feature activation+0.201
Top resid features:
green
Tokengreen
Feature activation+0.000
Top resid features:
toxic
Token toxic
Feature activation+0.000
Top resid features:
sl
Token sl
Feature activation+0.000
Top resid features:
udge
Tokenudge
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
first
Token first
Feature activation+0.001
Top resid features:
plank
Token plank
Feature activation+0.003
Top resid features:
(
Token (
Feature activation+0.006
Top resid features:
yellow
Tokenyellow
Feature activation+4.572
Top resid features:
marker
Token marker
Feature activation+0.081
Top resid features:
),
Token),
Feature activation+0.008
Top resid features:
I
Token I
Feature activation+0.004
Top resid features:
shift
Token shift
Feature activation-0.005
Top resid features:
my
Token my
Feature activation+0.003
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
i
Tokeni
Feature activation-0.001
Top resid features:
Mill
Token Mill
Feature activation-0.002
Top resid features:
i
Tokeni
Feature activation-0.002
Top resid features:
(
Token (
Feature activation+0.002
Top resid features:
red
Tokenred
Feature activation+5.493
Top resid features:
),
Token),
Feature activation-0.011
Top resid features:
He
Token He
Feature activation-0.004
Top resid features:
zb
Tokenzb
Feature activation-0.002
Top resid features:
-
Token-
Feature activation-0.004
Top resid features:
i
Tokeni
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
wood
Token wood
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.051
Top resid features:
Once
Token Once
Feature activation+0.007
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
stained
Token stained
Feature activation+4.290
Top resid features:
it
Token it
Feature activation-0.036
Top resid features:
however
Token however
Feature activation-0.026
Top resid features:
,
Token,
Feature activation-0.093
Top resid features:
it
Token it
Feature activation-0.044
Top resid features:
became
Token became
Feature activation+0.000
Top resid features:
{
Token {
Feature activation-0.008
Top resid features:
colored
Token colored
Feature activation+0.614
Top resid features:
Square
TokenSquare
Feature activation+0.038
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
background
Tokenbackground
Feature activation+0.103
Top resid features:
Color
TokenColor
Feature activation+1.980
Top resid features:
=
Token =
Feature activation+0.049
Top resid features:
U
Token U
Feature activation+0.015
Top resid features:
IC
TokenIC
Feature activation+0.012
Top resid features:
olor
Tokenolor
Feature activation+1.211
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
color
Token color
Feature activation+0.411
Top resid features:
palette
Token palette
Feature activation+0.025
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
with
Token with
Feature activation-0.002
Top resid features:
pale
Token pale
Feature activation+0.953
Top resid features:
red
Token red
Feature activation+2.685
Top resid features:
s
Tokens
Feature activation+0.055
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
greens
Token greens
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
qu
Tokenqu
Feature activation+0.005
Top resid features:
oise
Tokenoise
Feature activation+0.673
Top resid features:
for
Token for
Feature activation+0.011
Top resid features:
past
Token past
Feature activation-0.043
Top resid features:
el
Tokenel
Feature activation+0.545
Top resid features:
blue
Token blue
Feature activation+2.976
Top resid features:
or
Token or
Feature activation+0.040
Top resid features:
mint
Token mint
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
For
Token For
Feature activation+0.000
Top resid features:
condition
Token condition
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.176
Top resid features:
Step
Token Step
Feature activation-0.018
Top resid features:
Three
Token Three
Feature activation-0.005
Top resid features:
|
Token |
Feature activation-0.015
Top resid features:
Add
Token Add
Feature activation-0.011
Top resid features:
Color
Token Color
Feature activation+2.131
Top resid features:
If
Token If
Feature activation+0.037
Top resid features:
you
Token you
Feature activation+0.008
Top resid features:
are
Token are
Feature activation+0.011
Top resid features:
using
Token using
Feature activation+0.020
Top resid features:
color
Token color
Feature activation+1.832
Top resid features:
:
Token:
Feature activation-0.003
Top resid features:
items
Token items
Feature activation-0.011
Top resid features:
colored
Token colored
Feature activation+1.414
Top resid features:
in
Token in
Feature activation+0.079
Top resid features:
Sunset
Token Sunset
Feature activation+0.184
Top resid features:
Orange
Token Orange
Feature activation+1.896
Top resid features:
,
Token,
Feature activation+0.036
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
example
Token example
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
aren
Token aren
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
wood
Token wood
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.054
Top resid features:
Once
Token Once
Feature activation+0.010
Top resid features:
I
Token I
Feature activation+0.004
Top resid features:
stained
Token stained
Feature activation+2.164
Top resid features:
it
Token it
Feature activation+0.102
Top resid features:
however
Token however
Feature activation-0.012
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
it
Token it
Feature activation-0.011
Top resid features:
became
Token became
Feature activation+0.014
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.01

Head 2: 0.04

Head 3: 0.08

Head 4: 0.04

Head 5: 0.05

Head 6: 0.03

Head 7: 0.04

Head 8: 0.45

Head 9: 0.07

Head 10: 0.11

Head 11: 0.04

Positive logits

colors5.30

color5.15

colour5.05

colours5.04

Colors4.67

colored4.63

coloured4.52

coloring4.40

Color4.40

tint4.40

Colour4.36

Color4.36

pigment4.26

dye4.25

RGB4.21

hue4.03

colour4.01

rainbow3.97

palette3.97

shades3.94

Negative logits

Reviewer-2.04

Jake-2.02

hub-2.01

ository-2.01

lov-1.95

Spoon-1.93

iatus-1.91

ibling-1.91

FML-1.88

Pod-1.88

Cato-1.88

conom-1.86

Ham-1.85

Chambers-1.84

userc-1.84

Hastings-1.83

abo-1.81

pload-1.81

-1.79

\\\\\\\\-1.79

INTERVAL 6.283 - 6.981
CONTAINS 0.000%

receive
Token receive
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
three
Token three
Feature activation+0.000
colors
Token colors
Feature activation+0.000
:
Token:
Feature activation+6.981
Ċ
TokenĊ
Feature activation+1.538
Ċ
TokenĊ
Feature activation+6.134
Select
TokenSelect
Feature activation+1.924
members
Token members
Feature activation+0.106
(
Token (
Feature activation+1.085

INTERVAL 5.585 - 6.283
CONTAINS 0.000%

of
Token of
Feature activation+0.000
three
Token three
Feature activation+0.000
colors
Token colors
Feature activation+0.000
:
Token:
Feature activation+6.981
Ċ
TokenĊ
Feature activation+1.538
Ċ
TokenĊ
Feature activation+6.134
Select
TokenSelect
Feature activation+1.924
members
Token members
Feature activation+0.106
(
Token (
Feature activation+1.085
ann
Tokenann
Feature activation+0.519
ual
Tokenual
Feature activation+1.205
set
Token set
Feature activation+0.087
the
Token the
Feature activation+0.393
Fore
Token Fore
Feature activation+0.503
ground
Tokenground
Feature activation+0.705
color
Token color
Feature activation+0.608
to
Token to
Feature activation+5.616
black
Token black
Feature activation+1.278
.
Token.
Feature activation+1.152
In
Token In
Feature activation+1.325
the
Token the
Feature activation+0.977
Options
Token Options
Feature activation+0.000
change
Token change
Feature activation+0.000
the
Token the
Feature activation+0.000
background
Token background
Feature activation+0.000
color
Token color
Feature activation+0.103
//
Token //
Feature activation+0.800
to
Token to
Feature activation+5.938
red
Token red
Feature activation+0.162
and
Token and
Feature activation+2.668
the
Token the
Feature activation+0.857
x
Token x
Feature activation+0.207
-
Token-
Feature activation+0.185
at
Token at
Feature activation+0.987
first
Token first
Feature activation+1.067
was
Token was
Feature activation+5.470
going
Token going
Feature activation+3.482
to
Token to
Feature activation+4.697
be
Token be
Feature activation+5.921
a
Token a
Feature activation+5.450
50
Token 50
Feature activation+1.875
s
Tokens
Feature activation+0.717
tv
Token tv
Feature activation+0.094
show
Token show
Feature activation+0.126

INTERVAL 4.887 - 5.585
CONTAINS 0.000%

Comes
Token Comes
Feature activation+0.766
in
Token in
Feature activation+0.997
a
Token a
Feature activation+0.695
cool
Token cool
Feature activation+0.746
blue
Token blue
Feature activation+0.370
or
Token or
Feature activation+5.016
black
Token black
Feature activation+0.766
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.302
T
TokenT
Feature activation+0.940
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.936
game
Token game
Feature activation+0.918
at
Token at
Feature activation+0.987
first
Token first
Feature activation+1.067
was
Token was
Feature activation+5.470
going
Token going
Feature activation+3.482
to
Token to
Feature activation+4.697
be
Token be
Feature activation+5.921
a
Token a
Feature activation+5.450
50
Token 50
Feature activation+1.875
first
Token first
Feature activation+1.067
was
Token was
Feature activation+5.470
going
Token going
Feature activation+3.482
to
Token to
Feature activation+4.697
be
Token be
Feature activation+5.921
a
Token a
Feature activation+5.450
50
Token 50
Feature activation+1.875
s
Tokens
Feature activation+0.717
tv
Token tv
Feature activation+0.094
show
Token show
Feature activation+0.126
simulator
Token simulator
Feature activation+0.000

INTERVAL 4.189 - 4.887
CONTAINS 0.000%

game
Token game
Feature activation+0.918
at
Token at
Feature activation+0.987
first
Token first
Feature activation+1.067
was
Token was
Feature activation+5.470
going
Token going
Feature activation+3.482
to
Token to
Feature activation+4.697
be
Token be
Feature activation+5.921
a
Token a
Feature activation+5.450
50
Token 50
Feature activation+1.875
s
Tokens
Feature activation+0.717
tv
Token tv
Feature activation+0.094
a
Token a
Feature activation+1.008
particular
Token particular
Feature activation+1.180
color
Token color
Feature activation+0.377
standard
Token standard
Feature activation+0.323
,
Token,
Feature activation+0.733
like
Token like
Feature activation+4.683
Rec
Token Rec
Feature activation+1.494
.
Token.
Feature activation+0.787
709
Token709
Feature activation+0.399
(
Token (
Feature activation+2.352
HD
TokenHD
Feature activation+0.469
the
Token the
Feature activation+0.000
classic
Token classic
Feature activation+0.000
HL
Token HL
Feature activation+0.000
2
Token2
Feature activation+0.000
yellow
Token yellow
Feature activation+0.024
/
Token/
Feature activation+4.627
green
Tokengreen
Feature activation+0.836
toxic
Token toxic
Feature activation+0.609
sl
Token sl
Feature activation+0.707
udge
Tokenudge
Feature activation+0.000
must
Token must
Feature activation+0.252

INTERVAL 3.491 - 4.189
CONTAINS 0.001%

are
Token are
Feature activation+2.529
using
Token using
Feature activation+2.987
color
Token color
Feature activation+1.111
,
Token,
Feature activation+1.028
add
Token add
Feature activation+2.674
a
Token a
Feature activation+3.642
dash
Token dash
Feature activation+1.385
of
Token of
Feature activation+3.019
food
Token food
Feature activation+1.088
coloring
Token coloring
Feature activation+0.258
to
Token to
Feature activation+1.262
-
Token-
Feature activation+0.358
esque
Tokenesque
Feature activation+1.630
color
Token color
Feature activation+0.324
palette
Token palette
Feature activation+0.000
,
Token,
Feature activation+0.431
with
Token with
Feature activation+3.561
pale
Token pale
Feature activation+2.624
red
Token red
Feature activation+1.919
s
Tokens
Feature activation+1.185
and
Token and
Feature activation+3.710
greens
Token greens
Feature activation+1.333
Islam
Token Islam
Feature activation+0.000
i
Tokeni
Feature activation+0.000
Gul
Token Gul
Feature activation+0.000
b
Tokenb
Feature activation+0.000
uddin
Tokenuddin
Feature activation+0.000
(
Token (
Feature activation+4.147
dark
Tokendark
Feature activation+0.000
green
Token green
Feature activation+0.000
),
Token),
Feature activation+0.000
He
Token He
Feature activation+0.000
zb
Tokenzb
Feature activation+0.000
paint
Token paint
Feature activation+0.000
applied
Token applied
Feature activation+0.206
to
Token to
Feature activation+0.603
the
Token the
Feature activation+0.153
roofs
Token roofs
Feature activation+0.137
to
Token to
Feature activation+3.561
mimic
Token mimic
Feature activation+1.794
dirty
Token dirty
Feature activation+0.293
glass
Token glass
Feature activation+0.054
ceilings
Token ceilings
Feature activation+0.138
.
Token.
Feature activation+0.000
edge
Token edge
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
plank
Token plank
Feature activation+0.000
(
Token (
Feature activation+4.185
red
Tokenred
Feature activation+0.000
arrow
Token arrow
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
so
Token so
Feature activation+0.000

INTERVAL 2.792 - 3.491
CONTAINS 0.003%

use
Token use
Feature activation+0.000
nature
Token nature
Feature activation+0.000
-
Token-
Feature activation+0.000
related
Tokenrelated
Feature activation+0.000
colors
Token colors
Feature activation+0.000
like
Token like
Feature activation+3.355
green
Token green
Feature activation+0.621
,
Token,
Feature activation+1.712
brown
Token brown
Feature activation+0.521
and
Token and
Feature activation+2.510
blue
Token blue
Feature activation+0.144
els
Tokenels
Feature activation+0.203
in
Token in
Feature activation+0.421
blue
Token blue
Feature activation+0.376
,
Token,
Feature activation+2.856
red
Token red
Feature activation+0.998
,
Token,
Feature activation+2.897
purple
Token purple
Feature activation+0.675
and
Token and
Feature activation+2.574
yellow
Token yellow
Feature activation+0.282
!
Token!
Feature activation+0.264
Ċ
TokenĊ
Feature activation+0.000
i
Tokeni
Feature activation+0.000
Islam
Token Islam
Feature activation+0.000
i
Tokeni
Feature activation+0.000
Kh
Token Kh
Feature activation+0.000
alis
Tokenalis
Feature activation+0.000
(
Token (
Feature activation+3.300
white
Tokenwhite
Feature activation+0.654
-
Token-
Feature activation+1.091
green
Tokengreen
Feature activation+0.170
striped
Token striped
Feature activation+0.000
),
Token),
Feature activation+0.000
ages
Token ages
Feature activation+0.000
:
Token:
Feature activation+1.952
Cats
Token Cats
Feature activation+1.724
do
Token do
Feature activation+1.341
start
Token start
Feature activation+2.219
going
Token going
Feature activation+3.136
gray
Token gray
Feature activation+0.455
with
Token with
Feature activation+0.364
age
Token age
Feature activation+0.000
,
Token,
Feature activation+0.856
but
Token but
Feature activation+0.550
really
Token really
Feature activation+0.582
unfair
Token unfair
Feature activation+0.000
to
Token to
Feature activation+0.665
make
Token make
Feature activation+1.015
your
Token your
Feature activation+0.904
players
Token players
Feature activation+3.034
be
Token be
Feature activation+1.871
white
Token white
Feature activation+0.495
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
hi
Tokenhi
Feature activation+0.000

INTERVAL 2.094 - 2.792
CONTAINS 0.006%

robe
Tokenrobe
Feature activation+1.410
problems
Token problems
Feature activation+0.000
:
Token:
Feature activation+2.612
items
Token items
Feature activation+1.132
colored
Token colored
Feature activation+2.119
in
Token in
Feature activation+2.166
Sunset
Token Sunset
Feature activation+0.731
Orange
Token Orange
Feature activation+1.374
,
Token,
Feature activation+1.750
for
Token for
Feature activation+0.921
example
Token example
Feature activation+0.876
background
Token background
Feature activation+0.000
color
Token color
Feature activation+0.103
//
Token //
Feature activation+0.800
to
Token to
Feature activation+5.938
red
Token red
Feature activation+0.162
and
Token and
Feature activation+2.668
the
Token the
Feature activation+0.857
x
Token x
Feature activation+0.207
-
Token-
Feature activation+0.185
position
Tokenposition
Feature activation+0.000
of
Token of
Feature activation+0.000
esque
Tokenesque
Feature activation+1.630
color
Token color
Feature activation+0.324
palette
Token palette
Feature activation+0.000
,
Token,
Feature activation+0.431
with
Token with
Feature activation+3.561
pale
Token pale
Feature activation+2.624
red
Token red
Feature activation+1.919
s
Tokens
Feature activation+1.185
and
Token and
Feature activation+3.710
greens
Token greens
Feature activation+1.333
,
Token,
Feature activation+2.533
color
Token color
Feature activation+0.122
,
Token,
Feature activation+0.795
meaning
Token meaning
Feature activation+1.364
that
Token that
Feature activation+1.486
players
Token players
Feature activation+1.188
could
Token could
Feature activation+2.508
sport
Token sport
Feature activation+1.609
a
Token a
Feature activation+1.394
darker
Token darker
Feature activation+1.337
skin
Token skin
Feature activation+0.396
color
Token color
Feature activation+0.266
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.859
get
Token get
Feature activation+0.397
on
Token on
Feature activation+1.090
the
Token the
Feature activation+2.141
inside
Token inside
Feature activation+0.992
of
Token of
Feature activation+1.444
the
Token the
Feature activation+1.026
light
Token light
Feature activation+0.000
pipe
Token pipe
Feature activation+0.973

INTERVAL 1.396 - 2.094
CONTAINS 0.016%

B
Token B
Feature activation+0.000
TS
TokenTS
Feature activation+0.000
video
Token video
Feature activation+0.000
colours
Token colours
Feature activation+0.000
look
Token look
Feature activation+2.225
really
Token really
Feature activation+1.819
nice
Token nice
Feature activation+0.831
from
Token from
Feature activation+2.056
the
Token the
Feature activation+1.537
GH
Token GH
Feature activation+0.000
5
Token5
Feature activation+0.146
the
Token the
Feature activation+0.000
light
Token light
Feature activation+0.000
leave
Token leave
Feature activation+0.000
his
Token his
Feature activation+0.111
mother
Token mother
Feature activation+0.177
's
Token's
Feature activation+1.789
eyes
Token eyes
Feature activation+0.000
as
Token as
Feature activation+0.000
she
Token she
Feature activation+0.000
saw
Token saw
Feature activation+0.000
her
Token her
Feature activation+0.000
turned
Token turned
Feature activation+0.000
dark
Token dark
Feature activation+0.000
blue
Token blue
Feature activation+0.000
and
Token and
Feature activation+1.071
later
Token later
Feature activation+1.484
into
Token into
Feature activation+2.047
purple
Token purple
Feature activation+0.000
.
Token.
Feature activation+0.000
What
Token What
Feature activation+0.000
happened
Token happened
Feature activation+0.000
a
Token a
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.606
fur
Token fur
Feature activation+0.360
is
Token is
Feature activation+0.864
a
Token a
Feature activation+1.596
dark
Token dark
Feature activation+1.365
,
Token,
Feature activation+1.006
solid
Token solid
Feature activation+1.153
color
Token color
Feature activation+0.300
.
Token.
Feature activation+0.882
colors
Token colors
Feature activation+0.202
a
Token a
Feature activation+2.002
given
Token given
Feature activation+1.769
display
Token display
Feature activation+0.516
can
Token can
Feature activation+1.895
produce
Token produce
Feature activation+1.544
,
Token,
Feature activation+0.737
and
Token and
Feature activation+0.402
is
Token is
Feature activation+0.000
usually
Token usually
Feature activation+0.318
expressed
Token expressed
Feature activation+0.227

INTERVAL 0.698 - 1.396
CONTAINS 0.061%

If
Token If
Feature activation+1.354
you
Token you
Feature activation+1.285
are
Token are
Feature activation+2.529
using
Token using
Feature activation+2.987
color
Token color
Feature activation+1.111
,
Token,
Feature activation+1.028
add
Token add
Feature activation+2.674
a
Token a
Feature activation+3.642
dash
Token dash
Feature activation+1.385
of
Token of
Feature activation+3.019
food
Token food
Feature activation+1.088
.
Token.
Feature activation+0.341
A
Token A
Feature activation+0.784
slightly
Token slightly
Feature activation+1.169
off
Token off
Feature activation+0.795
-
Token-
Feature activation+0.669
white
Tokenwhite
Feature activation+0.810
head
Token head
Feature activation+0.771
of
Token of
Feature activation+0.166
a
Token a
Feature activation+0.148
finger
Token finger
Feature activation+0.000
stands
Token stands
Feature activation+0.240
comes
Token comes
Feature activation+0.192
in
Token in
Feature activation+0.000
America
Token America
Feature activation+0.000
tone
Token tone
Feature activation+0.901
and
Token and
Feature activation+0.905
features
Token features
Feature activation+1.022
arts
Token arts
Feature activation+0.000
y
Tokeny
Feature activation+0.812
eyel
Token eyel
Feature activation+0.049
iner
Tokeniner
Feature activation+0.157
and
Token and
Feature activation+1.176
sublime
Token sublime
Feature activation+0.000
shades
Token shades
Feature activation+0.370
of
Token of
Feature activation+1.474
cel
Token cel
Feature activation+0.860
ery
Tokenery
Feature activation+1.547
green
Token green
Feature activation+0.997
,
Token,
Feature activation+1.255
and
Token and
Feature activation+1.032
c
Token c
Feature activation+0.462
uffed
Tokenuffed
Feature activation+0.089
or
Token or
Feature activation+0.000
good
Token good
Feature activation+0.323
job
Token job
Feature activation+0.707
as
Token as
Feature activation+0.557
long
Token long
Feature activation+0.520
as
Token as
Feature activation+0.612
it
Token it
Feature activation+0.866
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.032
s
Tokens
Feature activation+0.769
mostly
Token mostly
Feature activation+0.800
white
Token white
Feature activation+0.334

INTERVAL 0.000 - 0.698
CONTAINS 99.911%

survey
Token survey
Feature activation+0.000
with
Token with
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
poll
Token poll
Feature activation+0.000
ster
Tokenster
Feature activation+0.000
Bill
Token Bill
Feature activation+0.000
McInt
Token McInt
Feature activation+0.000
ur
Tokenur
Feature activation+0.000
ff
Tokenff
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Generally
TokenGenerally
Feature activation+0.000
after
Token after
Feature activation+0.000
an
Token an
Feature activation+0.000
attack
Token attack
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
kind
Token kind
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
have
Token have
Feature activation+0.000
exaggerated
Token exaggerated
Feature activation+0.000
the
Token the
Feature activation+0.000
recovery
Token recovery
Feature activation+0.000
from
Token from
Feature activation+0.000
recession
Token recession
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
estimate
Token estimate
Feature activation+0.000
which
Token which
Feature activation+0.000
would
Token would
Feature activation+0.000
open
Token open
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
entire
Token entire
Feature activation+0.000
Act
Token Act
Feature activation+0.000
to
Token to
Feature activation+0.000
revision
Token revision
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
them
Token them
Feature activation+0.000
together
Token together
Feature activation+0.000
directly
Token directly
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
revolutionary
Token revolutionary
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
essence
Token essence
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
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 H8.8: (feature 11837)

TOP ACTIVATIONS
MAX = 4.221

with
Token with
Feature activation+0.000
twin
Token twin
Feature activation+0.000
towers
Token towers
Feature activation+0.000
of
Token of
Feature activation+0.000
17
Token 17
Feature activation+0.000
and
Token and
Feature activation+4.221
34
Token 34
Feature activation+0.000
store
Token store
Feature activation+0.000
ys
Tokenys
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
cent
Token cent
Feature activation+0.000
,
Token,
Feature activation+0.000
19
Token 19
Feature activation+0.000
times
Token times
Feature activation+0.028
out
Token out
Feature activation+0.000
of
Token of
Feature activation+3.670
20
Token 20
Feature activation+0.506
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
is
Token is
Feature activation+0.000
closing
Token closing
Feature activation+0.000
14
Token 14
Feature activation+0.000
of
Token of
Feature activation+3.649
its
Token its
Feature activation+1.611
7
Token 7
Feature activation+0.240
90
Token90
Feature activation+0.000
stores
Token stores
Feature activation+0.000
across
Token across
Feature activation+0.000
model
Token model
Feature activation+0.000
and
Token and
Feature activation+0.409
$
Token $
Feature activation+0.000
300
Token300
Feature activation+0.000
for
Token for
Feature activation+0.447
the
Token the
Feature activation+3.646
32
Token 32
Feature activation+0.000
GB
TokenGB
Feature activation+0.000
variant
Token variant
Feature activation+0.000
in
Token in
Feature activation+0.000
China
Token China
Feature activation+0.000
Almost
Token Almost
Feature activation+0.000
half
Token half
Feature activation+0.000
,
Token,
Feature activation+0.000
17
Token 17
Feature activation+0.000
out
Token out
Feature activation+0.218
of
Token of
Feature activation+3.412
the
Token the
Feature activation+2.254
40
Token 40
Feature activation+0.000
,
Token,
Feature activation+0.000
cities
Token cities
Feature activation+0.000
earned
Token earned
Feature activation+0.000
has
Token has
Feature activation+0.000
successfully
Token successfully
Feature activation+0.000
completed
Token completed
Feature activation+0.000
23
Token 23
Feature activation+0.000
out
Token out
Feature activation+1.262
of
Token of
Feature activation+3.357
25
Token 25
Feature activation+0.000
launches
Token launches
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
equ
Token equ
Feature activation+0.000
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
play
Token play
Feature activation+0.000
18
Token 18
Feature activation+0.000
of
Token of
Feature activation+3.209
their
Token their
Feature activation+3.346
next
Token next
Feature activation+2.842
29
Token 29
Feature activation+0.000
games
Token games
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
that
Token that
Feature activation+1.430
number
Token number
Feature activation+0.240
has
Token has
Feature activation+0.566
balloon
Token balloon
Feature activation+0.000
ed
Tokened
Feature activation+1.538
to
Token to
Feature activation+3.236
25
Token 25
Feature activation+0.000
percent
Token percent
Feature activation+0.000
.
Token.
Feature activation+0.000
Why
Token Why
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
16
Token 16
Feature activation+0.000
loans
Token loans
Feature activation+0.000
he
Token he
Feature activation+0.000
reported
Token reported
Feature activation+0.000
,
Token,
Feature activation+3.226
five
Token five
Feature activation+0.000
were
Token were
Feature activation+0.000
worth
Token worth
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
play
Token play
Feature activation+0.000
18
Token 18
Feature activation+0.000
of
Token of
Feature activation+3.209
their
Token their
Feature activation+3.346
next
Token next
Feature activation+2.842
29
Token 29
Feature activation+0.000
games
Token games
Feature activation+0.000
on
Token on
Feature activation+0.000
be
Token be
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
14
Token 14
Feature activation+0.000
metres
Token metres
Feature activation+0.000
(
Token (
Feature activation+3.189
or
Tokenor
Feature activation+0.318
46
Token 46
Feature activation+0.000
ft
Tokenft
Feature activation+0.000
long
Token long
Feature activation+0.000
)
Token)
Feature activation+0.000
final
Token final
Feature activation+0.000
stat
Token stat
Feature activation+0.000
line
Token line
Feature activation+0.000
of
Token of
Feature activation+0.000
17
Token 17
Feature activation+0.000
of
Token of
Feature activation+3.170
42
Token 42
Feature activation+0.000
for
Token for
Feature activation+0.000
185
Token 185
Feature activation+0.000
yards
Token yards
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Sens
Token Sens
Feature activation+0.000
won
Token won
Feature activation+0.000
23
Token 23
Feature activation+0.000
of
Token of
Feature activation+3.091
their
Token their
Feature activation+2.649
final
Token final
Feature activation+2.481
31
Token 31
Feature activation+0.000
games
Token games
Feature activation+0.000
to
Token to
Feature activation+0.009
are
Token are
Feature activation+0.000
increasing
Token increasing
Feature activation+0.000
from
Token from
Feature activation+0.000
15
Token 15
Feature activation+0.000
percent
Token percent
Feature activation+0.000
to
Token to
Feature activation+3.007
20
Token 20
Feature activation+0.000
percent
Token percent
Feature activation+0.000
for
Token for
Feature activation+0.000
singles
Token singles
Feature activation+0.000
earning
Token earning
Feature activation+0.000
at
Token at
Feature activation+0.000
low
Token low
Feature activation+0.000
temperatures
Token temperatures
Feature activation+0.000
for
Token for
Feature activation+0.000
12
Token 12
Feature activation+0.000
to
Token to
Feature activation+2.987
15
Token 15
Feature activation+0.000
hours
Token hours
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
temperature
Token temperature
Feature activation+0.000
by
Token by
Feature activation+0.000
double
Token double
Feature activation+0.000
digits
Token digits
Feature activation+0.000
in
Token in
Feature activation+0.000
10
Token 10
Feature activation+0.000
of
Token of
Feature activation+2.977
its
Token its
Feature activation+2.119
11
Token 11
Feature activation+0.000
losses
Token losses
Feature activation+0.000
and
Token and
Feature activation+0.000
tasting
Token tasting
Feature activation+0.000
85
Token85
Feature activation+0.000
.
Token.
Feature activation+0.000
Police
Token Police
Feature activation+0.000
said
Token said
Feature activation+0.000
16
Token 16
Feature activation+0.000
of
Token of
Feature activation+2.934
their
Token their
Feature activation+2.007
officers
Token officers
Feature activation+0.000
were
Token were
Feature activation+0.000
taken
Token taken
Feature activation+0.000
to
Token to
Feature activation+0.000
omin
Tokenomin
Feature activation+0.000
ville
Tokenville
Feature activation+0.000
posted
Token posted
Feature activation+0.000
18
Token 18
Feature activation+0.000
goals
Token goals
Feature activation+0.000
,
Token,
Feature activation+2.886
54
Token 54
Feature activation+0.000
points
Token points
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
plus
Token plus
Feature activation+0.000
step
Token step
Feature activation+0.000
father
Tokenfather
Feature activation+0.000
)
Token)
Feature activation+0.000
started
Token started
Feature activation+0.000
14
Token 14
Feature activation+0.000
of
Token of
Feature activation+2.863
15
Token 15
Feature activation+0.000
games
Token games
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
red
Token red
Feature activation+0.000
will
Token will
Feature activation+0.000
play
Token play
Feature activation+0.000
18
Token 18
Feature activation+0.000
of
Token of
Feature activation+3.209
their
Token their
Feature activation+3.346
next
Token next
Feature activation+2.842
29
Token 29
Feature activation+0.000
games
Token games
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
road
Token road
Feature activation+0.000

Top DFA by src position
MAX = 4.892

,
Token,
Feature activation+0.001
Top resid features:
with
Token with
Feature activation+0.009
Top resid features:
twin
Token twin
Feature activation-0.002
Top resid features:
towers
Token towers
Feature activation+0.043
Top resid features:
of
Token of
Feature activation+0.031
Top resid features:
17
Token 17
Feature activation+4.892
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
34
Token 34
Feature activation+0.000
Top resid features:
store
Token store
Feature activation+0.000
Top resid features:
ys
Tokenys
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
minus
Token minus
Feature activation-0.004
Top resid features:
four
Token four
Feature activation+0.091
Top resid features:
per
Token per
Feature activation-0.020
Top resid features:
cent
Token cent
Feature activation-0.020
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
19
Token 19
Feature activation+4.484
Top resid features:
times
Token times
Feature activation-0.023
Top resid features:
out
Token out
Feature activation-0.035
Top resid features:
of
Token of
Feature activation-0.059
Top resid features:
20
Token 20
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.011
Top resid features:
s
Tokens
Feature activation+0.030
Top resid features:
is
Token is
Feature activation+0.037
Top resid features:
closing
Token closing
Feature activation+0.060
Top resid features:
14
Token 14
Feature activation+4.249
Top resid features:
of
Token of
Feature activation+0.048
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
7
Token 7
Feature activation+0.000
Top resid features:
90
Token90
Feature activation+0.000
Top resid features:
stores
Token stores
Feature activation+0.000
Top resid features:
around
Token around
Feature activation-0.005
Top resid features:
$
Token $
Feature activation+0.008
Top resid features:
250
Token250
Feature activation-0.000
Top resid features:
for
Token for
Feature activation+0.025
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
16
Token 16
Feature activation+4.193
Top resid features:
GB
TokenGB
Feature activation+0.068
Top resid features:
model
Token model
Feature activation-0.061
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
$
Token $
Feature activation-0.034
Top resid features:
300
Token300
Feature activation+0.011
Top resid features:
leave
Token leave
Feature activation-0.010
Top resid features:
:
Token:
Feature activation+0.008
Top resid features:
Almost
Token Almost
Feature activation-0.000
Top resid features:
half
Token half
Feature activation-0.055
Top resid features:
,
Token,
Feature activation-0.046
Top resid features:
17
Token 17
Feature activation+3.967
Top resid features:
out
Token out
Feature activation-0.022
Top resid features:
of
Token of
Feature activation-0.022
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
40
Token 40
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
into
Token into
Feature activation+0.005
Top resid features:
space
Token space
Feature activation+0.006
Top resid features:
has
Token has
Feature activation+0.051
Top resid features:
successfully
Token successfully
Feature activation+0.015
Top resid features:
completed
Token completed
Feature activation+0.033
Top resid features:
23
Token 23
Feature activation+3.896
Top resid features:
out
Token out
Feature activation-0.022
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
25
Token 25
Feature activation+0.000
Top resid features:
launches
Token launches
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
fact
Token fact
Feature activation-0.005
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
they
Token they
Feature activation+0.004
Top resid features:
will
Token will
Feature activation+0.029
Top resid features:
play
Token play
Feature activation-0.021
Top resid features:
18
Token 18
Feature activation+4.567
Top resid features:
of
Token of
Feature activation-0.589
Top resid features:
their
Token their
Feature activation-0.015
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
29
Token 29
Feature activation+0.000
Top resid features:
games
Token games
Feature activation+0.000
Top resid features:
election
Tokenelection
Feature activation+0.001
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
1984
Token 1984
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
only
Token only
Feature activation-0.000
Top resid features:
17
Token 17
Feature activation+4.287
Top resid features:
percent
Token percent
Feature activation-0.326
Top resid features:
of
Token of
Feature activation-0.031
Top resid features:
voters
Token voters
Feature activation-0.004
Top resid features:
confessed
Token confessed
Feature activation+0.013
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.040
Top resid features:
Ċ
TokenĊ
Feature activation+0.035
Top resid features:
Ċ
TokenĊ
Feature activation+0.049
Top resid features:
Of
TokenOf
Feature activation-0.011
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
16
Token 16
Feature activation+3.657
Top resid features:
loans
Token loans
Feature activation+0.010
Top resid features:
he
Token he
Feature activation+0.002
Top resid features:
reported
Token reported
Feature activation+0.007
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
five
Token five
Feature activation+0.000
Top resid features:
fact
Token fact
Feature activation-0.007
Top resid features:
that
Token that
Feature activation+0.006
Top resid features:
they
Token they
Feature activation+0.024
Top resid features:
will
Token will
Feature activation+0.051
Top resid features:
play
Token play
Feature activation-0.064
Top resid features:
18
Token 18
Feature activation+3.777
Top resid features:
of
Token of
Feature activation-0.044
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
29
Token 29
Feature activation+0.000
Top resid features:
games
Token games
Feature activation+0.000
Top resid features:
ables
Tokenables
Feature activation+0.002
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.003
Top resid features:
up
Token up
Feature activation+0.005
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
14
Token 14
Feature activation+3.862
Top resid features:
metres
Token metres
Feature activation-0.029
Top resid features:
(
Token (
Feature activation-0.076
Top resid features:
or
Tokenor
Feature activation+0.000
Top resid features:
46
Token 46
Feature activation+0.000
Top resid features:
ft
Tokenft
Feature activation+0.000
Top resid features:
pedestrian
Token pedestrian
Feature activation-0.004
Top resid features:
final
Token final
Feature activation+0.004
Top resid features:
stat
Token stat
Feature activation+0.008
Top resid features:
line
Token line
Feature activation+0.031
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
17
Token 17
Feature activation+3.804
Top resid features:
of
Token of
Feature activation-0.028
Top resid features:
42
Token 42
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
185
Token 185
Feature activation+0.000
Top resid features:
yards
Token yards
Feature activation+0.000
Top resid features:
season
Token season
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
The
Token The
Feature activation+0.025
Top resid features:
Sens
Token Sens
Feature activation+0.011
Top resid features:
won
Token won
Feature activation-0.118
Top resid features:
23
Token 23
Feature activation+3.650
Top resid features:
of
Token of
Feature activation-0.014
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
final
Token final
Feature activation+0.000
Top resid features:
31
Token 31
Feature activation+0.000
Top resid features:
games
Token games
Feature activation+0.000
Top resid features:
tax
Token tax
Feature activation-0.006
Top resid features:
rates
Token rates
Feature activation-0.029
Top resid features:
are
Token are
Feature activation-0.011
Top resid features:
increasing
Token increasing
Feature activation-0.016
Top resid features:
from
Token from
Feature activation-0.060
Top resid features:
15
Token 15
Feature activation+4.316
Top resid features:
percent
Token percent
Feature activation-0.131
Top resid features:
to
Token to
Feature activation-0.303
Top resid features:
20
Token 20
Feature activation+0.000
Top resid features:
percent
Token percent
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
cooked
Token cooked
Feature activation+0.007
Top resid features:
at
Token at
Feature activation+0.022
Top resid features:
low
Token low
Feature activation-0.050
Top resid features:
temperatures
Token temperatures
Feature activation+0.018
Top resid features:
for
Token for
Feature activation-0.016
Top resid features:
12
Token 12
Feature activation+3.656
Top resid features:
to
Token to
Feature activation-0.023
Top resid features:
15
Token 15
Feature activation+0.000
Top resid features:
hours
Token hours
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
falling
Token falling
Feature activation-0.047
Top resid features:
by
Token by
Feature activation-0.017
Top resid features:
double
Token double
Feature activation-0.012
Top resid features:
digits
Token digits
Feature activation-0.002
Top resid features:
in
Token in
Feature activation+0.018
Top resid features:
10
Token 10
Feature activation+3.828
Top resid features:
of
Token of
Feature activation-0.032
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
11
Token 11
Feature activation+0.000
Top resid features:
losses
Token losses
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.011
Top resid features:
85
Token85
Feature activation-0.015
Top resid features:
.
Token.
Feature activation+0.075
Top resid features:
Police
Token Police
Feature activation-0.007
Top resid features:
said
Token said
Feature activation+0.070
Top resid features:
16
Token 16
Feature activation+3.377
Top resid features:
of
Token of
Feature activation-0.014
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
officers
Token officers
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
taken
Token taken
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
P
Token P
Feature activation-0.012
Top resid features:
omin
Tokenomin
Feature activation-0.006
Top resid features:
ville
Tokenville
Feature activation+0.007
Top resid features:
posted
Token posted
Feature activation+0.029
Top resid features:
18
Token 18
Feature activation+3.603
Top resid features:
goals
Token goals
Feature activation-0.070
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
54
Token 54
Feature activation+0.000
Top resid features:
points
Token points
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.002
Top resid features:
step
Token step
Feature activation+0.001
Top resid features:
father
Tokenfather
Feature activation-0.001
Top resid features:
)
Token)
Feature activation-0.014
Top resid features:
started
Token started
Feature activation+0.116
Top resid features:
14
Token 14
Feature activation+3.487
Top resid features:
of
Token of
Feature activation+0.024
Top resid features:
15
Token 15
Feature activation+0.000
Top resid features:
games
Token games
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
fact
Token fact
Feature activation-0.003
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
they
Token they
Feature activation+0.003
Top resid features:
will
Token will
Feature activation+0.015
Top resid features:
play
Token play
Feature activation-0.008
Top resid features:
18
Token 18
Feature activation+4.168
Top resid features:
of
Token of
Feature activation-0.516
Top resid features:
their
Token their
Feature activation-0.172
Top resid features:
next
Token next
Feature activation-0.059
Top resid features:
29
Token 29
Feature activation+0.000
Top resid features:
games
Token games
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.05

Head 2: 0.03

Head 3: 0.08

Head 4: 0.02

Head 5: 0.04

Head 6: 0.07

Head 7: 0.03

Head 8: 0.45

Head 9: 0.04

Head 10: 0.10

Head 11: 0.08

Positive logits

143.75

213.72

163.67

133.60

173.57

183.53

123.52

193.49

223.48

153.43

203.35

113.32

283.22

263.21

323.19

243.14

233.10

273.08

313.02

253.01

Negative logits

EStreamFrame-1.99

saint-1.84

Prometheus-1.83

-1.83

umblr-1.75

nob-1.75

Parkinson-1.74

ouf-1.72

patri-1.72

-1.72

Pegasus-1.71

meric-1.65

ivo-1.65

pudding-1.64

PP-1.63

uyomi-1.62

mob-1.62

uto-1.59

ppings-1.57

Parm-1.56

INTERVAL 3.799 - 4.221
CONTAINS 0.000%

with
Token with
Feature activation+0.000
twin
Token twin
Feature activation+0.000
towers
Token towers
Feature activation+0.000
of
Token of
Feature activation+0.000
17
Token 17
Feature activation+0.000
and
Token and
Feature activation+4.221
34
Token 34
Feature activation+0.000
store
Token store
Feature activation+0.000
ys
Tokenys
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.377 - 3.799
CONTAINS 0.001%

model
Token model
Feature activation+0.000
and
Token and
Feature activation+0.409
$
Token $
Feature activation+0.000
300
Token300
Feature activation+0.000
for
Token for
Feature activation+0.447
the
Token the
Feature activation+3.646
32
Token 32
Feature activation+0.000
GB
TokenGB
Feature activation+0.000
variant
Token variant
Feature activation+0.000
in
Token in
Feature activation+0.000
China
Token China
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
is
Token is
Feature activation+0.000
closing
Token closing
Feature activation+0.000
14
Token 14
Feature activation+0.000
of
Token of
Feature activation+3.649
its
Token its
Feature activation+1.611
7
Token 7
Feature activation+0.240
90
Token90
Feature activation+0.000
stores
Token stores
Feature activation+0.000
across
Token across
Feature activation+0.000
cent
Token cent
Feature activation+0.000
,
Token,
Feature activation+0.000
19
Token 19
Feature activation+0.000
times
Token times
Feature activation+0.028
out
Token out
Feature activation+0.000
of
Token of
Feature activation+3.670
20
Token 20
Feature activation+0.506
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Internet
Token Internet
Feature activation+0.000
Almost
Token Almost
Feature activation+0.000
half
Token half
Feature activation+0.000
,
Token,
Feature activation+0.000
17
Token 17
Feature activation+0.000
out
Token out
Feature activation+0.218
of
Token of
Feature activation+3.412
the
Token the
Feature activation+2.254
40
Token 40
Feature activation+0.000
,
Token,
Feature activation+0.000
cities
Token cities
Feature activation+0.000
earned
Token earned
Feature activation+0.000

INTERVAL 2.955 - 3.377
CONTAINS 0.001%

they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
play
Token play
Feature activation+0.000
18
Token 18
Feature activation+0.000
of
Token of
Feature activation+3.209
their
Token their
Feature activation+3.346
next
Token next
Feature activation+2.842
29
Token 29
Feature activation+0.000
games
Token games
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
by
Token by
Feature activation+0.000
double
Token double
Feature activation+0.000
digits
Token digits
Feature activation+0.000
in
Token in
Feature activation+0.000
10
Token 10
Feature activation+0.000
of
Token of
Feature activation+2.977
its
Token its
Feature activation+2.119
11
Token 11
Feature activation+0.000
losses
Token losses
Feature activation+0.000
and
Token and
Feature activation+0.000
tasting
Token tasting
Feature activation+0.000
are
Token are
Feature activation+0.000
increasing
Token increasing
Feature activation+0.000
from
Token from
Feature activation+0.000
15
Token 15
Feature activation+0.000
percent
Token percent
Feature activation+0.000
to
Token to
Feature activation+3.007
20
Token 20
Feature activation+0.000
percent
Token percent
Feature activation+0.000
for
Token for
Feature activation+0.000
singles
Token singles
Feature activation+0.000
earning
Token earning
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
play
Token play
Feature activation+0.000
18
Token 18
Feature activation+0.000
of
Token of
Feature activation+3.209
their
Token their
Feature activation+3.346
next
Token next
Feature activation+2.842
29
Token 29
Feature activation+0.000
games
Token games
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
16
Token 16
Feature activation+0.000
loans
Token loans
Feature activation+0.000
he
Token he
Feature activation+0.000
reported
Token reported
Feature activation+0.000
,
Token,
Feature activation+3.226
five
Token five
Feature activation+0.000
were
Token were
Feature activation+0.000
worth
Token worth
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000

INTERVAL 2.533 - 2.955
CONTAINS 0.003%

NDP
Token NDP
Feature activation+0.000
Leader
Token Leader
Feature activation+0.000
Greg
Token Greg
Feature activation+0.000
Sel
Token Sel
Feature activation+0.000
inger
Tokeninger
Feature activation+0.237
and
Token and
Feature activation+2.817
12
Token 12
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
supporting
Token supporting
Feature activation+0.000
Liberal
Token Liberal
Feature activation+0.000
estate
Token estate
Feature activation+0.000
recovery
Token recovery
Feature activation+0.000
will
Token will
Feature activation+0.000
take
Token take
Feature activation+0.000
10
Token 10
Feature activation+0.000
or
Token or
Feature activation+2.575
12
Token 12
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
85
Token85
Feature activation+0.000
.
Token.
Feature activation+0.000
Police
Token Police
Feature activation+0.000
said
Token said
Feature activation+0.000
16
Token 16
Feature activation+0.000
of
Token of
Feature activation+2.934
their
Token their
Feature activation+2.007
officers
Token officers
Feature activation+0.000
were
Token were
Feature activation+0.000
taken
Token taken
Feature activation+0.000
to
Token to
Feature activation+0.000
baseline
Token baseline
Feature activation+0.000
and
Token and
Feature activation+0.000
again
Token again
Feature activation+0.000
15
Token 15
Feature activation+0.000
-
Token-
Feature activation+0.611
and
Token and
Feature activation+2.637
60
Token 60
Feature activation+0.000
min
Token min
Feature activation+0.000
post
Token post
Feature activation+0.000
drink
Token drink
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
identify
Token identify
Feature activation+0.000
sharks
Token sharks
Feature activation+0.000
with
Token with
Feature activation+0.000
20
Token 20
Feature activation+0.000
to
Token to
Feature activation+2.718
30
Token 30
Feature activation+0.000
percent
Token percent
Feature activation+0.000
accuracy
Token accuracy
Feature activation+0.000
when
Token when
Feature activation+0.000
analyzing
Token analyzing
Feature activation+0.000

INTERVAL 2.111 - 2.533
CONTAINS 0.003%

and
Token and
Feature activation+0.172
July
Token July
Feature activation+0.000
6
Token 6
Feature activation+0.000
,
Token,
Feature activation+0.000
13
Token 13
Feature activation+0.000
,
Token,
Feature activation+2.360
20
Token 20
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
June
TokenJune
Feature activation+0.000
22
Token 22
Feature activation+0.000
.
Token.
Feature activation+0.000
Samp
Token Samp
Feature activation+0.000
son
Tokenson
Feature activation+0.000
took
Token took
Feature activation+0.000
nine
Token nine
Feature activation+0.000
of
Token of
Feature activation+2.491
the
Token the
Feature activation+2.256
33
Token 33
Feature activation+0.000
points
Token points
Feature activation+0.000
available
Token available
Feature activation+0.000
to
Token to
Feature activation+0.000
22
Token 22
Feature activation+0.000
land
Token land
Feature activation+0.000
,
Token,
Feature activation+0.025
as
Token as
Feature activation+0.000
opposed
Token opposed
Feature activation+0.658
to
Token to
Feature activation+2.410
the
Token the
Feature activation+0.197
Mono
Token Mono
Feature activation+0.000
B
TokenB
Feature activation+0.000
variant
Token variant
Feature activation+1.237
which
Token which
Feature activation+2.152
:
Token:
Feature activation+0.000
13
Token 13
Feature activation+0.000
.
Token.
Feature activation+0.000
6
Token6
Feature activation+0.000
m
Token m
Feature activation+0.000
(
Token (
Feature activation+2.516
45
Token45
Feature activation+0.000
ft
Token ft
Feature activation+0.000
)
Token)
Feature activation+0.000
Speed
Token Speed
Feature activation+0.000
:
Token:
Feature activation+0.000
Sens
Token Sens
Feature activation+0.000
won
Token won
Feature activation+0.000
23
Token 23
Feature activation+0.000
of
Token of
Feature activation+3.091
their
Token their
Feature activation+2.649
final
Token final
Feature activation+2.481
31
Token 31
Feature activation+0.000
games
Token games
Feature activation+0.000
to
Token to
Feature activation+0.009
vault
Token vault
Feature activation+0.000
seven
Token seven
Feature activation+0.000

INTERVAL 1.689 - 2.111
CONTAINS 0.005%

traps
Token traps
Feature activation+0.000
per
Token per
Feature activation+0.000
condition
Token condition
Feature activation+0.000
with
Token with
Feature activation+0.000
20
Token 20
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+1.853
25
Token25
Feature activation+0.000
flies
Token flies
Feature activation+0.000
in
Token in
Feature activation+0.000
each
Token each
Feature activation+0.000
trap
Token trap
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
percent
Token percent
Feature activation+0.000
,
Token,
Feature activation+0.000
down
Token down
Feature activation+0.000
from
Token from
Feature activation+1.698
9
Token 9
Feature activation+0.000
.
Token.
Feature activation+0.000
2
Token2
Feature activation+0.000
percent
Token percent
Feature activation+0.000
a
Token a
Feature activation+0.000
.
Token.
Feature activation+0.000
Police
Token Police
Feature activation+0.000
said
Token said
Feature activation+0.000
16
Token 16
Feature activation+0.000
of
Token of
Feature activation+2.934
their
Token their
Feature activation+2.007
officers
Token officers
Feature activation+0.000
were
Token were
Feature activation+0.000
taken
Token taken
Feature activation+0.000
to
Token to
Feature activation+0.000
hospital
Token hospital
Feature activation+0.000
Red
Token Red
Feature activation+0.000
Hat
Token Hat
Feature activation+0.000
only
Token only
Feature activation+0.000
renewed
Token renewed
Feature activation+0.000
24
Token 24
Feature activation+0.000
of
Token of
Feature activation+1.855
the
Token the
Feature activation+1.948
top
Token top
Feature activation+1.554
25
Token 25
Feature activation+0.000
deals
Token deals
Feature activation+0.000
that
Token that
Feature activation+0.000
and
Token and
Feature activation+0.000
unfair
Token unfair
Feature activation+0.000
competition
Token competition
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.071
22
Token22
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Make
TokenMake
Feature activation+0.000

INTERVAL 1.266 - 1.689
CONTAINS 0.010%

th
Tokenth
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2011
Token2011
Feature activation+0.000
:
Token:
Feature activation+1.412
17
Token 17
Feature activation+0.000
.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.000
%
Token%
Feature activation+0.000
(
Token (
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
built
Token built
Feature activation+0.000
up
Token up
Feature activation+0.000
6
Token 6
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+1.629
7
Token 7
Feature activation+0.000
kills
Token kills
Feature activation+0.000
/
Token/
Feature activation+0.000
st
Tokenst
Feature activation+0.000
uns
Tokenuns
Feature activation+0.099
ound
Tokenound
Feature activation+0.000
covers
Token covers
Feature activation+0.000
some
Token some
Feature activation+0.000
15
Token 15
Feature activation+0.000
acres
Token acres
Feature activation+0.000
(
Token (
Feature activation+1.364
6
Token6
Feature activation+0.000
hectares
Token hectares
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
is
Token is
Feature activation+0.000
Frozen
Token Frozen
Feature activation+0.000
in
Token in
Feature activation+0.000
Time
Token Time
Feature activation+0.000
--
Token --
Feature activation+0.000
7
Token 7
Feature activation+0.000
of
Token of
Feature activation+1.416
the
Token the
Feature activation+1.826
Worst
Token Worst
Feature activation+0.000
Blizz
Token Blizz
Feature activation+0.000
ards
Tokenards
Feature activation+0.000
To
Token To
Feature activation+0.000
only
Token only
Feature activation+0.000
renewed
Token renewed
Feature activation+0.000
24
Token 24
Feature activation+0.000
of
Token of
Feature activation+1.855
the
Token the
Feature activation+1.948
top
Token top
Feature activation+1.554
25
Token 25
Feature activation+0.000
deals
Token deals
Feature activation+0.000
that
Token that
Feature activation+0.000
came
Token came
Feature activation+0.000
up
Token up
Feature activation+0.000

INTERVAL 0.844 - 1.266
CONTAINS 0.014%

%
Token%
Feature activation+2.835
11
Token 11
Feature activation+0.000
%
Token%
Feature activation+0.000
Romney
Token Romney
Feature activation+1.633
31
Token 31
Feature activation+0.000
%
Token%
Feature activation+1.084
40
Token 40
Feature activation+0.000
%
Token%
Feature activation+0.000
Santorum
Token Santorum
Feature activation+0.000
38
Token 38
Feature activation+0.000
%
Token%
Feature activation+0.472
construction
Token construction
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.196
in
Token in
Feature activation+0.000
some
Token some
Feature activation+0.000
cases
Token cases
Feature activation+1.201
,
Token,
Feature activation+0.636
to
Token to
Feature activation+0.000
generate
Token generate
Feature activation+0.000
apartments
Token apartments
Feature activation+0.000
affordable
Token affordable
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
47
Token 47
Feature activation+0.000
.
Token.
Feature activation+0.000
Wyoming
Token Wyoming
Feature activation+0.000
:
Token:
Feature activation+1.119
17
Token 17
Feature activation+0.000
.
Token.
Feature activation+0.000
6
Token6
Feature activation+0.000
48
Token 48
Feature activation+0.000
.
Token.
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
late
Token late
Feature activation+0.000
20
Token 20
Feature activation+0.000
s
Tokens
Feature activation+0.000
and
Token and
Feature activation+1.256
early
Token early
Feature activation+1.592
30
Token 30
Feature activation+0.000
s
Tokens
Feature activation+0.000
were
Token were
Feature activation+0.000
staying
Token staying
Feature activation+0.000
HA
TokenHA
Feature activation+0.000
)
Token)
Feature activation+0.000
shows
Token shows
Feature activation+0.000
that
Token that
Feature activation+0.000
22
Token 22
Feature activation+0.000
per
Token per
Feature activation+0.847
cent
Token cent
Feature activation+0.000
of
Token of
Feature activation+0.000
renters
Token renters
Feature activation+0.000
were
Token were
Feature activation+0.000
spending
Token spending
Feature activation+0.000

INTERVAL 0.422 - 0.844
CONTAINS 0.030%

non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
quality
Tokenquality
Feature activation+0.000
temp
Token temp
Feature activation+0.000
chain
Token chain
Feature activation+0.000
gives
Token gives
Feature activation+0.615
us
Token us
Feature activation+1.895
29
Token 29
Feature activation+0.156
%
Token%
Feature activation+0.000
slower
Token slower
Feature activation+0.000
.
Token.
Feature activation+0.000
other
Token other
Feature activation+0.000
court
Token court
Feature activation+0.000
orders
Token orders
Feature activation+0.000
it
Token it
Feature activation+0.000
received
Token received
Feature activation+0.000
,
Token,
Feature activation+0.513
Amazon
Token Amazon
Feature activation+0.000
fully
Token fully
Feature activation+0.000
complied
Token complied
Feature activation+0.000
with
Token with
Feature activation+0.144
just
Token just
Feature activation+0.000
-
Token-
Feature activation+1.455
year
Tokenyear
Feature activation+0.000
age
Token age
Feature activation+0.000
limit
Token limit
Feature activation+0.000
,
Token,
Feature activation+0.693
with
Token with
Feature activation+0.777
the
Token the
Feature activation+0.162
possibility
Token possibility
Feature activation+0.199
of
Token of
Feature activation+0.954
going
Token going
Feature activation+1.022
down
Token down
Feature activation+1.453
14
Token 14
Feature activation+0.000
power
Token power
Feature activation+0.000
-
Token-
Feature activation+0.000
play
Tokenplay
Feature activation+0.000
points
Token points
Feature activation+0.000
and
Token and
Feature activation+0.596
252
Token 252
Feature activation+0.000
shots
Token shots
Feature activation+0.000
on
Token on
Feature activation+0.000
goal
Token goal
Feature activation+0.000
.
Token.
Feature activation+0.000
$
Token $
Feature activation+0.170
14
Token14
Feature activation+0.000
.
Token.
Feature activation+0.000
99
Token99
Feature activation+0.000
5
Token 5
Feature activation+0.000
11
Token 11
Feature activation+0.452
5
Token 5
Feature activation+0.354
-
Token -
Feature activation+0.000
2
Token2
Feature activation+0.000
2
Token 2
Feature activation+0.199
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.000 - 0.422
CONTAINS 99.933%

and
Token and
Feature activation+0.000
ignorance
Token ignorance
Feature activation+0.000
from
Token from
Feature activation+0.000
conservative
Token conservative
Feature activation+0.000
Christians
Token Christians
Feature activation+0.000
is
Token is
Feature activation+0.000
all
Token all
Feature activation+0.000
too
Token too
Feature activation+0.000
common
Token common
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
retreat
Token retreat
Feature activation+0.000
to
Token to
Feature activation+0.000
your
Token your
Feature activation+0.000
sick
Token sick
Feature activation+0.000
bed
Tokenbed
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+0.000
The
Token The
Feature activation+0.000
Magic
Token Magic
Feature activation+0.000
Mag
Token Mag
Feature activation+0.000
ick
Tokenick
Feature activation+0.000
,
Token,
Feature activation+0.000
complete
Token complete
Feature activation+0.000
with
Token with
Feature activation+0.000
expressions
Token expressions
Feature activation+0.000
I
Token I
Feature activation+0.000
used
Token used
Feature activation+0.000
and
Token and
Feature activation+0.000
breaking
Token breaking
Feature activation+0.000
down
Token down
Feature activation+0.000
with
Token with
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.000
Objective
Token Objective
Feature activation+0.000
-
Token-
Feature activation+0.000
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
With
TokenWith
Feature activation+0.000
every
Token every
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
arrival
Token arrival
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
social
Token social
Feature activation+0.000
media
Token media
Feature activation+0.000
expert
Token expert
Feature activation+0.000
Swan
Token Swan
Feature activation+0.000
said
Token said
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 H8.8: (feature 5311)

TOP ACTIVATIONS
MAX = 4.140

counterfe
Token counterfe
Feature activation+0.000
its
Tokenits
Feature activation+0.000
among
Token among
Feature activation+0.029
the
Token the
Feature activation+0.529
best
Token best
Feature activation+1.133
in
Token in
Feature activation+3.903
the
Token the
Feature activation+2.893
world
Token world
Feature activation+0.000
.
Token.
Feature activation+0.000
Photograph
Token Photograph
Feature activation+0.000
:
Token:
Feature activation+0.000
,
Token,
Feature activation+0.132
the
Token the
Feature activation+0.000
report
Token report
Feature activation+0.007
is
Token is
Feature activation+0.321
now
Token now
Feature activation+0.753
available
Token available
Feature activation+3.790
in
Token in
Feature activation+3.425
English
Token English
Feature activation+0.324
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.011
foreign
Token foreign
Feature activation+0.000
managers
Token managers
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.583
eight
Token eight
Feature activation+3.516
from
Token from
Feature activation+3.733
Bl
Token Bl
Feature activation+0.000
ighty
Tokenighty
Feature activation+0.578
(
Token (
Feature activation+0.201
five
Tokenfive
Feature activation+0.934
English
Token English
Feature activation+0.101
far
Token far
Feature activation+0.000
fewer
Token fewer
Feature activation+0.000
than
Token than
Feature activation+3.061
is
Token is
Feature activation+1.733
typical
Token typical
Feature activation+2.426
in
Token in
Feature activation+3.726
an
Token an
Feature activation+3.152
American
Token American
Feature activation+0.285
city
Token city
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
in
Token in
Feature activation+0.000
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.061
as
Token as
Feature activation+2.008
they
Token they
Feature activation+1.724
did
Token did
Feature activation+3.712
elsewhere
Token elsewhere
Feature activation+1.933
.
Token.
Feature activation+0.111
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.055
"
Token"
Feature activation+1.216
year
Token year
Feature activation+0.637
and
Token and
Feature activation+0.991
,
Token,
Feature activation+0.762
despite
Token despite
Feature activation+0.402
returning
Token returning
Feature activation+1.135
to
Token to
Feature activation+3.681
Nigeria
Token Nigeria
Feature activation+0.000
recently
Token recently
Feature activation+0.187
,
Token,
Feature activation+0.428
he
Token he
Feature activation+0.523
has
Token has
Feature activation+0.635
more
Token more
Feature activation+0.730
than
Token than
Feature activation+0.000
half
Token half
Feature activation+1.411
a
Token a
Feature activation+0.262
year
Token year
Feature activation+1.664
ago
Token ago
Feature activation+3.666
in
Token in
Feature activation+3.633
the
Token the
Feature activation+3.032
States
Token States
Feature activation+0.328
,
Token,
Feature activation+0.319
T
Token T
Feature activation+0.000
of
Token of
Feature activation+0.402
that
Token that
Feature activation+1.106
afforded
Token afforded
Feature activation+2.286
to
Token to
Feature activation+0.241
parents
Token parents
Feature activation+1.471
in
Token in
Feature activation+3.645
Europe
Token Europe
Feature activation+0.000
,
Token,
Feature activation+0.899
Canada
Token Canada
Feature activation+0.000
and
Token and
Feature activation+1.926
other
Token other
Feature activation+3.038
than
Token than
Feature activation+0.000
half
Token half
Feature activation+1.411
a
Token a
Feature activation+0.262
year
Token year
Feature activation+1.664
ago
Token ago
Feature activation+3.666
in
Token in
Feature activation+3.633
the
Token the
Feature activation+3.032
States
Token States
Feature activation+0.328
,
Token,
Feature activation+0.319
T
Token T
Feature activation+0.000
-
Token-
Feature activation+0.000
say
Token say
Feature activation+0.041
this
Token this
Feature activation+0.637
is
Token is
Feature activation+0.105
not
Token not
Feature activation+0.046
the
Token the
Feature activation+0.392
case
Token case
Feature activation+3.600
.
Token.
Feature activation+0.864
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.505
Men
TokenMen
Feature activation+0.052
and
Token and
Feature activation+0.000
cost
Token cost
Feature activation+0.068
of
Token of
Feature activation+0.652
the
Token the
Feature activation+0.875
comparable
Token comparable
Feature activation+0.897
drone
Token drone
Feature activation+0.612
produced
Token produced
Feature activation+3.591
in
Token in
Feature activation+2.961
the
Token the
Feature activation+3.009
US
Token US
Feature activation+0.191
,"
Token,"
Feature activation+0.058
giving
Token giving
Feature activation+0.000
traditionally
Token traditionally
Feature activation+0.000
been
Token been
Feature activation+0.000
stricter
Token stricter
Feature activation+0.148
than
Token than
Feature activation+3.192
in
Token in
Feature activation+3.182
the
Token the
Feature activation+3.530
US
Token US
Feature activation+0.323
,
Token,
Feature activation+0.281
and
Token and
Feature activation+0.285
recent
Token recent
Feature activation+0.485
changes
Token changes
Feature activation+0.727
12
Token 12
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
managers
Token managers
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.583
eight
Token eight
Feature activation+3.516
from
Token from
Feature activation+3.733
Bl
Token Bl
Feature activation+0.000
ighty
Tokenighty
Feature activation+0.578
(
Token (
Feature activation+0.201
five
Tokenfive
Feature activation+0.934
much
Token much
Feature activation+0.000
residential
Token residential
Feature activation+0.000
space
Token space
Feature activation+0.000
per
Token per
Feature activation+0.000
capita
Token capita
Feature activation+0.000
as
Token as
Feature activation+3.505
Belarus
Token Belarus
Feature activation+0.000
.
Token.
Feature activation+0.246
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.271
According
TokenAccording
Feature activation+0.000
00
Token 00
Feature activation+0.000
:
Token:
Feature activation+0.000
00
Token00
Feature activation+0.000
AM
Token AM
Feature activation+0.000
PST
Token PST
Feature activation+0.000
(
Token (
Feature activation+3.439
NA
TokenNA
Feature activation+0.498
server
Token server
Feature activation+0.000
),
Token),
Feature activation+0.000
the
Token the
Feature activation+0.000
Open
Token Open
Feature activation+0.000
the
Token the
Feature activation+0.000
report
Token report
Feature activation+0.007
is
Token is
Feature activation+0.321
now
Token now
Feature activation+0.753
available
Token available
Feature activation+3.790
in
Token in
Feature activation+3.425
English
Token English
Feature activation+0.324
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.011
K
TokenK
Feature activation+0.000
more
Token more
Feature activation+0.078
cool
Token cool
Feature activation+0.847
,
Token,
Feature activation+0.183
since
Token since
Feature activation+0.922
I
Token I
Feature activation+2.279
'm
Token'm
Feature activation+3.395
kinda
Token kinda
Feature activation+1.663
fascinated
Token fascinated
Feature activation+0.790
with
Token with
Feature activation+1.141
all
Token all
Feature activation+0.597
things
Token things
Feature activation+0.000
implements
Token implements
Feature activation+0.000
plain
Token plain
Feature activation+0.000
packaging
Token packaging
Feature activation+0.850
,
Token,
Feature activation+0.809
then
Token then
Feature activation+0.463
other
Token other
Feature activation+3.391
countries
Token countries
Feature activation+0.256
are
Token are
Feature activation+0.000
sure
Token sure
Feature activation+0.000
to
Token to
Feature activation+0.336
follow
Token follow
Feature activation+0.551
and
Token and
Feature activation+0.745
eventually
Token eventually
Feature activation+1.965
the
Token the
Feature activation+1.471
attention
Token attention
Feature activation+1.726
of
Token of
Feature activation+3.125
the
Token the
Feature activation+3.344
Washington
Token Washington
Feature activation+0.014
Post
Token Post
Feature activation+0.396
.
Token.
Feature activation+0.124
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.437
In
Token In
Feature activation+0.083
India
Token India
Feature activation+0.000
they
Token they
Feature activation+0.108
clean
Token clean
Feature activation+0.000
;
Token;
Feature activation+2.245
in
Token in
Feature activation+3.286
America
Token America
Feature activation+0.000
they
Token they
Feature activation+0.000
kill
Token kill
Feature activation+0.000
.
Token.
Feature activation+0.015
America
Token America
Feature activation+0.000

Top DFA by src position
MAX = 4.296

finest
Token finest
Feature activation+0.001
Top resid features:
details
Token details
Feature activation+0.011
Top resid features:
makes
Token makes
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
Per
Token Per
Feature activation-0.009
Top resid features:
uvian
Tokenuvian
Feature activation+4.244
Top resid features:
counterfe
Token counterfe
Feature activation-0.006
Top resid features:
its
Tokenits
Feature activation+0.018
Top resid features:
among
Token among
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
best
Token best
Feature activation+0.039
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
public
Token public
Feature activation-0.008
Top resid features:
only
Token only
Feature activation+0.006
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
Finnish
Token Finnish
Feature activation+3.936
Top resid features:
,
Token,
Feature activation+0.085
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
report
Token report
Feature activation-0.006
Top resid features:
is
Token is
Feature activation+0.008
Top resid features:
now
Token now
Feature activation+0.042
Top resid features:
ourced
Tokenourced
Feature activation+0.029
Top resid features:
overseas
Token overseas
Feature activation+1.839
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
reveals
Token reveals
Feature activation+0.006
Top resid features:
12
Token 12
Feature activation+0.009
Top resid features:
foreign
Token foreign
Feature activation+2.074
Top resid features:
managers
Token managers
Feature activation+0.067
Top resid features:
compared
Token compared
Feature activation+0.019
Top resid features:
to
Token to
Feature activation+0.074
Top resid features:
eight
Token eight
Feature activation+0.067
Top resid features:
from
Token from
Feature activation+0.018
Top resid features:
key
Token key
Feature activation+0.005
Top resid features:
points
Token points
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Japan
TokenJapan
Feature activation+3.307
Top resid features:
has
Token has
Feature activation+0.148
Top resid features:
12
Token 12
Feature activation+0.002
Top resid features:
basic
Token basic
Feature activation+0.004
Top resid features:
zones
Token zones
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
apply
Token apply
Feature activation+0.069
Top resid features:
as
Token as
Feature activation+0.035
Top resid features:
strongly
Token strongly
Feature activation+0.008
Top resid features:
in
Token in
Feature activation-0.272
Top resid features:
New
Token New
Feature activation+0.043
Top resid features:
Zealand
Token Zealand
Feature activation+4.296
Top resid features:
as
Token as
Feature activation+0.041
Top resid features:
they
Token they
Feature activation+0.015
Top resid features:
did
Token did
Feature activation+0.006
Top resid features:
elsewhere
Token elsewhere
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
He
TokenHe
Feature activation+0.012
Top resid features:
went
Token went
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
Saudi
Token Saudi
Feature activation+1.889
Top resid features:
Arabia
Token Arabia
Feature activation+1.986
Top resid features:
for
Token for
Feature activation+0.078
Top resid features:
medical
Token medical
Feature activation-0.000
Top resid features:
treatment
Token treatment
Feature activation+0.029
Top resid features:
in
Token in
Feature activation+0.031
Top resid features:
November
Token November
Feature activation+0.011
Top resid features:
released
Token released
Feature activation+0.044
Top resid features:
nearly
Token nearly
Feature activation+0.003
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
year
Token year
Feature activation+0.003
Top resid features:
ago
Token ago
Feature activation-0.037
Top resid features:
internationally
Token internationally
Feature activation+4.119
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
and
Token and
Feature activation+0.019
Top resid features:
more
Token more
Feature activation+0.006
Top resid features:
than
Token than
Feature activation+0.008
Top resid features:
half
Token half
Feature activation+0.020
Top resid features:
paternity
Token paternity
Feature activation-0.013
Top resid features:
leave
Token leave
Feature activation+0.006
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
United
Token United
Feature activation+0.087
Top resid features:
States
Token States
Feature activation+3.986
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
which
Token which
Feature activation+0.004
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
fraction
Token fraction
Feature activation+0.016
Top resid features:
released
Token released
Feature activation+0.019
Top resid features:
nearly
Token nearly
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
year
Token year
Feature activation+0.018
Top resid features:
ago
Token ago
Feature activation+0.008
Top resid features:
internationally
Token internationally
Feature activation+3.977
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
more
Token more
Feature activation+0.005
Top resid features:
than
Token than
Feature activation+0.007
Top resid features:
half
Token half
Feature activation+0.003
Top resid features:
government
Token government
Feature activation+0.004
Top resid features:
agencies
Token agencies
Feature activation-0.002
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
United
Token United
Feature activation+0.038
Top resid features:
States
Token States
Feature activation+3.632
Top resid features:
have
Token have
Feature activation+0.063
Top resid features:
acted
Token acted
Feature activation-0.000
Top resid features:
to
Token to
Feature activation+0.008
Top resid features:
cover
Token cover
Feature activation+0.010
Top resid features:
up
Token up
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
drone
Token drone
Feature activation-0.025
Top resid features:
produced
Token produced
Feature activation+0.027
Top resid features:
by
Token by
Feature activation+0.056
Top resid features:
China
Token China
Feature activation+3.904
Top resid features:
is
Token is
Feature activation+0.007
Top resid features:
"
Token "
Feature activation+0.058
Top resid features:
a
Tokena
Feature activation+0.011
Top resid features:
fraction
Token fraction
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
B
TokenB
Feature activation+0.006
Top resid features:
anking
Tokenanking
Feature activation+0.012
Top resid features:
regulation
Token regulation
Feature activation+0.007
Top resid features:
in
Token in
Feature activation-0.006
Top resid features:
Canada
Token Canada
Feature activation+3.052
Top resid features:
has
Token has
Feature activation+0.016
Top resid features:
traditionally
Token traditionally
Feature activation+0.031
Top resid features:
been
Token been
Feature activation+0.011
Top resid features:
stricter
Token stricter
Feature activation+0.012
Top resid features:
than
Token than
Feature activation+0.042
Top resid features:
ourced
Tokenourced
Feature activation+0.029
Top resid features:
overseas
Token overseas
Feature activation+0.830
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
reveals
Token reveals
Feature activation+0.002
Top resid features:
12
Token 12
Feature activation+0.004
Top resid features:
foreign
Token foreign
Feature activation+3.007
Top resid features:
managers
Token managers
Feature activation+0.101
Top resid features:
compared
Token compared
Feature activation+0.019
Top resid features:
to
Token to
Feature activation+0.058
Top resid features:
eight
Token eight
Feature activation+0.006
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
government
Token government
Feature activation+0.000
Top resid features:
boasts
Token boasts
Feature activation-0.004
Top resid features:
that
Token that
Feature activation-0.007
Top resid features:
no
Token no
Feature activation-0.000
Top resid features:
other
Token other
Feature activation+0.031
Top resid features:
country
Token country
Feature activation+3.640
Top resid features:
in
Token in
Feature activation+0.051
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
post
Token post
Feature activation+0.007
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
Soviet
TokenSoviet
Feature activation+0.006
Top resid features:
:
Token:
Feature activation+0.001
Top resid features:
00
Token00
Feature activation+0.000
Top resid features:
AM
Token AM
Feature activation-0.002
Top resid features:
CET
Token CET
Feature activation+0.039
Top resid features:
(
Token (
Feature activation+0.009
Top resid features:
EU
TokenEU
Feature activation+3.876
Top resid features:
server
Token server
Feature activation+0.081
Top resid features:
)
Token)
Feature activation+0.009
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
00
Token 00
Feature activation-0.008
Top resid features:
:
Token:
Feature activation-0.006
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
public
Token public
Feature activation-0.019
Top resid features:
only
Token only
Feature activation+0.004
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
Finnish
Token Finnish
Feature activation+3.436
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
report
Token report
Feature activation-0.002
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
now
Token now
Feature activation+0.041
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
My
TokenMy
Feature activation-0.002
Top resid features:
Santa
Token Santa
Feature activation+0.001
Top resid features:
is
Token is
Feature activation+0.008
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
England
Token England
Feature activation+3.772
Top resid features:
which
Token which
Feature activation+0.103
Top resid features:
made
Token made
Feature activation+0.011
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
even
Token even
Feature activation-0.003
Top resid features:
more
Token more
Feature activation+0.003
Top resid features:
massive
Token massive
Feature activation+0.004
Top resid features:
threat
Token threat
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
if
Token if
Feature activation+0.004
Top resid features:
Australia
Token Australia
Feature activation+3.607
Top resid features:
implements
Token implements
Feature activation+0.008
Top resid features:
plain
Token plain
Feature activation-0.014
Top resid features:
packaging
Token packaging
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
then
Token then
Feature activation+0.033
Top resid features:
.
Token.
Feature activation+0.027
Top resid features:
That
Token That
Feature activation-0.004
Top resid features:
led
Token led
Feature activation+0.012
Top resid features:
to
Token to
Feature activation+0.018
Top resid features:
more
Token more
Feature activation+0.006
Top resid features:
Canadian
Token Canadian
Feature activation+3.310
Top resid features:
media
Token media
Feature activation+0.085
Top resid features:
coverage
Token coverage
Feature activation+0.054
Top resid features:
and
Token and
Feature activation+0.027
Top resid features:
eventually
Token eventually
Feature activation+0.034
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
drinking
Token drinking
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
blood
Token blood
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
In
Token In
Feature activation-0.000
Top resid features:
India
Token India
Feature activation+3.777
Top resid features:
they
Token they
Feature activation+0.018
Top resid features:
clean
Token clean
Feature activation+0.003
Top resid features:
;
Token;
Feature activation+0.004
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
America
Token America
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.02

Head 2: 0.05

Head 3: 0.07

Head 4: 0.02

Head 5: 0.06

Head 6: 0.03

Head 7: 0.04

Head 8: 0.44

Head 9: 0.07

Head 10: 0.12

Head 11: 0.05

Positive logits

abroad5.34

overseas5.07

foreigners4.47

internationally4.22

Europeans4.20

countries4.19

foreigner4.17

Europe4.11

foreign4.10

Countries4.05

repatri3.98

visas3.98

exported3.96

mainland3.95

international3.93

European3.92

visa3.88

Netherlands3.84

export3.82

domestically3.82

Negative logits

��-2.54

utenberg-2.52

Darrell-2.25

odder-2.24

ospel-2.14

inventoryQuantity-2.04

alion-2.00

_{-1.99

bernatorial-1.99

essor-1.95

Wheel-1.93

adow-1.89

srfAttach-1.86

Rutherford-1.85

ulty-1.85

ertodd-1.84

utherford-1.84

ctive-1.81

onew-1.80

escent-1.80

INTERVAL 3.726 - 4.140
CONTAINS 0.001%

,
Token,
Feature activation+0.132
the
Token the
Feature activation+0.000
report
Token report
Feature activation+0.007
is
Token is
Feature activation+0.321
now
Token now
Feature activation+0.753
available
Token available
Feature activation+3.790
in
Token in
Feature activation+3.425
English
Token English
Feature activation+0.324
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.011
counterfe
Token counterfe
Feature activation+0.000
its
Tokenits
Feature activation+0.000
among
Token among
Feature activation+0.029
the
Token the
Feature activation+0.529
best
Token best
Feature activation+1.133
in
Token in
Feature activation+3.903
the
Token the
Feature activation+2.893
world
Token world
Feature activation+0.000
.
Token.
Feature activation+0.000
Photograph
Token Photograph
Feature activation+0.000
:
Token:
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
managers
Token managers
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.583
eight
Token eight
Feature activation+3.516
from
Token from
Feature activation+3.733
Bl
Token Bl
Feature activation+0.000
ighty
Tokenighty
Feature activation+0.578
(
Token (
Feature activation+0.201
five
Tokenfive
Feature activation+0.934
English
Token English
Feature activation+0.101

INTERVAL 3.312 - 3.726
CONTAINS 0.002%

implements
Token implements
Feature activation+0.000
plain
Token plain
Feature activation+0.000
packaging
Token packaging
Feature activation+0.850
,
Token,
Feature activation+0.809
then
Token then
Feature activation+0.463
other
Token other
Feature activation+3.391
countries
Token countries
Feature activation+0.256
are
Token are
Feature activation+0.000
sure
Token sure
Feature activation+0.000
to
Token to
Feature activation+0.336
follow
Token follow
Feature activation+0.551
12
Token 12
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
managers
Token managers
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.583
eight
Token eight
Feature activation+3.516
from
Token from
Feature activation+3.733
Bl
Token Bl
Feature activation+0.000
ighty
Tokenighty
Feature activation+0.578
(
Token (
Feature activation+0.201
five
Tokenfive
Feature activation+0.934
more
Token more
Feature activation+0.078
cool
Token cool
Feature activation+0.847
,
Token,
Feature activation+0.183
since
Token since
Feature activation+0.922
I
Token I
Feature activation+2.279
'm
Token'm
Feature activation+3.395
kinda
Token kinda
Feature activation+1.663
fascinated
Token fascinated
Feature activation+0.790
with
Token with
Feature activation+1.141
all
Token all
Feature activation+0.597
things
Token things
Feature activation+0.000
far
Token far
Feature activation+0.000
fewer
Token fewer
Feature activation+0.000
than
Token than
Feature activation+3.061
is
Token is
Feature activation+1.733
typical
Token typical
Feature activation+2.426
in
Token in
Feature activation+3.726
an
Token an
Feature activation+3.152
American
Token American
Feature activation+0.285
city
Token city
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
than
Token than
Feature activation+0.000
half
Token half
Feature activation+1.411
a
Token a
Feature activation+0.262
year
Token year
Feature activation+1.664
ago
Token ago
Feature activation+3.666
in
Token in
Feature activation+3.633
the
Token the
Feature activation+3.032
States
Token States
Feature activation+0.328
,
Token,
Feature activation+0.319
T
Token T
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 2.898 - 3.312
CONTAINS 0.004%

Canada
Token Canada
Feature activation+0.000
has
Token has
Feature activation+0.000
traditionally
Token traditionally
Feature activation+0.000
been
Token been
Feature activation+0.000
stricter
Token stricter
Feature activation+0.148
than
Token than
Feature activation+3.192
in
Token in
Feature activation+3.182
the
Token the
Feature activation+3.530
US
Token US
Feature activation+0.323
,
Token,
Feature activation+0.281
and
Token and
Feature activation+0.285
.
Token.
Feature activation+0.132
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.136
It
Token It
Feature activation+0.405
fared
Token fared
Feature activation+0.037
better
Token better
Feature activation+3.125
overseas
Token overseas
Feature activation+0.567
,
Token,
Feature activation+0.952
taking
Token taking
Feature activation+0.563
in
Token in
Feature activation+0.477
$
Token $
Feature activation+0.000
around
Token around
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.033
,
Token,
Feature activation+0.251
among
Token among
Feature activation+0.363
them
Token them
Feature activation+3.259
North
Token North
Feature activation+0.204
Korea
Token Korea
Feature activation+0.000
,
Token,
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
and
Token and
Feature activation+0.000
In
Token In
Feature activation+0.083
India
Token India
Feature activation+0.000
they
Token they
Feature activation+0.108
clean
Token clean
Feature activation+0.000
;
Token;
Feature activation+2.245
in
Token in
Feature activation+3.286
America
Token America
Feature activation+0.000
they
Token they
Feature activation+0.000
kill
Token kill
Feature activation+0.000
.
Token.
Feature activation+0.015
America
Token America
Feature activation+0.000
May
Token May
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
Europe
Token Europe
Feature activation+0.046
and
Token and
Feature activation+3.271
Asia
Token Asia
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.505
the
Token the
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000

INTERVAL 2.484 - 2.898
CONTAINS 0.005%

he
Token he
Feature activation+0.902
is
Token is
Feature activation+1.115
the
Token the
Feature activation+1.111
first
Token first
Feature activation+0.476
player
Token player
Feature activation+0.681
born
Token born
Feature activation+2.744
and
Token and
Feature activation+0.142
raised
Token raised
Feature activation+2.042
in
Token in
Feature activation+2.036
Croatia
Token Croatia
Feature activation+0.000
to
Token to
Feature activation+1.119
decades
Token decades
Feature activation+0.000
,
Token,
Feature activation+0.153
as
Token as
Feature activation+1.638
they
Token they
Feature activation+0.387
have
Token have
Feature activation+0.631
elsewhere
Token elsewhere
Feature activation+2.654
in
Token in
Feature activation+3.147
the
Token the
Feature activation+2.412
developed
Token developed
Feature activation+0.521
world
Token world
Feature activation+0.024
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
out
Token out
Feature activation+0.000
,
Token,
Feature activation+0.000
no
Token no
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
-
Token-
Feature activation+2.566
assembled
Tokenassembled
Feature activation+0.148
vehicle
Token vehicle
Feature activation+0.000
can
Token can
Feature activation+0.289
realistically
Token realistically
Feature activation+0.315
meet
Token meet
Feature activation+0.965
st
Tokenst
Feature activation+0.588
the
Token the
Feature activation+0.526
BR
Token BR
Feature activation+0.000
IC
TokenIC
Feature activation+0.000
nations
Token nations
Feature activation+0.354
,
Token,
Feature activation+2.836
Brazil
Token Brazil
Feature activation+0.476
was
Token was
Feature activation+0.950
represented
Token represented
Feature activation+0.050
last
Token last
Feature activation+0.076
year
Token year
Feature activation+0.236
the
Token the
Feature activation+0.735
UK
Token UK
Feature activation+0.000
,
Token,
Feature activation+0.437
and
Token and
Feature activation+1.720
Britons
Token Britons
Feature activation+1.354
living
Token living
Feature activation+2.507
abroad
Token abroad
Feature activation+0.761
,
Token,
Feature activation+0.008
are
Token are
Feature activation+0.090
worried
Token worried
Feature activation+0.206
about
Token about
Feature activation+1.332

INTERVAL 2.070 - 2.484
CONTAINS 0.012%

America
Token America
Feature activation+0.299
while
Token while
Feature activation+0.814
Black
Token Black
Feature activation+0.000
Panther
Token Panther
Feature activation+0.353
oversees
Token oversees
Feature activation+2.569
his
Token his
Feature activation+2.118
land
Token land
Feature activation+0.000
of
Token of
Feature activation+0.000
Wak
Token Wak
Feature activation+0.000
anda
Tokenanda
Feature activation+0.000
.
Token.
Feature activation+0.000
various
Token various
Feature activation+0.000
countries
Token countries
Feature activation+0.000
around
Token around
Feature activation+0.232
the
Token the
Feature activation+0.410
world
Token world
Feature activation+0.000
but
Token but
Feature activation+2.191
I
Token I
Feature activation+1.687
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+1.692
never
Token never
Feature activation+0.969
is
Token is
Feature activation+0.000
open
Token open
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
and
Token and
Feature activation+2.168
Canada
Token Canada
Feature activation+0.000
and
Token and
Feature activation+0.242
will
Token will
Feature activation+0.170
end
Token end
Feature activation+0.403
April
Token April
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+1.357
they
Token they
Feature activation+1.110
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.301
re
Tokenre
Feature activation+2.228
selling
Token selling
Feature activation+0.425
people
Token people
Feature activation+0.357
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.515
s
Tokens
Feature activation+0.030
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.328
than
Token than
Feature activation+0.238
the
Token the
Feature activation+0.163
U
Token U
Feature activation+1.926
.
Token.
Feature activation+2.312
S
TokenS
Feature activation+0.545
.
Token.
Feature activation+0.103
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
to
Token to
Feature activation+0.205

INTERVAL 1.656 - 2.070
CONTAINS 0.028%

the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
deal
Token deal
Feature activation+0.000
for
Token for
Feature activation+1.009
UK
Token UK
Feature activation+0.480
nationals
Token nationals
Feature activation+1.789
living
Token living
Feature activation+2.670
in
Token in
Feature activation+2.532
the
Token the
Feature activation+2.083
EU
Token EU
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.183
biggest
Token biggest
Feature activation+0.612
national
Token national
Feature activation+0.109
representation
Token representation
Feature activation+0.064
came
Token came
Feature activation+0.856
from
Token from
Feature activation+1.715
those
Token those
Feature activation+1.033
closest
Token closest
Feature activation+0.448
to
Token to
Feature activation+0.306
the
Token the
Feature activation+0.233
site
Token site
Feature activation+0.396
the
Token the
Feature activation+0.000
semi
Token semi
Feature activation+0.000
final
Token final
Feature activation+0.000
match
Token match
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
vs
Token vs
Feature activation+1.943
Czech
Token Czech
Feature activation+0.000
Republic
Token Republic
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
2015
Token 2015
Feature activation+0.451
major
Token major
Feature activation+0.000
difference
Token difference
Feature activation+0.000
when
Token when
Feature activation+0.088
comparing
Token comparing
Feature activation+0.319
baseball
Token baseball
Feature activation+1.146
here
Token here
Feature activation+1.873
vs
Token vs
Feature activation+2.805
.
Token.
Feature activation+2.692
baseball
Token baseball
Feature activation+2.734
there
Token there
Feature activation+1.671
.
Token.
Feature activation+0.282
parents
Token parents
Feature activation+1.471
in
Token in
Feature activation+3.645
Europe
Token Europe
Feature activation+0.000
,
Token,
Feature activation+0.899
Canada
Token Canada
Feature activation+0.000
and
Token and
Feature activation+1.926
other
Token other
Feature activation+3.038
advanced
Token advanced
Feature activation+0.969
economies
Token economies
Feature activation+0.262
,
Token,
Feature activation+0.120
is
Token is
Feature activation+0.022

INTERVAL 1.242 - 1.656
CONTAINS 0.059%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Vietnam
Token Vietnam
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
unlike
Token unlike
Feature activation+2.167
much
Token much
Feature activation+1.543
of
Token of
Feature activation+1.268
the
Token the
Feature activation+1.805
United
Token United
Feature activation+1.161
States
Token States
Feature activation+0.000
,
Token,
Feature activation+0.000
currency
Token currency
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
between
Token between
Feature activation+0.535
Scotland
Token Scotland
Feature activation+0.000
and
Token and
Feature activation+1.528
the
Token the
Feature activation+1.528
rest
Token rest
Feature activation+2.139
of
Token of
Feature activation+1.962
the
Token the
Feature activation+1.616
United
Token United
Feature activation+1.121
Kingdom
Token Kingdom
Feature activation+0.069
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
bourbon
Token bourbon
Feature activation+0.000
maker
Token maker
Feature activation+0.002
and
Token and
Feature activation+1.512
its
Token its
Feature activation+1.654
Japanese
Token Japanese
Feature activation+0.036
owner
Token owner
Feature activation+0.379
,
Token,
Feature activation+0.000
known
Token known
Feature activation+0.000
held
Token held
Feature activation+0.000
hosted
Token hosted
Feature activation+0.000
by
Token by
Feature activation+0.000
Middle
Token Middle
Feature activation+0.000
East
Token East
Feature activation+0.000
/
Token/
Feature activation+1.607
Af
TokenAf
Feature activation+0.000
rica
Tokenrica
Feature activation+0.000
between
Token between
Feature activation+0.000
the
Token the
Feature activation+0.000
highest
Token highest
Feature activation+0.660
that
Token that
Feature activation+1.824
for
Token for
Feature activation+1.665
the
Token the
Feature activation+1.027
rest
Token rest
Feature activation+1.421
of
Token of
Feature activation+1.553
the
Token the
Feature activation+1.325
world
Token world
Feature activation+0.088
combined
Token combined
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.018

INTERVAL 0.828 - 1.242
CONTAINS 0.171%

government
Token government
Feature activation+0.000
imped
Token imped
Feature activation+0.000
iments
Tokeniments
Feature activation+0.010
to
Token to
Feature activation+0.488
American
Token American
Feature activation+0.000
investment
Token investment
Feature activation+0.920
and
Token and
Feature activation+0.449
corporate
Token corporate
Feature activation+0.681
operations
Token operations
Feature activation+2.338
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
China
TokenChina
Feature activation+0.000
still
Token still
Feature activation+0.124
has
Token has
Feature activation+0.000
around
Token around
Feature activation+0.883
11
Token 11
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
mines
Token mines
Feature activation+0.000
in
Token in
Feature activation+0.232
of
Token of
Feature activation+0.000
$
Token $
Feature activation+0.000
5
Token5
Feature activation+0.098
million
Token million
Feature activation+1.370
a
Token a
Feature activation+0.277
year
Token year
Feature activation+1.108
,
Token,
Feature activation+1.574
analyst
Token analyst
Feature activation+0.000
Michael
Token Michael
Feature activation+0.000
P
Token P
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
,
Token,
Feature activation+0.163
Instagram
Token Instagram
Feature activation+0.036
has
Token has
Feature activation+0.000
grown
Token grown
Feature activation+0.060
stronger
Token stronger
Feature activation+0.294
in
Token in
Feature activation+0.990
the
Token the
Feature activation+0.462
last
Token last
Feature activation+0.000
four
Token four
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
health
Token health
Feature activation+0.163
issues
Token issues
Feature activation+0.823
don
Token don
Feature activation+0.515
't
Token't
Feature activation+0.498
vary
Token vary
Feature activation+0.874
much
Token much
Feature activation+0.933
by
Token by
Feature activation+1.026
region
Token region
Feature activation+0.242
,
Token,
Feature activation+0.207
the
Token the
Feature activation+0.000
CDC
Token CDC
Feature activation+0.000

INTERVAL 0.414 - 0.828
CONTAINS 0.508%

and
Token and
Feature activation+0.089
cultures
Token cultures
Feature activation+0.439
and
Token and
Feature activation+0.000
politics
Token politics
Feature activation+0.068
to
Token to
Feature activation+0.442
be
Token be
Feature activation+0.512
better
Token better
Feature activation+0.487
reflected
Token reflected
Feature activation+0.827
to
Token to
Feature activation+1.205
audiences
Token audiences
Feature activation+1.711
across
Token across
Feature activation+1.277
friends
Token friends
Feature activation+0.335
in
Token in
Feature activation+0.909
Central
Token Central
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
;
Token;
Feature activation+0.059
his
Token his
Feature activation+0.739
wife
Token wife
Feature activation+1.249
and
Token and
Feature activation+0.000
four
Token four
Feature activation+0.000
children
Token children
Feature activation+1.149
live
Token live
Feature activation+1.252
Australian
Token Australian
Feature activation+0.000
understands
Token understands
Feature activation+0.749
he
Token he
Feature activation+0.306
grew
Token grew
Feature activation+0.000
up
Token up
Feature activation+0.443
in
Token in
Feature activation+0.510
Mary
Token Mary
Feature activation+0.000
borough
Tokenborough
Feature activation+0.000
,
Token,
Feature activation+0.000
Queensland
Token Queensland
Feature activation+0.000
,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
international
Token international
Feature activation+0.000
community
Token community
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.502
1988
Token 1988
Feature activation+0.000
protests
Token protests
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
subsequent
Token subsequent
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
China
Token China
Feature activation+0.000
isn
Token isn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.701
part
Token part
Feature activation+0.170
of
Token of
Feature activation+1.073
the
Token the
Feature activation+1.669
deal
Token deal
Feature activation+0.000
,
Token,
Feature activation+1.064

INTERVAL 0.000 - 0.414
CONTAINS 99.210%

NFL
Token NFL
Feature activation+0.000
Media
Token Media
Feature activation+0.000
the
Token the
Feature activation+0.000
details
Token details
Feature activation+0.000
of
Token of
Feature activation+0.000
Wein
Token Wein
Feature activation+0.000
berg
Tokenberg
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
dec
Token dec
Feature activation+0.000
provocation
Token provocation
Feature activation+0.000
by
Token by
Feature activation+0.000
Seoul
Token Seoul
Feature activation+0.000
's
Token's
Feature activation+0.000
poor
Token poor
Feature activation+0.000
and
Token and
Feature activation+0.000
isolated
Token isolated
Feature activation+0.000
neighbour
Token neighbour
Feature activation+0.000
."
Token."
Feature activation+0.000
I
TokenI
Feature activation+0.000
am
Token am
Feature activation+0.000
in
Token in
Feature activation+0.000
Chicago
Token Chicago
Feature activation+0.000
,
Token,
Feature activation+0.000
almost
Token almost
Feature activation+0.000
65
Token 65
Feature activation+0.000
percent
Token percent
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
And
TokenAnd
Feature activation+0.205
that
Token that
Feature activation+0.000
Unfortunately
TokenUnfortunately
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
got
Token got
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+0.000
too
Token too
Feature activation+0.000
creative
Token creative
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
comment
Token comment
Feature activation+0.000
_
Token_
Feature activation+0.000
html
Tokenhtml
Feature activation+0.000
variable
Token variable
Feature activation+0.000
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
the
Token the
Feature activation+0.000
original
Token original
Feature activation+0.000
div
Token div
Feature activation+0.000
contents
Token contents
Feature activation+0.000
.
Token.
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H8.8: (feature 14739)

TOP ACTIVATIONS
MAX = 4.656

larger
Token larger
Feature activation+0.000
jars
Token jars
Feature activation+0.033
feel
Token feel
Feature activation+0.050
free
Token free
Feature activation+0.071
to
Token to
Feature activation+1.720
add
Token add
Feature activation+4.656
more
Token more
Feature activation+1.216
salt
Token salt
Feature activation+0.043
but
Token but
Feature activation+0.332
be
Token be
Feature activation+0.079
sure
Token sure
Feature activation+0.226
one
Token one
Feature activation+0.579
is
Token is
Feature activation+0.498
for
Token for
Feature activation+0.079
AC
Token AC
Feature activation+0.000
and
Token and
Feature activation+0.074
the
Token the
Feature activation+4.126
smaller
Token smaller
Feature activation+0.105
one
Token one
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.000
industry
Token industry
Feature activation+0.000
,
Token,
Feature activation+0.000
representing
Token representing
Feature activation+0.000
both
Token both
Feature activation+0.000
large
Token large
Feature activation+0.000
and
Token and
Feature activation+3.386
small
Token small
Feature activation+0.000
brewers
Token brewers
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
so
Token so
Feature activation+2.084
it
Token it
Feature activation+2.793
would
Token would
Feature activation+2.982
give
Token give
Feature activation+2.740
me
Token me
Feature activation+2.560
enough
Token enough
Feature activation+3.377
leg
Token leg
Feature activation+0.879
room
Token room
Feature activation+0.679
.
Token.
Feature activation+0.067
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.012
you
Token you
Feature activation+0.000
consider
Token consider
Feature activation+0.000
is
Token is
Feature activation+0.000
size
Token size
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+2.676
two
Token two
Feature activation+3.329
well
Token well
Feature activation+2.222
-
Token-
Feature activation+2.335
built
Tokenbuilt
Feature activation+1.258
men
Token men
Feature activation+0.920
in
Token in
Feature activation+0.397
size
Token size
Feature activation+0.026
(
Token (
Feature activation+2.418
e
Tokene
Feature activation+0.431
.
Token.
Feature activation+0.000
g
Tokeng
Feature activation+1.236
.
Token.
Feature activation+3.211
8
Token 8
Feature activation+1.042
KB
Token KB
Feature activation+1.217
).
Token).
Feature activation+0.288
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.129
more
Token more
Feature activation+0.500
flexibility
Token flexibility
Feature activation+0.000
for
Token for
Feature activation+0.373
navigation
Token navigation
Feature activation+0.039
,
Token,
Feature activation+0.311
but
Token but
Feature activation+3.147
they
Token they
Feature activation+0.371
also
Token also
Feature activation+0.164
take
Token take
Feature activation+0.123
up
Token up
Feature activation+0.035
more
Token more
Feature activation+0.025
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
too
Token too
Feature activation+0.000
small
Token small
Feature activation+0.838
for
Token for
Feature activation+3.053
us
Token us
Feature activation+0.589
to
Token to
Feature activation+2.976
make
Token make
Feature activation+2.431
,
Token,
Feature activation+0.452
but
Token but
Feature activation+0.471
inch
Token inch
Feature activation+0.887
wide
Token wide
Feature activation+0.447
instead
Token instead
Feature activation+0.327
so
Token so
Feature activation+2.084
it
Token it
Feature activation+2.793
would
Token would
Feature activation+2.982
give
Token give
Feature activation+2.740
me
Token me
Feature activation+2.560
enough
Token enough
Feature activation+3.377
leg
Token leg
Feature activation+0.879
room
Token room
Feature activation+0.679
are
Token are
Feature activation+0.000
too
Token too
Feature activation+0.000
small
Token small
Feature activation+0.838
for
Token for
Feature activation+3.053
us
Token us
Feature activation+0.589
to
Token to
Feature activation+2.976
make
Token make
Feature activation+2.431
,
Token,
Feature activation+0.452
but
Token but
Feature activation+0.471
we
Token we
Feature activation+0.204
've
Token've
Feature activation+0.451
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
size
Token size
Feature activation+0.000
does
Token does
Feature activation+2.183
not
Token not
Feature activation+2.533
fit
Token fit
Feature activation+2.974
all
Token all
Feature activation+0.881
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Life
TokenLife
Feature activation+0.000
are
Token are
Feature activation+0.000
beautiful
Token beautiful
Feature activation+0.000
historic
Token historic
Feature activation+0.000
homes
Token homes
Feature activation+0.000
big
Token big
Feature activation+0.000
and
Token and
Feature activation+2.925
small
Token small
Feature activation+0.000
in
Token in
Feature activation+0.000
various
Token various
Feature activation+0.000
styles
Token styles
Feature activation+0.000
,
Token,
Feature activation+0.000
women
Token women
Feature activation+0.000
and
Token and
Feature activation+0.000
of
Token of
Feature activation+0.000
nations
Token nations
Feature activation+0.000
large
Token large
Feature activation+0.000
and
Token and
Feature activation+2.915
small
Token small
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
smaller
Token smaller
Feature activation+0.180
-
Token-
Feature activation+0.627
sized
Tokensized
Feature activation+1.023
,
Token,
Feature activation+1.095
but
Token but
Feature activation+1.503
still
Token still
Feature activation+2.856
grotesque
Token grotesque
Feature activation+0.188
,
Token,
Feature activation+0.000
titan
Token titan
Feature activation+0.000
to
Token to
Feature activation+0.591
greet
Token greet
Feature activation+0.388
11
Token 11
Feature activation+1.273
inch
Token inch
Feature activation+0.887
wide
Token wide
Feature activation+0.447
instead
Token instead
Feature activation+0.327
so
Token so
Feature activation+2.084
it
Token it
Feature activation+2.793
would
Token would
Feature activation+2.982
give
Token give
Feature activation+2.740
me
Token me
Feature activation+2.560
enough
Token enough
Feature activation+3.377
leg
Token leg
Feature activation+0.879
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
size
Token size
Feature activation+0.000
(
Token (
Feature activation+1.909
one
Tokenone
Feature activation+2.778
of
Token of
Feature activation+0.450
wood
Token wood
Feature activation+0.115
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
wide
Token wide
Feature activation+0.447
instead
Token instead
Feature activation+0.327
so
Token so
Feature activation+2.084
it
Token it
Feature activation+2.793
would
Token would
Feature activation+2.982
give
Token give
Feature activation+2.740
me
Token me
Feature activation+2.560
enough
Token enough
Feature activation+3.377
leg
Token leg
Feature activation+0.879
room
Token room
Feature activation+0.679
.
Token.
Feature activation+0.067
thing
Token thing
Feature activation+0.000
you
Token you
Feature activation+0.000
consider
Token consider
Feature activation+0.000
is
Token is
Feature activation+0.000
size
Token size
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+2.676
two
Token two
Feature activation+3.329
well
Token well
Feature activation+2.222
-
Token-
Feature activation+2.335
built
Tokenbuilt
Feature activation+1.258
men
Token men
Feature activation+0.920
complete
Token complete
Feature activation+0.105
bread
Token bread
Feature activation+0.114
roll
Token roll
Feature activation+0.404
,
Token,
Feature activation+1.264
considering
Token considering
Feature activation+1.640
a
Token a
Feature activation+2.651
15
Token 15
Feature activation+1.509
%
Token%
Feature activation+1.315
shrink
Token shrink
Feature activation+0.251
age
Tokenage
Feature activation+0.412
by
Token by
Feature activation+0.696
shape
Token shape
Feature activation+0.000
.
Token.
Feature activation+0.098
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
thinking
Token thinking
Feature activation+1.177
a
Token a
Feature activation+2.631
line
Token line
Feature activation+0.448
of
Token of
Feature activation+1.053
S
Token S
Feature activation+1.664
+,
Token+,
Feature activation+0.000
M
Token M
Feature activation+0.000

Top DFA by src position
MAX = 5.234

If
Token If
Feature activation-0.002
Top resid features:
you
Token you
Feature activation+0.002
Top resid features:
are
Token are
Feature activation-0.001
Top resid features:
working
Token working
Feature activation-0.011
Top resid features:
with
Token with
Feature activation+0.016
Top resid features:
larger
Token larger
Feature activation+5.234
Top resid features:
jars
Token jars
Feature activation+0.098
Top resid features:
feel
Token feel
Feature activation+0.004
Top resid features:
free
Token free
Feature activation+0.056
Top resid features:
to
Token to
Feature activation+0.044
Top resid features:
add
Token add
Feature activation-0.016
Top resid features:
two
Token two
Feature activation-0.013
Top resid features:
device
Token device
Feature activation+0.002
Top resid features:
boxes
Token boxes
Feature activation-0.008
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
The
Token The
Feature activation+0.002
Top resid features:
larger
Token larger
Feature activation+5.152
Top resid features:
one
Token one
Feature activation-0.092
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
AC
Token AC
Feature activation-0.086
Top resid features:
and
Token and
Feature activation-0.048
Top resid features:
brewing
Token brewing
Feature activation-0.000
Top resid features:
industry
Token industry
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
representing
Token representing
Feature activation+0.007
Top resid features:
both
Token both
Feature activation+0.005
Top resid features:
large
Token large
Feature activation+4.115
Top resid features:
and
Token and
Feature activation-0.045
Top resid features:
small
Token small
Feature activation+0.000
Top resid features:
brewers
Token brewers
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.054
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
made
Token made
Feature activation+0.002
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
11
Token 11
Feature activation+0.016
Top resid features:
inch
Token inch
Feature activation+2.546
Top resid features:
wide
Token wide
Feature activation+1.161
Top resid features:
instead
Token instead
Feature activation-0.006
Top resid features:
so
Token so
Feature activation+0.013
Top resid features:
it
Token it
Feature activation-0.009
Top resid features:
would
Token would
Feature activation-0.007
Top resid features:
One
Token One
Feature activation-0.003
Top resid features:
thing
Token thing
Feature activation-0.018
Top resid features:
you
Token you
Feature activation-0.001
Top resid features:
consider
Token consider
Feature activation+0.026
Top resid features:
is
Token is
Feature activation+0.033
Top resid features:
size
Token size
Feature activation+3.460
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.105
Top resid features:
two
Token two
Feature activation+0.036
Top resid features:
well
Token well
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
built
Tokenbuilt
Feature activation+0.000
Top resid features:
into
Token into
Feature activation-0.004
Top resid features:
pages
Token pages
Feature activation+0.133
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.015
Top resid features:
certain
Token certain
Feature activation+0.051
Top resid features:
size
Token size
Feature activation+3.393
Top resid features:
(
Token (
Feature activation+0.093
Top resid features:
e
Tokene
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
g
Tokeng
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.029
Top resid features:
want
Token want
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
download
Token download
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
L
Token L
Feature activation+0.005
Top resid features:
arger
Tokenarger
Feature activation+3.037
Top resid features:
areas
Token areas
Feature activation+0.396
Top resid features:
will
Token will
Feature activation+0.202
Top resid features:
give
Token give
Feature activation+0.013
Top resid features:
you
Token you
Feature activation+0.006
Top resid features:
more
Token more
Feature activation+0.025
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.332
Top resid features:
that
Token that
Feature activation+0.013
Top resid features:
are
Token are
Feature activation+0.014
Top resid features:
too
Token too
Feature activation+0.103
Top resid features:
small
Token small
Feature activation+3.255
Top resid features:
for
Token for
Feature activation+0.174
Top resid features:
us
Token us
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:
,
Token,
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.002
Top resid features:
made
Token made
Feature activation-0.003
Top resid features:
it
Token it
Feature activation+0.006
Top resid features:
11
Token 11
Feature activation+0.065
Top resid features:
inch
Token inch
Feature activation+1.347
Top resid features:
wide
Token wide
Feature activation+1.782
Top resid features:
instead
Token instead
Feature activation-0.018
Top resid features:
so
Token so
Feature activation+0.034
Top resid features:
it
Token it
Feature activation-0.022
Top resid features:
would
Token would
Feature activation-0.017
Top resid features:
give
Token give
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.272
Top resid features:
that
Token that
Feature activation-0.006
Top resid features:
are
Token are
Feature activation+0.005
Top resid features:
too
Token too
Feature activation+0.113
Top resid features:
small
Token small
Feature activation+3.243
Top resid features:
for
Token for
Feature activation+0.143
Top resid features:
us
Token us
Feature activation+0.023
Top resid features:
to
Token to
Feature activation+0.022
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
learning
Token learning
Feature activation+0.004
Top resid features:
process
Token process
Feature activation-0.011
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
one
Token one
Feature activation-0.101
Top resid features:
size
Token size
Feature activation+3.544
Top resid features:
does
Token does
Feature activation+0.111
Top resid features:
not
Token not
Feature activation+0.062
Top resid features:
fit
Token fit
Feature activation+0.021
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
There
Token There
Feature activation+0.005
Top resid features:
are
Token are
Feature activation+0.007
Top resid features:
beautiful
Token beautiful
Feature activation+0.011
Top resid features:
historic
Token historic
Feature activation-0.026
Top resid features:
homes
Token homes
Feature activation-0.007
Top resid features:
big
Token big
Feature activation+3.428
Top resid features:
and
Token and
Feature activation+0.066
Top resid features:
small
Token small
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
various
Token various
Feature activation+0.000
Top resid features:
styles
Token styles
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.013
Top resid features:
women
Token women
Feature activation-0.064
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
of
Token of
Feature activation-0.007
Top resid features:
nations
Token nations
Feature activation-0.029
Top resid features:
large
Token large
Feature activation+3.738
Top resid features:
and
Token and
Feature activation+0.030
Top resid features:
small
Token small
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.242
Top resid features:
smaller
Token smaller
Feature activation+1.101
Top resid features:
-
Token-
Feature activation+0.323
Top resid features:
sized
Tokensized
Feature activation+1.287
Top resid features:
,
Token,
Feature activation+0.649
Top resid features:
but
Token but
Feature activation+0.058
Top resid features:
still
Token still
Feature activation+0.033
Top resid features:
grotesque
Token grotesque
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.002
Top resid features:
made
Token made
Feature activation+0.005
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
11
Token 11
Feature activation+0.061
Top resid features:
inch
Token inch
Feature activation+1.015
Top resid features:
wide
Token wide
Feature activation+1.929
Top resid features:
instead
Token instead
Feature activation-0.042
Top resid features:
so
Token so
Feature activation+0.052
Top resid features:
it
Token it
Feature activation-0.023
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
give
Token give
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.013
Top resid features:
balls
Token balls
Feature activation+0.033
Top resid features:
of
Token of
Feature activation-0.021
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
same
Token same
Feature activation+0.035
Top resid features:
size
Token size
Feature activation+2.483
Top resid features:
(
Token (
Feature activation+0.321
Top resid features:
one
Tokenone
Feature activation-0.024
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
wood
Token wood
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.042
Top resid features:
I
Token I
Feature activation+0.007
Top resid features:
made
Token made
Feature activation+0.002
Top resid features:
it
Token it
Feature activation-0.006
Top resid features:
11
Token 11
Feature activation+0.075
Top resid features:
inch
Token inch
Feature activation+1.825
Top resid features:
wide
Token wide
Feature activation+0.899
Top resid features:
instead
Token instead
Feature activation-0.009
Top resid features:
so
Token so
Feature activation+0.022
Top resid features:
it
Token it
Feature activation-0.008
Top resid features:
would
Token would
Feature activation+0.003
Top resid features:
One
Token One
Feature activation-0.026
Top resid features:
thing
Token thing
Feature activation-0.013
Top resid features:
you
Token you
Feature activation-0.008
Top resid features:
consider
Token consider
Feature activation+0.044
Top resid features:
is
Token is
Feature activation+0.057
Top resid features:
size
Token size
Feature activation+2.918
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.110
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
well
Token well
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
built
Tokenbuilt
Feature activation+0.000
Top resid features:
rece
Token rece
Feature activation+0.003
Top resid features:
on
Tokenon
Feature activation+0.008
Top resid features:
structed
Tokenstructed
Feature activation+0.011
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
original
Token original
Feature activation+0.016
Top resid features:
size
Token size
Feature activation+2.182
Top resid features:
of
Token of
Feature activation+0.393
Top resid features:
the
Token the
Feature activation+0.087
Top resid features:
complete
Token complete
Feature activation+0.072
Top resid features:
bread
Token bread
Feature activation-0.016
Top resid features:
roll
Token roll
Feature activation+0.064
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
develop
Token develop
Feature activation+0.006
Top resid features:
another
Token another
Feature activation-0.004
Top resid features:
series
Token series
Feature activation-0.022
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
sizes
Token sizes
Feature activation+2.704
Top resid features:
designed
Token designed
Feature activation+0.026
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
your
Token your
Feature activation+0.005
Top resid features:
shape
Token shape
Feature activation+0.151
Top resid features:
.
Token.
Feature activation+0.042
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.01

Head 2: 0.03

Head 3: 0.09

Head 4: 0.05

Head 5: 0.06

Head 6: 0.02

Head 7: 0.05

Head 8: 0.44

Head 9: 0.07

Head 10: 0.12

Head 11: 0.03

Positive logits

sizes3.99

size3.68

Size3.51

sized3.48

sized3.43

width3.41

SIZE3.40

Size3.39

Width3.34

size3.31

sizing3.31

smaller3.27

larg3.24

centimeters3.22

taller3.15

smallest3.11

Width3.11

thickness3.09

dimensions3.05

larger3.05

Negative logits

efe-1.96

Karma-1.87

indo-1.84

-1.82

reper-1.81

opathic-1.79

Brew-1.79

ceremonies-1.78

Bourbon-1.77

restart-1.75

relapse-1.71

extinguished-1.69

extingu-1.65

ceremony-1.64

revival-1.63

Renew-1.62

adrenaline-1.61

bourbon-1.61

Redemption-1.60

Salem-1.59

INTERVAL 4.190 - 4.656
CONTAINS 0.000%

larger
Token larger
Feature activation+0.000
jars
Token jars
Feature activation+0.033
feel
Token feel
Feature activation+0.050
free
Token free
Feature activation+0.071
to
Token to
Feature activation+1.720
add
Token add
Feature activation+4.656
more
Token more
Feature activation+1.216
salt
Token salt
Feature activation+0.043
but
Token but
Feature activation+0.332
be
Token be
Feature activation+0.079
sure
Token sure
Feature activation+0.226

INTERVAL 3.725 - 4.190
CONTAINS 0.000%

one
Token one
Feature activation+0.579
is
Token is
Feature activation+0.498
for
Token for
Feature activation+0.079
AC
Token AC
Feature activation+0.000
and
Token and
Feature activation+0.074
the
Token the
Feature activation+4.126
smaller
Token smaller
Feature activation+0.105
one
Token one
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
left
Token left
Feature activation+0.000

INTERVAL 3.259 - 3.725
CONTAINS 0.000%

industry
Token industry
Feature activation+0.000
,
Token,
Feature activation+0.000
representing
Token representing
Feature activation+0.000
both
Token both
Feature activation+0.000
large
Token large
Feature activation+0.000
and
Token and
Feature activation+3.386
small
Token small
Feature activation+0.000
brewers
Token brewers
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
you
Token you
Feature activation+0.000
consider
Token consider
Feature activation+0.000
is
Token is
Feature activation+0.000
size
Token size
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+2.676
two
Token two
Feature activation+3.329
well
Token well
Feature activation+2.222
-
Token-
Feature activation+2.335
built
Tokenbuilt
Feature activation+1.258
men
Token men
Feature activation+0.920
in
Token in
Feature activation+0.397
so
Token so
Feature activation+2.084
it
Token it
Feature activation+2.793
would
Token would
Feature activation+2.982
give
Token give
Feature activation+2.740
me
Token me
Feature activation+2.560
enough
Token enough
Feature activation+3.377
leg
Token leg
Feature activation+0.879
room
Token room
Feature activation+0.679
.
Token.
Feature activation+0.067
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.012

INTERVAL 2.794 - 3.259
CONTAINS 0.001%

are
Token are
Feature activation+0.000
too
Token too
Feature activation+0.000
small
Token small
Feature activation+0.838
for
Token for
Feature activation+3.053
us
Token us
Feature activation+0.589
to
Token to
Feature activation+2.976
make
Token make
Feature activation+2.431
,
Token,
Feature activation+0.452
but
Token but
Feature activation+0.471
we
Token we
Feature activation+0.204
've
Token've
Feature activation+0.451
size
Token size
Feature activation+0.026
(
Token (
Feature activation+2.418
e
Tokene
Feature activation+0.431
.
Token.
Feature activation+0.000
g
Tokeng
Feature activation+1.236
.
Token.
Feature activation+3.211
8
Token 8
Feature activation+1.042
KB
Token KB
Feature activation+1.217
).
Token).
Feature activation+0.288
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.129
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
too
Token too
Feature activation+0.000
small
Token small
Feature activation+0.838
for
Token for
Feature activation+3.053
us
Token us
Feature activation+0.589
to
Token to
Feature activation+2.976
make
Token make
Feature activation+2.431
,
Token,
Feature activation+0.452
but
Token but
Feature activation+0.471
smaller
Token smaller
Feature activation+0.180
-
Token-
Feature activation+0.627
sized
Tokensized
Feature activation+1.023
,
Token,
Feature activation+1.095
but
Token but
Feature activation+1.503
still
Token still
Feature activation+2.856
grotesque
Token grotesque
Feature activation+0.188
,
Token,
Feature activation+0.000
titan
Token titan
Feature activation+0.000
to
Token to
Feature activation+0.591
greet
Token greet
Feature activation+0.388
women
Token women
Feature activation+0.000
and
Token and
Feature activation+0.000
of
Token of
Feature activation+0.000
nations
Token nations
Feature activation+0.000
large
Token large
Feature activation+0.000
and
Token and
Feature activation+2.915
small
Token small
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.328 - 2.794
CONTAINS 0.002%

aves
Tokenaves
Feature activation+0.385
are
Token are
Feature activation+0.450
"
Token "
Feature activation+0.914
small
Tokensmall
Feature activation+0.554
"
Token"
Feature activation+0.436
(
Token (
Feature activation+2.454
having
Tokenhaving
Feature activation+2.521
shorter
Token shorter
Feature activation+0.771
wavelengths
Token wavelengths
Feature activation+0.380
),
Token),
Feature activation+0.386
compared
Token compared
Feature activation+0.038
process
Token process
Feature activation+0.000
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
size
Token size
Feature activation+0.000
does
Token does
Feature activation+2.183
not
Token not
Feature activation+2.533
fit
Token fit
Feature activation+2.974
all
Token all
Feature activation+0.881
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
pages
Token pages
Feature activation+0.000
of
Token of
Feature activation+0.057
a
Token a
Feature activation+0.158
certain
Token certain
Feature activation+0.333
size
Token size
Feature activation+0.026
(
Token (
Feature activation+2.418
e
Tokene
Feature activation+0.431
.
Token.
Feature activation+0.000
g
Tokeng
Feature activation+1.236
.
Token.
Feature activation+3.211
8
Token 8
Feature activation+1.042
wide
Token wide
Feature activation+0.447
instead
Token instead
Feature activation+0.327
so
Token so
Feature activation+2.084
it
Token it
Feature activation+2.793
would
Token would
Feature activation+2.982
give
Token give
Feature activation+2.740
me
Token me
Feature activation+2.560
enough
Token enough
Feature activation+3.377
leg
Token leg
Feature activation+0.879
room
Token room
Feature activation+0.679
.
Token.
Feature activation+0.067
necessary
Token necessary
Feature activation+0.000
to
Token to
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
both
Token both
Feature activation+0.000
big
Token big
Feature activation+0.000
and
Token and
Feature activation+2.466
smaller
Token smaller
Feature activation+0.000
teams
Token teams
Feature activation+0.000
;
Token;
Feature activation+0.013
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.862 - 2.328
CONTAINS 0.003%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
size
Token size
Feature activation+0.000
requires
Token requires
Feature activation+1.288
a
Token a
Feature activation+1.886
different
Token different
Feature activation+0.787
size
Token size
Feature activation+0.124
sole
Token sole
Feature activation+0.013
to
Token to
Feature activation+0.700
be
Token be
Feature activation+0.119
consider
Token consider
Feature activation+0.000
is
Token is
Feature activation+0.000
size
Token size
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+2.676
two
Token two
Feature activation+3.329
well
Token well
Feature activation+2.222
-
Token-
Feature activation+2.335
built
Tokenbuilt
Feature activation+1.258
men
Token men
Feature activation+0.920
in
Token in
Feature activation+0.397
a
Token a
Feature activation+0.092
.
Token.
Feature activation+0.789
A
Token A
Feature activation+2.027
larger
Token larger
Feature activation+2.247
display
Token display
Feature activation+0.586
increases
Token increases
Feature activation+1.843
the
Token the
Feature activation+1.960
visual
Token visual
Feature activation+1.086
angle
Token angle
Feature activation+0.083
at
Token at
Feature activation+0.542
which
Token which
Feature activation+0.606
content
Token content
Feature activation+0.748
big
Token big
Feature activation+0.000
and
Token and
Feature activation+1.626
small
Token small
Feature activation+0.000
would
Token would
Feature activation+0.895
be
Token be
Feature activation+0.879
too
Token too
Feature activation+1.925
small
Token small
Feature activation+0.000
...
Token...
Feature activation+0.522
Also
Token Also
Feature activation+0.452
ships
Token ships
Feature activation+1.676
super
Token super
Feature activation+0.295
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
in
Token in
Feature activation+0.000
towns
Token towns
Feature activation+0.000
large
Token large
Feature activation+0.000
and
Token and
Feature activation+2.115
small
Token small
Feature activation+0.000
,
Token,
Feature activation+0.000
those
Token those
Feature activation+0.000
within
Token within
Feature activation+0.000
resistance
Token resistance
Feature activation+0.000

INTERVAL 1.397 - 1.862
CONTAINS 0.009%

70
Token 70
Feature activation+0.805
mill
Token mill
Feature activation+0.711
imet
Tokenimet
Feature activation+0.000
res
Tokenres
Feature activation+0.847
(
Token (
Feature activation+0.813
2
Token2
Feature activation+1.413
.
Token.
Feature activation+1.277
8
Token8
Feature activation+1.148
in
Token in
Feature activation+0.248
)
Token)
Feature activation+0.717
ÃĹ
Token ÃĹ
Feature activation+0.216
how
Token how
Feature activation+0.000
small
Token small
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.113
.
Token.
Feature activation+0.402
A
Token A
Feature activation+1.662
mere
Token mere
Feature activation+1.257
fifteen
Token fifteen
Feature activation+1.161
players
Token players
Feature activation+0.997
make
Token make
Feature activation+0.562
up
Token up
Feature activation+0.194
lets
Tokenlets
Feature activation+0.000
is
Token is
Feature activation+0.837
0
Token 0
Feature activation+0.775
.
Token.
Feature activation+0.000
18
Token18
Feature activation+1.359
75
Token75
Feature activation+1.458
54
Token54
Feature activation+1.299
square
Token square
Feature activation+0.000
kilometres
Token kilometres
Feature activation+0.409
(
Token (
Feature activation+0.338
46
Token46
Feature activation+0.654
height
Token height
Feature activation+0.342
restrictions
Token restrictions
Feature activation+0.000
in
Token in
Feature activation+0.472
the
Token the
Feature activation+0.020
area
Token area
Feature activation+0.000
around
Token around
Feature activation+1.601
AT
Token AT
Feature activation+0.000
&
Token&
Feature activation+0.000
T
TokenT
Feature activation+0.000
Park
Token Park
Feature activation+0.000
,
Token,
Feature activation+0.000
Size
Token Size
Feature activation+1.465
:
Token:
Feature activation+1.074
640
Token 640
Feature activation+1.646
ÃĹ
Token ÃĹ
Feature activation+1.668
360
Token 360
Feature activation+1.287
480
Token 480
Feature activation+1.824
ÃĹ
Token ÃĹ
Feature activation+1.582
270
Token 270
Feature activation+0.542
Start
Token Start
Feature activation+0.764
at
Token at
Feature activation+0.000
:
Token:
Feature activation+0.250

INTERVAL 0.931 - 1.397
CONTAINS 0.024%

few
Token few
Feature activation+1.125
nan
Token nan
Feature activation+0.494
ometers
Tokenometers
Feature activation+0.721
thick
Token thick
Feature activation+0.000
,
Token,
Feature activation+0.477
any
Token any
Feature activation+1.074
ble
Token ble
Feature activation+0.048
m
Tokenm
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
this
Token this
Feature activation+0.000
line
Token line
Feature activation+0.000
is
Token is
Feature activation+0.015
0
Token 0
Feature activation+0.343
.
Token.
Feature activation+0.081
18
Token18
Feature activation+1.019
at
Token at
Feature activation+0.259
s
Token s
Feature activation+0.000
=
Token =
Feature activation+0.000
50
Token 50
Feature activation+0.000
,
Token,
Feature activation+0.329
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
much
Token much
Feature activation+0.000
smaller
Token smaller
Feature activation+0.195
sum
Token sum
Feature activation+0.000
to
Token to
Feature activation+0.404
the
Token the
Feature activation+1.076
Indian
Token Indian
Feature activation+0.000
Ocean
Token Ocean
Feature activation+0.000
island
Token island
Feature activation+0.000
country
Token country
Feature activation+0.000
.
Token.
Feature activation+0.013
Ċ
TokenĊ
Feature activation+0.000
Download
TokenDownload
Feature activation+0.000
(
Token (
Feature activation+0.000
PDF
TokenPDF
Feature activation+0.000
,
Token,
Feature activation+0.430
372
Token 372
Feature activation+1.112
KB
TokenKB
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+0.000
pounds
Token pounds
Feature activation+0.000
),
Token),
Feature activation+0.619
it
Token it
Feature activation+1.613
's
Token's
Feature activation+1.671
small
Token small
Feature activation+0.676
enough
Token enough
Feature activation+1.163
to
Token to
Feature activation+2.184
take
Token take
Feature activation+1.452
anywhere
Token anywhere
Feature activation+0.490
.
Token.
Feature activation+0.301
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.466 - 0.931
CONTAINS 0.080%

.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.245
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.110
neither
Token neither
Feature activation+0.493
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
-
Token-
Feature activation+0.000
scale
Tokenscale
Feature activation+0.000
partnership
Token partnership
Feature activation+0.000
suddenly
Token suddenly
Feature activation+0.106
became
Token became
Feature activation+1.132
something
Token something
Feature activation+0.703
much
Token much
Feature activation+0.535
more
Token more
Feature activation+0.206
significant
Token significant
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
,
Token,
Feature activation+0.128
Lev
Token Lev
Feature activation+0.000
itic
Tokenitic
Feature activation+0.000
us
Tokenus
Feature activation+1.501
is
Token is
Feature activation+1.358
the
Token the
Feature activation+0.546
shortest
Token shortest
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
Exodus
Token Exodus
Feature activation+0.347
is
Token is
Feature activation+0.339
scale
Tokenscale
Feature activation+0.000
partnership
Token partnership
Feature activation+0.000
suddenly
Token suddenly
Feature activation+0.106
became
Token became
Feature activation+1.132
something
Token something
Feature activation+0.703
much
Token much
Feature activation+0.535
more
Token more
Feature activation+0.206
significant
Token significant
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
US
Token US
Feature activation+0.000
small
Tokensmall
Feature activation+1.256
Height
TokenHeight
Feature activation+0.000
":
Token":
Feature activation+0.110
345
Token345
Feature activation+0.000
,"
Token,"
Feature activation+2.051
big
Tokenbig
Feature activation+0.583
Width
TokenWidth
Feature activation+0.000
":
Token":
Feature activation+0.339
760
Token760
Feature activation+0.000
,"
Token,"
Feature activation+2.572
big
Tokenbig
Feature activation+1.693

INTERVAL 0.000 - 0.466
CONTAINS 99.881%

on
Token on
Feature activation+0.000
my
Token my
Feature activation+0.000
own
Token own
Feature activation+0.000
godd
Token godd
Feature activation+0.000
am
Tokenam
Feature activation+0.000
ned
Tokenned
Feature activation+0.000
space
Token space
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
internet
Token internet
Feature activation+0.000
without
Token without
Feature activation+0.000
halluc
Token halluc
Feature activation+0.000
inate
Tokeninate
Feature activation+0.000
,
Token,
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
objects
Token objects
Feature activation+0.000
and
Token and
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
aren
Token aren
Feature activation+0.000
't
Token't
Feature activation+0.000
there
Token there
Feature activation+0.000
friend
Token friend
Feature activation+0.000
Theo
Token Theo
Feature activation+0.000
.
Token.
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Wal
Token Wal
Feature activation+0.000
cott
Tokencott
Feature activation+0.000
set
Token set
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.000
Dutch
Token Dutch
Feature activation+0.000
man
Tokenman
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
new
Token new
Feature activation+0.000
staffer
Token staffer
Feature activation+0.000
faces
Token faces
Feature activation+0.000
disciplinary
Token disciplinary
Feature activation+0.000
action
Token action
Feature activation+0.000
after
Token after
Feature activation+0.000
a
Token a
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
high
Token high
Feature activation+0.000
point
Token point
Feature activation+0.000
of
Token of
Feature activation+0.000
Beat
Token Beat
Feature activation+0.000
on
Tokenon
Feature activation+0.000
's
Token's
Feature activation+0.000
career
Token career
Feature activation+0.000
to
Token to
Feature activation+0.000
date
Token date
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 H8.8: (feature 14073)

TOP ACTIVATIONS
MAX = 3.313

a
Token a
Feature activation+0.338
mere
Token mere
Feature activation+0.428
five
Token five
Feature activation+0.827
minutes
Token minutes
Feature activation+0.836
can
Token can
Feature activation+2.834
turn
Token turn
Feature activation+3.313
into
Token into
Feature activation+3.107
mission
Token mission
Feature activation+0.278
impossible
Token impossible
Feature activation+0.875
when
Token when
Feature activation+2.322
baby
Token baby
Feature activation+0.856
mere
Token mere
Feature activation+0.428
five
Token five
Feature activation+0.827
minutes
Token minutes
Feature activation+0.836
can
Token can
Feature activation+2.834
turn
Token turn
Feature activation+3.313
into
Token into
Feature activation+3.107
mission
Token mission
Feature activation+0.278
impossible
Token impossible
Feature activation+0.875
when
Token when
Feature activation+2.322
baby
Token baby
Feature activation+0.856
becomes
Token becomes
Feature activation+1.598
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.000
short
Token short
Feature activation+0.000
and
Token and
Feature activation+3.085
long
Token long
Feature activation+0.000
terms
Token terms
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
by
Token by
Feature activation+0.000
Icon
Token Icon
Feature activation+0.000
1000
Token 1000
Feature activation+0.000
Reading
Token Reading
Feature activation+0.000
time
Token time
Feature activation+2.237
:
Token:
Feature activation+2.909
about
Token about
Feature activation+2.265
1
Token 1
Feature activation+1.652
minute
Token minute
Feature activation+1.781
.
Token.
Feature activation+0.882
American
Token American
Feature activation+0.000
taken
Token taken
Feature activation+0.461
a
Token a
Feature activation+0.338
mere
Token mere
Feature activation+0.428
five
Token five
Feature activation+0.827
minutes
Token minutes
Feature activation+0.836
can
Token can
Feature activation+2.834
turn
Token turn
Feature activation+3.313
into
Token into
Feature activation+3.107
mission
Token mission
Feature activation+0.278
impossible
Token impossible
Feature activation+0.875
when
Token when
Feature activation+2.322
is
Token is
Feature activation+0.068
a
Token a
Feature activation+0.000
relatively
Token relatively
Feature activation+0.020
short
Token short
Feature activation+0.124
presentation
Token presentation
Feature activation+0.255
or
Token or
Feature activation+2.738
to
Token to
Feature activation+0.839
allow
Token allow
Feature activation+0.958
enough
Token enough
Feature activation+1.284
time
Token time
Feature activation+0.355
at
Token at
Feature activation+0.599
at
Token at
Feature activation+0.000
his
Token his
Feature activation+0.000
position
Token position
Feature activation+0.000
sooner
Token sooner
Feature activation+0.000
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+2.697
later
Token later
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
3
Token3
Feature activation+0.000
game
Token game
Feature activation+0.000
time
Token time
Feature activation+0.000
clock
Token clock
Feature activation+0.089
is
Token is
Feature activation+1.524
now
Token now
Feature activation+1.241
11
Token 11
Feature activation+2.595
:
Token:
Feature activation+1.006
30
Token30
Feature activation+0.880
,
Token,
Feature activation+0.657
that
Token that
Feature activation+0.132
âĢ
TokenâĢ
Feature activation+0.000
limits
Token limits
Feature activation+0.000
.
Token.
Feature activation+0.151
E
Token E
Feature activation+0.486
.
Token.
Feature activation+0.000
g
Tokeng
Feature activation+0.000
.
Token.
Feature activation+2.442
traditional
Token traditional
Feature activation+1.243
401
Token 401
Feature activation+0.034
(
Token(
Feature activation+0.000
k
Tokenk
Feature activation+0.000
)
Token)
Feature activation+0.000
video
Token video
Feature activation+0.178
card
Token card
Feature activation+0.075
,
Token,
Feature activation+0.540
which
Token which
Feature activation+1.623
is
Token is
Feature activation+2.056
much
Token much
Feature activation+2.390
faster
Token faster
Feature activation+0.684
than
Token than
Feature activation+0.000
I
Token I
Feature activation+0.000
could
Token could
Feature activation+0.254
do
Token do
Feature activation+0.195
,
Token,
Feature activation+1.357
Siri
Token Siri
Feature activation+1.706
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.600
usage
Token usage
Feature activation+2.343
pattern
Token pattern
Feature activation+1.157
made
Token made
Feature activation+1.370
this
Token this
Feature activation+0.343
data
Token data
Feature activation+0.421
transfer
Token transfer
Feature activation+0.986
can
Token can
Feature activation+2.834
turn
Token turn
Feature activation+3.313
into
Token into
Feature activation+3.107
mission
Token mission
Feature activation+0.278
impossible
Token impossible
Feature activation+0.875
when
Token when
Feature activation+2.322
baby
Token baby
Feature activation+0.856
becomes
Token becomes
Feature activation+1.598
hungry
Token hungry
Feature activation+0.928
or
Token or
Feature activation+0.000
needs
Token needs
Feature activation+0.792
equally
Token equally
Feature activation+0.000
;
Token;
Feature activation+0.000
draft
Token draft
Feature activation+0.000
short
Token short
Feature activation+0.000
-
Token-
Feature activation+0.318
and
Token and
Feature activation+2.302
long
Token long
Feature activation+0.397
-
Token-
Feature activation+0.545
term
Tokenterm
Feature activation+0.000
career
Token career
Feature activation+0.000
plans
Token plans
Feature activation+0.000
thought
Token thought
Feature activation+0.000
processes
Token processes
Feature activation+0.000
,
Token,
Feature activation+0.000
long
Token long
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Token and
Feature activation+2.286
short
Token short
Feature activation+0.000
-
Token-
Feature activation+0.000
term
Tokenterm
Feature activation+0.000
memories
Token memories
Feature activation+0.000
,
Token,
Feature activation+0.014
Icon
Token Icon
Feature activation+0.000
1000
Token 1000
Feature activation+0.000
Reading
Token Reading
Feature activation+0.000
time
Token time
Feature activation+2.237
:
Token:
Feature activation+2.909
about
Token about
Feature activation+2.265
1
Token 1
Feature activation+1.652
minute
Token minute
Feature activation+1.781
.
Token.
Feature activation+0.882
American
Token American
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+1.855
There
Token There
Feature activation+1.936
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.040
little
Token little
Feature activation+2.263
any
Token any
Feature activation+0.761
economic
Token economic
Feature activation+0.197
doctor
Token doctor
Feature activation+0.064
can
Token can
Feature activation+0.604
do
Token do
Feature activation+0.271
Bastard
Token Bastard
Feature activation+0.000
by
Token by
Feature activation+0.000
Icon
Token Icon
Feature activation+0.000
1000
Token 1000
Feature activation+0.000
Reading
Token Reading
Feature activation+0.000
time
Token time
Feature activation+2.237
:
Token:
Feature activation+2.909
about
Token about
Feature activation+2.265
1
Token 1
Feature activation+1.652
minute
Token minute
Feature activation+1.781
.
Token.
Feature activation+0.882
sequence
Token sequence
Feature activation+0.000
or
Token or
Feature activation+1.917
that
Token that
Feature activation+1.047
cle
Token cle
Feature activation+0.000
avage
Tokenavage
Feature activation+1.968
occurred
Token occurred
Feature activation+2.191
as
Token as
Feature activation+1.871
expected
Token expected
Feature activation+0.286
three
Token three
Feature activation+2.035
nucle
Token nucle
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
quickly
Token quickly
Feature activation+0.000
,
Token,
Feature activation+0.689
only
Token only
Feature activation+1.989
six
Token six
Feature activation+2.047
or
Token or
Feature activation+0.000
seven
Token seven
Feature activation+2.183
months
Token months
Feature activation+0.747
after
Token after
Feature activation+0.100
he
Token he
Feature activation+0.000
started
Token started
Feature activation+0.000
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
bill
Token bill
Feature activation+0.000
,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.000
contrast
Token contrast
Feature activation+0.000
,
Token,
Feature activation+2.122
would
Token would
Feature activation+1.560
allow
Token allow
Feature activation+0.000
marijuana
Token marijuana
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000

Top DFA by src position
MAX = 3.493

have
Token have
Feature activation+0.016
Top resid features:
taken
Token taken
Feature activation+0.032
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
mere
Token mere
Feature activation+0.028
Top resid features:
five
Token five
Feature activation+0.112
Top resid features:
minutes
Token minutes
Feature activation+3.238
Top resid features:
can
Token can
Feature activation+0.095
Top resid features:
turn
Token turn
Feature activation+0.053
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
mission
Token mission
Feature activation+0.000
Top resid features:
impossible
Token impossible
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.008
Top resid features:
taken
Token taken
Feature activation+0.016
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
mere
Token mere
Feature activation+0.041
Top resid features:
five
Token five
Feature activation+0.273
Top resid features:
minutes
Token minutes
Feature activation+3.032
Top resid features:
can
Token can
Feature activation+0.062
Top resid features:
turn
Token turn
Feature activation+0.043
Top resid features:
into
Token into
Feature activation-0.053
Top resid features:
mission
Token mission
Feature activation+0.000
Top resid features:
impossible
Token impossible
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.002
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.012
Top resid features:
both
Token both
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
short
Token short
Feature activation+3.485
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
long
Token long
Feature activation+0.000
Top resid features:
terms
Token terms
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Bastard
Token Bastard
Feature activation-0.001
Top resid features:
by
Token by
Feature activation+0.004
Top resid features:
Icon
Token Icon
Feature activation+0.002
Top resid features:
1000
Token 1000
Feature activation+0.003
Top resid features:
Reading
Token Reading
Feature activation-0.025
Top resid features:
time
Token time
Feature activation+3.493
Top resid features:
:
Token:
Feature activation-0.061
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
1
Token 1
Feature activation+0.000
Top resid features:
minute
Token minute
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.023
Top resid features:
taken
Token taken
Feature activation+0.121
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
mere
Token mere
Feature activation+0.035
Top resid features:
five
Token five
Feature activation+0.099
Top resid features:
minutes
Token minutes
Feature activation+2.726
Top resid features:
can
Token can
Feature activation+0.031
Top resid features:
turn
Token turn
Feature activation+0.000
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
mission
Token mission
Feature activation+0.000
Top resid features:
impossible
Token impossible
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.106
Top resid features:
it
Token it
Feature activation+0.017
Top resid features:
is
Token is
Feature activation+0.013
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
relatively
Token relatively
Feature activation+0.031
Top resid features:
short
Token short
Feature activation+2.693
Top resid features:
presentation
Token presentation
Feature activation+0.234
Top resid features:
or
Token or
Feature activation+0.037
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
allow
Token allow
Feature activation+0.000
Top resid features:
enough
Token enough
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
best
Token best
Feature activation-0.003
Top resid features:
at
Token at
Feature activation-0.006
Top resid features:
his
Token his
Feature activation-0.011
Top resid features:
position
Token position
Feature activation+0.001
Top resid features:
sooner
Token sooner
Feature activation+3.285
Top resid features:
rather
Token rather
Feature activation+0.003
Top resid features:
than
Token than
Feature activation-0.065
Top resid features:
later
Token later
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
game
Token game
Feature activation+0.025
Top resid features:
time
Token time
Feature activation+0.141
Top resid features:
clock
Token clock
Feature activation+3.049
Top resid features:
is
Token is
Feature activation+0.008
Top resid features:
now
Token now
Feature activation+0.012
Top resid features:
11
Token 11
Feature activation-0.125
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
30
Token30
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.226
Top resid features:
or
Token or
Feature activation+0.005
Top resid features:
time
Token time
Feature activation+2.203
Top resid features:
limits
Token limits
Feature activation+0.526
Top resid features:
.
Token.
Feature activation+0.086
Top resid features:
E
Token E
Feature activation+0.020
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
g
Tokeng
Feature activation+0.053
Top resid features:
take
Token take
Feature activation+0.024
Top resid features:
about
Token about
Feature activation+0.027
Top resid features:
6
Token 6
Feature activation+0.048
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
8
Token8
Feature activation+0.023
Top resid features:
ms
Tokenms
Feature activation+2.121
Top resid features:
/
Token/
Feature activation+0.086
Top resid features:
frame
Tokenframe
Feature activation+0.243
Top resid features:
on
Token on
Feature activation+0.060
Top resid features:
this
Token this
Feature activation+0.010
Top resid features:
video
Token video
Feature activation-0.001
Top resid features:
interaction
Token interaction
Feature activation+0.011
Top resid features:
with
Token with
Feature activation-0.007
Top resid features:
Siri
Token Siri
Feature activation-0.007
Top resid features:
is
Token is
Feature activation+0.030
Top resid features:
relatively
Token relatively
Feature activation+0.016
Top resid features:
short
Token short
Feature activation+1.944
Top resid features:
,
Token,
Feature activation+0.084
Top resid features:
Siri
Token Siri
Feature activation+0.006
Top resid features:
âĢ
TokenâĢ
Feature activation-0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
s
Tokens
Feature activation-0.011
Top resid features:
have
Token have
Feature activation+0.010
Top resid features:
taken
Token taken
Feature activation+0.017
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
mere
Token mere
Feature activation+0.034
Top resid features:
five
Token five
Feature activation+0.305
Top resid features:
minutes
Token minutes
Feature activation+1.907
Top resid features:
can
Token can
Feature activation+0.068
Top resid features:
turn
Token turn
Feature activation+0.046
Top resid features:
into
Token into
Feature activation+0.023
Top resid features:
mission
Token mission
Feature activation+0.007
Top resid features:
impossible
Token impossible
Feature activation+0.007
Top resid features:
house
Token house
Feature activation-0.030
Top resid features:
work
Tokenwork
Feature activation-0.005
Top resid features:
equally
Token equally
Feature activation-0.005
Top resid features:
;
Token;
Feature activation+0.008
Top resid features:
draft
Token draft
Feature activation+0.000
Top resid features:
short
Token short
Feature activation+2.009
Top resid features:
-
Token-
Feature activation+0.878
Top resid features:
and
Token and
Feature activation-0.009
Top resid features:
long
Token long
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
term
Tokenterm
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.003
Top resid features:
complex
Token complex
Feature activation-0.004
Top resid features:
thought
Token thought
Feature activation+0.005
Top resid features:
processes
Token processes
Feature activation+0.028
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
long
Token long
Feature activation+2.048
Top resid features:
-
Token-
Feature activation+0.799
Top resid features:
and
Token and
Feature activation-0.020
Top resid features:
short
Token short
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
term
Tokenterm
Feature activation+0.000
Top resid features:
Bastard
Token Bastard
Feature activation-0.002
Top resid features:
by
Token by
Feature activation+0.004
Top resid features:
Icon
Token Icon
Feature activation+0.001
Top resid features:
1000
Token 1000
Feature activation+0.007
Top resid features:
Reading
Token Reading
Feature activation-0.001
Top resid features:
time
Token time
Feature activation+2.841
Top resid features:
:
Token:
Feature activation-0.022
Top resid features:
about
Token about
Feature activation-0.004
Top resid features:
1
Token 1
Feature activation+0.000
Top resid features:
minute
Token minute
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
But
Token But
Feature activation+0.027
Top resid features:
those
Token those
Feature activation+0.002
Top resid features:
policies
Token policies
Feature activation-0.016
Top resid features:
take
Token take
Feature activation+0.019
Top resid features:
time
Token time
Feature activation+2.303
Top resid features:
.
Token.
Feature activation+0.491
Top resid features:
There
Token There
Feature activation+0.013
Top resid features:
âĢ
TokenâĢ
Feature activation-0.008
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
s
Tokens
Feature activation+0.024
Top resid features:
Bastard
Token Bastard
Feature activation-0.002
Top resid features:
by
Token by
Feature activation+0.005
Top resid features:
Icon
Token Icon
Feature activation+0.002
Top resid features:
1000
Token 1000
Feature activation+0.001
Top resid features:
Reading
Token Reading
Feature activation+0.036
Top resid features:
time
Token time
Feature activation+2.683
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
1
Token 1
Feature activation+0.000
Top resid features:
minute
Token minute
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
whether
Token whether
Feature activation+0.028
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
cle
Token cle
Feature activation+0.004
Top resid features:
avage
Tokenavage
Feature activation+0.007
Top resid features:
happened
Token happened
Feature activation+0.001
Top resid features:
immediately
Token immediately
Feature activation+2.382
Top resid features:
after
Token after
Feature activation+0.183
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
P
Token P
Feature activation+0.001
Top resid features:
AM
TokenAM
Feature activation+0.001
Top resid features:
sequence
Token sequence
Feature activation-0.005
Top resid features:
atell
Tokenatell
Feature activation+0.004
Top resid features:
is
Tokenis
Feature activation+0.001
Top resid features:
were
Token were
Feature activation+0.039
Top resid features:
signed
Token signed
Feature activation-0.060
Top resid features:
relatively
Token relatively
Feature activation+0.005
Top resid features:
quickly
Token quickly
Feature activation+2.561
Top resid features:
,
Token,
Feature activation+0.116
Top resid features:
only
Token only
Feature activation+0.024
Top resid features:
six
Token six
Feature activation-0.029
Top resid features:
or
Token or
Feature activation-0.024
Top resid features:
seven
Token seven
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
program
Token program
Feature activation-0.003
Top resid features:
for
Token for
Feature activation+0.011
Top resid features:
moving
Token moving
Feature activation-0.001
Top resid features:
too
Token too
Feature activation+0.014
Top resid features:
slowly
Token slowly
Feature activation+2.533
Top resid features:
.
Token.
Feature activation+0.037
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Sc
TokenSc
Feature activation+0.002
Top resid features:
ut
Tokenut
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.02

Head 2: 0.03

Head 3: 0.08

Head 4: 0.05

Head 5: 0.07

Head 6: 0.02

Head 7: 0.05

Head 8: 0.44

Head 9: 0.07

Head 10: 0.10

Head 11: 0.03

Positive logits

timeout3.94

timeout3.71

Timeout3.61

delay3.59

elapsed3.59

milliseconds3.57

Delay3.56

timet3.43

pauses3.39

millisec3.38

delayed3.36

delays3.36

delay3.33

timer3.33

seconds3.32

seconds3.28

Timer3.26

interval3.21

instantaneous3.19

timers3.16

Negative logits

-2.01

alien-1.81

fab-1.79

Vinyl-1.77

helm-1.73

ogyn-1.72

Identified-1.71

orn-1.70

igion-1.70

urities-1.70

Gund-1.70

Evil-1.68

Evil-1.68

oros-1.67

gay-1.66

brand-1.65

affiliated-1.64

icultural-1.64

zx-1.62

wcsstore-1.62

INTERVAL 2.982 - 3.313
CONTAINS 0.000%

be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.000
short
Token short
Feature activation+0.000
and
Token and
Feature activation+3.085
long
Token long
Feature activation+0.000
terms
Token terms
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
a
Token a
Feature activation+0.338
mere
Token mere
Feature activation+0.428
five
Token five
Feature activation+0.827
minutes
Token minutes
Feature activation+0.836
can
Token can
Feature activation+2.834
turn
Token turn
Feature activation+3.313
into
Token into
Feature activation+3.107
mission
Token mission
Feature activation+0.278
impossible
Token impossible
Feature activation+0.875
when
Token when
Feature activation+2.322
baby
Token baby
Feature activation+0.856
mere
Token mere
Feature activation+0.428
five
Token five
Feature activation+0.827
minutes
Token minutes
Feature activation+0.836
can
Token can
Feature activation+2.834
turn
Token turn
Feature activation+3.313
into
Token into
Feature activation+3.107
mission
Token mission
Feature activation+0.278
impossible
Token impossible
Feature activation+0.875
when
Token when
Feature activation+2.322
baby
Token baby
Feature activation+0.856
becomes
Token becomes
Feature activation+1.598

INTERVAL 2.651 - 2.982
CONTAINS 0.000%

is
Token is
Feature activation+0.068
a
Token a
Feature activation+0.000
relatively
Token relatively
Feature activation+0.020
short
Token short
Feature activation+0.124
presentation
Token presentation
Feature activation+0.255
or
Token or
Feature activation+2.738
to
Token to
Feature activation+0.839
allow
Token allow
Feature activation+0.958
enough
Token enough
Feature activation+1.284
time
Token time
Feature activation+0.355
at
Token at
Feature activation+0.599
taken
Token taken
Feature activation+0.461
a
Token a
Feature activation+0.338
mere
Token mere
Feature activation+0.428
five
Token five
Feature activation+0.827
minutes
Token minutes
Feature activation+0.836
can
Token can
Feature activation+2.834
turn
Token turn
Feature activation+3.313
into
Token into
Feature activation+3.107
mission
Token mission
Feature activation+0.278
impossible
Token impossible
Feature activation+0.875
when
Token when
Feature activation+2.322
by
Token by
Feature activation+0.000
Icon
Token Icon
Feature activation+0.000
1000
Token 1000
Feature activation+0.000
Reading
Token Reading
Feature activation+0.000
time
Token time
Feature activation+2.237
:
Token:
Feature activation+2.909
about
Token about
Feature activation+2.265
1
Token 1
Feature activation+1.652
minute
Token minute
Feature activation+1.781
.
Token.
Feature activation+0.882
American
Token American
Feature activation+0.000
at
Token at
Feature activation+0.000
his
Token his
Feature activation+0.000
position
Token position
Feature activation+0.000
sooner
Token sooner
Feature activation+0.000
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+2.697
later
Token later
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
3
Token3
Feature activation+0.000

INTERVAL 2.319 - 2.651
CONTAINS 0.001%

game
Token game
Feature activation+0.000
time
Token time
Feature activation+0.000
clock
Token clock
Feature activation+0.089
is
Token is
Feature activation+1.524
now
Token now
Feature activation+1.241
11
Token 11
Feature activation+2.595
:
Token:
Feature activation+1.006
30
Token30
Feature activation+0.880
,
Token,
Feature activation+0.657
that
Token that
Feature activation+0.132
âĢ
TokenâĢ
Feature activation+0.000
limits
Token limits
Feature activation+0.000
.
Token.
Feature activation+0.151
E
Token E
Feature activation+0.486
.
Token.
Feature activation+0.000
g
Tokeng
Feature activation+0.000
.
Token.
Feature activation+2.442
traditional
Token traditional
Feature activation+1.243
401
Token 401
Feature activation+0.034
(
Token(
Feature activation+0.000
k
Tokenk
Feature activation+0.000
)
Token)
Feature activation+0.000
video
Token video
Feature activation+0.178
card
Token card
Feature activation+0.075
,
Token,
Feature activation+0.540
which
Token which
Feature activation+1.623
is
Token is
Feature activation+2.056
much
Token much
Feature activation+2.390
faster
Token faster
Feature activation+0.684
than
Token than
Feature activation+0.000
I
Token I
Feature activation+0.000
could
Token could
Feature activation+0.254
do
Token do
Feature activation+0.195
can
Token can
Feature activation+2.834
turn
Token turn
Feature activation+3.313
into
Token into
Feature activation+3.107
mission
Token mission
Feature activation+0.278
impossible
Token impossible
Feature activation+0.875
when
Token when
Feature activation+2.322
baby
Token baby
Feature activation+0.856
becomes
Token becomes
Feature activation+1.598
hungry
Token hungry
Feature activation+0.928
or
Token or
Feature activation+0.000
needs
Token needs
Feature activation+0.792
,
Token,
Feature activation+1.357
Siri
Token Siri
Feature activation+1.706
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.600
usage
Token usage
Feature activation+2.343
pattern
Token pattern
Feature activation+1.157
made
Token made
Feature activation+1.370
this
Token this
Feature activation+0.343
data
Token data
Feature activation+0.421
transfer
Token transfer
Feature activation+0.986

INTERVAL 1.988 - 2.319
CONTAINS 0.002%

sequence
Token sequence
Feature activation+0.000
or
Token or
Feature activation+1.917
that
Token that
Feature activation+1.047
cle
Token cle
Feature activation+0.000
avage
Tokenavage
Feature activation+1.968
occurred
Token occurred
Feature activation+2.191
as
Token as
Feature activation+1.871
expected
Token expected
Feature activation+0.286
three
Token three
Feature activation+2.035
nucle
Token nucle
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
to
Token to
Feature activation+0.393
reach
Token reach
Feature activation+0.000
Earth
Token Earth
Feature activation+0.294
,
Token,
Feature activation+0.349
and
Token and
Feature activation+0.621
another
Token another
Feature activation+2.019
21
Token 21
Feature activation+1.250
minutes
Token minutes
Feature activation+0.288
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
response
Token response
Feature activation+0.984
Bastard
Token Bastard
Feature activation+0.000
by
Token by
Feature activation+0.000
Icon
Token Icon
Feature activation+0.000
1000
Token 1000
Feature activation+0.000
Reading
Token Reading
Feature activation+0.000
time
Token time
Feature activation+2.237
:
Token:
Feature activation+2.909
about
Token about
Feature activation+2.265
1
Token 1
Feature activation+1.652
minute
Token minute
Feature activation+1.781
.
Token.
Feature activation+0.882
equally
Token equally
Feature activation+0.000
;
Token;
Feature activation+0.000
draft
Token draft
Feature activation+0.000
short
Token short
Feature activation+0.000
-
Token-
Feature activation+0.318
and
Token and
Feature activation+2.302
long
Token long
Feature activation+0.397
-
Token-
Feature activation+0.545
term
Tokenterm
Feature activation+0.000
career
Token career
Feature activation+0.000
plans
Token plans
Feature activation+0.000
a
Token a
Feature activation+0.687
child
Token child
Feature activation+0.491
is
Token is
Feature activation+0.852
not
Token not
Feature activation+1.124
born
Token born
Feature activation+1.675
at
Token at
Feature activation+2.104
exactly
Token exactly
Feature activation+1.345
the
Token the
Feature activation+0.650
same
Token same
Feature activation+0.000
time
Token time
Feature activation+0.159
as
Token as
Feature activation+0.000

INTERVAL 1.657 - 1.988
CONTAINS 0.004%

immediately
Token immediately
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.445
later
Token later
Feature activation+1.804
in
Token in
Feature activation+1.658
the
Token the
Feature activation+0.500
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
a
Token a
Feature activation+0.000
proper
Token proper
Feature activation+0.000
book
Token book
Feature activation+0.163
proposal
Token proposal
Feature activation+0.000
as
Token as
Feature activation+0.186
too
Token too
Feature activation+1.872
risky
Token risky
Feature activation+0.000
.[
Token.[
Feature activation+0.000
10
Token10
Feature activation+0.000
]
Token]
Feature activation+0.000
However
Token However
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Set
TokenSet
Feature activation+0.000
a
Token a
Feature activation+0.000
timer
Token timer
Feature activation+0.000
for
Token for
Feature activation+1.425
30
Token 30
Feature activation+1.689
minutes
Token minutes
Feature activation+0.426
when
Token when
Feature activation+0.404
you
Token you
Feature activation+0.409
put
Token put
Feature activation+0.000
your
Token your
Feature activation+0.000
time
Token time
Feature activation+0.931
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.351
contractual
Token contractual
Feature activation+0.254
hours
Token hours
Feature activation+0.488
from
Token from
Feature activation+1.658
07
Token 07
Feature activation+1.167
00
Token00
Feature activation+0.678
-
Token-
Feature activation+0.762
1900
Token1900
Feature activation+0.512
Mon
Token Mon
Feature activation+0.000
it
Token it
Feature activation+0.000
set
Token set
Feature activation+0.000
for
Token for
Feature activation+0.000
15
Token 15
Feature activation+0.432
minutes
Token minutes
Feature activation+0.000
or
Token or
Feature activation+1.856
so
Token so
Feature activation+0.822
.
Token.
Feature activation+0.135
This
Token This
Feature activation+0.154
can
Token can
Feature activation+0.103
be
Token be
Feature activation+0.130

INTERVAL 1.325 - 1.657
CONTAINS 0.009%

short
Token short
Feature activation+0.149
,
Token,
Feature activation+1.357
Siri
Token Siri
Feature activation+1.706
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.600
usage
Token usage
Feature activation+2.343
pattern
Token pattern
Feature activation+1.157
made
Token made
Feature activation+1.370
this
Token this
Feature activation+0.343
data
Token data
Feature activation+0.421
already
Token already
Feature activation+0.000
extend
Token extend
Feature activation+0.000
your
Token your
Feature activation+0.000
game
Token game
Feature activation+0.000
time
Token time
Feature activation+0.183
by
Token by
Feature activation+1.641
upgrading
Token upgrading
Feature activation+0.000
your
Token your
Feature activation+0.509
bundle
Token bundle
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.332
I
Token I
Feature activation+0.191
set
Token set
Feature activation+1.405
a
Token a
Feature activation+1.175
timer
Token timer
Feature activation+0.465
for
Token for
Feature activation+1.572
just
Token just
Feature activation+1.714
half
Token half
Feature activation+1.410
an
Token an
Feature activation+1.523
hour
Token hour
Feature activation+1.029
.
Token.
Feature activation+0.000
he
Token he
Feature activation+0.209
had
Token had
Feature activation+0.668
had
Token had
Feature activation+0.723
seven
Token seven
Feature activation+0.676
or
Token or
Feature activation+0.000
eight
Token eight
Feature activation+1.523
years
Token years
Feature activation+0.408
of
Token of
Feature activation+0.124
really
Token really
Feature activation+0.000
trying
Token trying
Feature activation+0.000
and
Token and
Feature activation+0.000
child
Token child
Feature activation+0.491
is
Token is
Feature activation+0.852
not
Token not
Feature activation+1.124
born
Token born
Feature activation+1.675
at
Token at
Feature activation+2.104
exactly
Token exactly
Feature activation+1.345
the
Token the
Feature activation+0.650
same
Token same
Feature activation+0.000
time
Token time
Feature activation+0.159
as
Token as
Feature activation+0.000
one
Token one
Feature activation+0.000

INTERVAL 0.994 - 1.325
CONTAINS 0.022%

the
Token the
Feature activation+0.000
idea
Token idea
Feature activation+0.000
that
Token that
Feature activation+0.134
the
Token the
Feature activation+0.356
game
Token game
Feature activation+0.353
could
Token could
Feature activation+1.044
be
Token be
Feature activation+1.119
delayed
Token delayed
Feature activation+0.658
.
Token.
Feature activation+0.526
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.150
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+1.362
get
Token get
Feature activation+1.336
out
Token out
Feature activation+1.139
of
Token of
Feature activation+1.010
the
Token the
Feature activation+0.371
hole
Token hole
Feature activation+0.203
.
Token.
Feature activation+0.190
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
was
Token was
Feature activation+0.000
on
Token on
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.249
he
Token he
Feature activation+0.000
was
Token was
Feature activation+1.073
patient
Token patient
Feature activation+0.242
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.080
listened
Token listened
Feature activation+0.375
,
Token,
Feature activation+0.000
ruck
Tokenruck
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
cabin
Token cabin
Feature activation+0.000
.
Token.
Feature activation+0.175
He
Token He
Feature activation+1.137
called
Token called
Feature activation+0.000
me
Token me
Feature activation+0.000
asking
Token asking
Feature activation+0.000
me
Token me
Feature activation+0.000
to
Token to
Feature activation+0.000
At
Token At
Feature activation+0.209
first
Token first
Feature activation+0.196
,
Token,
Feature activation+0.332
I
Token I
Feature activation+0.191
set
Token set
Feature activation+1.405
a
Token a
Feature activation+1.175
timer
Token timer
Feature activation+0.465
for
Token for
Feature activation+1.572
just
Token just
Feature activation+1.714
half
Token half
Feature activation+1.410
an
Token an
Feature activation+1.523

INTERVAL 0.663 - 0.994
CONTAINS 0.058%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
expression
Token expression
Feature activation+0.000
,
Token,
Feature activation+0.603
and
Token and
Feature activation+0.842
then
Token then
Feature activation+0.205
the
Token the
Feature activation+0.128
underlying
Token underlying
Feature activation+0.000
memory
Token memory
Feature activation+0.000
is
Token is
Feature activation+0.096
if
Token if
Feature activation+0.551
they
Token they
Feature activation+0.577
were
Token were
Feature activation+0.612
asked
Token asked
Feature activation+0.953
to
Token to
Feature activation+1.241
take
Token take
Feature activation+0.873
only
Token only
Feature activation+0.959
20
Token 20
Feature activation+0.761
minutes
Token minutes
Feature activation+0.515
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
,
Token,
Feature activation+0.098
a
Token a
Feature activation+0.448
fraction
Token fraction
Feature activation+1.110
of
Token of
Feature activation+0.711
a
Token a
Feature activation+1.039
second
Token second
Feature activation+0.914
in
Token in
Feature activation+0.148
reaction
Token reaction
Feature activation+0.451
time
Token time
Feature activation+0.165
makes
Token makes
Feature activation+2.030
all
Token all
Feature activation+1.059
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
particular
Token particular
Feature activation+0.042
situation
Token situation
Feature activation+0.473
,
Token,
Feature activation+0.827
van
Token van
Feature activation+0.000
Ri
Token Ri
Feature activation+0.000
ems
Tokenems
Feature activation+0.000
dy
Tokendy
Feature activation+0.000
k
Tokenk
Feature activation+1.144
turn
Token turn
Feature activation+3.313
into
Token into
Feature activation+3.107
mission
Token mission
Feature activation+0.278
impossible
Token impossible
Feature activation+0.875
when
Token when
Feature activation+2.322
baby
Token baby
Feature activation+0.856
becomes
Token becomes
Feature activation+1.598
hungry
Token hungry
Feature activation+0.928
or
Token or
Feature activation+0.000
needs
Token needs
Feature activation+0.792
a
Token a
Feature activation+0.375

INTERVAL 0.331 - 0.663
CONTAINS 0.174%

started
Token started
Feature activation+0.000
to
Token to
Feature activation+0.000
feel
Token feel
Feature activation+0.000
off
Token off
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.350
the
Token the
Feature activation+0.021
experience
Token experience
Feature activation+0.000
sounds
Token sounds
Feature activation+0.000
almost
Token almost
Feature activation+0.000
metaphysical
Token metaphysical
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
//
Token//
Feature activation+0.240
lets
Token lets
Feature activation+0.417
set
Token set
Feature activation+0.459
the
Token the
Feature activation+0.428
duration
Token duration
Feature activation+0.427
to
Token to
Feature activation+2.032
1
Token 1
Feature activation+1.493
.
Token.
Feature activation+0.881
0
Token0
Feature activation+0.696
have
Token have
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
shortcuts
Token shortcuts
Feature activation+0.000
to
Token to
Feature activation+0.370
quickly
Token quickly
Feature activation+0.558
open
Token open
Feature activation+0.585
the
Token the
Feature activation+0.069
apps
Token apps
Feature activation+0.000
you
Token you
Feature activation+0.000
nice
Token nice
Feature activation+0.000
just
Token just
Feature activation+0.000
to
Token to
Feature activation+0.000
catch
Token catch
Feature activation+0.000
up
Token up
Feature activation+0.566
on
Token on
Feature activation+0.533
a
Token a
Feature activation+0.306
lot
Token lot
Feature activation+0.186
of
Token of
Feature activation+0.266
things
Token things
Feature activation+0.000
I
Token I
Feature activation+0.552
the
Token the
Feature activation+0.000
tough
Token tough
Feature activation+0.000
connecting
Token connecting
Feature activation+0.000
tissue
Token tissue
Feature activation+0.000
take
Token take
Feature activation+0.000
time
Token time
Feature activation+0.520
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
but
Token but
Feature activation+1.259
break
Token break
Feature activation+1.101
down
Token down
Feature activation+0.619

INTERVAL 0.000 - 0.331
CONTAINS 99.730%

emissions
Token emissions
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Co
TokenCo
Feature activation+0.000
ast
Tokenast
Feature activation+0.000
al
Tokenal
Feature activation+0.000
erosion
Token erosion
Feature activation+0.000
reveals
Token reveals
Feature activation+0.000
the
Token the
Feature activation+0.000
ice
Token ice
Feature activation+0.000
"
Token"
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
I
Token I
Feature activation+0.000
thought
Token thought
Feature activation+0.000
stood
Token stood
Feature activation+0.000
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
was
Token was
Feature activation+0.000
for
Token for
Feature activation+0.000
those
Token those
Feature activation+0.000
about
Token about
Feature activation+0.000
possible
Token possible
Feature activation+0.000
riots
Token riots
Feature activation+0.000
or
Token or
Feature activation+0.000
up
Token up
Feature activation+0.000
ris
Tokenris
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
should
Token should
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
neighborhood
Token neighborhood
Feature activation+0.000
UK
Token UK
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
When
TokenWhen
Feature activation+0.000
you
Token you
Feature activation+0.000
hear
Token hear
Feature activation+0.000
politicians
Token politicians
Feature activation+0.000
call
Token call
Feature activation+0.000
for
Token for
Feature activation+0.000
USA
Token USA
Feature activation+0.000
,
Token,
Feature activation+0.000
Virtual
Token Virtual
Feature activation+0.000
En
Token En
Feature activation+0.000
vironments
Tokenvironments
Feature activation+0.000
and
Token and
Feature activation+0.000
Virtual
Token Virtual
Feature activation+0.000
Worlds
Token Worlds
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
R
Token R
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 H8.8: (feature 2140)

TOP ACTIVATIONS
MAX = 2.450

lots
Token lots
Feature activation+0.000
of
Token of
Feature activation+0.000
money
Token money
Feature activation+0.300
but
Token but
Feature activation+0.460
my
Token my
Feature activation+1.338
mum
Token mum
Feature activation+2.450
was
Token was
Feature activation+1.865
termin
Token termin
Feature activation+0.000
ally
Tokenally
Feature activation+0.343
ill
Token ill
Feature activation+0.206
and
Token and
Feature activation+0.322
down
Token down
Feature activation+0.000
14
Token 14
Feature activation+0.338
.
Token.
Feature activation+0.068
7
Token7
Feature activation+0.913
%
Token%
Feature activation+0.000
to
Token to
Feature activation+2.423
$
Token $
Feature activation+1.150
89
Token89
Feature activation+0.668
.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.470
-
Token-
Feature activation+0.000
highest
Token highest
Feature activation+0.000
-
Token-
Feature activation+0.000
paid
Tokenpaid
Feature activation+0.000
running
Token running
Feature activation+0.000
back
Token back
Feature activation+0.000
with
Token with
Feature activation+2.359
an
Token an
Feature activation+1.653
average
Token average
Feature activation+1.813
annual
Token annual
Feature activation+0.887
value
Token value
Feature activation+0.000
of
Token of
Feature activation+1.124
dollar
Token dollar
Feature activation+0.326
amount
Token amount
Feature activation+0.056
,
Token,
Feature activation+1.135
the
Token the
Feature activation+1.161
father
Token father
Feature activation+0.302
used
Token used
Feature activation+2.356
a
Token a
Feature activation+2.180
cryptic
Token cryptic
Feature activation+0.327
series
Token series
Feature activation+0.000
of
Token of
Feature activation+0.245
âĢ
Token âĢ
Feature activation+0.000
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
too
Token too
Feature activation+0.000
little
Token little
Feature activation+0.000
money
Token money
Feature activation+0.261
to
Token to
Feature activation+2.335
hire
Token hire
Feature activation+0.043
a
Token a
Feature activation+0.328
donkey
Token donkey
Feature activation+0.000
to
Token to
Feature activation+0.531
ride
Token ride
Feature activation+0.000
price
Token price
Feature activation+0.000
.
Token.
Feature activation+0.502
Instead
Token Instead
Feature activation+0.560
,
Token,
Feature activation+1.051
most
Token most
Feature activation+1.139
will
Token will
Feature activation+2.317
qualify
Token qualify
Feature activation+1.110
either
Token either
Feature activation+0.765
for
Token for
Feature activation+0.972
Medicaid
Token Medicaid
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
are
Token are
Feature activation+0.000
free
Token free
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+2.127
of
Token of
Feature activation+1.434
them
Token them
Feature activation+2.201
will
Token will
Feature activation+2.137
require
Token require
Feature activation+2.096
a
Token a
Feature activation+1.290
small
Token small
Feature activation+0.577
fee
Token fee
Feature activation+0.000
amount
Token amount
Feature activation+0.056
,
Token,
Feature activation+1.135
the
Token the
Feature activation+1.161
father
Token father
Feature activation+0.302
used
Token used
Feature activation+2.356
a
Token a
Feature activation+2.180
cryptic
Token cryptic
Feature activation+0.327
series
Token series
Feature activation+0.000
of
Token of
Feature activation+0.245
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
free
Token free
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+2.127
of
Token of
Feature activation+1.434
them
Token them
Feature activation+2.201
will
Token will
Feature activation+2.137
require
Token require
Feature activation+2.096
a
Token a
Feature activation+1.290
small
Token small
Feature activation+0.577
fee
Token fee
Feature activation+0.000
to
Token to
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
are
Token are
Feature activation+0.000
free
Token free
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+2.127
of
Token of
Feature activation+1.434
them
Token them
Feature activation+2.201
will
Token will
Feature activation+2.137
require
Token require
Feature activation+2.096
a
Token a
Feature activation+1.290
and
Token and
Feature activation+0.000
some
Token some
Feature activation+2.127
of
Token of
Feature activation+1.434
them
Token them
Feature activation+2.201
will
Token will
Feature activation+2.137
require
Token require
Feature activation+2.096
a
Token a
Feature activation+1.290
small
Token small
Feature activation+0.577
fee
Token fee
Feature activation+0.000
to
Token to
Feature activation+0.000
buy
Token buy
Feature activation+0.000
tax
Token tax
Feature activation+0.000
provision
Token provision
Feature activation+0.000
that
Token that
Feature activation+0.354
allows
Token allows
Feature activation+1.166
them
Token them
Feature activation+0.787
to
Token to
Feature activation+2.077
defer
Token defer
Feature activation+0.853
(
Token (
Feature activation+0.000
not
Tokennot
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
)
Token)
Feature activation+0.445
of
Token of
Feature activation+0.000
income
Token income
Feature activation+0.000
so
Token so
Feature activation+1.244
the
Token the
Feature activation+0.890
household
Token household
Feature activation+1.329
was
Token was
Feature activation+2.046
not
Token not
Feature activation+1.855
affluent
Token affluent
Feature activation+0.079
and
Token and
Feature activation+0.661
it
Token it
Feature activation+0.865
was
Token was
Feature activation+0.785
basketball
Token basketball
Feature activation+1.046
program
Token program
Feature activation+1.136
works
Token works
Feature activation+1.354
out
Token out
Feature activation+0.513
to
Token to
Feature activation+1.288
about
Token about
Feature activation+2.037
a
Token a
Feature activation+1.604
break
Token break
Feature activation+0.132
-
Token-
Feature activation+0.262
even
Tokeneven
Feature activation+0.000
status
Token status
Feature activation+0.000
average
Token average
Feature activation+0.551
NFL
Token NFL
Feature activation+0.000
player
Token player
Feature activation+0.593
salary
Token salary
Feature activation+0.000
exploded
Token exploded
Feature activation+0.060
from
Token from
Feature activation+1.980
$
Token $
Feature activation+1.515
27
Token27
Feature activation+0.708
,
Token,
Feature activation+0.148
500
Token500
Feature activation+0.502
in
Token in
Feature activation+0.820
industry
Token industry
Feature activation+0.015
rule
Token rule
Feature activation+0.000
of
Token of
Feature activation+0.537
thumb
Token thumb
Feature activation+0.000
is
Token is
Feature activation+0.382
that
Token that
Feature activation+1.910
it
Token it
Feature activation+1.838
costs
Token costs
Feature activation+0.250
about
Token about
Feature activation+0.578
10
Token 10
Feature activation+0.728
times
Token times
Feature activation+0.000
of
Token of
Feature activation+0.000
money
Token money
Feature activation+0.300
but
Token but
Feature activation+0.460
my
Token my
Feature activation+1.338
mum
Token mum
Feature activation+2.450
was
Token was
Feature activation+1.865
termin
Token termin
Feature activation+0.000
ally
Tokenally
Feature activation+0.343
ill
Token ill
Feature activation+0.206
and
Token and
Feature activation+0.322
I
Token I
Feature activation+0.271
income
Token income
Feature activation+0.000
so
Token so
Feature activation+1.244
the
Token the
Feature activation+0.890
household
Token household
Feature activation+1.329
was
Token was
Feature activation+2.046
not
Token not
Feature activation+1.855
affluent
Token affluent
Feature activation+0.079
and
Token and
Feature activation+0.661
it
Token it
Feature activation+0.865
was
Token was
Feature activation+0.785
a
Token a
Feature activation+1.140
we
Token we
Feature activation+0.000
agree
Token agree
Feature activation+0.000
payment
Token payment
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
a
Tokena
Feature activation+0.365
few
Token few
Feature activation+1.853
hundred
Token hundred
Feature activation+1.341
dollars
Token dollars
Feature activation+0.492
.
Token.
Feature activation+0.000
Rather
Token Rather
Feature activation+0.000
than
Token than
Feature activation+0.505
's
Token's
Feature activation+0.395
net
Token net
Feature activation+0.000
worth
Token worth
Feature activation+0.000
skyrocket
Token skyrocket
Feature activation+0.000
ed
Tokened
Feature activation+0.000
from
Token from
Feature activation+1.851
$
Token $
Feature activation+0.582
7
Token7
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
million
Token million
Feature activation+0.005

Top DFA by src position
MAX = 3.243

didn
Token didn
Feature activation+0.016
Top resid features:
't
Token't
Feature activation+0.013
Top resid features:
have
Token have
Feature activation+0.019
Top resid features:
lots
Token lots
Feature activation+0.020
Top resid features:
of
Token of
Feature activation+0.016
Top resid features:
money
Token money
Feature activation+2.567
Top resid features:
but
Token but
Feature activation+0.046
Top resid features:
my
Token my
Feature activation+0.040
Top resid features:
mum
Token mum
Feature activation+0.069
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
termin
Token termin
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
National
Token National
Feature activation+0.005
Top resid features:
Post
Token Post
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
said
Token said
Feature activation+0.006
Top resid features:
revenue
Token revenue
Feature activation+3.243
Top resid features:
from
Token from
Feature activation-0.003
Top resid features:
print
Token print
Feature activation+0.003
Top resid features:
advertising
Token advertising
Feature activation+0.031
Top resid features:
was
Token was
Feature activation-0.015
Top resid features:
down
Token down
Feature activation-0.009
Top resid features:
âĢ
TokenâĢ
Feature activation+0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.012
Top resid features:
s
Tokens
Feature activation+0.015
Top resid features:
highest
Token highest
Feature activation-0.002
Top resid features:
-
Token-
Feature activation-0.010
Top resid features:
paid
Tokenpaid
Feature activation+3.153
Top resid features:
running
Token running
Feature activation+0.002
Top resid features:
back
Token back
Feature activation-0.008
Top resid features:
with
Token with
Feature activation-0.056
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
average
Token average
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Instead
TokenInstead
Feature activation+0.007
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
a
Token a
Feature activation-0.024
Top resid features:
dollar
Token dollar
Feature activation+1.743
Top resid features:
amount
Token amount
Feature activation+1.045
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
father
Token father
Feature activation+0.025
Top resid features:
used
Token used
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
I
Token I
Feature activation-0.004
Top resid features:
had
Token had
Feature activation+0.025
Top resid features:
too
Token too
Feature activation+0.030
Top resid features:
little
Token little
Feature activation+0.123
Top resid features:
money
Token money
Feature activation+2.656
Top resid features:
to
Token to
Feature activation+0.023
Top resid features:
hire
Token hire
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
donkey
Token donkey
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
have
Token have
Feature activation-0.002
Top resid features:
to
Token to
Feature activation-0.062
Top resid features:
pay
Token pay
Feature activation+0.599
Top resid features:
the
Token the
Feature activation+0.083
Top resid features:
full
Token full
Feature activation+0.748
Top resid features:
price
Token price
Feature activation+1.147
Top resid features:
.
Token.
Feature activation+0.060
Top resid features:
Instead
Token Instead
Feature activation+0.035
Top resid features:
,
Token,
Feature activation+0.044
Top resid features:
most
Token most
Feature activation+0.021
Top resid features:
will
Token will
Feature activation+0.054
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Some
Token Some
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.007
Top resid features:
them
Token them
Feature activation+0.005
Top resid features:
are
Token are
Feature activation+0.056
Top resid features:
free
Token free
Feature activation+2.543
Top resid features:
and
Token and
Feature activation+0.029
Top resid features:
some
Token some
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
them
Token them
Feature activation+0.015
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Instead
TokenInstead
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
dollar
Token dollar
Feature activation+1.719
Top resid features:
amount
Token amount
Feature activation+0.867
Top resid features:
,
Token,
Feature activation+0.034
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
father
Token father
Feature activation+0.010
Top resid features:
used
Token used
Feature activation-0.011
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Some
Token Some
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
them
Token them
Feature activation+0.011
Top resid features:
are
Token are
Feature activation+0.006
Top resid features:
free
Token free
Feature activation+2.443
Top resid features:
and
Token and
Feature activation+0.075
Top resid features:
some
Token some
Feature activation+0.001
Top resid features:
of
Token of
Feature activation-0.007
Top resid features:
them
Token them
Feature activation+0.024
Top resid features:
will
Token will
Feature activation+0.054
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Some
Token Some
Feature activation+0.010
Top resid features:
of
Token of
Feature activation+0.020
Top resid features:
them
Token them
Feature activation+0.003
Top resid features:
are
Token are
Feature activation+0.059
Top resid features:
free
Token free
Feature activation+2.508
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
some
Token some
Feature activation+0.037
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
them
Token them
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Some
Token Some
Feature activation+0.003
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
them
Token them
Feature activation+0.009
Top resid features:
are
Token are
Feature activation+0.004
Top resid features:
free
Token free
Feature activation+2.479
Top resid features:
and
Token and
Feature activation+0.040
Top resid features:
some
Token some
Feature activation+0.003
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
them
Token them
Feature activation+0.019
Top resid features:
will
Token will
Feature activation+0.048
Top resid features:
able
Token able
Feature activation+0.011
Top resid features:
make
Token make
Feature activation-0.002
Top resid features:
use
Token use
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.050
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
tax
Token tax
Feature activation+2.304
Top resid features:
provision
Token provision
Feature activation+0.072
Top resid features:
that
Token that
Feature activation+0.024
Top resid features:
allows
Token allows
Feature activation+0.061
Top resid features:
them
Token them
Feature activation+0.040
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
not
Token not
Feature activation+0.004
Top resid features:
have
Token have
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
lot
Token lot
Feature activation+0.088
Top resid features:
of
Token of
Feature activation+0.016
Top resid features:
income
Token income
Feature activation+2.186
Top resid features:
so
Token so
Feature activation+0.123
Top resid features:
the
Token the
Feature activation+0.063
Top resid features:
household
Token household
Feature activation+0.034
Top resid features:
was
Token was
Feature activation+0.010
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
generally
Token generally
Feature activation+0.004
Top resid features:
cover
Token cover
Feature activation+0.007
Top resid features:
their
Token their
Feature activation+0.004
Top resid features:
own
Token own
Feature activation+0.005
Top resid features:
program
Token program
Feature activation+0.044
Top resid features:
costs
Token costs
Feature activation+2.428
Top resid features:
when
Token when
Feature activation+0.010
Top resid features:
fact
Token fact
Feature activation+0.001
Top resid features:
oring
Tokenoring
Feature activation+0.009
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
scholarships
Token scholarships
Feature activation+0.212
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
average
Token average
Feature activation+0.000
Top resid features:
NFL
Token NFL
Feature activation+0.005
Top resid features:
player
Token player
Feature activation+0.003
Top resid features:
salary
Token salary
Feature activation+2.260
Top resid features:
exploded
Token exploded
Feature activation+0.110
Top resid features:
from
Token from
Feature activation-0.172
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
27
Token27
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
made
Token made
Feature activation-0.002
Top resid features:
for
Token for
Feature activation+0.001
Top resid features:
reasons
Token reasons
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
cost
Token cost
Feature activation+2.131
Top resid features:
.
Token.
Feature activation+0.031
Top resid features:
The
Token The
Feature activation+0.006
Top resid features:
industry
Token industry
Feature activation-0.014
Top resid features:
rule
Token rule
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+0.057
Top resid features:
didn
Token didn
Feature activation+0.016
Top resid features:
't
Token't
Feature activation+0.006
Top resid features:
have
Token have
Feature activation+0.022
Top resid features:
lots
Token lots
Feature activation+0.023
Top resid features:
of
Token of
Feature activation+0.018
Top resid features:
money
Token money
Feature activation+1.974
Top resid features:
but
Token but
Feature activation+0.091
Top resid features:
my
Token my
Feature activation+0.032
Top resid features:
mum
Token mum
Feature activation+0.101
Top resid features:
was
Token was
Feature activation+0.010
Top resid features:
termin
Token termin
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.003
Top resid features:
have
Token have
Feature activation+0.012
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
lot
Token lot
Feature activation+0.077
Top resid features:
of
Token of
Feature activation+0.021
Top resid features:
income
Token income
Feature activation+1.870
Top resid features:
so
Token so
Feature activation+0.168
Top resid features:
the
Token the
Feature activation+0.065
Top resid features:
household
Token household
Feature activation+0.036
Top resid features:
was
Token was
Feature activation+0.088
Top resid features:
not
Token not
Feature activation+0.042
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Next
TokenNext
Feature activation+0.001
Top resid features:
we
Token we
Feature activation-0.017
Top resid features:
agree
Token agree
Feature activation-0.006
Top resid features:
payment
Token payment
Feature activation+2.115
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.193
Top resid features:
a
Tokena
Feature activation+0.022
Top resid features:
few
Token few
Feature activation-0.053
Top resid features:
hundred
Token hundred
Feature activation+0.000
Top resid features:
dollars
Token dollars
Feature activation+0.000
Top resid features:
âĢĵ
TokenâĢĵ
Feature activation+0.018
Top resid features:
the
Tokenthe
Feature activation-0.004
Top resid features:
couple
Token couple
Feature activation+0.016
Top resid features:
's
Token's
Feature activation+0.011
Top resid features:
net
Token net
Feature activation-0.011
Top resid features:
worth
Token worth
Feature activation+2.093
Top resid features:
skyrocket
Token skyrocket
Feature activation+0.038
Top resid features:
ed
Tokened
Feature activation+0.041
Top resid features:
from
Token from
Feature activation-0.176
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
7
Token7
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.01

Head 2: 0.05

Head 3: 0.07

Head 4: 0.05

Head 5: 0.05

Head 6: 0.02

Head 7: 0.04

Head 8: 0.44

Head 9: 0.08

Head 10: 0.09

Head 11: 0.04

Positive logits

expenses5.11

payments4.85

repayment4.77

money4.68

revenues4.65

coffers4.64

revenue4.62

cash4.62

salaries4.60

expenditures4.59

funds4.58

fees4.58

finances4.53

reimburse4.51

payment4.43

financing4.42

income4.39

taxpayers4.37

debts4.35

cash4.33

Negative logits

aptic-2.27

osite-2.18

Sensor-2.17

mosqu-2.17

keyes-2.14

ophen-2.14

heastern-2.13

ipolar-2.13

zai-2.13

colo-2.05

��-1.96

ModLoader-1.94

>[-1.94

vibration-1.92

atible-1.91

MODE-1.90

sonic-1.89

lon-1.89

vibrations-1.89

atibility-1.88

INTERVAL 2.205 - 2.450
CONTAINS 0.001%

down
Token down
Feature activation+0.000
14
Token 14
Feature activation+0.338
.
Token.
Feature activation+0.068
7
Token7
Feature activation+0.913
%
Token%
Feature activation+0.000
to
Token to
Feature activation+2.423
$
Token $
Feature activation+1.150
89
Token89
Feature activation+0.668
.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.470
-
Token-
Feature activation+0.000
highest
Token highest
Feature activation+0.000
-
Token-
Feature activation+0.000
paid
Tokenpaid
Feature activation+0.000
running
Token running
Feature activation+0.000
back
Token back
Feature activation+0.000
with
Token with
Feature activation+2.359
an
Token an
Feature activation+1.653
average
Token average
Feature activation+1.813
annual
Token annual
Feature activation+0.887
value
Token value
Feature activation+0.000
of
Token of
Feature activation+1.124
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
too
Token too
Feature activation+0.000
little
Token little
Feature activation+0.000
money
Token money
Feature activation+0.261
to
Token to
Feature activation+2.335
hire
Token hire
Feature activation+0.043
a
Token a
Feature activation+0.328
donkey
Token donkey
Feature activation+0.000
to
Token to
Feature activation+0.531
ride
Token ride
Feature activation+0.000
dollar
Token dollar
Feature activation+0.326
amount
Token amount
Feature activation+0.056
,
Token,
Feature activation+1.135
the
Token the
Feature activation+1.161
father
Token father
Feature activation+0.302
used
Token used
Feature activation+2.356
a
Token a
Feature activation+2.180
cryptic
Token cryptic
Feature activation+0.327
series
Token series
Feature activation+0.000
of
Token of
Feature activation+0.245
âĢ
Token âĢ
Feature activation+0.000
lots
Token lots
Feature activation+0.000
of
Token of
Feature activation+0.000
money
Token money
Feature activation+0.300
but
Token but
Feature activation+0.460
my
Token my
Feature activation+1.338
mum
Token mum
Feature activation+2.450
was
Token was
Feature activation+1.865
termin
Token termin
Feature activation+0.000
ally
Tokenally
Feature activation+0.343
ill
Token ill
Feature activation+0.206
and
Token and
Feature activation+0.322

INTERVAL 1.960 - 2.205
CONTAINS 0.001%

of
Token of
Feature activation+0.000
income
Token income
Feature activation+0.000
so
Token so
Feature activation+1.244
the
Token the
Feature activation+0.890
household
Token household
Feature activation+1.329
was
Token was
Feature activation+2.046
not
Token not
Feature activation+1.855
affluent
Token affluent
Feature activation+0.079
and
Token and
Feature activation+0.661
it
Token it
Feature activation+0.865
was
Token was
Feature activation+0.785
free
Token free
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+2.127
of
Token of
Feature activation+1.434
them
Token them
Feature activation+2.201
will
Token will
Feature activation+2.137
require
Token require
Feature activation+2.096
a
Token a
Feature activation+1.290
small
Token small
Feature activation+0.577
fee
Token fee
Feature activation+0.000
to
Token to
Feature activation+0.000
tax
Token tax
Feature activation+0.000
provision
Token provision
Feature activation+0.000
that
Token that
Feature activation+0.354
allows
Token allows
Feature activation+1.166
them
Token them
Feature activation+0.787
to
Token to
Feature activation+2.077
defer
Token defer
Feature activation+0.853
(
Token (
Feature activation+0.000
not
Tokennot
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
)
Token)
Feature activation+0.445
are
Token are
Feature activation+0.000
free
Token free
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+2.127
of
Token of
Feature activation+1.434
them
Token them
Feature activation+2.201
will
Token will
Feature activation+2.137
require
Token require
Feature activation+2.096
a
Token a
Feature activation+1.290
small
Token small
Feature activation+0.577
fee
Token fee
Feature activation+0.000
of
Token of
Feature activation+0.000
them
Token them
Feature activation+0.000
are
Token are
Feature activation+0.000
free
Token free
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+2.127
of
Token of
Feature activation+1.434
them
Token them
Feature activation+2.201
will
Token will
Feature activation+2.137
require
Token require
Feature activation+2.096
a
Token a
Feature activation+1.290

INTERVAL 1.715 - 1.960
CONTAINS 0.002%

of
Token of
Feature activation+0.000
money
Token money
Feature activation+0.300
but
Token but
Feature activation+0.460
my
Token my
Feature activation+1.338
mum
Token mum
Feature activation+2.450
was
Token was
Feature activation+1.865
termin
Token termin
Feature activation+0.000
ally
Tokenally
Feature activation+0.343
ill
Token ill
Feature activation+0.206
and
Token and
Feature activation+0.322
I
Token I
Feature activation+0.271
industry
Token industry
Feature activation+0.015
rule
Token rule
Feature activation+0.000
of
Token of
Feature activation+0.537
thumb
Token thumb
Feature activation+0.000
is
Token is
Feature activation+0.382
that
Token that
Feature activation+1.910
it
Token it
Feature activation+1.838
costs
Token costs
Feature activation+0.250
about
Token about
Feature activation+0.578
10
Token 10
Feature activation+0.728
times
Token times
Feature activation+0.000
we
Token we
Feature activation+0.000
rely
Token rely
Feature activation+0.000
on
Token on
Feature activation+0.636
ad
Token ad
Feature activation+0.040
revenue
Token revenue
Feature activation+0.000
to
Token to
Feature activation+1.823
keep
Token keep
Feature activation+0.789
the
Token the
Feature activation+1.019
lights
Token lights
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.541
's
Token's
Feature activation+0.395
net
Token net
Feature activation+0.000
worth
Token worth
Feature activation+0.000
skyrocket
Token skyrocket
Feature activation+0.000
ed
Tokened
Feature activation+0.000
from
Token from
Feature activation+1.851
$
Token $
Feature activation+0.582
7
Token7
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
million
Token million
Feature activation+0.005
income
Token income
Feature activation+0.000
so
Token so
Feature activation+1.244
the
Token the
Feature activation+0.890
household
Token household
Feature activation+1.329
was
Token was
Feature activation+2.046
not
Token not
Feature activation+1.855
affluent
Token affluent
Feature activation+0.079
and
Token and
Feature activation+0.661
it
Token it
Feature activation+0.865
was
Token was
Feature activation+0.785
a
Token a
Feature activation+1.140

INTERVAL 1.470 - 1.715
CONTAINS 0.004%

8
Token8
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
but
Token but
Feature activation+0.000
others
Token others
Feature activation+0.858
said
Token said
Feature activation+1.474
they
Token they
Feature activation+1.716
got
Token got
Feature activation+1.222
as
Token as
Feature activation+0.903
little
Token little
Feature activation+0.412
as
Token as
Feature activation+0.133
,
Token,
Feature activation+0.000
saw
Token saw
Feature activation+0.013
his
Token his
Feature activation+0.759
salary
Token salary
Feature activation+0.000
increase
Token increase
Feature activation+0.000
from
Token from
Feature activation+1.615
$
Token $
Feature activation+1.615
187
Token187
Feature activation+1.130
,
Token,
Feature activation+0.184
000
Token000
Feature activation+0.166
to
Token to
Feature activation+0.369
:
Token:
Feature activation+0.252
part
Token part
Feature activation+0.385
of
Token of
Feature activation+0.317
the
Token the
Feature activation+0.636
AFL
Token AFL
Feature activation+0.687
's
Token's
Feature activation+1.503
motivation
Token motivation
Feature activation+0.042
for
Token for
Feature activation+0.867
the
Token the
Feature activation+0.878
tax
Token tax
Feature activation+0.256
is
Token is
Feature activation+0.177
offset
Token offset
Feature activation+0.000
artists
Token artists
Feature activation+0.098
can
Token can
Feature activation+0.740
qualify
Token qualify
Feature activation+0.000
for
Token for
Feature activation+0.000
from
Token from
Feature activation+1.535
the
Token the
Feature activation+0.247
current
Token current
Feature activation+1.215
$
Token $
Feature activation+0.858
500
Token500
Feature activation+0.487
for
Token for
Feature activation+0.278
scholarships
Token scholarships
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.561
some
Token some
Feature activation+0.548
schools
Token schools
Feature activation+1.044
,
Token,
Feature activation+1.597
even
Token even
Feature activation+1.112
the
Token the
Feature activation+1.046
men
Token men
Feature activation+0.018
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 1.225 - 1.470
CONTAINS 0.012%

a
Token a
Feature activation+0.000
performance
Token performance
Feature activation+0.000
for
Token for
Feature activation+0.000
free
Token free
Feature activation+0.088
,
Token,
Feature activation+0.719
or
Token or
Feature activation+1.289
sharing
Token sharing
Feature activation+0.232
the
Token the
Feature activation+0.160
work
Token work
Feature activation+0.126
they
Token they
Feature activation+0.000
've
Token've
Feature activation+0.044
lif
Token lif
Feature activation+0.000
eline
Tokeneline
Feature activation+0.000
at
Token at
Feature activation+0.479
a
Token a
Feature activation+0.063
time
Token time
Feature activation+0.000
when
Token when
Feature activation+1.229
donor
Token donor
Feature activation+0.285
support
Token support
Feature activation+0.184
is
Token is
Feature activation+0.098
in
Token in
Feature activation+0.000
desperately
Token desperately
Feature activation+0.000
have
Token have
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
income
Token income
Feature activation+0.000
so
Token so
Feature activation+1.244
the
Token the
Feature activation+0.890
household
Token household
Feature activation+1.329
was
Token was
Feature activation+2.046
not
Token not
Feature activation+1.855
affluent
Token affluent
Feature activation+0.079
medical
Token medical
Feature activation+0.000
bills
Token bills
Feature activation+0.000
are
Token are
Feature activation+0.562
likely
Token likely
Feature activation+0.736
to
Token to
Feature activation+0.957
be
Token be
Feature activation+1.235
steep
Token steep
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.099
in
Token in
Feature activation+0.522
the
Token the
Feature activation+0.502
range
Token range
Feature activation+0.421
at
Token at
Feature activation+0.070
all
Token all
Feature activation+0.067
.
Token.
Feature activation+0.730
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.444
The
TokenThe
Feature activation+1.285
aim
Token aim
Feature activation+0.000
here
Token here
Feature activation+0.075
,
Token,
Feature activation+0.000
Give
Token Give
Feature activation+0.610
Direct
TokenDirect
Feature activation+0.000

INTERVAL 0.980 - 1.225
CONTAINS 0.028%

of
Token of
Feature activation+0.566
a
Token a
Feature activation+0.718
dollar
Token dollar
Feature activation+0.326
amount
Token amount
Feature activation+0.056
,
Token,
Feature activation+1.135
the
Token the
Feature activation+1.161
father
Token father
Feature activation+0.302
used
Token used
Feature activation+2.356
a
Token a
Feature activation+2.180
cryptic
Token cryptic
Feature activation+0.327
series
Token series
Feature activation+0.000
taxes
Token taxes
Feature activation+0.000
,
Token,
Feature activation+0.023
at
Token at
Feature activation+0.431
more
Token more
Feature activation+0.572
than
Token than
Feature activation+0.347
$
Token $
Feature activation+1.144
2
Token2
Feature activation+0.638
,
Token,
Feature activation+0.000
600
Token600
Feature activation+0.045
per
Token per
Feature activation+1.279
person
Token person
Feature activation+0.000
upheld
Token upheld
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
will
Token will
Feature activation+0.000
buy
Token buy
Feature activation+0.000
and
Token and
Feature activation+1.114
sell
Token sell
Feature activation+0.000
guns
Token guns
Feature activation+0.000
from
Token from
Feature activation+0.000
whom
Token whom
Feature activation+0.000
we
Token we
Feature activation+0.280
$
Token $
Feature activation+0.000
8
Token8
Feature activation+0.000
million
Token million
Feature activation+0.000
.
Token.
Feature activation+0.000
Which
Token Which
Feature activation+0.069
is
Token is
Feature activation+0.998
about
Token about
Feature activation+0.382
$
Token $
Feature activation+0.000
2
Token2
Feature activation+0.142
million
Token million
Feature activation+0.000
more
Token more
Feature activation+0.074
For
Token For
Feature activation+0.561
some
Token some
Feature activation+0.548
schools
Token schools
Feature activation+1.044
,
Token,
Feature activation+1.597
even
Token even
Feature activation+1.112
the
Token the
Feature activation+1.046
men
Token men
Feature activation+0.018
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
basketball
Token basketball
Feature activation+1.046

INTERVAL 0.735 - 0.980
CONTAINS 0.066%

of
Token of
Feature activation+0.364
the
Token the
Feature activation+1.121
roughly
Token roughly
Feature activation+0.363
80
Token 80
Feature activation+0.540
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.889
people
Token people
Feature activation+0.737
who
Token who
Feature activation+1.145
are
Token are
Feature activation+0.414
wounded
Token wounded
Feature activation+0.097
by
Token by
Feature activation+0.168
By
Token By
Feature activation+0.191
law
Token law
Feature activation+0.031
,
Token,
Feature activation+0.588
the
Token the
Feature activation+0.593
commission
Token commission
Feature activation+0.140
can
Token can
Feature activation+0.760
bring
Token bring
Feature activation+0.157
only
Token only
Feature activation+0.337
civil
Token civil
Feature activation+0.000
cases
Token cases
Feature activation+0.000
.
Token.
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.718
tax
Token tax
Feature activation+0.076
cuts
Token cuts
Feature activation+0.000
do
Token do
Feature activation+0.910
not
Token not
Feature activation+1.159
pay
Token pay
Feature activation+0.137
for
Token for
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Manafort
Token Manafort
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.758
work
Token work
Feature activation+0.000
in
Token in
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+0.000
appeared
Token appeared
Feature activation+0.000
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
F
TokenF
Feature activation+0.000
ee
Tokenee
Feature activation+0.000
:
Token:
Feature activation+0.882
FREE
Token FREE
Feature activation+0.161
!
Token!
Feature activation+0.000
Level
Token Level
Feature activation+0.000
:
Token:
Feature activation+0.104
all
Token all
Feature activation+0.421

INTERVAL 0.490 - 0.735
CONTAINS 0.156%

isons
Tokenisons
Feature activation+0.000
depend
Token depend
Feature activation+0.000
on
Token on
Feature activation+0.000
this
Token this
Feature activation+0.000
income
Token income
Feature activation+0.000
.
Token.
Feature activation+0.628
Corporate
Token Corporate
Feature activation+0.634
stock
Token stock
Feature activation+0.070
holders
Tokenholders
Feature activation+0.744
who
Token who
Feature activation+0.693
make
Token make
Feature activation+0.264
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
balance
Token balance
Feature activation+0.000
between
Token between
Feature activation+0.000
commercial
Token commercial
Feature activation+0.004
and
Token and
Feature activation+0.558
residential
Token residential
Feature activation+0.000
tax
Token tax
Feature activation+0.102
rates
Token rates
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
?
Token?
Feature activation+0.000
What
Token What
Feature activation+0.000
about
Token about
Feature activation+0.000
money
Token money
Feature activation+0.129
-
Token-
Feature activation+0.374
making
Tokenmaking
Feature activation+0.532
schemes
Token schemes
Feature activation+0.034
wrapped
Token wrapped
Feature activation+0.000
up
Token up
Feature activation+0.258
in
Token in
Feature activation+0.329
socially
Token socially
Feature activation+0.160
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
that
Token that
Feature activation+0.490
there
Token there
Feature activation+0.528
was
Token was
Feature activation+0.518
enough
Token enough
Feature activation+0.715
money
Token money
Feature activation+0.000
left
Token left
Feature activation+0.476
over
Token over
Feature activation+0.000
was
Token was
Feature activation+0.000
simply
Token simply
Feature activation+0.000
financial
Token financial
Feature activation+0.000
.
Token.
Feature activation+0.412
Until
Token Until
Feature activation+0.622
the
Token the
Feature activation+0.515
French
Token French
Feature activation+0.000
Revolution
Token Revolution
Feature activation+0.000
,
Token,
Feature activation+0.994
the
Token the
Feature activation+0.230
Catholic
Token Catholic
Feature activation+0.622

INTERVAL 0.245 - 0.490
CONTAINS 0.411%

of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
bankruptcy
Token bankruptcy
Feature activation+0.000
and
Token and
Feature activation+0.000
need
Token need
Feature activation+0.000
for
Token for
Feature activation+0.382
a
Token a
Feature activation+0.248
bailout
Token bailout
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
feds
Token feds
Feature activation+0.000
and
Token and
Feature activation+0.204
what
Token what
Feature activation+0.605
it
Token it
Feature activation+1.311
gets
Token gets
Feature activation+1.317
back
Token back
Feature activation+0.396
.
Token.
Feature activation+0.000
New
Token New
Feature activation+0.269
Jersey
Token Jersey
Feature activation+0.339
has
Token has
Feature activation+0.531
the
Token the
Feature activation+0.432
especially
Token especially
Feature activation+0.000
those
Token those
Feature activation+0.000
receiving
Token receiving
Feature activation+0.155
government
Token government
Feature activation+0.080
grants
Token grants
Feature activation+0.000
for
Token for
Feature activation+0.365
their
Token their
Feature activation+0.360
confirmation
Token confirmation
Feature activation+0.000
bias
Token bias
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
who
Token who
Feature activation+0.340
are
Token are
Feature activation+0.254
clearly
Token clearly
Feature activation+0.138
vested
Token vested
Feature activation+0.000
in
Token in
Feature activation+0.000
not
Token not
Feature activation+0.323
seeing
Token seeing
Feature activation+0.281
this
Token this
Feature activation+0.222
thing
Token thing
Feature activation+0.162
passed
Token passed
Feature activation+0.098
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
relation
Token relation
Feature activation+0.000
to
Token to
Feature activation+0.000
men
Token men
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.287
studies
Token studies
Feature activation+0.000
suggest
Token suggest
Feature activation+1.131
that
Token that
Feature activation+0.718
in
Token in
Feature activation+0.468
general
Token general
Feature activation+0.701

INTERVAL 0.000 - 0.245
CONTAINS 99.321%

own
Token own
Feature activation+0.000
debt
Token debt
Feature activation+0.000
crisis
Token crisis
Feature activation+0.000
,
Token,
Feature activation+0.000
Latin
Token Latin
Feature activation+0.000
America
Token America
Feature activation+0.000
now
Token now
Feature activation+0.514
looks
Token looks
Feature activation+0.000
like
Token like
Feature activation+0.000
an
Token an
Feature activation+0.122
enticing
Token enticing
Feature activation+0.000
Chairman
Token Chairman
Feature activation+0.000
Tom
Token Tom
Feature activation+0.000
Wheeler
Token Wheeler
Feature activation+0.000
promised
Token promised
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
that
Token that
Feature activation+0.000
power
Token power
Feature activation+0.000
,
Token,
Feature activation+0.000
congressional
Token congressional
Feature activation+0.000
and
Token and
Feature activation+0.000
hours
Token hours
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Bass
Token Bass
Feature activation+0.000
ano
Tokenano
Feature activation+0.000
recalls
Token recalls
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
that
Token that
Feature activation+0.000
rare
Token rare
Feature activation+0.000
political
Token political
Feature activation+0.000
figure
Token figure
Feature activation+0.000
who
Token who
Feature activation+0.000
really
Token really
Feature activation+0.000
accomplished
Token accomplished
Feature activation+0.000
her
Token her
Feature activation+0.000
life
Token life
Feature activation+0.000
's
Token's
Feature activation+0.000
work
Token work
Feature activation+0.000
Royal
Token Royal
Feature activation+0.000
Navy
Token Navy
Feature activation+0.000
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
worth
Token worth
Feature activation+0.000
highlighting
Token highlighting
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
Royal
Token Royal
Feature activation+0.000
Navy
Token Navy
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 H8.8: (feature 17590)

TOP ACTIVATIONS
MAX = 4.471

fill
Tokenfill
Feature activation+0.000
routers
Token routers
Feature activation+0.000
from
Token from
Feature activation+0.000
5
Token 5
Feature activation+0.000
to
Token to
Feature activation+3.922
almost
Token almost
Feature activation+4.471
100
Token 100
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
increased
Token increased
Feature activation+0.000
reliability
Token reliability
Feature activation+0.000
flood
Token flood
Feature activation+0.000
fill
Tokenfill
Feature activation+0.000
routers
Token routers
Feature activation+0.000
from
Token from
Feature activation+0.000
5
Token 5
Feature activation+0.000
to
Token to
Feature activation+3.922
almost
Token almost
Feature activation+4.471
100
Token 100
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
increased
Token increased
Feature activation+0.000
than
Token than
Feature activation+0.000
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
km
Token km
Feature activation+0.000
(
Token (
Feature activation+3.908
1
Token1
Feature activation+0.000
,
Token,
Feature activation+0.000
200
Token200
Feature activation+0.000
miles
Token miles
Feature activation+0.000
)
Token)
Feature activation+0.000
site
Token site
Feature activation+0.000
is
Token is
Feature activation+0.000
located
Token located
Feature activation+0.000
7
Token 7
Feature activation+0.000
kilometres
Token kilometres
Feature activation+0.000
(
Token (
Feature activation+3.800
4
Token4
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token3
Feature activation+0.000
mi
Token mi
Feature activation+0.000
)
Token)
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
voters
Token voters
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
and
Token and
Feature activation+0.000
6
Token 6
Feature activation+0.000
in
Token in
Feature activation+3.770
10
Token 10
Feature activation+0.000
independents
Token independents
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
said
Token said
Feature activation+0.000
they
Token they
Feature activation+0.000
and
Token and
Feature activation+0.000
polished
Token polished
Feature activation+0.000
demo
Token demo
Feature activation+0.000
in
Token in
Feature activation+0.000
4
Token 4
Feature activation+0.000
to
Token to
Feature activation+3.617
5
Token 5
Feature activation+0.451
months
Token months
Feature activation+0.000
so
Token so
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
vote
Token vote
Feature activation+0.000
of
Token of
Feature activation+0.000
6
Token 6
Feature activation+0.000
to
Token to
Feature activation+3.550
3
Token 3
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Three
TokenThree
Feature activation+0.000
heights
Token heights
Feature activation+0.000
forecast
Token forecast
Feature activation+0.000
ed
Tokened
Feature activation+0.000
at
Token at
Feature activation+0.000
4
Token 4
Feature activation+0.000
to
Token to
Feature activation+3.417
8
Token 8
Feature activation+0.088
feet
Token feet
Feature activation+0.000
along
Token along
Feature activation+0.000
the
Token the
Feature activation+0.000
coast
Token coast
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+1.422
4
Token 4
Feature activation+0.000
and
Token and
Feature activation+3.398
1
Token 1
Feature activation+0.000
stamps
Token stamps
Feature activation+0.000
auto
Token auto
Feature activation+0.000
-
Token-
Feature activation+0.000
filled
Tokenfilled
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
surge
Token surge
Feature activation+0.000
may
Token may
Feature activation+0.000
climb
Token climb
Feature activation+0.234
to
Token to
Feature activation+3.359
11
Token 11
Feature activation+0.000
feet
Token feet
Feature activation+0.000
in
Token in
Feature activation+0.000
bodies
Token bodies
Feature activation+0.000
of
Token of
Feature activation+0.000
ill
Tokenill
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
3
Token 3
Feature activation+0.000
-
Token-
Feature activation+0.014
to
Token to
Feature activation+3.331
5
Token 5
Feature activation+0.926
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
3
Token3
Feature activation+0.000
focused
Token focused
Feature activation+0.000
unit
Token unit
Feature activation+0.000
charges
Token charges
Feature activation+0.000
3
Token 3
Feature activation+0.000
and
Token and
Feature activation+3.324
includes
Token includes
Feature activation+0.000
external
Token external
Feature activation+0.000
USB
Token USB
Feature activation+0.000
battery
Token battery
Feature activation+0.000
-
Token-
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
election
Token election
Feature activation+0.000
,
Token,
Feature activation+0.000
9
Token 9
Feature activation+0.000
in
Token in
Feature activation+3.305
10
Token 10
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
voters
Token voters
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
and
Token and
Feature activation+0.000
five
Token five
Feature activation+0.000
mutations
Token mutations
Feature activation+0.000
in
Token in
Feature activation+0.000
just
Token just
Feature activation+0.000
3
Token 3
Feature activation+0.000
to
Token to
Feature activation+3.245
4
Token 4
Feature activation+0.277
weeks
Token weeks
Feature activation+0.000
,
Token,
Feature activation+0.000
whereas
Token whereas
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
9
Token 9
Feature activation+0.000
of
Token of
Feature activation+3.224
9
Token 9
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
fourth
Token fourth
Feature activation+0.000
quarter
Token quarter
Feature activation+0.000
spread
Token spread
Feature activation+0.000
over
Token over
Feature activation+0.000
6
Token 6
Feature activation+0.000
square
Token square
Feature activation+0.000
miles
Token miles
Feature activation+0.000
(
Token (
Feature activation+3.160
16
Token16
Feature activation+0.016
square
Token square
Feature activation+0.000
km
Token km
Feature activation+0.000
),
Token),
Feature activation+0.000
but
Token but
Feature activation+0.000
ble
Tokenble
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
6
Token 6
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Token to
Feature activation+3.152
14
Token 14
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
dec
Token dec
Feature activation+0.000
adal
Tokenadal
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
rises
Token rises
Feature activation+0.000
to
Token to
Feature activation+0.000
5
Token 5
Feature activation+0.000
-
Token-
Feature activation+3.149
19
Token19
Feature activation+0.000
percent
Token percent
Feature activation+0.000
in
Token in
Feature activation+0.000
net
Token net
Feature activation+0.000
-
Token-
Feature activation+0.000
Beck
Token Beck
Feature activation+0.000
worth
Tokenworth
Feature activation+0.000
suggests
Token suggests
Feature activation+0.000
it
Token it
Feature activation+1.690
is
Token is
Feature activation+2.793
actually
Token actually
Feature activation+3.092
the
Token the
Feature activation+1.170
range
Token range
Feature activation+0.237
of
Token of
Feature activation+0.000
1
Token 1
Feature activation+0.000
%
Token%
Feature activation+0.000
if
Tokenif
Feature activation+0.000
would
Token would
Feature activation+0.000
take
Token take
Feature activation+0.000
about
Token about
Feature activation+0.000
6
Token 6
Feature activation+0.000
-
Token-
Feature activation+3.079
8
Token8
Feature activation+0.605
ms
Tokenms
Feature activation+0.000
/
Token/
Feature activation+0.258
frame
Tokenframe
Feature activation+0.000
on
Token on
Feature activation+0.000

Top DFA by src position
MAX = 4.768

in
Token in
Feature activation+0.016
Top resid features:
flood
Token flood
Feature activation-0.008
Top resid features:
fill
Tokenfill
Feature activation+0.005
Top resid features:
routers
Token routers
Feature activation+0.007
Top resid features:
from
Token from
Feature activation+0.042
Top resid features:
5
Token 5
Feature activation+4.768
Top resid features:
to
Token to
Feature activation+0.324
Top resid features:
almost
Token almost
Feature activation+0.071
Top resid features:
100
Token 100
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
flood
Token flood
Feature activation-0.002
Top resid features:
fill
Tokenfill
Feature activation+0.001
Top resid features:
routers
Token routers
Feature activation+0.024
Top resid features:
from
Token from
Feature activation-0.036
Top resid features:
5
Token 5
Feature activation+4.660
Top resid features:
to
Token to
Feature activation+0.051
Top resid features:
almost
Token almost
Feature activation+0.000
Top resid features:
100
Token 100
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
southern
Token southern
Feature activation-0.017
Top resid features:
zone
Token zone
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
more
Token more
Feature activation+0.016
Top resid features:
than
Token than
Feature activation+0.003
Top resid features:
2
Token 2
Feature activation+4.291
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
000
Token000
Feature activation+0.009
Top resid features:
km
Token km
Feature activation+0.268
Top resid features:
(
Token (
Feature activation-0.002
Top resid features:
1
Token1
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.022
Top resid features:
The
Token The
Feature activation-0.025
Top resid features:
site
Token site
Feature activation+0.002
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
located
Token located
Feature activation+0.028
Top resid features:
7
Token 7
Feature activation+4.105
Top resid features:
kilometres
Token kilometres
Feature activation+0.323
Top resid features:
(
Token (
Feature activation+0.028
Top resid features:
4
Token4
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
3
Token3
Feature activation+0.000
Top resid features:
10
Token 10
Feature activation+0.125
Top resid features:
Republican
Token Republican
Feature activation-0.006
Top resid features:
voters
Token voters
Feature activation-0.004
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
6
Token 6
Feature activation+4.261
Top resid features:
in
Token in
Feature activation-0.030
Top resid features:
10
Token 10
Feature activation+0.000
Top resid features:
independents
Token independents
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
made
Token made
Feature activation+0.014
Top resid features:
and
Token and
Feature activation-0.011
Top resid features:
polished
Token polished
Feature activation+0.003
Top resid features:
demo
Token demo
Feature activation-0.015
Top resid features:
in
Token in
Feature activation+0.012
Top resid features:
4
Token 4
Feature activation+4.245
Top resid features:
to
Token to
Feature activation+0.062
Top resid features:
5
Token 5
Feature activation+0.000
Top resid features:
months
Token months
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.001
Top resid features:
by
Token by
Feature activation+0.002
Top resid features:
a
Token a
Feature activation-0.011
Top resid features:
vote
Token vote
Feature activation-0.004
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
6
Token 6
Feature activation+4.157
Top resid features:
to
Token to
Feature activation+0.019
Top resid features:
3
Token 3
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:
surge
Token surge
Feature activation-0.000
Top resid features:
heights
Token heights
Feature activation+0.009
Top resid features:
forecast
Token forecast
Feature activation+0.021
Top resid features:
ed
Tokened
Feature activation+0.018
Top resid features:
at
Token at
Feature activation+0.023
Top resid features:
4
Token 4
Feature activation+4.002
Top resid features:
to
Token to
Feature activation+0.070
Top resid features:
8
Token 8
Feature activation+0.000
Top resid features:
feet
Token feet
Feature activation+0.000
Top resid features:
along
Token along
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
as
Tokenas
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
with
Token with
Feature activation+0.022
Top resid features:
2
Token 2
Feature activation+1.278
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
4
Token 4
Feature activation+2.729
Top resid features:
and
Token and
Feature activation+0.022
Top resid features:
1
Token 1
Feature activation+0.000
Top resid features:
stamps
Token stamps
Feature activation+0.000
Top resid features:
auto
Token auto
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
surge
Token surge
Feature activation-0.006
Top resid features:
heights
Token heights
Feature activation+0.049
Top resid features:
forecast
Token forecast
Feature activation+0.001
Top resid features:
ed
Tokened
Feature activation+0.005
Top resid features:
at
Token at
Feature activation+0.005
Top resid features:
4
Token 4
Feature activation+3.318
Top resid features:
to
Token to
Feature activation+0.025
Top resid features:
8
Token 8
Feature activation+0.245
Top resid features:
feet
Token feet
Feature activation+0.259
Top resid features:
along
Token along
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
inst
Token inst
Feature activation+0.011
Top resid features:
ill
Tokenill
Feature activation+0.006
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
its
Token its
Feature activation-0.004
Top resid features:
3
Token 3
Feature activation+3.774
Top resid features:
-
Token-
Feature activation+0.146
Top resid features:
to
Token to
Feature activation+0.185
Top resid features:
5
Token 5
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
year
Tokenyear
Feature activation+0.000
Top resid features:
PS
Token PS
Feature activation-0.035
Top resid features:
3
Token3
Feature activation-0.014
Top resid features:
focused
Token focused
Feature activation+0.004
Top resid features:
unit
Token unit
Feature activation-0.027
Top resid features:
charges
Token charges
Feature activation+0.049
Top resid features:
3
Token 3
Feature activation+3.748
Top resid features:
and
Token and
Feature activation+0.019
Top resid features:
includes
Token includes
Feature activation+0.000
Top resid features:
external
Token external
Feature activation+0.000
Top resid features:
USB
Token USB
Feature activation+0.000
Top resid features:
battery
Token battery
Feature activation+0.000
Top resid features:
shortly
Token shortly
Feature activation-0.004
Top resid features:
before
Token before
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
election
Token election
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
9
Token 9
Feature activation+4.098
Top resid features:
in
Token in
Feature activation-0.044
Top resid features:
10
Token 10
Feature activation+0.000
Top resid features:
Republican
Token Republican
Feature activation+0.000
Top resid features:
voters
Token voters
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.016
Top resid features:
five
Token five
Feature activation+0.037
Top resid features:
mutations
Token mutations
Feature activation+0.017
Top resid features:
in
Token in
Feature activation+0.021
Top resid features:
just
Token just
Feature activation+0.040
Top resid features:
3
Token 3
Feature activation+3.791
Top resid features:
to
Token to
Feature activation+0.047
Top resid features:
4
Token 4
Feature activation+0.000
Top resid features:
weeks
Token weeks
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
whereas
Token whereas
Feature activation+0.000
Top resid features:
interceptions
Token interceptions
Feature activation-0.008
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
but
Token but
Feature activation-0.001
Top resid features:
he
Token he
Feature activation-0.004
Top resid features:
was
Token was
Feature activation-0.017
Top resid features:
9
Token 9
Feature activation+4.071
Top resid features:
of
Token of
Feature activation-0.049
Top resid features:
9
Token 9
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
fourth
Token fourth
Feature activation+0.000
Top resid features:
120
Token 120
Feature activation-0.236
Top resid features:
m
Token m
Feature activation+0.048
Top resid features:
ounds
Tokenounds
Feature activation+0.051
Top resid features:
spread
Token spread
Feature activation+0.019
Top resid features:
over
Token over
Feature activation+0.037
Top resid features:
6
Token 6
Feature activation+3.543
Top resid features:
square
Token square
Feature activation+0.204
Top resid features:
miles
Token miles
Feature activation+0.016
Top resid features:
(
Token (
Feature activation+0.081
Top resid features:
16
Token16
Feature activation+0.000
Top resid features:
square
Token square
Feature activation+0.000
Top resid features:
owitz
Tokenowitz
Feature activation-0.001
Top resid features:
wob
Token wob
Feature activation+0.005
Top resid features:
ble
Tokenble
Feature activation-0.002
Top resid features:
)
Token)
Feature activation+0.010
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
6
Token 6
Feature activation+3.843
Top resid features:
-
Token-
Feature activation+0.044
Top resid features:
to
Token to
Feature activation+0.031
Top resid features:
14
Token 14
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
year
Tokenyear
Feature activation+0.000
Top resid features:
type
Token type
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
This
Token This
Feature activation-0.004
Top resid features:
rises
Token rises
Feature activation+0.008
Top resid features:
to
Token to
Feature activation+0.041
Top resid features:
5
Token 5
Feature activation+3.269
Top resid features:
-
Token-
Feature activation+0.008
Top resid features:
19
Token19
Feature activation+0.000
Top resid features:
percent
Token percent
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
net
Token net
Feature activation+0.000
Top resid features:
's
Token's
Feature activation-0.002
Top resid features:
inflation
Token inflation
Feature activation-0.013
Top resid features:
target
Token target
Feature activation-0.012
Top resid features:
is
Token is
Feature activation-0.012
Top resid features:
actually
Token actually
Feature activation-0.047
Top resid features:
2
Token 2
Feature activation+3.895
Top resid features:
%.
Token%.
Feature activation+0.055
Top resid features:
David
Token David
Feature activation-0.006
Top resid features:
Beck
Token Beck
Feature activation+0.000
Top resid features:
worth
Tokenworth
Feature activation+0.001
Top resid features:
suggests
Token suggests
Feature activation+0.082
Top resid features:
Yad
Token Yad
Feature activation+0.005
Top resid features:
if
Tokenif
Feature activation+0.002
Top resid features:
would
Token would
Feature activation+0.012
Top resid features:
take
Token take
Feature activation+0.046
Top resid features:
about
Token about
Feature activation+0.022
Top resid features:
6
Token 6
Feature activation+3.486
Top resid features:
-
Token-
Feature activation+0.125
Top resid features:
8
Token8
Feature activation+0.000
Top resid features:
ms
Tokenms
Feature activation+0.000
Top resid features:
/
Token/
Feature activation+0.000
Top resid features:
frame
Tokenframe
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.03

Head 2: 0.03

Head 3: 0.09

Head 4: 0.02

Head 5: 0.04

Head 6: 0.08

Head 7: 0.05

Head 8: 0.44

Head 9: 0.04

Head 10: 0.10

Head 11: 0.06

Positive logits

63.48

73.42

43.41

33.38

53.32

83.30

93.21

22.98

112.64

102.64

122.56

72.44

132.44

62.42

42.42

12.41

142.39

52.38

82.36

92.33

Negative logits

intage-1.88

borgh-1.77

irgin-1.76

igent-1.75

ppo-1.73

hum-1.73

mint-1.70

Pebble-1.70

seller-1.67

Draper-1.64

ascar-1.61

conce-1.60

Pioneer-1.58

NetMessage-1.58

reinvent-1.58

penn-1.57

PDATE-1.57

ridges-1.54

fart-1.53

humble-1.53

INTERVAL 4.024 - 4.471
CONTAINS 0.000%

fill
Tokenfill
Feature activation+0.000
routers
Token routers
Feature activation+0.000
from
Token from
Feature activation+0.000
5
Token 5
Feature activation+0.000
to
Token to
Feature activation+3.922
almost
Token almost
Feature activation+4.471
100
Token 100
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
increased
Token increased
Feature activation+0.000
reliability
Token reliability
Feature activation+0.000

INTERVAL 3.577 - 4.024
CONTAINS 0.001%

Republican
Token Republican
Feature activation+0.000
voters
Token voters
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
and
Token and
Feature activation+0.000
6
Token 6
Feature activation+0.000
in
Token in
Feature activation+3.770
10
Token 10
Feature activation+0.000
independents
Token independents
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
said
Token said
Feature activation+0.000
they
Token they
Feature activation+0.000
flood
Token flood
Feature activation+0.000
fill
Tokenfill
Feature activation+0.000
routers
Token routers
Feature activation+0.000
from
Token from
Feature activation+0.000
5
Token 5
Feature activation+0.000
to
Token to
Feature activation+3.922
almost
Token almost
Feature activation+4.471
100
Token 100
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
increased
Token increased
Feature activation+0.000
site
Token site
Feature activation+0.000
is
Token is
Feature activation+0.000
located
Token located
Feature activation+0.000
7
Token 7
Feature activation+0.000
kilometres
Token kilometres
Feature activation+0.000
(
Token (
Feature activation+3.800
4
Token4
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token3
Feature activation+0.000
mi
Token mi
Feature activation+0.000
)
Token)
Feature activation+0.000
than
Token than
Feature activation+0.000
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
km
Token km
Feature activation+0.000
(
Token (
Feature activation+3.908
1
Token1
Feature activation+0.000
,
Token,
Feature activation+0.000
200
Token200
Feature activation+0.000
miles
Token miles
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
polished
Token polished
Feature activation+0.000
demo
Token demo
Feature activation+0.000
in
Token in
Feature activation+0.000
4
Token 4
Feature activation+0.000
to
Token to
Feature activation+3.617
5
Token 5
Feature activation+0.451
months
Token months
Feature activation+0.000
so
Token so
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000

INTERVAL 3.130 - 3.577
CONTAINS 0.001%

.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
rises
Token rises
Feature activation+0.000
to
Token to
Feature activation+0.000
5
Token 5
Feature activation+0.000
-
Token-
Feature activation+3.149
19
Token19
Feature activation+0.000
percent
Token percent
Feature activation+0.000
in
Token in
Feature activation+0.000
net
Token net
Feature activation+0.000
-
Token-
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
vote
Token vote
Feature activation+0.000
of
Token of
Feature activation+0.000
6
Token 6
Feature activation+0.000
to
Token to
Feature activation+3.550
3
Token 3
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Three
TokenThree
Feature activation+0.000
ill
Tokenill
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
3
Token 3
Feature activation+0.000
-
Token-
Feature activation+0.014
to
Token to
Feature activation+3.331
5
Token 5
Feature activation+0.926
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+1.422
4
Token 4
Feature activation+0.000
and
Token and
Feature activation+3.398
1
Token 1
Feature activation+0.000
stamps
Token stamps
Feature activation+0.000
auto
Token auto
Feature activation+0.000
-
Token-
Feature activation+0.000
filled
Tokenfilled
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
election
Token election
Feature activation+0.000
,
Token,
Feature activation+0.000
9
Token 9
Feature activation+0.000
in
Token in
Feature activation+3.305
10
Token 10
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
voters
Token voters
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 2.683 - 3.130
CONTAINS 0.002%

if
Tokenif
Feature activation+0.000
would
Token would
Feature activation+0.000
take
Token take
Feature activation+0.000
about
Token about
Feature activation+0.000
6
Token 6
Feature activation+0.000
-
Token-
Feature activation+3.079
8
Token8
Feature activation+0.605
ms
Tokenms
Feature activation+0.000
/
Token/
Feature activation+0.258
frame
Tokenframe
Feature activation+0.000
on
Token on
Feature activation+0.000
conventional
Token conventional
Feature activation+0.000
way
Token way
Feature activation+0.018
would
Token would
Feature activation+0.252
take
Token take
Feature activation+0.000
3
Token 3
Feature activation+0.000
to
Token to
Feature activation+2.794
4
Token 4
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
only
Token only
Feature activation+0.000
about
Token about
Feature activation+0.000
2
Token 2
Feature activation+0.000
or
Token or
Feature activation+2.961
3
Token 3
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
in
Token in
Feature activation+0.000
between
Token between
Feature activation+0.000
3
Token 3
Feature activation+0.153
,
Token,
Feature activation+1.709
5
Token 5
Feature activation+0.433
or
Token or
Feature activation+2.975
10
Token 10
Feature activation+0.000
videos
Token videos
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
type
Token type
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+2.794
10
Token 10
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
think
Token think
Feature activation+0.000
the
Token the
Feature activation+0.000
national
Token national
Feature activation+0.000

INTERVAL 2.236 - 2.683
CONTAINS 0.003%

some
Token some
Feature activation+0.000
light
Token light
Feature activation+0.000
handling
Token handling
Feature activation+0.000
by
Token by
Feature activation+0.000
4
Token 4
Feature activation+0.000
and
Token and
Feature activation+2.603
2
Token 2
Feature activation+0.000
year
Token year
Feature activation+0.000
old
Token old
Feature activation+0.000
boys
Token boys
Feature activation+0.000
,
Token,
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
billion
Token billion
Feature activation+0.000
Euros
Token Euros
Feature activation+0.000
($
Token ($
Feature activation+2.649
A
TokenA
Feature activation+0.000
US
TokenUS
Feature activation+0.000
3
Token 3
Feature activation+0.000
billion
Token billion
Feature activation+0.000
)
Token)
Feature activation+0.000
the
Token the
Feature activation+0.000
C
Token C
Feature activation+0.000
ME
TokenME
Feature activation+0.000
equivalent
Token equivalent
Feature activation+0.000
was
Token was
Feature activation+0.614
near
Token near
Feature activation+2.350
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
's
Token's
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
4
Token 4
Feature activation+0.000
-
Token-
Feature activation+2.571
5
Token5
Feature activation+0.000
million
Token million
Feature activation+0.000
homes
Token homes
Feature activation+0.000
permanently
Token permanently
Feature activation+0.000
off
Token off
Feature activation+0.000
from
Token from
Feature activation+0.000
traffic
Token traffic
Feature activation+0.000
for
Token for
Feature activation+0.000
about
Token about
Feature activation+0.000
2
Token 2
Feature activation+0.000
-
Token-
Feature activation+2.384
½
Token½
Feature activation+0.000
hours
Token hours
Feature activation+0.000
and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
re
Token re
Feature activation+0.000

INTERVAL 1.789 - 2.236
CONTAINS 0.005%

ations
Tokenations
Feature activation+0.000
survey
Token survey
Feature activation+0.000
shows
Token shows
Feature activation+0.000
that
Token that
Feature activation+0.000
1
Token 1
Feature activation+0.000
out
Token out
Feature activation+1.888
of
Token of
Feature activation+2.430
every
Token every
Feature activation+2.666
4
Token 4
Feature activation+0.000
Filip
Token Filip
Feature activation+0.000
inos
Tokeninos
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.031
above
Token above
Feature activation+1.879
3
Token 3
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
17
Token17
Feature activation+0.000
million
Token million
Feature activation+0.000
viewers
Token viewers
Feature activation+0.000
,
Token,
Feature activation+0.000
down
Token down
Feature activation+0.000
from
Token from
Feature activation+2.179
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.149
's
Token's
Feature activation+1.816
3
Token 3
Feature activation+0.000
.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.000
percent
Token percent
Feature activation+0.000
in
Token in
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
and
Token and
Feature activation+1.686
to
Token to
Feature activation+2.120
increase
Token increase
Feature activation+0.000
the
Token the
Feature activation+0.000
S
Token S
Feature activation+0.000
AW
TokenAW
Feature activation+0.000
S
TokenS
Feature activation+0.000
s
Tokens
Feature activation+0.000
9
Token 9
Feature activation+0.000
.
Token.
Feature activation+0.000
82
Token82
Feature activation+0.000
K
Token K
Feature activation+0.000
/
Token/
Feature activation+1.998
9
Token9
Feature activation+0.000
and
Token and
Feature activation+0.391
19
Token 19
Feature activation+0.121
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.567

INTERVAL 1.341 - 1.789
CONTAINS 0.008%

1
Token1
Feature activation+0.000
,
Token,
Feature activation+0.000
1
Token1
Feature activation+0.000
,
Token,
Feature activation+0.000
3
Token3
Feature activation+0.000
);
Token);
Feature activation+1.346
5
Token 5
Feature activation+0.000
teams
Token teams
Feature activation+0.000
(
Token (
Feature activation+0.000
1
Token1
Feature activation+0.000
,
Token,
Feature activation+0.000
least
Token least
Feature activation+0.000
`
Token `
Feature activation+0.000
2
Token2
Feature activation+0.000
,
Token,
Feature activation+0.188
000
Token000
Feature activation+0.000
to
Token to
Feature activation+1.611
test
Token test
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
lit
Token lit
Feature activation+0.000
re
Tokenre
Feature activation+0.000
taking
Token taking
Feature activation+0.000
out
Token out
Feature activation+0.000
1
Token 1
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
to
Token to
Feature activation+1.704
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
tons
Token tons
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
9
Token9
Feature activation+0.000
percent
Token percent
Feature activation+0.000
in
Token in
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
and
Token and
Feature activation+1.686
to
Token to
Feature activation+2.120
increase
Token increase
Feature activation+0.000
the
Token the
Feature activation+0.000
S
Token S
Feature activation+0.000
AW
TokenAW
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
may
Token may
Feature activation+0.000
receive
Token receive
Feature activation+0.000
1
Token 1
Feature activation+0.000
or
Token or
Feature activation+1.584
more
Token more
Feature activation+0.000
SMS
Token SMS
Feature activation+0.000
messages
Token messages
Feature activation+0.000
from
Token from
Feature activation+0.000
your
Token your
Feature activation+0.000

INTERVAL 0.894 - 1.341
CONTAINS 0.012%

sleep
Token sleep
Feature activation+0.000
rebound
Token rebound
Feature activation+0.000
after
Token after
Feature activation+0.000
a
Token a
Feature activation+0.000
6
Token 6
Feature activation+0.031
-
Token-
Feature activation+1.187
hr
Tokenhr
Feature activation+0.000
sleep
Token sleep
Feature activation+0.000
deprivation
Token deprivation
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.053
Now
TokenNow
Feature activation+0.000
with
Token with
Feature activation+0.000
X
Token X
Feature activation+0.000
code
Tokencode
Feature activation+0.000
6
Token 6
Feature activation+0.000
and
Token and
Feature activation+1.028
iOS
Token iOS
Feature activation+0.000
8
Token 8
Feature activation+0.000
,
Token,
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
have
Token have
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
gap
Token gap
Feature activation+0.000
balloon
Token balloon
Feature activation+0.000
ed
Tokened
Feature activation+0.000
to
Token to
Feature activation+1.293
five
Token five
Feature activation+0.000
runs
Token runs
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
seventh
Token seventh
Feature activation+0.000
Young
Token Young
Feature activation+0.000
(
Token (
Feature activation+0.000
Y
TokenY
Feature activation+0.000
,
Token,
Feature activation+0.000
4
Token 4
Feature activation+0.000
-
Token-
Feature activation+1.136
6
Token6
Feature activation+0.000
months
Token months
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
old
Token old
Feature activation+0.000
-
Token-
Feature activation+0.000
NE
TokenNE
Feature activation+0.000
V
TokenV
Feature activation+0.000
.)
Token.)
Feature activation+0.000
5
Token 5
Feature activation+0.000
>>
Token >>
Feature activation+1.066
2
Token 2
Feature activation+0.000
/
Token/
Feature activation+0.000
19
Token19
Feature activation+0.000
James
Token James
Feature activation+0.000
E
Token E
Feature activation+0.000

INTERVAL 0.447 - 0.894
CONTAINS 0.030%

5
Token 5
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
ended
Token ended
Feature activation+0.530
on
Token on
Feature activation+0.000
July
Token July
Feature activation+0.737
27
Token 27
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
array
Token array
Feature activation+0.000
can
Token can
Feature activation+0.000
display
Token display
Feature activation+0.000
some
Token some
Feature activation+0.000
10
Token 10
Feature activation+0.000
,
Token,
Feature activation+0.581
000
Token000
Feature activation+0.000
random
Token random
Feature activation+0.000
ised
Tokenised
Feature activation+0.000
patterns
Token patterns
Feature activation+0.000
per
Token per
Feature activation+0.000
06
Token06
Feature activation+0.000
miles
Token miles
Feature activation+0.000
,
Token,
Feature activation+0.214
and
Token and
Feature activation+1.985
South
Token South
Feature activation+0.000
Pond
Token Pond
Feature activation+0.788
is
Token is
Feature activation+2.507
4
Token 4
Feature activation+0.000
.
Token.
Feature activation+0.000
17
Token17
Feature activation+0.000
miles
Token miles
Feature activation+0.000
at
Token at
Feature activation+0.000
low
Token low
Feature activation+0.000
temperatures
Token temperatures
Feature activation+0.000
for
Token for
Feature activation+0.000
12
Token 12
Feature activation+0.000
to
Token to
Feature activation+0.890
15
Token 15
Feature activation+0.000
hours
Token hours
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
temperature
Token temperature
Feature activation+0.000
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
1
Token 1
Feature activation+0.000
-
Token-
Feature activation+0.034
in
Tokenin
Feature activation+0.015
-
Token-
Feature activation+0.500
100
Token100
Feature activation+0.000
year
Token year
Feature activation+0.000
and
Token and
Feature activation+0.000
1
Token 1
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 0.000 - 0.447
CONTAINS 99.938%

-
Token -
Feature activation+0.000
on
Token on
Feature activation+0.000
Dec
Token Dec
Feature activation+0.000
28
Token 28
Feature activation+0.000
-
Token -
Feature activation+0.000
the
Token the
Feature activation+0.000
explorers
Token explorers
Feature activation+0.000
were
Token were
Feature activation+0.000
continuing
Token continuing
Feature activation+0.000
to
Token to
Feature activation+0.000
battle
Token battle
Feature activation+0.000
Steam
Token Steam
Feature activation+0.000
Support
Token Support
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
item
Token item
Feature activation+0.000
is
Token is
Feature activation+0.000
incompatible
Token incompatible
Feature activation+0.000
with
Token with
Feature activation+0.000
Overwatch
Token Overwatch
Feature activation+0.000
.
Token.
Feature activation+0.000
X
Token X
Feature activation+0.000
:
Token:
Feature activation+0.000
16
Token 16
Feature activation+0.000
Sum
Token Sum
Feature activation+0.000
:
Token:
Feature activation+0.093
30
Token 30
Feature activation+0.000
X
Token X
Feature activation+0.000
:
Token:
Feature activation+0.000
32
Token 32
Feature activation+0.000
62
Token 62
Feature activation+0.000
1
Token 1
Feature activation+0.000
em
Tokenem
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
referring
Token referring
Feature activation+0.000
specifically
Token specifically
Feature activation+0.000
to
Token to
Feature activation+0.000
rebel
Token rebel
Feature activation+0.000
-
Token-
Feature activation+0.000
held
Tokenheld
Feature activation+0.000
Idlib
Token Idlib
Feature activation+0.000
province
Token province
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.000
128
Token128
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
M
TokenM
Feature activation+0.000
ey
Tokeney
Feature activation+0.000
er
Tokener
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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