H9.0 top features

Top feature 0 in H9.0: (feature 16056)

TOP ACTIVATIONS
MAX = 5.937

to
Token to
Feature activation+0.000
show
Token show
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
is
Token is
Feature activation+5.937
now
Token now
Feature activation+1.037
to
Token to
Feature activation+0.000
implement
Token implement
Feature activation+0.000
strategies
Token strategies
Feature activation+0.000
to
Token to
Feature activation+0.000
sure
Token sure
Feature activation+0.000
you
Token you
Feature activation+0.000
appreciate
Token appreciate
Feature activation+0.000
our
Token our
Feature activation+0.000
time
Token time
Feature activation+0.000
was
Token was
Feature activation+5.604
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+0.000
hundred
Token hundred
Feature activation+0.000
-
Token-
Feature activation+0.000
fold
Tokenfold
Feature activation+2.412
do
Token do
Feature activation+0.000
this
Token this
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
time
Token time
Feature activation+0.000
is
Token is
Feature activation+5.113
right
Token right
Feature activation+0.353
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.000
ready
Token ready
Feature activation+0.000
i
Tokeni
Feature activation+0.000
have
Token have
Feature activation+0.000
decided
Token decided
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.408
has
Token has
Feature activation+5.093
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
close
Token close
Feature activation+0.000
its
Token its
Feature activation+0.000
ministries
Token ministries
Feature activation+0.000
her
Token her
Feature activation+0.000
time
Token time
Feature activation+0.352
to
Token to
Feature activation+0.000
ask
Token ask
Feature activation+0.000
questions
Token questions
Feature activation+0.914
was
Token was
Feature activation+5.023
limited
Token limited
Feature activation+1.998
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
China
Token China
Feature activation+0.000
who
Token who
Feature activation+0.000
think
Token think
Feature activation+0.000
their
Token their
Feature activation+0.000
time
Token time
Feature activation+0.020
has
Token has
Feature activation+5.016
come
Token come
Feature activation+2.357
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
America
Token America
Feature activation+0.000
's
Token's
Feature activation+0.000
comes
Token comes
Feature activation+0.606
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.394
will
Token will
Feature activation+4.735
come
Token come
Feature activation+1.824
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
James
Token James
Feature activation+0.000
how
Token how
Feature activation+0.000
many
Token many
Feature activation+0.000
takedown
Token takedown
Feature activation+0.000
requests
Token requests
Feature activation+0.000
)
Token)
Feature activation+0.000
will
Token will
Feature activation+4.715
pass
Token pass
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
few
Token few
Feature activation+0.000
growing
Token growing
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
itself
Token itself
Feature activation+1.846
is
Token is
Feature activation+4.388
r
Token r
Feature activation+0.066
ipp
Tokenipp
Feature activation+0.000
ling
Tokenling
Feature activation+0.160
,
Token,
Feature activation+0.000
trying
Token trying
Feature activation+0.000
a
Token a
Feature activation+0.000
proper
Token proper
Feature activation+0.000
book
Token book
Feature activation+0.000
proposal
Token proposal
Feature activation+0.000
as
Token as
Feature activation+3.172
too
Token too
Feature activation+4.333
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
wrong
Token wrong
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Time
TokenTime
Feature activation+0.000
is
Token is
Feature activation+4.178
more
Token more
Feature activation+1.288
important
Token important
Feature activation+0.208
than
Token than
Feature activation+0.487
money
Token money
Feature activation+0.214
!
Token!
Feature activation+0.033
recent
Token recent
Feature activation+0.000
memory
Token memory
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
time
Token time
Feature activation+0.000
is
Token is
Feature activation+4.028
now
Token now
Feature activation+3.547
âĢĵ
Token âĢĵ
Feature activation+0.000
seven
Token seven
Feature activation+0.000
years
Token years
Feature activation+0.000
since
Token since
Feature activation+0.000
games
Token games
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
preparation
Token preparation
Feature activation+0.000
time
Token time
Feature activation+2.405
so
Token so
Feature activation+3.751
short
Token short
Feature activation+0.168
and
Token and
Feature activation+0.000
with
Token with
Feature activation+0.000
no
Token no
Feature activation+0.000
mid
Token mid
Feature activation+0.000
memory
Token memory
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
time
Token time
Feature activation+0.000
is
Token is
Feature activation+4.028
now
Token now
Feature activation+3.547
âĢĵ
Token âĢĵ
Feature activation+0.000
seven
Token seven
Feature activation+0.000
years
Token years
Feature activation+0.000
since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
time
Token time
Feature activation+0.319
has
Token has
Feature activation+3.219
passed
Token passed
Feature activation+0.083
since
Token since
Feature activation+0.000
then
Token then
Feature activation+0.000
and
Token and
Feature activation+0.000
lots
Token lots
Feature activation+0.000
write
Token write
Feature activation+0.000
a
Token a
Feature activation+0.000
proper
Token proper
Feature activation+0.000
book
Token book
Feature activation+0.000
proposal
Token proposal
Feature activation+0.000
as
Token as
Feature activation+3.172
too
Token too
Feature activation+4.333
risky
Token risky
Feature activation+0.000
.[
Token.[
Feature activation+0.000
10
Token10
Feature activation+0.000
]
Token]
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
times
Token times
Feature activation+0.452
,
Token,
Feature activation+0.267
they
Token they
Feature activation+2.447
are
Token are
Feature activation+3.150
a
Token a
Feature activation+1.533
-
Token-
Feature activation+0.400
ch
Tokench
Feature activation+0.000
ang
Tokenang
Feature activation+0.000
in
Tokenin
Feature activation+0.000
time
Token time
Feature activation+0.000
for
Token for
Feature activation+0.000
cookie
Token cookie
Feature activation+0.000
fract
Token fract
Feature activation+0.000
als
Tokenals
Feature activation+0.000
has
Token has
Feature activation+2.863
come
Token come
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
between
Token between
Feature activation+0.000
you
Token you
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
writer
Token writer
Feature activation+0.000
is
Token is
Feature activation+2.846
gone
Token gone
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.037
near
Token near
Feature activation+0.000
future
Token future
Feature activation+0.261
that
Token that
Feature activation+1.257
will
Token will
Feature activation+2.669
permit
Token permit
Feature activation+0.000
both
Token both
Feature activation+0.000
sides
Token sides
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000

Top DFA by src position
MAX = 6.648

evidence
Token evidence
Feature activation-0.003
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
show
Token show
Feature activation+0.011
Top resid features:
that
Token that
Feature activation+0.036
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
time
Token time
Feature activation+6.648
Top resid features:
is
Token is
Feature activation+0.130
Top resid features:
now
Token now
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
implement
Token implement
Feature activation+0.000
Top resid features:
strategies
Token strategies
Feature activation+0.000
Top resid features:
'm
Token'm
Feature activation+0.004
Top resid features:
sure
Token sure
Feature activation-0.000
Top resid features:
you
Token you
Feature activation+0.011
Top resid features:
appreciate
Token appreciate
Feature activation+0.057
Top resid features:
our
Token our
Feature activation+0.012
Top resid features:
time
Token time
Feature activation+6.369
Top resid features:
was
Token was
Feature activation+0.160
Top resid features:
spent
Token spent
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
hundred
Token hundred
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:
do
Token do
Feature activation-0.002
Top resid features:
this
Token this
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
The
Token The
Feature activation+0.007
Top resid features:
time
Token time
Feature activation+5.826
Top resid features:
is
Token is
Feature activation+0.152
Top resid features:
right
Token right
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
're
Token're
Feature activation+0.000
Top resid features:
vant
Tokenvant
Feature activation-0.001
Top resid features:
i
Tokeni
Feature activation+0.004
Top resid features:
have
Token have
Feature activation+0.004
Top resid features:
decided
Token decided
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.054
Top resid features:
time
Token time
Feature activation+5.728
Top resid features:
has
Token has
Feature activation+0.054
Top resid features:
come
Token come
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
close
Token close
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
March
Token March
Feature activation-0.001
Top resid features:
1
Token 1
Feature activation+0.007
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
as
Token as
Feature activation+0.035
Top resid features:
her
Token her
Feature activation+0.023
Top resid features:
time
Token time
Feature activation+5.660
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
ask
Token ask
Feature activation-0.002
Top resid features:
questions
Token questions
Feature activation+0.036
Top resid features:
was
Token was
Feature activation+0.093
Top resid features:
limited
Token limited
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
China
Token China
Feature activation+0.003
Top resid features:
who
Token who
Feature activation-0.004
Top resid features:
think
Token think
Feature activation-0.023
Top resid features:
their
Token their
Feature activation+0.017
Top resid features:
time
Token time
Feature activation+5.631
Top resid features:
has
Token has
Feature activation+0.157
Top resid features:
come
Token come
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:
America
Token America
Feature activation+0.000
Top resid features:
fall
Token fall
Feature activation-0.015
Top resid features:
down
Token down
Feature activation-0.006
Top resid features:
faster
Token faster
Feature activation-0.007
Top resid features:
when
Token when
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
time
Token time
Feature activation+2.777
Top resid features:
comes
Token comes
Feature activation+0.058
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
and
Token and
Feature activation+0.049
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
time
Token time
Feature activation+2.684
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Who
Token Who
Feature activation+0.005
Top resid features:
knows
Token knows
Feature activation-0.003
Top resid features:
how
Token how
Feature activation+0.027
Top resid features:
much
Token much
Feature activation+0.010
Top resid features:
time
Token time
Feature activation+5.648
Top resid features:
(
Token (
Feature activation+0.003
Top resid features:
or
Tokenor
Feature activation+0.009
Top resid features:
how
Token how
Feature activation+0.004
Top resid features:
many
Token many
Feature activation-0.014
Top resid features:
takedown
Token takedown
Feature activation-0.036
Top resid features:
so
Token so
Feature activation-0.090
Top resid features:
dangerous
Token dangerous
Feature activation-0.014
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
that
Token that
Feature activation+0.032
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
time
Token time
Feature activation+5.215
Top resid features:
itself
Token itself
Feature activation+0.282
Top resid features:
is
Token is
Feature activation+0.063
Top resid features:
r
Token r
Feature activation+0.000
Top resid features:
ipp
Tokenipp
Feature activation+0.000
Top resid features:
ling
Tokenling
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.008
Top resid features:
comfortable
Token comfortable
Feature activation+0.022
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
saw
Token saw
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
time
Token time
Feature activation+4.622
Top resid features:
needed
Token needed
Feature activation+0.320
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
write
Token write
Feature activation-0.013
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
proper
Token proper
Feature activation-0.022
Top resid features:
all
Token all
Feature activation+0.001
Top resid features:
wrong
Token wrong
Feature activation+0.015
Top resid features:
!
Token!
Feature activation+0.084
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.047
Top resid features:
Time
TokenTime
Feature activation+4.201
Top resid features:
is
Token is
Feature activation+0.288
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
important
Token important
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
money
Token money
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
recent
Token recent
Feature activation+0.004
Top resid features:
memory
Token memory
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.045
Top resid features:
The
Token The
Feature activation+0.061
Top resid features:
time
Token time
Feature activation+4.642
Top resid features:
is
Token is
Feature activation+0.151
Top resid features:
now
Token now
Feature activation+0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
seven
Token seven
Feature activation+0.000
Top resid features:
years
Token years
Feature activation+0.000
Top resid features:
Nations
Token Nations
Feature activation-0.001
Top resid features:
games
Token games
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
With
Token With
Feature activation+0.009
Top resid features:
preparation
Token preparation
Feature activation+0.112
Top resid features:
time
Token time
Feature activation+4.380
Top resid features:
so
Token so
Feature activation+0.015
Top resid features:
short
Token short
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
recent
Token recent
Feature activation+0.001
Top resid features:
memory
Token memory
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.095
Top resid features:
The
Token The
Feature activation+0.031
Top resid features:
time
Token time
Feature activation+3.686
Top resid features:
is
Token is
Feature activation+0.366
Top resid features:
now
Token now
Feature activation+0.157
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
seven
Token seven
Feature activation+0.000
Top resid features:
years
Token years
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
A
TokenA
Feature activation-0.001
Top resid features:
lot
Token lot
Feature activation-0.019
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
time
Token time
Feature activation+3.688
Top resid features:
has
Token has
Feature activation+0.136
Top resid features:
passed
Token passed
Feature activation+0.000
Top resid features:
since
Token since
Feature activation+0.000
Top resid features:
then
Token then
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.013
Top resid features:
comfortable
Token comfortable
Feature activation+0.012
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
saw
Token saw
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
time
Token time
Feature activation+3.296
Top resid features:
needed
Token needed
Feature activation+0.394
Top resid features:
to
Token to
Feature activation+0.016
Top resid features:
write
Token write
Feature activation-0.009
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
proper
Token proper
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Of
TokenOf
Feature activation-0.004
Top resid features:
course
Token course
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
times
Token times
Feature activation+3.943
Top resid features:
,
Token,
Feature activation+0.061
Top resid features:
they
Token they
Feature activation+0.071
Top resid features:
are
Token are
Feature activation-0.008
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
fract
Token fract
Feature activation-0.005
Top resid features:
als
Tokenals
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
but
Token but
Feature activation+0.065
Top resid features:
the
Token the
Feature activation-0.014
Top resid features:
time
Token time
Feature activation+3.701
Top resid features:
for
Token for
Feature activation+0.074
Top resid features:
cookie
Token cookie
Feature activation-0.003
Top resid features:
fract
Token fract
Feature activation-0.002
Top resid features:
als
Tokenals
Feature activation+0.028
Top resid features:
has
Token has
Feature activation+0.060
Top resid features:
Ļ
TokenĻ
Feature activation-0.011
Top resid features:
t
Tokent
Feature activation-0.012
Top resid features:
matter
Token matter
Feature activation-0.077
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
The
Token The
Feature activation+0.004
Top resid features:
time
Token time
Feature activation+3.634
Top resid features:
between
Token between
Feature activation+0.060
Top resid features:
you
Token you
Feature activation+0.072
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
writer
Token writer
Feature activation-0.003
Top resid features:
looking
Token looking
Feature activation+0.006
Top resid features:
for
Token for
Feature activation+0.010
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
mutually
Token mutually
Feature activation-0.059
Top resid features:
convenient
Token convenient
Feature activation+0.062
Top resid features:
time
Token time
Feature activation+2.670
Top resid features:
in
Token in
Feature activation+0.101
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
near
Token near
Feature activation-0.006
Top resid features:
future
Token future
Feature activation+0.112
Top resid features:
that
Token that
Feature activation+0.157
Top resid features:

Decoder Weights Distribution

Head 0: 0.53

Head 1: 0.02

Head 2: 0.13

Head 3: 0.06

Head 4: 0.02

Head 5: 0.04

Head 6: 0.02

Head 7: 0.04

Head 8: 0.02

Head 9: 0.02

Head 10: 0.09

Head 11: 0.02

Positive logits

netflix2.58

dayName2.29

ourning2.28

isine2.20

ARDIS2.19

ppo2.16

slice2.15

cast2.11

continuum2.09

elapsed2.08

Downloadha2.07

calling2.07

ago2.04

wasted2.02

adj2.01

xxxxxxxx2.00

oway1.99

MpServer1.97

geon1.96

urations1.95

Negative logits

posts-2.32

posts-2.31

HEAD-2.20

EL-2.20

oval-2.18

naires-2.12

inline-2.08

follower-2.05

Transparency-2.03

mods-2.02

reply-1.96

spokes-1.96

modifications-1.95

pumps-1.94

response-1.94

responses-1.93

tons-1.92

submission-1.91

responsive-1.91

Massive-1.89

INTERVAL 5.343 - 5.937
CONTAINS 0.000%

sure
Token sure
Feature activation+0.000
you
Token you
Feature activation+0.000
appreciate
Token appreciate
Feature activation+0.000
our
Token our
Feature activation+0.000
time
Token time
Feature activation+0.000
was
Token was
Feature activation+5.604
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+0.000
hundred
Token hundred
Feature activation+0.000
-
Token-
Feature activation+0.000
fold
Tokenfold
Feature activation+2.412
to
Token to
Feature activation+0.000
show
Token show
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
is
Token is
Feature activation+5.937
now
Token now
Feature activation+1.037
to
Token to
Feature activation+0.000
implement
Token implement
Feature activation+0.000
strategies
Token strategies
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 4.749 - 5.343
CONTAINS 0.000%

China
Token China
Feature activation+0.000
who
Token who
Feature activation+0.000
think
Token think
Feature activation+0.000
their
Token their
Feature activation+0.000
time
Token time
Feature activation+0.020
has
Token has
Feature activation+5.016
come
Token come
Feature activation+2.357
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
America
Token America
Feature activation+0.000
's
Token's
Feature activation+0.000
her
Token her
Feature activation+0.000
time
Token time
Feature activation+0.352
to
Token to
Feature activation+0.000
ask
Token ask
Feature activation+0.000
questions
Token questions
Feature activation+0.914
was
Token was
Feature activation+5.023
limited
Token limited
Feature activation+1.998
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
do
Token do
Feature activation+0.000
this
Token this
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
time
Token time
Feature activation+0.000
is
Token is
Feature activation+5.113
right
Token right
Feature activation+0.353
and
Token and
Feature activation+0.000
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.000
ready
Token ready
Feature activation+0.000
i
Tokeni
Feature activation+0.000
have
Token have
Feature activation+0.000
decided
Token decided
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.408
has
Token has
Feature activation+5.093
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.000
close
Token close
Feature activation+0.000
its
Token its
Feature activation+0.000
ministries
Token ministries
Feature activation+0.000

INTERVAL 4.156 - 4.749
CONTAINS 0.001%

,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
itself
Token itself
Feature activation+1.846
is
Token is
Feature activation+4.388
r
Token r
Feature activation+0.066
ipp
Tokenipp
Feature activation+0.000
ling
Tokenling
Feature activation+0.160
,
Token,
Feature activation+0.000
trying
Token trying
Feature activation+0.000
comes
Token comes
Feature activation+0.606
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.394
will
Token will
Feature activation+4.735
come
Token come
Feature activation+1.824
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
James
Token James
Feature activation+0.000
wrong
Token wrong
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Time
TokenTime
Feature activation+0.000
is
Token is
Feature activation+4.178
more
Token more
Feature activation+1.288
important
Token important
Feature activation+0.208
than
Token than
Feature activation+0.487
money
Token money
Feature activation+0.214
!
Token!
Feature activation+0.033
a
Token a
Feature activation+0.000
proper
Token proper
Feature activation+0.000
book
Token book
Feature activation+0.000
proposal
Token proposal
Feature activation+0.000
as
Token as
Feature activation+3.172
too
Token too
Feature activation+4.333
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
how
Token how
Feature activation+0.000
many
Token many
Feature activation+0.000
takedown
Token takedown
Feature activation+0.000
requests
Token requests
Feature activation+0.000
)
Token)
Feature activation+0.000
will
Token will
Feature activation+4.715
pass
Token pass
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
few
Token few
Feature activation+0.000
growing
Token growing
Feature activation+0.000

INTERVAL 3.562 - 4.156
CONTAINS 0.000%

recent
Token recent
Feature activation+0.000
memory
Token memory
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
time
Token time
Feature activation+0.000
is
Token is
Feature activation+4.028
now
Token now
Feature activation+3.547
âĢĵ
Token âĢĵ
Feature activation+0.000
seven
Token seven
Feature activation+0.000
years
Token years
Feature activation+0.000
since
Token since
Feature activation+0.000
games
Token games
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
preparation
Token preparation
Feature activation+0.000
time
Token time
Feature activation+2.405
so
Token so
Feature activation+3.751
short
Token short
Feature activation+0.168
and
Token and
Feature activation+0.000
with
Token with
Feature activation+0.000
no
Token no
Feature activation+0.000
mid
Token mid
Feature activation+0.000

INTERVAL 2.968 - 3.562
CONTAINS 0.000%

memory
Token memory
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
time
Token time
Feature activation+0.000
is
Token is
Feature activation+4.028
now
Token now
Feature activation+3.547
âĢĵ
Token âĢĵ
Feature activation+0.000
seven
Token seven
Feature activation+0.000
years
Token years
Feature activation+0.000
since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
write
Token write
Feature activation+0.000
a
Token a
Feature activation+0.000
proper
Token proper
Feature activation+0.000
book
Token book
Feature activation+0.000
proposal
Token proposal
Feature activation+0.000
as
Token as
Feature activation+3.172
too
Token too
Feature activation+4.333
risky
Token risky
Feature activation+0.000
.[
Token.[
Feature activation+0.000
10
Token10
Feature activation+0.000
]
Token]
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
times
Token times
Feature activation+0.452
,
Token,
Feature activation+0.267
they
Token they
Feature activation+2.447
are
Token are
Feature activation+3.150
a
Token a
Feature activation+1.533
-
Token-
Feature activation+0.400
ch
Tokench
Feature activation+0.000
ang
Tokenang
Feature activation+0.000
in
Tokenin
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
time
Token time
Feature activation+0.319
has
Token has
Feature activation+3.219
passed
Token passed
Feature activation+0.083
since
Token since
Feature activation+0.000
then
Token then
Feature activation+0.000
and
Token and
Feature activation+0.000
lots
Token lots
Feature activation+0.000

INTERVAL 2.375 - 2.968
CONTAINS 0.001%

fall
Token fall
Feature activation+0.000
down
Token down
Feature activation+0.000
faster
Token faster
Feature activation+0.000
when
Token when
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+2.586
comes
Token comes
Feature activation+0.606
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.394
between
Token between
Feature activation+0.000
you
Token you
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
writer
Token writer
Feature activation+0.000
is
Token is
Feature activation+2.846
gone
Token gone
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
time
Token time
Feature activation+0.000
for
Token for
Feature activation+0.000
cookie
Token cookie
Feature activation+0.000
fract
Token fract
Feature activation+0.000
als
Tokenals
Feature activation+0.000
has
Token has
Feature activation+2.863
come
Token come
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.037
near
Token near
Feature activation+0.000
future
Token future
Feature activation+0.261
that
Token that
Feature activation+1.257
will
Token will
Feature activation+2.669
permit
Token permit
Feature activation+0.000
both
Token both
Feature activation+0.000
sides
Token sides
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
Nations
Token Nations
Feature activation+0.000
games
Token games
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
preparation
Token preparation
Feature activation+0.000
time
Token time
Feature activation+2.405
so
Token so
Feature activation+3.751
short
Token short
Feature activation+0.168
and
Token and
Feature activation+0.000
with
Token with
Feature activation+0.000
no
Token no
Feature activation+0.000

INTERVAL 1.781 - 2.375
CONTAINS 0.001%

dangerous
Token dangerous
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
itself
Token itself
Feature activation+1.846
is
Token is
Feature activation+4.388
r
Token r
Feature activation+0.066
ipp
Tokenipp
Feature activation+0.000
ling
Tokenling
Feature activation+0.160
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
too
Token too
Feature activation+0.000
much
Token much
Feature activation+0.000
time
Token time
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+2.143
hands
Token hands
Feature activation+0.000
and
Token and
Feature activation+0.000
use
Token use
Feature activation+0.000
that
Token that
Feature activation+0.000
money
Token money
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+0.000
time
Token time
Feature activation+0.000
had
Token had
Feature activation+2.171
passed
Token passed
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
noticed
Token noticed
Feature activation+0.000
his
Token his
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.394
will
Token will
Feature activation+4.735
come
Token come
Feature activation+1.824
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
James
Token James
Feature activation+0.000
Hughes
Token Hughes
Feature activation+0.000
time
Token time
Feature activation+0.352
to
Token to
Feature activation+0.000
ask
Token ask
Feature activation+0.000
questions
Token questions
Feature activation+0.914
was
Token was
Feature activation+5.023
limited
Token limited
Feature activation+1.998
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000

INTERVAL 1.187 - 1.781
CONTAINS 0.003%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
decade
Token decade
Feature activation+0.000
is
Token is
Feature activation+0.571
not
Token not
Feature activation+1.246
over
Token over
Feature activation+0.176
yet
Token yet
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
comfortable
Token comfortable
Feature activation+0.000
and
Token and
Feature activation+0.000
saw
Token saw
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.156
needed
Token needed
Feature activation+1.354
to
Token to
Feature activation+0.000
write
Token write
Feature activation+0.000
a
Token a
Feature activation+0.000
proper
Token proper
Feature activation+0.000
book
Token book
Feature activation+0.000
the
Token the
Feature activation+0.000
appropriate
Token appropriate
Feature activation+0.000
"
Token "
Feature activation+0.000
duration
Tokenduration
Feature activation+0.000
"
Token"
Feature activation+0.000
has
Token has
Feature activation+1.400
expired
Token expired
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
're
Token're
Feature activation+0.000
betting
Token betting
Feature activation+0.000
keeps
Token keeps
Feature activation+0.000
her
Token her
Feature activation+0.000
stumbling
Token stumbling
Feature activation+0.000
backward
Token backward
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.754
are
Token are
Feature activation+1.311
truly
Token truly
Feature activation+0.284
great
Token great
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Half
Token Half
Feature activation+0.000
hour
Token hour
Feature activation+0.000
before
Token before
Feature activation+0.000
cook
Token cook
Feature activation+0.000
time
Token time
Feature activation+0.000
is
Token is
Feature activation+1.567
up
Token up
Feature activation+0.071
add
Token add
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
salt
Token salt
Feature activation+0.000

INTERVAL 0.594 - 1.187
CONTAINS 0.011%

the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
year
Token year
Feature activation+0.000
actually
Token actually
Feature activation+0.370
starts
Token starts
Feature activation+0.000
to
Token to
Feature activation+0.900
do
Token do
Feature activation+0.000
so
Token so
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
of
Token of
Feature activation+0.000
workers
Token workers
Feature activation+0.000
,
Token,
Feature activation+0.000
those
Token those
Feature activation+0.000
days
Token days
Feature activation+0.000
are
Token are
Feature activation+0.605
over
Token over
Feature activation+0.580
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
ec
Tokenec
Feature activation+0.000
il
Tokenil
Feature activation+0.000
's
Token's
Feature activation+0.000
playing
Token playing
Feature activation+0.000
days
Token days
Feature activation+0.000
were
Token were
Feature activation+0.606
before
Token before
Feature activation+0.000
my
Token my
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
14
Token14
Feature activation+0.000
),
Token),
Feature activation+0.000
another
Token another
Feature activation+0.000
20
Token 20
Feature activation+0.000
days
Token days
Feature activation+0.240
have
Token have
Feature activation+0.724
passed
Token passed
Feature activation+0.000
in
Token in
Feature activation+0.000
Season
Token Season
Feature activation+0.000
2
Token 2
Feature activation+0.000
.
Token.
Feature activation+0.000
almost
Token almost
Feature activation+0.000
any
Token any
Feature activation+0.000
food
Token food
Feature activation+0.000
when
Token when
Feature activation+0.000
times
Token times
Feature activation+0.219
were
Token were
Feature activation+0.794
tough
Token tough
Feature activation+0.070
;
Token;
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
throwing
Token throwing
Feature activation+0.000

INTERVAL 0.000 - 0.594
CONTAINS 99.982%

and
Token and
Feature activation+0.000
business
Token business
Feature activation+0.000
models
Token models
Feature activation+0.000
emerge
Token emerge
Feature activation+0.000
;
Token;
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
destructive
Token destructive
Feature activation+0.000
one
Token one
Feature activation+0.000
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
RA
TokenRA
Feature activation+0.000
GG
TokenGG
Feature activation+0.000
ED
TokenED
Feature activation+0.000
ED
Token ED
Feature activation+0.000
GE
TokenGE
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
your
Token your
Feature activation+0.000
game
Token game
Feature activation+0.000
'm
Token'm
Feature activation+0.000
using
Token using
Feature activation+0.000
that
Token that
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
tentative
Token tentative
Feature activation+0.000
assumption
Token assumption
Feature activation+0.000
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
pretty
Token pretty
Feature activation+0.000
big
Token big
Feature activation+0.000
gender
Token gender
Feature activation+0.000
gap
Token gap
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
37
Token 37
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
women
Token women
Feature activation+0.000
citing
Token citing
Feature activation+0.000
The
Token The
Feature activation+0.000
founding
Token founding
Feature activation+0.000
fathers
Token fathers
Feature activation+0.000
of
Token of
Feature activation+0.000
Detroit
Token Detroit
Feature activation+0.000
--
Token --
Feature activation+0.000
and
Token and
Feature activation+0.000
Michigan
Token Michigan
Feature activation+0.000
--
Token --
Feature activation+0.000
are
Token are
Feature activation+0.000
buried
Token buried
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 H9.0: (feature 24001)

TOP ACTIVATIONS
MAX = 7.153

machine
Token machine
Feature activation+0.000
.
Token.
Feature activation+0.000
Thus
Token Thus
Feature activation+0.000
,
Token,
Feature activation+0.000
focus
Token focus
Feature activation+0.555
was
Token was
Feature activation+7.153
trained
Token trained
Feature activation+4.394
all
Token all
Feature activation+0.394
last
Token last
Feature activation+0.000
month
Token month
Feature activation+1.855
on
Token on
Feature activation+0.000
Thomas
Token Thomas
Feature activation+0.000
&
Token &
Feature activation+0.000
Mack
Token Mack
Feature activation+0.000
Center
Token Center
Feature activation+2.001
is
Token is
Feature activation+4.811
usually
Token usually
Feature activation+5.963
on
Token on
Feature activation+0.000
basketball
Token basketball
Feature activation+0.000
this
Token this
Feature activation+0.000
time
Token time
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+1.863
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
coming
Token coming
Feature activation+0.000
year
Token year
Feature activation+0.325
will
Token will
Feature activation+5.918
be
Token be
Feature activation+4.141
on
Token on
Feature activation+0.000
merchant
Token merchant
Feature activation+0.000
acquisition
Token acquisition
Feature activation+0.000
and
Token and
Feature activation+0.000
pace
Token pace
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
the
Token the
Feature activation+0.000
focus
Token focus
Feature activation+3.230
shifts
Token shifts
Feature activation+5.345
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
Championships
Token Championships
Feature activation+0.000
and
Token and
Feature activation+0.000
and
Token and
Feature activation+0.000
case
Token case
Feature activation+0.000
preparation
Token preparation
Feature activation+0.000
should
Token should
Feature activation+4.140
not
Token not
Feature activation+4.422
be
Token be
Feature activation+5.334
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
credibility
Token credibility
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
's
Token's
Feature activation+0.000
focus
Token focus
Feature activation+3.473
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
future
Token future
Feature activation+3.025
is
Token is
Feature activation+4.884
centered
Token centered
Feature activation+2.878
on
Token on
Feature activation+0.000
five
Token five
Feature activation+0.000
core
Token core
Feature activation+0.000
businesses
Token businesses
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
The
TokenThe
Feature activation+0.000
emphasis
Token emphasis
Feature activation+1.617
is
Token is
Feature activation+4.881
on
Token on
Feature activation+0.000
head
Token head
Feature activation+0.000
and
Token and
Feature activation+0.000
neck
Token neck
Feature activation+0.000
hits
Token hits
Feature activation+0.000
the
Token the
Feature activation+0.000
Thomas
Token Thomas
Feature activation+0.000
&
Token &
Feature activation+0.000
Mack
Token Mack
Feature activation+0.000
Center
Token Center
Feature activation+2.001
is
Token is
Feature activation+4.811
usually
Token usually
Feature activation+5.963
on
Token on
Feature activation+0.000
basketball
Token basketball
Feature activation+0.000
this
Token this
Feature activation+0.000
time
Token time
Feature activation+0.000
tex
Tokentex
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
particular
Token particular
Feature activation+0.000
focus
Token focus
Feature activation+4.799
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Mediterranean
Token Mediterranean
Feature activation+0.000
and
Token and
Feature activation+0.000
North
Token North
Feature activation+0.000
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
abortions
Token abortions
Feature activation+0.000
and
Token and
Feature activation+3.093
instead
Token instead
Feature activation+4.625
focused
Token focused
Feature activation+0.902
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
women
Token women
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
and
Token and
Feature activation+0.000
case
Token case
Feature activation+0.000
preparation
Token preparation
Feature activation+0.000
should
Token should
Feature activation+4.140
not
Token not
Feature activation+4.422
be
Token be
Feature activation+5.334
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
credibility
Token credibility
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
Thus
Token Thus
Feature activation+0.000
,
Token,
Feature activation+0.000
focus
Token focus
Feature activation+0.555
was
Token was
Feature activation+7.153
trained
Token trained
Feature activation+4.394
all
Token all
Feature activation+0.394
last
Token last
Feature activation+0.000
month
Token month
Feature activation+1.855
on
Token on
Feature activation+0.000
Argentina
Token Argentina
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
coming
Token coming
Feature activation+0.000
year
Token year
Feature activation+0.325
will
Token will
Feature activation+5.918
be
Token be
Feature activation+4.141
on
Token on
Feature activation+0.000
merchant
Token merchant
Feature activation+0.000
acquisition
Token acquisition
Feature activation+0.000
and
Token and
Feature activation+0.000
increasing
Token increasing
Feature activation+0.000
any
Token any
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
and
Token and
Feature activation+0.000
case
Token case
Feature activation+0.000
preparation
Token preparation
Feature activation+0.000
should
Token should
Feature activation+4.140
not
Token not
Feature activation+4.422
be
Token be
Feature activation+5.334
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
credibility
Token credibility
Feature activation+0.000
have
Token have
Feature activation+0.000
caused
Token caused
Feature activation+0.000
schools
Token schools
Feature activation+0.000
to
Token to
Feature activation+0.000
focus
Token focus
Feature activation+0.320
entirely
Token entirely
Feature activation+3.920
on
Token on
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
benchmark
Token benchmark
Feature activation+0.000
or
Token or
Feature activation+0.000
requirement
Token requirement
Feature activation+0.000
the
Token the
Feature activation+0.000
fight
Token fight
Feature activation+0.000
,
Token,
Feature activation+0.000
their
Token their
Feature activation+0.000
attention
Token attention
Feature activation+2.405
now
Token now
Feature activation+3.899
turns
Token turns
Feature activation+2.960
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
enemy
Token enemy
Feature activation+0.000
ship
Token ship
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+0.000
focuses
Token focuses
Feature activation+0.226
more
Token more
Feature activation+3.608
on
Token on
Feature activation+0.000
software
Token software
Feature activation+0.000
than
Token than
Feature activation+0.000
hardware
Token hardware
Feature activation+0.000
:
Token:
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Samsung
TokenSamsung
Feature activation+0.000
's
Token's
Feature activation+0.000
focus
Token focus
Feature activation+3.473
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
future
Token future
Feature activation+3.025
is
Token is
Feature activation+4.884
centered
Token centered
Feature activation+2.878
the
Token the
Feature activation+0.000
attention
Token attention
Feature activation+0.781
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+1.617
is
Token is
Feature activation+3.311
focused
Token focused
Feature activation+2.170
on
Token on
Feature activation+0.000
genetically
Token genetically
Feature activation+0.000
modified
Token modified
Feature activation+0.000
(
Token (
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
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
emphasis
Token emphasis
Feature activation+3.295
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
esports
Token esports
Feature activation+0.000
side
Token side
Feature activation+0.000
of
Token of
Feature activation+0.000

Top DFA by src position
MAX = 7.847

political
Token political
Feature activation-0.002
Top resid features:
machine
Token machine
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
Thus
Token Thus
Feature activation+0.057
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
focus
Token focus
Feature activation+7.847
Top resid features:
was
Token was
Feature activation+0.086
Top resid features:
trained
Token trained
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
last
Token last
Feature activation+0.000
Top resid features:
month
Token month
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
While
TokenWhile
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
focus
Token focus
Feature activation+6.551
Top resid features:
at
Token at
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
Thomas
Token Thomas
Feature activation+0.011
Top resid features:
&
Token &
Feature activation+0.012
Top resid features:
Mack
Token Mack
Feature activation-0.032
Top resid features:
said
Token said
Feature activation+0.020
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
The
TokenThe
Feature activation+0.011
Top resid features:
focus
Token focus
Feature activation+6.520
Top resid features:
for
Token for
Feature activation+0.041
Top resid features:
13
Token 13
Feature activation-0.001
Top resid features:
37
Token37
Feature activation+0.016
Top resid features:
Tech
Token Tech
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
honest
Token honest
Feature activation+0.006
Top resid features:
pace
Token pace
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.053
Top resid features:
Now
Token Now
Feature activation+0.075
Top resid features:
the
Token the
Feature activation+0.078
Top resid features:
focus
Token focus
Feature activation+5.294
Top resid features:
shifts
Token shifts
Feature activation+0.531
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
US
Token US
Feature activation+0.000
Top resid features:
Championships
Token Championships
Feature activation+0.000
Top resid features:
child
Token child
Feature activation-0.011
Top resid features:
sexual
Token sexual
Feature activation-0.016
Top resid features:
abuse
Token abuse
Feature activation+0.018
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
focus
Token focus
Feature activation+5.639
Top resid features:
of
Token of
Feature activation+0.070
Top resid features:
any
Token any
Feature activation+0.012
Top resid features:
investigation
Token investigation
Feature activation+0.038
Top resid features:
and
Token and
Feature activation+0.018
Top resid features:
case
Token case
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Samsung
TokenSamsung
Feature activation+0.024
Top resid features:
's
Token's
Feature activation+0.030
Top resid features:
focus
Token focus
Feature activation+5.359
Top resid features:
in
Token in
Feature activation+0.039
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
future
Token future
Feature activation+0.181
Top resid features:
is
Token is
Feature activation+0.338
Top resid features:
centered
Token centered
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
"
Token"
Feature activation+0.109
Top resid features:
The
TokenThe
Feature activation+0.045
Top resid features:
emphasis
Token emphasis
Feature activation+5.271
Top resid features:
is
Token is
Feature activation+0.307
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
head
Token head
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
neck
Token neck
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
While
TokenWhile
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
focus
Token focus
Feature activation+5.661
Top resid features:
at
Token at
Feature activation+0.024
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
Thomas
Token Thomas
Feature activation+0.005
Top resid features:
&
Token &
Feature activation+0.012
Top resid features:
Mack
Token Mack
Feature activation-0.049
Top resid features:
tex
Tokentex
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
with
Token with
Feature activation+0.038
Top resid features:
a
Token a
Feature activation+0.031
Top resid features:
particular
Token particular
Feature activation+0.085
Top resid features:
focus
Token focus
Feature activation+5.428
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Mediterranean
Token Mediterranean
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
North
Token North
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
What
TokenWhat
Feature activation-0.008
Top resid features:
if
Token if
Feature activation+0.018
Top resid features:
we
Token we
Feature activation-0.012
Top resid features:
stopped
Token stopped
Feature activation+0.041
Top resid features:
focusing
Token focusing
Feature activation+4.679
Top resid features:
on
Token on
Feature activation+0.466
Top resid features:
the
Token the
Feature activation+0.118
Top resid features:
number
Token number
Feature activation-0.026
Top resid features:
of
Token of
Feature activation-0.006
Top resid features:
abortions
Token abortions
Feature activation-0.003
Top resid features:
child
Token child
Feature activation+0.002
Top resid features:
sexual
Token sexual
Feature activation-0.004
Top resid features:
abuse
Token abuse
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.028
Top resid features:
focus
Token focus
Feature activation+4.920
Top resid features:
of
Token of
Feature activation+0.080
Top resid features:
any
Token any
Feature activation+0.012
Top resid features:
investigation
Token investigation
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
case
Token case
Feature activation+0.010
Top resid features:
political
Token political
Feature activation-0.006
Top resid features:
machine
Token machine
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
Thus
Token Thus
Feature activation+0.050
Top resid features:
,
Token,
Feature activation+0.085
Top resid features:
focus
Token focus
Feature activation+4.849
Top resid features:
was
Token was
Feature activation+0.216
Top resid features:
trained
Token trained
Feature activation+0.251
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
last
Token last
Feature activation+0.000
Top resid features:
month
Token month
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.017
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
The
TokenThe
Feature activation+0.010
Top resid features:
focus
Token focus
Feature activation+5.139
Top resid features:
for
Token for
Feature activation+0.035
Top resid features:
13
Token 13
Feature activation-0.006
Top resid features:
37
Token37
Feature activation+0.023
Top resid features:
Tech
Token Tech
Feature activation-0.036
Top resid features:
,
Token,
Feature activation+0.080
Top resid features:
child
Token child
Feature activation+0.008
Top resid features:
sexual
Token sexual
Feature activation+0.001
Top resid features:
abuse
Token abuse
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
focus
Token focus
Feature activation+4.638
Top resid features:
of
Token of
Feature activation+0.057
Top resid features:
any
Token any
Feature activation+0.008
Top resid features:
investigation
Token investigation
Feature activation+0.038
Top resid features:
and
Token and
Feature activation+0.027
Top resid features:
case
Token case
Feature activation+0.004
Top resid features:
Washington
Token Washington
Feature activation-0.009
Top resid features:
have
Token have
Feature activation+0.002
Top resid features:
caused
Token caused
Feature activation+0.021
Top resid features:
schools
Token schools
Feature activation-0.076
Top resid features:
to
Token to
Feature activation+0.053
Top resid features:
focus
Token focus
Feature activation+4.663
Top resid features:
entirely
Token entirely
Feature activation+0.094
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
whatever
Token whatever
Feature activation+0.000
Top resid features:
benchmark
Token benchmark
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
fight
Token fight
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
their
Token their
Feature activation+0.034
Top resid features:
attention
Token attention
Feature activation+4.399
Top resid features:
now
Token now
Feature activation+0.218
Top resid features:
turns
Token turns
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
enemy
Token enemy
Feature activation+0.000
Top resid features:
AL
TokenAL
Feature activation+0.031
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
by
Token by
Feature activation-0.008
Top resid features:
contrast
Token contrast
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
focuses
Token focuses
Feature activation+4.423
Top resid features:
more
Token more
Feature activation+0.136
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
software
Token software
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
hardware
Token hardware
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.053
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Samsung
TokenSamsung
Feature activation+0.017
Top resid features:
's
Token's
Feature activation+0.019
Top resid features:
focus
Token focus
Feature activation+4.033
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
future
Token future
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
centered
Token centered
Feature activation+0.000
Top resid features:
America
Token America
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
While
TokenWhile
Feature activation-0.028
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
attention
Token attention
Feature activation+3.242
Top resid features:
of
Token of
Feature activation+0.157
Top resid features:
the
Token the
Feature activation+0.065
Top resid features:
world
Token world
Feature activation+0.127
Top resid features:
is
Token is
Feature activation+0.577
Top resid features:
focused
Token focused
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
with
Token with
Feature activation+0.049
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
lot
Token lot
Feature activation+0.022
Top resid features:
of
Token of
Feature activation+0.020
Top resid features:
emphasis
Token emphasis
Feature activation+3.845
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
esports
Token esports
Feature activation+0.000
Top resid features:
side
Token side
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.52

Head 1: 0.02

Head 2: 0.07

Head 3: 0.06

Head 4: 0.03

Head 5: 0.06

Head 6: 0.02

Head 7: 0.03

Head 8: 0.03

Head 9: 0.02

Head 10: 0.11

Head 11: 0.02

Positive logits

focus3.64

Focus3.61

Focus3.45

ocusing3.17

focus3.14

ocus3.12

foc3.06

focusing3.04

unfocused3.02

focused2.88

ocused2.85

idis2.75

lens2.68

focused2.62

shifted2.53

focuses2.50

lenses2.43

shift2.42

Lens2.41

Horizon2.33

Negative logits

reprint-2.42

cipher-2.39

Bucc-2.32

crypt-2.27

handshake-2.25

ITNESS-2.24

Codes-2.24

Clever-2.23

Passage-2.20

Serv-2.17

signatures-2.15

Print-2.12

BART-2.12

Rak-2.08

jokes-2.08

vending-2.08

joke-2.07

Prosper-2.06

messenger-2.05

guiActiveUn-2.02

INTERVAL 6.438 - 7.153
CONTAINS 0.000%

machine
Token machine
Feature activation+0.000
.
Token.
Feature activation+0.000
Thus
Token Thus
Feature activation+0.000
,
Token,
Feature activation+0.000
focus
Token focus
Feature activation+0.555
was
Token was
Feature activation+7.153
trained
Token trained
Feature activation+4.394
all
Token all
Feature activation+0.394
last
Token last
Feature activation+0.000
month
Token month
Feature activation+1.855
on
Token on
Feature activation+0.000

INTERVAL 5.723 - 6.438
CONTAINS 0.000%

,
Token,
Feature activation+1.863
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
coming
Token coming
Feature activation+0.000
year
Token year
Feature activation+0.325
will
Token will
Feature activation+5.918
be
Token be
Feature activation+4.141
on
Token on
Feature activation+0.000
merchant
Token merchant
Feature activation+0.000
acquisition
Token acquisition
Feature activation+0.000
and
Token and
Feature activation+0.000
Thomas
Token Thomas
Feature activation+0.000
&
Token &
Feature activation+0.000
Mack
Token Mack
Feature activation+0.000
Center
Token Center
Feature activation+2.001
is
Token is
Feature activation+4.811
usually
Token usually
Feature activation+5.963
on
Token on
Feature activation+0.000
basketball
Token basketball
Feature activation+0.000
this
Token this
Feature activation+0.000
time
Token time
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 5.007 - 5.723
CONTAINS 0.000%

and
Token and
Feature activation+0.000
case
Token case
Feature activation+0.000
preparation
Token preparation
Feature activation+0.000
should
Token should
Feature activation+4.140
not
Token not
Feature activation+4.422
be
Token be
Feature activation+5.334
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
credibility
Token credibility
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
pace
Token pace
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
the
Token the
Feature activation+0.000
focus
Token focus
Feature activation+3.230
shifts
Token shifts
Feature activation+5.345
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
Championships
Token Championships
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 4.292 - 5.007
CONTAINS 0.001%

investigation
Token investigation
Feature activation+0.000
and
Token and
Feature activation+0.000
case
Token case
Feature activation+0.000
preparation
Token preparation
Feature activation+0.000
should
Token should
Feature activation+4.140
not
Token not
Feature activation+4.422
be
Token be
Feature activation+5.334
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
credibility
Token credibility
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
abortions
Token abortions
Feature activation+0.000
and
Token and
Feature activation+3.093
instead
Token instead
Feature activation+4.625
focused
Token focused
Feature activation+0.902
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
women
Token women
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
the
Token the
Feature activation+0.000
Thomas
Token Thomas
Feature activation+0.000
&
Token &
Feature activation+0.000
Mack
Token Mack
Feature activation+0.000
Center
Token Center
Feature activation+2.001
is
Token is
Feature activation+4.811
usually
Token usually
Feature activation+5.963
on
Token on
Feature activation+0.000
basketball
Token basketball
Feature activation+0.000
this
Token this
Feature activation+0.000
time
Token time
Feature activation+0.000
.
Token.
Feature activation+0.000
Thus
Token Thus
Feature activation+0.000
,
Token,
Feature activation+0.000
focus
Token focus
Feature activation+0.555
was
Token was
Feature activation+7.153
trained
Token trained
Feature activation+4.394
all
Token all
Feature activation+0.394
last
Token last
Feature activation+0.000
month
Token month
Feature activation+1.855
on
Token on
Feature activation+0.000
Argentina
Token Argentina
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
The
TokenThe
Feature activation+0.000
emphasis
Token emphasis
Feature activation+1.617
is
Token is
Feature activation+4.881
on
Token on
Feature activation+0.000
head
Token head
Feature activation+0.000
and
Token and
Feature activation+0.000
neck
Token neck
Feature activation+0.000
hits
Token hits
Feature activation+0.000

INTERVAL 3.577 - 4.292
CONTAINS 0.001%

for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
coming
Token coming
Feature activation+0.000
year
Token year
Feature activation+0.325
will
Token will
Feature activation+5.918
be
Token be
Feature activation+4.141
on
Token on
Feature activation+0.000
merchant
Token merchant
Feature activation+0.000
acquisition
Token acquisition
Feature activation+0.000
and
Token and
Feature activation+0.000
increasing
Token increasing
Feature activation+0.000
any
Token any
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
and
Token and
Feature activation+0.000
case
Token case
Feature activation+0.000
preparation
Token preparation
Feature activation+0.000
should
Token should
Feature activation+4.140
not
Token not
Feature activation+4.422
be
Token be
Feature activation+5.334
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
credibility
Token credibility
Feature activation+0.000
have
Token have
Feature activation+0.000
caused
Token caused
Feature activation+0.000
schools
Token schools
Feature activation+0.000
to
Token to
Feature activation+0.000
focus
Token focus
Feature activation+0.320
entirely
Token entirely
Feature activation+3.920
on
Token on
Feature activation+0.000
whatever
Token whatever
Feature activation+0.000
benchmark
Token benchmark
Feature activation+0.000
or
Token or
Feature activation+0.000
requirement
Token requirement
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+0.000
focuses
Token focuses
Feature activation+0.226
more
Token more
Feature activation+3.608
on
Token on
Feature activation+0.000
software
Token software
Feature activation+0.000
than
Token than
Feature activation+0.000
hardware
Token hardware
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
fight
Token fight
Feature activation+0.000
,
Token,
Feature activation+0.000
their
Token their
Feature activation+0.000
attention
Token attention
Feature activation+2.405
now
Token now
Feature activation+3.899
turns
Token turns
Feature activation+2.960
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
enemy
Token enemy
Feature activation+0.000
ship
Token ship
Feature activation+0.000

INTERVAL 2.861 - 3.577
CONTAINS 0.001%

on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
abortions
Token abortions
Feature activation+0.000
and
Token and
Feature activation+3.093
instead
Token instead
Feature activation+4.625
focused
Token focused
Feature activation+0.902
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
women
Token women
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Samsung
TokenSamsung
Feature activation+0.000
's
Token's
Feature activation+0.000
focus
Token focus
Feature activation+3.473
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
future
Token future
Feature activation+3.025
is
Token is
Feature activation+4.884
centered
Token centered
Feature activation+2.878
fight
Token fight
Feature activation+0.000
,
Token,
Feature activation+0.000
their
Token their
Feature activation+0.000
attention
Token attention
Feature activation+2.405
now
Token now
Feature activation+3.899
turns
Token turns
Feature activation+2.960
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
enemy
Token enemy
Feature activation+0.000
ship
Token ship
Feature activation+0.000
of
Token of
Feature activation+0.000
development
Token development
Feature activation+0.000
focus
Token focus
Feature activation+1.635
for
Token for
Feature activation+0.000
this
Token this
Feature activation+0.000
mode
Token mode
Feature activation+0.626
is
Token is
Feature activation+2.894
to
Token to
Feature activation+0.000
reward
Token reward
Feature activation+0.000
intelligent
Token intelligent
Feature activation+0.000
team
Token team
Feature activation+0.000
play
Tokenplay
Feature activation+0.000
speaks
Token speaks
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
eyes
Token eyes
Feature activation+2.557
will
Token will
Feature activation+3.118
be
Token be
Feature activation+3.039
on
Token on
Feature activation+0.000
Comey
Token Comey
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
when
Token when
Feature activation+0.000

INTERVAL 2.146 - 2.861
CONTAINS 0.001%

society
Token society
Feature activation+0.000
.
Token.
Feature activation+0.000
Our
Token Our
Feature activation+0.000
focus
Token focus
Feature activation+0.386
is
Token is
Feature activation+2.456
currently
Token currently
Feature activation+2.788
on
Token on
Feature activation+0.000
men
Token men
Feature activation+0.000
and
Token and
Feature activation+0.000
boys
Token boys
Feature activation+0.000
because
Token because
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
which
Token which
Feature activation+0.000
focuses
Token focuses
Feature activation+0.000
almost
Token almost
Feature activation+0.757
entirely
Token entirely
Feature activation+2.760
on
Token on
Feature activation+0.000
writings
Token writings
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
perspective
Token perspective
Feature activation+0.000
of
Token of
Feature activation+0.000
society
Token society
Feature activation+0.000
.
Token.
Feature activation+0.000
Our
Token Our
Feature activation+0.000
focus
Token focus
Feature activation+0.386
is
Token is
Feature activation+2.456
currently
Token currently
Feature activation+2.788
on
Token on
Feature activation+0.000
men
Token men
Feature activation+0.000
and
Token and
Feature activation+0.000
boys
Token boys
Feature activation+0.000
attention
Token attention
Feature activation+0.781
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+1.617
is
Token is
Feature activation+3.311
focused
Token focused
Feature activation+2.170
on
Token on
Feature activation+0.000
genetically
Token genetically
Feature activation+0.000
modified
Token modified
Feature activation+0.000
(
Token (
Feature activation+0.000
GM
TokenGM
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
fight
Token fight
Feature activation+0.000
,
Token,
Feature activation+0.000
their
Token their
Feature activation+0.000
attention
Token attention
Feature activation+2.405
now
Token now
Feature activation+3.899
turns
Token turns
Feature activation+2.960
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
enemy
Token enemy
Feature activation+0.000

INTERVAL 1.431 - 2.146
CONTAINS 0.002%

command
Token command
Feature activation+0.000
the
Token the
Feature activation+0.000
lion
Token lion
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.492
share
Token share
Feature activation+0.000
of
Token of
Feature activation+0.000
attention
Token attention
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
while
Token while
Feature activation+0.000
eyes
Token eyes
Feature activation+0.526
will
Token will
Feature activation+2.236
mostly
Token mostly
Feature activation+2.010
be
Token be
Feature activation+1.994
on
Token on
Feature activation+0.000
Alex
Token Alex
Feature activation+0.000
O
Token O
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
ick
Tokenick
Feature activation+0.000
eters
Tokeneters
Feature activation+0.000
have
Token have
Feature activation+0.000
focused
Token focused
Feature activation+0.000
almost
Token almost
Feature activation+0.796
solely
Token solely
Feature activation+1.462
on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
performances
Token performances
Feature activation+0.000
.
Token.
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Thomas
Token Thomas
Feature activation+0.000
&
Token &
Feature activation+0.000
Mack
Token Mack
Feature activation+0.000
Center
Token Center
Feature activation+2.001
is
Token is
Feature activation+4.811
usually
Token usually
Feature activation+5.963
on
Token on
Feature activation+0.000
basketball
Token basketball
Feature activation+0.000
this
Token this
Feature activation+0.000
no
Token no
Feature activation+0.000
real
Token real
Feature activation+0.000
detail
Token detail
Feature activation+0.000
on
Token on
Feature activation+0.000
what
Token what
Feature activation+0.000
that
Token that
Feature activation+1.674
means
Token means
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
a
Token a
Feature activation+0.000
screenshot
Token screenshot
Feature activation+0.000

INTERVAL 0.715 - 1.431
CONTAINS 0.008%

child
Token child
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
focus
Token focus
Feature activation+0.801
of
Token of
Feature activation+0.000
any
Token any
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
and
Token and
Feature activation+0.000
case
Token case
Feature activation+0.000
ken
Tokenken
Feature activation+0.000
continued
Token continued
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
We
TokenWe
Feature activation+0.506
're
Token're
Feature activation+0.839
doing
Token doing
Feature activation+0.000
it
Token it
Feature activation+0.242
all
Token all
Feature activation+0.000
internally
Token internally
Feature activation+0.000
ourselves
Token ourselves
Feature activation+0.000
regardless
Token regardless
Feature activation+0.463
of
Token of
Feature activation+0.468
logic
Token logic
Feature activation+0.000
and
Token and
Feature activation+0.000
data
Token data
Feature activation+0.000
,
Token,
Feature activation+0.738
inex
Token inex
Feature activation+0.000
or
Tokenor
Feature activation+0.000
ably
Tokenably
Feature activation+0.722
dev
Token dev
Feature activation+0.000
olve
Tokenolve
Feature activation+0.333
after
Token after
Feature activation+0.000
-
Token-
Feature activation+0.000
thought
Tokenthought
Feature activation+0.000
that
Token that
Feature activation+0.000
focused
Token focused
Feature activation+0.000
mostly
Token mostly
Feature activation+1.087
on
Token on
Feature activation+0.000
cosmetics
Token cosmetics
Feature activation+0.000
.
Token.
Feature activation+0.000
Design
Token Design
Feature activation+0.000
only
Token only
Feature activation+0.000
feedback
Token feedback
Feature activation+0.000
really
Token really
Feature activation+0.000
helps
Token helps
Feature activation+0.000
refine
Token refine
Feature activation+0.000
a
Token a
Feature activation+0.000
focus
Token focus
Feature activation+1.091
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Info
TokenInfo
Feature activation+0.000
Q
TokenQ
Feature activation+0.000

INTERVAL 0.000 - 0.715
CONTAINS 99.986%

the
Token the
Feature activation+0.000
cars
Token cars
Feature activation+0.000
give
Token give
Feature activation+0.000
me
Token me
Feature activation+0.000
a
Token a
Feature activation+0.000
feeling
Token feeling
Feature activation+0.000
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
't
Token't
Feature activation+0.000
get
Token get
Feature activation+0.000
of
Token of
Feature activation+0.000
Sir
Token Sir
Feature activation+0.000
Alex
Token Alex
Feature activation+0.000
Ferguson
Token Ferguson
Feature activation+0.000
.
Token.
Feature activation+0.000
Chelsea
Token Chelsea
Feature activation+0.000
have
Token have
Feature activation+0.000
won
Token won
Feature activation+0.000
it
Token it
Feature activation+0.000
on
Token on
Feature activation+0.000
five
Token five
Feature activation+0.000
did
Token did
Feature activation+0.000
a
Token a
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
test
Tokentest
Feature activation+0.000
run
Token run
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
bulls
Token bulls
Feature activation+0.000
PM
Token PM
Feature activation+0.000
GMT
Token GMT
Feature activation+0.000
/
Token /
Feature activation+0.000
Source
Token Source
Feature activation+0.000
:
Token:
Feature activation+0.000
Associated
Token Associated
Feature activation+0.000
Press
Token Press
Feature activation+0.000
By
Token By
Feature activation+0.000
The
Token The
Feature activation+0.000
Associated
Token Associated
Feature activation+0.000
Press
Token Press
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
it
Token it
Feature activation+0.000
went
Token went
Feature activation+0.000
up
Token up
Feature activation+0.000
every
Token every
Feature activation+0.000
10
Token 10
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
fairly
Token fairly
Feature activation+0.000
regularly
Token regularly
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 H9.0: (feature 8376)

TOP ACTIVATIONS
MAX = 6.375

All
TokenAll
Feature activation+0.000
work
Token work
Feature activation+1.169
for
Token for
Feature activation+0.000
each
Token each
Feature activation+0.000
release
Token release
Feature activation+3.921
is
Token is
Feature activation+6.375
visible
Token visible
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
public
Token public
Feature activation+0.000
and
Token and
Feature activation+0.000
overall
Token overall
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
still
Token still
Feature activation+0.000
has
Token has
Feature activation+0.000
work
Token work
Feature activation+0.000
to
Token to
Feature activation+5.797
do
Token do
Feature activation+0.312
to
Token to
Feature activation+0.000
reach
Token reach
Feature activation+0.000
gender
Token gender
Feature activation+0.000
equality
Token equality
Feature activation+0.000
payment
Token payment
Feature activation+0.000
even
Token even
Feature activation+0.000
when
Token when
Feature activation+0.000
work
Token work
Feature activation+0.539
was
Token was
Feature activation+5.602
not
Token not
Feature activation+5.699
completed
Token completed
Feature activation+0.471
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
illustrious
Token illustrious
Feature activation+0.000
for
Token for
Feature activation+0.000
payment
Token payment
Feature activation+0.000
even
Token even
Feature activation+0.000
when
Token when
Feature activation+0.000
work
Token work
Feature activation+0.539
was
Token was
Feature activation+5.602
not
Token not
Feature activation+5.699
completed
Token completed
Feature activation+0.471
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
a
Token a
Feature activation+0.000
sound
Token sound
Feature activation+0.000
that
Token that
Feature activation+0.000
means
Token means
Feature activation+0.000
work
Token work
Feature activation+0.000
is
Token is
Feature activation+5.098
getting
Token getting
Feature activation+4.907
done
Token done
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
sound
Token sound
Feature activation+0.000
that
Token that
Feature activation+0.000
means
Token means
Feature activation+0.000
work
Token work
Feature activation+0.000
is
Token is
Feature activation+5.098
getting
Token getting
Feature activation+4.907
done
Token done
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Paper
TokenPaper
Feature activation+0.000
But
Token But
Feature activation+0.000
nowadays
Token nowadays
Feature activation+0.000
serious
Token serious
Feature activation+0.000
work
Token work
Feature activation+0.000
is
Token is
Feature activation+3.537
being
Token being
Feature activation+4.539
undertaken
Token undertaken
Feature activation+0.196
in
Token in
Feature activation+0.000
terms
Token terms
Feature activation+0.000
of
Token of
Feature activation+0.000
reconstruct
Token reconstruct
Feature activation+0.000
000
Token000
Feature activation+0.000
in
Token in
Feature activation+0.000
payments
Token payments
Feature activation+0.000
for
Token for
Feature activation+0.000
work
Token work
Feature activation+0.000
he
Token he
Feature activation+4.448
did
Token did
Feature activation+1.518
on
Token on
Feature activation+0.000
her
Token her
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
.
Token.
Feature activation+0.000
required
Token required
Feature activation+0.770
to
Token to
Feature activation+0.024
implement
Token implement
Feature activation+0.000
the
Token the
Feature activation+0.000
merging
Token merging
Feature activation+0.000
was
Token was
Feature activation+4.376
done
Token done
Feature activation+0.592
,
Token,
Feature activation+0.065
but
Token but
Feature activation+0.145
with
Token with
Feature activation+0.011
the
Token the
Feature activation+0.000
there
Token there
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
less
Token less
Feature activation+0.000
work
Token work
Feature activation+0.462
to
Token to
Feature activation+4.369
do
Token do
Feature activation+0.248
this
Token this
Feature activation+0.000
time
Token time
Feature activation+0.000
around
Token around
Feature activation+0.147
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
that
Token that
Feature activation+1.261
he
Token he
Feature activation+4.298
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+4.052
doing
Token doing
Feature activation+0.380
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
have
Token have
Feature activation+0.000
work
Token work
Feature activation+0.000
to
Token to
Feature activation+4.228
do
Token do
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
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
more
Token more
Feature activation+0.000
work
Token work
Feature activation+0.601
to
Token to
Feature activation+4.024
be
Token be
Feature activation+4.180
done
Token done
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
supported
Token supported
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
the
Token the
Feature activation+0.000
corporation
Token corporation
Feature activation+2.540
was
Token was
Feature activation+4.173
already
Token already
Feature activation+2.524
doing
Token doing
Feature activation+0.000
to
Token to
Feature activation+0.000
reflect
Token reflect
Feature activation+0.000
identities
Token identities
Feature activation+0.000
work
Token work
Feature activation+0.000
that
Token that
Feature activation+1.261
he
Token he
Feature activation+4.298
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+4.052
doing
Token doing
Feature activation+0.380
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
we
Token we
Feature activation+0.000
just
Token just
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
more
Token more
Feature activation+0.000
work
Token work
Feature activation+0.601
to
Token to
Feature activation+4.024
be
Token be
Feature activation+4.180
done
Token done
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
All
TokenAll
Feature activation+0.000
work
Token work
Feature activation+1.169
for
Token for
Feature activation+0.000
each
Token each
Feature activation+0.000
release
Token release
Feature activation+3.921
is
Token is
Feature activation+6.375
visible
Token visible
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
public
Token public
Feature activation+0.000
vant
Tokenvant
Feature activation+0.000
i
Tokeni
Feature activation+1.202
and
Token and
Feature activation+0.000
Tony
Token Tony
Feature activation+0.000
Anthony
Token Anthony
Feature activation+0.000
have
Token have
Feature activation+3.667
done
Token done
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
years
Token years
Feature activation+0.329
around
Token around
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
nowadays
Token nowadays
Feature activation+0.000
serious
Token serious
Feature activation+0.000
work
Token work
Feature activation+0.000
is
Token is
Feature activation+3.537
being
Token being
Feature activation+4.539
undertaken
Token undertaken
Feature activation+0.196
in
Token in
Feature activation+0.000
terms
Token terms
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
mountains
Token mountains
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
I
Token I
Feature activation+3.531
was
Token was
Feature activation+3.272
doing
Token doing
Feature activation+0.085
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
I
Token I
Feature activation+0.000

Top DFA by src position
MAX = 7.047

Ŀ
TokenĿ
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
All
TokenAll
Feature activation+0.010
Top resid features:
work
Token work
Feature activation+7.047
Top resid features:
for
Token for
Feature activation+0.063
Top resid features:
each
Token each
Feature activation-0.001
Top resid features:
release
Token release
Feature activation+0.077
Top resid features:
is
Token is
Feature activation+0.058
Top resid features:
visible
Token visible
Feature activation+0.000
Top resid features:
science
Token science
Feature activation+0.008
Top resid features:
overall
Token overall
Feature activation-0.009
Top resid features:
âĢĶ
Token âĢĶ
Feature activation-0.014
Top resid features:
still
Token still
Feature activation-0.002
Top resid features:
has
Token has
Feature activation+0.013
Top resid features:
work
Token work
Feature activation+6.563
Top resid features:
to
Token to
Feature activation+0.170
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
reach
Token reach
Feature activation+0.000
Top resid features:
gender
Token gender
Feature activation+0.000
Top resid features:
allowed
Token allowed
Feature activation-0.024
Top resid features:
for
Token for
Feature activation-0.017
Top resid features:
payment
Token payment
Feature activation+0.007
Top resid features:
even
Token even
Feature activation+0.005
Top resid features:
when
Token when
Feature activation+0.028
Top resid features:
work
Token work
Feature activation+6.556
Top resid features:
was
Token was
Feature activation+0.149
Top resid features:
not
Token not
Feature activation+0.073
Top resid features:
completed
Token completed
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
allowed
Token allowed
Feature activation-0.021
Top resid features:
for
Token for
Feature activation-0.028
Top resid features:
payment
Token payment
Feature activation+0.009
Top resid features:
even
Token even
Feature activation+0.007
Top resid features:
when
Token when
Feature activation+0.063
Top resid features:
work
Token work
Feature activation+6.717
Top resid features:
was
Token was
Feature activation+0.040
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
completed
Token completed
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
sound
Token sound
Feature activation-0.013
Top resid features:
that
Token that
Feature activation+0.029
Top resid features:
means
Token means
Feature activation+0.091
Top resid features:
work
Token work
Feature activation+5.779
Top resid features:
is
Token is
Feature activation+0.094
Top resid features:
getting
Token getting
Feature activation+0.000
Top resid features:
done
Token done
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
sound
Token sound
Feature activation-0.015
Top resid features:
that
Token that
Feature activation+0.028
Top resid features:
means
Token means
Feature activation+0.072
Top resid features:
work
Token work
Feature activation+5.243
Top resid features:
is
Token is
Feature activation+0.446
Top resid features:
getting
Token getting
Feature activation+0.086
Top resid features:
done
Token done
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
impossible
Token impossible
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
But
Token But
Feature activation+0.005
Top resid features:
nowadays
Token nowadays
Feature activation+0.076
Top resid features:
serious
Token serious
Feature activation+0.013
Top resid features:
work
Token work
Feature activation+4.891
Top resid features:
is
Token is
Feature activation+0.490
Top resid features:
being
Token being
Feature activation+0.167
Top resid features:
undertaken
Token undertaken
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
terms
Token terms
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
000
Token000
Feature activation-0.030
Top resid features:
in
Token in
Feature activation-0.006
Top resid features:
payments
Token payments
Feature activation+0.003
Top resid features:
for
Token for
Feature activation+0.204
Top resid features:
work
Token work
Feature activation+5.256
Top resid features:
he
Token he
Feature activation+0.249
Top resid features:
did
Token did
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
campaign
Token campaign
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.614
Top resid features:
The
Token The
Feature activation+0.021
Top resid features:
technical
Token technical
Feature activation-0.001
Top resid features:
work
Token work
Feature activation+4.498
Top resid features:
required
Token required
Feature activation+0.434
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
implement
Token implement
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
merging
Token merging
Feature activation+0.011
Top resid features:
while
Token while
Feature activation+0.009
Top resid features:
there
Token there
Feature activation-0.000
Top resid features:
may
Token may
Feature activation+0.010
Top resid features:
be
Token be
Feature activation+0.006
Top resid features:
less
Token less
Feature activation+0.030
Top resid features:
work
Token work
Feature activation+4.892
Top resid features:
to
Token to
Feature activation+0.305
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
around
Token around
Feature activation+0.000
Top resid features:
no
Token no
Feature activation+0.008
Top resid features:
pain
Token pain
Feature activation+0.064
Top resid features:
with
Token with
Feature activation+0.033
Top resid features:
all
Token all
Feature activation+0.113
Top resid features:
the
Token the
Feature activation+0.090
Top resid features:
work
Token work
Feature activation+4.501
Top resid features:
that
Token that
Feature activation+0.712
Top resid features:
he
Token he
Feature activation+0.065
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.029
Top resid features:
âĢ
Token âĢ
Feature activation+0.004
Top resid features:
ľ
Tokenľ
Feature activation+0.015
Top resid features:
We
TokenWe
Feature activation+0.004
Top resid features:
have
Token have
Feature activation+0.009
Top resid features:
work
Token work
Feature activation+4.760
Top resid features:
to
Token to
Feature activation+0.409
Top resid features:
do
Token do
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:
there
Token there
Feature activation+0.008
Top resid features:
âĢ
TokenâĢ
Feature activation-0.003
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
s
Tokens
Feature activation+0.050
Top resid features:
more
Token more
Feature activation+0.023
Top resid features:
work
Token work
Feature activation+4.714
Top resid features:
to
Token to
Feature activation+0.340
Top resid features:
be
Token be
Feature activation+0.011
Top resid features:
done
Token done
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
BBC
Token BBC
Feature activation-0.023
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
supported
Token supported
Feature activation+0.023
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
work
Token work
Feature activation+4.923
Top resid features:
the
Token the
Feature activation+0.037
Top resid features:
corporation
Token corporation
Feature activation+0.058
Top resid features:
was
Token was
Feature activation+0.044
Top resid features:
already
Token already
Feature activation+0.000
Top resid features:
doing
Token doing
Feature activation+0.000
Top resid features:
no
Token no
Feature activation+0.005
Top resid features:
pain
Token pain
Feature activation+0.105
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.067
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
work
Token work
Feature activation+4.063
Top resid features:
that
Token that
Feature activation+0.758
Top resid features:
he
Token he
Feature activation+0.209
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ļ
TokenĻ
Feature activation-0.005
Top resid features:
s
Tokens
Feature activation+0.015
Top resid features:
there
Token there
Feature activation+0.005
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
s
Tokens
Feature activation+0.034
Top resid features:
more
Token more
Feature activation+0.043
Top resid features:
work
Token work
Feature activation+4.585
Top resid features:
to
Token to
Feature activation+0.254
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
done
Token done
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:
.
Token.
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
All
TokenAll
Feature activation+0.056
Top resid features:
work
Token work
Feature activation+4.603
Top resid features:
for
Token for
Feature activation+0.125
Top resid features:
each
Token each
Feature activation+0.152
Top resid features:
release
Token release
Feature activation+0.013
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
visible
Token visible
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
they
Token they
Feature activation+0.002
Top resid features:
recognise
Token recognise
Feature activation+0.033
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
good
Token good
Feature activation+0.043
Top resid features:
work
Token work
Feature activation+4.166
Top resid features:
that
Token that
Feature activation+0.431
Top resid features:
A
Token A
Feature activation+0.002
Top resid features:
vant
Tokenvant
Feature activation+0.001
Top resid features:
i
Tokeni
Feature activation+0.025
Top resid features:
and
Token and
Feature activation-0.027
Top resid features:
impossible
Token impossible
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.034
Top resid features:
But
Token But
Feature activation+0.016
Top resid features:
nowadays
Token nowadays
Feature activation+0.101
Top resid features:
serious
Token serious
Feature activation+0.018
Top resid features:
work
Token work
Feature activation+4.013
Top resid features:
is
Token is
Feature activation+0.386
Top resid features:
being
Token being
Feature activation+0.000
Top resid features:
undertaken
Token undertaken
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
terms
Token terms
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
mountains
Token mountains
Feature activation-0.104
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
work
Token work
Feature activation+4.319
Top resid features:
I
Token I
Feature activation+0.258
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
doing
Token doing
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.51

Head 1: 0.02

Head 2: 0.12

Head 3: 0.06

Head 4: 0.02

Head 5: 0.04

Head 6: 0.02

Head 7: 0.03

Head 8: 0.03

Head 9: 0.02

Head 10: 0.09

Head 11: 0.02

Positive logits

Work3.57

work3.51

work3.43

WORK3.36

Work3.09

Working2.99

collaborators2.92

collaborative2.89

WORK2.85

worked2.84

collaborator2.83

done2.82

done2.78

works2.76

worked2.75

performed2.72

completed2.70

Job2.70

ompl2.70

abor2.64

Negative logits

Royale-2.44

midrange-2.37

issuer-2.32

Sovereign-2.28

Flavoring-2.26

Heller-2.24

ejected-2.24

broadcasting-2.24

Kodi-2.22

Seat-2.22

Chips-2.21

elector-2.18

nostalg-2.17

BIOS-2.17

flyers-2.16

Reserve-2.15

booster-2.13

osphere-2.13

ramer-2.13

Hilton-2.12

INTERVAL 5.737 - 6.375
CONTAINS 0.000%

overall
Token overall
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
still
Token still
Feature activation+0.000
has
Token has
Feature activation+0.000
work
Token work
Feature activation+0.000
to
Token to
Feature activation+5.797
do
Token do
Feature activation+0.312
to
Token to
Feature activation+0.000
reach
Token reach
Feature activation+0.000
gender
Token gender
Feature activation+0.000
equality
Token equality
Feature activation+0.000
All
TokenAll
Feature activation+0.000
work
Token work
Feature activation+1.169
for
Token for
Feature activation+0.000
each
Token each
Feature activation+0.000
release
Token release
Feature activation+3.921
is
Token is
Feature activation+6.375
visible
Token visible
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
public
Token public
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 5.100 - 5.737
CONTAINS 0.000%

for
Token for
Feature activation+0.000
payment
Token payment
Feature activation+0.000
even
Token even
Feature activation+0.000
when
Token when
Feature activation+0.000
work
Token work
Feature activation+0.539
was
Token was
Feature activation+5.602
not
Token not
Feature activation+5.699
completed
Token completed
Feature activation+0.471
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
payment
Token payment
Feature activation+0.000
even
Token even
Feature activation+0.000
when
Token when
Feature activation+0.000
work
Token work
Feature activation+0.539
was
Token was
Feature activation+5.602
not
Token not
Feature activation+5.699
completed
Token completed
Feature activation+0.471
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
illustrious
Token illustrious
Feature activation+0.000

INTERVAL 4.462 - 5.100
CONTAINS 0.000%

But
Token But
Feature activation+0.000
nowadays
Token nowadays
Feature activation+0.000
serious
Token serious
Feature activation+0.000
work
Token work
Feature activation+0.000
is
Token is
Feature activation+3.537
being
Token being
Feature activation+4.539
undertaken
Token undertaken
Feature activation+0.196
in
Token in
Feature activation+0.000
terms
Token terms
Feature activation+0.000
of
Token of
Feature activation+0.000
reconstruct
Token reconstruct
Feature activation+0.000
a
Token a
Feature activation+0.000
sound
Token sound
Feature activation+0.000
that
Token that
Feature activation+0.000
means
Token means
Feature activation+0.000
work
Token work
Feature activation+0.000
is
Token is
Feature activation+5.098
getting
Token getting
Feature activation+4.907
done
Token done
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
sound
Token sound
Feature activation+0.000
that
Token that
Feature activation+0.000
means
Token means
Feature activation+0.000
work
Token work
Feature activation+0.000
is
Token is
Feature activation+5.098
getting
Token getting
Feature activation+4.907
done
Token done
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Paper
TokenPaper
Feature activation+0.000

INTERVAL 3.825 - 4.462
CONTAINS 0.001%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
more
Token more
Feature activation+0.000
work
Token work
Feature activation+0.601
to
Token to
Feature activation+4.024
be
Token be
Feature activation+4.180
done
Token done
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
more
Token more
Feature activation+0.000
work
Token work
Feature activation+0.601
to
Token to
Feature activation+4.024
be
Token be
Feature activation+4.180
done
Token done
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.000
with
Token with
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
that
Token that
Feature activation+1.261
he
Token he
Feature activation+4.298
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+4.052
doing
Token doing
Feature activation+0.380
,
Token,
Feature activation+0.000
work
Token work
Feature activation+0.000
that
Token that
Feature activation+1.261
he
Token he
Feature activation+4.298
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+4.052
doing
Token doing
Feature activation+0.380
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
we
Token we
Feature activation+0.000
just
Token just
Feature activation+0.000
000
Token000
Feature activation+0.000
in
Token in
Feature activation+0.000
payments
Token payments
Feature activation+0.000
for
Token for
Feature activation+0.000
work
Token work
Feature activation+0.000
he
Token he
Feature activation+4.448
did
Token did
Feature activation+1.518
on
Token on
Feature activation+0.000
her
Token her
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 3.187 - 3.825
CONTAINS 0.001%

vant
Tokenvant
Feature activation+0.000
i
Tokeni
Feature activation+1.202
and
Token and
Feature activation+0.000
Tony
Token Tony
Feature activation+0.000
Anthony
Token Anthony
Feature activation+0.000
have
Token have
Feature activation+3.667
done
Token done
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
years
Token years
Feature activation+0.329
around
Token around
Feature activation+0.000
mountains
Token mountains
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
I
Token I
Feature activation+3.531
was
Token was
Feature activation+3.272
doing
Token doing
Feature activation+0.085
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
I
Token I
Feature activation+0.000
missed
Token missed
Feature activation+0.000
eter
Tokeneter
Feature activation+0.000
.
Token.
Feature activation+0.000
Once
Token Once
Feature activation+0.000
this
Token this
Feature activation+0.000
work
Token work
Feature activation+0.898
has
Token has
Feature activation+3.209
been
Token been
Feature activation+3.432
completed
Token completed
Feature activation+0.494
,
Token,
Feature activation+0.000
specific
Token specific
Feature activation+0.000
targets
Token targets
Feature activation+0.000
F
Token F
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
ano
Tokenano
Feature activation+0.000
.
Token.
Feature activation+0.000
Work
Token Work
Feature activation+0.356
was
Token was
Feature activation+3.242
stopped
Token stopped
Feature activation+0.965
in
Token in
Feature activation+0.000
June
Token June
Feature activation+0.000
2013
Token 2013
Feature activation+0.704
because
Token because
Feature activation+0.000
.
Token.
Feature activation+0.000
Once
Token Once
Feature activation+0.000
this
Token this
Feature activation+0.000
work
Token work
Feature activation+0.898
has
Token has
Feature activation+3.209
been
Token been
Feature activation+3.432
completed
Token completed
Feature activation+0.494
,
Token,
Feature activation+0.000
specific
Token specific
Feature activation+0.000
targets
Token targets
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 2.550 - 3.187
CONTAINS 0.001%

our
Token our
Feature activation+0.000
team
Token team
Feature activation+0.000
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+0.000
work
Token work
Feature activation+0.000
is
Token is
Feature activation+3.143
almost
Token almost
Feature activation+2.159
finished
Token finished
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
given
Token given
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
track
Token track
Feature activation+0.000
work
Token work
Feature activation+0.558
continues
Token continues
Feature activation+2.073
to
Token to
Feature activation+2.803
progress
Token progress
Feature activation+0.610
in
Token in
Feature activation+0.388
this
Token this
Feature activation+0.255
area
Token area
Feature activation+0.746
we
Token we
Feature activation+0.000
they
Token they
Feature activation+0.000
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
have
Token have
Feature activation+0.000
work
Token work
Feature activation+0.000
to
Token to
Feature activation+2.662
do
Token do
Feature activation+0.399
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
may
Token may
Feature activation+0.000
think
Token think
Feature activation+0.000
itself
Token itself
Feature activation+0.905
,
Token,
Feature activation+0.165
however
Token however
Feature activation+0.602
,
Token,
Feature activation+1.327
is
Token is
Feature activation+1.298
being
Token being
Feature activation+2.956
largely
Token largely
Feature activation+2.202
undertaken
Token undertaken
Feature activation+0.000
by
Token by
Feature activation+0.000
TTC
Token TTC
Feature activation+0.000
staff
Token staff
Feature activation+0.000
he
Token he
Feature activation+0.658
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.404
currently
Token currently
Feature activation+1.288
putting
Token putting
Feature activation+2.783
in
Token in
Feature activation+1.105
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
four
Token four
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 1.912 - 2.550
CONTAINS 0.002%

should
Token should
Feature activation+0.000
overlook
Token overlook
Feature activation+0.000
the
Token the
Feature activation+0.000
groundbreaking
Token groundbreaking
Feature activation+0.000
work
Token work
Feature activation+0.098
he
Token he
Feature activation+2.354
did
Token did
Feature activation+0.778
on
Token on
Feature activation+0.000
'
Token '
Feature activation+0.000
2001
Token2001
Feature activation+0.000
:
Token:
Feature activation+0.000
required
Token required
Feature activation+0.196
.
Token.
Feature activation+0.000
Apply
TokenApply
Feature activation+0.000
at
Token at
Feature activation+0.000
your
Token your
Feature activation+0.829
local
Token local
Feature activation+2.018
welfare
Token welfare
Feature activation+0.000
office
Token office
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
or
Token or
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
they
Token they
Feature activation+0.886
've
Token've
Feature activation+2.004
done
Token done
Feature activation+0.181
as
Token as
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
an
Token an
Feature activation+0.010
team
Token team
Feature activation+0.000
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+0.000
work
Token work
Feature activation+0.000
is
Token is
Feature activation+3.143
almost
Token almost
Feature activation+2.159
finished
Token finished
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
given
Token given
Feature activation+0.000
the
Token the
Feature activation+0.000
itous
Tokenitous
Feature activation+0.000
Computing
Token Computing
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
work
Token work
Feature activation+0.000
originally
Token originally
Feature activation+2.281
focused
Token focused
Feature activation+0.000
on
Token on
Feature activation+0.000
adapting
Token adapting
Feature activation+0.000
widely
Token widely
Feature activation+0.000
available
Token available
Feature activation+0.000

INTERVAL 1.275 - 1.912
CONTAINS 0.005%

in
Token in
Feature activation+0.000
law
Token law
Feature activation+0.000
enforcement
Token enforcement
Feature activation+0.000
,
Token,
Feature activation+0.000
work
Token work
Feature activation+0.000
that
Token that
Feature activation+1.565
he
Token he
Feature activation+0.420
did
Token did
Feature activation+0.040
not
Token not
Feature activation+1.554
want
Token want
Feature activation+1.600
to
Token to
Feature activation+1.469
other
Token other
Feature activation+0.000
labor
Token labor
Feature activation+0.000
reforms
Token reforms
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.524
boosting
Token boosting
Feature activation+1.593
the
Token the
Feature activation+1.429
sub
Token sub
Feature activation+0.000
-
Token-
Feature activation+0.000
minimum
Tokenminimum
Feature activation+0.000
wage
Token wage
Feature activation+0.000
business
Token business
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
is
Token is
Feature activation+1.741
crisp
Token crisp
Feature activation+0.000
and
Token and
Feature activation+1.223
effective
Token effective
Feature activation+0.000
.
Token.
Feature activation+0.000
Y
Token Y
Feature activation+0.000
labor
Token labor
Feature activation+0.000
reforms
Token reforms
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.524
boosting
Token boosting
Feature activation+1.593
the
Token the
Feature activation+1.429
sub
Token sub
Feature activation+0.000
-
Token-
Feature activation+0.000
minimum
Tokenminimum
Feature activation+0.000
wage
Token wage
Feature activation+0.000
level
Token level
Feature activation+0.000
work
Token work
Feature activation+0.000
itself
Token itself
Feature activation+0.905
,
Token,
Feature activation+0.165
however
Token however
Feature activation+0.602
,
Token,
Feature activation+1.327
is
Token is
Feature activation+1.298
being
Token being
Feature activation+2.956
largely
Token largely
Feature activation+2.202
undertaken
Token undertaken
Feature activation+0.000
by
Token by
Feature activation+0.000
TTC
Token TTC
Feature activation+0.000

INTERVAL 0.637 - 1.275
CONTAINS 0.015%

the
Token the
Feature activation+0.000
hard
Token hard
Feature activation+0.000
work
Token work
Feature activation+1.031
that
Token that
Feature activation+0.752
the
Token the
Feature activation+0.000
recovery
Token recovery
Feature activation+0.641
would
Token would
Feature activation+3.226
entail
Token entail
Feature activation+0.413
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
dilemma
Token dilemma
Feature activation+0.000
was
Token was
Feature activation+0.000
allegedly
Token allegedly
Feature activation+0.000
being
Token being
Feature activation+0.000
forced
Token forced
Feature activation+0.000
by
Token by
Feature activation+0.000
his
Token his
Feature activation+0.996
family
Token family
Feature activation+0.000
to
Token to
Feature activation+0.000
marry
Token marry
Feature activation+0.000
someone
Token someone
Feature activation+0.000
else
Token else
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
rehab
Token rehab
Feature activation+0.000
work
Token work
Feature activation+0.169
he
Token he
Feature activation+0.658
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.404
currently
Token currently
Feature activation+1.288
putting
Token putting
Feature activation+2.783
is
Token is
Feature activation+0.000
by
Token by
Feature activation+0.000
definition
Token definition
Feature activation+0.000
a
Token a
Feature activation+0.000
work
Token work
Feature activation+0.000
in
Token in
Feature activation+1.246
progress
Token progress
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
this
Token this
Feature activation+0.000
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
its
Token its
Feature activation+0.000
organized
Token organized
Feature activation+0.000
labor
Token labor
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.865
advocating
Token advocating
Feature activation+0.111
worker
Token worker
Feature activation+0.000
control
Token control
Feature activation+0.000
and
Token and
Feature activation+0.889
anarchist
Token anarchist
Feature activation+0.000

INTERVAL 0.000 - 0.637
CONTAINS 99.975%

c
Tokenc
Feature activation+0.000
ob
Tokenob
Feature activation+0.000
acter
Tokenacter
Feature activation+0.000
ium
Tokenium
Feature activation+0.000
tuberculosis
Token tuberculosis
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
resistant
Token resistant
Feature activation+0.000
to
Token to
Feature activation+0.000
all
Token all
Feature activation+0.000
in
Token in
Feature activation+0.000
arsenic
Token arsenic
Feature activation+0.000
removal
Token removal
Feature activation+0.000
have
Token have
Feature activation+0.000
taken
Token taken
Feature activation+0.000
place
Token place
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
must
Token must
Feature activation+0.000
consider
Token consider
Feature activation+0.000
variations
Token variations
Feature activation+0.000
for
Tokenfor
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
board
Token board
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
original
Token original
Feature activation+0.000
posure
Tokenposure
Feature activation+0.000
bracket
Token bracket
Feature activation+0.000
ing
Tokening
Feature activation+0.000
may
Token may
Feature activation+0.000
work
Token work
Feature activation+0.000
in
Token in
Feature activation+0.000
some
Token some
Feature activation+0.000
cases
Token cases
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
prefer
Token prefer
Feature activation+0.000
tre
Tokentre
Feature activation+0.000
accord
Token accord
Feature activation+0.000
és
Tokenés
Feature activation+0.000
par
Token par
Feature activation+0.000
une
Token une
Feature activation+0.000
j
Token j
Feature activation+0.000
uge
Tokenuge
Feature activation+0.000
de
Token de
Feature activation+0.000
prem
Token prem
Feature activation+0.000
i
Tokeni
Feature activation+0.000
ère
Tokenère
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 H9.0: (feature 23355)

TOP ACTIVATIONS
MAX = 6.926

and
Token and
Feature activation+0.000
Marty
Token Marty
Feature activation+0.000
Alexander
Token Alexander
Feature activation+0.000
cast
Token cast
Feature activation+2.101
a
Token a
Feature activation+6.888
broader
Token broader
Feature activation+6.926
net
Token net
Feature activation+0.951
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
suggested
Token suggested
Feature activation+0.000
that
Token that
Feature activation+0.000
ocks
Tokenocks
Feature activation+0.000
and
Token and
Feature activation+0.000
Marty
Token Marty
Feature activation+0.000
Alexander
Token Alexander
Feature activation+0.000
cast
Token cast
Feature activation+2.101
a
Token a
Feature activation+6.888
broader
Token broader
Feature activation+6.926
net
Token net
Feature activation+0.951
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
suggested
Token suggested
Feature activation+0.000
The
TokenThe
Feature activation+0.000
tactic
Token tactic
Feature activation+0.000
has
Token has
Feature activation+0.000
cast
Token cast
Feature activation+2.085
such
Token such
Feature activation+2.029
a
Token a
Feature activation+6.470
shadow
Token shadow
Feature activation+2.293
of
Token of
Feature activation+0.140
fear
Token fear
Feature activation+2.484
over
Token over
Feature activation+0.000
strike
Token strike
Feature activation+0.000
and
Token and
Feature activation+0.000
so
Token so
Feature activation+0.000
on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
casting
Token casting
Feature activation+0.435
a
Token a
Feature activation+6.255
gradually
Token gradually
Feature activation+1.965
wider
Token wider
Feature activation+5.854
net
Token net
Feature activation+0.721
.
Token.
Feature activation+0.000
An
Token An
Feature activation+0.000
on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
casting
Token casting
Feature activation+0.435
a
Token a
Feature activation+6.255
gradually
Token gradually
Feature activation+1.965
wider
Token wider
Feature activation+5.854
net
Token net
Feature activation+0.721
.
Token.
Feature activation+0.000
An
Token An
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
official
Token official
Feature activation+0.000
views
Token views
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
only
Token only
Feature activation+0.000
cast
Token cast
Feature activation+0.286
one
Token one
Feature activation+5.718
vote
Token vote
Feature activation+1.668
myself
Token myself
Feature activation+0.365
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
material
Tokenmaterial
Feature activation+0.000
uncertainty
Token uncertainty
Feature activation+0.000
which
Token which
Feature activation+0.000
may
Token may
Feature activation+0.000
cast
Token cast
Feature activation+0.854
significant
Token significant
Feature activation+5.541
doubt
Token doubt
Feature activation+0.758
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
consolidated
Token consolidated
Feature activation+0.000
entity
Token entity
Feature activation+0.000
:
Token:
Feature activation+0.000
who
Token who
Feature activation+0.000
may
Token may
Feature activation+0.000
cast
Token cast
Feature activation+0.000
the
Token the
Feature activation+4.630
first
Token first
Feature activation+5.010
stone
Token stone
Feature activation+0.288
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
racism
Token racism
Feature activation+0.000
:
Token:
Feature activation+0.000
who
Token who
Feature activation+0.000
may
Token may
Feature activation+0.000
cast
Token cast
Feature activation+0.000
the
Token the
Feature activation+4.630
first
Token first
Feature activation+5.010
stone
Token stone
Feature activation+0.288
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
P
Token P
Feature activation+0.000
BO
TokenBO
Feature activation+0.000
projections
Token projections
Feature activation+0.000
have
Token have
Feature activation+0.000
cast
Token cast
Feature activation+1.272
doubt
Token doubt
Feature activation+4.224
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
balanced
Token balanced
Feature activation+0.000
budget
Token budget
Feature activation+0.000
this
Token this
Feature activation+0.000
The
Token The
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Post
Token Post
Feature activation+0.000
article
Token article
Feature activation+0.000
cast
Token cast
Feature activation+1.773
it
Token it
Feature activation+4.212
in
Token in
Feature activation+3.613
an
Token an
Feature activation+3.437
Orwell
Token Orwell
Feature activation+0.000
ian
Tokenian
Feature activation+2.065
light
Token light
Feature activation+0.000
and
Token and
Feature activation+0.000
warrant
Token warrant
Feature activation+0.000
less
Tokenless
Feature activation+0.000
surveillance
Token surveillance
Feature activation+0.000
cast
Token cast
Feature activation+0.714
a
Token a
Feature activation+3.899
shadow
Token shadow
Feature activation+2.974
over
Token over
Feature activation+0.000
existing
Token existing
Feature activation+0.000
democratic
Token democratic
Feature activation+0.000
legal
Token legal
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Post
Token Post
Feature activation+0.000
article
Token article
Feature activation+0.000
cast
Token cast
Feature activation+1.773
it
Token it
Feature activation+4.212
in
Token in
Feature activation+3.613
an
Token an
Feature activation+3.437
Orwell
Token Orwell
Feature activation+0.000
ian
Tokenian
Feature activation+2.065
light
Token light
Feature activation+0.000
:
Token:
Feature activation+0.000
are
Token are
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
cast
Token cast
Feature activation+0.000
oversee
Token oversee
Feature activation+1.011
able
Tokenable
Feature activation+3.613
,
Token,
Feature activation+0.000
ver
Token ver
Feature activation+0.000
ifiable
Tokenifiable
Feature activation+2.419
votes
Token votes
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
the
Token the
Feature activation+0.000
casting
Token casting
Feature activation+0.000
of
Token of
Feature activation+3.605
votes
Token votes
Feature activation+0.000
online
Token online
Feature activation+0.000
pretty
Token pretty
Feature activation+0.000
much
Token much
Feature activation+0.000
the
Token the
Feature activation+0.000
Post
Token Post
Feature activation+0.000
article
Token article
Feature activation+0.000
cast
Token cast
Feature activation+1.773
it
Token it
Feature activation+4.212
in
Token in
Feature activation+3.613
an
Token an
Feature activation+3.437
Orwell
Token Orwell
Feature activation+0.000
ian
Tokenian
Feature activation+2.065
light
Token light
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Aside
TokenAside
Feature activation+0.000
from
Token from
Feature activation+0.000
casting
Token casting
Feature activation+0.988
light
Token light
Feature activation+3.291
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
murky
Token murky
Feature activation+0.000
nexus
Token nexus
Feature activation+0.000
of
Token of
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
just
Token just
Feature activation+0.000
casting
Token casting
Feature activation+0.000
a
Token a
Feature activation+2.986
person
Token person
Feature activation+0.838
of
Token of
Feature activation+0.000
color
Token color
Feature activation+2.551
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
warrant
Token warrant
Feature activation+0.000
less
Tokenless
Feature activation+0.000
surveillance
Token surveillance
Feature activation+0.000
cast
Token cast
Feature activation+0.714
a
Token a
Feature activation+3.899
shadow
Token shadow
Feature activation+2.974
over
Token over
Feature activation+0.000
existing
Token existing
Feature activation+0.000
democratic
Token democratic
Feature activation+0.000
legal
Token legal
Feature activation+0.000
protections
Token protections
Feature activation+0.000
President
Token President
Feature activation+0.000
Vladimir
Token Vladimir
Feature activation+0.000
Putin
Token Putin
Feature activation+0.000
and
Token and
Feature activation+0.000
cast
Token cast
Feature activation+0.272
doubt
Token doubt
Feature activation+2.795
on
Token on
Feature activation+0.512
the
Token the
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
community
Token community
Feature activation+0.000
's
Token's
Feature activation+0.000

Top DFA by src position
MAX = 7.699

St
Token St
Feature activation-0.000
Top resid features:
ocks
Tokenocks
Feature activation-0.003
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
Marty
Token Marty
Feature activation-0.000
Top resid features:
Alexander
Token Alexander
Feature activation+0.003
Top resid features:
cast
Token cast
Feature activation+7.191
Top resid features:
a
Token a
Feature activation+0.565
Top resid features:
broader
Token broader
Feature activation+0.151
Top resid features:
net
Token net
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
They
Token They
Feature activation+0.000
Top resid features:
St
Token St
Feature activation+0.001
Top resid features:
ocks
Tokenocks
Feature activation-0.006
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
Marty
Token Marty
Feature activation+0.002
Top resid features:
Alexander
Token Alexander
Feature activation+0.052
Top resid features:
cast
Token cast
Feature activation+7.699
Top resid features:
a
Token a
Feature activation+0.149
Top resid features:
broader
Token broader
Feature activation+0.000
Top resid features:
net
Token net
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
They
Token They
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
The
TokenThe
Feature activation+0.011
Top resid features:
tactic
Token tactic
Feature activation+0.008
Top resid features:
has
Token has
Feature activation+0.011
Top resid features:
cast
Token cast
Feature activation+7.165
Top resid features:
such
Token such
Feature activation+0.163
Top resid features:
a
Token a
Feature activation+0.170
Top resid features:
shadow
Token shadow
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
fear
Token fear
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
so
Token so
Feature activation-0.025
Top resid features:
on
Token on
Feature activation-0.024
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
casting
Token casting
Feature activation+7.108
Top resid features:
a
Token a
Feature activation+0.174
Top resid features:
gradually
Token gradually
Feature activation+0.000
Top resid features:
wider
Token wider
Feature activation+0.000
Top resid features:
net
Token net
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
so
Token so
Feature activation+0.001
Top resid features:
on
Token on
Feature activation-0.010
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
casting
Token casting
Feature activation+6.173
Top resid features:
a
Token a
Feature activation+0.513
Top resid features:
gradually
Token gradually
Feature activation+0.047
Top resid features:
wider
Token wider
Feature activation+0.136
Top resid features:
net
Token net
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
ist
Tokenist
Feature activation+0.006
Top resid features:
views
Token views
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
I
Token I
Feature activation+0.033
Top resid features:
only
Token only
Feature activation+0.013
Top resid features:
cast
Token cast
Feature activation+6.552
Top resid features:
one
Token one
Feature activation+0.186
Top resid features:
vote
Token vote
Feature activation+0.000
Top resid features:
myself
Token myself
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.004
Top resid features:
material
Tokenmaterial
Feature activation-0.001
Top resid features:
uncertainty
Token uncertainty
Feature activation+0.112
Top resid features:
which
Token which
Feature activation+0.051
Top resid features:
may
Token may
Feature activation+0.066
Top resid features:
cast
Token cast
Feature activation+6.425
Top resid features:
significant
Token significant
Feature activation+0.058
Top resid features:
doubt
Token doubt
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
consolidated
Token consolidated
Feature activation+0.000
Top resid features:
alleged
Token alleged
Feature activation-0.011
Top resid features:
racism
Token racism
Feature activation-0.098
Top resid features:
:
Token:
Feature activation+0.004
Top resid features:
who
Token who
Feature activation-0.003
Top resid features:
may
Token may
Feature activation+0.027
Top resid features:
cast
Token cast
Feature activation+5.994
Top resid features:
the
Token the
Feature activation+0.194
Top resid features:
first
Token first
Feature activation+0.116
Top resid features:
stone
Token stone
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
alleged
Token alleged
Feature activation-0.014
Top resid features:
racism
Token racism
Feature activation-0.101
Top resid features:
:
Token:
Feature activation+0.007
Top resid features:
who
Token who
Feature activation-0.002
Top resid features:
may
Token may
Feature activation+0.041
Top resid features:
cast
Token cast
Feature activation+5.816
Top resid features:
the
Token the
Feature activation+0.137
Top resid features:
first
Token first
Feature activation+0.000
Top resid features:
stone
Token stone
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
P
Token P
Feature activation-0.001
Top resid features:
BO
TokenBO
Feature activation+0.003
Top resid features:
projections
Token projections
Feature activation+0.040
Top resid features:
have
Token have
Feature activation+0.040
Top resid features:
cast
Token cast
Feature activation+4.198
Top resid features:
doubt
Token doubt
Feature activation+0.776
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
balanced
Token balanced
Feature activation+0.000
Top resid features:
budget
Token budget
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.031
Top resid features:
The
Token The
Feature activation+0.019
Top resid features:
Washington
Token Washington
Feature activation-0.003
Top resid features:
Post
Token Post
Feature activation-0.022
Top resid features:
article
Token article
Feature activation-0.014
Top resid features:
cast
Token cast
Feature activation+4.989
Top resid features:
it
Token it
Feature activation+0.137
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
Orwell
Token Orwell
Feature activation+0.000
Top resid features:
ian
Tokenian
Feature activation+0.000
Top resid features:
rights
Token rights
Feature activation-0.003
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
warrant
Token warrant
Feature activation-0.003
Top resid features:
less
Tokenless
Feature activation+0.001
Top resid features:
surveillance
Token surveillance
Feature activation-0.025
Top resid features:
cast
Token cast
Feature activation+4.840
Top resid features:
a
Token a
Feature activation+0.137
Top resid features:
shadow
Token shadow
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
existing
Token existing
Feature activation+0.000
Top resid features:
democratic
Token democratic
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
The
Token The
Feature activation+0.023
Top resid features:
Washington
Token Washington
Feature activation+0.008
Top resid features:
Post
Token Post
Feature activation+0.007
Top resid features:
article
Token article
Feature activation-0.047
Top resid features:
cast
Token cast
Feature activation+3.995
Top resid features:
it
Token it
Feature activation+0.480
Top resid features:
in
Token in
Feature activation+0.072
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
Orwell
Token Orwell
Feature activation+0.000
Top resid features:
ian
Tokenian
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.002
Top resid features:
voters
Token voters
Feature activation+0.060
Top resid features:
are
Token are
Feature activation+0.001
Top resid features:
able
Token able
Feature activation-0.003
Top resid features:
to
Token to
Feature activation+0.034
Top resid features:
cast
Token cast
Feature activation+4.686
Top resid features:
oversee
Token oversee
Feature activation+0.149
Top resid features:
able
Tokenable
Feature activation+0.100
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
ver
Token ver
Feature activation+0.000
Top resid features:
ifiable
Tokenifiable
Feature activation+0.000
Top resid features:
isn
Token isn
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation-0.047
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
t
Tokent
Feature activation-0.013
Top resid features:
the
Token the
Feature activation-0.052
Top resid features:
casting
Token casting
Feature activation+4.429
Top resid features:
of
Token of
Feature activation+0.417
Top resid features:
votes
Token votes
Feature activation+0.000
Top resid features:
online
Token online
Feature activation+0.000
Top resid features:
pretty
Token pretty
Feature activation+0.000
Top resid features:
much
Token much
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
The
Token The
Feature activation+0.015
Top resid features:
Washington
Token Washington
Feature activation+0.007
Top resid features:
Post
Token Post
Feature activation-0.031
Top resid features:
article
Token article
Feature activation-0.026
Top resid features:
cast
Token cast
Feature activation+3.930
Top resid features:
it
Token it
Feature activation+0.328
Top resid features:
in
Token in
Feature activation+0.230
Top resid features:
an
Token an
Feature activation+0.052
Top resid features:
Orwell
Token Orwell
Feature activation+0.000
Top resid features:
ian
Tokenian
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
âĢ
TokenâĢ
Feature activation-0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
Aside
TokenAside
Feature activation+0.004
Top resid features:
from
Token from
Feature activation+0.005
Top resid features:
casting
Token casting
Feature activation+3.908
Top resid features:
light
Token light
Feature activation+0.228
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
murky
Token murky
Feature activation+0.000
Top resid features:
nexus
Token nexus
Feature activation+0.000
Top resid features:
diversity
Token diversity
Feature activation-0.006
Top resid features:
is
Token is
Feature activation-0.006
Top resid features:
more
Token more
Feature activation-0.006
Top resid features:
than
Token than
Feature activation+0.038
Top resid features:
just
Token just
Feature activation+0.093
Top resid features:
casting
Token casting
Feature activation+3.753
Top resid features:
a
Token a
Feature activation+0.331
Top resid features:
person
Token person
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
color
Token color
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
warrant
Token warrant
Feature activation+0.000
Top resid features:
less
Tokenless
Feature activation-0.000
Top resid features:
surveillance
Token surveillance
Feature activation-0.003
Top resid features:
cast
Token cast
Feature activation+0.766
Top resid features:
a
Token a
Feature activation+0.103
Top resid features:
shadow
Token shadow
Feature activation+2.975
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
existing
Token existing
Feature activation+0.000
Top resid features:
democratic
Token democratic
Feature activation+0.000
Top resid features:
legal
Token legal
Feature activation+0.000
Top resid features:
protections
Token protections
Feature activation+0.000
Top resid features:
Russian
Token Russian
Feature activation+0.018
Top resid features:
President
Token President
Feature activation-0.004
Top resid features:
Vladimir
Token Vladimir
Feature activation+0.003
Top resid features:
Putin
Token Putin
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
cast
Token cast
Feature activation+2.448
Top resid features:
doubt
Token doubt
Feature activation+0.975
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
intelligence
Token intelligence
Feature activation+0.000
Top resid features:
community
Token community
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.51

Head 1: 0.01

Head 2: 0.05

Head 3: 0.08

Head 4: 0.02

Head 5: 0.03

Head 6: 0.02

Head 7: 0.04

Head 8: 0.03

Head 9: 0.02

Head 10: 0.17

Head 11: 0.02

Positive logits

casting4.36

cast3.88

Casting3.88

casts3.74

Actor3.41

actors3.40

actresses3.30

film3.26

Cast3.19

Oscars3.17

actor3.14

Actor3.07

Movie3.02

film3.00

Film2.96

Oscar2.92

actress2.85

casting2.85

Cast2.82

movie2.81

Negative logits

��-2.61

othermal-2.39

Chip-2.33

pedal-2.24

Chip-2.22

Register-2.22

Submit-2.18

omorphic-2.16

vending-2.12

Sale-2.11

vendors-2.09

PCI-2.07

sales-2.04

vendor-2.02

puter-2.01

ASIC-1.99

selling-1.99

warranties-1.96

scl-1.96

��-1.95

INTERVAL 6.233 - 6.926
CONTAINS 0.000%

The
TokenThe
Feature activation+0.000
tactic
Token tactic
Feature activation+0.000
has
Token has
Feature activation+0.000
cast
Token cast
Feature activation+2.085
such
Token such
Feature activation+2.029
a
Token a
Feature activation+6.470
shadow
Token shadow
Feature activation+2.293
of
Token of
Feature activation+0.140
fear
Token fear
Feature activation+2.484
over
Token over
Feature activation+0.000
strike
Token strike
Feature activation+0.000
ocks
Tokenocks
Feature activation+0.000
and
Token and
Feature activation+0.000
Marty
Token Marty
Feature activation+0.000
Alexander
Token Alexander
Feature activation+0.000
cast
Token cast
Feature activation+2.101
a
Token a
Feature activation+6.888
broader
Token broader
Feature activation+6.926
net
Token net
Feature activation+0.951
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
suggested
Token suggested
Feature activation+0.000
and
Token and
Feature activation+0.000
Marty
Token Marty
Feature activation+0.000
Alexander
Token Alexander
Feature activation+0.000
cast
Token cast
Feature activation+2.101
a
Token a
Feature activation+6.888
broader
Token broader
Feature activation+6.926
net
Token net
Feature activation+0.951
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
suggested
Token suggested
Feature activation+0.000
that
Token that
Feature activation+0.000
and
Token and
Feature activation+0.000
so
Token so
Feature activation+0.000
on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
casting
Token casting
Feature activation+0.435
a
Token a
Feature activation+6.255
gradually
Token gradually
Feature activation+1.965
wider
Token wider
Feature activation+5.854
net
Token net
Feature activation+0.721
.
Token.
Feature activation+0.000
An
Token An
Feature activation+0.000

INTERVAL 5.541 - 6.233
CONTAINS 0.000%

on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
casting
Token casting
Feature activation+0.435
a
Token a
Feature activation+6.255
gradually
Token gradually
Feature activation+1.965
wider
Token wider
Feature activation+5.854
net
Token net
Feature activation+0.721
.
Token.
Feature activation+0.000
An
Token An
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
official
Token official
Feature activation+0.000
views
Token views
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
only
Token only
Feature activation+0.000
cast
Token cast
Feature activation+0.286
one
Token one
Feature activation+5.718
vote
Token vote
Feature activation+1.668
myself
Token myself
Feature activation+0.365
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
material
Tokenmaterial
Feature activation+0.000
uncertainty
Token uncertainty
Feature activation+0.000
which
Token which
Feature activation+0.000
may
Token may
Feature activation+0.000
cast
Token cast
Feature activation+0.854
significant
Token significant
Feature activation+5.541
doubt
Token doubt
Feature activation+0.758
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
consolidated
Token consolidated
Feature activation+0.000
entity
Token entity
Feature activation+0.000

INTERVAL 4.848 - 5.541
CONTAINS 0.000%

:
Token:
Feature activation+0.000
who
Token who
Feature activation+0.000
may
Token may
Feature activation+0.000
cast
Token cast
Feature activation+0.000
the
Token the
Feature activation+4.630
first
Token first
Feature activation+5.010
stone
Token stone
Feature activation+0.288
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
TokenWe
Feature activation+0.000

INTERVAL 4.156 - 4.848
CONTAINS 0.000%

The
Token The
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Post
Token Post
Feature activation+0.000
article
Token article
Feature activation+0.000
cast
Token cast
Feature activation+1.773
it
Token it
Feature activation+4.212
in
Token in
Feature activation+3.613
an
Token an
Feature activation+3.437
Orwell
Token Orwell
Feature activation+0.000
ian
Tokenian
Feature activation+2.065
light
Token light
Feature activation+0.000
P
Token P
Feature activation+0.000
BO
TokenBO
Feature activation+0.000
projections
Token projections
Feature activation+0.000
have
Token have
Feature activation+0.000
cast
Token cast
Feature activation+1.272
doubt
Token doubt
Feature activation+4.224
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
balanced
Token balanced
Feature activation+0.000
budget
Token budget
Feature activation+0.000
this
Token this
Feature activation+0.000
racism
Token racism
Feature activation+0.000
:
Token:
Feature activation+0.000
who
Token who
Feature activation+0.000
may
Token may
Feature activation+0.000
cast
Token cast
Feature activation+0.000
the
Token the
Feature activation+4.630
first
Token first
Feature activation+5.010
stone
Token stone
Feature activation+0.288
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.463 - 4.156
CONTAINS 0.001%

Washington
Token Washington
Feature activation+0.000
Post
Token Post
Feature activation+0.000
article
Token article
Feature activation+0.000
cast
Token cast
Feature activation+1.773
it
Token it
Feature activation+4.212
in
Token in
Feature activation+3.613
an
Token an
Feature activation+3.437
Orwell
Token Orwell
Feature activation+0.000
ian
Tokenian
Feature activation+2.065
light
Token light
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
the
Token the
Feature activation+0.000
casting
Token casting
Feature activation+0.000
of
Token of
Feature activation+3.605
votes
Token votes
Feature activation+0.000
online
Token online
Feature activation+0.000
pretty
Token pretty
Feature activation+0.000
much
Token much
Feature activation+0.000
the
Token the
Feature activation+0.000
are
Token are
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
cast
Token cast
Feature activation+0.000
oversee
Token oversee
Feature activation+1.011
able
Tokenable
Feature activation+3.613
,
Token,
Feature activation+0.000
ver
Token ver
Feature activation+0.000
ifiable
Tokenifiable
Feature activation+2.419
votes
Token votes
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
warrant
Token warrant
Feature activation+0.000
less
Tokenless
Feature activation+0.000
surveillance
Token surveillance
Feature activation+0.000
cast
Token cast
Feature activation+0.714
a
Token a
Feature activation+3.899
shadow
Token shadow
Feature activation+2.974
over
Token over
Feature activation+0.000
existing
Token existing
Feature activation+0.000
democratic
Token democratic
Feature activation+0.000
legal
Token legal
Feature activation+0.000

INTERVAL 2.770 - 3.463
CONTAINS 0.001%

âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Aside
TokenAside
Feature activation+0.000
from
Token from
Feature activation+0.000
casting
Token casting
Feature activation+0.988
light
Token light
Feature activation+3.291
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
murky
Token murky
Feature activation+0.000
nexus
Token nexus
Feature activation+0.000
of
Token of
Feature activation+0.000
President
Token President
Feature activation+0.000
Vladimir
Token Vladimir
Feature activation+0.000
Putin
Token Putin
Feature activation+0.000
and
Token and
Feature activation+0.000
cast
Token cast
Feature activation+0.272
doubt
Token doubt
Feature activation+2.795
on
Token on
Feature activation+0.512
the
Token the
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
community
Token community
Feature activation+0.000
's
Token's
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
just
Token just
Feature activation+0.000
casting
Token casting
Feature activation+0.000
a
Token a
Feature activation+2.986
person
Token person
Feature activation+0.838
of
Token of
Feature activation+0.000
color
Token color
Feature activation+2.551
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
ably
Tokenably
Feature activation+0.000
dev
Token dev
Feature activation+0.000
olve
Tokenolve
Feature activation+0.000
to
Token to
Feature activation+0.000
casting
Token casting
Feature activation+0.387
as
Token as
Feature activation+2.775
pers
Tokenpers
Feature activation+0.000
ions
Tokenions
Feature activation+0.307
and
Token and
Feature activation+0.085
adolescent
Token adolescent
Feature activation+0.102
name
Token name
Feature activation+0.000
warrant
Token warrant
Feature activation+0.000
less
Tokenless
Feature activation+0.000
surveillance
Token surveillance
Feature activation+0.000
cast
Token cast
Feature activation+0.714
a
Token a
Feature activation+3.899
shadow
Token shadow
Feature activation+2.974
over
Token over
Feature activation+0.000
existing
Token existing
Feature activation+0.000
democratic
Token democratic
Feature activation+0.000
legal
Token legal
Feature activation+0.000
protections
Token protections
Feature activation+0.000

INTERVAL 2.078 - 2.770
CONTAINS 0.001%

St
Token St
Feature activation+0.000
ocks
Tokenocks
Feature activation+0.000
and
Token and
Feature activation+0.000
Marty
Token Marty
Feature activation+0.000
Alexander
Token Alexander
Feature activation+0.000
cast
Token cast
Feature activation+2.101
a
Token a
Feature activation+6.888
broader
Token broader
Feature activation+6.926
net
Token net
Feature activation+0.951
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
as
Tokenas
Feature activation+0.000
mania
Tokenmania
Feature activation+0.000
's
Token's
Feature activation+0.000
Opposition
Token Opposition
Feature activation+0.000
casts
Token casts
Feature activation+0.846
doubt
Token doubt
Feature activation+2.096
over
Token over
Feature activation+0.000
$
Token $
Feature activation+0.000
16
Token16
Feature activation+0.000
m
Tokenm
Feature activation+0.000
Cad
Token Cad
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
tower
Token tower
Feature activation+0.000
and
Token and
Feature activation+0.000
cast
Token cast
Feature activation+0.000
their
Token their
Feature activation+2.162
ballots
Token ballots
Feature activation+0.000
for
Token for
Feature activation+0.000
individuals
Token individuals
Feature activation+0.000
who
Token who
Feature activation+0.000
get
Token get
Feature activation+0.000
tactic
Token tactic
Feature activation+0.000
has
Token has
Feature activation+0.000
cast
Token cast
Feature activation+2.085
such
Token such
Feature activation+2.029
a
Token a
Feature activation+6.470
shadow
Token shadow
Feature activation+2.293
of
Token of
Feature activation+0.140
fear
Token fear
Feature activation+2.484
over
Token over
Feature activation+0.000
strike
Token strike
Feature activation+0.000
zones
Token zones
Feature activation+0.000
just
Token just
Feature activation+0.000
casting
Token casting
Feature activation+0.000
a
Token a
Feature activation+2.986
person
Token person
Feature activation+0.838
of
Token of
Feature activation+0.000
color
Token color
Feature activation+2.551
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 1.385 - 2.078
CONTAINS 0.001%

magazine
Token magazine
Feature activation+0.000
def
Token def
Feature activation+0.000
amed
Tokenamed
Feature activation+0.000
her
Token her
Feature activation+0.000
by
Token by
Feature activation+0.000
casting
Token casting
Feature activation+1.568
the
Token the
Feature activation+0.217
former
Token former
Feature activation+0.000
associate
Token associate
Feature activation+0.000
dean
Token dean
Feature activation+0.646
as
Token as
Feature activation+0.000
cast
Token cast
Feature activation+1.773
it
Token it
Feature activation+4.212
in
Token in
Feature activation+3.613
an
Token an
Feature activation+3.437
Orwell
Token Orwell
Feature activation+0.000
ian
Tokenian
Feature activation+2.065
light
Token light
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
only
Token only
Feature activation+0.000
cast
Token cast
Feature activation+0.286
one
Token one
Feature activation+5.718
vote
Token vote
Feature activation+1.668
myself
Token myself
Feature activation+0.365
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
tactic
Token tactic
Feature activation+0.000
has
Token has
Feature activation+0.000
cast
Token cast
Feature activation+2.085
such
Token such
Feature activation+2.029
a
Token a
Feature activation+6.470
shadow
Token shadow
Feature activation+2.293
of
Token of
Feature activation+0.140
fear
Token fear
Feature activation+2.484
over
Token over
Feature activation+0.000
problem
Token problem
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
cast
Token cast
Feature activation+0.000
even
Token even
Feature activation+2.018
3
Token 3
Feature activation+2.054
level
Token level
Feature activation+0.093
9
Token 9
Feature activation+1.033
spells
Token spells
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.693 - 1.385
CONTAINS 0.004%

second
Token second
Feature activation+0.000
cast
Token cast
Feature activation+0.000
time
Token time
Feature activation+0.344
before
Token before
Feature activation+1.324
emerging
Token emerging
Feature activation+0.000
from
Token from
Feature activation+0.969
underground
Token underground
Feature activation+0.000
and
Token and
Feature activation+0.000
leaping
Token leaping
Feature activation+0.000
at
Token at
Feature activation+0.000
her
Token her
Feature activation+0.000
rights
Token rights
Feature activation+0.000
and
Token and
Feature activation+0.000
warrant
Token warrant
Feature activation+0.000
less
Tokenless
Feature activation+0.000
surveillance
Token surveillance
Feature activation+0.000
cast
Token cast
Feature activation+0.714
a
Token a
Feature activation+3.899
shadow
Token shadow
Feature activation+2.974
over
Token over
Feature activation+0.000
existing
Token existing
Feature activation+0.000
democratic
Token democratic
Feature activation+0.000
uncertainty
Token uncertainty
Feature activation+0.000
which
Token which
Feature activation+0.000
may
Token may
Feature activation+0.000
cast
Token cast
Feature activation+0.854
significant
Token significant
Feature activation+5.541
doubt
Token doubt
Feature activation+0.758
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
consolidated
Token consolidated
Feature activation+0.000
entity
Token entity
Feature activation+0.000
's
Token's
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
casting
Tokencasting
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
;
Token;
Feature activation+0.000
the
Token the
Feature activation+1.308
molten
Token molten
Feature activation+0.000
alloy
Token alloy
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
melting
Token melting
Feature activation+0.000
all
Token all
Feature activation+0.000
nine
Token nine
Feature activation+0.000
bodies
Token bodies
Feature activation+0.000
threw
Token threw
Feature activation+0.000
their
Token their
Feature activation+0.214
own
Token own
Feature activation+0.892
anomalies
Token anomalies
Feature activation+0.486
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
some
Token some
Feature activation+0.000
bodies
Token bodies
Feature activation+0.000

INTERVAL 0.000 - 0.693
CONTAINS 99.992%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
'
Token'
Feature activation+0.000
Operation
TokenOperation
Feature activation+0.000
Gold
Token Gold
Feature activation+0.000
ing
Tokening
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
strand
Token strand
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
fundraising
Token fundraising
Feature activation+0.000
email
Token email
Feature activation+0.000
paid
Token paid
Feature activation+0.000
for
Token for
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
D
Token D
Feature activation+0.000
CCC
TokenCCC
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
not
Token not
Feature activation+0.000
appear
Token appear
Feature activation+0.000
to
Token to
Feature activation+0.000
want
Token want
Feature activation+0.000
the
Token the
Feature activation+0.000
Alliance
Token Alliance
Feature activation+0.000
fleet
Token fleet
Feature activation+0.000
to
Token to
Feature activation+0.000
reach
Token reach
Feature activation+0.000
their
Token their
Feature activation+0.000
home
Token home
Feature activation+0.000
school
Token school
Feature activation+0.000
-
Token-
Feature activation+0.000
age
Tokenage
Feature activation+0.000
girl
Token girl
Feature activation+0.000
holding
Token holding
Feature activation+0.000
what
Token what
Feature activation+0.000
appears
Token appears
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
drawing
Token drawing
Feature activation+0.000
them
Token them
Feature activation+0.000
!
Token!
Feature activation+0.000
These
TokenThese
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
for
Token for
Feature activation+0.000
any
Token any
Feature activation+0.000
specific
Token specific
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 H9.0: (feature 21955)

TOP ACTIVATIONS
MAX = 7.064

and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+7.064
will
Token will
Feature activation+6.971
be
Token be
Feature activation+6.472
following
Token following
Feature activation+0.000
our
Token our
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
the
Token the
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+7.064
will
Token will
Feature activation+6.971
be
Token be
Feature activation+6.472
following
Token following
Feature activation+0.000
our
Token our
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
in
Token in
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+7.064
will
Token will
Feature activation+6.971
be
Token be
Feature activation+6.472
following
Token following
Feature activation+0.000
our
Token our
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
her
Token her
Feature activation+0.000
chin
Token chin
Feature activation+0.000
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+2.223
had
Token had
Feature activation+6.171
been
Token been
Feature activation+5.861
cut
Token cut
Feature activation+4.893
out
Token out
Feature activation+4.220
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
while
Token while
Feature activation+0.000
eyes
Token eyes
Feature activation+1.404
will
Token will
Feature activation+5.995
mostly
Token mostly
Feature activation+6.144
be
Token be
Feature activation+5.901
on
Token on
Feature activation+0.000
Alex
Token Alex
Feature activation+0.000
O
Token O
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
NHL
Token NHL
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
while
Token while
Feature activation+0.000
eyes
Token eyes
Feature activation+1.404
will
Token will
Feature activation+5.995
mostly
Token mostly
Feature activation+6.144
be
Token be
Feature activation+5.901
on
Token on
Feature activation+0.000
Alex
Token Alex
Feature activation+0.000
O
Token O
Feature activation+0.000
and
Token and
Feature activation+0.000
while
Token while
Feature activation+0.000
eyes
Token eyes
Feature activation+1.404
will
Token will
Feature activation+5.995
mostly
Token mostly
Feature activation+6.144
be
Token be
Feature activation+5.901
on
Token on
Feature activation+0.000
Alex
Token Alex
Feature activation+0.000
O
Token O
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
ch
Tokench
Feature activation+0.000
chin
Token chin
Feature activation+0.000
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+2.223
had
Token had
Feature activation+6.171
been
Token been
Feature activation+5.861
cut
Token cut
Feature activation+4.893
out
Token out
Feature activation+4.220
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
knife
Token knife
Feature activation+0.000
Dun
TokenDun
Feature activation+0.000
can
Tokencan
Feature activation+0.000
frowned
Token frowned
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
eyes
Token eyes
Feature activation+5.571
looking
Token looking
Feature activation+1.623
slightly
Token slightly
Feature activation+4.739
un
Token un
Feature activation+2.372
hing
Tokenhing
Feature activation+0.000
ed
Tokened
Feature activation+0.354
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
eyes
Token eyes
Feature activation+3.855
will
Token will
Feature activation+4.943
be
Token be
Feature activation+5.225
on
Token on
Feature activation+0.000
Comey
Token Comey
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.000
speaks
Token speaks
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
eyes
Token eyes
Feature activation+3.855
will
Token will
Feature activation+4.943
be
Token be
Feature activation+5.225
on
Token on
Feature activation+0.000
Comey
Token Comey
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
when
Token when
Feature activation+0.000
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+2.223
had
Token had
Feature activation+6.171
been
Token been
Feature activation+5.861
cut
Token cut
Feature activation+4.893
out
Token out
Feature activation+4.220
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
knife
Token knife
Feature activation+0.000
,
Token,
Feature activation+0.000
frowned
Token frowned
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
eyes
Token eyes
Feature activation+5.571
looking
Token looking
Feature activation+1.623
slightly
Token slightly
Feature activation+4.739
un
Token un
Feature activation+2.372
hing
Tokenhing
Feature activation+0.000
ed
Tokened
Feature activation+0.354
and
Token and
Feature activation+1.316
blazing
Token blazing
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+2.223
had
Token had
Feature activation+6.171
been
Token been
Feature activation+5.861
cut
Token cut
Feature activation+4.893
out
Token out
Feature activation+4.220
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
knife
Token knife
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
y
Tokeny
Feature activation+0.000
speaks
Token speaks
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
eyes
Token eyes
Feature activation+3.855
will
Token will
Feature activation+4.943
be
Token be
Feature activation+5.225
on
Token on
Feature activation+0.000
Comey
Token Comey
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
i
Tokeni
Feature activation+0.000
.
Token.
Feature activation+0.000
Seeing
Token Seeing
Feature activation+0.000
Rey
Token Rey
Feature activation+0.000
's
Token's
Feature activation+0.000
eyes
Token eyes
Feature activation+3.253
,
Token,
Feature activation+0.000
lifeless
Token lifeless
Feature activation+0.000
,
Token,
Feature activation+1.146
scared
Token scared
Feature activation+0.000
Ren
Token Ren
Feature activation+0.000
Families
Token Families
Feature activation+0.000
Party
Token Party
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
laser
Token laser
Feature activation+0.000
-
Token-
Feature activation+3.135
focused
Tokenfocused
Feature activation+0.000
in
Token in
Feature activation+0.000
pushing
Token pushing
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
lyn
Tokenlyn
Feature activation+0.000
Black
Token Black
Feature activation+0.000
's
Token's
Feature activation+0.000
eyes
Token eyes
Feature activation+2.038
shot
Token shot
Feature activation+2.916
open
Token open
Feature activation+0.956
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
lay
Token lay
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
GOP
Token GOP
Feature activation+0.000
nominees
Token nominees
Feature activation+0.000
made
Token made
Feature activation+0.000
eyebrow
Token eyebrow
Feature activation+0.000
-
Token-
Feature activation+2.672
raising
Tokenraising
Feature activation+0.000
remarks
Token remarks
Feature activation+0.000
about
Token about
Feature activation+0.000
rape
Token rape
Feature activation+0.000
.
Token.
Feature activation+0.000
awoke
Token awoke
Feature activation+0.000
.
Token.
Feature activation+0.000
Her
Token Her
Feature activation+0.000
safety
Token safety
Feature activation+0.000
goggles
Token goggles
Feature activation+0.000
were
Token were
Feature activation+2.499
covered
Token covered
Feature activation+0.000
in
Token in
Feature activation+0.000
so
Token so
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 8.051

energy
Token energy
Feature activation-0.019
Top resid features:
market
Token market
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.048
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
eyes
Token eyes
Feature activation+8.051
Top resid features:
of
Token of
Feature activation+0.156
Top resid features:
the
Token the
Feature activation+0.067
Top resid features:
world
Token world
Feature activation+0.095
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
energy
Token energy
Feature activation-0.025
Top resid features:
market
Token market
Feature activation-0.014
Top resid features:
,
Token,
Feature activation+0.039
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
eyes
Token eyes
Feature activation+7.853
Top resid features:
of
Token of
Feature activation+0.104
Top resid features:
the
Token the
Feature activation+0.045
Top resid features:
world
Token world
Feature activation+0.143
Top resid features:
will
Token will
Feature activation+0.134
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
energy
Token energy
Feature activation-0.044
Top resid features:
market
Token market
Feature activation-0.020
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
and
Token and
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
eyes
Token eyes
Feature activation+7.315
Top resid features:
of
Token of
Feature activation+0.074
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
world
Token world
Feature activation+0.113
Top resid features:
will
Token will
Feature activation+0.337
Top resid features:
be
Token be
Feature activation+0.110
Top resid features:
under
Token under
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.002
Top resid features:
chin
Token chin
Feature activation+0.004
Top resid features:
and
Token and
Feature activation-0.024
Top resid features:
her
Token her
Feature activation-0.011
Top resid features:
eyes
Token eyes
Feature activation+7.301
Top resid features:
had
Token had
Feature activation+0.119
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
cut
Token cut
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
NHL
Token NHL
Feature activation-0.026
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
and
Token and
Feature activation-0.018
Top resid features:
while
Token while
Feature activation-0.050
Top resid features:
eyes
Token eyes
Feature activation+7.240
Top resid features:
will
Token will
Feature activation+0.298
Top resid features:
mostly
Token mostly
Feature activation+0.024
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Alex
Token Alex
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
NHL
Token NHL
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
and
Token and
Feature activation-0.018
Top resid features:
while
Token while
Feature activation-0.077
Top resid features:
eyes
Token eyes
Feature activation+7.088
Top resid features:
will
Token will
Feature activation+0.094
Top resid features:
mostly
Token mostly
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Alex
Token Alex
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
NHL
Token NHL
Feature activation-0.019
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
and
Token and
Feature activation-0.009
Top resid features:
while
Token while
Feature activation-0.039
Top resid features:
eyes
Token eyes
Feature activation+7.216
Top resid features:
will
Token will
Feature activation+0.247
Top resid features:
mostly
Token mostly
Feature activation-0.215
Top resid features:
be
Token be
Feature activation+0.034
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Alex
Token Alex
Feature activation+0.000
Top resid features:
under
Token under
Feature activation+0.001
Top resid features:
her
Token her
Feature activation+0.002
Top resid features:
chin
Token chin
Feature activation+0.010
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
her
Token her
Feature activation-0.012
Top resid features:
eyes
Token eyes
Feature activation+7.018
Top resid features:
had
Token had
Feature activation+0.115
Top resid features:
been
Token been
Feature activation+0.019
Top resid features:
cut
Token cut
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Dun
TokenDun
Feature activation+0.000
Top resid features:
can
Tokencan
Feature activation+0.010
Top resid features:
frowned
Token frowned
Feature activation+0.153
Top resid features:
,
Token,
Feature activation-0.017
Top resid features:
his
Token his
Feature activation+0.062
Top resid features:
eyes
Token eyes
Feature activation+6.392
Top resid features:
looking
Token looking
Feature activation+0.000
Top resid features:
slightly
Token slightly
Feature activation+0.000
Top resid features:
un
Token un
Feature activation+0.000
Top resid features:
hing
Tokenhing
Feature activation+0.000
Top resid features:
ed
Tokened
Feature activation+0.000
Top resid features:
y
Tokeny
Feature activation-0.004
Top resid features:
speaks
Token speaks
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
All
TokenAll
Feature activation+0.005
Top resid features:
eyes
Token eyes
Feature activation+6.034
Top resid features:
will
Token will
Feature activation+0.246
Top resid features:
be
Token be
Feature activation+0.013
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Comey
Token Comey
Feature activation+0.000
Top resid features:
Thursday
Token Thursday
Feature activation+0.000
Top resid features:
y
Tokeny
Feature activation-0.003
Top resid features:
speaks
Token speaks
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.025
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
All
TokenAll
Feature activation+0.004
Top resid features:
eyes
Token eyes
Feature activation+5.816
Top resid features:
will
Token will
Feature activation+0.066
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Comey
Token Comey
Feature activation+0.000
Top resid features:
Thursday
Token Thursday
Feature activation+0.000
Top resid features:
under
Token under
Feature activation-0.006
Top resid features:
her
Token her
Feature activation-0.001
Top resid features:
chin
Token chin
Feature activation+0.049
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
her
Token her
Feature activation-0.000
Top resid features:
eyes
Token eyes
Feature activation+5.711
Top resid features:
had
Token had
Feature activation+0.095
Top resid features:
been
Token been
Feature activation+0.051
Top resid features:
cut
Token cut
Feature activation+0.100
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Dun
TokenDun
Feature activation-0.001
Top resid features:
can
Tokencan
Feature activation+0.007
Top resid features:
frowned
Token frowned
Feature activation+0.100
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
his
Token his
Feature activation+0.056
Top resid features:
eyes
Token eyes
Feature activation+5.453
Top resid features:
looking
Token looking
Feature activation+0.242
Top resid features:
slightly
Token slightly
Feature activation+0.082
Top resid features:
un
Token un
Feature activation+0.000
Top resid features:
hing
Tokenhing
Feature activation+0.000
Top resid features:
ed
Tokened
Feature activation+0.000
Top resid features:
under
Token under
Feature activation-0.008
Top resid features:
her
Token her
Feature activation-0.012
Top resid features:
chin
Token chin
Feature activation+0.050
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
her
Token her
Feature activation-0.009
Top resid features:
eyes
Token eyes
Feature activation+4.811
Top resid features:
had
Token had
Feature activation+0.093
Top resid features:
been
Token been
Feature activation+0.060
Top resid features:
cut
Token cut
Feature activation+0.209
Top resid features:
out
Token out
Feature activation+0.020
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
y
Tokeny
Feature activation-0.006
Top resid features:
speaks
Token speaks
Feature activation-0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.037
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
All
TokenAll
Feature activation+0.020
Top resid features:
eyes
Token eyes
Feature activation+4.801
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Comey
Token Comey
Feature activation+0.000
Top resid features:
Thursday
Token Thursday
Feature activation+0.000
Top resid features:
i
Tokeni
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Seeing
Token Seeing
Feature activation+0.074
Top resid features:
Rey
Token Rey
Feature activation-0.015
Top resid features:
's
Token's
Feature activation+0.034
Top resid features:
eyes
Token eyes
Feature activation+4.364
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
lifeless
Token lifeless
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
scared
Token scared
Feature activation+0.000
Top resid features:
Ren
Token Ren
Feature activation+0.000
Top resid features:
Working
Token Working
Feature activation+0.002
Top resid features:
Families
Token Families
Feature activation-0.003
Top resid features:
Party
Token Party
Feature activation-0.002
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
been
Token been
Feature activation-0.019
Top resid features:
laser
Token laser
Feature activation+4.183
Top resid features:
-
Token-
Feature activation+0.044
Top resid features:
focused
Tokenfocused
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
pushing
Token pushing
Feature activation+0.000
Top resid features:
New
Token New
Feature activation+0.000
Top resid features:
E
TokenE
Feature activation+0.006
Top resid features:
ve
Tokenve
Feature activation+0.002
Top resid features:
lyn
Tokenlyn
Feature activation+0.011
Top resid features:
Black
Token Black
Feature activation+0.001
Top resid features:
's
Token's
Feature activation+0.064
Top resid features:
eyes
Token eyes
Feature activation+3.627
Top resid features:
shot
Token shot
Feature activation+0.104
Top resid features:
open
Token open
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
She
Token She
Feature activation+0.000
Top resid features:
lay
Token lay
Feature activation+0.000
Top resid features:
when
Token when
Feature activation-0.017
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
GOP
Token GOP
Feature activation-0.004
Top resid features:
nominees
Token nominees
Feature activation-0.002
Top resid features:
made
Token made
Feature activation-0.011
Top resid features:
eyebrow
Token eyebrow
Feature activation+3.913
Top resid features:
-
Token-
Feature activation+0.043
Top resid features:
raising
Tokenraising
Feature activation+0.000
Top resid features:
remarks
Token remarks
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
rape
Token rape
Feature activation+0.000
Top resid features:
gear
Tokengear
Feature activation+0.003
Top resid features:
awoke
Token awoke
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
Her
Token Her
Feature activation+0.044
Top resid features:
safety
Token safety
Feature activation+0.009
Top resid features:
goggles
Token goggles
Feature activation+3.534
Top resid features:
were
Token were
Feature activation+0.093
Top resid features:
covered
Token covered
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
ot
Tokenot
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.51

Head 1: 0.02

Head 2: 0.09

Head 3: 0.10

Head 4: 0.03

Head 5: 0.07

Head 6: 0.02

Head 7: 0.04

Head 8: 0.03

Head 9: 0.02

Head 10: 0.07

Head 11: 0.02

Positive logits

gaze3.92

lenses3.86

lens3.59

aperture3.39

gazing3.38

eyel3.34

glare3.33

brightest3.20

dim3.19

tint3.11

flickering3.10

telescope3.07

lashes3.06

shutter3.04

Lens3.03

unfocused3.02

eyes3.01

ocular3.01

brighter2.98

gazed2.97

Negative logits

remix-2.66

reprint-2.61

Guitar-2.57

itol-2.56

drums-2.54

bps-2.45

poem-2.42

songs-2.38

TPP-2.35

pedal-2.35

tempo-2.32

Meier-2.31

pedals-2.29

PCB-2.29

Ply-2.29

carts-2.28

melody-2.23

poems-2.23

wav-2.22

cassette-2.20

INTERVAL 6.358 - 7.064
CONTAINS 0.000%

and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+7.064
will
Token will
Feature activation+6.971
be
Token be
Feature activation+6.472
following
Token following
Feature activation+0.000
our
Token our
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
the
Token the
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+7.064
will
Token will
Feature activation+6.971
be
Token be
Feature activation+6.472
following
Token following
Feature activation+0.000
our
Token our
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
in
Token in
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+7.064
will
Token will
Feature activation+6.971
be
Token be
Feature activation+6.472
following
Token following
Feature activation+0.000
our
Token our
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000

INTERVAL 5.651 - 6.358
CONTAINS 0.001%

NHL
Token NHL
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
while
Token while
Feature activation+0.000
eyes
Token eyes
Feature activation+1.404
will
Token will
Feature activation+5.995
mostly
Token mostly
Feature activation+6.144
be
Token be
Feature activation+5.901
on
Token on
Feature activation+0.000
Alex
Token Alex
Feature activation+0.000
O
Token O
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
while
Token while
Feature activation+0.000
eyes
Token eyes
Feature activation+1.404
will
Token will
Feature activation+5.995
mostly
Token mostly
Feature activation+6.144
be
Token be
Feature activation+5.901
on
Token on
Feature activation+0.000
Alex
Token Alex
Feature activation+0.000
O
Token O
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
and
Token and
Feature activation+0.000
while
Token while
Feature activation+0.000
eyes
Token eyes
Feature activation+1.404
will
Token will
Feature activation+5.995
mostly
Token mostly
Feature activation+6.144
be
Token be
Feature activation+5.901
on
Token on
Feature activation+0.000
Alex
Token Alex
Feature activation+0.000
O
Token O
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
ch
Tokench
Feature activation+0.000
her
Token her
Feature activation+0.000
chin
Token chin
Feature activation+0.000
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+2.223
had
Token had
Feature activation+6.171
been
Token been
Feature activation+5.861
cut
Token cut
Feature activation+4.893
out
Token out
Feature activation+4.220
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
chin
Token chin
Feature activation+0.000
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+2.223
had
Token had
Feature activation+6.171
been
Token been
Feature activation+5.861
cut
Token cut
Feature activation+4.893
out
Token out
Feature activation+4.220
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
knife
Token knife
Feature activation+0.000

INTERVAL 4.945 - 5.651
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
eyes
Token eyes
Feature activation+3.855
will
Token will
Feature activation+4.943
be
Token be
Feature activation+5.225
on
Token on
Feature activation+0.000
Comey
Token Comey
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.000
Dun
TokenDun
Feature activation+0.000
can
Tokencan
Feature activation+0.000
frowned
Token frowned
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
eyes
Token eyes
Feature activation+5.571
looking
Token looking
Feature activation+1.623
slightly
Token slightly
Feature activation+4.739
un
Token un
Feature activation+2.372
hing
Tokenhing
Feature activation+0.000
ed
Tokened
Feature activation+0.354

INTERVAL 4.238 - 4.945
CONTAINS 0.000%

and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+2.223
had
Token had
Feature activation+6.171
been
Token been
Feature activation+5.861
cut
Token cut
Feature activation+4.893
out
Token out
Feature activation+4.220
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
knife
Token knife
Feature activation+0.000
,
Token,
Feature activation+0.000
speaks
Token speaks
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
eyes
Token eyes
Feature activation+3.855
will
Token will
Feature activation+4.943
be
Token be
Feature activation+5.225
on
Token on
Feature activation+0.000
Comey
Token Comey
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
when
Token when
Feature activation+0.000
frowned
Token frowned
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
eyes
Token eyes
Feature activation+5.571
looking
Token looking
Feature activation+1.623
slightly
Token slightly
Feature activation+4.739
un
Token un
Feature activation+2.372
hing
Tokenhing
Feature activation+0.000
ed
Tokened
Feature activation+0.354
and
Token and
Feature activation+1.316
blazing
Token blazing
Feature activation+0.000

INTERVAL 3.532 - 4.238
CONTAINS 0.000%

her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+2.223
had
Token had
Feature activation+6.171
been
Token been
Feature activation+5.861
cut
Token cut
Feature activation+4.893
out
Token out
Feature activation+4.220
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
knife
Token knife
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
y
Tokeny
Feature activation+0.000
speaks
Token speaks
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
eyes
Token eyes
Feature activation+3.855
will
Token will
Feature activation+4.943
be
Token be
Feature activation+5.225
on
Token on
Feature activation+0.000
Comey
Token Comey
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000

INTERVAL 2.826 - 3.532
CONTAINS 0.000%

Families
Token Families
Feature activation+0.000
Party
Token Party
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
laser
Token laser
Feature activation+0.000
-
Token-
Feature activation+3.135
focused
Tokenfocused
Feature activation+0.000
in
Token in
Feature activation+0.000
pushing
Token pushing
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
lyn
Tokenlyn
Feature activation+0.000
Black
Token Black
Feature activation+0.000
's
Token's
Feature activation+0.000
eyes
Token eyes
Feature activation+2.038
shot
Token shot
Feature activation+2.916
open
Token open
Feature activation+0.956
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
lay
Token lay
Feature activation+0.000
in
Token in
Feature activation+0.000
i
Tokeni
Feature activation+0.000
.
Token.
Feature activation+0.000
Seeing
Token Seeing
Feature activation+0.000
Rey
Token Rey
Feature activation+0.000
's
Token's
Feature activation+0.000
eyes
Token eyes
Feature activation+3.253
,
Token,
Feature activation+0.000
lifeless
Token lifeless
Feature activation+0.000
,
Token,
Feature activation+1.146
scared
Token scared
Feature activation+0.000
Ren
Token Ren
Feature activation+0.000

INTERVAL 2.119 - 2.826
CONTAINS 0.001%

under
Token under
Feature activation+0.000
her
Token her
Feature activation+0.000
chin
Token chin
Feature activation+0.000
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
eyes
Token eyes
Feature activation+2.223
had
Token had
Feature activation+6.171
been
Token been
Feature activation+5.861
cut
Token cut
Feature activation+4.893
out
Token out
Feature activation+4.220
with
Token with
Feature activation+0.000
their
Token their
Feature activation+0.000
eyes
Token eyes
Feature activation+0.063
.
Token.
Feature activation+0.000
What
Token What
Feature activation+0.063
did
Token did
Feature activation+0.000
they
Token they
Feature activation+2.496
think
Token think
Feature activation+0.142
,
Token,
Feature activation+0.000
watching
Token watching
Feature activation+0.000
this
Token this
Feature activation+0.000
adult
Token adult
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
eyes
Token eyes
Feature activation+5.571
looking
Token looking
Feature activation+1.623
slightly
Token slightly
Feature activation+4.739
un
Token un
Feature activation+2.372
hing
Tokenhing
Feature activation+0.000
ed
Tokened
Feature activation+0.354
and
Token and
Feature activation+1.316
blazing
Token blazing
Feature activation+0.000
anger
Token anger
Feature activation+0.000
the
Token the
Feature activation+0.000
GOP
Token GOP
Feature activation+0.000
nominees
Token nominees
Feature activation+0.000
made
Token made
Feature activation+0.000
eyebrow
Token eyebrow
Feature activation+0.000
-
Token-
Feature activation+2.672
raising
Tokenraising
Feature activation+0.000
remarks
Token remarks
Feature activation+0.000
about
Token about
Feature activation+0.000
rape
Token rape
Feature activation+0.000
.
Token.
Feature activation+0.000
stuff
Token stuff
Feature activation+0.000
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
their
Token their
Feature activation+0.000
eyes
Token eyes
Feature activation+2.268
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
local
Token local
Feature activation+0.000
Occup
Token Occup
Feature activation+0.000
iers
Tokeniers
Feature activation+0.000

INTERVAL 1.413 - 2.119
CONTAINS 0.002%

decade
Token decade
Feature activation+0.000
before
Token before
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
eyes
Tokeneyes
Feature activation+0.000
and
Token and
Feature activation+0.560
cut
Token cut
Feature activation+1.771
ie
Tokenie
Feature activation+0.000
mark
Token mark
Feature activation+0.000
are
Token are
Feature activation+0.000
machine
Token machine
Feature activation+0.000
embro
Token embro
Feature activation+0.000
other
Token other
Feature activation+1.274
eye
Token eye
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
had
Token had
Feature activation+0.832
regular
Token regular
Feature activation+1.523
check
Token check
Feature activation+0.011
-
Token-
Feature activation+0.000
ups
Tokenups
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+1.568
Coffee
Token Coffee
Feature activation+0.000
is
Token is
Feature activation+0.000
poured
Token poured
Feature activation+0.000
,
Token,
Feature activation+0.000
windows
Token windows
Feature activation+0.876
are
Token are
Feature activation+1.555
gazed
Token gazed
Feature activation+0.000
at
Token at
Feature activation+0.000
p
Token p
Feature activation+0.000
ensive
Tokenensive
Feature activation+0.000
ly
Tokenly
Feature activation+0.002
you
Token you
Feature activation+0.000
stare
Token stare
Feature activation+0.000
long
Token long
Feature activation+1.128
enough
Token enough
Feature activation+0.376
you
Token you
Feature activation+0.920
can
Token can
Feature activation+1.835
find
Token find
Feature activation+0.320
reasons
Token reasons
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
optimistic
Token optimistic
Feature activation+0.000
opened
Token opened
Feature activation+0.000
my
Token my
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
the
Token the
Feature activation+0.000
lights
Token lights
Feature activation+0.329
are
Token are
Feature activation+1.949
out
Token out
Feature activation+0.000
and
Token and
Feature activation+0.000
here
Token here
Feature activation+0.000
comes
Token comes
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.706 - 1.413
CONTAINS 0.007%

I
TokenI
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
keeping
Token keeping
Feature activation+0.000
my
Token my
Feature activation+0.000
eye
Token eye
Feature activation+0.842
on
Token on
Feature activation+0.000
them
Token them
Feature activation+0.000
ever
Token ever
Feature activation+0.000
since
Token since
Feature activation+0.000
they
Token they
Feature activation+0.000
,
Token,
Feature activation+0.000
az
Token az
Feature activation+0.000
ul
Tokenul
Feature activation+0.000
ene
Tokenene
Feature activation+0.000
,
Token,
Feature activation+0.000
reduces
Token reduces
Feature activation+0.830
red
Token red
Feature activation+0.570
ness
Tokenness
Feature activation+0.000
and
Token and
Feature activation+0.619
like
Token like
Feature activation+0.000
F
Token F
Feature activation+0.000
lash
Token lash
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
.
Token.
Feature activation+0.174
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.735
government
Token government
Feature activation+0.000
says
Token says
Feature activation+0.000
we
Token we
Feature activation+0.000
shouldn
Token shouldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
whisk
Token whisk
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
your
Token your
Feature activation+0.000
cat
Token cat
Feature activation+0.000
has
Token has
Feature activation+0.000
on
Token on
Feature activation+0.718
either
Token either
Feature activation+0.199
side
Token side
Feature activation+0.071
of
Token of
Feature activation+0.523
her
Token her
Feature activation+0.722
nose
Token nose
Feature activation+0.000
guns
Token guns
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
the
Token the
Feature activation+0.000
jury
Token jury
Feature activation+0.000
is
Token is
Feature activation+0.914
still
Token still
Feature activation+0.868
out
Token out
Feature activation+0.000
on
Token on
Feature activation+0.000
Cyborg
Token Cyborg
Feature activation+0.000
though
Token though
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000

INTERVAL 0.000 - 0.706
CONTAINS 99.988%

change
Token change
Feature activation+0.000
wakes
Token wakes
Feature activation+0.000
you
Token you
Feature activation+0.000
up
Token up
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
your
Token your
Feature activation+0.000
stagnation
Token stagnation
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
make
Token make
Feature activation+0.000
any
Token any
Feature activation+0.000
mistakes
Token mistakes
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
run
Token run
Feature activation+0.000
a
Token a
Feature activation+0.000
carefully
Token carefully
Feature activation+0.000
managed
Token managed
Feature activation+0.000
t
Tokent
Feature activation+0.000
necessarily
Token necessarily
Feature activation+0.000
a
Token a
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
tra
Tokentra
Feature activation+0.000
iler
Tokeniler
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
U
TokenU
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
State
Token State
Feature activation+0.000
Department
Token Department
Feature activation+0.000
spokesman
Token spokesman
Feature activation+0.000
Mark
Token Mark
Feature activation+0.000
T
Token T
Feature activation+0.000
oner
Tokenoner
Feature activation+0.000
said
Token said
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
div
Token div
Feature activation+0.000
is
Tokenis
Feature activation+0.000
or
Tokenor
Feature activation+0.000
.
Token.
Feature activation+0.000
Priv
Token Priv
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
va
Tokenva
Feature activation+0.000
never
Token never
Feature activation+0.000
sees
Token sees
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 H9.0: (feature 21764)

TOP ACTIVATIONS
MAX = 2.777

Mine
Token Mine
Feature activation+0.000
&
Token &
Feature activation+0.000
O
Token O
Feature activation+0.000
urs
Tokenurs
Feature activation+0.436
"
Token"
Feature activation+1.617
(
Token (
Feature activation+2.777
2005
Token2005
Feature activation+1.403
)
Token)
Feature activation+0.756
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
movie
Token movie
Feature activation+0.009
will
Token will
Feature activation+2.380
be
Token be
Feature activation+2.325
in
Token in
Feature activation+2.045
post
Token post
Feature activation+0.715
-
Token-
Feature activation+1.474
production
Tokenproduction
Feature activation+0.000
watching
Token watching
Feature activation+0.000
a
Token a
Feature activation+0.000
horror
Token horror
Feature activation+0.000
film
Token film
Feature activation+0.000
.
Token.
Feature activation+0.000
Its
Token Its
Feature activation+2.342
atmosphere
Token atmosphere
Feature activation+0.000
and
Token and
Feature activation+1.545
violence
Token violence
Feature activation+0.000
tug
Token tug
Feature activation+0.000
at
Token at
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
movie
Token movie
Feature activation+0.009
will
Token will
Feature activation+2.380
be
Token be
Feature activation+2.325
in
Token in
Feature activation+2.045
post
Token post
Feature activation+0.715
-
Token-
Feature activation+1.474
production
Tokenproduction
Feature activation+0.000
for
Token for
Feature activation+1.103
ang
Tokenang
Feature activation+0.000
oli
Tokenoli
Feature activation+0.947
(
Token (
Feature activation+1.621
19
Token19
Feature activation+0.057
62
Token62
Feature activation+1.244
)
Token)
Feature activation+2.246
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.080
It
TokenIt
Feature activation+0.286
was
Token was
Feature activation+0.380
a
Token a
Feature activation+0.097
China
Token China
Feature activation+0.000
's
Token's
Feature activation+0.372
biggest
Token biggest
Feature activation+0.287
movie
Token movie
Feature activation+0.000
ever
Token ever
Feature activation+2.019
,
Token,
Feature activation+2.206
how
Token how
Feature activation+0.000
it
Token it
Feature activation+0.285
feels
Token feels
Feature activation+0.000
to
Token to
Feature activation+0.000
suddenly
Token suddenly
Feature activation+0.000
in
Token in
Feature activation+0.000
award
Token award
Feature activation+0.000
-
Token-
Feature activation+0.000
winning
Tokenwinning
Feature activation+0.000
films
Token films
Feature activation+0.000
like
Token like
Feature activation+2.143
Gall
Token Gall
Feature activation+0.482
ip
Tokenip
Feature activation+0.000
oli
Tokenoli
Feature activation+0.218
.
Token.
Feature activation+0.000
Of
Token Of
Feature activation+0.000
-
Token-
Feature activation+0.000
winning
Tokenwinning
Feature activation+0.000
film
Token film
Feature activation+0.000
of
Token of
Feature activation+0.000
1937
Token 1937
Feature activation+0.589
].
Token].
Feature activation+2.106
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.844
Credits
TokenCredits
Feature activation+0.000
:
Token:
Feature activation+1.022
cast
Token cast
Feature activation+0.000
film
Token film
Feature activation+0.000
written
Token written
Feature activation+0.000
by
Token by
Feature activation+0.911
Noah
Token Noah
Feature activation+0.000
Greenberg
Token Greenberg
Feature activation+0.000
,
Token,
Feature activation+2.102
Marcus
Token Marcus
Feature activation+0.000
S
Token S
Feature activation+0.000
atory
Tokenatory
Feature activation+0.000
,
Token,
Feature activation+0.031
Christopher
Token Christopher
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
movie
Token movie
Feature activation+0.265
's
Token's
Feature activation+2.097
cast
Token cast
Feature activation+0.000
and
Token and
Feature activation+0.778
crew
Token crew
Feature activation+0.000
members
Token members
Feature activation+0.000
each
Token each
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.963
second
Token second
Feature activation+2.075
half
Token half
Feature activation+0.056
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
expressing
Token expressing
Feature activation+0.000
disappointment
Token disappointment
Feature activation+0.000
the
Token the
Feature activation+0.417
film
Token film
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
film
Token film
Feature activation+0.897
was
Token was
Feature activation+2.060
later
Token later
Feature activation+1.456
rem
Token rem
Feature activation+1.143
ade
Tokenade
Feature activation+0.732
in
Token in
Feature activation+0.593
T
Token T
Feature activation+0.000
Claus
Token Claus
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+1.397
And
Token And
Feature activation+1.462
in
Token in
Feature activation+2.051
The
Token The
Feature activation+1.969
Dark
Token Dark
Feature activation+0.000
Knight
Token Knight
Feature activation+0.000
,
Token,
Feature activation+0.620
Batman
Token Batman
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
movie
Token movie
Feature activation+0.009
will
Token will
Feature activation+2.380
be
Token be
Feature activation+2.325
in
Token in
Feature activation+2.045
post
Token post
Feature activation+0.715
-
Token-
Feature activation+1.474
production
Tokenproduction
Feature activation+0.000
for
Token for
Feature activation+1.103
the
Token the
Feature activation+0.709
Greatest
Token Greatest
Feature activation+0.000
Sci
Token Sci
Feature activation+0.000
-
Token-
Feature activation+0.000
Fi
TokenFi
Feature activation+0.000
Film
Token Film
Feature activation+0.000
Never
Token Never
Feature activation+2.032
Made
Token Made
Feature activation+0.189
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.688
The
TokenThe
Feature activation+0.351
long
Token long
Feature activation+0.000
on
Token on
Feature activation+0.154
China
Token China
Feature activation+0.000
's
Token's
Feature activation+0.372
biggest
Token biggest
Feature activation+0.287
movie
Token movie
Feature activation+0.000
ever
Token ever
Feature activation+2.019
,
Token,
Feature activation+2.206
how
Token how
Feature activation+0.000
it
Token it
Feature activation+0.285
feels
Token feels
Feature activation+0.000
to
Token to
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+1.397
And
Token And
Feature activation+1.462
in
Token in
Feature activation+2.051
The
Token The
Feature activation+1.969
Dark
Token Dark
Feature activation+0.000
Knight
Token Knight
Feature activation+0.000
,
Token,
Feature activation+0.620
Batman
Token Batman
Feature activation+0.000
represents
Token represents
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.963
second
Token second
Feature activation+2.075
half
Token half
Feature activation+0.056
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
expressing
Token expressing
Feature activation+0.000
sober
Token sober
Feature activation+0.000
man
Token man
Feature activation+0.000
feel
Token feel
Feature activation+0.000
drunk
Token drunk
Feature activation+0.000
.
Token.
Feature activation+0.921
The
Token The
Feature activation+1.923
plot
Token plot
Feature activation+0.000
operates
Token operates
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
devil
Token devil
Feature activation+0.000
eye
Token eye
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+0.000
genuine
Token genuine
Feature activation+0.000
compassion
Token compassion
Feature activation+0.000
,"
Token,"
Feature activation+1.907
and
Token and
Feature activation+0.994
succeeds
Token succeeds
Feature activation+0.000
on
Token on
Feature activation+0.000
occasion
Token occasion
Feature activation+0.000
(
Token (
Feature activation+0.166

Top DFA by src position
MAX = 3.341

Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Screen
TokenScreen
Feature activation-0.008
Top resid features:
cap
Tokencap
Feature activation-0.022
Top resid features:
from
Token from
Feature activation-0.015
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
movie
Token movie
Feature activation+3.341
Top resid features:
"
Token "
Feature activation+0.005
Top resid features:
Y
TokenY
Feature activation+0.003
Top resid features:
ours
Tokenours
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
Mine
Token Mine
Feature activation-0.001
Top resid features:
last
Token last
Feature activation-0.013
Top resid features:
week
Token week
Feature activation-0.033
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
and
Token and
Feature activation-0.022
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
movie
Token movie
Feature activation+3.080
Top resid features:
will
Token will
Feature activation+0.012
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
post
Token post
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.193
Top resid features:
Imagine
TokenImagine
Feature activation-0.022
Top resid features:
watching
Token watching
Feature activation+0.019
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
horror
Token horror
Feature activation-0.036
Top resid features:
film
Token film
Feature activation+2.958
Top resid features:
.
Token.
Feature activation+0.051
Top resid features:
Its
Token Its
Feature activation+0.014
Top resid features:
atmosphere
Token atmosphere
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
violence
Token violence
Feature activation+0.000
Top resid features:
last
Token last
Feature activation-0.007
Top resid features:
week
Token week
Feature activation-0.026
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
and
Token and
Feature activation-0.018
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
movie
Token movie
Feature activation+3.050
Top resid features:
will
Token will
Feature activation+0.035
Top resid features:
be
Token be
Feature activation-0.001
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
post
Token post
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.006
Top resid features:
then
Token then
Feature activation-0.001
Top resid features:
featured
Token featured
Feature activation-0.044
Top resid features:
in
Token in
Feature activation-0.043
Top resid features:
the
Token the
Feature activation-0.006
Top resid features:
film
Token film
Feature activation+2.827
Top resid features:
R
Token R
Feature activation+0.002
Top resid features:
ang
Tokenang
Feature activation+0.034
Top resid features:
oli
Tokenoli
Feature activation-0.005
Top resid features:
(
Token (
Feature activation-0.003
Top resid features:
19
Token19
Feature activation+0.002
Top resid features:
working
Token working
Feature activation-0.037
Top resid features:
on
Token on
Feature activation-0.027
Top resid features:
China
Token China
Feature activation+0.063
Top resid features:
's
Token's
Feature activation-0.002
Top resid features:
biggest
Token biggest
Feature activation-0.027
Top resid features:
movie
Token movie
Feature activation+2.768
Top resid features:
ever
Token ever
Feature activation-0.034
Top resid features:
,
Token,
Feature activation-0.018
Top resid features:
how
Token how
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
feels
Token feels
Feature activation+0.000
Top resid features:
oid
Tokenoid
Feature activation-0.021
Top resid features:
in
Token in
Feature activation-0.012
Top resid features:
award
Token award
Feature activation-0.013
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
winning
Tokenwinning
Feature activation-0.016
Top resid features:
films
Token films
Feature activation+2.919
Top resid features:
like
Token like
Feature activation-0.001
Top resid features:
Gall
Token Gall
Feature activation+0.000
Top resid features:
ip
Tokenip
Feature activation+0.000
Top resid features:
oli
Tokenoli
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
An
TokenAn
Feature activation+0.004
Top resid features:
amateur
Token amateur
Feature activation-0.014
Top resid features:
prize
Token prize
Feature activation-0.019
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
winning
Tokenwinning
Feature activation-0.015
Top resid features:
film
Token film
Feature activation+2.783
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
1937
Token 1937
Feature activation+0.051
Top resid features:
].
Token].
Feature activation+0.042
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
kok
Tokenkok
Feature activation+0.007
Top resid features:
is
Token is
Feature activation-0.002
Top resid features:
an
Token an
Feature activation-0.007
Top resid features:
original
Token original
Feature activation+0.006
Top resid features:
horror
Token horror
Feature activation+0.033
Top resid features:
film
Token film
Feature activation+2.653
Top resid features:
written
Token written
Feature activation+0.011
Top resid features:
by
Token by
Feature activation+0.045
Top resid features:
Noah
Token Noah
Feature activation-0.004
Top resid features:
Greenberg
Token Greenberg
Feature activation+0.014
Top resid features:
,
Token,
Feature activation-0.022
Top resid features:
8
Token8
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
000
Token000
Feature activation-0.074
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
The
Token The
Feature activation+0.042
Top resid features:
movie
Token movie
Feature activation+2.679
Top resid features:
's
Token's
Feature activation+0.050
Top resid features:
cast
Token cast
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
crew
Token crew
Feature activation+0.000
Top resid features:
members
Token members
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
yet
Token yet
Feature activation-0.000
Top resid features:
seen
Token seen
Feature activation+0.008
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
film
Token film
Feature activation+1.538
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
don
Token don
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation-0.000
Top resid features:
in
Token in
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
film
Token film
Feature activation+0.648
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
The
Token The
Feature activation+0.025
Top resid features:
film
Token film
Feature activation+1.186
Top resid features:
was
Token was
Feature activation+0.018
Top resid features:
later
Token later
Feature activation+0.000
Top resid features:
rem
Token rem
Feature activation+0.000
Top resid features:
ade
Tokenade
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:
conservative
Token conservative
Feature activation+0.045
Top resid features:
review
Token review
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
each
Token each
Feature activation+0.001
Top resid features:
movie
Token movie
Feature activation+2.850
Top resid features:
from
Token from
Feature activation-0.001
Top resid features:
N
Token N
Feature activation-0.015
Top resid features:
RO
TokenRO
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
I
Token I
Feature activation-0.002
Top resid features:
last
Token last
Feature activation-0.007
Top resid features:
week
Token week
Feature activation-0.025
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
and
Token and
Feature activation-0.016
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
movie
Token movie
Feature activation+2.669
Top resid features:
will
Token will
Feature activation+0.076
Top resid features:
be
Token be
Feature activation+0.006
Top resid features:
in
Token in
Feature activation-0.019
Top resid features:
post
Token post
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
The
Token The
Feature activation-0.006
Top resid features:
Greatest
Token Greatest
Feature activation-0.027
Top resid features:
Sci
Token Sci
Feature activation-0.022
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
Fi
TokenFi
Feature activation-0.033
Top resid features:
Film
Token Film
Feature activation+2.717
Top resid features:
Never
Token Never
Feature activation-0.002
Top resid features:
Made
Token Made
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:
The
TokenThe
Feature activation+0.000
Top resid features:
working
Token working
Feature activation-0.050
Top resid features:
on
Token on
Feature activation-0.019
Top resid features:
China
Token China
Feature activation+0.030
Top resid features:
's
Token's
Feature activation-0.002
Top resid features:
biggest
Token biggest
Feature activation-0.020
Top resid features:
movie
Token movie
Feature activation+2.518
Top resid features:
ever
Token ever
Feature activation+0.040
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
how
Token how
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
feels
Token feels
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
conservative
Token conservative
Feature activation+0.027
Top resid features:
review
Token review
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
each
Token each
Feature activation-0.000
Top resid features:
movie
Token movie
Feature activation+2.521
Top resid features:
from
Token from
Feature activation-0.001
Top resid features:
N
Token N
Feature activation-0.009
Top resid features:
RO
TokenRO
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
I
Token I
Feature activation-0.001
Top resid features:
character
Token character
Feature activation+0.023
Top resid features:
disappears
Token disappears
Feature activation-0.058
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
for
Token for
Feature activation+0.046
Top resid features:
the
Token the
Feature activation+0.054
Top resid features:
film
Token film
Feature activation+1.996
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
s
Tokens
Feature activation+0.027
Top resid features:
second
Token second
Feature activation+0.000
Top resid features:
half
Token half
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.014
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
rare
Token rare
Feature activation-0.001
Top resid features:
sort
Token sort
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
movie
Token movie
Feature activation+1.422
Top resid features:
that
Token that
Feature activation+0.018
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
make
Token make
Feature activation-0.000
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
sober
Token sober
Feature activation+0.017
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.270
Top resid features:
Real
Token Real
Feature activation-0.043
Top resid features:
."
Token."
Feature activation-0.025
Top resid features:
The
Token The
Feature activation+0.013
Top resid features:
movie
Token movie
Feature activation+2.399
Top resid features:
tries
Token tries
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
"
Token "
Feature activation+0.002
Top resid features:
con
Tokencon
Feature activation+0.001
Top resid features:
front
Tokenfront
Feature activation+0.005
Top resid features:

Decoder Weights Distribution

Head 0: 0.50

Head 1: 0.02

Head 2: 0.05

Head 3: 0.07

Head 4: 0.03

Head 5: 0.08

Head 6: 0.04

Head 7: 0.06

Head 8: 0.04

Head 9: 0.03

Head 10: 0.04

Head 11: 0.03

Positive logits

filmmakers4.82

film4.58

films4.46

cinem4.39

movie4.26

cinema4.24

filmmaker4.17

filmmaking4.09

movie3.94

filming3.91

screenplay3.90

theaters3.87

movies3.84

filmed3.67

film3.66

Films3.64

trailer3.62

actresses3.52

Movie3.50

screenings3.49

Negative logits

MHz-2.55

FreeBSD-2.41

Register-2.37

MHz-2.27

UTC-2.27

Site-2.26

Hew-2.25

calcul-2.24

SI-2.23

Column-2.22

Forums-2.22

eBay-2.21

WordPress-2.19

AOL-2.19

SATA-2.19

Sites-2.19

���-2.17

MLS-2.15

RFC-2.14

Admin-2.12

INTERVAL 2.499 - 2.777
CONTAINS 0.000%

Mine
Token Mine
Feature activation+0.000
&
Token &
Feature activation+0.000
O
Token O
Feature activation+0.000
urs
Tokenurs
Feature activation+0.436
"
Token"
Feature activation+1.617
(
Token (
Feature activation+2.777
2005
Token2005
Feature activation+1.403
)
Token)
Feature activation+0.756
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000

INTERVAL 2.221 - 2.499
CONTAINS 0.000%

watching
Token watching
Feature activation+0.000
a
Token a
Feature activation+0.000
horror
Token horror
Feature activation+0.000
film
Token film
Feature activation+0.000
.
Token.
Feature activation+0.000
Its
Token Its
Feature activation+2.342
atmosphere
Token atmosphere
Feature activation+0.000
and
Token and
Feature activation+1.545
violence
Token violence
Feature activation+0.000
tug
Token tug
Feature activation+0.000
at
Token at
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
movie
Token movie
Feature activation+0.009
will
Token will
Feature activation+2.380
be
Token be
Feature activation+2.325
in
Token in
Feature activation+2.045
post
Token post
Feature activation+0.715
-
Token-
Feature activation+1.474
production
Tokenproduction
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
movie
Token movie
Feature activation+0.009
will
Token will
Feature activation+2.380
be
Token be
Feature activation+2.325
in
Token in
Feature activation+2.045
post
Token post
Feature activation+0.715
-
Token-
Feature activation+1.474
production
Tokenproduction
Feature activation+0.000
for
Token for
Feature activation+1.103
ang
Tokenang
Feature activation+0.000
oli
Tokenoli
Feature activation+0.947
(
Token (
Feature activation+1.621
19
Token19
Feature activation+0.057
62
Token62
Feature activation+1.244
)
Token)
Feature activation+2.246
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.080
It
TokenIt
Feature activation+0.286
was
Token was
Feature activation+0.380
a
Token a
Feature activation+0.097

INTERVAL 1.944 - 2.221
CONTAINS 0.001%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+1.397
And
Token And
Feature activation+1.462
in
Token in
Feature activation+2.051
The
Token The
Feature activation+1.969
Dark
Token Dark
Feature activation+0.000
Knight
Token Knight
Feature activation+0.000
,
Token,
Feature activation+0.620
Batman
Token Batman
Feature activation+0.000
represents
Token represents
Feature activation+0.000
China
Token China
Feature activation+0.000
's
Token's
Feature activation+0.372
biggest
Token biggest
Feature activation+0.287
movie
Token movie
Feature activation+0.000
ever
Token ever
Feature activation+2.019
,
Token,
Feature activation+2.206
how
Token how
Feature activation+0.000
it
Token it
Feature activation+0.285
feels
Token feels
Feature activation+0.000
to
Token to
Feature activation+0.000
suddenly
Token suddenly
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
movie
Token movie
Feature activation+0.009
will
Token will
Feature activation+2.380
be
Token be
Feature activation+2.325
in
Token in
Feature activation+2.045
post
Token post
Feature activation+0.715
-
Token-
Feature activation+1.474
production
Tokenproduction
Feature activation+0.000
for
Token for
Feature activation+1.103
the
Token the
Feature activation+0.709
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.963
second
Token second
Feature activation+2.075
half
Token half
Feature activation+0.056
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
expressing
Token expressing
Feature activation+0.000
the
Token the
Feature activation+0.417
film
Token film
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
film
Token film
Feature activation+0.897
was
Token was
Feature activation+2.060
later
Token later
Feature activation+1.456
rem
Token rem
Feature activation+1.143
ade
Tokenade
Feature activation+0.732
in
Token in
Feature activation+0.593
T
Token T
Feature activation+0.000

INTERVAL 1.666 - 1.944
CONTAINS 0.003%

eye
Token eye
Feature activation+0.000
and
Token and
Feature activation+0.000
some
Token some
Feature activation+0.000
genuine
Token genuine
Feature activation+0.000
compassion
Token compassion
Feature activation+0.000
,"
Token,"
Feature activation+1.907
and
Token and
Feature activation+0.994
succeeds
Token succeeds
Feature activation+0.000
on
Token on
Feature activation+0.000
occasion
Token occasion
Feature activation+0.000
(
Token (
Feature activation+0.166
s
Tokens
Feature activation+0.519
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.243
general
Token general
Feature activation+0.626
.
Token.
Feature activation+1.414
It
Token It
Feature activation+1.880
became
Token became
Feature activation+1.012
a
Token a
Feature activation+0.995
trend
Token trend
Feature activation+0.000
set
Tokenset
Feature activation+0.000
ter
Tokenter
Feature activation+0.000
story
Token story
Feature activation+0.000
,
Token,
Feature activation+1.007
titled
Token titled
Feature activation+0.000
Life
Token Life
Feature activation+0.000
boat
Tokenboat
Feature activation+0.000
.
Token.
Feature activation+1.670
After
Token After
Feature activation+1.777
a
Token a
Feature activation+0.070
ship
Token ship
Feature activation+0.000
wreck
Tokenwreck
Feature activation+0.000
,
Token,
Feature activation+0.000
Ant
Token Ant
Feature activation+0.000
icipated
Tokenicipated
Feature activation+0.680
Movies
Token Movies
Feature activation+0.000
:
Token:
Feature activation+0.000
'
Token '
Feature activation+1.257
X
TokenX
Feature activation+1.688
-
Token-
Feature activation+1.239
Men
TokenMen
Feature activation+0.560
:
Token:
Feature activation+0.000
Days
Token Days
Feature activation+0.000
of
Token of
Feature activation+0.000
succeeds
Token succeeds
Feature activation+0.000
on
Token on
Feature activation+0.000
occasion
Token occasion
Feature activation+0.000
(
Token (
Feature activation+0.166
for
Tokenfor
Feature activation+0.230
instance
Token instance
Feature activation+1.672
,
Token,
Feature activation+1.699
when
Token when
Feature activation+1.814
civil
Token civil
Feature activation+0.000
rights
Token rights
Feature activation+0.000
activist
Token activist
Feature activation+0.000

INTERVAL 1.388 - 1.666
CONTAINS 0.005%

io
Tokenio
Feature activation+0.000
was
Token was
Feature activation+0.000
discussing
Token discussing
Feature activation+0.000
the
Token the
Feature activation+0.392
movie
Token movie
Feature activation+0.000
's
Token's
Feature activation+1.636
soundtrack
Token soundtrack
Feature activation+0.000
having
Token having
Feature activation+0.000
become
Token become
Feature activation+0.000
his
Token his
Feature activation+0.000
life
Token life
Feature activation+0.000
ologue
Tokenologue
Feature activation+0.000
at
Token at
Feature activation+0.936
the
Token the
Feature activation+1.001
beginning
Token beginning
Feature activation+0.000
of
Token of
Feature activation+1.414
the
Token the
Feature activation+1.567
movie
Token movie
Feature activation+0.000
is
Token is
Feature activation+0.000
R
Token R
Feature activation+0.073
enton
Tokenenton
Feature activation+0.000
talking
Token talking
Feature activation+0.000
plans
Token plans
Feature activation+0.000
to
Token to
Feature activation+0.222
submit
Token submit
Feature activation+0.560
the
Token the
Feature activation+1.184
film
Token film
Feature activation+0.000
to
Token to
Feature activation+1.537
various
Token various
Feature activation+0.284
festivals
Token festivals
Feature activation+0.000
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
work
Token work
Feature activation+0.000
Neill
TokenNeill
Feature activation+0.320
is
Token is
Feature activation+0.877
a
Token a
Feature activation+1.234
main
Token main
Feature activation+0.000
character
Token character
Feature activation+0.000
in
Token in
Feature activation+1.637
the
Token the
Feature activation+1.644
TNT
Token TNT
Feature activation+0.247
movie
Token movie
Feature activation+0.000
Rough
Token Rough
Feature activation+0.000
Riders
Token Riders
Feature activation+0.473
table
Tokentable
Feature activation+0.000
family
Token family
Feature activation+0.000
-
Token-
Feature activation+0.000
friendly
Tokenfriendly
Feature activation+0.000
movies
Token movies
Feature activation+0.000
like
Token like
Feature activation+1.496
Honey
Token Honey
Feature activation+0.000
moon
Tokenmoon
Feature activation+0.000
In
Token In
Feature activation+0.000
Vegas
Token Vegas
Feature activation+0.086
and
Token and
Feature activation+1.374

INTERVAL 1.111 - 1.388
CONTAINS 0.008%

.
Token.
Feature activation+0.067
The
Token The
Feature activation+0.000
film
Token film
Feature activation+0.110
is
Token is
Feature activation+0.812
slated
Token slated
Feature activation+0.647
to
Token to
Feature activation+1.313
open
Token open
Feature activation+0.810
in
Token in
Feature activation+0.383
Japanese
Token Japanese
Feature activation+0.114
theaters
Token theaters
Feature activation+0.000
in
Token in
Feature activation+0.142
icipated
Tokenicipated
Feature activation+0.680
Movies
Token Movies
Feature activation+0.000
:
Token:
Feature activation+0.000
'
Token '
Feature activation+1.257
X
TokenX
Feature activation+1.688
-
Token-
Feature activation+1.239
Men
TokenMen
Feature activation+0.560
:
Token:
Feature activation+0.000
Days
Token Days
Feature activation+0.000
of
Token of
Feature activation+0.000
Future
Token Future
Feature activation+0.000
Japanese
TokenJapanese
Feature activation+1.434
films
Token films
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.388
City
TokenCity
Feature activation+0.000
Lights
Token Lights
Feature activation+1.219
,
Token,
Feature activation+1.109
Dir
Token Dir
Feature activation+0.000
.
Token.
Feature activation+0.000
Charlie
Token Charlie
Feature activation+0.564
Cha
Token Cha
Feature activation+0.000
s
Tokens
Feature activation+0.000
new
Token new
Feature activation+0.000
film
Token film
Feature activation+0.000
is
Token is
Feature activation+1.205
a
Token a
Feature activation+0.305
certified
Token certified
Feature activation+1.240
fl
Token fl
Feature activation+0.000
op
Tokenop
Feature activation+0.409
.
Token.
Feature activation+0.283
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.512
with
Token with
Feature activation+0.307
a
Token a
Feature activation+1.046
script
Token script
Feature activation+0.000
,
Token,
Feature activation+0.820
director
Token director
Feature activation+0.000
,
Token,
Feature activation+1.243
and
Token and
Feature activation+1.289
studio
Token studio
Feature activation+0.000
all
Token all
Feature activation+0.000
set
Token set
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.833 - 1.111
CONTAINS 0.016%

films
Token films
Feature activation+0.000
that
Token that
Feature activation+0.000
were
Token were
Feature activation+0.170
either
Token either
Feature activation+0.938
killed
Token killed
Feature activation+0.431
at
Token at
Feature activation+0.847
the
Token the
Feature activation+0.976
treatment
Token treatment
Feature activation+0.000
or
Token or
Feature activation+0.960
script
Token script
Feature activation+0.000
stage
Token stage
Feature activation+0.000
cute
Token cute
Feature activation+0.000
movie
Token movie
Feature activation+0.103
.
Token.
Feature activation+0.608
There
Token There
Feature activation+0.265
was
Token was
Feature activation+0.507
no
Token no
Feature activation+0.947
music
Token music
Feature activation+0.014
at
Token at
Feature activation+0.911
all
Token all
Feature activation+0.000
on
Token on
Feature activation+1.723
it
Token it
Feature activation+0.407
a
Token a
Feature activation+0.000
surprise
Token surprise
Feature activation+0.000
as
Token as
Feature activation+0.000
nobody
Token nobody
Feature activation+0.000
knows
Token knows
Feature activation+0.000
the
Token the
Feature activation+1.080
character
Token character
Feature activation+0.000
better
Token better
Feature activation+0.000
than
Token than
Feature activation+0.305
the
Token the
Feature activation+0.000
ones
Token ones
Feature activation+0.000
unreal
Token unreal
Feature activation+0.000
ized
Tokenized
Feature activation+0.357
films
Token films
Feature activation+0.000
that
Token that
Feature activation+0.000
were
Token were
Feature activation+0.170
either
Token either
Feature activation+0.938
killed
Token killed
Feature activation+0.431
at
Token at
Feature activation+0.847
the
Token the
Feature activation+0.976
treatment
Token treatment
Feature activation+0.000
or
Token or
Feature activation+0.960
on
Token on
Feature activation+1.441
March
Token March
Feature activation+0.000
1
Token 1
Feature activation+0.000
,
Token,
Feature activation+0.416
2013
Token 2013
Feature activation+0.748
,
Token,
Feature activation+0.978
received
Token received
Feature activation+0.746
generally
Token generally
Feature activation+0.139
unfavorable
Token unfavorable
Feature activation+0.320
reviews
Token reviews
Feature activation+0.008
from
Token from
Feature activation+1.024

INTERVAL 0.555 - 0.833
CONTAINS 0.027%

orman
Tokenorman
Feature activation+0.000
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.638
upcoming
Token upcoming
Feature activation+0.754
Jon
Token Jon
Feature activation+0.000
H
Token H
Feature activation+0.000
eder
Tokeneder
Feature activation+0.000
series
Token series
Feature activation+0.000
,
Token,
Feature activation+0.000
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+0.000
throughout
Token throughout
Feature activation+0.000
the
Token the
Feature activation+0.366
whole
Token whole
Feature activation+0.610
book
Token book
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
Fi
TokenFi
Feature activation+0.000
Film
Token Film
Feature activation+0.000
Never
Token Never
Feature activation+2.032
Made
Token Made
Feature activation+0.189
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.688
The
TokenThe
Feature activation+0.351
long
Token long
Feature activation+0.000
and
Token and
Feature activation+0.077
st
Token st
Feature activation+0.000
oried
Tokenoried
Feature activation+0.716
classic
Token classic
Feature activation+0.355
Journey
Token Journey
Feature activation+0.210
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.264
tales
Token tales
Feature activation+0.656
--
Token --
Feature activation+0.000
Stephen
Token Stephen
Feature activation+0.103
Chow
Token Chow
Feature activation+0.000
's
Token's
Feature activation+0.949
Journey
Token Journey
Feature activation+0.166
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.000
Pyongyang
Token Pyongyang
Feature activation+0.000
the
Token the
Feature activation+0.000
finger
Token finger
Feature activation+0.000
:
Token:
Feature activation+0.769
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.203
After
TokenAfter
Feature activation+0.030
Sony
Token Sony
Feature activation+0.000
canceled
Token canceled
Feature activation+0.545

INTERVAL 0.278 - 0.555
CONTAINS 0.044%

Vision
Token Vision
Feature activation+0.000
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.000
you
Token you
Feature activation+0.000
get
Token get
Feature activation+0.000
into
Token into
Feature activation+0.545
your
Token your
Feature activation+0.179
Superman
Token Superman
Feature activation+0.000
territory
Token territory
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
end
Token end
Feature activation+0.000
,
Token,
Feature activation+0.000
rather
Token rather
Feature activation+0.000
than
Token than
Feature activation+0.000
throughout
Token throughout
Feature activation+0.000
the
Token the
Feature activation+0.366
whole
Token whole
Feature activation+0.610
book
Token book
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,'
Token,'
Feature activation+0.457
'
Token '
Feature activation+1.630
M
TokenM
Feature activation+0.810
ocking
Tokenocking
Feature activation+0.000
jay
Tokenjay
Feature activation+0.000
,'
Token,'
Feature activation+0.479
'
Token '
Feature activation+1.133
Spider
TokenSpider
Feature activation+0.000
-
Token-
Feature activation+0.000
Man
TokenMan
Feature activation+0.000
2
Token 2
Feature activation+0.000
it
Token it
Feature activation+0.000
out
Token out
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
when
Token when
Feature activation+0.000
a
Token a
Feature activation+0.292
script
Token script
Feature activation+0.000
on
Token on
Feature activation+0.324
their
Token their
Feature activation+0.060
desks
Token desks
Feature activation+0.000
contain
Token contain
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.068
both
Token both
Feature activation+0.000
myself
Token myself
Feature activation+0.000
and
Token and
Feature activation+0.245
my
Token my
Feature activation+0.289
sister
Token sister
Feature activation+0.000
,
Token,
Feature activation+0.000
t
Token t
Feature activation+0.000
ep
Tokenep
Feature activation+0.000
id
Tokenid
Feature activation+0.230

INTERVAL 0.000 - 0.278
CONTAINS 99.897%

wives
Token wives
Feature activation+0.000
and
Token and
Feature activation+0.000
their
Token their
Feature activation+0.000
kids
Token kids
Feature activation+0.000
and
Token and
Feature activation+0.000
their
Token their
Feature activation+0.000
grandparents
Token grandparents
Feature activation+0.000
and
Token and
Feature activation+0.000
their
Token their
Feature activation+0.000
extended
Token extended
Feature activation+0.000
families
Token families
Feature activation+0.000
six
Token six
Feature activation+0.000
-
Token-
Feature activation+0.000
person
Tokenperson
Feature activation+0.000
interior
Token interior
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
BMW
Token BMW
Feature activation+0.000
X
Token X
Feature activation+0.000
7
Token7
Feature activation+0.000
i
Token i
Feature activation+0.000
Performance
TokenPerformance
Feature activation+0.000
companies
Token companies
Feature activation+0.000
bid
Token bid
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
tiny
Token tiny
Feature activation+0.000
fraction
Token fraction
Feature activation+0.000
of
Token of
Feature activation+0.000
land
Token land
Feature activation+0.000
available
Token available
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
only
Token only
Feature activation+0.000
in
Token in
Feature activation+0.000
1978
Token 1978
Feature activation+0.000
.
Token.
Feature activation+0.000
Before
Token Before
Feature activation+0.000
the
Token the
Feature activation+0.000
independent
Token independent
Feature activation+0.000
counsel
Token counsel
Feature activation+0.000
brought
Token brought
Feature activation+0.000
her
Token her
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
exploiting
Token exploiting
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
legal
Token legal
Feature activation+0.000
paths
Token paths
Feature activation+0.000
to
Token to
Feature activation+0.000
travel
Token travel
Feature activation+0.000
to
Token to
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 H9.0: (feature 20665)

TOP ACTIVATIONS
MAX = 5.075

vant
Tokenvant
Feature activation+0.000
i
Tokeni
Feature activation+0.000
's
Token's
Feature activation+0.000
email
Token email
Feature activation+0.000
address
Token address
Feature activation+0.008
were
Token were
Feature activation+5.075
unsuccessful
Token unsuccessful
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
vant
Tokenvant
Feature activation+0.000
i
Tokeni
Feature activation+0.000
Italian
Token Italian
Feature activation+0.000
unification
Token unification
Feature activation+0.000
in
Token in
Feature activation+0.000
1861
Token 1861
Feature activation+0.000
attempts
Token attempts
Feature activation+1.665
were
Token were
Feature activation+4.721
made
Token made
Feature activation+2.568
to
Token to
Feature activation+0.000
tackle
Token tackle
Feature activation+0.000
the
Token the
Feature activation+0.000
Cam
Token Cam
Feature activation+0.000
the
Token the
Feature activation+0.000
effort
Token effort
Feature activation+0.165
that
Token that
Feature activation+2.567
its
Token its
Feature activation+0.000
government
Token government
Feature activation+3.521
had
Token had
Feature activation+4.590
to
Token to
Feature activation+1.236
go
Token go
Feature activation+1.807
to
Token to
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
station
Token station
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
resolution
Token resolution
Feature activation+0.000
efforts
Token efforts
Feature activation+3.643
will
Token will
Feature activation+4.568
continue
Token continue
Feature activation+3.356
.
Token.
Feature activation+0.000
R
TokenR
Feature activation+0.000
ane
Tokenane
Feature activation+0.000
b
Tokenb
Feature activation+0.000
every
Token every
Feature activation+0.000
watch
Token watch
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
effort
Token effort
Feature activation+0.000
they
Token they
Feature activation+3.610
have
Token have
Feature activation+4.474
made
Token made
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
contrary
Token contrary
Feature activation+0.000
,
Token,
Feature activation+0.000
Jordan
Token Jordan
Feature activation+0.000
and
Token and
Feature activation+0.000
Egypt
Token Egypt
Feature activation+0.000
,
Token,
Feature activation+0.000
efforts
Token efforts
Feature activation+0.408
were
Token were
Feature activation+4.472
made
Token made
Feature activation+0.408
to
Token to
Feature activation+0.000
block
Token block
Feature activation+0.000
the
Token the
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
at
Token at
Feature activation+0.000
NSA
Token NSA
Feature activation+0.000
reform
Token reform
Feature activation+2.598
on
Token on
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+4.462
this
Token this
Feature activation+0.000
year
Token year
Feature activation+3.614
have
Token have
Feature activation+3.047
been
Token been
Feature activation+3.842
slow
Token slow
Feature activation+0.543
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
every
Token every
Feature activation+0.000
effort
Token effort
Feature activation+0.639
will
Token will
Feature activation+3.022
be
Token be
Feature activation+4.161
made
Token made
Feature activation+0.000
to
Token to
Feature activation+0.000
res
Token res
Feature activation+0.000
che
Tokenche
Feature activation+0.000
dule
Tokendule
Feature activation+0.000
effort
Token effort
Feature activation+0.000
to
Token to
Feature activation+0.000
correct
Token correct
Feature activation+0.000
the
Token the
Feature activation+0.000
anomaly
Token anomaly
Feature activation+0.000
was
Token was
Feature activation+4.094
the
Token the
Feature activation+0.398
launch
Token launch
Feature activation+0.000
of
Token of
Feature activation+0.000
National
Token National
Feature activation+0.000
Mission
Token Mission
Feature activation+0.000
research
Token research
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.464
need
Token need
Feature activation+0.068
to
Token to
Feature activation+2.809
be
Token be
Feature activation+3.971
re
Token re
Feature activation+1.839
thought
Tokenthought
Feature activation+0.155
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
regulate
Token regulate
Feature activation+0.000
disruptive
Token disruptive
Feature activation+0.000
technologies
Token technologies
Feature activation+0.000
have
Token have
Feature activation+2.443
traditionally
Token traditionally
Feature activation+2.079
been
Token been
Feature activation+3.845
a
Token a
Feature activation+0.554
function
Token function
Feature activation+0.000
of
Token of
Feature activation+0.114
the
Token the
Feature activation+0.000
technology
Token technology
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+4.462
this
Token this
Feature activation+0.000
year
Token year
Feature activation+3.614
have
Token have
Feature activation+3.047
been
Token been
Feature activation+3.842
slow
Token slow
Feature activation+0.543
going
Token going
Feature activation+0.554
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
in
Token in
Feature activation+0.000
i
Tokeni
Feature activation+0.000
station
Token station
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
resolution
Token resolution
Feature activation+0.000
efforts
Token efforts
Feature activation+3.643
will
Token will
Feature activation+4.568
continue
Token continue
Feature activation+3.356
.
Token.
Feature activation+0.000
R
TokenR
Feature activation+0.000
ane
Tokenane
Feature activation+0.000
reform
Token reform
Feature activation+2.598
on
Token on
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+4.462
this
Token this
Feature activation+0.000
year
Token year
Feature activation+3.614
have
Token have
Feature activation+3.047
been
Token been
Feature activation+3.842
slow
Token slow
Feature activation+0.543
going
Token going
Feature activation+0.554
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
every
Token every
Feature activation+0.000
watch
Token watch
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
effort
Token effort
Feature activation+0.000
they
Token they
Feature activation+3.610
have
Token have
Feature activation+4.474
made
Token made
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
contrary
Token contrary
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
effort
Token effort
Feature activation+0.165
that
Token that
Feature activation+2.567
its
Token its
Feature activation+0.000
government
Token government
Feature activation+3.521
had
Token had
Feature activation+4.590
to
Token to
Feature activation+1.236
go
Token go
Feature activation+1.807
to
Token to
Feature activation+0.000
in
Token in
Feature activation+0.000
via
Token via
Feature activation+0.000
email
Token email
Feature activation+0.000
that
Token that
Feature activation+0.000
their
Token their
Feature activation+0.000
efforts
Token efforts
Feature activation+0.000
are
Token are
Feature activation+3.445
geared
Token geared
Feature activation+0.127
towards
Token towards
Feature activation+0.000
educating
Token educating
Feature activation+0.000
the
Token the
Feature activation+0.000
healthcare
Token healthcare
Feature activation+0.000
council
Token council
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
efforts
Token efforts
Feature activation+0.573
have
Token have
Feature activation+3.414
failed
Token failed
Feature activation+0.023
to
Token to
Feature activation+1.128
bring
Token bring
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
resolution
Token resolution
Feature activation+0.000
efforts
Token efforts
Feature activation+3.643
will
Token will
Feature activation+4.568
continue
Token continue
Feature activation+3.356
.
Token.
Feature activation+0.000
R
TokenR
Feature activation+0.000
ane
Tokenane
Feature activation+0.000
b
Tokenb
Feature activation+0.000
enn
Tokenenn
Feature activation+0.000
.
Token.
Feature activation+0.000
Though
Token Though
Feature activation+0.000
some
Token some
Feature activation+0.000
attempts
Token attempts
Feature activation+0.296
have
Token have
Feature activation+2.888
been
Token been
Feature activation+3.206
made
Token made
Feature activation+0.321
at
Token at
Feature activation+0.000
rudimentary
Token rudimentary
Feature activation+0.000
conditioning
Token conditioning
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000

Top DFA by src position
MAX = 5.486

his
Token his
Feature activation+0.000
Top resid features:
family
Token family
Feature activation+0.000
Top resid features:
."
Token."
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Attempts
TokenAttempts
Feature activation+5.486
Top resid features:
to
Token to
Feature activation+0.164
Top resid features:
reach
Token reach
Feature activation+0.028
Top resid features:
Anthony
Token Anthony
Feature activation-0.001
Top resid features:
through
Token through
Feature activation+0.007
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
Following
TokenFollowing
Feature activation-0.008
Top resid features:
Italian
Token Italian
Feature activation+0.002
Top resid features:
unification
Token unification
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
1861
Token 1861
Feature activation-0.010
Top resid features:
attempts
Token attempts
Feature activation+5.346
Top resid features:
were
Token were
Feature activation+0.049
Top resid features:
made
Token made
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
tackle
Token tackle
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.003
Top resid features:
still
Token still
Feature activation-0.004
Top resid features:
recovering
Token recovering
Feature activation-0.003
Top resid features:
from
Token from
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
effort
Token effort
Feature activation+5.107
Top resid features:
that
Token that
Feature activation+0.065
Top resid features:
its
Token its
Feature activation+0.006
Top resid features:
government
Token government
Feature activation+0.069
Top resid features:
had
Token had
Feature activation+0.031
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
i
Tokeni
Feature activation+0.000
Top resid features:
station
Token station
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
said
Token said
Feature activation+0.075
Top resid features:
resolution
Token resolution
Feature activation+0.028
Top resid features:
efforts
Token efforts
Feature activation+5.081
Top resid features:
will
Token will
Feature activation+0.092
Top resid features:
continue
Token continue
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
R
TokenR
Feature activation+0.000
Top resid features:
ane
Tokenane
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
every
Token every
Feature activation+0.009
Top resid features:
watch
Token watch
Feature activation+0.003
Top resid features:
ful
Tokenful
Feature activation+0.011
Top resid features:
effort
Token effort
Feature activation+5.018
Top resid features:
they
Token they
Feature activation+0.201
Top resid features:
have
Token have
Feature activation+0.032
Top resid features:
made
Token made
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
Jordan
Token Jordan
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
Egypt
Token Egypt
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
efforts
Token efforts
Feature activation+5.021
Top resid features:
were
Token were
Feature activation+0.048
Top resid features:
made
Token made
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
block
Token block
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
But
TokenBut
Feature activation+0.025
Top resid features:
attempts
Token attempts
Feature activation+4.655
Top resid features:
at
Token at
Feature activation+0.152
Top resid features:
NSA
Token NSA
Feature activation+0.019
Top resid features:
reform
Token reform
Feature activation+0.134
Top resid features:
on
Token on
Feature activation+0.093
Top resid features:
Capitol
Token Capitol
Feature activation+0.014
Top resid features:
decision
Token decision
Feature activation-0.006
Top resid features:
lightly
Token lightly
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
every
Token every
Feature activation+0.016
Top resid features:
effort
Token effort
Feature activation+4.511
Top resid features:
will
Token will
Feature activation+0.279
Top resid features:
be
Token be
Feature activation+0.018
Top resid features:
made
Token made
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
res
Token res
Feature activation+0.000
Top resid features:
people
Token people
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
An
TokenAn
Feature activation+0.001
Top resid features:
effort
Token effort
Feature activation+4.467
Top resid features:
to
Token to
Feature activation+0.074
Top resid features:
correct
Token correct
Feature activation+0.038
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
anomaly
Token anomaly
Feature activation+0.073
Top resid features:
was
Token was
Feature activation+0.070
Top resid features:
an
Token an
Feature activation+0.009
Top resid features:
active
Token active
Feature activation+0.022
Top resid features:
debate
Token debate
Feature activation+0.007
Top resid features:
about
Token about
Feature activation+0.009
Top resid features:
whether
Token whether
Feature activation+0.057
Top resid features:
efforts
Token efforts
Feature activation+4.165
Top resid features:
to
Token to
Feature activation+0.035
Top resid features:
combat
Token combat
Feature activation+0.013
Top resid features:
cancer
Token cancer
Feature activation-0.001
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.049
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
ľ
Tokenľ
Feature activation-0.001
Top resid features:
In
TokenIn
Feature activation+0.001
Top resid features:
fact
Token fact
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
serious
Token serious
Feature activation-0.005
Top resid features:
efforts
Token efforts
Feature activation+3.445
Top resid features:
to
Token to
Feature activation+0.145
Top resid features:
regulate
Token regulate
Feature activation+0.049
Top resid features:
disruptive
Token disruptive
Feature activation+0.012
Top resid features:
technologies
Token technologies
Feature activation+0.070
Top resid features:
have
Token have
Feature activation+0.387
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
But
TokenBut
Feature activation+0.022
Top resid features:
attempts
Token attempts
Feature activation+3.435
Top resid features:
at
Token at
Feature activation+0.134
Top resid features:
NSA
Token NSA
Feature activation-0.002
Top resid features:
reform
Token reform
Feature activation+0.082
Top resid features:
on
Token on
Feature activation+0.007
Top resid features:
Capitol
Token Capitol
Feature activation+0.001
Top resid features:
i
Tokeni
Feature activation-0.002
Top resid features:
station
Token station
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.015
Top resid features:
said
Token said
Feature activation+0.339
Top resid features:
resolution
Token resolution
Feature activation+0.041
Top resid features:
efforts
Token efforts
Feature activation+4.124
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
continue
Token continue
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
R
TokenR
Feature activation+0.000
Top resid features:
ane
Tokenane
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
But
TokenBut
Feature activation+0.028
Top resid features:
attempts
Token attempts
Feature activation+3.682
Top resid features:
at
Token at
Feature activation+0.155
Top resid features:
NSA
Token NSA
Feature activation+0.009
Top resid features:
reform
Token reform
Feature activation+0.075
Top resid features:
on
Token on
Feature activation+0.029
Top resid features:
Capitol
Token Capitol
Feature activation+0.012
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
every
Token every
Feature activation+0.016
Top resid features:
watch
Token watch
Feature activation-0.014
Top resid features:
ful
Tokenful
Feature activation+0.009
Top resid features:
effort
Token effort
Feature activation+4.302
Top resid features:
they
Token they
Feature activation+0.065
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
made
Token made
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.005
Top resid features:
still
Token still
Feature activation-0.009
Top resid features:
recovering
Token recovering
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
effort
Token effort
Feature activation+4.271
Top resid features:
that
Token that
Feature activation+0.034
Top resid features:
its
Token its
Feature activation+0.031
Top resid features:
government
Token government
Feature activation+0.071
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
us
Token us
Feature activation+0.081
Top resid features:
via
Token via
Feature activation-0.007
Top resid features:
email
Token email
Feature activation-0.012
Top resid features:
that
Token that
Feature activation+0.025
Top resid features:
their
Token their
Feature activation-0.000
Top resid features:
efforts
Token efforts
Feature activation+4.204
Top resid features:
are
Token are
Feature activation+0.069
Top resid features:
geared
Token geared
Feature activation+0.000
Top resid features:
towards
Token towards
Feature activation+0.000
Top resid features:
educating
Token educating
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
council
Token council
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+0.017
Top resid features:
Ļ
TokenĻ
Feature activation+0.025
Top resid features:
s
Tokens
Feature activation+0.020
Top resid features:
efforts
Token efforts
Feature activation+3.801
Top resid features:
have
Token have
Feature activation+0.204
Top resid features:
failed
Token failed
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
bring
Token bring
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
i
Tokeni
Feature activation+0.003
Top resid features:
station
Token station
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
said
Token said
Feature activation+0.111
Top resid features:
resolution
Token resolution
Feature activation+0.008
Top resid features:
efforts
Token efforts
Feature activation+3.671
Top resid features:
will
Token will
Feature activation+0.224
Top resid features:
continue
Token continue
Feature activation+0.094
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
R
TokenR
Feature activation+0.000
Top resid features:
ane
Tokenane
Feature activation+0.000
Top resid features:
similar
Token similar
Feature activation+0.002
Top resid features:
ways
Token ways
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
Though
Token Though
Feature activation+0.047
Top resid features:
some
Token some
Feature activation+0.032
Top resid features:
attempts
Token attempts
Feature activation+3.540
Top resid features:
have
Token have
Feature activation+0.193
Top resid features:
been
Token been
Feature activation+0.098
Top resid features:
made
Token made
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
rudimentary
Token rudimentary
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.50

Head 1: 0.02

Head 2: 0.11

Head 3: 0.07

Head 4: 0.02

Head 5: 0.04

Head 6: 0.02

Head 7: 0.05

Head 8: 0.03

Head 9: 0.02

Head 10: 0.10

Head 11: 0.02

Positive logits

succeed3.30

unsuccessful3.23

ouble3.20

successful3.18

succeeded3.00

successfully2.96

futile2.78

successes2.75

2.66

Impossible2.60

zanne2.60

Success2.60

efforts2.58

issance2.57

successful2.57

undertaken2.55

Eff2.55

success2.54

succeeds2.48

ogo2.41

Negative logits

spoilers-2.99

spoiler-2.51

paraph-2.33

lett-2.29

seating-2.28

OIL-2.27

clauses-2.26

indent-2.20

certific-2.19

prescribing-2.16

instructor-2.16

Maul-2.15

reader-2.11

occupancy-2.11

commenting-2.11

column-2.10

Newsp-2.09

grammar-2.07

whistlebl-2.06

pronouns-2.06

INTERVAL 4.568 - 5.075
CONTAINS 0.000%

station
Token station
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
resolution
Token resolution
Feature activation+0.000
efforts
Token efforts
Feature activation+3.643
will
Token will
Feature activation+4.568
continue
Token continue
Feature activation+3.356
.
Token.
Feature activation+0.000
R
TokenR
Feature activation+0.000
ane
Tokenane
Feature activation+0.000
b
Tokenb
Feature activation+0.000
the
Token the
Feature activation+0.000
effort
Token effort
Feature activation+0.165
that
Token that
Feature activation+2.567
its
Token its
Feature activation+0.000
government
Token government
Feature activation+3.521
had
Token had
Feature activation+4.590
to
Token to
Feature activation+1.236
go
Token go
Feature activation+1.807
to
Token to
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
vant
Tokenvant
Feature activation+0.000
i
Tokeni
Feature activation+0.000
's
Token's
Feature activation+0.000
email
Token email
Feature activation+0.000
address
Token address
Feature activation+0.008
were
Token were
Feature activation+5.075
unsuccessful
Token unsuccessful
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
vant
Tokenvant
Feature activation+0.000
i
Tokeni
Feature activation+0.000
Italian
Token Italian
Feature activation+0.000
unification
Token unification
Feature activation+0.000
in
Token in
Feature activation+0.000
1861
Token 1861
Feature activation+0.000
attempts
Token attempts
Feature activation+1.665
were
Token were
Feature activation+4.721
made
Token made
Feature activation+2.568
to
Token to
Feature activation+0.000
tackle
Token tackle
Feature activation+0.000
the
Token the
Feature activation+0.000
Cam
Token Cam
Feature activation+0.000

INTERVAL 4.060 - 4.568
CONTAINS 0.001%

Jordan
Token Jordan
Feature activation+0.000
and
Token and
Feature activation+0.000
Egypt
Token Egypt
Feature activation+0.000
,
Token,
Feature activation+0.000
efforts
Token efforts
Feature activation+0.408
were
Token were
Feature activation+4.472
made
Token made
Feature activation+0.408
to
Token to
Feature activation+0.000
block
Token block
Feature activation+0.000
the
Token the
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
effort
Token effort
Feature activation+0.000
to
Token to
Feature activation+0.000
correct
Token correct
Feature activation+0.000
the
Token the
Feature activation+0.000
anomaly
Token anomaly
Feature activation+0.000
was
Token was
Feature activation+4.094
the
Token the
Feature activation+0.398
launch
Token launch
Feature activation+0.000
of
Token of
Feature activation+0.000
National
Token National
Feature activation+0.000
Mission
Token Mission
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
every
Token every
Feature activation+0.000
effort
Token effort
Feature activation+0.639
will
Token will
Feature activation+3.022
be
Token be
Feature activation+4.161
made
Token made
Feature activation+0.000
to
Token to
Feature activation+0.000
res
Token res
Feature activation+0.000
che
Tokenche
Feature activation+0.000
dule
Tokendule
Feature activation+0.000
at
Token at
Feature activation+0.000
NSA
Token NSA
Feature activation+0.000
reform
Token reform
Feature activation+2.598
on
Token on
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+4.462
this
Token this
Feature activation+0.000
year
Token year
Feature activation+3.614
have
Token have
Feature activation+3.047
been
Token been
Feature activation+3.842
slow
Token slow
Feature activation+0.543
every
Token every
Feature activation+0.000
watch
Token watch
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
effort
Token effort
Feature activation+0.000
they
Token they
Feature activation+3.610
have
Token have
Feature activation+4.474
made
Token made
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
contrary
Token contrary
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 3.553 - 4.060
CONTAINS 0.001%

Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+4.462
this
Token this
Feature activation+0.000
year
Token year
Feature activation+3.614
have
Token have
Feature activation+3.047
been
Token been
Feature activation+3.842
slow
Token slow
Feature activation+0.543
going
Token going
Feature activation+0.554
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
in
Token in
Feature activation+0.000
regulate
Token regulate
Feature activation+0.000
disruptive
Token disruptive
Feature activation+0.000
technologies
Token technologies
Feature activation+0.000
have
Token have
Feature activation+2.443
traditionally
Token traditionally
Feature activation+2.079
been
Token been
Feature activation+3.845
a
Token a
Feature activation+0.554
function
Token function
Feature activation+0.000
of
Token of
Feature activation+0.114
the
Token the
Feature activation+0.000
technology
Token technology
Feature activation+0.000
research
Token research
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.464
need
Token need
Feature activation+0.068
to
Token to
Feature activation+2.809
be
Token be
Feature activation+3.971
re
Token re
Feature activation+1.839
thought
Tokenthought
Feature activation+0.155
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
reform
Token reform
Feature activation+2.598
on
Token on
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+4.462
this
Token this
Feature activation+0.000
year
Token year
Feature activation+3.614
have
Token have
Feature activation+3.047
been
Token been
Feature activation+3.842
slow
Token slow
Feature activation+0.543
going
Token going
Feature activation+0.554
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
every
Token every
Feature activation+0.000
watch
Token watch
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
effort
Token effort
Feature activation+0.000
they
Token they
Feature activation+3.610
have
Token have
Feature activation+4.474
made
Token made
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
contrary
Token contrary
Feature activation+0.000

INTERVAL 3.045 - 3.553
CONTAINS 0.001%

,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
resolution
Token resolution
Feature activation+0.000
efforts
Token efforts
Feature activation+3.643
will
Token will
Feature activation+4.568
continue
Token continue
Feature activation+3.356
.
Token.
Feature activation+0.000
R
TokenR
Feature activation+0.000
ane
Tokenane
Feature activation+0.000
b
Tokenb
Feature activation+0.000
enn
Tokenenn
Feature activation+0.000
on
Token on
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+4.462
this
Token this
Feature activation+0.000
year
Token year
Feature activation+3.614
have
Token have
Feature activation+3.047
been
Token been
Feature activation+3.842
slow
Token slow
Feature activation+0.543
going
Token going
Feature activation+0.554
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
staff
Token staff
Feature activation+0.000
to
Token to
Feature activation+0.000
leave
Token leave
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+1.203
obviously
Token obviously
Feature activation+3.195
reveals
Token reveals
Feature activation+0.000
that
Token that
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
lacks
Token lacks
Feature activation+0.000
sincerity
Token sincerity
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
effort
Token effort
Feature activation+0.165
that
Token that
Feature activation+2.567
its
Token its
Feature activation+0.000
government
Token government
Feature activation+3.521
had
Token had
Feature activation+4.590
to
Token to
Feature activation+1.236
go
Token go
Feature activation+1.807
to
Token to
Feature activation+0.000
in
Token in
Feature activation+0.000
.
Token.
Feature activation+0.000
Though
Token Though
Feature activation+0.000
some
Token some
Feature activation+0.000
attempts
Token attempts
Feature activation+0.296
have
Token have
Feature activation+2.888
been
Token been
Feature activation+3.206
made
Token made
Feature activation+0.321
at
Token at
Feature activation+0.000
rudimentary
Token rudimentary
Feature activation+0.000
conditioning
Token conditioning
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000

INTERVAL 2.538 - 3.045
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
attempts
Token attempts
Feature activation+0.184
at
Token at
Feature activation+0.000
NSA
Token NSA
Feature activation+0.000
reform
Token reform
Feature activation+2.598
on
Token on
Feature activation+0.000
Capitol
Token Capitol
Feature activation+0.000
Hill
Token Hill
Feature activation+4.462
this
Token this
Feature activation+0.000
year
Token year
Feature activation+3.614
ways
Token ways
Feature activation+0.000
.
Token.
Feature activation+0.000
Though
Token Though
Feature activation+0.000
some
Token some
Feature activation+0.000
attempts
Token attempts
Feature activation+0.296
have
Token have
Feature activation+2.888
been
Token been
Feature activation+3.206
made
Token made
Feature activation+0.321
at
Token at
Feature activation+0.000
rudimentary
Token rudimentary
Feature activation+0.000
conditioning
Token conditioning
Feature activation+0.000
unification
Token unification
Feature activation+0.000
in
Token in
Feature activation+0.000
1861
Token 1861
Feature activation+0.000
attempts
Token attempts
Feature activation+1.665
were
Token were
Feature activation+4.721
made
Token made
Feature activation+2.568
to
Token to
Feature activation+0.000
tackle
Token tackle
Feature activation+0.000
the
Token the
Feature activation+0.000
Cam
Token Cam
Feature activation+0.000
or
Tokenor
Feature activation+0.000
construct
Token construct
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Another
Token Another
Feature activation+0.000
effort
Token effort
Feature activation+0.102
was
Token was
Feature activation+2.597
made
Token made
Feature activation+0.717
in
Token in
Feature activation+0.040
1928
Token 1928
Feature activation+0.000
.
Token.
Feature activation+0.000
More
Token More
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
attempts
Token attempts
Feature activation+0.572
were
Token were
Feature activation+2.902
made
Token made
Feature activation+0.341
to
Token to
Feature activation+0.000
confront
Token confront
Feature activation+0.000
Br
Token Br
Feature activation+0.000
onson
Tokenonson
Feature activation+0.000

INTERVAL 2.030 - 2.538
CONTAINS 0.001%

series
Token series
Feature activation+0.000
of
Token of
Feature activation+0.000
man
Token man
Feature activation+0.000
hun
Tokenhun
Feature activation+0.000
ts
Tokents
Feature activation+0.459
were
Token were
Feature activation+2.529
made
Token made
Feature activation+1.602
from
Token from
Feature activation+0.000
18
Token 18
Feature activation+0.000
82
Token82
Feature activation+0.000
on
Token on
Feature activation+0.415
rescue
Token rescue
Feature activation+0.000
and
Token and
Feature activation+0.000
rehabilitation
Token rehabilitation
Feature activation+0.000
efforts
Token efforts
Feature activation+0.385
have
Token have
Feature activation+0.807
been
Token been
Feature activation+2.434
undertaken
Token undertaken
Feature activation+0.000
by
Token by
Feature activation+0.000
army
Token army
Feature activation+0.000
,
Token,
Feature activation+0.000
navy
Token navy
Feature activation+0.000
to
Token to
Feature activation+0.000
regulate
Token regulate
Feature activation+0.000
disruptive
Token disruptive
Feature activation+0.000
technologies
Token technologies
Feature activation+0.000
have
Token have
Feature activation+2.443
traditionally
Token traditionally
Feature activation+2.079
been
Token been
Feature activation+3.845
a
Token a
Feature activation+0.554
function
Token function
Feature activation+0.000
of
Token of
Feature activation+0.114
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
healthcare
Token healthcare
Feature activation+0.000
system
Token system
Feature activation+0.000
has
Token has
Feature activation+2.291
generated
Token generated
Feature activation+0.132
an
Token an
Feature activation+0.122
enormous
Token enormous
Feature activation+0.221
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
efforts
Token efforts
Feature activation+0.117
to
Token to
Feature activation+0.000
regulate
Token regulate
Feature activation+0.000
disruptive
Token disruptive
Feature activation+0.000
technologies
Token technologies
Feature activation+0.000
have
Token have
Feature activation+2.443
traditionally
Token traditionally
Feature activation+2.079
been
Token been
Feature activation+3.845
a
Token a
Feature activation+0.554
function
Token function
Feature activation+0.000
of
Token of
Feature activation+0.114

INTERVAL 1.523 - 2.030
CONTAINS 0.002%

limiting
Token limiting
Feature activation+0.000
the
Token the
Feature activation+0.000
reach
Token reach
Feature activation+0.000
of
Token of
Feature activation+0.000
jihadists
Token jihadists
Feature activation+0.000
may
Token may
Feature activation+1.773
also
Token also
Feature activation+1.949
work
Token work
Feature activation+0.251
for
Token for
Feature activation+0.000
white
Token white
Feature activation+0.000
supremacists
Token supremacists
Feature activation+0.000
gun
Token gun
Feature activation+0.000
-
Token-
Feature activation+0.000
control
Tokencontrol
Feature activation+0.000
efforts
Token efforts
Feature activation+0.264
back
Token back
Feature activation+0.185
on
Token on
Feature activation+2.018
the
Token the
Feature activation+1.430
agenda
Token agenda
Feature activation+0.022
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
BE
TokenBE
Feature activation+0.000
and
Token and
Feature activation+0.000
Sec
Token Sec
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
State
Token State
Feature activation+0.000
as
Token as
Feature activation+1.651
"
Token "
Feature activation+0.470
sh
Tokensh
Feature activation+0.000
ame
Tokename
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
."
Token."
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
the
Token the
Feature activation+0.000
Scottish
Token Scottish
Feature activation+0.000
throne
Token throne
Feature activation+0.235
is
Token is
Feature activation+1.924
going
Token going
Feature activation+0.642
to
Token to
Feature activation+0.995
fail
Token fail
Feature activation+0.452
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
man
Token man
Feature activation+0.000
hun
Tokenhun
Feature activation+0.000
ts
Tokents
Feature activation+0.459
were
Token were
Feature activation+2.529
made
Token made
Feature activation+1.602
from
Token from
Feature activation+0.000
18
Token 18
Feature activation+0.000
82
Token82
Feature activation+0.000
on
Token on
Feature activation+0.415
.
Token.
Feature activation+0.011

INTERVAL 1.015 - 1.523
CONTAINS 0.003%

(
Token (
Feature activation+0.000
slow
Tokenslow
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
)
Token)
Feature activation+0.000
working
Token working
Feature activation+0.018
its
Token its
Feature activation+1.248
way
Token way
Feature activation+0.230
through
Token through
Feature activation+0.000
federal
Token federal
Feature activation+0.000
approvals
Token approvals
Feature activation+0.000
.
Token.
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
both
Token both
Feature activation+0.844
of
Token of
Feature activation+0.000
them
Token them
Feature activation+1.034
are
Token are
Feature activation+0.979
still
Token still
Feature activation+0.495
tens
Token tens
Feature activation+0.000
of
Token of
Feature activation+0.071
thousands
Token thousands
Feature activation+0.000
level
Tokenlevel
Feature activation+0.000
endeav
Token endeav
Feature activation+0.000
ours
Tokenours
Feature activation+0.000
are
Token are
Feature activation+0.641
pretty
Token pretty
Feature activation+0.000
much
Token much
Feature activation+1.164
doomed
Token doomed
Feature activation+0.000
to
Token to
Feature activation+0.747
failure
Token failure
Feature activation+0.000
.
Token.
Feature activation+0.000
Em
Token Em
Feature activation+0.000
response
Token response
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
efforts
Token efforts
Feature activation+0.000
that
Token that
Feature activation+0.624
may
Token may
Feature activation+1.511
work
Token work
Feature activation+1.021
for
Token for
Feature activation+0.000
limiting
Token limiting
Feature activation+0.000
the
Token the
Feature activation+0.000
reach
Token reach
Feature activation+0.000
of
Token of
Feature activation+0.000
extra
Token extra
Feature activation+0.000
security
Token security
Feature activation+0.000
measures
Token measures
Feature activation+0.064
would
Token would
Feature activation+0.502
be
Token be
Feature activation+0.858
put
Token put
Feature activation+1.024
in
Token in
Feature activation+1.000
place
Token place
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.508 - 1.015
CONTAINS 0.017%

struggle
Token struggle
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Malt
Token Malt
Feature activation+0.000
ese
Tokenese
Feature activation+0.000
people
Token people
Feature activation+0.935
against
Token against
Feature activation+0.000
oppression
Token oppression
Feature activation+0.000
was
Token was
Feature activation+1.088
recognised
Token recognised
Feature activation+0.000
personally
Token personally
Feature activation+0.000
These
Token These
Feature activation+0.000
actions
Token actions
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
have
Token have
Feature activation+0.250
been
Token been
Feature activation+0.566
employed
Token employed
Feature activation+0.288
during
Token during
Feature activation+0.000
previous
Token previous
Feature activation+0.000
debt
Token debt
Feature activation+0.000
limit
Token limit
Feature activation+0.000
WATCHED
Token WATCHED
Feature activation+0.000
Search
Token Search
Feature activation+0.000
for
Token for
Feature activation+0.000
gas
Token gas
Feature activation+0.000
gets
Token gets
Feature activation+0.650
more
Token more
Feature activation+0.721
desperate
Token desperate
Feature activation+0.000
Replay
Token Replay
Feature activation+0.000
More
Token More
Feature activation+0.000
Videos
Token Videos
Feature activation+0.000
...
Token ...
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
investigation
Token investigation
Feature activation+0.000
can
Token can
Feature activation+0.558
draw
Token draw
Feature activation+0.000
out
Token out
Feature activation+0.000
indefinitely
Token indefinitely
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
rules
Token rules
Feature activation+0.000
were
Token were
Feature activation+0.000
tightened
Token tightened
Feature activation+0.000
and
Token and
Feature activation+0.000
education
Token education
Feature activation+0.000
campaigns
Token campaigns
Feature activation+0.532
launched
Token launched
Feature activation+0.597
to
Token to
Feature activation+0.000
reduce
Token reduce
Feature activation+0.000
erosion
Token erosion
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.000 - 0.508
CONTAINS 99.972%

FL
TokenFL
Feature activation+0.000
D
TokenD
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
leading
Token leading
Feature activation+0.000
cause
Token cause
Feature activation+0.000
of
Token of
Feature activation+0.000
chronic
Token chronic
Feature activation+0.000
liver
Token liver
Feature activation+0.000
disease
Token disease
Feature activation+0.000
as
Token as
Feature activation+0.000
They
Token They
Feature activation+0.000
're
Token're
Feature activation+0.000
everywhere
Token everywhere
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
internet
Token internet
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
name
Token name
Feature activation+0.000
any
Token any
Feature activation+0.000
subject
Token subject
Feature activation+0.000
lights
Tokenlights
Feature activation+0.000
.
Token.
Feature activation+0.000
Most
Token Most
Feature activation+0.000
modern
Token modern
Feature activation+0.000
military
Token military
Feature activation+0.000
firearms
Token firearms
Feature activation+0.000
have
Token have
Feature activation+0.000
similar
Token similar
Feature activation+0.000
structures
Token structures
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
the
Token the
Feature activation+0.000
Farm
Token Farm
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Put
TokenPut
Feature activation+0.000
your
Token your
Feature activation+0.000
vehicle
Token vehicle
Feature activation+0.000
on
Token on
Feature activation+0.000
autop
Token autop
Feature activation+0.000
ilot
Tokenilot
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
-
Token-
Feature activation+0.000
art
Tokenart
Feature activation+0.000
inf
Token inf
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
ainment
Tokenainment
Feature activation+0.000
system
Token system
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Also
TokenAlso
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 H9.0: (feature 13744)

TOP ACTIVATIONS
MAX = 8.905

pler
Tokenpler
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
odds
Token odds
Feature activation+4.085
are
Token are
Feature activation+8.465
fairly
Token fairly
Feature activation+8.905
good
Token good
Feature activation+3.487
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
made
Token made
Feature activation+0.000
a
Tokena
Feature activation+0.000
pler
Tokenpler
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
odds
Token odds
Feature activation+4.085
are
Token are
Feature activation+8.465
fairly
Token fairly
Feature activation+8.905
good
Token good
Feature activation+3.487
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
are
Token are
Feature activation+7.087
"
Token "
Feature activation+4.616
extremely
Tokenextremely
Feature activation+6.655
low
Token low
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
chances
Token chances
Feature activation+5.414
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
seemed
Token seemed
Feature activation+7.054
sl
Token sl
Feature activation+2.982
immer
Tokenimmer
Feature activation+1.914
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
pussy
Token pussy
Feature activation+0.000
chances
Token chances
Feature activation+4.249
are
Token are
Feature activation+7.011
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
be
Token be
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
asteroid
Token asteroid
Feature activation+0.000
hitting
Token hitting
Feature activation+0.000
Earth
Token Earth
Feature activation+1.964
were
Token were
Feature activation+6.580
first
Token first
Feature activation+4.167
estimated
Token estimated
Feature activation+0.000
at
Token at
Feature activation+0.724
one
Token one
Feature activation+0.247
in
Token in
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
odds
Token odds
Feature activation+1.971
are
Token are
Feature activation+6.463
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
embarrassing
Token embarrassing
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
odds
Token odds
Feature activation+1.625
are
Token are
Feature activation+6.449
good
Token good
Feature activation+3.825
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
goods
Token goods
Feature activation+0.119
...
Token...
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
odds
Token odds
Feature activation+0.932
are
Token are
Feature activation+6.234
in
Token in
Feature activation+1.025
C
Token C
Feature activation+0.000
ough
Tokenough
Feature activation+0.000
lin
Tokenlin
Feature activation+0.000
's
Token's
Feature activation+0.160
visiting
Token visiting
Feature activation+0.000
the
Token the
Feature activation+0.000
blog
Token blog
Feature activation+0.000
,
Token,
Feature activation+0.000
chances
Token chances
Feature activation+2.987
are
Token are
Feature activation+6.131
good
Token good
Feature activation+1.461
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
odds
Token odds
Feature activation+0.622
are
Token are
Feature activation+5.535
Toronto
Token Toronto
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
possession
Token possession
Feature activation+0.000
,
Token,
Feature activation+0.000
also
Token also
Feature activation+0.000
(
Token (
Feature activation+0.000
ch
Tokench
Feature activation+0.000
ances
Tokenances
Feature activation+5.200
are
Token are
Feature activation+5.433
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
,
Token,
Feature activation+0.000
Hood
Token Hood
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
chances
Token chances
Feature activation+5.414
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
seemed
Token seemed
Feature activation+7.054
sl
Token sl
Feature activation+2.982
immer
Tokenimmer
Feature activation+1.914
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
taken
Token taken
Feature activation+0.000
alive
Token alive
Feature activation+0.000
was
Token was
Feature activation+5.329
high
Token high
Feature activation+0.675
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
component
Token component
Feature activation+0.000
,
Token,
Feature activation+0.000
also
Token also
Feature activation+0.000
(
Token (
Feature activation+0.000
ch
Tokench
Feature activation+0.000
ances
Tokenances
Feature activation+5.200
are
Token are
Feature activation+5.433
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
guaranteed
Token guaranteed
Feature activation+0.000
salary
Token salary
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
chances
Token chances
Feature activation+4.782
of
Token of
Feature activation+0.000
hammer
Token hammer
Feature activation+0.000
ing
Tokening
Feature activation+0.000
out
Token out
Feature activation+0.000
a
Token a
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
are
Token are
Feature activation+7.087
"
Token "
Feature activation+4.616
extremely
Tokenextremely
Feature activation+6.655
low
Token low
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
said
Token said
Feature activation+0.000
bean
Token bean
Feature activation+0.392
to
Token to
Feature activation+0.000
reach
Token reach
Feature activation+0.000
that
Token that
Feature activation+0.000
threshold
Token threshold
Feature activation+3.094
is
Token is
Feature activation+4.397
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.078
whether
Token whether
Feature activation+0.000
each
Token each
Feature activation+0.000
band
Token band
Feature activation+0.000
plan
Token plan
Feature activation+0.000
for
Token for
Feature activation+0.000
Syria
Token Syria
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
odds
Token odds
Feature activation+4.256
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
rational
Token rational
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
chick
Token chick
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
pussy
Token pussy
Feature activation+0.000
chances
Token chances
Feature activation+4.249
are
Token are
Feature activation+7.011
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000

Top DFA by src position
MAX = 9.212

st
Token st
Feature activation+0.004
Top resid features:
a
Tokena
Feature activation+0.001
Top resid features:
pler
Tokenpler
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.034
Top resid features:
the
Token the
Feature activation+0.035
Top resid features:
odds
Token odds
Feature activation+9.212
Top resid features:
are
Token are
Feature activation+0.432
Top resid features:
fairly
Token fairly
Feature activation+0.084
Top resid features:
good
Token good
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
st
Token st
Feature activation+0.008
Top resid features:
a
Tokena
Feature activation+0.017
Top resid features:
pler
Tokenpler
Feature activation+0.213
Top resid features:
,
Token,
Feature activation+0.141
Top resid features:
the
Token the
Feature activation+0.074
Top resid features:
odds
Token odds
Feature activation+8.311
Top resid features:
are
Token are
Feature activation+0.350
Top resid features:
fairly
Token fairly
Feature activation+0.000
Top resid features:
good
Token good
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.012
Top resid features:
safe
Token safe
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.014
Top resid features:
that
Token that
Feature activation+0.033
Top resid features:
the
Token the
Feature activation+0.048
Top resid features:
chances
Token chances
Feature activation+7.481
Top resid features:
of
Token of
Feature activation+0.100
Top resid features:
an
Token an
Feature activation+0.061
Top resid features:
outbreak
Token outbreak
Feature activation+0.061
Top resid features:
in
Token in
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.051
Top resid features:
Hood
Token Hood
Feature activation+0.009
Top resid features:
said
Token said
Feature activation+0.043
Top resid features:
,
Token,
Feature activation+0.065
Top resid features:
the
Token the
Feature activation+0.118
Top resid features:
chances
Token chances
Feature activation+7.720
Top resid features:
of
Token of
Feature activation+0.050
Top resid features:
that
Token that
Feature activation+0.080
Top resid features:
seemed
Token seemed
Feature activation+0.019
Top resid features:
sl
Token sl
Feature activation+0.000
Top resid features:
immer
Tokenimmer
Feature activation+0.000
Top resid features:
chick
Token chick
Feature activation+0.166
Top resid features:
âĢ
TokenâĢ
Feature activation+0.020
Top resid features:
Ļ
TokenĻ
Feature activation+0.013
Top resid features:
s
Tokens
Feature activation+0.043
Top resid features:
pussy
Token pussy
Feature activation+0.042
Top resid features:
chances
Token chances
Feature activation+7.404
Top resid features:
are
Token are
Feature activation+0.465
Top resid features:
you
Token you
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:
d
Tokend
Feature activation+0.000
Top resid features:
Nature
Token Nature
Feature activation-0.022
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.052
Top resid features:
The
TokenThe
Feature activation+0.031
Top resid features:
odds
Token odds
Feature activation+7.478
Top resid features:
of
Token of
Feature activation+0.112
Top resid features:
the
Token the
Feature activation+0.051
Top resid features:
asteroid
Token asteroid
Feature activation+0.043
Top resid features:
hitting
Token hitting
Feature activation+0.005
Top resid features:
Earth
Token Earth
Feature activation+0.065
Top resid features:
circumstances
Token circumstances
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.056
Top resid features:
Ċ
TokenĊ
Feature activation+0.039
Top resid features:
Ċ
TokenĊ
Feature activation+0.083
Top resid features:
...
Token...
Feature activation+0.263
Top resid features:
odds
Token odds
Feature activation+6.919
Top resid features:
are
Token are
Feature activation+0.171
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
embarrassing
Token embarrassing
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.029
Top resid features:
.
Token.
Feature activation+0.044
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.064
Top resid features:
The
TokenThe
Feature activation+0.031
Top resid features:
odds
Token odds
Feature activation+7.355
Top resid features:
are
Token are
Feature activation+0.199
Top resid features:
good
Token good
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
More
Token More
Feature activation-0.003
Top resid features:
...
Token...
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.043
Top resid features:
Ċ
TokenĊ
Feature activation+0.062
Top resid features:
The
TokenThe
Feature activation+0.121
Top resid features:
odds
Token odds
Feature activation+6.875
Top resid features:
are
Token are
Feature activation+0.178
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
C
Token C
Feature activation+0.000
Top resid features:
ough
Tokenough
Feature activation+0.000
Top resid features:
lin
Tokenlin
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.015
Top resid features:
visiting
Token visiting
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
blog
Token blog
Feature activation-0.098
Top resid features:
,
Token,
Feature activation+0.066
Top resid features:
chances
Token chances
Feature activation+6.748
Top resid features:
are
Token are
Feature activation+0.559
Top resid features:
good
Token good
Feature activation+0.000
Top resid features:
you
Token you
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:
league
Token league
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.052
Top resid features:
Ċ
TokenĊ
Feature activation+0.049
Top resid features:
Ċ
TokenĊ
Feature activation+0.068
Top resid features:
The
TokenThe
Feature activation+0.072
Top resid features:
odds
Token odds
Feature activation+6.264
Top resid features:
are
Token are
Feature activation+0.182
Top resid features:
Toronto
Token Toronto
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
component
Token component
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
also
Token also
Feature activation+0.015
Top resid features:
(
Token (
Feature activation+0.114
Top resid features:
ch
Tokench
Feature activation+0.015
Top resid features:
ances
Tokenances
Feature activation+5.927
Top resid features:
are
Token are
Feature activation+0.183
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
you
Token you
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:
,
Token,
Feature activation+0.109
Top resid features:
Hood
Token Hood
Feature activation+0.004
Top resid features:
said
Token said
Feature activation+0.093
Top resid features:
,
Token,
Feature activation+0.097
Top resid features:
the
Token the
Feature activation+0.227
Top resid features:
chances
Token chances
Feature activation+5.933
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
seemed
Token seemed
Feature activation+0.000
Top resid features:
sl
Token sl
Feature activation+0.000
Top resid features:
immer
Tokenimmer
Feature activation+0.000
Top resid features:
operation
Token operation
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.083
Top resid features:
âĢ
Token âĢ
Feature activation+0.017
Top resid features:
ľ
Tokenľ
Feature activation+0.012
Top resid features:
the
Tokenthe
Feature activation+0.058
Top resid features:
likelihood
Token likelihood
Feature activation+6.074
Top resid features:
that
Token that
Feature activation+0.082
Top resid features:
he
Token he
Feature activation+0.015
Top resid features:
would
Token would
Feature activation+0.007
Top resid features:
have
Token have
Feature activation+0.006
Top resid features:
been
Token been
Feature activation+0.007
Top resid features:
component
Token component
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
also
Token also
Feature activation+0.007
Top resid features:
(
Token (
Feature activation+0.017
Top resid features:
ch
Tokench
Feature activation+0.003
Top resid features:
ances
Tokenances
Feature activation+5.966
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
you
Token you
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:
guaranteed
Token guaranteed
Feature activation-0.006
Top resid features:
salary
Token salary
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
and
Token and
Feature activation+0.040
Top resid features:
the
Token the
Feature activation+0.095
Top resid features:
chances
Token chances
Feature activation+5.211
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
hammer
Token hammer
Feature activation+0.000
Top resid features:
ing
Tokening
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.005
Top resid features:
safe
Token safe
Feature activation-0.008
Top resid features:
and
Token and
Feature activation+0.027
Top resid features:
that
Token that
Feature activation+0.029
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
chances
Token chances
Feature activation+4.791
Top resid features:
of
Token of
Feature activation+0.041
Top resid features:
an
Token an
Feature activation+0.030
Top resid features:
outbreak
Token outbreak
Feature activation+0.012
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
vill
Token vill
Feature activation-0.001
Top resid features:
ager
Tokenager
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.036
Top resid features:
and
Token and
Feature activation-0.019
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
probability
Token probability
Feature activation+5.252
Top resid features:
of
Token of
Feature activation+0.065
Top resid features:
any
Token any
Feature activation+0.037
Top resid features:
given
Token given
Feature activation+0.022
Top resid features:
band
Token band
Feature activation+0.002
Top resid features:
it
Tokenit
Feature activation+0.006
Top resid features:
plan
Token plan
Feature activation+0.004
Top resid features:
for
Token for
Feature activation+0.006
Top resid features:
Syria
Token Syria
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.049
Top resid features:
odds
Token odds
Feature activation+4.951
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
rational
Token rational
Feature activation+0.000
Top resid features:
U
Token U
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
chick
Token chick
Feature activation+0.030
Top resid features:
âĢ
TokenâĢ
Feature activation+0.016
Top resid features:
Ļ
TokenĻ
Feature activation+0.007
Top resid features:
s
Tokens
Feature activation+0.024
Top resid features:
pussy
Token pussy
Feature activation+0.017
Top resid features:
chances
Token chances
Feature activation+4.924
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
you
Token you
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:
d
Tokend
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.50

Head 1: 0.02

Head 2: 0.13

Head 3: 0.05

Head 4: 0.03

Head 5: 0.07

Head 6: 0.02

Head 7: 0.03

Head 8: 0.03

Head 9: 0.02

Head 10: 0.08

Head 11: 0.02

Positive logits

finder3.03

chance2.69

slim2.43

Luck2.42

icators2.26

Weaver2.25

Trem2.21

onder2.21

Fav2.19

Thorn2.16

dice2.10

oubted2.10

Composite2.06

Finder2.06

dread2.02

Lans2.02

Kinnikuman2.02

ilus1.99

龍契士1.98

Brett1.97

Negative logits

lyrics-2.86

hasht-2.54

appropriation-2.41

rant-2.37

code-2.22

uttered-2.20

monet-2.20

codes-2.15

nozzle-2.08

abbre-2.06

conduct-2.06

disclosures-2.06

coined-2.05

blogging-2.05

motivations-2.03

terminology-2.02

curtain-2.02

usage-2.01

Disclaimer-2.01

prescriptions-2.00

INTERVAL 8.014 - 8.905
CONTAINS 0.000%

a
Tokena
Feature activation+0.000
pler
Tokenpler
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
odds
Token odds
Feature activation+4.085
are
Token are
Feature activation+8.465
fairly
Token fairly
Feature activation+8.905
good
Token good
Feature activation+3.487
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
pler
Tokenpler
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
odds
Token odds
Feature activation+4.085
are
Token are
Feature activation+8.465
fairly
Token fairly
Feature activation+8.905
good
Token good
Feature activation+3.487
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
made
Token made
Feature activation+0.000

INTERVAL 7.124 - 8.014
CONTAINS 0.000%

INTERVAL 6.233 - 7.124
CONTAINS 0.001%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
pussy
Token pussy
Feature activation+0.000
chances
Token chances
Feature activation+4.249
are
Token are
Feature activation+7.011
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
be
Token be
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
odds
Token odds
Feature activation+1.971
are
Token are
Feature activation+6.463
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
embarrassing
Token embarrassing
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
are
Token are
Feature activation+7.087
"
Token "
Feature activation+4.616
extremely
Tokenextremely
Feature activation+6.655
low
Token low
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
odds
Token odds
Feature activation+1.625
are
Token are
Feature activation+6.449
good
Token good
Feature activation+3.825
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
goods
Token goods
Feature activation+0.119
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
asteroid
Token asteroid
Feature activation+0.000
hitting
Token hitting
Feature activation+0.000
Earth
Token Earth
Feature activation+1.964
were
Token were
Feature activation+6.580
first
Token first
Feature activation+4.167
estimated
Token estimated
Feature activation+0.000
at
Token at
Feature activation+0.724
one
Token one
Feature activation+0.247
in
Token in
Feature activation+0.000

INTERVAL 5.343 - 6.233
CONTAINS 0.001%

,
Token,
Feature activation+0.000
also
Token also
Feature activation+0.000
(
Token (
Feature activation+0.000
ch
Tokench
Feature activation+0.000
ances
Tokenances
Feature activation+5.200
are
Token are
Feature activation+5.433
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
visiting
Token visiting
Feature activation+0.000
the
Token the
Feature activation+0.000
blog
Token blog
Feature activation+0.000
,
Token,
Feature activation+0.000
chances
Token chances
Feature activation+2.987
are
Token are
Feature activation+6.131
good
Token good
Feature activation+1.461
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
odds
Token odds
Feature activation+0.622
are
Token are
Feature activation+5.535
Toronto
Token Toronto
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
possession
Token possession
Feature activation+0.000
,
Token,
Feature activation+0.000
Hood
Token Hood
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
chances
Token chances
Feature activation+5.414
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
seemed
Token seemed
Feature activation+7.054
sl
Token sl
Feature activation+2.982
immer
Tokenimmer
Feature activation+1.914

INTERVAL 4.452 - 5.343
CONTAINS 0.000%

component
Token component
Feature activation+0.000
,
Token,
Feature activation+0.000
also
Token also
Feature activation+0.000
(
Token (
Feature activation+0.000
ch
Tokench
Feature activation+0.000
ances
Tokenances
Feature activation+5.200
are
Token are
Feature activation+5.433
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
taken
Token taken
Feature activation+0.000
alive
Token alive
Feature activation+0.000
was
Token was
Feature activation+5.329
high
Token high
Feature activation+0.675
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
are
Token are
Feature activation+7.087
"
Token "
Feature activation+4.616
extremely
Tokenextremely
Feature activation+6.655
low
Token low
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
said
Token said
Feature activation+0.000
guaranteed
Token guaranteed
Feature activation+0.000
salary
Token salary
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
chances
Token chances
Feature activation+4.782
of
Token of
Feature activation+0.000
hammer
Token hammer
Feature activation+0.000
ing
Tokening
Feature activation+0.000
out
Token out
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 3.562 - 4.452
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
odds
Token odds
Feature activation+1.625
are
Token are
Feature activation+6.449
good
Token good
Feature activation+3.825
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
goods
Token goods
Feature activation+0.119
are
Token are
Feature activation+0.000
every
Token every
Feature activation+0.000
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
ances
Tokenances
Feature activation+3.097
are
Token are
Feature activation+3.728
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
like
Token like
Feature activation+0.000
fantasy
Token fantasy
Feature activation+0.000
sports
Token sports
Feature activation+0.000
st
Token st
Feature activation+0.000
a
Tokena
Feature activation+0.000
pler
Tokenpler
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
odds
Token odds
Feature activation+4.085
are
Token are
Feature activation+8.465
fairly
Token fairly
Feature activation+8.905
good
Token good
Feature activation+3.487
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
are
Token are
Feature activation+3.937
,
Token,
Feature activation+0.165
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
opinion
Token opinion
Feature activation+2.231
,
Token,
Feature activation+3.887
low
Token low
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Judge
Token Judge
Feature activation+0.000
Carm
Token Carm
Feature activation+0.000
ody
Tokenody
Feature activation+0.000
chick
Token chick
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
pussy
Token pussy
Feature activation+0.000
chances
Token chances
Feature activation+4.249
are
Token are
Feature activation+7.011
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000

INTERVAL 2.671 - 3.562
CONTAINS 0.001%

it
Token it
Feature activation+0.000
every
Token every
Feature activation+0.000
day
Token day
Feature activation+0.000
.
Token.
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
ances
Tokenances
Feature activation+3.097
are
Token are
Feature activation+3.728
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
like
Token like
Feature activation+0.000
fantasy
Token fantasy
Feature activation+0.000
th
Tokenth
Feature activation+0.000
bean
Token bean
Feature activation+0.392
to
Token to
Feature activation+0.000
reach
Token reach
Feature activation+0.000
that
Token that
Feature activation+0.000
threshold
Token threshold
Feature activation+3.094
is
Token is
Feature activation+4.397
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.078
whether
Token whether
Feature activation+0.000
each
Token each
Feature activation+0.000
at
Token at
Feature activation+0.000
work
Token work
Feature activation+0.000
.
Token.
Feature activation+0.000
Every
Token Every
Feature activation+0.000
chance
Token chance
Feature activation+0.000
we
Token we
Feature activation+2.902
get
Token get
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
document
Token document
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
chances
Token chances
Feature activation+5.414
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
seemed
Token seemed
Feature activation+7.054
sl
Token sl
Feature activation+2.982
immer
Tokenimmer
Feature activation+1.914
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
slowly
Token slowly
Feature activation+0.000
the
Token the
Feature activation+0.000
chances
Token chances
Feature activation+0.988
came
Token came
Feature activation+3.021
.
Token.
Feature activation+0.000
Steven
Token Steven
Feature activation+0.000
N
Token N
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 1.781 - 2.671
CONTAINS 0.002%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
chances
Token chances
Feature activation+1.894
of
Token of
Feature activation+0.000
us
Token us
Feature activation+0.000
reun
Token reun
Feature activation+0.000
iting
Tokeniting
Feature activation+0.000
Mary
Token Mary
Feature activation+0.000
away
Token away
Feature activation+0.000
-
Token -
Feature activation+0.000
and
Token and
Feature activation+0.000
how
Token how
Feature activation+0.000
likely
Token likely
Feature activation+0.000
it
Token it
Feature activation+2.375
is
Token is
Feature activation+0.699
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
support
Token support
Feature activation+0.000
operation
Token operation
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
likelihood
Token likelihood
Feature activation+1.815
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
2018
Token 2018
Feature activation+0.000
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Like
TokenLike
Feature activation+0.000
lihood
Tokenlihood
Feature activation+2.162
:
Token:
Feature activation+2.504
Good
Token Good
Feature activation+2.523
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Greens
Token Greens
Feature activation+0.000
circumstances
Token circumstances
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
odds
Token odds
Feature activation+1.971
are
Token are
Feature activation+6.463
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.000
embarrassing
Token embarrassing
Feature activation+0.000

INTERVAL 0.890 - 1.781
CONTAINS 0.004%

Bernie
Token Bernie
Feature activation+0.000
Sanders
Token Sanders
Feature activation+0.000
's
Token's
Feature activation+0.000
chance
Token chance
Feature activation+0.027
of
Token of
Feature activation+0.000
success
Token success
Feature activation+1.505
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
nomination
Token nomination
Feature activation+0.000
race
Token race
Feature activation+0.611
will
Token will
Feature activation+0.969
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.000
chances
Token chances
Feature activation+0.174
I
Token I
Feature activation+0.000
explained
Token explained
Feature activation+0.000
would
Token would
Feature activation+1.397
have
Token have
Feature activation+0.632
taken
Token taken
Feature activation+0.000
one
Token one
Feature activation+0.000
pass
Token pass
Feature activation+0.000
.
Token.
Feature activation+0.000
enemy
Token enemy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
every
Token every
Feature activation+0.000
chance
Token chance
Feature activation+0.000
he
Token he
Feature activation+1.371
gets
Token gets
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
MSM
Token MSM
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
goods
Token goods
Feature activation+0.119
are
Token are
Feature activation+0.000
odd
Token odd
Feature activation+1.041
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
could
Token could
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
year
Token year
Feature activation+0.000
or
Token or
Feature activation+0.000
two
Token two
Feature activation+1.330
is
Token is
Feature activation+1.067
actually
Token actually
Feature activation+1.030
lower
Token lower
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.000 - 0.890
CONTAINS 99.991%

time
Token time
Feature activation+0.000
and
Token and
Feature activation+0.000
once
Token once
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
jail
Token jail
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
began
Token began
Feature activation+0.000
to
Token to
Feature activation+0.000
experience
Token experience
Feature activation+0.000
will
Token will
Feature activation+0.000
not
Token not
Feature activation+0.000
seal
Token seal
Feature activation+0.000
properly
Token properly
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
old
Tokenold
Feature activation+0.000
dough
Token dough
Feature activation+0.000
over
Token over
Feature activation+0.000
)
Token)
Feature activation+0.000
-
Token -
Feature activation+0.000
China
Token China
Feature activation+0.000
has
Token has
Feature activation+0.000
invited
Token invited
Feature activation+0.000
British
Token British
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+0.000
Theresa
Token Theresa
Feature activation+0.000
May
Token May
Feature activation+0.000
to
Token to
Feature activation+0.000
into
Token into
Feature activation+0.000
a
Token a
Feature activation+0.000
$
Token $
Feature activation+0.000
10
Token10
Feature activation+0.000
million
Token million
Feature activation+0.000
loan
Token loan
Feature activation+0.000
guarantee
Token guarantee
Feature activation+0.000
approved
Token approved
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
U
Token U
Feature activation+0.000
people
Token people
Feature activation+0.000
behind
Token behind
Feature activation+0.000
this
Token this
Feature activation+0.000
idea
Token idea
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
many
Token many
Feature activation+0.000
overlapping
Token overlapping
Feature activation+0.000
collect
Token collect
Feature activation+0.000
ives
Tokenives
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 H9.0: (feature 21696)

TOP ACTIVATIONS
MAX = 6.323

then
Token then
Feature activation+0.000
where
Token where
Feature activation+0.000
do
Token do
Feature activation+0.000
you
Token you
Feature activation+0.000
draw
Token draw
Feature activation+4.817
the
Token the
Feature activation+6.323
line
Token line
Feature activation+2.985
?
Token?
Feature activation+0.000
What
Token What
Feature activation+0.000
could
Token could
Feature activation+0.000
God
Token God
Feature activation+0.000
Biology
Token Biology
Feature activation+0.000
professor
Token professor
Feature activation+0.000
Bret
Token Bret
Feature activation+0.000
Weinstein
Token Weinstein
Feature activation+0.000
drew
Token drew
Feature activation+0.615
the
Token the
Feature activation+5.241
ire
Token ire
Feature activation+0.000
of
Token of
Feature activation+0.000
campus
Token campus
Feature activation+0.000
inqu
Token inqu
Feature activation+0.000
is
Tokenis
Feature activation+0.000
decided
Token decided
Feature activation+0.000
I
Token I
Feature activation+0.000
needed
Token needed
Feature activation+0.000
to
Token to
Feature activation+0.000
draw
Token draw
Feature activation+1.019
some
Token some
Feature activation+5.205
diagrams
Token diagrams
Feature activation+0.000
to
Token to
Feature activation+0.934
help
Token help
Feature activation+0.184
me
Token me
Feature activation+0.585
get
Token get
Feature activation+0.000
David
Token David
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
drew
Token drew
Feature activation+0.723
other
Token other
Feature activation+4.963
details
Token details
Feature activation+1.161
from
Token from
Feature activation+0.000
his
Token his
Feature activation+0.000
visit
Token visit
Feature activation+0.000
to
Token to
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
elite
Token elite
Feature activation+0.000
universities
Token universities
Feature activation+0.000
have
Token have
Feature activation+0.000
drawn
Token drawn
Feature activation+0.368
the
Token the
Feature activation+4.856
most
Token most
Feature activation+3.216
talented
Token talented
Feature activation+0.000
people
Token people
Feature activation+0.124
from
Token from
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
where
Token where
Feature activation+0.000
do
Token do
Feature activation+0.000
you
Token you
Feature activation+0.000
draw
Token draw
Feature activation+4.817
the
Token the
Feature activation+6.323
line
Token line
Feature activation+2.985
?
Token?
Feature activation+0.000
What
Token What
Feature activation+0.000
could
Token could
Feature activation+0.000
hospitals
Token hospitals
Feature activation+0.000
,
Token,
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
draw
Token draw
Feature activation+1.747
a
Token a
Feature activation+4.658
broad
Token broad
Feature activation+3.563
sample
Token sample
Feature activation+0.498
of
Token of
Feature activation+0.000
infections
Token infections
Feature activation+0.021
.
Token.
Feature activation+0.000
entire
Token entire
Feature activation+0.000
world
Token world
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
drawing
Token drawing
Feature activation+0.239
a
Token a
Feature activation+3.954
broader
Token broader
Feature activation+0.565
circle
Token circle
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
player
Token player
Feature activation+0.000
to
Token to
Feature activation+0.000
draw
Token draw
Feature activation+0.721
a
Token a
Feature activation+3.662
line
Token line
Feature activation+0.322
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
,
Token,
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
draw
Token draw
Feature activation+1.747
a
Token a
Feature activation+4.658
broad
Token broad
Feature activation+3.563
sample
Token sample
Feature activation+0.498
of
Token of
Feature activation+0.000
infections
Token infections
Feature activation+0.021
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
elite
Token elite
Feature activation+0.000
universities
Token universities
Feature activation+0.000
have
Token have
Feature activation+0.000
drawn
Token drawn
Feature activation+0.368
the
Token the
Feature activation+4.856
most
Token most
Feature activation+3.216
talented
Token talented
Feature activation+0.000
people
Token people
Feature activation+0.124
from
Token from
Feature activation+0.000
all
Token all
Feature activation+0.000
over
Token over
Feature activation+0.000
-
Token-
Feature activation+0.000
game
Tokengame
Feature activation+0.000
purchases
Token purchases
Feature activation+0.000
and
Token and
Feature activation+0.000
drew
Token drew
Feature activation+0.000
a
Token a
Feature activation+3.134
comparison
Token comparison
Feature activation+0.000
to
Token to
Feature activation+0.000
gambling
Token gambling
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
person
Token person
Feature activation+1.722
to
Token to
Feature activation+3.119
draw
Token draw
Feature activation+0.394
a
Token a
Feature activation+2.257
line
Token line
Feature activation+0.956
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
before
Token before
Feature activation+0.000
drawing
Token drawing
Feature activation+0.197
back
Token back
Feature activation+1.785
a
Token a
Feature activation+2.822
few
Token few
Feature activation+3.113
hundred
Token hundred
Feature activation+2.213
yards
Token yards
Feature activation+0.000
to
Token to
Feature activation+0.095
proceed
Token proceed
Feature activation+0.056
with
Token with
Feature activation+0.842
a
Token a
Feature activation+0.000
million
Token million
Feature activation+0.000
triangles
Token triangles
Feature activation+0.000
,
Token,
Feature activation+0.000
draw
Token draw
Feature activation+0.466
a
Token a
Feature activation+3.098
million
Token million
Feature activation+1.450
diagrams
Token diagrams
Feature activation+0.124
,
Token,
Feature activation+0.337
and
Token and
Feature activation+0.031
he
Token he
Feature activation+0.000
some
Token some
Feature activation+0.000
degree
Token degree
Feature activation+0.000
of
Token of
Feature activation+0.000
modesty
Token modesty
Feature activation+0.000
draw
Token draw
Feature activation+0.000
an
Token an
Feature activation+3.096
association
Token association
Feature activation+0.165
from
Token from
Feature activation+0.000
nudity
Token nudity
Feature activation+0.000
to
Token to
Feature activation+0.000
sexuality
Token sexuality
Feature activation+0.000
where
Token where
Feature activation+0.000
do
Token do
Feature activation+0.000
you
Token you
Feature activation+0.000
draw
Token draw
Feature activation+4.817
the
Token the
Feature activation+6.323
line
Token line
Feature activation+2.985
?
Token?
Feature activation+0.000
What
Token What
Feature activation+0.000
could
Token could
Feature activation+0.000
God
Token God
Feature activation+0.000
command
Token command
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
before
Token before
Feature activation+0.000
drawing
Token drawing
Feature activation+0.197
back
Token back
Feature activation+1.785
a
Token a
Feature activation+2.822
few
Token few
Feature activation+3.113
hundred
Token hundred
Feature activation+2.213
yards
Token yards
Feature activation+0.000
to
Token to
Feature activation+0.095
proceed
Token proceed
Feature activation+0.056
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
person
Token person
Feature activation+1.722
to
Token to
Feature activation+3.119
draw
Token draw
Feature activation+0.394
a
Token a
Feature activation+2.257
line
Token line
Feature activation+0.956
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
winner
Token winner
Feature activation+0.000
.
Token.
Feature activation+0.000
any
Token any
Feature activation+0.099
specific
Token specific
Feature activation+0.134
person
Token person
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+1.450
simply
Token simply
Feature activation+2.234
wanted
Token wanted
Feature activation+0.285
to
Token to
Feature activation+0.356
make
Token make
Feature activation+0.350
them
Token them
Feature activation+0.052
.
Token.
Feature activation+0.000

Top DFA by src position
MAX = 7.067

,
Token,
Feature activation+0.025
Top resid features:
then
Token then
Feature activation+0.006
Top resid features:
where
Token where
Feature activation+0.043
Top resid features:
do
Token do
Feature activation+0.069
Top resid features:
you
Token you
Feature activation+0.051
Top resid features:
draw
Token draw
Feature activation+7.067
Top resid features:
the
Token the
Feature activation+0.199
Top resid features:
line
Token line
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
What
Token What
Feature activation+0.000
Top resid features:
could
Token could
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.074
Top resid features:
Biology
Token Biology
Feature activation-0.012
Top resid features:
professor
Token professor
Feature activation-0.018
Top resid features:
Bret
Token Bret
Feature activation+0.000
Top resid features:
Weinstein
Token Weinstein
Feature activation+0.025
Top resid features:
drew
Token drew
Feature activation+5.949
Top resid features:
the
Token the
Feature activation+0.190
Top resid features:
ire
Token ire
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
campus
Token campus
Feature activation+0.000
Top resid features:
inqu
Token inqu
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.020
Top resid features:
decided
Token decided
Feature activation+0.002
Top resid features:
I
Token I
Feature activation+0.019
Top resid features:
needed
Token needed
Feature activation+0.060
Top resid features:
to
Token to
Feature activation+0.018
Top resid features:
draw
Token draw
Feature activation+5.834
Top resid features:
some
Token some
Feature activation+0.080
Top resid features:
diagrams
Token diagrams
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
help
Token help
Feature activation+0.000
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.041
Top resid features:
David
Token David
Feature activation-0.025
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
however
Token however
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
drew
Token drew
Feature activation+5.853
Top resid features:
other
Token other
Feature activation+0.060
Top resid features:
details
Token details
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
visit
Token visit
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.571
Top resid features:
elite
Token elite
Feature activation+0.016
Top resid features:
universities
Token universities
Feature activation-0.034
Top resid features:
have
Token have
Feature activation+0.021
Top resid features:
drawn
Token drawn
Feature activation+5.620
Top resid features:
the
Token the
Feature activation+0.175
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
talented
Token talented
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.043
Top resid features:
then
Token then
Feature activation+0.021
Top resid features:
where
Token where
Feature activation+0.071
Top resid features:
do
Token do
Feature activation+0.040
Top resid features:
you
Token you
Feature activation+0.109
Top resid features:
draw
Token draw
Feature activation+5.497
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
line
Token line
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
What
Token What
Feature activation+0.000
Top resid features:
could
Token could
Feature activation+0.000
Top resid features:
183
Token 183
Feature activation+0.002
Top resid features:
hospitals
Token hospitals
Feature activation-0.010
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
enough
Token enough
Feature activation+0.024
Top resid features:
to
Token to
Feature activation+0.266
Top resid features:
draw
Token draw
Feature activation+5.175
Top resid features:
a
Token a
Feature activation+0.244
Top resid features:
broad
Token broad
Feature activation+0.000
Top resid features:
sample
Token sample
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
infections
Token infections
Feature activation+0.000
Top resid features:
my
Token my
Feature activation+0.021
Top resid features:
entire
Token entire
Feature activation-0.002
Top resid features:
world
Token world
Feature activation-0.018
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
and
Token and
Feature activation-0.009
Top resid features:
drawing
Token drawing
Feature activation+4.711
Top resid features:
a
Token a
Feature activation+0.231
Top resid features:
broader
Token broader
Feature activation+0.000
Top resid features:
circle
Token circle
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
other
Token other
Feature activation-0.050
Top resid features:
player
Token player
Feature activation+0.008
Top resid features:
to
Token to
Feature activation+0.148
Top resid features:
draw
Token draw
Feature activation+4.234
Top resid features:
a
Token a
Feature activation+0.129
Top resid features:
line
Token line
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:
183
Token 183
Feature activation-0.001
Top resid features:
hospitals
Token hospitals
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
enough
Token enough
Feature activation+0.014
Top resid features:
to
Token to
Feature activation+0.126
Top resid features:
draw
Token draw
Feature activation+3.376
Top resid features:
a
Token a
Feature activation+0.745
Top resid features:
broad
Token broad
Feature activation+0.354
Top resid features:
sample
Token sample
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
infections
Token infections
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.645
Top resid features:
elite
Token elite
Feature activation+0.018
Top resid features:
universities
Token universities
Feature activation-0.085
Top resid features:
have
Token have
Feature activation+0.030
Top resid features:
drawn
Token drawn
Feature activation+3.888
Top resid features:
the
Token the
Feature activation+0.194
Top resid features:
most
Token most
Feature activation+0.039
Top resid features:
talented
Token talented
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
game
Tokengame
Feature activation+0.267
Top resid features:
purchases
Token purchases
Feature activation+0.009
Top resid features:
and
Token and
Feature activation-0.032
Top resid features:
drew
Token drew
Feature activation+3.694
Top resid features:
a
Token a
Feature activation+0.171
Top resid features:
comparison
Token comparison
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
gambling
Token gambling
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
player
Token player
Feature activation-0.035
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
draw
Token draw
Feature activation+3.853
Top resid features:
a
Token a
Feature activation+0.041
Top resid features:
line
Token line
Feature activation+0.076
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
ista
Tokenista
Feature activation-0.037
Top resid features:
!
Token!
Feature activation-0.045
Top resid features:
âĢ
TokenâĢ
Feature activation-0.038
Top resid features:
Ŀ
TokenĿ
Feature activation+0.015
Top resid features:
before
Token before
Feature activation+0.011
Top resid features:
drawing
Token drawing
Feature activation+3.662
Top resid features:
back
Token back
Feature activation+0.422
Top resid features:
a
Token a
Feature activation+0.093
Top resid features:
few
Token few
Feature activation+0.030
Top resid features:
hundred
Token hundred
Feature activation+0.000
Top resid features:
yards
Token yards
Feature activation+0.000
Top resid features:
measure
Token measure
Feature activation-0.014
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
million
Token million
Feature activation-0.004
Top resid features:
triangles
Token triangles
Feature activation-0.053
Top resid features:
,
Token,
Feature activation+0.121
Top resid features:
draw
Token draw
Feature activation+3.923
Top resid features:
a
Token a
Feature activation+0.181
Top resid features:
million
Token million
Feature activation+0.000
Top resid features:
diagrams
Token diagrams
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
demand
Token demand
Feature activation+0.052
Top resid features:
some
Token some
Feature activation+0.007
Top resid features:
degree
Token degree
Feature activation-0.012
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
modesty
Token modesty
Feature activation-0.002
Top resid features:
draw
Token draw
Feature activation+3.797
Top resid features:
an
Token an
Feature activation+0.100
Top resid features:
association
Token association
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
nudity
Token nudity
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
then
Token then
Feature activation+0.009
Top resid features:
where
Token where
Feature activation+0.034
Top resid features:
do
Token do
Feature activation+0.086
Top resid features:
you
Token you
Feature activation+0.001
Top resid features:
draw
Token draw
Feature activation+3.258
Top resid features:
the
Token the
Feature activation+0.298
Top resid features:
line
Token line
Feature activation+0.203
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
What
Token What
Feature activation+0.000
Top resid features:
could
Token could
Feature activation+0.000
Top resid features:
ista
Tokenista
Feature activation-0.034
Top resid features:
!
Token!
Feature activation-0.042
Top resid features:
âĢ
TokenâĢ
Feature activation-0.038
Top resid features:
Ŀ
TokenĿ
Feature activation+0.039
Top resid features:
before
Token before
Feature activation+0.026
Top resid features:
drawing
Token drawing
Feature activation+3.445
Top resid features:
back
Token back
Feature activation+0.295
Top resid features:
a
Token a
Feature activation+0.048
Top resid features:
few
Token few
Feature activation+0.000
Top resid features:
hundred
Token hundred
Feature activation+0.000
Top resid features:
yards
Token yards
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
other
Token other
Feature activation+0.006
Top resid features:
player
Token player
Feature activation-0.005
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
draw
Token draw
Feature activation+1.507
Top resid features:
a
Token a
Feature activation+0.071
Top resid features:
line
Token line
Feature activation+0.532
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
thing
Token thing
Feature activation-0.001
Top resid features:
I
Token I
Feature activation-0.006
Top resid features:
knew
Token knew
Feature activation-0.023
Top resid features:
I
Token I
Feature activation-0.000
Top resid features:
was
Token was
Feature activation-0.000
Top resid features:
drawing
Token drawing
Feature activation+2.930
Top resid features:
them
Token them
Feature activation+0.111
Top resid features:
!
Token!
Feature activation+0.040
Top resid features:
These
TokenThese
Feature activation+0.037
Top resid features:
are
Token are
Feature activation+0.013
Top resid features:
not
Token not
Feature activation+0.019
Top resid features:

Decoder Weights Distribution

Head 0: 0.50

Head 1: 0.02

Head 2: 0.07

Head 3: 0.10

Head 4: 0.02

Head 5: 0.06

Head 6: 0.02

Head 7: 0.04

Head 8: 0.03

Head 9: 0.03

Head 10: 0.09

Head 11: 0.02

Positive logits

drawn4.41

drawing4.14

Drawing4.06

Draw3.80

draw3.70

Draw3.68

Drawn3.61

draw3.59

drew3.43

drawn3.26

draws3.16

SVG3.10

drawings3.07

ink2.99

inference2.81

shading2.71

cards2.69

sket2.67

strokes2.64

pens2.61

Negative logits

Marketplace-2.23

NX-2.14

stall-2.03

duc-2.02

delivery-2.01

Scient-2.01

Sell-2.00

rum-2.00

ourn-2.00

adish-2.00

Whe-1.99

rpm-1.99

store-1.99

Repair-1.99

aroma-1.98

Slov-1.97

ppelin-1.96

Chong-1.96

Farming-1.96

Lloyd-1.95

INTERVAL 5.691 - 6.323
CONTAINS 0.000%

then
Token then
Feature activation+0.000
where
Token where
Feature activation+0.000
do
Token do
Feature activation+0.000
you
Token you
Feature activation+0.000
draw
Token draw
Feature activation+4.817
the
Token the
Feature activation+6.323
line
Token line
Feature activation+2.985
?
Token?
Feature activation+0.000
What
Token What
Feature activation+0.000
could
Token could
Feature activation+0.000
God
Token God
Feature activation+0.000

INTERVAL 5.059 - 5.691
CONTAINS 0.000%

Biology
Token Biology
Feature activation+0.000
professor
Token professor
Feature activation+0.000
Bret
Token Bret
Feature activation+0.000
Weinstein
Token Weinstein
Feature activation+0.000
drew
Token drew
Feature activation+0.615
the
Token the
Feature activation+5.241
ire
Token ire
Feature activation+0.000
of
Token of
Feature activation+0.000
campus
Token campus
Feature activation+0.000
inqu
Token inqu
Feature activation+0.000
is
Tokenis
Feature activation+0.000
decided
Token decided
Feature activation+0.000
I
Token I
Feature activation+0.000
needed
Token needed
Feature activation+0.000
to
Token to
Feature activation+0.000
draw
Token draw
Feature activation+1.019
some
Token some
Feature activation+5.205
diagrams
Token diagrams
Feature activation+0.000
to
Token to
Feature activation+0.934
help
Token help
Feature activation+0.184
me
Token me
Feature activation+0.585
get
Token get
Feature activation+0.000

INTERVAL 4.426 - 5.059
CONTAINS 0.000%

David
Token David
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
drew
Token drew
Feature activation+0.723
other
Token other
Feature activation+4.963
details
Token details
Feature activation+1.161
from
Token from
Feature activation+0.000
his
Token his
Feature activation+0.000
visit
Token visit
Feature activation+0.000
to
Token to
Feature activation+0.000
hospitals
Token hospitals
Feature activation+0.000
,
Token,
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
draw
Token draw
Feature activation+1.747
a
Token a
Feature activation+4.658
broad
Token broad
Feature activation+3.563
sample
Token sample
Feature activation+0.498
of
Token of
Feature activation+0.000
infections
Token infections
Feature activation+0.021
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
elite
Token elite
Feature activation+0.000
universities
Token universities
Feature activation+0.000
have
Token have
Feature activation+0.000
drawn
Token drawn
Feature activation+0.368
the
Token the
Feature activation+4.856
most
Token most
Feature activation+3.216
talented
Token talented
Feature activation+0.000
people
Token people
Feature activation+0.124
from
Token from
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
where
Token where
Feature activation+0.000
do
Token do
Feature activation+0.000
you
Token you
Feature activation+0.000
draw
Token draw
Feature activation+4.817
the
Token the
Feature activation+6.323
line
Token line
Feature activation+2.985
?
Token?
Feature activation+0.000
What
Token What
Feature activation+0.000
could
Token could
Feature activation+0.000

INTERVAL 3.794 - 4.426
CONTAINS 0.000%

entire
Token entire
Feature activation+0.000
world
Token world
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
drawing
Token drawing
Feature activation+0.239
a
Token a
Feature activation+3.954
broader
Token broader
Feature activation+0.565
circle
Token circle
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000

INTERVAL 3.162 - 3.794
CONTAINS 0.000%

the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
player
Token player
Feature activation+0.000
to
Token to
Feature activation+0.000
draw
Token draw
Feature activation+0.721
a
Token a
Feature activation+3.662
line
Token line
Feature activation+0.322
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
,
Token,
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
draw
Token draw
Feature activation+1.747
a
Token a
Feature activation+4.658
broad
Token broad
Feature activation+3.563
sample
Token sample
Feature activation+0.498
of
Token of
Feature activation+0.000
infections
Token infections
Feature activation+0.021
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
elite
Token elite
Feature activation+0.000
universities
Token universities
Feature activation+0.000
have
Token have
Feature activation+0.000
drawn
Token drawn
Feature activation+0.368
the
Token the
Feature activation+4.856
most
Token most
Feature activation+3.216
talented
Token talented
Feature activation+0.000
people
Token people
Feature activation+0.124
from
Token from
Feature activation+0.000
all
Token all
Feature activation+0.000
over
Token over
Feature activation+0.000

INTERVAL 2.529 - 3.162
CONTAINS 0.001%

-
Token-
Feature activation+0.000
game
Tokengame
Feature activation+0.000
purchases
Token purchases
Feature activation+0.000
and
Token and
Feature activation+0.000
drew
Token drew
Feature activation+0.000
a
Token a
Feature activation+3.134
comparison
Token comparison
Feature activation+0.000
to
Token to
Feature activation+0.000
gambling
Token gambling
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
before
Token before
Feature activation+0.000
drawing
Token drawing
Feature activation+0.197
back
Token back
Feature activation+1.785
a
Token a
Feature activation+2.822
few
Token few
Feature activation+3.113
hundred
Token hundred
Feature activation+2.213
yards
Token yards
Feature activation+0.000
to
Token to
Feature activation+0.095
proceed
Token proceed
Feature activation+0.056
with
Token with
Feature activation+0.842
some
Token some
Feature activation+0.000
degree
Token degree
Feature activation+0.000
of
Token of
Feature activation+0.000
modesty
Token modesty
Feature activation+0.000
draw
Token draw
Feature activation+0.000
an
Token an
Feature activation+3.096
association
Token association
Feature activation+0.165
from
Token from
Feature activation+0.000
nudity
Token nudity
Feature activation+0.000
to
Token to
Feature activation+0.000
sexuality
Token sexuality
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
before
Token before
Feature activation+0.000
drawing
Token drawing
Feature activation+0.197
back
Token back
Feature activation+1.785
a
Token a
Feature activation+2.822
few
Token few
Feature activation+3.113
hundred
Token hundred
Feature activation+2.213
yards
Token yards
Feature activation+0.000
to
Token to
Feature activation+0.095
proceed
Token proceed
Feature activation+0.056
a
Token a
Feature activation+0.000
million
Token million
Feature activation+0.000
triangles
Token triangles
Feature activation+0.000
,
Token,
Feature activation+0.000
draw
Token draw
Feature activation+0.466
a
Token a
Feature activation+3.098
million
Token million
Feature activation+1.450
diagrams
Token diagrams
Feature activation+0.124
,
Token,
Feature activation+0.337
and
Token and
Feature activation+0.031
he
Token he
Feature activation+0.000

INTERVAL 1.897 - 2.529
CONTAINS 0.001%

the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
person
Token person
Feature activation+1.722
to
Token to
Feature activation+3.119
draw
Token draw
Feature activation+0.394
a
Token a
Feature activation+2.257
line
Token line
Feature activation+0.956
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
winner
Token winner
Feature activation+0.000
.
Token.
Feature activation+0.000
before
Token before
Feature activation+0.000
drawing
Token drawing
Feature activation+0.197
back
Token back
Feature activation+1.785
a
Token a
Feature activation+2.822
few
Token few
Feature activation+3.113
hundred
Token hundred
Feature activation+2.213
yards
Token yards
Feature activation+0.000
to
Token to
Feature activation+0.095
proceed
Token proceed
Feature activation+0.056
with
Token with
Feature activation+0.842
the
Token the
Feature activation+1.550
any
Token any
Feature activation+0.099
specific
Token specific
Feature activation+0.134
person
Token person
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+1.450
simply
Token simply
Feature activation+2.234
wanted
Token wanted
Feature activation+0.285
to
Token to
Feature activation+0.356
make
Token make
Feature activation+0.350
them
Token them
Feature activation+0.052
.
Token.
Feature activation+0.000
innovations
Token innovations
Feature activation+0.000
of
Token of
Feature activation+0.107
literal
Token literal
Feature activation+0.501
centuries
Token centuries
Feature activation+0.000
to
Token to
Feature activation+1.042
produce
Token produce
Feature activation+1.999
a
Token a
Feature activation+1.351
colossal
Token colossal
Feature activation+1.707
metal
Token metal
Feature activation+0.000
marvel
Token marvel
Feature activation+0.000
that
Token that
Feature activation+0.000
kind
Token kind
Feature activation+0.000
of
Token of
Feature activation+0.000
drawing
Token drawing
Feature activation+0.000
,
Token,
Feature activation+1.315
in
Token in
Feature activation+0.329
which
Token which
Feature activation+2.217
the
Token the
Feature activation+1.325
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
inner
Tokeninner
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 1.265 - 1.897
CONTAINS 0.003%

watch
Token watch
Feature activation+0.000
and
Token and
Feature activation+0.000
try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000
draw
Token draw
Feature activation+0.648
the
Token the
Feature activation+1.759
bird
Token bird
Feature activation+0.447
yourself
Token yourself
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
183
Token 183
Feature activation+0.000
hospitals
Token hospitals
Feature activation+0.000
,
Token,
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
draw
Token draw
Feature activation+1.747
a
Token a
Feature activation+4.658
broad
Token broad
Feature activation+3.563
sample
Token sample
Feature activation+0.498
of
Token of
Feature activation+0.000
infections
Token infections
Feature activation+0.021
19
Token 19
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
draws
Token draws
Feature activation+0.000
some
Token some
Feature activation+1.605
calming
Token calming
Feature activation+1.422
vib
Token vib
Feature activation+0.000
es
Tokenes
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
tap
Token tap
Feature activation+0.000
of
Token of
Feature activation+0.000
drawing
Token drawing
Feature activation+0.000
,
Token,
Feature activation+1.315
in
Token in
Feature activation+0.329
which
Token which
Feature activation+2.217
the
Token the
Feature activation+1.325
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
inner
Tokeninner
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
cutting
Token cutting
Feature activation+0.000
paper
Token paper
Feature activation+0.000
and
Token and
Feature activation+0.000
drawing
Token drawing
Feature activation+0.756
lines
Token lines
Feature activation+0.000
and
Token and
Feature activation+1.662
shapes
Token shapes
Feature activation+0.000
),
Token),
Feature activation+0.000
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
fared
Token fared
Feature activation+0.000

INTERVAL 0.632 - 1.265
CONTAINS 0.008%

,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
drew
Token drew
Feature activation+0.723
other
Token other
Feature activation+4.963
details
Token details
Feature activation+1.161
from
Token from
Feature activation+0.000
his
Token his
Feature activation+0.000
visit
Token visit
Feature activation+0.000
to
Token to
Feature activation+0.000
Mar
Token Mar
Feature activation+0.000
my
Token my
Feature activation+0.000
opinion
Token opinion
Feature activation+0.000
,
Token,
Feature activation+0.000
low
Token low
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Judge
Token Judge
Feature activation+0.966
Carm
Token Carm
Feature activation+0.000
ody
Tokenody
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
3
Token 3
Feature activation+0.000
,
Token,
Feature activation+0.000
100
Token100
Feature activation+0.000
mAh
TokenmAh
Feature activation+0.732
battery
Token battery
Feature activation+0.000
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
sweet
Token sweet
Feature activation+0.000
en
Tokenen
Feature activation+0.000
describe
Token describe
Feature activation+0.000
Furious
Token Furious
Feature activation+0.000
,
Token,
Feature activation+0.000
be
Token be
Feature activation+0.000
it
Token it
Feature activation+0.500
the
Token the
Feature activation+0.672
series
Token series
Feature activation+0.000
or
Token or
Feature activation+0.107
its
Token its
Feature activation+0.000
lead
Token lead
Feature activation+0.000
character
Token character
Feature activation+0.000
those
Token those
Feature activation+0.335
who
Token who
Feature activation+1.243
can
Token can
Feature activation+1.024
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.885
,
Token,
Feature activation+0.393
it
Token it
Feature activation+0.000
can
Token can
Feature activation+0.000
never
Token never
Feature activation+0.000
really
Token really
Feature activation+0.000

INTERVAL 0.000 - 0.632
CONTAINS 99.987%

underground
Token underground
Feature activation+0.000
ing
Tokening
Feature activation+0.000
will
Token will
Feature activation+0.000
take
Token take
Feature activation+0.000
off
Token off
Feature activation+0.000
anytime
Token anytime
Feature activation+0.000
soon
Token soon
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
not
Token not
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
fabric
Token fabric
Feature activation+0.000
bear
Token bear
Feature activation+0.000
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
cut
Token cut
Feature activation+0.000
out
Token out
Feature activation+0.000
and
Token and
Feature activation+0.000
attach
Token attach
Feature activation+0.000
CIA
Token CIA
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
dis
Token dis
Feature activation+0.000
semb
Tokensemb
Feature activation+0.000
ling
Tokenling
Feature activation+0.000
to
Token to
Feature activation+0.000
cover
Token cover
Feature activation+0.000
-
Token-
Feature activation+0.000
up
Tokenup
Feature activation+0.000
from
Token from
Feature activation+0.000
five
Token five
Feature activation+0.000
months
Token months
Feature activation+0.000
of
Token of
Feature activation+0.000
captivity
Token captivity
Feature activation+0.000
in
Token in
Feature activation+0.000
Afghanistan
Token Afghanistan
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
weekend
Token weekend
Feature activation+0.000
.
Token.
Feature activation+0.000
out
Token out
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
is
Token is
Feature activation+0.000
our
Token our
Feature activation+0.000
Anglo
Token Anglo
Feature activation+0.000
-
Token-
Feature activation+0.000
Pro
TokenPro
Feature activation+0.000
test
Tokentest
Feature activation+0.000
ant
Tokenant
Feature activation+0.000
heritage
Token heritage
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 H9.0: (feature 12375)

TOP ACTIVATIONS
MAX = 6.031

ľ
Tokenľ
Feature activation+0.000
Re
TokenRe
Feature activation+0.000
ality
Tokenality
Feature activation+0.440
still
Token still
Feature activation+5.961
hasn
Token hasn
Feature activation+0.000
't
Token't
Feature activation+6.031
set
Token set
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Re
TokenRe
Feature activation+0.000
ality
Tokenality
Feature activation+0.440
still
Token still
Feature activation+5.961
hasn
Token hasn
Feature activation+0.000
't
Token't
Feature activation+6.031
set
Token set
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
reality
Token reality
Feature activation+1.442
is
Token is
Feature activation+5.228
stark
Token stark
Feature activation+0.887
ly
Tokenly
Feature activation+5.519
different
Token different
Feature activation+0.530
.
Token.
Feature activation+0.000
Today
Token Today
Feature activation+0.000
,
Token,
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
years
Token years
Feature activation+0.000
later
Token later
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
reality
Token reality
Feature activation+1.442
is
Token is
Feature activation+5.228
stark
Token stark
Feature activation+0.887
ly
Tokenly
Feature activation+5.519
different
Token different
Feature activation+0.530
.
Token.
Feature activation+0.000
Today
Token Today
Feature activation+0.000
a
Token a
Feature activation+0.000
deputy
Token deputy
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
reality
Token reality
Feature activation+2.933
TV
Token TV
Feature activation+4.054
show
Token show
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
il
Tokenil
Feature activation+0.000
ocks
Tokenocks
Feature activation+0.000
Matrix
Token Matrix
Feature activation+0.000
as
Token as
Feature activation+0.000
reality
Token reality
Feature activation+1.965
is
Token is
Feature activation+3.872
scoff
Token scoff
Feature activation+0.000
ed
Tokened
Feature activation+0.000
at
Token at
Feature activation+0.654
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
ratings
Token ratings
Feature activation+0.000
-
Token-
Feature activation+0.000
grab
Tokengrab
Feature activation+0.000
bing
Tokenbing
Feature activation+0.000
reality
Token reality
Feature activation+3.743
show
Token show
Feature activation+1.330
"
Token "
Feature activation+1.238
Extreme
TokenExtreme
Feature activation+0.000
Make
Token Make
Feature activation+0.000
over
Tokenover
Feature activation+0.288
distance
Token distance
Feature activation+0.000
from
Token from
Feature activation+0.000
it
Token it
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
reality
Token reality
Feature activation+3.399
paints
Token paints
Feature activation+0.643
a
Token a
Feature activation+0.000
different
Token different
Feature activation+0.000
picture
Token picture
Feature activation+0.938
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
former
Token former
Feature activation+0.000
reality
Token reality
Feature activation+2.868
TV
Token TV
Feature activation+3.130
star
Token star
Feature activation+0.000
's
Token's
Feature activation+0.000
95
Token 95
Feature activation+0.000
percent
Token percent
Feature activation+0.000
pledge
Token pledge
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
deputy
Token deputy
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
reality
Token reality
Feature activation+2.933
TV
Token TV
Feature activation+4.054
show
Token show
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
former
Token former
Feature activation+0.000
reality
Token reality
Feature activation+2.868
TV
Token TV
Feature activation+3.130
star
Token star
Feature activation+0.000
's
Token's
Feature activation+0.000
95
Token 95
Feature activation+0.000
percent
Token percent
Feature activation+0.000
or
Tokenor
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
reality
Token reality
Feature activation+1.688
is
Token is
Feature activation+2.789
,
Token,
Feature activation+0.000
Jewish
Token Jewish
Feature activation+0.000
ethics
Token ethics
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+0.000
Of
Token Of
Feature activation+0.000
course
Token course
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
reality
Token reality
Feature activation+0.000
is
Token is
Feature activation+2.416
likely
Token likely
Feature activation+1.658
still
Token still
Feature activation+2.122
off
Token off
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
wake
Token wake
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
reality
Token reality
Feature activation+2.394
of
Token of
Feature activation+0.000
England
Token England
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
unbelievable
Token unbelievable
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
reality
Token reality
Feature activation+1.824
is
Token is
Feature activation+2.177
that
Token that
Feature activation+0.000
this
Token this
Feature activation+0.000
image
Token image
Feature activation+0.000
was
Token was
Feature activation+0.152
never
Token never
Feature activation+0.186
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
reality
Token reality
Feature activation+0.000
is
Token is
Feature activation+2.416
likely
Token likely
Feature activation+1.658
still
Token still
Feature activation+2.122
off
Token off
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
distance
Token distance
Feature activation+0.370
âĢĶ
Token âĢĶ
Feature activation+0.000
Gold
Token Gold
Feature activation+0.000
il
Tokenil
Feature activation+0.000
ocks
Tokenocks
Feature activation+0.000
Matrix
Token Matrix
Feature activation+0.000
as
Token as
Feature activation+0.000
reality
Token reality
Feature activation+1.965
is
Token is
Feature activation+3.872
scoff
Token scoff
Feature activation+0.000
ed
Tokened
Feature activation+0.000
at
Token at
Feature activation+0.654
,
Token,
Feature activation+0.000
harsh
Token harsh
Feature activation+0.000
reality
Token reality
Feature activation+0.629
of
Token of
Feature activation+0.000
college
Token college
Feature activation+0.000
sports
Token sports
Feature activation+0.000
is
Token is
Feature activation+1.898
that
Token that
Feature activation+0.000
football
Token football
Feature activation+0.000
and
Token and
Feature activation+0.000
men
Token men
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
seems
Token seems
Feature activation+0.000
unbelievable
Token unbelievable
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
reality
Token reality
Feature activation+1.824
is
Token is
Feature activation+2.177
that
Token that
Feature activation+0.000
this
Token this
Feature activation+0.000
image
Token image
Feature activation+0.000
was
Token was
Feature activation+0.152
somewhere
Token somewhere
Feature activation+0.000
else
Token else
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
reality
Token reality
Feature activation+0.559
is
Token is
Feature activation+1.774
that
Token that
Feature activation+0.000
any
Token any
Feature activation+0.000
really
Token really
Feature activation+0.000
clean
Token clean
Feature activation+0.000
government
Token government
Feature activation+0.000

Top DFA by src position
MAX = 7.462

Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
âĢ
TokenâĢ
Feature activation-0.007
Top resid features:
ľ
Tokenľ
Feature activation+0.010
Top resid features:
Re
TokenRe
Feature activation-0.014
Top resid features:
ality
Tokenality
Feature activation+7.235
Top resid features:
still
Token still
Feature activation+0.079
Top resid features:
hasn
Token hasn
Feature activation+0.473
Top resid features:
't
Token't
Feature activation-0.001
Top resid features:
set
Token set
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
âĢ
TokenâĢ
Feature activation+0.013
Top resid features:
ľ
Tokenľ
Feature activation+0.064
Top resid features:
Re
TokenRe
Feature activation-0.006
Top resid features:
ality
Tokenality
Feature activation+7.462
Top resid features:
still
Token still
Feature activation+0.097
Top resid features:
hasn
Token hasn
Feature activation+0.000
Top resid features:
't
Token't
Feature activation+0.000
Top resid features:
set
Token set
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
ven
Tokenven
Feature activation-0.003
Top resid features:
years
Token years
Feature activation-0.026
Top resid features:
later
Token later
Feature activation-0.056
Top resid features:
,
Token,
Feature activation+0.034
Top resid features:
the
Token the
Feature activation-0.021
Top resid features:
reality
Token reality
Feature activation+6.056
Top resid features:
is
Token is
Feature activation+0.639
Top resid features:
stark
Token stark
Feature activation+0.537
Top resid features:
ly
Tokenly
Feature activation+0.196
Top resid features:
different
Token different
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
ven
Tokenven
Feature activation+0.003
Top resid features:
years
Token years
Feature activation-0.049
Top resid features:
later
Token later
Feature activation-0.101
Top resid features:
,
Token,
Feature activation+0.128
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
reality
Token reality
Feature activation+6.470
Top resid features:
is
Token is
Feature activation+0.524
Top resid features:
stark
Token stark
Feature activation+0.000
Top resid features:
ly
Tokenly
Feature activation+0.000
Top resid features:
different
Token different
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.030
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
deputy
Token deputy
Feature activation-0.093
Top resid features:
for
Token for
Feature activation-0.046
Top resid features:
a
Token a
Feature activation-0.274
Top resid features:
reality
Token reality
Feature activation+5.643
Top resid features:
TV
Token TV
Feature activation+0.578
Top resid features:
show
Token show
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:
Gold
Token Gold
Feature activation-0.004
Top resid features:
il
Tokenil
Feature activation-0.006
Top resid features:
ocks
Tokenocks
Feature activation-0.015
Top resid features:
Matrix
Token Matrix
Feature activation+0.072
Top resid features:
as
Token as
Feature activation+0.144
Top resid features:
reality
Token reality
Feature activation+5.492
Top resid features:
is
Token is
Feature activation+0.194
Top resid features:
scoff
Token scoff
Feature activation+0.000
Top resid features:
ed
Tokened
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.047
Top resid features:
ratings
Token ratings
Feature activation+0.069
Top resid features:
-
Token-
Feature activation+0.007
Top resid features:
grab
Tokengrab
Feature activation-0.001
Top resid features:
bing
Tokenbing
Feature activation+0.075
Top resid features:
reality
Token reality
Feature activation+5.236
Top resid features:
show
Token show
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
Extreme
TokenExtreme
Feature activation+0.000
Top resid features:
Make
Token Make
Feature activation+0.000
Top resid features:
over
Tokenover
Feature activation+0.000
Top resid features:
distance
Token distance
Feature activation-0.002
Top resid features:
from
Token from
Feature activation+0.011
Top resid features:
it
Token it
Feature activation+0.011
Top resid features:
all
Token all
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.373
Top resid features:
reality
Token reality
Feature activation+4.214
Top resid features:
paints
Token paints
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
different
Token different
Feature activation+0.000
Top resid features:
picture
Token picture
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
The
TokenThe
Feature activation+0.016
Top resid features:
former
Token former
Feature activation-0.531
Top resid features:
reality
Token reality
Feature activation+4.501
Top resid features:
TV
Token TV
Feature activation+0.674
Top resid features:
star
Token star
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
95
Token 95
Feature activation+0.000
Top resid features:
percent
Token percent
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.002
Top resid features:
a
Token a
Feature activation+0.016
Top resid features:
deputy
Token deputy
Feature activation-0.036
Top resid features:
for
Token for
Feature activation-0.079
Top resid features:
a
Token a
Feature activation-0.230
Top resid features:
reality
Token reality
Feature activation+4.822
Top resid features:
TV
Token TV
Feature activation+0.000
Top resid features:
show
Token show
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:
Ŀ
TokenĿ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
The
TokenThe
Feature activation+0.018
Top resid features:
former
Token former
Feature activation-0.557
Top resid features:
reality
Token reality
Feature activation+4.875
Top resid features:
TV
Token TV
Feature activation+0.000
Top resid features:
star
Token star
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
95
Token 95
Feature activation+0.000
Top resid features:
percent
Token percent
Feature activation+0.000
Top resid features:
rig
Token rig
Feature activation-0.026
Top resid features:
or
Tokenor
Feature activation-0.013
Top resid features:
.
Token.
Feature activation+0.241
Top resid features:
But
Token But
Feature activation+0.153
Top resid features:
the
Token the
Feature activation+0.085
Top resid features:
reality
Token reality
Feature activation+3.887
Top resid features:
is
Token is
Feature activation+0.290
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Jewish
Token Jewish
Feature activation+0.000
Top resid features:
ethics
Token ethics
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Of
Token Of
Feature activation-0.009
Top resid features:
course
Token course
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.079
Top resid features:
that
Token that
Feature activation+0.062
Top resid features:
reality
Token reality
Feature activation+3.525
Top resid features:
is
Token is
Feature activation+0.274
Top resid features:
likely
Token likely
Feature activation+0.000
Top resid features:
still
Token still
Feature activation+0.000
Top resid features:
off
Token off
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
wake
Token wake
Feature activation+0.009
Top resid features:
of
Token of
Feature activation-0.012
Top resid features:
the
Token the
Feature activation+0.076
Top resid features:
reality
Token reality
Feature activation+3.962
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
England
Token England
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
seems
Token seems
Feature activation+0.007
Top resid features:
unbelievable
Token unbelievable
Feature activation+0.050
Top resid features:
.
Token.
Feature activation+0.153
Top resid features:
But
Token But
Feature activation+0.149
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
reality
Token reality
Feature activation+2.986
Top resid features:
is
Token is
Feature activation+0.338
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
image
Token image
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.033
Top resid features:
Of
Token Of
Feature activation-0.009
Top resid features:
course
Token course
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.069
Top resid features:
that
Token that
Feature activation+0.033
Top resid features:
reality
Token reality
Feature activation+2.949
Top resid features:
is
Token is
Feature activation+0.316
Top resid features:
likely
Token likely
Feature activation+0.125
Top resid features:
still
Token still
Feature activation+0.068
Top resid features:
off
Token off
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Gold
Token Gold
Feature activation-0.005
Top resid features:
il
Tokenil
Feature activation-0.004
Top resid features:
ocks
Tokenocks
Feature activation-0.023
Top resid features:
Matrix
Token Matrix
Feature activation+0.071
Top resid features:
as
Token as
Feature activation+0.290
Top resid features:
reality
Token reality
Feature activation+2.926
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
scoff
Token scoff
Feature activation+0.000
Top resid features:
ed
Tokened
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.066
Top resid features:
Ċ
TokenĊ
Feature activation+0.063
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
The
TokenThe
Feature activation+0.038
Top resid features:
harsh
Token harsh
Feature activation+0.069
Top resid features:
reality
Token reality
Feature activation+2.629
Top resid features:
of
Token of
Feature activation+0.219
Top resid features:
college
Token college
Feature activation-0.089
Top resid features:
sports
Token sports
Feature activation+0.008
Top resid features:
is
Token is
Feature activation+0.519
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
seems
Token seems
Feature activation-0.009
Top resid features:
unbelievable
Token unbelievable
Feature activation+0.030
Top resid features:
.
Token.
Feature activation+0.217
Top resid features:
But
Token But
Feature activation+0.138
Top resid features:
the
Token the
Feature activation+0.087
Top resid features:
reality
Token reality
Feature activation+2.444
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
image
Token image
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
turn
Token turn
Feature activation-0.011
Top resid features:
somewhere
Token somewhere
Feature activation-0.001
Top resid features:
else
Token else
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.261
Top resid features:
The
Token The
Feature activation+0.038
Top resid features:
reality
Token reality
Feature activation+3.734
Top resid features:
is
Token is
Feature activation+0.308
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
really
Token really
Feature activation+0.000
Top resid features:
clean
Token clean
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.49

Head 1: 0.02

Head 2: 0.09

Head 3: 0.07

Head 4: 0.03

Head 5: 0.05

Head 6: 0.02

Head 7: 0.04

Head 8: 0.04

Head 9: 0.02

Head 10: 0.11

Head 11: 0.02

Positive logits

TV2.73

TV2.72

levision2.57

tv2.56

tv2.53

Television2.44

telev2.42

television2.37

ITV2.34

WATCH2.31

TVs2.31

shakes2.26

BBC2.23

reality2.12

contestant2.11

enance2.10

Reality2.09

CBS2.08

viewers2.06

reality2.06

Negative logits

earch-2.24

percussion-2.20

onym-2.17

perf-2.14

Grateful-2.12

exc-2.10

explor-2.07

solicitation-2.04

inguished-2.03

Palo-2.02

fundraising-2.02

collecting-2.02

phil-2.01

DAC-2.01

arij-2.01

Ack-2.00

borrowing-1.98

eaves-1.97

IPO-1.96

akedown-1.95

INTERVAL 5.428 - 6.031
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Re
TokenRe
Feature activation+0.000
ality
Tokenality
Feature activation+0.440
still
Token still
Feature activation+5.961
hasn
Token hasn
Feature activation+0.000
't
Token't
Feature activation+6.031
set
Token set
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Re
TokenRe
Feature activation+0.000
ality
Tokenality
Feature activation+0.440
still
Token still
Feature activation+5.961
hasn
Token hasn
Feature activation+0.000
't
Token't
Feature activation+6.031
set
Token set
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
's
Token's
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
reality
Token reality
Feature activation+1.442
is
Token is
Feature activation+5.228
stark
Token stark
Feature activation+0.887
ly
Tokenly
Feature activation+5.519
different
Token different
Feature activation+0.530
.
Token.
Feature activation+0.000
Today
Token Today
Feature activation+0.000
,
Token,
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000

INTERVAL 4.825 - 5.428
CONTAINS 0.000%

years
Token years
Feature activation+0.000
later
Token later
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
reality
Token reality
Feature activation+1.442
is
Token is
Feature activation+5.228
stark
Token stark
Feature activation+0.887
ly
Tokenly
Feature activation+5.519
different
Token different
Feature activation+0.530
.
Token.
Feature activation+0.000
Today
Token Today
Feature activation+0.000

INTERVAL 4.222 - 4.825
CONTAINS 0.000%

INTERVAL 3.619 - 4.222
CONTAINS 0.000%

a
Token a
Feature activation+0.000
deputy
Token deputy
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
reality
Token reality
Feature activation+2.933
TV
Token TV
Feature activation+4.054
show
Token show
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
il
Tokenil
Feature activation+0.000
ocks
Tokenocks
Feature activation+0.000
Matrix
Token Matrix
Feature activation+0.000
as
Token as
Feature activation+0.000
reality
Token reality
Feature activation+1.965
is
Token is
Feature activation+3.872
scoff
Token scoff
Feature activation+0.000
ed
Tokened
Feature activation+0.000
at
Token at
Feature activation+0.654
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
ratings
Token ratings
Feature activation+0.000
-
Token-
Feature activation+0.000
grab
Tokengrab
Feature activation+0.000
bing
Tokenbing
Feature activation+0.000
reality
Token reality
Feature activation+3.743
show
Token show
Feature activation+1.330
"
Token "
Feature activation+1.238
Extreme
TokenExtreme
Feature activation+0.000
Make
Token Make
Feature activation+0.000
over
Tokenover
Feature activation+0.288

INTERVAL 3.016 - 3.619
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
former
Token former
Feature activation+0.000
reality
Token reality
Feature activation+2.868
TV
Token TV
Feature activation+3.130
star
Token star
Feature activation+0.000
's
Token's
Feature activation+0.000
95
Token 95
Feature activation+0.000
percent
Token percent
Feature activation+0.000
pledge
Token pledge
Feature activation+0.000
distance
Token distance
Feature activation+0.000
from
Token from
Feature activation+0.000
it
Token it
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
reality
Token reality
Feature activation+3.399
paints
Token paints
Feature activation+0.643
a
Token a
Feature activation+0.000
different
Token different
Feature activation+0.000
picture
Token picture
Feature activation+0.938
.
Token.
Feature activation+0.000

INTERVAL 2.413 - 3.016
CONTAINS 0.000%

Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
former
Token former
Feature activation+0.000
reality
Token reality
Feature activation+2.868
TV
Token TV
Feature activation+3.130
star
Token star
Feature activation+0.000
's
Token's
Feature activation+0.000
95
Token 95
Feature activation+0.000
percent
Token percent
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
deputy
Token deputy
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
reality
Token reality
Feature activation+2.933
TV
Token TV
Feature activation+4.054
show
Token show
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
or
Tokenor
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
reality
Token reality
Feature activation+1.688
is
Token is
Feature activation+2.789
,
Token,
Feature activation+0.000
Jewish
Token Jewish
Feature activation+0.000
ethics
Token ethics
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+0.000
Of
Token Of
Feature activation+0.000
course
Token course
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
reality
Token reality
Feature activation+0.000
is
Token is
Feature activation+2.416
likely
Token likely
Feature activation+1.658
still
Token still
Feature activation+2.122
off
Token off
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.809 - 2.413
CONTAINS 0.001%

Gold
Token Gold
Feature activation+0.000
il
Tokenil
Feature activation+0.000
ocks
Tokenocks
Feature activation+0.000
Matrix
Token Matrix
Feature activation+0.000
as
Token as
Feature activation+0.000
reality
Token reality
Feature activation+1.965
is
Token is
Feature activation+3.872
scoff
Token scoff
Feature activation+0.000
ed
Tokened
Feature activation+0.000
at
Token at
Feature activation+0.654
,
Token,
Feature activation+0.000
unbelievable
Token unbelievable
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
reality
Token reality
Feature activation+1.824
is
Token is
Feature activation+2.177
that
Token that
Feature activation+0.000
this
Token this
Feature activation+0.000
image
Token image
Feature activation+0.000
was
Token was
Feature activation+0.152
never
Token never
Feature activation+0.186
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
wake
Token wake
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
reality
Token reality
Feature activation+2.394
of
Token of
Feature activation+0.000
England
Token England
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
seems
Token seems
Feature activation+0.000
unbelievable
Token unbelievable
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
reality
Token reality
Feature activation+1.824
is
Token is
Feature activation+2.177
that
Token that
Feature activation+0.000
this
Token this
Feature activation+0.000
image
Token image
Feature activation+0.000
was
Token was
Feature activation+0.152
harsh
Token harsh
Feature activation+0.000
reality
Token reality
Feature activation+0.629
of
Token of
Feature activation+0.000
college
Token college
Feature activation+0.000
sports
Token sports
Feature activation+0.000
is
Token is
Feature activation+1.898
that
Token that
Feature activation+0.000
football
Token football
Feature activation+0.000
and
Token and
Feature activation+0.000
men
Token men
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 1.206 - 1.809
CONTAINS 0.002%

somewhere
Token somewhere
Feature activation+0.000
else
Token else
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
reality
Token reality
Feature activation+0.559
is
Token is
Feature activation+1.774
that
Token that
Feature activation+0.000
any
Token any
Feature activation+0.000
really
Token really
Feature activation+0.000
clean
Token clean
Feature activation+0.000
government
Token government
Feature activation+0.000
longer
Token longer
Feature activation+0.000
exist
Token exist
Feature activation+0.000
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+0.000
a
Token a
Feature activation+0.000
reality
Token reality
Feature activation+1.547
we
Token we
Feature activation+1.467
now
Token now
Feature activation+1.086
live
Token live
Feature activation+1.030
in
Token in
Feature activation+1.161
that
Token that
Feature activation+1.322
course
Token course
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
reality
Token reality
Feature activation+0.000
is
Token is
Feature activation+2.416
likely
Token likely
Feature activation+1.658
still
Token still
Feature activation+2.122
off
Token off
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
distance
Token distance
Feature activation+0.370
scoff
Token scoff
Feature activation+0.000
ed
Tokened
Feature activation+0.000
at
Token at
Feature activation+0.654
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
illusion
Token illusion
Feature activation+1.444
becomes
Token becomes
Feature activation+0.684
king
Token king
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
as
Token as
Feature activation+0.000
exist
Token exist
Feature activation+0.000
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+0.000
a
Token a
Feature activation+0.000
reality
Token reality
Feature activation+1.547
we
Token we
Feature activation+1.467
now
Token now
Feature activation+1.086
live
Token live
Feature activation+1.030
in
Token in
Feature activation+1.161
that
Token that
Feature activation+1.322
we
Token we
Feature activation+1.645

INTERVAL 0.603 - 1.206
CONTAINS 0.004%

The
Token The
Feature activation+0.000
truth
Token truth
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+0.716
good
Token good
Feature activation+0.000
enough
Token enough
Feature activation+0.000
for
Token for
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+1.161
that
Token that
Feature activation+1.322
we
Token we
Feature activation+1.645
take
Token take
Feature activation+0.693
for
Token for
Feature activation+0.000
granted
Token granted
Feature activation+0.734
).
Token).
Feature activation+0.000
More
Token More
Feature activation+0.000
than
Token than
Feature activation+0.000
half
Token half
Feature activation+0.000
of
Token of
Feature activation+0.000
horribly
Token horribly
Feature activation+0.000
circular
Token circular
Feature activation+0.000
reality
Token reality
Feature activation+1.299
means
Token means
Feature activation+0.000
that
Token that
Feature activation+0.230
it
Token it
Feature activation+0.945
is
Token is
Feature activation+0.464
only
Token only
Feature activation+0.000
destined
Token destined
Feature activation+0.000
to
Token to
Feature activation+0.643
get
Token get
Feature activation+0.369
break
Token break
Feature activation+0.000
neck
Tokenneck
Feature activation+0.000
pace
Token pace
Feature activation+0.000
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
reality
Token reality
Feature activation+0.865
has
Token has
Feature activation+1.709
public
Token public
Feature activation+0.000
safety
Token safety
Feature activation+0.000
implications
Token implications
Feature activation+0.000
:
Token:
Feature activation+0.000
to
Token to
Feature activation+0.643
get
Token get
Feature activation+0.369
worse
Token worse
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
it
Token it
Feature activation+0.638
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.382
very
Token very
Feature activation+0.000
pand
Token pand
Feature activation+0.000
ering
Tokenering
Feature activation+0.000

INTERVAL 0.000 - 0.603
CONTAINS 99.992%

speak
Token speak
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
real
Token real
Feature activation+0.000
cause
Token cause
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
'
Token '
Feature activation+0.000
L
TokenL
Feature activation+0.000
uther
Tokenuther
Feature activation+0.000
an
Tokenan
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
stealth
Token stealth
Feature activation+0.000
recruitment
Token recruitment
Feature activation+0.000
and
Token and
Feature activation+0.000
militar
Token militar
Feature activation+0.000
ization
Tokenization
Feature activation+0.000
of
Token of
Feature activation+0.000
young
Token young
Feature activation+0.000
minds
Token minds
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
both
Token both
Feature activation+0.000
sexist
Token sexist
Feature activation+0.000
and
Token and
Feature activation+0.000
ignorant
Token ignorant
Feature activation+0.000
by
Token by
Feature activation+0.000
those
Token those
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
chess
Token chess
Feature activation+0.000
community
Token community
Feature activation+0.000
emotional
Token emotional
Feature activation+0.000
beats
Token beats
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
emotional
Token emotional
Feature activation+0.000
beats
Token beats
Feature activation+0.000
often
Token often
Feature activation+0.000
portray
Token portray
Feature activation+0.000
emotional
Token emotional
Feature activation+0.000
sub
Token sub
Feature activation+0.000
text
Tokentext
Feature activation+0.000
Library
Token Library
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Oakland
Token Oakland
Feature activation+0.000
Tool
Token Tool
Feature activation+0.000
L
Token L
Feature activation+0.000
ending
Tokenending
Feature activation+0.000
Library
Token Library
Feature activation+0.000
currently
Token currently
Feature activation+0.000
offers
Token offers
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