H2.0 top features

Top feature 0 in H2.0: (feature 18511)

TOP ACTIVATIONS
MAX = 3.027

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
only
Token only
Feature activation+0.000
so
Token so
Feature activation+1.726
much
Token much
Feature activation+3.027
you
Token you
Feature activation+0.626
can
Token can
Feature activation+0.844
do
Token do
Feature activation+0.364
without
Token without
Feature activation+0.866
having
Token having
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+0.000
only
Token only
Feature activation+0.240
compelling
Token compelling
Feature activation+2.916
speeches
Token speeches
Feature activation+0.126
and
Token and
Feature activation+1.336
storylines
Token storylines
Feature activation+0.567
of
Token of
Feature activation+0.420
the
Token the
Feature activation+0.220
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
only
Token only
Feature activation+0.515
fitting
Token fitting
Feature activation+2.735
that
Token that
Feature activation+0.963
Hillary
Token Hillary
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
would
Token would
Feature activation+0.000
select
Token select
Feature activation+0.000
are
Token are
Feature activation+0.000
for
Token for
Feature activation+0.000
...
Token...
Feature activation+0.000
The
Token The
Feature activation+0.000
only
Token only
Feature activation+0.000
reason
Token reason
Feature activation+2.709
we
Token we
Feature activation+0.947
were
Token were
Feature activation+0.396
there
Token there
Feature activation+0.561
was
Token was
Feature activation+0.312
because
Token because
Feature activation+0.507
spectrum
Token spectrum
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
only
Token only
Feature activation+0.148
seems
Token seems
Feature activation+1.367
like
Token like
Feature activation+2.665
a
Token a
Feature activation+1.009
radical
Token radical
Feature activation+0.805
because
Token because
Feature activation+0.666
of
Token of
Feature activation+0.000
how
Token how
Feature activation+0.000
motive
Token motive
Feature activation+0.000
and
Token and
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
can
Token can
Feature activation+0.000
only
Token only
Feature activation+0.016
begin
Token begin
Feature activation+2.621
once
Token once
Feature activation+0.245
we
Token we
Feature activation+0.082
know
Token know
Feature activation+0.470
what
Token what
Feature activation+0.464
actually
Token actually
Feature activation+0.015
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
only
Token only
Feature activation+0.057
get
Token get
Feature activation+1.099
more
Token more
Feature activation+2.582
entertaining
Token entertaining
Feature activation+0.732
.
Token.
Feature activation+0.814
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
that
Token that
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
only
Token only
Feature activation+0.094
the
Token the
Feature activation+1.086
first
Token first
Feature activation+2.485
leg
Token leg
Feature activation+0.375
.
Token.
Feature activation+0.935
With
Token With
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
oters
Tokenoters
Feature activation+0.000
will
Token will
Feature activation+0.000
only
Token only
Feature activation+0.000
be
Token be
Feature activation+0.841
pushed
Token pushed
Feature activation+0.540
so
Token so
Feature activation+2.454
far
Token far
Feature activation+2.269
.
Token.
Feature activation+0.755
And
Token And
Feature activation+0.295
then
Token then
Feature activation+0.000
they
Token they
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.576
way
Token way
Feature activation+2.438
we
Token we
Feature activation+1.009
can
Token can
Feature activation+1.339
do
Token do
Feature activation+0.928
it
Token it
Feature activation+0.305
.
Token.
Feature activation+0.824
a
Token a
Feature activation+0.000
spot
Token spot
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
only
Token only
Feature activation+0.474
way
Token way
Feature activation+2.397
I
Token I
Feature activation+1.361
see
Token see
Feature activation+2.207
him
Token him
Feature activation+0.925
not
Token not
Feature activation+0.652
starting
Token starting
Feature activation+0.351
To
TokenTo
Feature activation+0.000
this
Token this
Feature activation+0.000
point
Token point
Feature activation+0.000
,
Token,
Feature activation+0.000
only
Token only
Feature activation+0.000
much
Token much
Feature activation+2.331
smaller
Token smaller
Feature activation+0.031
local
Token local
Feature activation+0.000
governments
Token governments
Feature activation+0.000
have
Token have
Feature activation+0.118
gone
Token gone
Feature activation+0.476
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
only
Token only
Feature activation+0.680
thing
Token thing
Feature activation+2.313
show
Token show
Feature activation+1.019
runners
Tokenrunners
Feature activation+0.562
Lisa
Token Lisa
Feature activation+0.639
Joy
Token Joy
Feature activation+0.236
and
Token and
Feature activation+0.436
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
death
Token death
Feature activation+0.000
is
Token is
Feature activation+0.000
my
Token my
Feature activation+0.000
only
Token only
Feature activation+0.617
true
Token true
Feature activation+2.285
revenge
Token revenge
Feature activation+0.413
,"
Token,"
Feature activation+0.341
Amanda
Token Amanda
Feature activation+0.230
(
Token (
Feature activation+0.000
Emily
TokenEmily
Feature activation+0.000
"
Token "
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.590
way
Token way
Feature activation+2.275
to
Token to
Feature activation+0.977
get
Token get
Feature activation+0.678
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
He
TokenHe
Feature activation+0.000
had
Token had
Feature activation+0.000
only
Token only
Feature activation+0.000
received
Token received
Feature activation+0.000
his
Token his
Feature activation+0.098
first
Token first
Feature activation+2.272
booking
Token booking
Feature activation+0.088
in
Token in
Feature activation+0.118
the
Token the
Feature activation+0.000
third
Token third
Feature activation+0.000
minute
Token minute
Feature activation+0.000
will
Token will
Feature activation+0.000
only
Token only
Feature activation+0.000
be
Token be
Feature activation+0.841
pushed
Token pushed
Feature activation+0.540
so
Token so
Feature activation+2.454
far
Token far
Feature activation+2.269
.
Token.
Feature activation+0.755
And
Token And
Feature activation+0.295
then
Token then
Feature activation+0.000
they
Token they
Feature activation+0.000
push
Token push
Feature activation+0.000
English
Token English
Feature activation+0.000
dub
Token dub
Feature activation+0.000
.
Token.
Feature activation+0.000
Only
Token Only
Feature activation+0.000
the
Token the
Feature activation+0.501
first
Token first
Feature activation+2.253
half
Token half
Feature activation+0.000
of
Token of
Feature activation+0.156
the
Token the
Feature activation+0.283
series
Token series
Feature activation+0.225
is
Token is
Feature activation+0.251
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
only
Token only
Feature activation+0.050
fallen
Token fallen
Feature activation+0.038
more
Token more
Feature activation+2.241
in
Token in
Feature activation+0.000
love
Token love
Feature activation+0.016
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
fastest
Token fastest
Feature activation+0.000
in
Token in
Feature activation+0.000
1968
Token 1968
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
only
Token only
Feature activation+0.227
remarkable
Token remarkable
Feature activation+2.230
thing
Token thing
Feature activation+1.537
about
Token about
Feature activation+1.263
those
Token those
Feature activation+0.250
outcomes
Token outcomes
Feature activation+0.055
is
Token is
Feature activation+0.166

Top DFA by src position
MAX = 3.658

but
Token but
Feature activation-0.014
Top resid features:
there
Token there
Feature activation+0.027
Top resid features:
âĢ
TokenâĢ
Feature activation-0.017
Top resid features:
Ļ
TokenĻ
Feature activation-0.007
Top resid features:
s
Tokens
Feature activation+0.040
Top resid features:
only
Token only
Feature activation+3.658
Top resid features:
so
Token so
Feature activation-0.094
Top resid features:
much
Token much
Feature activation+0.003
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
marriage
Token marriage
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ŀ
TokenĿ
Feature activation+0.022
Top resid features:
the
Token the
Feature activation-0.045
Top resid features:
only
Token only
Feature activation+3.413
Top resid features:
compelling
Token compelling
Feature activation+0.060
Top resid features:
speeches
Token speeches
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
storylines
Token storylines
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.020
Top resid features:
"
Token"
Feature activation+0.029
Top resid features:
It
TokenIt
Feature activation-0.072
Top resid features:
's
Token's
Feature activation-0.042
Top resid features:
only
Token only
Feature activation+3.384
Top resid features:
fitting
Token fitting
Feature activation+0.017
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
Hillary
Token Hillary
Feature activation+0.000
Top resid features:
Clinton
Token Clinton
Feature activation+0.000
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.001
Top resid features:
are
Token are
Feature activation-0.016
Top resid features:
for
Token for
Feature activation+0.011
Top resid features:
...
Token...
Feature activation-0.024
Top resid features:
The
Token The
Feature activation-0.026
Top resid features:
only
Token only
Feature activation+3.169
Top resid features:
reason
Token reason
Feature activation+0.068
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
sane
Token sane
Feature activation+0.021
Top resid features:
political
Token political
Feature activation+0.004
Top resid features:
spectrum
Token spectrum
Feature activation-0.009
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
He
Token He
Feature activation+0.023
Top resid features:
only
Token only
Feature activation+3.124
Top resid features:
seems
Token seems
Feature activation-0.007
Top resid features:
like
Token like
Feature activation+0.018
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
radical
Token radical
Feature activation+0.000
Top resid features:
because
Token because
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
motive
Token motive
Feature activation+0.012
Top resid features:
and
Token and
Feature activation-0.013
Top resid features:
opportunity
Token opportunity
Feature activation+0.039
Top resid features:
can
Token can
Feature activation-0.043
Top resid features:
only
Token only
Feature activation+3.268
Top resid features:
begin
Token begin
Feature activation+0.009
Top resid features:
once
Token once
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
know
Token know
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
stepping
Token stepping
Feature activation+0.009
Top resid features:
up
Token up
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
it
Token it
Feature activation+0.017
Top resid features:
will
Token will
Feature activation+0.001
Top resid features:
only
Token only
Feature activation+3.151
Top resid features:
get
Token get
Feature activation-0.056
Top resid features:
more
Token more
Feature activation+0.011
Top resid features:
entertaining
Token entertaining
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
calculus
Token calculus
Feature activation+0.013
Top resid features:
is
Token is
Feature activation-0.011
Top resid features:
that
Token that
Feature activation+0.060
Top resid features:
this
Token this
Feature activation+0.014
Top resid features:
is
Token is
Feature activation-0.060
Top resid features:
only
Token only
Feature activation+3.035
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
first
Token first
Feature activation-0.018
Top resid features:
leg
Token leg
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
With
Token With
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
"
Token "
Feature activation+0.058
Top resid features:
V
TokenV
Feature activation+0.015
Top resid features:
oters
Tokenoters
Feature activation+0.050
Top resid features:
will
Token will
Feature activation+0.030
Top resid features:
only
Token only
Feature activation+2.889
Top resid features:
be
Token be
Feature activation+0.009
Top resid features:
pushed
Token pushed
Feature activation-0.036
Top resid features:
so
Token so
Feature activation+0.038
Top resid features:
far
Token far
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
it
Token it
Feature activation-0.006
Top resid features:
's
Token's
Feature activation-0.027
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
only
Token only
Feature activation+3.039
Top resid features:
way
Token way
Feature activation+0.035
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.020
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
spot
Token spot
Feature activation-0.013
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
The
Token The
Feature activation-0.015
Top resid features:
only
Token only
Feature activation+2.903
Top resid features:
way
Token way
Feature activation+0.029
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
see
Token see
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.026
Top resid features:
To
TokenTo
Feature activation+0.032
Top resid features:
this
Token this
Feature activation+0.010
Top resid features:
point
Token point
Feature activation-0.011
Top resid features:
,
Token,
Feature activation-0.018
Top resid features:
only
Token only
Feature activation+2.961
Top resid features:
much
Token much
Feature activation+0.026
Top resid features:
smaller
Token smaller
Feature activation+0.000
Top resid features:
local
Token local
Feature activation+0.000
Top resid features:
governments
Token governments
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
details
Token details
Feature activation+0.012
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.021
Top resid features:
The
TokenThe
Feature activation-0.042
Top resid features:
only
Token only
Feature activation+2.818
Top resid features:
thing
Token thing
Feature activation+0.088
Top resid features:
show
Token show
Feature activation+0.000
Top resid features:
runners
Tokenrunners
Feature activation+0.000
Top resid features:
Lisa
Token Lisa
Feature activation+0.000
Top resid features:
Joy
Token Joy
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.017
Top resid features:
death
Token death
Feature activation+0.008
Top resid features:
is
Token is
Feature activation-0.049
Top resid features:
my
Token my
Feature activation+0.112
Top resid features:
only
Token only
Feature activation+2.794
Top resid features:
true
Token true
Feature activation+0.071
Top resid features:
revenge
Token revenge
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:
Amanda
Token Amanda
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
"
Token "
Feature activation+0.019
Top resid features:
It
TokenIt
Feature activation-0.009
Top resid features:
's
Token's
Feature activation-0.027
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
only
Token only
Feature activation+2.947
Top resid features:
way
Token way
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.017
Top resid features:
He
TokenHe
Feature activation+0.011
Top resid features:
had
Token had
Feature activation+0.006
Top resid features:
only
Token only
Feature activation+2.747
Top resid features:
received
Token received
Feature activation+0.016
Top resid features:
his
Token his
Feature activation+0.048
Top resid features:
first
Token first
Feature activation+0.028
Top resid features:
booking
Token booking
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
"
Token "
Feature activation+0.049
Top resid features:
V
TokenV
Feature activation+0.011
Top resid features:
oters
Tokenoters
Feature activation+0.039
Top resid features:
will
Token will
Feature activation+0.023
Top resid features:
only
Token only
Feature activation+2.521
Top resid features:
be
Token be
Feature activation+0.023
Top resid features:
pushed
Token pushed
Feature activation+0.079
Top resid features:
so
Token so
Feature activation+0.086
Top resid features:
far
Token far
Feature activation+0.035
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
or
Token or
Feature activation-0.008
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
English
Token English
Feature activation+0.033
Top resid features:
dub
Token dub
Feature activation+0.011
Top resid features:
.
Token.
Feature activation-0.028
Top resid features:
Only
Token Only
Feature activation+2.608
Top resid features:
the
Token the
Feature activation+0.083
Top resid features:
first
Token first
Feature activation+0.022
Top resid features:
half
Token half
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
),
Token),
Feature activation-0.007
Top resid features:
I
Token I
Feature activation+0.019
Top resid features:
âĢ
TokenâĢ
Feature activation-0.008
Top resid features:
Ļ
TokenĻ
Feature activation-0.000
Top resid features:
ve
Tokenve
Feature activation+0.010
Top resid features:
only
Token only
Feature activation+2.949
Top resid features:
fallen
Token fallen
Feature activation-0.179
Top resid features:
more
Token more
Feature activation+0.016
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
love
Token love
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Nixon
Token Nixon
Feature activation+0.004
Top resid features:
in
Token in
Feature activation+0.029
Top resid features:
1968
Token 1968
Feature activation-0.014
Top resid features:
.
Token.
Feature activation-0.063
Top resid features:
The
Token The
Feature activation-0.099
Top resid features:
only
Token only
Feature activation+2.874
Top resid features:
remarkable
Token remarkable
Feature activation+0.034
Top resid features:
thing
Token thing
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
outcomes
Token outcomes
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.38

Head 1: 0.02

Head 2: 0.03

Head 3: 0.11

Head 4: 0.13

Head 5: 0.06

Head 6: 0.05

Head 7: 0.02

Head 8: 0.06

Head 9: 0.05

Head 10: 0.06

Head 11: 0.02

Positive logits

Seah1.54

soType1.47

"$:/1.45

soever1.33

Hallow1.28

peas1.26

Marin1.23

Strawberry1.23

Blacks1.21

Rag1.16

Alabama1.16

FML1.16

Rebellion1.15

:(1.15

peanuts1.15

Beet1.14

nor1.14

Sec1.12

Revival1.11

Sponge1.11

Negative logits

enhagen-1.40

thumbnails-1.39

onduct-1.36

shaw-1.35

obal-1.33

icio-1.31

oine-1.30

hematic-1.30

endix-1.29

capacity-1.29

itus-1.29

ilings-1.28

posium-1.26

allery-1.26

untled-1.26

psey-1.26

vor-1.26

owship-1.25

atern-1.25

engu-1.25

INTERVAL 2.725 - 3.027
CONTAINS 0.000%

,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.240
compelling
Token compelling
Feature activation+2.916
speeches
Token speeches
Feature activation+0.126
and
Token and
Feature activation+1.336
storylines
Token storylines
Feature activation+0.567
of
Token of
Feature activation+0.420
the
Token the
Feature activation+0.220
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
only
Token only
Feature activation+0.515
fitting
Token fitting
Feature activation+2.735
that
Token that
Feature activation+0.963
Hillary
Token Hillary
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
would
Token would
Feature activation+0.000
select
Token select
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
only
Token only
Feature activation+0.000
so
Token so
Feature activation+1.726
much
Token much
Feature activation+3.027
you
Token you
Feature activation+0.626
can
Token can
Feature activation+0.844
do
Token do
Feature activation+0.364
without
Token without
Feature activation+0.866
having
Token having
Feature activation+0.000

INTERVAL 2.422 - 2.725
CONTAINS 0.001%

oters
Tokenoters
Feature activation+0.000
will
Token will
Feature activation+0.000
only
Token only
Feature activation+0.000
be
Token be
Feature activation+0.841
pushed
Token pushed
Feature activation+0.540
so
Token so
Feature activation+2.454
far
Token far
Feature activation+2.269
.
Token.
Feature activation+0.755
And
Token And
Feature activation+0.295
then
Token then
Feature activation+0.000
they
Token they
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.576
way
Token way
Feature activation+2.438
we
Token we
Feature activation+1.009
can
Token can
Feature activation+1.339
do
Token do
Feature activation+0.928
it
Token it
Feature activation+0.305
.
Token.
Feature activation+0.824
that
Token that
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
only
Token only
Feature activation+0.094
the
Token the
Feature activation+1.086
first
Token first
Feature activation+2.485
leg
Token leg
Feature activation+0.375
.
Token.
Feature activation+0.935
With
Token With
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
motive
Token motive
Feature activation+0.000
and
Token and
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
can
Token can
Feature activation+0.000
only
Token only
Feature activation+0.016
begin
Token begin
Feature activation+2.621
once
Token once
Feature activation+0.245
we
Token we
Feature activation+0.082
know
Token know
Feature activation+0.470
what
Token what
Feature activation+0.464
actually
Token actually
Feature activation+0.015
are
Token are
Feature activation+0.000
for
Token for
Feature activation+0.000
...
Token...
Feature activation+0.000
The
Token The
Feature activation+0.000
only
Token only
Feature activation+0.000
reason
Token reason
Feature activation+2.709
we
Token we
Feature activation+0.947
were
Token were
Feature activation+0.396
there
Token there
Feature activation+0.561
was
Token was
Feature activation+0.312
because
Token because
Feature activation+0.507

INTERVAL 2.119 - 2.422
CONTAINS 0.002%

English
Token English
Feature activation+0.000
dub
Token dub
Feature activation+0.000
.
Token.
Feature activation+0.000
Only
Token Only
Feature activation+0.000
the
Token the
Feature activation+0.501
first
Token first
Feature activation+2.253
half
Token half
Feature activation+0.000
of
Token of
Feature activation+0.156
the
Token the
Feature activation+0.283
series
Token series
Feature activation+0.225
is
Token is
Feature activation+0.251
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.086
reason
Token reason
Feature activation+2.204
we
Token we
Feature activation+0.660
know
Token know
Feature activation+0.752
of
Token of
Feature activation+0.562
her
Token her
Feature activation+0.019
actions
Token actions
Feature activation+0.183
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
only
Token only
Feature activation+0.474
way
Token way
Feature activation+2.397
I
Token I
Feature activation+1.361
see
Token see
Feature activation+2.207
him
Token him
Feature activation+0.925
not
Token not
Feature activation+0.652
starting
Token starting
Feature activation+0.351
in
Token in
Feature activation+0.000
Week
Token Week
Feature activation+0.000
in
Token in
Feature activation+0.000
1968
Token 1968
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
only
Token only
Feature activation+0.227
remarkable
Token remarkable
Feature activation+2.230
thing
Token thing
Feature activation+1.537
about
Token about
Feature activation+1.263
those
Token those
Feature activation+0.250
outcomes
Token outcomes
Feature activation+0.055
is
Token is
Feature activation+0.166
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
only
Token only
Feature activation+0.680
thing
Token thing
Feature activation+2.313
show
Token show
Feature activation+1.019
runners
Tokenrunners
Feature activation+0.562
Lisa
Token Lisa
Feature activation+0.639
Joy
Token Joy
Feature activation+0.236
and
Token and
Feature activation+0.436

INTERVAL 1.816 - 2.119
CONTAINS 0.004%

collector
Token collector
Feature activation+0.000
.
Token.
Feature activation+0.000
Now
Token Now
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.212
way
Token way
Feature activation+1.851
that
Token that
Feature activation+1.038
Has
Token Has
Feature activation+0.107
bro
Tokenbro
Feature activation+0.000
can
Token can
Feature activation+0.611
improve
Token improve
Feature activation+0.541
js
Tokenjs
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.171
sane
Token sane
Feature activation+1.331
way
Token way
Feature activation+1.959
to
Token to
Feature activation+0.730
handle
Token handle
Feature activation+0.003
a
Token a
Feature activation+0.163
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
,
Token,
Feature activation+0.000
Lopez
Token Lopez
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.253
big
Token big
Feature activation+1.848
man
Token man
Feature activation+0.995
in
Token in
Feature activation+0.602
the
Token the
Feature activation+0.129
NBA
Token NBA
Feature activation+0.000
to
Token to
Feature activation+0.000
as
Token as
Feature activation+0.000
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
only
Token only
Feature activation+0.094
difference
Token difference
Feature activation+2.099
is
Token is
Feature activation+1.238
that
Token that
Feature activation+1.406
they
Token they
Feature activation+0.430
live
Token live
Feature activation+0.227
better
Token better
Feature activation+0.750
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Perhaps
TokenPerhaps
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.209
thing
Token thing
Feature activation+1.900
missing
Token missing
Feature activation+0.961
from
Token from
Feature activation+0.764
the
Token the
Feature activation+0.000
list
Token list
Feature activation+0.000
below
Token below
Feature activation+0.000

INTERVAL 1.514 - 1.816
CONTAINS 0.006%

,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.101
other
Token other
Feature activation+0.642
candidate
Token candidate
Feature activation+0.065
still
Token still
Feature activation+1.587
in
Token in
Feature activation+0.291
the
Token the
Feature activation+0.055
Republican
Token Republican
Feature activation+0.000
race
Token race
Feature activation+0.000
,
Token,
Feature activation+0.161
muff
Token muff
Feature activation+0.000
ins
Tokenins
Feature activation+0.000
are
Token are
Feature activation+0.000
stirred
Token stirred
Feature activation+0.000
only
Token only
Feature activation+0.000
enough
Token enough
Feature activation+1.581
to
Token to
Feature activation+0.000
moist
Token moist
Feature activation+0.000
en
Tokenen
Feature activation+0.000
the
Token the
Feature activation+0.000
dry
Token dry
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
only
Token only
Feature activation+0.616
the
Token the
Feature activation+1.677
current
Token current
Feature activation+1.650
version
Token version
Feature activation+0.387
that
Token that
Feature activation+0.920
is
Token is
Feature activation+0.450
affected
Token affected
Feature activation+0.045
but
Token but
Feature activation+0.691
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
only
Token only
Feature activation+0.088
the
Token the
Feature activation+0.826
preseason
Token preseason
Feature activation+0.757
,
Token,
Feature activation+1.547
but
Token but
Feature activation+1.648
Johnson
Token Johnson
Feature activation+0.363
is
Token is
Feature activation+0.595
showing
Token showing
Feature activation+0.133
his
Token his
Feature activation+0.000
So
TokenSo
Feature activation+0.000
far
Token far
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.100
thing
Token thing
Feature activation+1.784
we
Token we
Feature activation+1.017
have
Token have
Feature activation+0.263
learned
Token learned
Feature activation+1.107
about
Token about
Feature activation+0.501
business
Token business
Feature activation+0.000

INTERVAL 1.211 - 1.514
CONTAINS 0.007%

can
Token can
Feature activation+0.000
only
Token only
Feature activation+0.081
imagine
Token imagine
Feature activation+2.200
the
Token the
Feature activation+0.898
stories
Token stories
Feature activation+0.730
generations
Token generations
Feature activation+1.257
of
Token of
Feature activation+0.050
fighters
Token fighters
Feature activation+0.000
from
Token from
Feature activation+0.000
special
Token special
Feature activation+0.000
units
Token units
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
only
Token only
Feature activation+0.241
goal
Token goal
Feature activation+1.310
is
Token is
Feature activation+1.657
I
Token I
Feature activation+1.248
want
Token want
Feature activation+1.250
the
Token the
Feature activation+0.954
overall
Token overall
Feature activation+0.734
tax
Token tax
Feature activation+0.000
burden
Token burden
Feature activation+0.000
.
Token.
Feature activation+0.000
Only
Token Only
Feature activation+0.003
specific
Token specific
Feature activation+0.777
sensory
Token sensory
Feature activation+0.294
detail
Token detail
Feature activation+0.764
:
Token:
Feature activation+1.386
action
Token action
Feature activation+0.349
,
Token,
Feature activation+0.227
smell
Token smell
Feature activation+0.000
,
Token,
Feature activation+0.000
taste
Token taste
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Lou
TokenLou
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
only
Token only
Feature activation+0.000
learned
Token learned
Feature activation+1.125
a
Token a
Feature activation+1.215
small
Token small
Feature activation+0.000
amount
Token amount
Feature activation+0.277
of
Token of
Feature activation+0.090
Latin
Token Latin
Feature activation+0.000
in
Token in
Feature activation+0.000
political
Token political
Feature activation+0.000
spectrum
Token spectrum
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
only
Token only
Feature activation+0.148
seems
Token seems
Feature activation+1.367
like
Token like
Feature activation+2.665
a
Token a
Feature activation+1.009
radical
Token radical
Feature activation+0.805
because
Token because
Feature activation+0.666
of
Token of
Feature activation+0.000

INTERVAL 0.908 - 1.211
CONTAINS 0.014%

of
Token of
Feature activation+0.000
fairy
Token fairy
Feature activation+0.000
tale
Token tale
Feature activation+0.000
only
Token only
Feature activation+0.186
Kissinger
Token Kissinger
Feature activation+0.000
could
Token could
Feature activation+1.060
find
Token find
Feature activation+0.369
happy
Token happy
Feature activation+0.003
.
Token.
Feature activation+0.610
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
only
Token only
Feature activation+0.000
there
Token there
Feature activation+0.616
,
Token,
Feature activation+1.177
you
Token you
Feature activation+1.095
are
Token are
Feature activation+0.443
only
Token only
Feature activation+0.378
in
Token in
Feature activation+0.824
the
Token the
Feature activation+0.620
,
Token,
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
acts
Token acts
Feature activation+0.000
are
Token are
Feature activation+0.000
only
Token only
Feature activation+0.000
appropriate
Token appropriate
Feature activation+0.953
for
Token for
Feature activation+0.229
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.140
are
Token are
Feature activation+0.000
complementary
Token complementary
Feature activation+0.000
The
Token The
Feature activation+0.000
only
Token only
Feature activation+0.210
things
Token things
Feature activation+1.944
we
Token we
Feature activation+1.106
can
Token can
Feature activation+1.363
get
Token get
Feature activation+0.946
here
Token here
Feature activation+0.408
in
Token in
Feature activation+0.000
Utah
Token Utah
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
few
Token few
Feature activation+0.000
years
Token years
Feature activation+0.000
has
Token has
Feature activation+0.000
only
Token only
Feature activation+0.000
deep
Token deep
Feature activation+1.127
ened
Tokenened
Feature activation+1.204
this
Token this
Feature activation+0.208
lack
Token lack
Feature activation+0.021
of
Token of
Feature activation+0.000
co
Token co
Feature activation+0.000

INTERVAL 0.605 - 0.908
CONTAINS 0.033%

current
Token current
Feature activation+1.650
version
Token version
Feature activation+0.387
that
Token that
Feature activation+0.920
is
Token is
Feature activation+0.450
affected
Token affected
Feature activation+0.045
but
Token but
Feature activation+0.691
,
Token,
Feature activation+0.057
given
Token given
Feature activation+0.000
that
Token that
Feature activation+0.000
prior
Token prior
Feature activation+0.000
releases
Token releases
Feature activation+0.000
only
Token only
Feature activation+0.148
seems
Token seems
Feature activation+1.367
like
Token like
Feature activation+2.665
a
Token a
Feature activation+1.009
radical
Token radical
Feature activation+0.805
because
Token because
Feature activation+0.666
of
Token of
Feature activation+0.000
how
Token how
Feature activation+0.000
far
Token far
Feature activation+0.000
to
Token to
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
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
only
Token only
Feature activation+0.692
one
Token one
Feature activation+0.419
of
Token of
Feature activation+0.899
the
Token the
Feature activation+0.601
four
Token four
Feature activation+0.000
times
Token times
Feature activation+0.000
but
Token but
Feature activation+0.000
only
Token only
Feature activation+0.000
wanted
Token wanted
Feature activation+0.819
to
Token to
Feature activation+0.526
give
Token give
Feature activation+0.255
ourselves
Token ourselves
Feature activation+0.638
the
Token the
Feature activation+0.313
best
Token best
Feature activation+0.606
opportunity
Token opportunity
Feature activation+0.000
of
Token of
Feature activation+0.000
competing
Token competing
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.274
state
Token state
Feature activation+0.000
that
Token that
Feature activation+1.042
has
Token has
Feature activation+0.143
already
Token already
Feature activation+0.871
passed
Token passed
Feature activation+0.161
legislation
Token legislation
Feature activation+0.358
opting
Token opting
Feature activation+0.102
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.303 - 0.605
CONTAINS 0.068%

in
Token in
Feature activation+0.000
nature
Token nature
Feature activation+0.000
and
Token and
Feature activation+0.000
only
Token only
Feature activation+0.000
require
Token require
Feature activation+0.000
a
Token a
Feature activation+0.490
tiny
Token tiny
Feature activation+0.000
poke
Token poke
Feature activation+0.000
for
Token for
Feature activation+0.000
me
Token me
Feature activation+0.000
to
Token to
Feature activation+0.000
Official
Token Official
Feature activation+0.000
Use
Token Use
Feature activation+0.000
Only
Token Only
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
and
Token and
Feature activation+0.381
emails
Token emails
Feature activation+0.000
as
Token as
Feature activation+0.356
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Attorney
TokenAttorney
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
only
Token only
Feature activation+0.000
difficult
Token difficult
Feature activation+1.917
because
Token because
Feature activation+0.337
most
Token most
Feature activation+1.092
r
Token r
Feature activation+0.000
pg
Tokenpg
Feature activation+0.000
advice
Token advice
Feature activation+0.452
for
Token for
Feature activation+0.000
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
funny
Token funny
Feature activation+0.000
,
Token,
Feature activation+0.468
but
Token but
Feature activation+0.182
allows
Token allows
Feature activation+0.000
your
Token your
Feature activation+0.000
friends
Token friends
Feature activation+0.000
to
Token to
Feature activation+0.000
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
only
Token only
Feature activation+0.000
thing
Token thing
Feature activation+0.730
to
Token to
Feature activation+0.427
do
Token do
Feature activation+0.400
in
Token in
Feature activation+0.098
Kentucky
Token Kentucky
Feature activation+0.000
just
Token just
Feature activation+0.092
began
Token began
Feature activation+0.149
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.303
CONTAINS 99.865%

10
Token 10
Feature activation+0.000
)
Token)
Feature activation+0.000
released
Token released
Feature activation+0.000
18
Token 18
Feature activation+0.000
September
Token September
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
:
Token:
Feature activation+0.000
3
Token 3
Feature activation+0.000
R
TokenR
Feature activation+0.000
V
TokenV
Feature activation+0.000
X
TokenX
Feature activation+0.000
the
Token the
Feature activation+0.000
party
Token party
Feature activation+0.000
from
Token from
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
president
Token president
Feature activation+0.000
has
Token has
Feature activation+0.000
tweeted
Token tweeted
Feature activation+0.000
his
Token his
Feature activation+0.000
support
Token support
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
infected
Token infected
Feature activation+0.000
machine
Token machine
Feature activation+0.000
also
Token also
Feature activation+0.000
used
Token used
Feature activation+0.000
Microsoft
Token Microsoft
Feature activation+0.000
's
Token's
Feature activation+0.000
NET
Token NET
Feature activation+0.000
SH
TokenSH
Feature activation+0.000
networking
Token networking
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
of
Token of
Feature activation+0.000
such
Token such
Feature activation+0.000
super
Token super
Feature activation+0.000
-
Token-
Feature activation+0.000
agers
Tokenagers
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
too
Token too
Feature activation+0.000
late
Token late
Feature activation+0.000
to
Token to
Feature activation+0.000
rescue
Token rescue
Feature activation+0.000
the
Token the
Feature activation+0.000
Yes
Token Yes
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H2.0: (feature 9353)

TOP ACTIVATIONS
MAX = 1.795

Super
TokenSuper
Feature activation+0.000
intendent
Tokenintendent
Feature activation+0.000
Alan
Token Alan
Feature activation+0.000
Sp
Token Sp
Feature activation+0.000
iers
Tokeniers
Feature activation+0.000
admit
Token admit
Feature activation+1.795
that
Token that
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
reg
Tokenreg
Feature activation+0.000
rett
Tokenrett
Feature activation+0.000
---
Token ---
Feature activation+0.000
I
TokenI
Feature activation+0.000
saw
Token saw
Feature activation+0.000
Bis
Token Bis
Feature activation+0.000
u
Tokenu
Feature activation+0.000
talking
Token talking
Feature activation+1.456
about
Token about
Feature activation+0.819
Soul
Token Soul
Feature activation+0.000
key
Tokenkey
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
facing
Token facing
Feature activation+0.000
your
Token your
Feature activation+0.000
chest
Token chest
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
see
Token see
Feature activation+0.000
Photos
Token Photos
Feature activation+1.392
B
Token B
Feature activation+0.000
and
Token and
Feature activation+0.000
C
Token C
Feature activation+0.000
.
Token.
Feature activation+0.000
Turn
Token Turn
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
M
TokenM
Feature activation+0.000
ourn
Tokenourn
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
watch
Token watch
Feature activation+0.000
as
Token as
Feature activation+1.231
the
Token the
Feature activation+0.000
funeral
Token funeral
Feature activation+0.185
procession
Token procession
Feature activation+0.135
moves
Token moves
Feature activation+0.302
through
Token through
Feature activation+0.000
en
Tokenen
Feature activation+0.000
zi
Tokenzi
Feature activation+0.000
stood
Token stood
Feature activation+0.000
and
Token and
Feature activation+0.000
watched
Token watched
Feature activation+0.000
as
Token as
Feature activation+1.146
flames
Token flames
Feature activation+0.241
shot
Token shot
Feature activation+0.598
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
roof
Token roof
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
good
Token good
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
saw
Token saw
Feature activation+0.000
pictures
Token pictures
Feature activation+1.120
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
hot
Token hot
Feature activation+0.000
dog
Token dog
Feature activation+0.000
and
Token and
Feature activation+0.000
January
Token January
Feature activation+0.000
Fed
Token Fed
Feature activation+0.000
officials
Token officials
Feature activation+0.000
had
Token had
Feature activation+0.000
watched
Token watched
Feature activation+0.000
as
Token as
Feature activation+1.107
market
Token market
Feature activation+0.000
turmoil
Token turmoil
Feature activation+0.000
stemming
Token stemming
Feature activation+0.000
from
Token from
Feature activation+0.000
economic
Token economic
Feature activation+0.000
Alternatively
Token Alternatively
Feature activation+0.000
,
Token,
Feature activation+0.000
watch
Token watch
Feature activation+0.000
the
Token the
Feature activation+0.000
technical
Token technical
Feature activation+0.143
overview
Token overview
Feature activation+1.060
presentation
Token presentation
Feature activation+0.850
that
Token that
Feature activation+0.153
I
Token I
Feature activation+0.499
recently
Token recently
Feature activation+0.000
gave
Token gave
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
seen
Token seen
Feature activation+0.000
have
Token have
Feature activation+1.049
been
Token been
Feature activation+0.890
about
Token about
Feature activation+1.059
1
Token 1
Feature activation+0.000
)
Token)
Feature activation+0.000
How
Token How
Feature activation+0.000
people
Token people
Feature activation+0.000
were
Token were
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
added
Token added
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
see
Token see
Feature activation+0.000
below
Token below
Feature activation+1.056
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
continue
Tokencontinue
Feature activation+0.193
reading
Token reading
Feature activation+0.000
the
Token the
Feature activation+0.000
pleasure
Token pleasure
Feature activation+0.000
of
Token of
Feature activation+0.000
watching
Token watching
Feature activation+0.000
him
Token him
Feature activation+0.000
as
Token as
Feature activation+1.052
an
Token an
Feature activation+0.000
assistant
Token assistant
Feature activation+0.000
coach
Token coach
Feature activation+0.000
and
Token and
Feature activation+0.000
defensive
Token defensive
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
seen
Token seen
Feature activation+0.000
have
Token have
Feature activation+1.049
been
Token been
Feature activation+0.890
about
Token about
Feature activation+1.059
1
Token 1
Feature activation+0.000
)
Token)
Feature activation+0.000
How
Token How
Feature activation+0.000
Fight
Token Fight
Feature activation+0.000
Pass
Token Pass
Feature activation+0.000
,
Token,
Feature activation+0.000
saw
Token saw
Feature activation+0.014
a
Token a
Feature activation+0.000
record
Token record
Feature activation+1.044
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
finishes
Token finishes
Feature activation+0.000
as
Token as
Feature activation+0.000
every
Token every
Feature activation+0.000
myself
Token myself
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
saw
Token saw
Feature activation+0.000
them
Token them
Feature activation+0.000
talking
Token talking
Feature activation+1.042
about
Token about
Feature activation+0.748
me
Token me
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
knew
Token knew
Feature activation+0.052
bug
Token bug
Feature activation+0.000
(
Token(
Feature activation+0.000
see
Tokensee
Feature activation+0.000
bugs
Token bugs
Feature activation+0.000
section
Token section
Feature activation+0.129
),
Token),
Feature activation+1.020
you
Token you
Feature activation+0.000
need
Token need
Feature activation+0.000
a
Token a
Feature activation+0.000
32
Token 32
Feature activation+0.000
bit
Tokenbit
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
is
Token is
Feature activation+0.000
seen
Token seen
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
challenge
Token challenge
Feature activation+1.013
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
serious
Token serious
Feature activation+0.000
,
Token,
Feature activation+0.000
magical
Token magical
Feature activation+0.000
emerged
Token emerged
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
watched
Token watched
Feature activation+0.000
as
Token as
Feature activation+1.010
deep
Token deep
Feature activation+0.000
_
Token_
Feature activation+0.000
orange
Tokenorange
Feature activation+0.000
dreamed
Token dreamed
Feature activation+0.211
up
Token up
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
some
Token some
Feature activation+0.000
,
Token,
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
envelop
Token envelop
Feature activation+1.003
es
Tokenes
Feature activation+0.000
addressed
Token addressed
Feature activation+0.406
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
American
Token American
Feature activation+0.000
Gal
TokenGal
Feature activation+0.000
bra
Tokenbra
Feature activation+0.000
ith
Tokenith
Feature activation+0.000
is
Token is
Feature activation+0.000
seen
Token seen
Feature activation+0.000
questioning
Token questioning
Feature activation+0.979
the
Token the
Feature activation+0.000
do
Token do
Feature activation+0.300
orman
Tokenorman
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
An
TokenAn
Feature activation+0.000
official
Token official
Feature activation+0.000
then
Token then
Feature activation+0.000
watches
Token watches
Feature activation+0.000
as
Token as
Feature activation+0.943
they
Token they
Feature activation+0.000
vote
Token vote
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 2.728

Ċ
TokenĊ
Feature activation-0.019
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
The
TokenThe
Feature activation-0.024
Top resid features:
incident
Token incident
Feature activation+0.021
Top resid features:
has
Token has
Feature activation+0.037
Top resid features:
seen
Token seen
Feature activation+2.728
Top resid features:
Chief
Token Chief
Feature activation-0.016
Top resid features:
Super
TokenSuper
Feature activation-0.003
Top resid features:
intendent
Tokenintendent
Feature activation-0.042
Top resid features:
Alan
Token Alan
Feature activation+0.012
Top resid features:
Sp
Token Sp
Feature activation-0.012
Top resid features:
od
Tokenod
Feature activation-0.015
Top resid features:
-
Token-
Feature activation-0.022
Top resid features:
war
Tokenwar
Feature activation-0.009
Top resid features:
---
Token ---
Feature activation-0.002
Top resid features:
I
TokenI
Feature activation+0.022
Top resid features:
saw
Token saw
Feature activation+2.119
Top resid features:
Bis
Token Bis
Feature activation-0.023
Top resid features:
u
Tokenu
Feature activation+0.092
Top resid features:
talking
Token talking
Feature activation+0.188
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
Soul
Token Soul
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.025
Top resid features:
facing
Token facing
Feature activation+0.021
Top resid features:
your
Token your
Feature activation+0.038
Top resid features:
chest
Token chest
Feature activation-0.023
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.136
Top resid features:
see
Token see
Feature activation+2.482
Top resid features:
Photos
Token Photos
Feature activation+0.020
Top resid features:
B
Token B
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
C
Token C
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.038
Top resid features:
Ċ
TokenĊ
Feature activation-0.029
Top resid features:
M
TokenM
Feature activation+0.007
Top resid features:
ourn
Tokenourn
Feature activation+0.013
Top resid features:
ers
Tokeners
Feature activation+0.075
Top resid features:
watch
Token watch
Feature activation+2.188
Top resid features:
as
Token as
Feature activation+0.031
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
funeral
Token funeral
Feature activation+0.000
Top resid features:
procession
Token procession
Feature activation+0.000
Top resid features:
moves
Token moves
Feature activation+0.000
Top resid features:
inc
Tokeninc
Feature activation-0.013
Top resid features:
en
Tokenen
Feature activation-0.017
Top resid features:
zi
Tokenzi
Feature activation-0.019
Top resid features:
stood
Token stood
Feature activation+0.139
Top resid features:
and
Token and
Feature activation+0.033
Top resid features:
watched
Token watched
Feature activation+1.800
Top resid features:
as
Token as
Feature activation+0.044
Top resid features:
flames
Token flames
Feature activation+0.000
Top resid features:
shot
Token shot
Feature activation+0.000
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
stupid
Token stupid
Feature activation+0.003
Top resid features:
ly
Tokenly
Feature activation-0.029
Top resid features:
good
Token good
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.039
Top resid features:
I
Token I
Feature activation-0.016
Top resid features:
saw
Token saw
Feature activation+1.888
Top resid features:
pictures
Token pictures
Feature activation+0.151
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
hot
Token hot
Feature activation+0.000
Top resid features:
dog
Token dog
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.022
Top resid features:
January
Token January
Feature activation-0.013
Top resid features:
Fed
Token Fed
Feature activation-0.025
Top resid features:
officials
Token officials
Feature activation-0.002
Top resid features:
had
Token had
Feature activation-0.008
Top resid features:
watched
Token watched
Feature activation+2.133
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
market
Token market
Feature activation+0.000
Top resid features:
turmoil
Token turmoil
Feature activation+0.000
Top resid features:
stemming
Token stemming
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.011
Top resid features:
FAQ
Token FAQ
Feature activation+0.012
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
Alternatively
Token Alternatively
Feature activation+0.023
Top resid features:
,
Token,
Feature activation-0.042
Top resid features:
watch
Token watch
Feature activation+1.749
Top resid features:
the
Token the
Feature activation+0.031
Top resid features:
technical
Token technical
Feature activation-0.102
Top resid features:
overview
Token overview
Feature activation+0.032
Top resid features:
presentation
Token presentation
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
discussions
Token discussions
Feature activation+0.041
Top resid features:
I
Token I
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.027
Top resid features:
Ļ
TokenĻ
Feature activation-0.006
Top resid features:
ve
Tokenve
Feature activation-0.022
Top resid features:
seen
Token seen
Feature activation+1.723
Top resid features:
have
Token have
Feature activation+0.041
Top resid features:
been
Token been
Feature activation-0.034
Top resid features:
about
Token about
Feature activation+0.135
Top resid features:
1
Token 1
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
ation
Tokenation
Feature activation-0.018
Top resid features:
has
Token has
Feature activation-0.019
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
added
Token added
Feature activation-0.036
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.065
Top resid features:
see
Token see
Feature activation+1.982
Top resid features:
below
Token below
Feature activation+0.043
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
continue
Tokencontinue
Feature activation+0.000
Top resid features:
I
Token I
Feature activation-0.013
Top resid features:
had
Token had
Feature activation+0.008
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
pleasure
Token pleasure
Feature activation+0.056
Top resid features:
of
Token of
Feature activation+0.027
Top resid features:
watching
Token watching
Feature activation+1.904
Top resid features:
him
Token him
Feature activation+0.060
Top resid features:
as
Token as
Feature activation-0.018
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
assistant
Token assistant
Feature activation+0.000
Top resid features:
coach
Token coach
Feature activation+0.000
Top resid features:
discussions
Token discussions
Feature activation+0.083
Top resid features:
I
Token I
Feature activation+0.006
Top resid features:
âĢ
TokenâĢ
Feature activation+0.017
Top resid features:
Ļ
TokenĻ
Feature activation-0.023
Top resid features:
ve
Tokenve
Feature activation-0.028
Top resid features:
seen
Token seen
Feature activation+1.899
Top resid features:
have
Token have
Feature activation-0.033
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
1
Token 1
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.021
Top resid features:
UFC
Token UFC
Feature activation-0.014
Top resid features:
Fight
Token Fight
Feature activation+0.005
Top resid features:
Pass
Token Pass
Feature activation+0.047
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
saw
Token saw
Feature activation+1.427
Top resid features:
a
Token a
Feature activation+0.154
Top resid features:
record
Token record
Feature activation+0.030
Top resid features:
number
Token number
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
finishes
Token finishes
Feature activation+0.000
Top resid features:
drink
Token drink
Feature activation+0.023
Top resid features:
for
Token for
Feature activation+0.021
Top resid features:
myself
Token myself
Feature activation+0.006
Top resid features:
.
Token.
Feature activation-0.062
Top resid features:
I
Token I
Feature activation-0.029
Top resid features:
saw
Token saw
Feature activation+1.629
Top resid features:
them
Token them
Feature activation+0.141
Top resid features:
talking
Token talking
Feature activation+0.174
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.013
Top resid features:
horrible
Token horrible
Feature activation+0.019
Top resid features:
bug
Token bug
Feature activation-0.050
Top resid features:
(
Token(
Feature activation+0.008
Top resid features:
see
Tokensee
Feature activation+2.019
Top resid features:
bugs
Token bugs
Feature activation-0.121
Top resid features:
section
Token section
Feature activation-0.019
Top resid features:
),
Token),
Feature activation+0.122
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
need
Token need
Feature activation+0.000
Top resid features:
political
Token political
Feature activation-0.010
Top resid features:
scene
Token scene
Feature activation+0.026
Top resid features:
,
Token,
Feature activation-0.028
Top resid features:
Thursday
Token Thursday
Feature activation+0.008
Top resid features:
is
Token is
Feature activation-0.042
Top resid features:
seen
Token seen
Feature activation+1.712
Top resid features:
as
Token as
Feature activation+0.131
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
challenge
Token challenge
Feature activation+0.054
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
something
Token something
Feature activation+0.016
Top resid features:
magical
Token magical
Feature activation-0.008
Top resid features:
emerged
Token emerged
Feature activation+0.014
Top resid features:
.
Token.
Feature activation-0.050
Top resid features:
I
Token I
Feature activation-0.041
Top resid features:
watched
Token watched
Feature activation+2.003
Top resid features:
as
Token as
Feature activation+0.028
Top resid features:
deep
Token deep
Feature activation+0.000
Top resid features:
_
Token_
Feature activation+0.000
Top resid features:
orange
Tokenorange
Feature activation+0.000
Top resid features:
dreamed
Token dreamed
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
For
TokenFor
Feature activation-0.001
Top resid features:
some
Token some
Feature activation+0.086
Top resid features:
,
Token,
Feature activation-0.160
Top resid features:
seeing
Token seeing
Feature activation+1.898
Top resid features:
envelop
Token envelop
Feature activation+0.030
Top resid features:
es
Tokenes
Feature activation+0.000
Top resid features:
addressed
Token addressed
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-0.008
Top resid features:
Gal
TokenGal
Feature activation-0.015
Top resid features:
bra
Tokenbra
Feature activation-0.003
Top resid features:
ith
Tokenith
Feature activation-0.023
Top resid features:
is
Token is
Feature activation-0.064
Top resid features:
seen
Token seen
Feature activation+1.677
Top resid features:
questioning
Token questioning
Feature activation+0.109
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
orman
Tokenorman
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.021
Top resid features:
Ċ
TokenĊ
Feature activation-0.022
Top resid features:
An
TokenAn
Feature activation-0.008
Top resid features:
official
Token official
Feature activation-0.049
Top resid features:
then
Token then
Feature activation-0.096
Top resid features:
watches
Token watches
Feature activation+2.126
Top resid features:
as
Token as
Feature activation-0.003
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
vote
Token vote
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.37

Head 1: 0.04

Head 2: 0.05

Head 3: 0.07

Head 4: 0.04

Head 5: 0.07

Head 6: 0.05

Head 7: 0.03

Head 8: 0.11

Head 9: 0.06

Head 10: 0.09

Head 11: 0.03

Positive logits

rouse1.51

bound1.39

don1.38

Hung1.35

NY1.32

hung1.31

seeking1.30

die1.29

sn1.28

alert1.26

scan1.25

sw1.23

wid1.21

Brit1.21

Nap1.20

NK1.18

aline1.17

enhagen1.17

sharing1.17

Sw1.15

Negative logits

WATCHED-1.69

constitu-1.61

destro-1.57

kefeller-1.57

resil-1.49

FANTASY-1.48

issance-1.47

GOODMAN-1.39

excuses-1.39

},"-1.36

ABOUT-1.36

̶-1.36

ディ-1.35

Franch-1.31

Horses-1.30

DRAG-1.28

INESS-1.28

フォ-1.27

aceutical-1.27

excuse-1.26

INTERVAL 1.615 - 1.795
CONTAINS 0.000%

Super
TokenSuper
Feature activation+0.000
intendent
Tokenintendent
Feature activation+0.000
Alan
Token Alan
Feature activation+0.000
Sp
Token Sp
Feature activation+0.000
iers
Tokeniers
Feature activation+0.000
admit
Token admit
Feature activation+1.795
that
Token that
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
reg
Tokenreg
Feature activation+0.000
rett
Tokenrett
Feature activation+0.000

INTERVAL 1.436 - 1.615
CONTAINS 0.000%

---
Token ---
Feature activation+0.000
I
TokenI
Feature activation+0.000
saw
Token saw
Feature activation+0.000
Bis
Token Bis
Feature activation+0.000
u
Tokenu
Feature activation+0.000
talking
Token talking
Feature activation+1.456
about
Token about
Feature activation+0.819
Soul
Token Soul
Feature activation+0.000
key
Tokenkey
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000

INTERVAL 1.256 - 1.436
CONTAINS 0.000%

facing
Token facing
Feature activation+0.000
your
Token your
Feature activation+0.000
chest
Token chest
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
see
Token see
Feature activation+0.000
Photos
Token Photos
Feature activation+1.392
B
Token B
Feature activation+0.000
and
Token and
Feature activation+0.000
C
Token C
Feature activation+0.000
.
Token.
Feature activation+0.000
Turn
Token Turn
Feature activation+0.000

INTERVAL 1.077 - 1.256
CONTAINS 0.000%

January
Token January
Feature activation+0.000
Fed
Token Fed
Feature activation+0.000
officials
Token officials
Feature activation+0.000
had
Token had
Feature activation+0.000
watched
Token watched
Feature activation+0.000
as
Token as
Feature activation+1.107
market
Token market
Feature activation+0.000
turmoil
Token turmoil
Feature activation+0.000
stemming
Token stemming
Feature activation+0.000
from
Token from
Feature activation+0.000
economic
Token economic
Feature activation+0.000
en
Tokenen
Feature activation+0.000
zi
Tokenzi
Feature activation+0.000
stood
Token stood
Feature activation+0.000
and
Token and
Feature activation+0.000
watched
Token watched
Feature activation+0.000
as
Token as
Feature activation+1.146
flames
Token flames
Feature activation+0.241
shot
Token shot
Feature activation+0.598
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
roof
Token roof
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
good
Token good
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
saw
Token saw
Feature activation+0.000
pictures
Token pictures
Feature activation+1.120
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
hot
Token hot
Feature activation+0.000
dog
Token dog
Feature activation+0.000
and
Token and
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
M
TokenM
Feature activation+0.000
ourn
Tokenourn
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
watch
Token watch
Feature activation+0.000
as
Token as
Feature activation+1.231
the
Token the
Feature activation+0.000
funeral
Token funeral
Feature activation+0.185
procession
Token procession
Feature activation+0.135
moves
Token moves
Feature activation+0.302
through
Token through
Feature activation+0.000

INTERVAL 0.897 - 1.077
CONTAINS 0.001%

magical
Token magical
Feature activation+0.000
emerged
Token emerged
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
watched
Token watched
Feature activation+0.000
as
Token as
Feature activation+1.010
deep
Token deep
Feature activation+0.000
_
Token_
Feature activation+0.000
orange
Tokenorange
Feature activation+0.000
dreamed
Token dreamed
Feature activation+0.211
up
Token up
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
seen
Token seen
Feature activation+0.000
have
Token have
Feature activation+1.049
been
Token been
Feature activation+0.890
about
Token about
Feature activation+1.059
1
Token 1
Feature activation+0.000
)
Token)
Feature activation+0.000
How
Token How
Feature activation+0.000
people
Token people
Feature activation+0.000
were
Token were
Feature activation+0.000
the
Token the
Feature activation+0.000
pleasure
Token pleasure
Feature activation+0.000
of
Token of
Feature activation+0.000
watching
Token watching
Feature activation+0.000
him
Token him
Feature activation+0.000
as
Token as
Feature activation+1.052
an
Token an
Feature activation+0.000
assistant
Token assistant
Feature activation+0.000
coach
Token coach
Feature activation+0.000
and
Token and
Feature activation+0.000
defensive
Token defensive
Feature activation+0.000
Thursday
Token Thursday
Feature activation+0.000
is
Token is
Feature activation+0.000
seen
Token seen
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
challenge
Token challenge
Feature activation+1.013
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
serious
Token serious
Feature activation+0.000
,
Token,
Feature activation+0.000
Alternatively
Token Alternatively
Feature activation+0.000
,
Token,
Feature activation+0.000
watch
Token watch
Feature activation+0.000
the
Token the
Feature activation+0.000
technical
Token technical
Feature activation+0.143
overview
Token overview
Feature activation+1.060
presentation
Token presentation
Feature activation+0.850
that
Token that
Feature activation+0.153
I
Token I
Feature activation+0.499
recently
Token recently
Feature activation+0.000
gave
Token gave
Feature activation+0.000

INTERVAL 0.718 - 0.897
CONTAINS 0.002%

visitation
Token visitation
Feature activation+0.000
(
Token (
Feature activation+0.000
see
Tokensee
Feature activation+0.000
comprehensive
Token comprehensive
Feature activation+0.000
tables
Token tables
Feature activation+0.000
),
Token),
Feature activation+0.842
though
Token though
Feature activation+0.061
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
wide
Token wide
Feature activation+0.000
I
TokenI
Feature activation+0.000
saw
Token saw
Feature activation+0.000
Bis
Token Bis
Feature activation+0.000
u
Tokenu
Feature activation+0.000
talking
Token talking
Feature activation+1.456
about
Token about
Feature activation+0.819
Soul
Token Soul
Feature activation+0.000
key
Tokenkey
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
stream
Token stream
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
saw
Token saw
Feature activation+0.000
them
Token them
Feature activation+0.000
talking
Token talking
Feature activation+1.042
about
Token about
Feature activation+0.748
me
Token me
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
knew
Token knew
Feature activation+0.052
what
Token what
Feature activation+0.000
now
Token now
Feature activation+0.000
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
those
Token those
Feature activation+0.000
policies
Token policies
Feature activation+0.770
spill
Token spill
Feature activation+0.322
out
Token out
Feature activation+0.000
to
Token to
Feature activation+0.000
affect
Token affect
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.000
watched
Token watched
Feature activation+0.000
as
Token as
Feature activation+0.820
Lock
Token Lock
Feature activation+0.000
ett
Tokenett
Feature activation+0.000
was
Token was
Feature activation+0.046
covered
Token covered
Feature activation+0.288
in
Token in
Feature activation+0.000

INTERVAL 0.538 - 0.718
CONTAINS 0.004%

the
Token the
Feature activation+0.000
Monitor
Token Monitor
Feature activation+0.052
's
Token's
Feature activation+0.000
main
Token main
Feature activation+0.365
gardening
Token gardening
Feature activation+0.000
page
Token page
Feature activation+0.599
and
Token and
Feature activation+0.000
our
Token our
Feature activation+0.000
lively
Token lively
Feature activation+0.000
gardening
Token gardening
Feature activation+0.000
blog
Token blog
Feature activation+0.000
Overwatch
Token Overwatch
Feature activation+0.000
.
Token.
Feature activation+0.000
Please
Token Please
Feature activation+0.000
see
Token see
Feature activation+0.000
the
Token the
Feature activation+0.000
instructions
Token instructions
Feature activation+0.608
page
Token page
Feature activation+0.370
for
Token for
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
why
Token why
Feature activation+0.000
this
Token this
Feature activation+0.000
another
Token another
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
seen
Token seen
Feature activation+0.000
holding
Token holding
Feature activation+0.549
up
Token up
Feature activation+0.000
a
Token a
Feature activation+0.000
protected
Token protected
Feature activation+0.000
spotted
Token spotted
Feature activation+0.000
eagle
Token eagle
Feature activation+0.000
.
Token.
Feature activation+0.000
[
Token [
Feature activation+0.000
I
TokenI
Feature activation+0.000
later
Token later
Feature activation+0.000
saw
Token saw
Feature activation+0.000
copies
Token copies
Feature activation+0.692
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
mail
Token mail
Feature activation+0.000
-
Token-
Feature activation+0.000
order
Tokenorder
Feature activation+0.000
that
Token that
Feature activation+0.000
saw
Token saw
Feature activation+0.000
the
Token the
Feature activation+0.000
secretive
Token secretive
Feature activation+0.137
company
Token company
Feature activation+0.000
embarrassed
Token embarrassed
Feature activation+0.543
when
Token when
Feature activation+0.000
important
Token important
Feature activation+0.000
trade
Token trade
Feature activation+0.000
secrets
Token secrets
Feature activation+0.000
were
Token were
Feature activation+0.000

INTERVAL 0.359 - 0.538
CONTAINS 0.007%

the
Token the
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
lawmaker
Token lawmaker
Feature activation+0.000
was
Token was
Feature activation+0.000
filmed
Token filmed
Feature activation+0.000
saying
Token saying
Feature activation+0.400
while
Token while
Feature activation+0.000
advocating
Token advocating
Feature activation+0.134
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
bill
Token bill
Feature activation+0.000
them
Token them
Feature activation+0.000
watching
Token watching
Feature activation+0.000
me
Token me
Feature activation+0.000
play
Token play
Feature activation+0.000
football
Token football
Feature activation+0.000
was
Token was
Feature activation+0.380
a
Token a
Feature activation+0.041
great
Token great
Feature activation+0.233
thing
Token thing
Feature activation+0.000
for
Token for
Feature activation+0.000
me
Token me
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
seen
Token seen
Feature activation+0.000
advertisements
Token advertisements
Feature activation+0.519
for
Token for
Feature activation+0.514
what
Token what
Feature activation+0.000
consumer
Token consumer
Feature activation+0.000
advocates
Token advocates
Feature activation+0.000
have
Token have
Feature activation+0.000
.
Token.
Feature activation+0.000
Please
Token Please
Feature activation+0.000
see
Token see
Feature activation+0.000
the
Token the
Feature activation+0.000
instructions
Token instructions
Feature activation+0.608
page
Token page
Feature activation+0.370
for
Token for
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
why
Token why
Feature activation+0.000
this
Token this
Feature activation+0.000
item
Token item
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
is
Token is
Feature activation+0.160
promising
Token promising
Feature activation+0.370
and
Token and
Feature activation+0.000
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000

INTERVAL 0.179 - 0.359
CONTAINS 0.018%

version
Token version
Feature activation+0.000
,
Token,
Feature activation+0.000
showing
Token showing
Feature activation+0.000
my
Token my
Feature activation+0.000
work
Token work
Feature activation+0.095
:
Token:
Feature activation+0.237
Juventus
Token Juventus
Feature activation+0.000
are
Token are
Feature activation+0.000
taking
Token taking
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
Hale
Token Hale
Feature activation+0.000
and
Token and
Feature activation+0.000
also
Token also
Feature activation+0.000
saw
Token saw
Feature activation+0.000
a
Token a
Feature activation+0.000
bag
Token bag
Feature activation+0.351
gie
Tokengie
Feature activation+0.038
of
Token of
Feature activation+0.000
methamphetamine
Token methamphetamine
Feature activation+0.000
and
Token and
Feature activation+0.000
numerous
Token numerous
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
never
Token never
Feature activation+0.000
seen
Token seen
Feature activation+0.000
transparency
Token transparency
Feature activation+0.215
be
Token be
Feature activation+0.000
more
Token more
Feature activation+0.000
important
Token important
Feature activation+0.000
and
Token and
Feature activation+0.000
have
Token have
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
we
Token we
Feature activation+0.000
are
Token are
Feature activation+0.000
seeing
Token seeing
Feature activation+0.000
women
Token women
Feature activation+0.000
fight
Token fight
Feature activation+0.216
back
Token back
Feature activation+0.000
against
Token against
Feature activation+0.000
unrealistic
Token unrealistic
Feature activation+0.000
body
Token body
Feature activation+0.000
expectations
Token expectations
Feature activation+0.000
,
Token,
Feature activation+0.027
I
Token I
Feature activation+0.521
have
Token have
Feature activation+0.245
a
Token a
Feature activation+0.000
better
Token better
Feature activation+0.000
knowledge
Token knowledge
Feature activation+0.219
of
Token of
Feature activation+0.000
that
Token that
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
time
Token time
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.000 - 0.179
CONTAINS 99.966%

took
Token took
Feature activation+0.000
place
Token place
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
press
Token press
Feature activation+0.000
conference
Token conference
Feature activation+0.000
in
Token in
Feature activation+0.000
Emer
Token Emer
Feature activation+0.000
y
Tokeny
Feature activation+0.000
ville
Tokenville
Feature activation+0.000
,
Token,
Feature activation+0.000
John
Token John
Feature activation+0.000
Qu
Token Qu
Feature activation+0.000
ill
Tokenill
Feature activation+0.000
igan
Tokenigan
Feature activation+0.000
because
Token because
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
seriousness
Token seriousness
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
charge
Token charge
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
will
Token will
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
prepared
Token prepared
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
ready
Token ready
Feature activation+0.000
,
Token,
Feature activation+0.000
writing
Token writing
Feature activation+0.000
this
Token this
Feature activation+0.000
article
Token article
Feature activation+0.000
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
saw
Token saw
Feature activation+0.000
two
Token two
Feature activation+0.000
posts
Token posts
Feature activation+0.000
on
Token on
Feature activation+0.000
my
Token my
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
fourth
Token fourth
Feature activation+0.000
firefighter
Token firefighter
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
Cuban
Token Cuban
Feature activation+0.000
é
Token é
Feature activation+0.000
m
Tokenm
Feature activation+0.000
igr
Tokenigr
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 2 in H2.0: (feature 17165)

TOP ACTIVATIONS
MAX = 1.768

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.351
nice
Token nice
Feature activation+1.768
being
Token being
Feature activation+0.808
able
Token able
Feature activation+0.302
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
something
Token something
Feature activation+0.115
âĢĶ
TokenâĢĶ
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
's
Token's
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.389
rather
Token rather
Feature activation+1.759
bit
Token bit
Feature activation+0.451
too
Token too
Feature activation+0.000
eager
Token eager
Feature activation+0.000
to
Token to
Feature activation+0.000
tell
Token tell
Feature activation+0.000
The
Token The
Feature activation+0.000
screen
Token screen
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.028
a
Token a
Feature activation+0.364
big
Token big
Feature activation+1.733
bit
Token bit
Feature activation+0.597
map
Tokenmap
Feature activation+0.000
,
Token,
Feature activation+0.677
and
Token and
Feature activation+0.104
all
Token all
Feature activation+0.000
Court
Token Court
Feature activation+0.000
has
Token has
Feature activation+0.000
just
Token just
Feature activation+0.110
issued
Token issued
Feature activation+0.186
its
Token its
Feature activation+0.028
long
Token long
Feature activation+1.636
-
Token-
Feature activation+0.000
awaited
Tokenawaited
Feature activation+0.725
judgment
Token judgment
Feature activation+0.000
in
Token in
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
Just
TokenJust
Feature activation+0.295
a
Token a
Feature activation+0.034
couple
Token couple
Feature activation+1.629
of
Token of
Feature activation+0.188
months
Token months
Feature activation+0.000
into
Token into
Feature activation+0.000
hiking
Token hiking
Feature activation+0.000
season
Token season
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Iss
TokenIss
Feature activation+0.000
a
Tokena
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.467
plain
Token plain
Feature activation+1.621
wrong
Token wrong
Feature activation+0.137
to
Token to
Feature activation+0.000
assume
Token assume
Feature activation+0.000
American
Token American
Feature activation+0.000
would
Token would
Feature activation+0.066
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.154
another
Token another
Feature activation+1.455
embarrassment
Token embarrassment
Feature activation+0.189
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
owner
Token owner
Feature activation+0.000
who
Token who
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
just
Token just
Feature activation+0.000
this
Token this
Feature activation+0.000
long
Token long
Feature activation+1.395
building
Token building
Feature activation+0.000
with
Token with
Feature activation+0.150
a
Token a
Feature activation+0.000
bunch
Token bunch
Feature activation+0.000
of
Token of
Feature activation+0.000
practices
Token practices
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
just
Tokenjust
Feature activation+0.051
like
Token like
Feature activation+0.000
good
Token good
Feature activation+0.095
old
Token old
Feature activation+1.372
-
Token -
Feature activation+0.100
w
Tokenw
Feature activation+0.000
in
Token in
Feature activation+0.000
Perl
Token Perl
Feature activation+0.000
.
Token.
Feature activation+0.044
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
just
Token just
Feature activation+0.124
very
Token very
Feature activation+1.359
,
Token,
Feature activation+0.606
very
Token very
Feature activation+1.003
frightening
Token frightening
Feature activation+0.145
."
Token."
Feature activation+0.049
Ċ
TokenĊ
Feature activation+0.000
realize
Token realize
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.134
a
Token a
Feature activation+0.462
little
Token little
Feature activation+1.358
slice
Token slice
Feature activation+0.007
of
Token of
Feature activation+0.086
high
Token high
Feature activation+0.000
fantasy
Token fantasy
Feature activation+0.000
and
Token and
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Just
TokenJust
Feature activation+0.000
days
Token days
Feature activation+0.000
ago
Token ago
Feature activation+1.340
,
Token,
Feature activation+0.186
Indian
Token Indian
Feature activation+0.000
Air
Token Air
Feature activation+0.017
Force
Token Force
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
say
Token say
Feature activation+0.000
it
Token it
Feature activation+0.019
?
Token?
Feature activation+0.000
Just
Token Just
Feature activation+0.426
âĢ¦
TokenâĢ¦
Feature activation+1.116
happier
Token happier
Feature activation+1.312
.
Token.
Feature activation+0.991
Now
Token Now
Feature activation+1.034
losing
Token losing
Feature activation+0.000
all
Token all
Feature activation+0.000
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
form
Token form
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
couple
Token couple
Feature activation+1.287
of
Token of
Feature activation+0.014
feet
Token feet
Feature activation+0.000
above
Token above
Feature activation+0.020
a
Token a
Feature activation+0.000
rock
Token rock
Feature activation+0.000
ship
Tokenship
Feature activation+0.000
Cache
TokenCache
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.427
an
Token an
Feature activation+0.760
interface
Token interface
Feature activation+1.266
to
Token to
Feature activation+0.000
handle
Token handle
Feature activation+0.000
caching
Token caching
Feature activation+0.000
.
Token.
Feature activation+0.324
Ċ
TokenĊ
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
seizures
Token seizures
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.065
plain
Token plain
Feature activation+1.259
stress
Token stress
Feature activation+0.000
,
Token,
Feature activation+0.639
no
Token no
Feature activation+0.369
rest
Token rest
Feature activation+0.093
,
Token,
Feature activation+0.163
.
Token.
Feature activation+0.000
Ha
Token Ha
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
kidding
Token kidding
Feature activation+0.000
!
Token!
Feature activation+1.223
There
Token There
Feature activation+0.195
was
Token was
Feature activation+0.622
no
Token no
Feature activation+0.279
stored
Token stored
Feature activation+0.000
procedure
Token procedure
Feature activation+0.000
the
Token the
Feature activation+0.000
bedroom
Token bedroom
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
say
Token say
Feature activation+0.963
,
Token,
Feature activation+1.212
"
Token "
Feature activation+0.508
OK
TokenOK
Feature activation+0.269
Kindle
Token Kindle
Feature activation+0.000
,
Token,
Feature activation+0.065
bring
Token bring
Feature activation+0.000
These
Token These
Feature activation+0.000
devices
Token devices
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.294
a
Token a
Feature activation+0.548
few
Token few
Feature activation+1.196
examples
Token examples
Feature activation+0.028
of
Token of
Feature activation+0.029
what
Token what
Feature activation+0.000
is
Token is
Feature activation+0.000
known
Token known
Feature activation+0.000
the
Token the
Feature activation+0.000
Cleveland
Token Cleveland
Feature activation+0.000
offense
Token offense
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+1.183
more
Token more
Feature activation+0.470
push
Token push
Feature activation+0.000
,
Token,
Feature activation+0.313
with
Token with
Feature activation+0.213
the
Token the
Feature activation+0.000

Top DFA by src position
MAX = 2.289

.
Token.
Feature activation-0.024
Top resid features:
Ċ
TokenĊ
Feature activation-0.051
Top resid features:
Ċ
TokenĊ
Feature activation-0.058
Top resid features:
It
TokenIt
Feature activation-0.165
Top resid features:
is
Token is
Feature activation-0.064
Top resid features:
just
Token just
Feature activation+2.289
Top resid features:
nice
Token nice
Feature activation-0.045
Top resid features:
being
Token being
Feature activation+0.000
Top resid features:
able
Token able
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
those
Token those
Feature activation-0.015
Top resid features:
things
Token things
Feature activation-0.035
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation-0.039
Top resid features:
he
Tokenhe
Feature activation-0.079
Top resid features:
's
Token's
Feature activation-0.106
Top resid features:
just
Token just
Feature activation+2.159
Top resid features:
a
Token a
Feature activation+0.055
Top resid features:
rather
Token rather
Feature activation-0.080
Top resid features:
bit
Token bit
Feature activation+0.000
Top resid features:
too
Token too
Feature activation+0.000
Top resid features:
eager
Token eager
Feature activation+0.000
Top resid features:
around
Token around
Feature activation-0.032
Top resid features:
.
Token.
Feature activation-0.023
Top resid features:
The
Token The
Feature activation-0.014
Top resid features:
screen
Token screen
Feature activation-0.134
Top resid features:
is
Token is
Feature activation-0.065
Top resid features:
just
Token just
Feature activation+2.243
Top resid features:
a
Token a
Feature activation+0.036
Top resid features:
big
Token big
Feature activation-0.101
Top resid features:
bit
Token bit
Feature activation+0.000
Top resid features:
map
Tokenmap
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation-0.029
Top resid features:
Minnesota
Token Minnesota
Feature activation-0.055
Top resid features:
Supreme
Token Supreme
Feature activation-0.049
Top resid features:
Court
Token Court
Feature activation-0.048
Top resid features:
has
Token has
Feature activation-0.084
Top resid features:
just
Token just
Feature activation+1.850
Top resid features:
issued
Token issued
Feature activation+0.128
Top resid features:
its
Token its
Feature activation+0.137
Top resid features:
long
Token long
Feature activation-0.109
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
awaited
Tokenawaited
Feature activation+0.000
Top resid features:
unprecedented
Token unprecedented
Feature activation-0.030
Top resid features:
popularity
Token popularity
Feature activation-0.066
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.044
Top resid features:
Ċ
TokenĊ
Feature activation-0.054
Top resid features:
Just
TokenJust
Feature activation+1.930
Top resid features:
a
Token a
Feature activation+0.116
Top resid features:
couple
Token couple
Feature activation-0.087
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
months
Token months
Feature activation+0.000
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.051
Top resid features:
Ċ
TokenĊ
Feature activation-0.060
Top resid features:
Iss
TokenIss
Feature activation-0.069
Top resid features:
a
Tokena
Feature activation-0.021
Top resid features:
is
Token is
Feature activation-0.041
Top resid features:
just
Token just
Feature activation+2.099
Top resid features:
plain
Token plain
Feature activation-0.074
Top resid features:
wrong
Token wrong
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
assume
Token assume
Feature activation+0.000
Top resid features:
American
Token American
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.022
Top resid features:
Ċ
TokenĊ
Feature activation-0.047
Top resid features:
Ċ
TokenĊ
Feature activation-0.061
Top resid features:
It
TokenIt
Feature activation-0.022
Top resid features:
is
Token is
Feature activation-0.123
Top resid features:
just
Token just
Feature activation+1.949
Top resid features:
another
Token another
Feature activation-0.055
Top resid features:
embarrassment
Token embarrassment
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
owner
Token owner
Feature activation+0.000
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation-0.039
Top resid features:
It
Token It
Feature activation-0.011
Top resid features:
âĢ
TokenâĢ
Feature activation-0.039
Top resid features:
Ļ
TokenĻ
Feature activation-0.046
Top resid features:
s
Tokens
Feature activation-0.043
Top resid features:
just
Token just
Feature activation+1.710
Top resid features:
this
Token this
Feature activation+0.171
Top resid features:
long
Token long
Feature activation-0.149
Top resid features:
building
Token building
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
out
Token out
Feature activation-0.018
Top resid features:
questionable
Token questionable
Feature activation-0.043
Top resid features:
coding
Token coding
Feature activation-0.022
Top resid features:
practices
Token practices
Feature activation-0.078
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.035
Top resid features:
just
Tokenjust
Feature activation+1.841
Top resid features:
like
Token like
Feature activation-0.056
Top resid features:
good
Token good
Feature activation-0.104
Top resid features:
old
Token old
Feature activation-0.067
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
w
Tokenw
Feature activation+0.000
Top resid features:
gown
Token gown
Feature activation-0.050
Top resid features:
s
Tokens
Feature activation-0.016
Top resid features:
.
Token.
Feature activation-0.048
Top resid features:
It
Token It
Feature activation-0.051
Top resid features:
's
Token's
Feature activation-0.126
Top resid features:
just
Token just
Feature activation+1.976
Top resid features:
very
Token very
Feature activation-0.125
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
very
Token very
Feature activation+0.000
Top resid features:
frightening
Token frightening
Feature activation+0.000
Top resid features:
."
Token."
Feature activation+0.000
Top resid features:
we
Token we
Feature activation-0.027
Top resid features:
all
Token all
Feature activation+0.037
Top resid features:
realize
Token realize
Feature activation-0.053
Top resid features:
this
Token this
Feature activation-0.031
Top resid features:
is
Token is
Feature activation-0.042
Top resid features:
just
Token just
Feature activation+1.602
Top resid features:
a
Token a
Feature activation+0.056
Top resid features:
little
Token little
Feature activation-0.072
Top resid features:
slice
Token slice
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
high
Token high
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.011
Top resid features:
issue
Token issue
Feature activation-0.043
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.038
Top resid features:
Ċ
TokenĊ
Feature activation-0.046
Top resid features:
Just
TokenJust
Feature activation+2.026
Top resid features:
days
Token days
Feature activation-0.280
Top resid features:
ago
Token ago
Feature activation-0.095
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Indian
Token Indian
Feature activation+0.000
Top resid features:
Air
Token Air
Feature activation+0.000
Top resid features:
dare
Token dare
Feature activation+0.043
Top resid features:
I
Token I
Feature activation-0.009
Top resid features:
say
Token say
Feature activation-0.045
Top resid features:
it
Token it
Feature activation-0.001
Top resid features:
?
Token?
Feature activation-0.044
Top resid features:
Just
Token Just
Feature activation+1.623
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation-0.149
Top resid features:
happier
Token happier
Feature activation-0.053
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Now
Token Now
Feature activation+0.000
Top resid features:
losing
Token losing
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.008
Top resid features:
waves
Tokenwaves
Feature activation-0.033
Top resid features:
.
Token.
Feature activation-0.042
Top resid features:
They
Token They
Feature activation-0.029
Top resid features:
form
Token form
Feature activation-0.233
Top resid features:
just
Token just
Feature activation+1.818
Top resid features:
a
Token a
Feature activation+0.092
Top resid features:
couple
Token couple
Feature activation-0.089
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
feet
Token feet
Feature activation+0.000
Top resid features:
above
Token above
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.045
Top resid features:
Town
TokenTown
Feature activation-0.037
Top resid features:
ship
Tokenship
Feature activation-0.041
Top resid features:
Cache
TokenCache
Feature activation-0.089
Top resid features:
is
Token is
Feature activation-0.046
Top resid features:
just
Token just
Feature activation+1.675
Top resid features:
an
Token an
Feature activation+0.088
Top resid features:
interface
Token interface
Feature activation-0.116
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
handle
Token handle
Feature activation+0.000
Top resid features:
caching
Token caching
Feature activation+0.000
Top resid features:
being
Token being
Feature activation-0.038
Top resid features:
for
Token for
Feature activation-0.073
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
seizures
Token seizures
Feature activation-0.090
Top resid features:
is
Token is
Feature activation-0.041
Top resid features:
just
Token just
Feature activation+1.671
Top resid features:
plain
Token plain
Feature activation-0.070
Top resid features:
stress
Token stress
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
rest
Token rest
Feature activation+0.000
Top resid features:
invoice
Token invoice
Feature activation-0.037
Top resid features:
codes
Token codes
Feature activation-0.046
Top resid features:
.
Token.
Feature activation-0.018
Top resid features:
Ha
Token Ha
Feature activation-0.024
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
just
Token just
Feature activation+1.641
Top resid features:
kidding
Token kidding
Feature activation-0.111
Top resid features:
!
Token!
Feature activation-0.094
Top resid features:
There
Token There
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
phone
Token phone
Feature activation-0.052
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
bedroom
Token bedroom
Feature activation-0.097
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
just
Token just
Feature activation+1.594
Top resid features:
say
Token say
Feature activation-0.077
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
OK
TokenOK
Feature activation+0.000
Top resid features:
Kindle
Token Kindle
Feature activation+0.000
Top resid features:
smart
Token smart
Feature activation-0.030
Top resid features:
.
Token.
Feature activation-0.035
Top resid features:
These
Token These
Feature activation+0.023
Top resid features:
devices
Token devices
Feature activation-0.138
Top resid features:
,
Token,
Feature activation-0.008
Top resid features:
just
Token just
Feature activation+1.545
Top resid features:
a
Token a
Feature activation+0.021
Top resid features:
few
Token few
Feature activation-0.090
Top resid features:
examples
Token examples
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.000
Top resid features:
Williams
TokenWilliams
Feature activation-0.053
Top resid features:
gives
Token gives
Feature activation-0.041
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
Cleveland
Token Cleveland
Feature activation-0.060
Top resid features:
offense
Token offense
Feature activation-0.087
Top resid features:
just
Token just
Feature activation+1.565
Top resid features:
a
Token a
Feature activation+0.072
Top resid features:
little
Token little
Feature activation-0.046
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
push
Token push
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.36

Head 1: 0.03

Head 2: 0.07

Head 3: 0.09

Head 4: 0.07

Head 5: 0.05

Head 6: 0.05

Head 7: 0.03

Head 8: 0.07

Head 9: 0.07

Head 10: 0.07

Head 11: 0.03

Positive logits

darn1.52

ain1.33

damn1.25

Immortal1.20

mole1.20

DragonMagazine1.16

dude1.16

1.15

fml1.14

Fake1.13

fuck1.13

hops1.11

ゴン1.11

Naruto1.10

goddamn1.09

godd1.09

Tooth1.09

bastard1.09

goof1.07

1.07

Negative logits

Cosponsors-1.53

ivities-1.35

iencies-1.30

ourse-1.28

icip-1.28

efully-1.28

ourses-1.27

utherland-1.26

iannopoulos-1.24

yrinth-1.24

vals-1.20

ustomed-1.19

inez-1.18

cession-1.17

ationally-1.17

NL-1.16

lig-1.16

notably-1.16

idently-1.16

UX-1.15

INTERVAL 1.591 - 1.768
CONTAINS 0.001%

Court
Token Court
Feature activation+0.000
has
Token has
Feature activation+0.000
just
Token just
Feature activation+0.110
issued
Token issued
Feature activation+0.186
its
Token its
Feature activation+0.028
long
Token long
Feature activation+1.636
-
Token-
Feature activation+0.000
awaited
Tokenawaited
Feature activation+0.725
judgment
Token judgment
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Iss
TokenIss
Feature activation+0.000
a
Tokena
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.467
plain
Token plain
Feature activation+1.621
wrong
Token wrong
Feature activation+0.137
to
Token to
Feature activation+0.000
assume
Token assume
Feature activation+0.000
American
Token American
Feature activation+0.000
would
Token would
Feature activation+0.066
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.351
nice
Token nice
Feature activation+1.768
being
Token being
Feature activation+0.808
able
Token able
Feature activation+0.302
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
something
Token something
Feature activation+0.115
The
Token The
Feature activation+0.000
screen
Token screen
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.028
a
Token a
Feature activation+0.364
big
Token big
Feature activation+1.733
bit
Token bit
Feature activation+0.597
map
Tokenmap
Feature activation+0.000
,
Token,
Feature activation+0.677
and
Token and
Feature activation+0.104
all
Token all
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
's
Token's
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.389
rather
Token rather
Feature activation+1.759
bit
Token bit
Feature activation+0.451
too
Token too
Feature activation+0.000
eager
Token eager
Feature activation+0.000
to
Token to
Feature activation+0.000
tell
Token tell
Feature activation+0.000

INTERVAL 1.414 - 1.591
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.154
another
Token another
Feature activation+1.455
embarrassment
Token embarrassment
Feature activation+0.189
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
owner
Token owner
Feature activation+0.000
who
Token who
Feature activation+0.000

INTERVAL 1.237 - 1.414
CONTAINS 0.001%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
just
Token just
Feature activation+0.000
this
Token this
Feature activation+0.000
long
Token long
Feature activation+1.395
building
Token building
Feature activation+0.000
with
Token with
Feature activation+0.150
a
Token a
Feature activation+0.000
bunch
Token bunch
Feature activation+0.000
of
Token of
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
seizures
Token seizures
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.065
plain
Token plain
Feature activation+1.259
stress
Token stress
Feature activation+0.000
,
Token,
Feature activation+0.639
no
Token no
Feature activation+0.369
rest
Token rest
Feature activation+0.093
,
Token,
Feature activation+0.163
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
just
Token just
Feature activation+0.124
very
Token very
Feature activation+1.359
,
Token,
Feature activation+0.606
very
Token very
Feature activation+1.003
frightening
Token frightening
Feature activation+0.145
."
Token."
Feature activation+0.049
Ċ
TokenĊ
Feature activation+0.000
say
Token say
Feature activation+0.000
it
Token it
Feature activation+0.019
?
Token?
Feature activation+0.000
Just
Token Just
Feature activation+0.426
âĢ¦
TokenâĢ¦
Feature activation+1.116
happier
Token happier
Feature activation+1.312
.
Token.
Feature activation+0.991
Now
Token Now
Feature activation+1.034
losing
Token losing
Feature activation+0.000
all
Token all
Feature activation+0.000
that
Token that
Feature activation+0.000
practices
Token practices
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
just
Tokenjust
Feature activation+0.051
like
Token like
Feature activation+0.000
good
Token good
Feature activation+0.095
old
Token old
Feature activation+1.372
-
Token -
Feature activation+0.100
w
Tokenw
Feature activation+0.000
in
Token in
Feature activation+0.000
Perl
Token Perl
Feature activation+0.000
.
Token.
Feature activation+0.044

INTERVAL 1.061 - 1.237
CONTAINS 0.002%

the
Token the
Feature activation+0.000
Cleveland
Token Cleveland
Feature activation+0.000
offense
Token offense
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+1.183
more
Token more
Feature activation+0.470
push
Token push
Feature activation+0.000
,
Token,
Feature activation+0.313
with
Token with
Feature activation+0.213
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
comes
Token comes
Feature activation+0.000
just
Token just
Feature activation+0.093
a
Token a
Feature activation+0.749
few
Token few
Feature activation+1.181
hours
Token hours
Feature activation+0.000
after
Token after
Feature activation+0.308
Ch
Token Ch
Feature activation+0.000
ah
Tokenah
Feature activation+0.000
al
Tokenal
Feature activation+0.000
dead
Token dead
Feature activation+0.000
!
Token!
Feature activation+0.000
And
Token And
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.168
couple
Token couple
Feature activation+1.129
weeks
Token weeks
Feature activation+0.000
after
Token after
Feature activation+0.159
taking
Token taking
Feature activation+0.000
office
Token office
Feature activation+0.000
.
Token.
Feature activation+0.089
the
Token the
Feature activation+0.000
bedroom
Token bedroom
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
say
Token say
Feature activation+0.963
,
Token,
Feature activation+1.212
"
Token "
Feature activation+0.508
OK
TokenOK
Feature activation+0.269
Kindle
Token Kindle
Feature activation+0.000
,
Token,
Feature activation+0.065
bring
Token bring
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.100
recommendation
Token recommendation
Feature activation+0.158
,
Token,
Feature activation+1.136
and
Token and
Feature activation+0.321
some
Token some
Feature activation+0.443
under
Token under
Feature activation+0.079
writers
Tokenwriters
Feature activation+0.000
may
Token may
Feature activation+0.000

INTERVAL 0.884 - 1.061
CONTAINS 0.004%

Facebook
Token Facebook
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.695
months
Token months
Feature activation+0.000
ago
Token ago
Feature activation+0.996
on
Token on
Feature activation+0.000
June
Token June
Feature activation+0.000
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.287
play
Token play
Feature activation+0.000
.
Token.
Feature activation+0.885
He
Token He
Feature activation+0.259
played
Token played
Feature activation+0.000
quarterback
Token quarterback
Feature activation+0.000
.
Token.
Feature activation+0.000
Nick
Token Nick
Feature activation+0.000
AIN
TokenAIN
Feature activation+0.000
:
Token:
Feature activation+0.000
It
Token It
Feature activation+0.000
just
Token just
Feature activation+0.071
gave
Token gave
Feature activation+0.457
you
Token you
Feature activation+0.914
that
Token that
Feature activation+0.000
eerie
Token eerie
Feature activation+0.000
feeling
Token feeling
Feature activation+0.003
of
Token of
Feature activation+0.000
-
Token -
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.000
be
Token be
Feature activation+0.000
present
Token present
Feature activation+0.000
,
Token,
Feature activation+0.956
just
Token just
Feature activation+0.397
be
Token be
Feature activation+0.375
around
Token around
Feature activation+0.854
,"
Token,"
Feature activation+0.125
Rob
Token Rob
Feature activation+0.115
flag
Tokenflag
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.322
a
Token a
Feature activation+0.895
boolean
Token boolean
Feature activation+0.822
variable
Token variable
Feature activation+0.113
that
Token that
Feature activation+0.112
will
Token will
Feature activation+0.312
tell
Token tell
Feature activation+0.000

INTERVAL 0.707 - 0.884
CONTAINS 0.006%

likes
Token likes
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
think
Token think
Feature activation+0.000
,
Token,
Feature activation+0.961
if
Token if
Feature activation+0.760
every
Token every
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
likes
Token likes
Feature activation+0.000
guy
Token guy
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
just
Token just
Feature activation+0.000
his
Token his
Feature activation+0.000
pick
Token pick
Feature activation+0.000
.
Token.
Feature activation+0.851
He
Token He
Feature activation+0.288
even
Token even
Feature activation+0.708
noted
Token noted
Feature activation+0.000
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
Perth
Token Perth
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
just
Token just
Feature activation+0.135
sort
Token sort
Feature activation+0.368
of
Token of
Feature activation+0.767
became
Token became
Feature activation+0.348
the
Token the
Feature activation+0.244
beginning
Token beginning
Feature activation+0.060
of
Token of
Feature activation+0.207
the
Token the
Feature activation+0.000
f
Tokenf
Feature activation+0.000
ishing
Tokenishing
Feature activation+0.000
.
Token.
Feature activation+0.000
Just
Token Just
Feature activation+0.069
pick
Token pick
Feature activation+0.000
your
Token your
Feature activation+0.769
c
Token c
Feature activation+0.000
aye
Tokenaye
Feature activation+0.000
(
Token (
Feature activation+0.000
small
Tokensmall
Feature activation+0.000
island
Token island
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Just
TokenJust
Feature activation+0.497
thought
Token thought
Feature activation+0.000
you
Token you
Feature activation+0.875
âĢ
TokenâĢ
Feature activation+0.933
Ļ
TokenĻ
Feature activation+0.503
d
Tokend
Feature activation+0.334
like
Token like
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.530 - 0.707
CONTAINS 0.013%

aren
Token aren
Feature activation+0.119
âĢ
TokenâĢ
Feature activation+0.088
Ļ
TokenĻ
Feature activation+0.039
t
Tokent
Feature activation+0.137
needed
Token needed
Feature activation+0.000
anymore
Token anymore
Feature activation+0.561
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
devices
Token devices
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.294
a
Token a
Feature activation+0.548
few
Token few
Feature activation+1.196
examples
Token examples
Feature activation+0.028
of
Token of
Feature activation+0.029
what
Token what
Feature activation+0.000
is
Token is
Feature activation+0.000
impression
Token impression
Feature activation+0.000
that
Token that
Feature activation+0.000
this
Token this
Feature activation+0.000
was
Token was
Feature activation+0.000
just
Token just
Feature activation+0.000
another
Token another
Feature activation+0.579
piece
Token piece
Feature activation+0.000
thrown
Token thrown
Feature activation+0.098
onto
Token onto
Feature activation+0.000
the
Token the
Feature activation+0.000
mountain
Token mountain
Feature activation+0.000
That
Token That
Feature activation+0.000
's
Token's
Feature activation+0.000
just
Token just
Feature activation+0.120
typical
Token typical
Feature activation+1.026
me
Token me
Feature activation+0.036
though
Token though
Feature activation+0.587
."
Token."
Feature activation+0.135
Wayne
Token Wayne
Feature activation+0.000
is
Token is
Feature activation+0.000
planning
Token planning
Feature activation+0.000
a
Token a
Feature activation+0.000
presence
Token presence
Feature activation+0.000
just
Token just
Feature activation+0.000
made
Token made
Feature activation+0.000
me
Token me
Feature activation+0.000
feel
Token feel
Feature activation+0.040
comfortable
Token comfortable
Feature activation+0.655
."
Token."
Feature activation+0.108
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
day
Token day
Feature activation+0.000

INTERVAL 0.354 - 0.530
CONTAINS 0.023%

Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
There
TokenThere
Feature activation+0.000
was
Token was
Feature activation+0.000
just
Token just
Feature activation+0.000
an
Token an
Feature activation+0.443
incred
Token incred
Feature activation+0.202
ulous
Tokenulous
Feature activation+0.148
feeling
Token feeling
Feature activation+0.354
as
Token as
Feature activation+0.000
people
Token people
Feature activation+0.000
rumors
Token rumors
Feature activation+0.000
are
Token are
Feature activation+0.000
just
Token just
Feature activation+0.000
that
Token that
Feature activation+0.221
,
Token,
Feature activation+0.960
rumors
Token rumors
Feature activation+0.397
.
Token.
Feature activation+0.349
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
GREEN
TokenGREEN
Feature activation+0.000
VILLE
TokenVILLE
Feature activation+0.000
,
Token,
Feature activation+0.000
no
Token no
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
just
Token just
Feature activation+0.000
kind
Token kind
Feature activation+0.135
of
Token of
Feature activation+0.456
happened
Token happened
Feature activation+0.000
.
Token.
Feature activation+0.400
We
Token We
Feature activation+0.202
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
hiber
Token hiber
Feature activation+0.000
n
Tokenn
Feature activation+0.000
ating
Tokenating
Feature activation+0.051
as
Token as
Feature activation+0.000
usual
Token usual
Feature activation+0.329
,
Token,
Feature activation+0.468
as
Token as
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
land
Token land
Feature activation+0.000
er
Tokener
Feature activation+0.000
was
Token was
Feature activation+0.000
bombing
Token bombing
Feature activation+0.000
civilians
Token civilians
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.385
day
Token day
Feature activation+0.192
after
Token after
Feature activation+0.062
world
Token world
Feature activation+0.000
powers
Token powers
Feature activation+0.000
agreed
Token agreed
Feature activation+0.000

INTERVAL 0.177 - 0.354
CONTAINS 0.052%

a
Token a
Feature activation+0.412
call
Token call
Feature activation+0.106
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
governor
Token governor
Feature activation+0.000
,
Token,
Feature activation+0.178
and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000
a
Token a
Feature activation+0.000
particular
Token particular
Feature activation+0.000
a
Token a
Feature activation+0.000
very
Token very
Feature activation+0.495
good
Token good
Feature activation+0.253
hitter
Token hitter
Feature activation+0.000
,
Token,
Feature activation+0.230
but
Token but
Feature activation+0.180
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
hitters
Token hitters
Feature activation+0.000
a
Token a
Feature activation+0.000
piano
Token piano
Feature activation+0.000
accompan
Token accompan
Feature activation+0.089
iment
Tokeniment
Feature activation+0.111
,
Token,
Feature activation+0.408
or
Token or
Feature activation+0.219
when
Token when
Feature activation+0.000
TE
Token TE
Feature activation+0.000
Z
TokenZ
Feature activation+0.000
nailed
Token nailed
Feature activation+0.000
an
Token an
Feature activation+0.000
beers
Token beers
Feature activation+0.000
may
Token may
Feature activation+0.000
still
Token still
Feature activation+0.000
be
Token be
Feature activation+0.000
just
Token just
Feature activation+0.000
slightly
Token slightly
Feature activation+0.235
unpopular
Token unpopular
Feature activation+0.636
enough
Token enough
Feature activation+0.000
for
Token for
Feature activation+0.000
hip
Token hip
Feature activation+0.000
sters
Tokensters
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Just
TokenJust
Feature activation+0.008
leave
Token leave
Feature activation+0.000
,
Token,
Feature activation+0.219
please
Token please
Feature activation+0.000
,
Token,
Feature activation+0.008
âĢ
TokenâĢ
Feature activation+0.270
Ŀ
TokenĿ
Feature activation+0.089
I
Token I
Feature activation+0.000

INTERVAL 0.000 - 0.177
CONTAINS 99.899%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
staff
Token staff
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
:
Token:
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
worked
Token worked
Feature activation+0.000
on
Token on
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+0.000
as
Token as
Feature activation+0.000
they
Token they
Feature activation+0.000
[
Token [
Feature activation+0.000
Prince
TokenPrince
Feature activation+0.000
Philip
Token Philip
Feature activation+0.000
and
Token and
Feature activation+0.000
Lord
Token Lord
Feature activation+0.000
Mont
Token Mont
Feature activation+0.000
b
Tokenb
Feature activation+0.000
atten
Tokenatten
Feature activation+0.000
]
Token]
Feature activation+0.000
showed
Token showed
Feature activation+0.000
go
Token go
Feature activation+0.000
?
Token?
Feature activation+0.000
Two
Token Two
Feature activation+0.000
things
Token things
Feature activation+0.000
will
Token will
Feature activation+0.000
determine
Token determine
Feature activation+0.000
how
Token how
Feature activation+0.000
far
Token far
Feature activation+0.000
he
Token he
Feature activation+0.000
can
Token can
Feature activation+0.000
go
Token go
Feature activation+0.000
of
Token of
Feature activation+0.000
gender
Token gender
Feature activation+0.000
transition
Token transition
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
was
Token was
Feature activation+0.000
signed
Token signed
Feature activation+0.000
by
Token by
Feature activation+0.000
Dr
Token Dr
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 3 in H2.0: (feature 23851)

TOP ACTIVATIONS
MAX = 1.646

The
TokenThe
Feature activation+0.000
choice
Token choice
Feature activation+0.000
has
Token has
Feature activation+0.000
never
Token never
Feature activation+0.000
been
Token been
Feature activation+0.000
clearer
Token clearer
Feature activation+1.646
-
Token -
Feature activation+0.722
Donald
Token Donald
Feature activation+0.395
Trump
Token Trump
Feature activation+0.145
calls
Token calls
Feature activation+0.391
on
Token on
Feature activation+0.071
franchise
Token franchise
Feature activation+0.000
never
Token never
Feature activation+0.000
did
Token did
Feature activation+0.000
quite
Token quite
Feature activation+1.080
as
Token as
Feature activation+0.450
well
Token well
Feature activation+1.514
at
Token at
Feature activation+0.126
the
Token the
Feature activation+0.073
box
Token box
Feature activation+0.000
office
Token office
Feature activation+0.000
as
Token as
Feature activation+0.159
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
never
Token never
Feature activation+0.000
seen
Token seen
Feature activation+0.000
anything
Token anything
Feature activation+0.937
like
Token like
Feature activation+1.503
this
Token this
Feature activation+0.188
before
Token before
Feature activation+0.469
âĢĵ
Token âĢĵ
Feature activation+0.388
or
Token or
Feature activation+0.000
at
Token at
Feature activation+0.000
have
Token have
Feature activation+0.000
never
Token never
Feature activation+0.000
seen
Token seen
Feature activation+0.000
Friedman
Token Friedman
Feature activation+0.000
be
Token be
Feature activation+0.903
so
Token so
Feature activation+1.432
negative
Token negative
Feature activation+0.466
,
Token,
Feature activation+0.230
or
Token or
Feature activation+0.000
for
Token for
Feature activation+0.000
that
Token that
Feature activation+0.000
Ferr
Token Ferr
Feature activation+0.000
aris
Tokenaris
Feature activation+0.000
.
Token.
Feature activation+0.000
Never
Token Never
Feature activation+0.000
married
Token married
Feature activation+0.000
and
Token and
Feature activation+1.423
without
Token without
Feature activation+0.286
children
Token children
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
cars
Token cars
Feature activation+0.000
had
Token had
Feature activation+0.144
anyone
Token anyone
Feature activation+0.681
massage
Token massage
Feature activation+0.834
my
Token my
Feature activation+0.683
face
Token face
Feature activation+0.523
and
Token and
Feature activation+1.416
it
Token it
Feature activation+0.512
just
Token just
Feature activation+0.536
feels
Token feels
Feature activation+0.000
unbelievable
Token unbelievable
Feature activation+0.000
,
Token,
Feature activation+0.000
ball
Token ball
Feature activation+0.000
was
Token was
Feature activation+0.000
never
Token never
Feature activation+0.000
fully
Token fully
Feature activation+0.142
cleared
Token cleared
Feature activation+0.290
and
Token and
Feature activation+1.365
T
Token T
Feature activation+0.000
oni
Tokenoni
Feature activation+0.000
Kro
Token Kro
Feature activation+0.000
os
Tokenos
Feature activation+0.000
,
Token,
Feature activation+0.000
ees
Tokenees
Feature activation+0.000
will
Token will
Feature activation+0.000
never
Token never
Feature activation+0.000
be
Token be
Feature activation+0.209
judged
Token judged
Feature activation+0.619
purely
Token purely
Feature activation+1.364
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
skills
Token skills
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
"
Token "
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
never
Token never
Feature activation+0.003
been
Token been
Feature activation+0.463
more
Token more
Feature activation+1.353
important
Token important
Feature activation+1.343
,
Token,
Feature activation+0.479
or
Token or
Feature activation+0.193
more
Token more
Feature activation+0.237
difficult
Token difficult
Feature activation+0.337
G
Token G
Feature activation+0.000
ED
TokenED
Feature activation+0.000
but
Token but
Feature activation+0.000
never
Token never
Feature activation+0.000
graduated
Token graduated
Feature activation+0.131
from
Token from
Feature activation+1.349
college
Token college
Feature activation+0.082
.
Token.
Feature activation+0.139
In
Token In
Feature activation+0.000
2003
Token 2003
Feature activation+0.000
,
Token,
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
never
Token never
Feature activation+0.003
been
Token been
Feature activation+0.463
more
Token more
Feature activation+1.353
important
Token important
Feature activation+1.343
,
Token,
Feature activation+0.479
or
Token or
Feature activation+0.193
more
Token more
Feature activation+0.237
difficult
Token difficult
Feature activation+0.337
,
Token,
Feature activation+0.000
But
Token But
Feature activation+0.000
they
Token they
Feature activation+0.000
never
Token never
Feature activation+0.000
grow
Token grow
Feature activation+0.000
large
Token large
Feature activation+0.816
enough
Token enough
Feature activation+1.327
to
Token to
Feature activation+0.410
be
Token be
Feature activation+0.430
seen
Token seen
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000
I
TokenI
Feature activation+0.000
never
Token never
Feature activation+0.155
thought
Token thought
Feature activation+1.247
I
Token I
Feature activation+0.877
would
Token would
Feature activation+1.326
be
Token be
Feature activation+0.958
a
Token a
Feature activation+1.203
pan
Token pan
Feature activation+0.235
handler
Tokenhandler
Feature activation+0.268
,
Token,
Feature activation+0.796
emotions
Token emotions
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
never
Token never
Feature activation+0.066
did
Token did
Feature activation+0.213
think
Token think
Feature activation+1.315
we
Token we
Feature activation+0.734
were
Token were
Feature activation+0.954
going
Token going
Feature activation+0.592
to
Token to
Feature activation+0.018
die
Token die
Feature activation+0.000
never
Token never
Feature activation+0.000
really
Token really
Feature activation+0.000
liked
Token liked
Feature activation+0.269
Mole
Token Mole
Feature activation+0.000
very
Token very
Feature activation+0.547
much
Token much
Feature activation+1.306
because
Token because
Feature activation+0.487
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
an
Token an
Feature activation+0.000
unwanted
Token unwanted
Feature activation+0.000
never
Token never
Feature activation+0.000
has
Token has
Feature activation+0.000
there
Token there
Feature activation+0.000
been
Token been
Feature activation+0.079
a
Token a
Feature activation+0.818
more
Token more
Feature activation+1.302
nond
Token nond
Feature activation+0.038
esc
Tokenesc
Feature activation+0.000
ript
Tokenript
Feature activation+0.221
f
Token f
Feature activation+0.000
***
Token***
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
never
Token never
Feature activation+0.000
far
Token far
Feature activation+0.000
from
Token from
Feature activation+1.284
something
Token something
Feature activation+0.581
that
Token that
Feature activation+0.462
needs
Token needs
Feature activation+0.358
celebrating
Token celebrating
Feature activation+0.000
.
Token.
Feature activation+0.000
was
Token was
Feature activation+0.000
never
Token never
Feature activation+0.234
attacked
Token attacked
Feature activation+1.264
,
Token,
Feature activation+0.368
and
Token and
Feature activation+1.262
quickly
Token quickly
Feature activation+1.282
dis
Token dis
Feature activation+0.000
assembled
Tokenassembled
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
never
Token never
Feature activation+0.000
predictable
Token predictable
Feature activation+0.929
-
Token -
Feature activation+0.000
well
Token well
Feature activation+1.280
,
Token,
Feature activation+0.000
except
Token except
Feature activation+0.000
for
Token for
Feature activation+0.000
one
Token one
Feature activation+0.000
bit
Token bit
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
someone
Token someone
Feature activation+0.000
you
Token you
Feature activation+0.000
never
Token never
Feature activation+0.238
expected
Token expected
Feature activation+1.280
.
Token.
Feature activation+0.121
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
the
Token the
Feature activation+0.000

Top DFA by src position
MAX = 2.290

behind
Token behind
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.045
Top resid features:
The
TokenThe
Feature activation+0.022
Top resid features:
choice
Token choice
Feature activation-0.009
Top resid features:
has
Token has
Feature activation-0.039
Top resid features:
never
Token never
Feature activation+2.290
Top resid features:
been
Token been
Feature activation+0.153
Top resid features:
clearer
Token clearer
Feature activation+0.081
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
Donald
Token Donald
Feature activation+0.000
Top resid features:
Trump
Token Trump
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.006
Top resid features:
Diver
Token Diver
Feature activation-0.005
Top resid features:
gent
Tokengent
Feature activation+0.007
Top resid features:
movie
Token movie
Feature activation-0.002
Top resid features:
franchise
Token franchise
Feature activation-0.004
Top resid features:
never
Token never
Feature activation+1.962
Top resid features:
did
Token did
Feature activation+0.166
Top resid features:
quite
Token quite
Feature activation-0.023
Top resid features:
as
Token as
Feature activation+0.220
Top resid features:
well
Token well
Feature activation+0.027
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
I
TokenI
Feature activation+0.021
Top resid features:
âĢ
TokenâĢ
Feature activation+0.013
Top resid features:
Ļ
TokenĻ
Feature activation+0.012
Top resid features:
ve
Tokenve
Feature activation+0.021
Top resid features:
never
Token never
Feature activation+1.974
Top resid features:
seen
Token seen
Feature activation+0.196
Top resid features:
anything
Token anything
Feature activation+0.015
Top resid features:
like
Token like
Feature activation+0.055
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
first
Token first
Feature activation+0.021
Top resid features:
wife
Token wife
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.075
Top resid features:
I
Token I
Feature activation+0.006
Top resid features:
have
Token have
Feature activation+0.007
Top resid features:
never
Token never
Feature activation+2.051
Top resid features:
seen
Token seen
Feature activation+0.075
Top resid features:
Friedman
Token Friedman
Feature activation-0.113
Top resid features:
be
Token be
Feature activation+0.054
Top resid features:
so
Token so
Feature activation+0.053
Top resid features:
negative
Token negative
Feature activation+0.000
Top resid features:
as
Tokenas
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
Ferr
Token Ferr
Feature activation-0.031
Top resid features:
aris
Tokenaris
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
Never
Token Never
Feature activation+1.749
Top resid features:
married
Token married
Feature activation+0.285
Top resid features:
and
Token and
Feature activation+0.190
Top resid features:
without
Token without
Feature activation+0.000
Top resid features:
children
Token children
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
I
Token I
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.005
Top resid features:
d
Tokend
Feature activation+0.019
Top resid features:
never
Token never
Feature activation+1.606
Top resid features:
really
Token really
Feature activation+0.060
Top resid features:
had
Token had
Feature activation+0.085
Top resid features:
anyone
Token anyone
Feature activation+0.081
Top resid features:
massage
Token massage
Feature activation+0.059
Top resid features:
my
Token my
Feature activation+0.132
Top resid features:
seconds
Token seconds
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.039
Top resid features:
The
Token The
Feature activation+0.005
Top resid features:
ball
Token ball
Feature activation+0.006
Top resid features:
was
Token was
Feature activation+0.024
Top resid features:
never
Token never
Feature activation+1.700
Top resid features:
fully
Token fully
Feature activation+0.049
Top resid features:
cleared
Token cleared
Feature activation+0.197
Top resid features:
and
Token and
Feature activation+0.197
Top resid features:
T
Token T
Feature activation+0.000
Top resid features:
oni
Tokenoni
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.010
Top resid features:
these
Token these
Feature activation-0.012
Top resid features:
train
Token train
Feature activation-0.010
Top resid features:
ees
Tokenees
Feature activation+0.014
Top resid features:
will
Token will
Feature activation+0.029
Top resid features:
never
Token never
Feature activation+2.096
Top resid features:
be
Token be
Feature activation+0.039
Top resid features:
judged
Token judged
Feature activation+0.158
Top resid features:
purely
Token purely
Feature activation+0.022
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
Dynamics
Token Dynamics
Feature activation-0.028
Top resid features:
said
Token said
Feature activation+0.015
Top resid features:
"
Token "
Feature activation+0.027
Top resid features:
It
TokenIt
Feature activation-0.006
Top resid features:
's
Token's
Feature activation-0.056
Top resid features:
never
Token never
Feature activation+2.145
Top resid features:
been
Token been
Feature activation+0.052
Top resid features:
more
Token more
Feature activation+0.050
Top resid features:
important
Token important
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
earned
Token earned
Feature activation+0.039
Top resid features:
a
Token a
Feature activation+0.041
Top resid features:
G
Token G
Feature activation+0.008
Top resid features:
ED
TokenED
Feature activation-0.012
Top resid features:
but
Token but
Feature activation+0.033
Top resid features:
never
Token never
Feature activation+2.089
Top resid features:
graduated
Token graduated
Feature activation+0.049
Top resid features:
from
Token from
Feature activation+0.110
Top resid features:
college
Token college
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
In
Token In
Feature activation+0.000
Top resid features:
Dynamics
Token Dynamics
Feature activation-0.020
Top resid features:
said
Token said
Feature activation+0.018
Top resid features:
"
Token "
Feature activation+0.020
Top resid features:
It
TokenIt
Feature activation-0.039
Top resid features:
's
Token's
Feature activation-0.049
Top resid features:
never
Token never
Feature activation+1.919
Top resid features:
been
Token been
Feature activation+0.130
Top resid features:
more
Token more
Feature activation+0.218
Top resid features:
important
Token important
Feature activation+0.020
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
male
Token male
Feature activation+0.013
Top resid features:
worms
Token worms
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.042
Top resid features:
But
Token But
Feature activation-0.005
Top resid features:
they
Token they
Feature activation-0.013
Top resid features:
never
Token never
Feature activation+2.022
Top resid features:
grow
Token grow
Feature activation+0.089
Top resid features:
large
Token large
Feature activation-0.048
Top resid features:
enough
Token enough
Feature activation+0.055
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
quickly
Token quickly
Feature activation+0.029
Top resid features:
added
Token added
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
"
Token "
Feature activation+0.011
Top resid features:
I
TokenI
Feature activation+0.024
Top resid features:
never
Token never
Feature activation+1.669
Top resid features:
thought
Token thought
Feature activation+0.186
Top resid features:
I
Token I
Feature activation+0.079
Top resid features:
would
Token would
Feature activation+0.164
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.011
Top resid features:
these
Token these
Feature activation-0.003
Top resid features:
emotions
Token emotions
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.040
Top resid features:
I
Token I
Feature activation-0.022
Top resid features:
never
Token never
Feature activation+2.045
Top resid features:
did
Token did
Feature activation+0.064
Top resid features:
think
Token think
Feature activation+0.045
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
going
Token going
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
this
Token this
Feature activation-0.003
Top resid features:
very
Token very
Feature activation+0.012
Top resid features:
day
Token day
Feature activation-0.012
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
never
Token never
Feature activation+1.653
Top resid features:
really
Token really
Feature activation+0.066
Top resid features:
liked
Token liked
Feature activation+0.038
Top resid features:
Mole
Token Mole
Feature activation+0.087
Top resid features:
very
Token very
Feature activation+0.253
Top resid features:
much
Token much
Feature activation+0.044
Top resid features:
ing
Tokening
Feature activation+0.001
Top resid features:
N
Token N
Feature activation-0.019
Top resid features:
ought
Tokenought
Feature activation+0.006
Top resid features:
ies
Tokenies
Feature activation-0.006
Top resid features:
and
Token and
Feature activation+0.060
Top resid features:
never
Token never
Feature activation+1.727
Top resid features:
has
Token has
Feature activation+0.019
Top resid features:
there
Token there
Feature activation+0.135
Top resid features:
been
Token been
Feature activation+0.059
Top resid features:
a
Token a
Feature activation+0.124
Top resid features:
more
Token more
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
you
Token you
Feature activation-0.013
Top resid features:
âĢ
TokenâĢ
Feature activation+0.068
Top resid features:
Ļ
TokenĻ
Feature activation-0.038
Top resid features:
re
Tokenre
Feature activation-0.027
Top resid features:
never
Token never
Feature activation+2.111
Top resid features:
far
Token far
Feature activation-0.013
Top resid features:
from
Token from
Feature activation+0.114
Top resid features:
something
Token something
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
needs
Token needs
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.148
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
built
Tokenbuilt
Feature activation+0.014
Top resid features:
city
Token city
Feature activation-0.004
Top resid features:
was
Token was
Feature activation-0.000
Top resid features:
never
Token never
Feature activation+2.147
Top resid features:
attacked
Token attacked
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.093
Top resid features:
and
Token and
Feature activation+0.123
Top resid features:
quickly
Token quickly
Feature activation-0.105
Top resid features:
dis
Token dis
Feature activation+0.000
Top resid features:
while
Token while
Feature activation-0.005
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
but
Token but
Feature activation+0.009
Top resid features:
it
Token it
Feature activation+0.004
Top resid features:
was
Token was
Feature activation+0.003
Top resid features:
never
Token never
Feature activation+2.041
Top resid features:
predictable
Token predictable
Feature activation-0.064
Top resid features:
-
Token -
Feature activation+0.264
Top resid features:
well
Token well
Feature activation+0.033
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
except
Token except
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.023
Top resid features:
to
Token to
Feature activation+0.037
Top resid features:
be
Token be
Feature activation+0.017
Top resid features:
someone
Token someone
Feature activation+0.029
Top resid features:
you
Token you
Feature activation+0.082
Top resid features:
never
Token never
Feature activation+1.656
Top resid features:
expected
Token expected
Feature activation+0.126
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:
But
TokenBut
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.35

Head 1: 0.03

Head 2: 0.05

Head 3: 0.07

Head 4: 0.07

Head 5: 0.06

Head 6: 0.05

Head 7: 0.04

Head 8: 0.08

Head 9: 0.06

Head 10: 0.09

Head 11: 0.04

Positive logits

anymore2.40

nor2.38

slightest1.51

urga1.49

��1.49

EVER1.46

whatsoever1.45

Ever1.41

anybody1.41

Nor1.40

anywhere1.38

thood1.38

Alone1.38

yet1.37

ocalypse1.36

anything1.35

nor1.33

anything1.33

Yet1.27

Lilly1.24

Negative logits

unsurprisingly-1.29

-1.23

ACTIONS-1.17

redes-1.16

slowly-1.15

assorted-1.15

anwhile-1.12

largeDownload-1.12

iliar-1.11

awfully-1.11

lik-1.10

-1.07

doubtless-1.07

usable-1.06

incorporates-1.05

trak-1.04

pairs-1.04

-1.04

surprisingly-1.04

braces-1.03

INTERVAL 1.481 - 1.646
CONTAINS 0.000%

Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
never
Token never
Feature activation+0.000
seen
Token seen
Feature activation+0.000
anything
Token anything
Feature activation+0.937
like
Token like
Feature activation+1.503
this
Token this
Feature activation+0.188
before
Token before
Feature activation+0.469
âĢĵ
Token âĢĵ
Feature activation+0.388
or
Token or
Feature activation+0.000
at
Token at
Feature activation+0.000
The
TokenThe
Feature activation+0.000
choice
Token choice
Feature activation+0.000
has
Token has
Feature activation+0.000
never
Token never
Feature activation+0.000
been
Token been
Feature activation+0.000
clearer
Token clearer
Feature activation+1.646
-
Token -
Feature activation+0.722
Donald
Token Donald
Feature activation+0.395
Trump
Token Trump
Feature activation+0.145
calls
Token calls
Feature activation+0.391
on
Token on
Feature activation+0.071
franchise
Token franchise
Feature activation+0.000
never
Token never
Feature activation+0.000
did
Token did
Feature activation+0.000
quite
Token quite
Feature activation+1.080
as
Token as
Feature activation+0.450
well
Token well
Feature activation+1.514
at
Token at
Feature activation+0.126
the
Token the
Feature activation+0.073
box
Token box
Feature activation+0.000
office
Token office
Feature activation+0.000
as
Token as
Feature activation+0.159

INTERVAL 1.317 - 1.481
CONTAINS 0.001%

But
Token But
Feature activation+0.000
they
Token they
Feature activation+0.000
never
Token never
Feature activation+0.000
grow
Token grow
Feature activation+0.000
large
Token large
Feature activation+0.816
enough
Token enough
Feature activation+1.327
to
Token to
Feature activation+0.410
be
Token be
Feature activation+0.430
seen
Token seen
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
have
Token have
Feature activation+0.000
never
Token never
Feature activation+0.000
seen
Token seen
Feature activation+0.000
Friedman
Token Friedman
Feature activation+0.000
be
Token be
Feature activation+0.903
so
Token so
Feature activation+1.432
negative
Token negative
Feature activation+0.466
,
Token,
Feature activation+0.230
or
Token or
Feature activation+0.000
for
Token for
Feature activation+0.000
that
Token that
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
never
Token never
Feature activation+0.003
been
Token been
Feature activation+0.463
more
Token more
Feature activation+1.353
important
Token important
Feature activation+1.343
,
Token,
Feature activation+0.479
or
Token or
Feature activation+0.193
more
Token more
Feature activation+0.237
difficult
Token difficult
Feature activation+0.337
,
Token,
Feature activation+0.000
ees
Tokenees
Feature activation+0.000
will
Token will
Feature activation+0.000
never
Token never
Feature activation+0.000
be
Token be
Feature activation+0.209
judged
Token judged
Feature activation+0.619
purely
Token purely
Feature activation+1.364
for
Token for
Feature activation+0.000
their
Token their
Feature activation+0.000
skills
Token skills
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
G
Token G
Feature activation+0.000
ED
TokenED
Feature activation+0.000
but
Token but
Feature activation+0.000
never
Token never
Feature activation+0.000
graduated
Token graduated
Feature activation+0.131
from
Token from
Feature activation+1.349
college
Token college
Feature activation+0.082
.
Token.
Feature activation+0.139
In
Token In
Feature activation+0.000
2003
Token 2003
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.152 - 1.317
CONTAINS 0.003%

never
Token never
Feature activation+0.034
tried
Token tried
Feature activation+0.669
to
Token to
Feature activation+0.547
see
Token see
Feature activation+0.006
me
Token me
Feature activation+0.275
and
Token and
Feature activation+1.233
there
Token there
Feature activation+0.092
had
Token had
Feature activation+0.168
been
Token been
Feature activation+0.029
no
Token no
Feature activation+0.000
restraining
Token restraining
Feature activation+0.000
city
Token city
Feature activation+0.000
was
Token was
Feature activation+0.000
never
Token never
Feature activation+0.234
attacked
Token attacked
Feature activation+1.264
,
Token,
Feature activation+0.368
and
Token and
Feature activation+1.262
quickly
Token quickly
Feature activation+1.282
dis
Token dis
Feature activation+0.000
assembled
Tokenassembled
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
different
Token different
Feature activation+0.000
people
Token people
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
never
Token never
Feature activation+0.183
seemed
Token seemed
Feature activation+1.241
to
Token to
Feature activation+0.819
have
Token have
Feature activation+0.097
great
Token great
Feature activation+0.345
chemistry
Token chemistry
Feature activation+0.263
,
Token,
Feature activation+0.561
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
never
Token never
Feature activation+0.178
thought
Token thought
Feature activation+1.217
I
Token I
Feature activation+0.886
'd
Token'd
Feature activation+0.750
say
Token say
Feature activation+0.546
this
Token this
Feature activation+0.777
but
Token but
Feature activation+1.008
users
Token users
Feature activation+0.000
should
Token should
Feature activation+0.000
never
Token never
Feature activation+0.000
use
Token use
Feature activation+0.000
the
Token the
Feature activation+0.324
same
Token same
Feature activation+1.190
password
Token password
Feature activation+0.356
on
Token on
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
sites
Token sites
Feature activation+0.000
or
Token or
Feature activation+0.000

INTERVAL 0.987 - 1.152
CONTAINS 0.004%

would
Token would
Feature activation+0.000
never
Token never
Feature activation+0.000
say
Token say
Feature activation+0.222
never
Token never
Feature activation+0.713
.
Token.
Feature activation+0.490
But
Token But
Feature activation+1.009
it
Token it
Feature activation+0.378
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.102
s
Tokens
Feature activation+0.000
not
Token not
Feature activation+0.000
ancient
Token ancient
Feature activation+0.000
ancestors
Token ancestors
Feature activation+0.000
never
Token never
Feature activation+0.000
knew
Token knew
Feature activation+0.000
they
Token they
Feature activation+0.757
needed
Token needed
Feature activation+1.025
.
Token.
Feature activation+0.072
Second
Token Second
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
reduced
Token reduced
Feature activation+0.000
bro
Token bro
Feature activation+0.000
tha
Tokentha
Feature activation+0.000
never
Token never
Feature activation+0.000
runs
Token runs
Feature activation+0.040
his
Token his
Feature activation+0.492
little
Token little
Feature activation+1.014
mouth
Token mouth
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.223
Ċ
TokenĊ
Feature activation+0.096
'
Token'
Feature activation+0.000
cause
Tokencause
Feature activation+0.000
."
Token."
Feature activation+0.000
We
TokenWe
Feature activation+0.000
never
Token never
Feature activation+0.040
once
Token once
Feature activation+0.682
imagined
Token imagined
Feature activation+1.136
that
Token that
Feature activation+1.004
this
Token this
Feature activation+0.567
would
Token would
Feature activation+0.750
touch
Token touch
Feature activation+0.334
anyone
Token anyone
Feature activation+0.196
high
Token high
Feature activation+0.000
appearance
Token appearance
Feature activation+0.000
."
Token."
Feature activation+0.000
We
TokenWe
Feature activation+0.000
never
Token never
Feature activation+0.040
once
Token once
Feature activation+0.682
imagined
Token imagined
Feature activation+1.136
that
Token that
Feature activation+1.004
this
Token this
Feature activation+0.567
would
Token would
Feature activation+0.750
touch
Token touch
Feature activation+0.334
anyone
Token anyone
Feature activation+0.196

INTERVAL 0.823 - 0.987
CONTAINS 0.006%

they
Token they
Feature activation+0.000
never
Token never
Feature activation+0.000
make
Token make
Feature activation+0.108
a
Token a
Feature activation+0.887
neutral
Token neutral
Feature activation+0.859
statement
Token statement
Feature activation+0.904
.
Token.
Feature activation+0.338
Someone
Token Someone
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
TSA
Token TSA
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
never
Token never
Feature activation+0.000
get
Token get
Feature activation+0.000
into
Token into
Feature activation+0.103
defining
Token defining
Feature activation+0.875
other
Token other
Feature activation+0.190
people
Token people
Feature activation+0.000
,
Token,
Feature activation+0.485
âĢ
TokenâĢ
Feature activation+0.099
Ŀ
TokenĿ
Feature activation+0.000
d
Tokend
Feature activation+0.000
never
Token never
Feature activation+0.000
really
Token really
Feature activation+0.000
had
Token had
Feature activation+0.144
anyone
Token anyone
Feature activation+0.681
massage
Token massage
Feature activation+0.834
my
Token my
Feature activation+0.683
face
Token face
Feature activation+0.523
and
Token and
Feature activation+1.416
it
Token it
Feature activation+0.512
just
Token just
Feature activation+0.536
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
never
Token never
Feature activation+0.000
a
Token a
Feature activation+0.262
good
Token good
Feature activation+0.858
idea
Token idea
Feature activation+1.152
to
Token to
Feature activation+0.331
rely
Token rely
Feature activation+0.232
on
Token on
Feature activation+0.000
legal
Token legal
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
never
Token never
Feature activation+0.000
seen
Token seen
Feature activation+0.000
anything
Token anything
Feature activation+0.937
like
Token like
Feature activation+1.503
this
Token this
Feature activation+0.188
before
Token before
Feature activation+0.469
âĢĵ
Token âĢĵ
Feature activation+0.388
or
Token or
Feature activation+0.000

INTERVAL 0.658 - 0.823
CONTAINS 0.011%

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
Earth
Token Earth
Feature activation+0.204
(
Token (
Feature activation+0.664
Vol
TokenVol
Feature activation+0.000
va
Tokenva
Feature activation+0.000
),
Token),
Feature activation+0.000
Sub
Token Sub
Feature activation+0.000
vol
Tokenvol
Feature activation+0.000
's
Token's
Feature activation+0.000
never
Token never
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.189
get
Token get
Feature activation+0.000
more
Token more
Feature activation+0.668
deadly
Token deadly
Feature activation+0.330
serious
Token serious
Feature activation+0.000
than
Token than
Feature activation+0.141
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.199
never
Token never
Feature activation+0.178
thought
Token thought
Feature activation+1.217
I
Token I
Feature activation+0.886
'd
Token'd
Feature activation+0.750
say
Token say
Feature activation+0.546
this
Token this
Feature activation+0.777
but
Token but
Feature activation+1.008
,
Token,
Feature activation+0.234
R
Token R
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
ael
Tokenael
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
never
Token never
Feature activation+0.000
been
Token been
Feature activation+0.000
too
Token too
Feature activation+0.493
shy
Token shy
Feature activation+0.787
to
Token to
Feature activation+0.029
grab
Token grab
Feature activation+0.000
its
Token its
Feature activation+0.000
target
Token target
Feature activation+0.000
audience
Token audience
Feature activation+0.000
choice
Token choice
Feature activation+0.000
has
Token has
Feature activation+0.000
never
Token never
Feature activation+0.000
been
Token been
Feature activation+0.000
clearer
Token clearer
Feature activation+1.646
-
Token -
Feature activation+0.722
Donald
Token Donald
Feature activation+0.395
Trump
Token Trump
Feature activation+0.145
calls
Token calls
Feature activation+0.391
on
Token on
Feature activation+0.071
us
Token us
Feature activation+0.000

INTERVAL 0.494 - 0.658
CONTAINS 0.016%

you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
never
Token never
Feature activation+0.000
experienced
Token experienced
Feature activation+0.283
this
Token this
Feature activation+0.463
,
Token,
Feature activation+0.607
but
Token but
Feature activation+0.350
are
Token are
Feature activation+0.102
you
Token you
Feature activation+0.000
sure
Token sure
Feature activation+0.000
?
Token?
Feature activation+0.000
heard
Token heard
Feature activation+0.000
such
Token such
Feature activation+0.861
a
Token a
Feature activation+1.111
tir
Token tir
Feature activation+0.689
ade
Tokenade
Feature activation+0.512
before
Token before
Feature activation+0.582
,
Token,
Feature activation+0.055
not
Token not
Feature activation+0.000
even
Token even
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
never
Token never
Feature activation+0.000
seen
Token seen
Feature activation+0.000
transparency
Token transparency
Feature activation+0.133
be
Token be
Feature activation+0.625
more
Token more
Feature activation+1.015
important
Token important
Feature activation+0.544
and
Token and
Feature activation+1.020
have
Token have
Feature activation+0.000
companies
Token companies
Feature activation+0.000
actively
Token actively
Feature activation+0.000
asking
Token asking
Feature activation+0.000
PRO
Token PRO
Feature activation+0.000
BA
TokenBA
Feature activation+0.000
BL
TokenBL
Feature activation+0.000
Y
TokenY
Feature activation+0.000
NEVER
Token NEVER
Feature activation+0.000
BE
Token BE
Feature activation+0.506
CHAR
Token CHAR
Feature activation+0.318
G
TokenG
Feature activation+0.163
ED
TokenED
Feature activation+0.063
FOR
Token FOR
Feature activation+0.274
)
Token)
Feature activation+0.222
you
Token you
Feature activation+0.000
've
Token've
Feature activation+0.000
never
Token never
Feature activation+0.000
seen
Token seen
Feature activation+0.000
it
Token it
Feature activation+0.180
before
Token before
Feature activation+0.495
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
know
Token know
Feature activation+0.000
the
Token the
Feature activation+0.000
rules
Token rules
Feature activation+0.000

INTERVAL 0.329 - 0.494
CONTAINS 0.024%

should
Token should
Feature activation+0.000
never
Token never
Feature activation+0.000
use
Token use
Feature activation+0.000
the
Token the
Feature activation+0.324
same
Token same
Feature activation+1.190
password
Token password
Feature activation+0.356
on
Token on
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
sites
Token sites
Feature activation+0.000
or
Token or
Feature activation+0.000
services
Token services
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Have
TokenHave
Feature activation+0.000
you
Token you
Feature activation+0.000
ever
Token ever
Feature activation+0.000
noticed
Token noticed
Feature activation+0.575
that
Token that
Feature activation+0.341
whenever
Token whenever
Feature activation+0.256
it
Token it
Feature activation+0.000
comes
Token comes
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Never
TokenNever
Feature activation+0.092
in
Token in
Feature activation+0.000
human
Token human
Feature activation+0.359
f
Token f
Feature activation+0.241
***
Token***
Feature activation+0.346
ing
Tokening
Feature activation+0.000
history
Token history
Feature activation+0.000
,
Token,
Feature activation+0.006
since
Token since
Feature activation+0.000
fish
Token fish
Feature activation+0.000
Too
TokenToo
Feature activation+0.000
bad
Token bad
Feature activation+0.000
the
Token the
Feature activation+0.000
bureaucrats
Token bureaucrats
Feature activation+0.000
never
Token never
Feature activation+0.000
consider
Token consider
Feature activation+0.408
the
Token the
Feature activation+0.208
reverse
Token reverse
Feature activation+0.775
:
Token:
Feature activation+0.014
What
Token What
Feature activation+0.000
if
Token if
Feature activation+0.000
never
Token never
Feature activation+0.000
be
Token be
Feature activation+0.400
able
Token able
Feature activation+0.308
to
Token to
Feature activation+0.000
find
Token find
Feature activation+0.000
,
Token,
Feature activation+0.337
such
Token such
Feature activation+0.012
as
Token as
Feature activation+0.000
mis
Token mis
Feature activation+0.000
stat
Tokenstat
Feature activation+0.000
ements
Tokenements
Feature activation+0.000

INTERVAL 0.165 - 0.329
CONTAINS 0.041%

Have
TokenHave
Feature activation+0.000
you
Token you
Feature activation+0.000
ever
Token ever
Feature activation+0.000
noticed
Token noticed
Feature activation+0.575
that
Token that
Feature activation+0.341
whenever
Token whenever
Feature activation+0.256
it
Token it
Feature activation+0.000
comes
Token comes
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
stand
Token stand
Feature activation+0.000
again
Token again
Feature activation+0.007
promises
Token promises
Feature activation+0.812
were
Token were
Feature activation+0.393
a
Token a
Feature activation+0.398
deterrent
Token deterrent
Feature activation+0.213
especially
Token especially
Feature activation+0.193
when
Token when
Feature activation+0.000
there
Token there
Feature activation+0.000
were
Token were
Feature activation+0.000
repeated
Token repeated
Feature activation+0.000
problems
Token problems
Feature activation+0.000
,
Token,
Feature activation+0.000
none
Token none
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
created
Token created
Feature activation+0.000
yet
Token yet
Feature activation+0.182
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
captain
Token captain
Feature activation+0.000
,
Token,
Feature activation+0.000
Jeb
Token Jeb
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
seldom
Token seldom
Feature activation+0.000
tell
Token tell
Feature activation+0.000
the
Token the
Feature activation+0.021
truth
Token truth
Feature activation+0.241
about
Token about
Feature activation+0.000
their
Token their
Feature activation+0.000
brutal
Token brutal
Feature activation+0.000
encounters
Token encounters
Feature activation+0.000
with
Token with
Feature activation+0.000
to
Token to
Feature activation+0.547
see
Token see
Feature activation+0.006
me
Token me
Feature activation+0.275
and
Token and
Feature activation+1.233
there
Token there
Feature activation+0.092
had
Token had
Feature activation+0.168
been
Token been
Feature activation+0.029
no
Token no
Feature activation+0.000
restraining
Token restraining
Feature activation+0.000
order
Token order
Feature activation+0.000
against
Token against
Feature activation+0.000

INTERVAL 0.000 - 0.165
CONTAINS 99.894%

bothering
Token bothering
Feature activation+0.000
her
Token her
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
major
Token major
Feature activation+0.000
,''
Token,''
Feature activation+0.000
a
Token a
Feature activation+0.000
source
Token source
Feature activation+0.000
standing
Token standing
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
-
Token-
Feature activation+0.000
largest
Tokenlargest
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
North
Token North
Feature activation+0.000
Pat
Token Pat
Feature activation+0.000
agon
Tokenagon
Feature activation+0.000
a
Token a
Feature activation+0.000
p
Token p
Feature activation+0.000
iet
Tokeniet
Feature activation+0.000
istic
Tokenistic
Feature activation+0.000
Protestant
Token Protestant
Feature activation+0.000
movement
Token movement
Feature activation+0.000
know
Token know
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
An
Token An
Feature activation+0.000
ab
Tokenab
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
Diego
Token Diego
Feature activation+0.000
Rivera
Token Rivera
Feature activation+0.000
and
Token and
Feature activation+0.000
R
Token R
Feature activation+0.000
uf
Tokenuf
Feature activation+0.000
ino
Tokenino
Feature activation+0.000
Tam
Token Tam
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
o
Tokeno
Feature activation+0.000
knew
Token knew
Feature activation+0.000
we
Token we
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+0.000
disco
Token disco
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H2.0: (feature 8272)

TOP ACTIVATIONS
MAX = 2.554

getting
Token getting
Feature activation+0.000
thousands
Token thousands
Feature activation+0.482
of
Token of
Feature activation+0.562
views
Token views
Feature activation+1.040
a
Token a
Feature activation+1.026
day
Token day
Feature activation+2.554
,
Token,
Feature activation+0.088
had
Token had
Feature activation+0.078
already
Token already
Feature activation+0.011
been
Token been
Feature activation+0.000
up
Token up
Feature activation+0.064
currently
Token currently
Feature activation+0.000
is
Token is
Feature activation+0.000
for
Token for
Feature activation+0.000
thousands
Token thousands
Feature activation+0.052
of
Token of
Feature activation+0.162
years
Token years
Feature activation+2.371
,
Token,
Feature activation+0.000
hundreds
Token hundreds
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+0.993
.
Token.
Feature activation+0.000
has
Token has
Feature activation+0.000
existed
Token existed
Feature activation+0.000
for
Token for
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+2.200
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Clinton
TokenClinton
Feature activation+0.000
appeared
Token appeared
Feature activation+0.000
area
Token area
Feature activation+0.000
dating
Token dating
Feature activation+0.000
back
Token back
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+2.146
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.000
and
Token and
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
thousand
Token thousand
Feature activation+0.000
year
Token year
Feature activation+1.969
el
Token el
Feature activation+0.000
ixir
Tokenixir
Feature activation+0.000
whenever
Token whenever
Feature activation+0.000
possible
Token possible
Feature activation+0.000
.
Token.
Feature activation+0.000
national
Token national
Feature activation+0.000
forum
Token forum
Feature activation+0.000
where
Token where
Feature activation+0.000
a
Token a
Feature activation+0.000
thousand
Token thousand
Feature activation+0.899
attendees
Token attendees
Feature activation+1.966
where
Token where
Feature activation+0.997
chosen
Token chosen
Feature activation+0.871
by
Token by
Feature activation+0.000
lottery
Token lottery
Feature activation+0.000
.
Token.
Feature activation+0.000
gathers
Token gathers
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
a
Token a
Feature activation+0.000
million
Token million
Feature activation+0.422
signatures
Token signatures
Feature activation+1.938
across
Token across
Feature activation+0.374
a
Token a
Feature activation+0.437
minimum
Token minimum
Feature activation+0.653
of
Token of
Feature activation+0.000
seven
Token seven
Feature activation+0.000
for
Token for
Feature activation+0.000
hundreds
Token hundreds
Feature activation+0.000
of
Token of
Feature activation+0.000
millions
Token millions
Feature activation+0.020
of
Token of
Feature activation+0.000
years
Token years
Feature activation+1.904
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
may
Token may
Feature activation+0.000
carry
Token carry
Feature activation+0.000
advantages
Token advantages
Feature activation+0.000
this
Token this
Feature activation+0.000
cave
Token cave
Feature activation+0.000
for
Token for
Feature activation+0.000
thousands
Token thousands
Feature activation+0.038
of
Token of
Feature activation+0.000
years
Token years
Feature activation+1.877
,
Token,
Feature activation+0.000
during
Token during
Feature activation+0.000
which
Token which
Feature activation+0.000
time
Token time
Feature activation+0.000
bats
Token bats
Feature activation+0.000
with
Token with
Feature activation+0.000
us
Token us
Feature activation+0.000
for
Token for
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+1.856
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
making
Token making
Feature activation+0.000
a
Token a
Feature activation+0.000
comeback
Token comeback
Feature activation+0.000
possible
Token possible
Feature activation+0.000
that
Token that
Feature activation+0.000
this
Token this
Feature activation+0.000
thousand
Token thousand
Feature activation+0.184
-
Token-
Feature activation+0.475
strong
Tokenstrong
Feature activation+1.843
group
Token group
Feature activation+1.078
was
Token was
Feature activation+0.700
able
Token able
Feature activation+0.372
to
Token to
Feature activation+0.053
come
Token come
Feature activation+0.261
millions
Token millions
Feature activation+0.000
of
Token of
Feature activation+0.189
dollars
Token dollars
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
years
Token years
Feature activation+1.776
from
Token from
Feature activation+0.000
industry
Token industry
Feature activation+0.000
like
Token like
Feature activation+0.000
Exxon
Token Exxon
Feature activation+0.000
Mobil
TokenMobil
Feature activation+0.000
;
Token;
Feature activation+0.000
polar
Token polar
Feature activation+0.000
bears
Token bears
Feature activation+0.000
a
Token a
Feature activation+0.000
million
Token million
Feature activation+0.439
times
Token times
Feature activation+1.755
less
Token less
Feature activation+1.191
.
Token.
Feature activation+0.045
To
Token To
Feature activation+0.000
say
Token say
Feature activation+0.000
this
Token this
Feature activation+0.000
were
Token were
Feature activation+0.000
thousands
Token thousands
Feature activation+0.301
of
Token of
Feature activation+0.426
person
Token person
Feature activation+0.453
-
Token-
Feature activation+0.000
years
Tokenyears
Feature activation+1.678
of
Token of
Feature activation+0.347
studying
Token studying
Feature activation+0.000
animal
Token animal
Feature activation+0.000
behavior
Token behavior
Feature activation+0.000
in
Token in
Feature activation+0.000
Images
Token Images
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
CLOSE
TokenCLOSE
Feature activation+0.000
This
Token This
Feature activation+0.000
million
Token million
Feature activation+0.107
dollar
Token dollar
Feature activation+1.600
t
Token t
Feature activation+0.341
-
Token-
Feature activation+0.142
shirt
Tokenshirt
Feature activation+0.528
making
Token making
Feature activation+0.000
company
Token company
Feature activation+0.127
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
million
Token million
Feature activation+0.430
other
Token other
Feature activation+0.759
sources
Token sources
Feature activation+1.474
(
Token (
Feature activation+0.716
especially
Tokenespecially
Feature activation+0.393
folk
Token folk
Feature activation+0.185
)
Token)
Feature activation+0.000
before
Token before
Feature activation+0.000
two
Token two
Feature activation+0.000
million
Token million
Feature activation+0.000
UK
Token UK
Feature activation+0.000
consumers
Token consumers
Feature activation+0.195
a
Token a
Feature activation+0.147
year
Token year
Feature activation+1.400
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
large
Token large
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
of
Token of
Feature activation+0.000
picture
Token picture
Feature activation+0.000
is
Token is
Feature activation+0.000
worth
Token worth
Feature activation+0.000
a
Token a
Feature activation+0.000
thousand
Token thousand
Feature activation+0.923
words
Token words
Feature activation+1.372
Ċ
TokenĊ
Feature activation+0.205
Ċ
TokenĊ
Feature activation+0.137
Data
TokenData
Feature activation+0.206
pages
Token pages
Feature activation+0.562
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
hundred
Token hundred
Feature activation+0.879
years
Token years
Feature activation+1.331
ago
Token ago
Feature activation+0.302
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
Images
Token Images
Feature activation+0.000
)
Token)
Feature activation+0.000
Four
Token Four
Feature activation+0.000
million
Token million
Feature activation+0.000
people
Token people
Feature activation+0.867
around
Token around
Feature activation+1.313
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.354
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
500
Token 500
Feature activation+0.000

Top DFA by src position
MAX = 2.796

.
Token.
Feature activation-0.023
Top resid features:
The
Token The
Feature activation+0.027
Top resid features:
video
Token video
Feature activation+0.063
Top resid features:
was
Token was
Feature activation+0.066
Top resid features:
getting
Token getting
Feature activation+0.037
Top resid features:
thousands
Token thousands
Feature activation+2.607
Top resid features:
of
Token of
Feature activation-0.033
Top resid features:
views
Token views
Feature activation+0.116
Top resid features:
a
Token a
Feature activation+0.151
Top resid features:
day
Token day
Feature activation+0.081
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
way
Token way
Feature activation+0.018
Top resid features:
it
Token it
Feature activation+0.029
Top resid features:
currently
Token currently
Feature activation+0.033
Top resid features:
is
Token is
Feature activation+0.054
Top resid features:
for
Token for
Feature activation+0.085
Top resid features:
thousands
Token thousands
Feature activation+2.796
Top resid features:
of
Token of
Feature activation-0.032
Top resid features:
years
Token years
Feature activation+0.077
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
hundreds
Token hundreds
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Child
TokenChild
Feature activation+0.021
Top resid features:
marriage
Token marriage
Feature activation+0.036
Top resid features:
has
Token has
Feature activation+0.040
Top resid features:
existed
Token existed
Feature activation+0.027
Top resid features:
for
Token for
Feature activation+0.050
Top resid features:
thousands
Token thousands
Feature activation+2.736
Top resid features:
of
Token of
Feature activation-0.088
Top resid features:
years
Token years
Feature activation+0.081
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
about
Token about
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.046
Top resid features:
area
Token area
Feature activation+0.027
Top resid features:
dating
Token dating
Feature activation+0.011
Top resid features:
back
Token back
Feature activation+0.223
Top resid features:
thousands
Token thousands
Feature activation+2.685
Top resid features:
of
Token of
Feature activation-0.024
Top resid features:
years
Token years
Feature activation+0.071
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:
combos
Token combos
Feature activation+0.029
Top resid features:
and
Token and
Feature activation+0.018
Top resid features:
abuse
Token abuse
Feature activation+0.058
Top resid features:
of
Token of
Feature activation-0.009
Top resid features:
the
Token the
Feature activation+0.085
Top resid features:
thousand
Token thousand
Feature activation+2.258
Top resid features:
year
Token year
Feature activation+0.075
Top resid features:
el
Token el
Feature activation+0.000
Top resid features:
ixir
Tokenixir
Feature activation+0.000
Top resid features:
whenever
Token whenever
Feature activation+0.000
Top resid features:
possible
Token possible
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.049
Top resid features:
national
Token national
Feature activation+0.035
Top resid features:
forum
Token forum
Feature activation+0.054
Top resid features:
where
Token where
Feature activation-0.037
Top resid features:
a
Token a
Feature activation+0.160
Top resid features:
thousand
Token thousand
Feature activation+2.164
Top resid features:
attendees
Token attendees
Feature activation+0.059
Top resid features:
where
Token where
Feature activation+0.000
Top resid features:
chosen
Token chosen
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
lottery
Token lottery
Feature activation+0.000
Top resid features:
petition
Token petition
Feature activation+0.070
Top resid features:
gathers
Token gathers
Feature activation+0.116
Top resid features:
more
Token more
Feature activation+0.024
Top resid features:
than
Token than
Feature activation-0.057
Top resid features:
a
Token a
Feature activation+0.117
Top resid features:
million
Token million
Feature activation+2.191
Top resid features:
signatures
Token signatures
Feature activation+0.067
Top resid features:
across
Token across
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
minimum
Token minimum
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
doing
Token doing
Feature activation+0.015
Top resid features:
it
Token it
Feature activation+0.017
Top resid features:
for
Token for
Feature activation+0.052
Top resid features:
hundreds
Token hundreds
Feature activation+0.812
Top resid features:
of
Token of
Feature activation-0.038
Top resid features:
millions
Token millions
Feature activation+1.639
Top resid features:
of
Token of
Feature activation-0.086
Top resid features:
years
Token years
Feature activation+0.048
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
may
Token may
Feature activation+0.000
Top resid features:
inund
Token inund
Feature activation+0.019
Top resid features:
ating
Tokenating
Feature activation+0.019
Top resid features:
this
Token this
Feature activation+0.016
Top resid features:
cave
Token cave
Feature activation+0.035
Top resid features:
for
Token for
Feature activation+0.074
Top resid features:
thousands
Token thousands
Feature activation+2.232
Top resid features:
of
Token of
Feature activation-0.087
Top resid features:
years
Token years
Feature activation+0.077
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
during
Token during
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.051
Top resid features:
been
Token been
Feature activation+0.036
Top resid features:
with
Token with
Feature activation+0.036
Top resid features:
us
Token us
Feature activation+0.082
Top resid features:
for
Token for
Feature activation+0.076
Top resid features:
thousands
Token thousands
Feature activation+2.282
Top resid features:
of
Token of
Feature activation-0.052
Top resid features:
years
Token years
Feature activation+0.075
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
making
Token making
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.043
Top resid features:
was
Token was
Feature activation+0.042
Top resid features:
possible
Token possible
Feature activation+0.010
Top resid features:
that
Token that
Feature activation-0.092
Top resid features:
this
Token this
Feature activation+0.015
Top resid features:
thousand
Token thousand
Feature activation+2.242
Top resid features:
-
Token-
Feature activation+0.016
Top resid features:
strong
Tokenstrong
Feature activation+0.052
Top resid features:
group
Token group
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
able
Token able
Feature activation+0.000
Top resid features:
regulations
Token regulations
Feature activation+0.014
Top resid features:
,
Token,
Feature activation-0.022
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
has
Token has
Feature activation+0.040
Top resid features:
taken
Token taken
Feature activation+0.054
Top resid features:
millions
Token millions
Feature activation+2.125
Top resid features:
of
Token of
Feature activation-0.016
Top resid features:
dollars
Token dollars
Feature activation-0.014
Top resid features:
over
Token over
Feature activation+0.118
Top resid features:
the
Token the
Feature activation+0.120
Top resid features:
years
Token years
Feature activation+0.113
Top resid features:
wild
Token wild
Feature activation+0.006
Top resid features:
;
Token;
Feature activation-0.098
Top resid features:
polar
Token polar
Feature activation+0.015
Top resid features:
bears
Token bears
Feature activation-0.000
Top resid features:
a
Token a
Feature activation+0.158
Top resid features:
million
Token million
Feature activation+2.033
Top resid features:
times
Token times
Feature activation+0.205
Top resid features:
less
Token less
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:
say
Token say
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.017
Top resid features:
childhood
Token childhood
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.059
Top resid features:
There
Token There
Feature activation+0.061
Top resid features:
were
Token were
Feature activation+0.075
Top resid features:
thousands
Token thousands
Feature activation+2.176
Top resid features:
of
Token of
Feature activation-0.040
Top resid features:
person
Token person
Feature activation-0.039
Top resid features:
-
Token-
Feature activation-0.007
Top resid features:
years
Tokenyears
Feature activation+0.131
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Getty
TokenGetty
Feature activation+0.008
Top resid features:
Images
Token Images
Feature activation+0.016
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.087
Top resid features:
CLOSE
TokenCLOSE
Feature activation-0.050
Top resid features:
This
Token This
Feature activation-0.008
Top resid features:
million
Token million
Feature activation+2.279
Top resid features:
dollar
Token dollar
Feature activation+0.121
Top resid features:
t
Token t
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
shirt
Tokenshirt
Feature activation+0.000
Top resid features:
making
Token making
Feature activation+0.000
Top resid features:
Willie
Token Willie
Feature activation-0.026
Top resid features:
Dixon
Token Dixon
Feature activation-0.043
Top resid features:
)
Token)
Feature activation-0.040
Top resid features:
and
Token and
Feature activation-0.045
Top resid features:
a
Token a
Feature activation+0.117
Top resid features:
million
Token million
Feature activation+1.881
Top resid features:
other
Token other
Feature activation+0.050
Top resid features:
sources
Token sources
Feature activation+0.146
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
especially
Tokenespecially
Feature activation+0.000
Top resid features:
folk
Token folk
Feature activation+0.000
Top resid features:
effective
Token effective
Feature activation+0.011
Top resid features:
restriction
Token restriction
Feature activation+0.021
Top resid features:
to
Token to
Feature activation-0.024
Top resid features:
about
Token about
Feature activation-0.009
Top resid features:
two
Token two
Feature activation-0.047
Top resid features:
million
Token million
Feature activation+1.980
Top resid features:
UK
Token UK
Feature activation-0.064
Top resid features:
consumers
Token consumers
Feature activation-0.111
Top resid features:
a
Token a
Feature activation+0.172
Top resid features:
year
Token year
Feature activation+0.106
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
A
TokenA
Feature activation+0.043
Top resid features:
picture
Token picture
Feature activation+0.111
Top resid features:
is
Token is
Feature activation+0.112
Top resid features:
worth
Token worth
Feature activation+0.013
Top resid features:
a
Token a
Feature activation+0.111
Top resid features:
thousand
Token thousand
Feature activation+1.566
Top resid features:
words
Token words
Feature activation+0.086
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Data
TokenData
Feature activation+0.000
Top resid features:
pages
Token pages
Feature activation+0.000
Top resid features:
know
Token know
Feature activation+0.061
Top resid features:
,
Token,
Feature activation-0.041
Top resid features:
it
Token it
Feature activation+0.008
Top resid features:
was
Token was
Feature activation+0.102
Top resid features:
a
Token a
Feature activation+0.107
Top resid features:
hundred
Token hundred
Feature activation+1.585
Top resid features:
years
Token years
Feature activation+0.125
Top resid features:
ago
Token ago
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:
via
Token via
Feature activation-0.000
Top resid features:
Getty
Token Getty
Feature activation+0.017
Top resid features:
Images
Token Images
Feature activation-0.003
Top resid features:
)
Token)
Feature activation-0.016
Top resid features:
Four
Token Four
Feature activation-0.058
Top resid features:
million
Token million
Feature activation+2.071
Top resid features:
people
Token people
Feature activation+0.017
Top resid features:
around
Token around
Feature activation-0.075
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
world
Token world
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.33

Head 1: 0.04

Head 2: 0.04

Head 3: 0.07

Head 4: 0.08

Head 5: 0.07

Head 6: 0.03

Head 7: 0.03

Head 8: 0.05

Head 9: 0.15

Head 10: 0.07

Head 11: 0.03

Positive logits

oké1.36

pees1.35

panic1.35

etimes1.30

worm1.29

iversary1.29

illion1.27

Rot1.25

aceae1.25

akra1.25

enium1.25

quartered1.24

million1.23

itsu1.22

ruciating1.22

reciation1.22

mable1.22

tiny1.21

uggle1.21

Shap1.21

Negative logits

ettings-1.37

outcomes-1.36

encour-1.33

iquette-1.30

policies-1.24

conspicuous-1.24

footing-1.21

fare-1.21

preferences-1.20

dictate-1.17

objectives-1.17

nonetheless-1.16

retaining-1.15

retains-1.15

Otherwise-1.15

semantics-1.15

albeit-1.14

criteria-1.13

igning-1.13

ally-1.13

INTERVAL 2.298 - 2.554
CONTAINS 0.000%

getting
Token getting
Feature activation+0.000
thousands
Token thousands
Feature activation+0.482
of
Token of
Feature activation+0.562
views
Token views
Feature activation+1.040
a
Token a
Feature activation+1.026
day
Token day
Feature activation+2.554
,
Token,
Feature activation+0.088
had
Token had
Feature activation+0.078
already
Token already
Feature activation+0.011
been
Token been
Feature activation+0.000
up
Token up
Feature activation+0.064
currently
Token currently
Feature activation+0.000
is
Token is
Feature activation+0.000
for
Token for
Feature activation+0.000
thousands
Token thousands
Feature activation+0.052
of
Token of
Feature activation+0.162
years
Token years
Feature activation+2.371
,
Token,
Feature activation+0.000
hundreds
Token hundreds
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+0.993
.
Token.
Feature activation+0.000

INTERVAL 2.043 - 2.298
CONTAINS 0.000%

has
Token has
Feature activation+0.000
existed
Token existed
Feature activation+0.000
for
Token for
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+2.200
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Clinton
TokenClinton
Feature activation+0.000
appeared
Token appeared
Feature activation+0.000
area
Token area
Feature activation+0.000
dating
Token dating
Feature activation+0.000
back
Token back
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+2.146
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.000

INTERVAL 1.788 - 2.043
CONTAINS 0.001%

national
Token national
Feature activation+0.000
forum
Token forum
Feature activation+0.000
where
Token where
Feature activation+0.000
a
Token a
Feature activation+0.000
thousand
Token thousand
Feature activation+0.899
attendees
Token attendees
Feature activation+1.966
where
Token where
Feature activation+0.997
chosen
Token chosen
Feature activation+0.871
by
Token by
Feature activation+0.000
lottery
Token lottery
Feature activation+0.000
.
Token.
Feature activation+0.000
possible
Token possible
Feature activation+0.000
that
Token that
Feature activation+0.000
this
Token this
Feature activation+0.000
thousand
Token thousand
Feature activation+0.184
-
Token-
Feature activation+0.475
strong
Tokenstrong
Feature activation+1.843
group
Token group
Feature activation+1.078
was
Token was
Feature activation+0.700
able
Token able
Feature activation+0.372
to
Token to
Feature activation+0.053
come
Token come
Feature activation+0.261
for
Token for
Feature activation+0.000
hundreds
Token hundreds
Feature activation+0.000
of
Token of
Feature activation+0.000
millions
Token millions
Feature activation+0.020
of
Token of
Feature activation+0.000
years
Token years
Feature activation+1.904
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
may
Token may
Feature activation+0.000
carry
Token carry
Feature activation+0.000
advantages
Token advantages
Feature activation+0.000
gathers
Token gathers
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
a
Token a
Feature activation+0.000
million
Token million
Feature activation+0.422
signatures
Token signatures
Feature activation+1.938
across
Token across
Feature activation+0.374
a
Token a
Feature activation+0.437
minimum
Token minimum
Feature activation+0.653
of
Token of
Feature activation+0.000
seven
Token seven
Feature activation+0.000
with
Token with
Feature activation+0.000
us
Token us
Feature activation+0.000
for
Token for
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+1.856
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
making
Token making
Feature activation+0.000
a
Token a
Feature activation+0.000
comeback
Token comeback
Feature activation+0.000

INTERVAL 1.532 - 1.788
CONTAINS 0.001%

;
Token;
Feature activation+0.000
polar
Token polar
Feature activation+0.000
bears
Token bears
Feature activation+0.000
a
Token a
Feature activation+0.000
million
Token million
Feature activation+0.439
times
Token times
Feature activation+1.755
less
Token less
Feature activation+1.191
.
Token.
Feature activation+0.045
To
Token To
Feature activation+0.000
say
Token say
Feature activation+0.000
this
Token this
Feature activation+0.000
were
Token were
Feature activation+0.000
thousands
Token thousands
Feature activation+0.301
of
Token of
Feature activation+0.426
person
Token person
Feature activation+0.453
-
Token-
Feature activation+0.000
years
Tokenyears
Feature activation+1.678
of
Token of
Feature activation+0.347
studying
Token studying
Feature activation+0.000
animal
Token animal
Feature activation+0.000
behavior
Token behavior
Feature activation+0.000
in
Token in
Feature activation+0.000
millions
Token millions
Feature activation+0.000
of
Token of
Feature activation+0.189
dollars
Token dollars
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
years
Token years
Feature activation+1.776
from
Token from
Feature activation+0.000
industry
Token industry
Feature activation+0.000
like
Token like
Feature activation+0.000
Exxon
Token Exxon
Feature activation+0.000
Mobil
TokenMobil
Feature activation+0.000
Images
Token Images
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
CLOSE
TokenCLOSE
Feature activation+0.000
This
Token This
Feature activation+0.000
million
Token million
Feature activation+0.107
dollar
Token dollar
Feature activation+1.600
t
Token t
Feature activation+0.341
-
Token-
Feature activation+0.142
shirt
Tokenshirt
Feature activation+0.528
making
Token making
Feature activation+0.000
company
Token company
Feature activation+0.127

INTERVAL 1.277 - 1.532
CONTAINS 0.001%

Images
Token Images
Feature activation+0.000
)
Token)
Feature activation+0.000
Four
Token Four
Feature activation+0.000
million
Token million
Feature activation+0.000
people
Token people
Feature activation+0.867
around
Token around
Feature activation+1.313
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.354
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
500
Token 500
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
million
Token million
Feature activation+0.430
other
Token other
Feature activation+0.759
sources
Token sources
Feature activation+1.474
(
Token (
Feature activation+0.716
especially
Tokenespecially
Feature activation+0.393
folk
Token folk
Feature activation+0.185
)
Token)
Feature activation+0.000
before
Token before
Feature activation+0.000
picture
Token picture
Feature activation+0.000
is
Token is
Feature activation+0.000
worth
Token worth
Feature activation+0.000
a
Token a
Feature activation+0.000
thousand
Token thousand
Feature activation+0.923
words
Token words
Feature activation+1.372
Ċ
TokenĊ
Feature activation+0.205
Ċ
TokenĊ
Feature activation+0.137
Data
TokenData
Feature activation+0.206
pages
Token pages
Feature activation+0.562
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
hundred
Token hundred
Feature activation+0.879
years
Token years
Feature activation+1.331
ago
Token ago
Feature activation+0.302
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
At
TokenAt
Feature activation+0.000
two
Token two
Feature activation+0.000
million
Token million
Feature activation+0.000
UK
Token UK
Feature activation+0.000
consumers
Token consumers
Feature activation+0.195
a
Token a
Feature activation+0.147
year
Token year
Feature activation+1.400
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
large
Token large
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.021 - 1.277
CONTAINS 0.002%

a
Token a
Feature activation+0.000
million
Token million
Feature activation+0.884
unf
Token unf
Feature activation+0.732
illed
Tokenilled
Feature activation+0.419
computer
Token computer
Feature activation+0.825
science
Token science
Feature activation+1.248
âĢĵ
TokenâĢĵ
Feature activation+0.615
related
Tokenrelated
Feature activation+0.644
jobs
Token jobs
Feature activation+0.140
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.000
over
Token over
Feature activation+0.000
500
Token 500
Feature activation+0.000
million
Token million
Feature activation+0.000
years
Token years
Feature activation+1.238
old
Token old
Feature activation+0.367
,
Token,
Feature activation+0.041
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.383
a
Token a
Feature activation+0.555
demand
Token demand
Feature activation+0.000
was
Token was
Feature activation+0.000
overwhelming
Token overwhelming
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
hundred
Token hundred
Feature activation+1.070
and
Token and
Feature activation+0.000
eighty
Token eighty
Feature activation+0.036
refugees
Token refugees
Feature activation+0.000
turned
Token turned
Feature activation+0.305
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
billion
Token billion
Feature activation+0.113
-
Token-
Feature activation+0.000
dollar
Tokendollar
Feature activation+0.336
franchise
Token franchise
Feature activation+0.827
club
Token club
Feature activation+1.064
later
Token later
Feature activation+0.041
this
Token this
Feature activation+0.000
week
Token week
Feature activation+0.259
.
Token.
Feature activation+0.000
Not
Token Not
Feature activation+0.000
An
Token An
Feature activation+0.000
auction
Token auction
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
A
TokenA
Feature activation+0.000
hundred
Token hundred
Feature activation+1.099
years
Token years
Feature activation+1.189
ago
Token ago
Feature activation+0.168
yesterday
Token yesterday
Feature activation+0.836
,
Token,
Feature activation+0.064
Germany
Token Germany
Feature activation+0.072
invaded
Token invaded
Feature activation+0.000

INTERVAL 0.766 - 1.021
CONTAINS 0.004%

final
Token final
Feature activation+0.000
break
Token break
Feature activation+0.000
the
Token the
Feature activation+0.000
billion
Token billion
Feature activation+0.000
dollar
Token dollar
Feature activation+0.291
mark
Token mark
Feature activation+1.012
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
worldwide
Token worldwide
Feature activation+0.000
box
Token box
Feature activation+0.000
office
Token office
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
70
Token70
Feature activation+0.000
billion
Token billion
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.366
is
Token is
Feature activation+0.948
the
Token the
Feature activation+0.798
first
Token first
Feature activation+0.569
major
Token major
Feature activation+0.000
deal
Token deal
Feature activation+0.000
for
Token for
Feature activation+0.000
s
Tokens
Feature activation+0.000
millions
Token millions
Feature activation+0.000
of
Token of
Feature activation+0.079
supporters
Token supporters
Feature activation+0.904
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.786
care
Token care
Feature activation+0.121
about
Token about
Feature activation+0.505
any
Token any
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
joins
Token joins
Feature activation+0.000
the
Token the
Feature activation+0.000
billion
Token billion
Feature activation+0.113
-
Token-
Feature activation+0.000
dollar
Tokendollar
Feature activation+0.336
franchise
Token franchise
Feature activation+0.827
club
Token club
Feature activation+1.064
later
Token later
Feature activation+0.041
this
Token this
Feature activation+0.000
week
Token week
Feature activation+0.259
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
nine
Token nine
Feature activation+0.000
-
Token-
Feature activation+0.000
million
Tokenmillion
Feature activation+0.000
-
Token-
Feature activation+0.102
euro
Tokeneuro
Feature activation+0.919
loan
Token loan
Feature activation+0.354
in
Token in
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
r
Tokenr
Feature activation+0.000
ul
Tokenul
Feature activation+0.000

INTERVAL 0.511 - 0.766
CONTAINS 0.008%

had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
million
Token million
Feature activation+0.672
-
Token-
Feature activation+0.368
dollar
Tokendollar
Feature activation+0.816
lottery
Token lottery
Feature activation+0.609
ticket
Token ticket
Feature activation+0.996
in
Token in
Feature activation+0.156
their
Token their
Feature activation+0.000
hands
Token hands
Feature activation+0.051
,
Token,
Feature activation+0.000
10
Token 10
Feature activation+0.000
million
Token million
Feature activation+0.000
users
Token users
Feature activation+0.238
is
Token is
Feature activation+0.077
the
Token the
Feature activation+0.354
new
Token new
Feature activation+0.700
1
Token 1
Feature activation+0.000
million
Token million
Feature activation+0.061
users
Token users
Feature activation+0.467
.
Token.
Feature activation+0.000
10
Token 10
Feature activation+0.000
23
Token23
Feature activation+0.000
]
Token]
Feature activation+0.000
Seven
Token Seven
Feature activation+0.000
thousand
Token thousand
Feature activation+0.000
people
Token people
Feature activation+0.550
gathered
Token gathered
Feature activation+0.609
to
Token to
Feature activation+0.000
witness
Token witness
Feature activation+0.000
the
Token the
Feature activation+0.027
unveiling
Token unveiling
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
disease
Token disease
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
hundred
Token hundred
Feature activation+0.538
days
Token days
Feature activation+0.681
without
Token without
Feature activation+0.000
a
Token a
Feature activation+0.421
Batman
Token Batman
Feature activation+0.000
,
Token,
Feature activation+0.000
police
Token police
Feature activation+0.000
wave
Token wave
Feature activation+0.000
of
Token of
Feature activation+0.000
disease
Token disease
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
hundred
Token hundred
Feature activation+0.538
days
Token days
Feature activation+0.681
without
Token without
Feature activation+0.000
a
Token a
Feature activation+0.421
Batman
Token Batman
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.255 - 0.511
CONTAINS 0.019%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
has
Token has
Feature activation+0.000
traveled
Token traveled
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
of
Token of
Feature activation+0.000
miles
Token miles
Feature activation+0.288
and
Token and
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.220
week
Token week
Feature activation+1.119
three
Token three
Feature activation+0.000
thousand
Token thousand
Feature activation+0.000
billion
Token billion
Feature activation+0.042
trillion
Token trillion
Feature activation+0.035
entries
Token entries
Feature activation+0.608
,
Token,
Feature activation+0.296
and
Token and
Feature activation+0.345
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
contacted
Token contacted
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
a
Token a
Feature activation+0.000
dozen
Token dozen
Feature activation+0.000
people
Token people
Feature activation+0.458
who
Token who
Feature activation+0.000
attended
Token attended
Feature activation+0.000
the
Token the
Feature activation+0.000
party
Token party
Feature activation+0.000
and
Token and
Feature activation+0.000
few
Token few
Feature activation+0.000
hundred
Token hundred
Feature activation+0.062
k
Token k
Feature activation+0.000
ms
Tokenms
Feature activation+0.000
,
Token,
Feature activation+0.016
the
Token the
Feature activation+0.366
journey
Token journey
Feature activation+0.316
took
Token took
Feature activation+0.000
24
Token 24
Feature activation+0.000
hours
Token hours
Feature activation+0.000
and
Token and
Feature activation+0.000
melt
Token melt
Feature activation+0.000
4
Token 4
Feature activation+0.000
.
Token.
Feature activation+0.000
23
Token23
Feature activation+0.000
million
Token million
Feature activation+0.000
years
Token years
Feature activation+0.400
ago
Token ago
Feature activation+0.478
.
Token.
Feature activation+0.000
Image
Token Image
Feature activation+0.000
source
Token source
Feature activation+0.000
:
Token:
Feature activation+0.000

INTERVAL 0.000 - 0.255
CONTAINS 99.964%

they
Token they
Feature activation+0.000
've
Token've
Feature activation+0.000
done
Token done
Feature activation+0.000
as
Token as
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
an
Token an
Feature activation+0.000
exhibition
Token exhibition
Feature activation+0.000
."
Token."
Feature activation+0.000
Artists
Token Artists
Feature activation+0.000
would
Token would
Feature activation+0.000
president
Token president
Feature activation+0.000
.
Token.
Feature activation+0.000
pic
Token pic
Feature activation+0.000
.
Token.
Feature activation+0.000
twitter
Tokentwitter
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+0.000
J
TokenJ
Feature activation+0.000
T
TokenT
Feature activation+0.000
3
Token3
Feature activation+0.000
Oak
Token Oak
Feature activation+0.000
Ridge
Token Ridge
Feature activation+0.000
(
Token (
Feature activation+0.000
TN
TokenTN
Feature activation+0.000
)
Token)
Feature activation+0.000
National
Token National
Feature activation+0.000
Laboratory
Token Laboratory
Feature activation+0.000
in
Token in
Feature activation+0.000
1996
Token 1996
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hur
TokenHur
Feature activation+0.000
ricane
Tokenricane
Feature activation+0.000
Sandy
Token Sandy
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
and
Tokenand
Feature activation+0.000
being
Token being
Feature activation+0.000
an
Token an
Feature activation+0.000
independent
Token independent
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
has
Tokenhas
Feature activation+0.000
broader
Token broader
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
source
Token source
Feature activation+0.000
of
Token of
Feature activation+0.000
methane
Token methane
Feature activation+0.000
emissions
Token emissions
Feature activation+0.000
from
Token from
Feature activation+0.000
melting
Token melting
Feature activation+0.000
perm
Token perm
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 5 in H2.0: (feature 17252)

TOP ACTIVATIONS
MAX = 1.835

there
Token there
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+0.122
good
Token good
Feature activation+1.835
news
Token news
Feature activation+0.248
.
Token.
Feature activation+0.441
We
Token We
Feature activation+0.091
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
't
Token't
Feature activation+0.000
be
Token be
Feature activation+0.000
any
Token any
Feature activation+0.000
more
Token more
Feature activation+0.000
good
Token good
Feature activation+1.428
news
Token news
Feature activation+0.000
for
Token for
Feature activation+0.000
South
Token South
Feature activation+0.000
Downtown
Token Downtown
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
The
Token The
Feature activation+0.000
result
Token result
Feature activation+0.000
is
Token is
Feature activation+0.000
less
Token less
Feature activation+0.284
"
Token "
Feature activation+0.115
high
Tokenhigh
Feature activation+1.376
-
Token-
Feature activation+0.000
tech
Tokentech
Feature activation+0.000
theme
Token theme
Feature activation+0.026
park
Token park
Feature activation+0.000
robots
Token robots
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
more
Token more
Feature activation+0.000
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.052
young
Token young
Feature activation+1.370
people
Token people
Feature activation+0.127
discover
Token discover
Feature activation+0.291
car
Token car
Feature activation+0.073
culture
Token culture
Feature activation+0.000
through
Token through
Feature activation+0.000
health
Token health
Feature activation+0.000
regeneration
Token regeneration
Feature activation+0.000
ticks
Token ticks
Feature activation+0.000
more
Token more
Feature activation+0.176
quickly
Token quickly
Feature activation+0.911
but
Token but
Feature activation+1.339
max
Token max
Feature activation+0.190
regeneration
Token regeneration
Feature activation+0.000
is
Token is
Feature activation+0.000
down
Token down
Feature activation+0.183
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
love
Token love
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
more
Token more
Feature activation+0.000
you
Token you
Feature activation+1.306
get
Token get
Feature activation+0.944
to
Token to
Feature activation+0.000
know
Token know
Feature activation+0.000
a
Token a
Feature activation+0.000
person
Token person
Feature activation+0.000
the
Token the
Feature activation+0.011
data
Token data
Feature activation+0.230
,
Token,
Feature activation+0.035
the
Token the
Feature activation+0.228
more
Token more
Feature activation+0.640
we
Token we
Feature activation+1.282
are
Token are
Feature activation+1.019
convinced
Token convinced
Feature activation+0.887
your
Token your
Feature activation+0.995
logo
Token logo
Feature activation+0.324
is
Token is
Feature activation+0.211
noble
Token noble
Feature activation+0.000
work
Token work
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
greater
Token greater
Feature activation+0.000
good
Token good
Feature activation+1.270
.
Token.
Feature activation+0.005
Everyone
Token Everyone
Feature activation+0.000
will
Token will
Feature activation+0.000
feel
Token feel
Feature activation+0.000
good
Token good
Feature activation+0.355
country
Token country
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
more
Token more
Feature activation+0.347
remarkable
Token remarkable
Feature activation+1.239
when
Token when
Feature activation+0.755
you
Token you
Feature activation+0.643
consider
Token consider
Feature activation+0.000
the
Token the
Feature activation+0.201
fact
Token fact
Feature activation+0.383
paths
Token paths
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
spread
Token spread
Feature activation+0.000
more
Token more
Feature activation+0.128
fairly
Token fairly
Feature activation+1.226
and
Token and
Feature activation+0.236
shared
Token shared
Feature activation+0.000
across
Token across
Feature activation+0.349
the
Token the
Feature activation+0.000
communities
Token communities
Feature activation+0.000
feel
Token feel
Feature activation+0.190
,
Token,
Feature activation+0.504
the
Token the
Feature activation+0.640
more
Token more
Feature activation+1.105
chocolate
Token chocolate
Feature activation+0.630
they
Token they
Feature activation+1.225
tend
Token tend
Feature activation+0.874
to
Token to
Feature activation+0.361
eat
Token eat
Feature activation+0.000
.
Token.
Feature activation+0.324
Ċ
TokenĊ
Feature activation+0.045
work
Token work
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
greater
Token greater
Feature activation+0.000
good
Token good
Feature activation+1.206
of
Token of
Feature activation+0.000
more
Token more
Feature activation+0.000
?
Token?
Feature activation+0.000
Private
Token Private
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
More
TokenMore
Feature activation+0.025
power
Token power
Feature activation+0.000
is
Token is
Feature activation+0.154
nice
Token nice
Feature activation+1.205
but
Token but
Feature activation+0.421
reduced
Token reduced
Feature activation+0.000
weight
Token weight
Feature activation+0.000
is
Token is
Feature activation+0.028
even
Token even
Feature activation+0.097
reporting
Token reporting
Feature activation+0.000
are
Token are
Feature activation+0.270
,
Token,
Feature activation+0.236
the
Token the
Feature activation+0.247
more
Token more
Feature activation+0.766
they
Token they
Feature activation+1.202
will
Token will
Feature activation+0.752
continue
Token continue
Feature activation+0.639
to
Token to
Feature activation+0.236
pursue
Token pursue
Feature activation+0.000
that
Token that
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
C
TokenC
Feature activation+0.000
atch
Tokenatch
Feature activation+0.000
more
Token more
Feature activation+0.000
rare
Token rare
Feature activation+1.183
stories
Token stories
Feature activation+0.000
like
Token like
Feature activation+0.000
this
Token this
Feature activation+0.000
in
Token in
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
and
Token and
Feature activation+0.000
thus
Token thus
Feature activation+0.000
more
Token more
Feature activation+0.000
scoring
Token scoring
Feature activation+0.000
is
Token is
Feature activation+0.015
good
Token good
Feature activation+1.180
if
Token if
Feature activation+0.418
you
Token you
Feature activation+0.129
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
a
Token a
Feature activation+0.000
person
Token person
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.172
you
Token you
Feature activation+1.173
will
Token will
Feature activation+0.611
realise
Token realise
Feature activation+0.173
if
Token if
Feature activation+0.734
you
Token you
Feature activation+0.075
are
Token are
Feature activation+0.000
is
Token is
Feature activation+0.000
important
Token important
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
more
Token more
Feature activation+0.455
alternatives
Token alternatives
Feature activation+1.166
we
Token we
Feature activation+0.786
see
Token see
Feature activation+0.435
,
Token,
Feature activation+0.209
the
Token the
Feature activation+0.288
healthier
Token healthier
Feature activation+0.169
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
I
TokenI
Feature activation+0.000
feel
Token feel
Feature activation+0.000
more
Token more
Feature activation+0.158
alive
Token alive
Feature activation+1.158
,
Token,
Feature activation+0.341
I
Token I
Feature activation+0.482
feel
Token feel
Feature activation+0.117
more
Token more
Feature activation+0.614
focused
Token focused
Feature activation+0.000
teams
Token teams
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
The
Token The
Feature activation+0.000
more
Token more
Feature activation+0.065
damage
Token damage
Feature activation+0.319
your
Token your
Feature activation+1.147
team
Token team
Feature activation+0.805
gives
Token gives
Feature activation+0.087
,
Token,
Feature activation+0.194
the
Token the
Feature activation+0.374
higher
Token higher
Feature activation+0.848

Top DFA by src position
MAX = 2.574

,
Token,
Feature activation-0.000
Top resid features:
there
Token there
Feature activation+0.121
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ļ
TokenĻ
Feature activation+0.031
Top resid features:
s
Tokens
Feature activation+0.024
Top resid features:
more
Token more
Feature activation+2.574
Top resid features:
good
Token good
Feature activation+0.084
Top resid features:
news
Token news
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
We
Token We
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.049
Top resid features:
couldn
Token couldn
Feature activation+0.028
Top resid features:
't
Token't
Feature activation+0.019
Top resid features:
be
Token be
Feature activation-0.041
Top resid features:
any
Token any
Feature activation+0.080
Top resid features:
more
Token more
Feature activation+2.214
Top resid features:
good
Token good
Feature activation+0.070
Top resid features:
news
Token news
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
South
Token South
Feature activation+0.000
Top resid features:
Downtown
Token Downtown
Feature activation+0.000
Top resid features:
them
Token them
Feature activation+0.015
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
The
Token The
Feature activation+0.031
Top resid features:
result
Token result
Feature activation+0.058
Top resid features:
is
Token is
Feature activation-0.011
Top resid features:
less
Token less
Feature activation+2.208
Top resid features:
"
Token "
Feature activation+0.068
Top resid features:
high
Tokenhigh
Feature activation+0.126
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
tech
Tokentech
Feature activation+0.000
Top resid features:
theme
Token theme
Feature activation+0.000
Top resid features:
happen
Token happen
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
as
Token as
Feature activation+0.051
Top resid features:
more
Token more
Feature activation+1.047
Top resid features:
and
Token and
Feature activation+0.043
Top resid features:
more
Token more
Feature activation+1.207
Top resid features:
young
Token young
Feature activation+0.058
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
discover
Token discover
Feature activation+0.000
Top resid features:
car
Token car
Feature activation+0.000
Top resid features:
culture
Token culture
Feature activation+0.000
Top resid features:
row
Tokenrow
Feature activation+0.011
Top resid features:
ed
Tokened
Feature activation+0.025
Top resid features:
health
Token health
Feature activation+0.024
Top resid features:
regeneration
Token regeneration
Feature activation-0.006
Top resid features:
ticks
Token ticks
Feature activation+0.005
Top resid features:
more
Token more
Feature activation+1.755
Top resid features:
quickly
Token quickly
Feature activation+0.313
Top resid features:
but
Token but
Feature activation+0.025
Top resid features:
max
Token max
Feature activation+0.000
Top resid features:
regeneration
Token regeneration
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
comes
Token comes
Feature activation-0.018
Top resid features:
to
Token to
Feature activation+0.024
Top resid features:
love
Token love
Feature activation+0.029
Top resid features:
.
Token.
Feature activation-0.066
Top resid features:
The
Token The
Feature activation+0.099
Top resid features:
more
Token more
Feature activation+2.437
Top resid features:
you
Token you
Feature activation+0.102
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
know
Token know
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.089
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
data
Token data
Feature activation+0.069
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
the
Token the
Feature activation+0.137
Top resid features:
more
Token more
Feature activation+1.567
Top resid features:
we
Token we
Feature activation+0.082
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
convinced
Token convinced
Feature activation+0.000
Top resid features:
your
Token your
Feature activation+0.000
Top resid features:
logo
Token logo
Feature activation+0.000
Top resid features:
doing
Token doing
Feature activation+0.019
Top resid features:
noble
Token noble
Feature activation+0.081
Top resid features:
work
Token work
Feature activation+0.008
Top resid features:
for
Token for
Feature activation+0.091
Top resid features:
a
Token a
Feature activation+0.088
Top resid features:
greater
Token greater
Feature activation+1.919
Top resid features:
good
Token good
Feature activation+0.050
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Everyone
Token Everyone
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
feel
Token feel
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
country
Token country
Feature activation+0.019
Top resid features:
.
Token.
Feature activation-0.021
Top resid features:
It
Token It
Feature activation-0.002
Top resid features:
is
Token is
Feature activation-0.051
Top resid features:
more
Token more
Feature activation+1.983
Top resid features:
remarkable
Token remarkable
Feature activation+0.228
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
consider
Token consider
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
flight
Token flight
Feature activation+0.011
Top resid features:
paths
Token paths
Feature activation-0.001
Top resid features:
should
Token should
Feature activation+0.031
Top resid features:
be
Token be
Feature activation-0.010
Top resid features:
spread
Token spread
Feature activation+0.167
Top resid features:
more
Token more
Feature activation+1.900
Top resid features:
fairly
Token fairly
Feature activation+0.098
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
shared
Token shared
Feature activation+0.000
Top resid features:
across
Token across
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
depressed
Token depressed
Feature activation+0.050
Top resid features:
they
Token they
Feature activation+0.049
Top resid features:
feel
Token feel
Feature activation+0.064
Top resid features:
,
Token,
Feature activation+0.043
Top resid features:
the
Token the
Feature activation+0.118
Top resid features:
more
Token more
Feature activation+1.319
Top resid features:
chocolate
Token chocolate
Feature activation+0.200
Top resid features:
they
Token they
Feature activation+0.160
Top resid features:
tend
Token tend
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
eat
Token eat
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.024
Top resid features:
work
Token work
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
for
Token for
Feature activation+0.077
Top resid features:
the
Token the
Feature activation+0.074
Top resid features:
greater
Token greater
Feature activation+2.119
Top resid features:
good
Token good
Feature activation+0.060
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.000
Top resid features:
Private
Token Private
Feature activation+0.000
Top resid features:
W
TokenW
Feature activation+0.008
Top resid features:
range
Token range
Feature activation+0.013
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
More
TokenMore
Feature activation+1.896
Top resid features:
power
Token power
Feature activation+0.097
Top resid features:
is
Token is
Feature activation-0.075
Top resid features:
nice
Token nice
Feature activation+0.248
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
reduced
Token reduced
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.037
Top resid features:
reporting
Token reporting
Feature activation+0.017
Top resid features:
are
Token are
Feature activation+0.035
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
the
Token the
Feature activation+0.107
Top resid features:
more
Token more
Feature activation+1.550
Top resid features:
they
Token they
Feature activation+0.117
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
continue
Token continue
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
pursue
Token pursue
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.033
Top resid features:
C
TokenC
Feature activation+0.043
Top resid features:
atch
Tokenatch
Feature activation+0.023
Top resid features:
more
Token more
Feature activation+1.880
Top resid features:
rare
Token rare
Feature activation+0.093
Top resid features:
stories
Token stories
Feature activation+0.000
Top resid features:
like
Token like
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
offensive
Token offensive
Feature activation+0.020
Top resid features:
scoring
Token scoring
Feature activation+0.013
Top resid features:
efficiency
Token efficiency
Feature activation+0.018
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
thus
Token thus
Feature activation+0.033
Top resid features:
more
Token more
Feature activation+1.917
Top resid features:
scoring
Token scoring
Feature activation+0.060
Top resid features:
is
Token is
Feature activation-0.041
Top resid features:
good
Token good
Feature activation+0.077
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
know
Token know
Feature activation+0.020
Top resid features:
a
Token a
Feature activation+0.026
Top resid features:
person
Token person
Feature activation+0.045
Top resid features:
,
Token,
Feature activation+0.033
Top resid features:
the
Token the
Feature activation+0.132
Top resid features:
more
Token more
Feature activation+1.654
Top resid features:
you
Token you
Feature activation+0.143
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
realise
Token realise
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
projects
Token projects
Feature activation-0.010
Top resid features:
is
Token is
Feature activation-0.020
Top resid features:
important
Token important
Feature activation+0.106
Top resid features:
.
Token.
Feature activation-0.010
Top resid features:
The
Token The
Feature activation+0.053
Top resid features:
more
Token more
Feature activation+1.792
Top resid features:
alternatives
Token alternatives
Feature activation+0.117
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
see
Token see
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:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
"
Token"
Feature activation+0.064
Top resid features:
I
TokenI
Feature activation+0.040
Top resid features:
feel
Token feel
Feature activation+0.098
Top resid features:
more
Token more
Feature activation+1.818
Top resid features:
alive
Token alive
Feature activation+0.109
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
feel
Token feel
Feature activation+0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
inflicted
Token inflicted
Feature activation+0.021
Top resid features:
by
Token by
Feature activation+0.032
Top resid features:
teams
Token teams
Feature activation+0.010
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.026
Top resid features:
The
Token The
Feature activation+0.063
Top resid features:
more
Token more
Feature activation+1.889
Top resid features:
damage
Token damage
Feature activation+0.035
Top resid features:
your
Token your
Feature activation+0.178
Top resid features:
team
Token team
Feature activation+0.000
Top resid features:
gives
Token gives
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.33

Head 1: 0.03

Head 2: 0.07

Head 3: 0.10

Head 4: 0.03

Head 5: 0.07

Head 6: 0.04

Head 7: 0.04

Head 8: 0.08

Head 9: 0.09

Head 10: 0.09

Head 11: 0.03

Positive logits

than1.44

":"/1.26

tends1.26

tert1.19

economy1.17

Murray1.16

Mole1.15

ーテ1.14

Than1.14

spectrum1.09

1.07

ーティ1.07

entropy1.07

Rebell1.07

quot1.06

compared1.06

mole1.06

tended1.06

mog1.04

ッド1.04

Negative logits

lain-1.85

uthor-1.72

avage-1.53

onen-1.38

outhern-1.38

ledged-1.37

itars-1.35

ateful-1.35

afety-1.31

regor-1.26

software-1.26

ogens-1.26

acebook-1.24

heng-1.22

yrights-1.22

kill-1.20

issy-1.19

appropriate-1.18

omon-1.18

osal-1.18

INTERVAL 1.652 - 1.835
CONTAINS 0.000%

there
Token there
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+0.122
good
Token good
Feature activation+1.835
news
Token news
Feature activation+0.248
.
Token.
Feature activation+0.441
We
Token We
Feature activation+0.091
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 1.468 - 1.652
CONTAINS 0.000%

INTERVAL 1.285 - 1.468
CONTAINS 0.001%

,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
more
Token more
Feature activation+0.000
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.052
young
Token young
Feature activation+1.370
people
Token people
Feature activation+0.127
discover
Token discover
Feature activation+0.291
car
Token car
Feature activation+0.073
culture
Token culture
Feature activation+0.000
through
Token through
Feature activation+0.000
health
Token health
Feature activation+0.000
regeneration
Token regeneration
Feature activation+0.000
ticks
Token ticks
Feature activation+0.000
more
Token more
Feature activation+0.176
quickly
Token quickly
Feature activation+0.911
but
Token but
Feature activation+1.339
max
Token max
Feature activation+0.190
regeneration
Token regeneration
Feature activation+0.000
is
Token is
Feature activation+0.000
down
Token down
Feature activation+0.183
.
Token.
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
't
Token't
Feature activation+0.000
be
Token be
Feature activation+0.000
any
Token any
Feature activation+0.000
more
Token more
Feature activation+0.000
good
Token good
Feature activation+1.428
news
Token news
Feature activation+0.000
for
Token for
Feature activation+0.000
South
Token South
Feature activation+0.000
Downtown
Token Downtown
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
The
Token The
Feature activation+0.000
result
Token result
Feature activation+0.000
is
Token is
Feature activation+0.000
less
Token less
Feature activation+0.284
"
Token "
Feature activation+0.115
high
Tokenhigh
Feature activation+1.376
-
Token-
Feature activation+0.000
tech
Tokentech
Feature activation+0.000
theme
Token theme
Feature activation+0.026
park
Token park
Feature activation+0.000
robots
Token robots
Feature activation+0.000
to
Token to
Feature activation+0.000
love
Token love
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
more
Token more
Feature activation+0.000
you
Token you
Feature activation+1.306
get
Token get
Feature activation+0.944
to
Token to
Feature activation+0.000
know
Token know
Feature activation+0.000
a
Token a
Feature activation+0.000
person
Token person
Feature activation+0.000

INTERVAL 1.101 - 1.285
CONTAINS 0.002%

tightly
Token tightly
Feature activation+0.484
and
Token and
Feature activation+0.376
release
Token release
Feature activation+0.326
it
Token it
Feature activation+0.146
more
Token more
Feature activation+0.496
slowly
Token slowly
Feature activation+1.116
[
Token [
Feature activation+0.313
_
Token_
Feature activation+0.087
2
Token2
Feature activation+0.116
_
Token_
Feature activation+0.000
]
Token]
Feature activation+0.000
and
Token and
Feature activation+0.000
thus
Token thus
Feature activation+0.000
more
Token more
Feature activation+0.000
scoring
Token scoring
Feature activation+0.000
is
Token is
Feature activation+0.015
good
Token good
Feature activation+1.180
if
Token if
Feature activation+0.418
you
Token you
Feature activation+0.129
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
work
Token work
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
greater
Token greater
Feature activation+0.000
good
Token good
Feature activation+1.206
of
Token of
Feature activation+0.000
more
Token more
Feature activation+0.000
?
Token?
Feature activation+0.000
Private
Token Private
Feature activation+0.000
citizens
Token citizens
Feature activation+0.000
depressed
Token depressed
Feature activation+0.463
they
Token they
Feature activation+0.754
feel
Token feel
Feature activation+0.190
,
Token,
Feature activation+0.504
the
Token the
Feature activation+0.640
more
Token more
Feature activation+1.105
chocolate
Token chocolate
Feature activation+0.630
they
Token they
Feature activation+1.225
tend
Token tend
Feature activation+0.874
to
Token to
Feature activation+0.361
eat
Token eat
Feature activation+0.000
say
Token say
Feature activation+0.000
that
Token that
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.106
sorry
Token sorry
Feature activation+1.142
than
Token than
Feature activation+0.000
I
Token I
Feature activation+0.000
am
Token am
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000

INTERVAL 0.918 - 1.101
CONTAINS 0.003%

less
Token less
Feature activation+0.274
boring
Token boring
Feature activation+0.454
.
Token.
Feature activation+0.475
There
Token There
Feature activation+0.255
are
Token are
Feature activation+0.287
good
Token good
Feature activation+0.941
cases
Token cases
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
made
Token made
Feature activation+0.000
for
Token for
Feature activation+0.000
more
Token more
Feature activation+0.000
time
Token time
Feature activation+0.165
will
Token will
Feature activation+0.212
be
Token be
Feature activation+0.077
a
Token a
Feature activation+0.177
lot
Token lot
Feature activation+0.944
of
Token of
Feature activation+0.000
fun
Token fun
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
was
Token was
Feature activation+0.000
ier
Tokenier
Feature activation+0.100
and
Token and
Feature activation+0.150
more
Token more
Feature activation+0.466
devastating
Token devastating
Feature activation+0.712
ly
Tokenly
Feature activation+0.347
young
Token young
Feature activation+1.037
.
Token.
Feature activation+0.033
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Next
Token Next
Feature activation+0.000
without
Token without
Feature activation+0.000
passing
Token passing
Feature activation+0.000
.
Token.
Feature activation+0.000
View
Token View
Feature activation+0.000
more
Token more
Feature activation+0.025
No
Token No
Feature activation+0.991
,
Token,
Feature activation+0.309
Henderson
Token Henderson
Feature activation+0.000
replied
Token replied
Feature activation+0.250
.
Token.
Feature activation+0.145
He
Token He
Feature activation+0.000
now
Token now
Feature activation+0.000
more
Token more
Feature activation+0.000
stable
Token stable
Feature activation+0.399
,
Token,
Feature activation+0.064
(
Token (
Feature activation+0.000
yet
Tokenyet
Feature activation+1.076
)
Token)
Feature activation+0.000
people
Token people
Feature activation+0.000
are
Token are
Feature activation+0.000
getting
Token getting
Feature activation+0.000
more
Token more
Feature activation+0.035

INTERVAL 0.734 - 0.918
CONTAINS 0.007%

a
Token a
Feature activation+0.000
longer
Token longer
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.047
more
Token more
Feature activation+0.191
beautiful
Token beautiful
Feature activation+0.888
version
Token version
Feature activation+0.466
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
source
Token source
Feature activation+0.051
code
Token code
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
the
Token the
Feature activation+0.000
more
Token more
Feature activation+0.377
depressed
Token depressed
Feature activation+0.463
they
Token they
Feature activation+0.754
feel
Token feel
Feature activation+0.190
,
Token,
Feature activation+0.504
the
Token the
Feature activation+0.640
more
Token more
Feature activation+1.105
chocolate
Token chocolate
Feature activation+0.630
you
Token you
Feature activation+1.035
give
Token give
Feature activation+0.241
,
Token,
Feature activation+0.263
the
Token the
Feature activation+0.527
higher
Token higher
Feature activation+0.892
amount
Token amount
Feature activation+0.761
of
Token of
Feature activation+0.224
balls
Token balls
Feature activation+0.000
of
Token of
Feature activation+0.000
Premier
Token Premier
Feature activation+0.000
Balls
Token Balls
Feature activation+0.000
alcohol
Token alcohol
Feature activation+0.000
is
Token is
Feature activation+0.502
consumed
Token consumed
Feature activation+0.000
,
Token,
Feature activation+0.165
the
Token the
Feature activation+0.409
higher
Token higher
Feature activation+0.749
the
Token the
Feature activation+0.621
risk
Token risk
Feature activation+0.454
of
Token of
Feature activation+0.133
early
Token early
Feature activation+0.112
death
Token death
Feature activation+0.000
people
Token people
Feature activation+0.787
reporting
Token reporting
Feature activation+0.000
are
Token are
Feature activation+0.270
,
Token,
Feature activation+0.236
the
Token the
Feature activation+0.247
more
Token more
Feature activation+0.766
they
Token they
Feature activation+1.202
will
Token will
Feature activation+0.752
continue
Token continue
Feature activation+0.639
to
Token to
Feature activation+0.236
pursue
Token pursue
Feature activation+0.000

INTERVAL 0.551 - 0.734
CONTAINS 0.015%

police
Token police
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
more
Token more
Feature activation+0.000
charges
Token charges
Feature activation+0.001
may
Token may
Feature activation+0.580
be
Token be
Feature activation+0.044
forthcoming
Token forthcoming
Feature activation+0.000
as
Token as
Feature activation+0.314
the
Token the
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
More
TokenMore
Feature activation+0.016
worrying
Token worrying
Feature activation+0.032
is
Token is
Feature activation+0.076
the
Token the
Feature activation+0.360
possibility
Token possibility
Feature activation+0.673
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
flat
Token flat
Feature activation+0.000
or
Token or
Feature activation+0.000
negative
Token negative
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
less
Token less
Feature activation+0.249
certain
Token certain
Feature activation+0.859
is
Token is
Feature activation+0.694
the
Token the
Feature activation+0.577
information
Token information
Feature activation+0.522
,
Token,
Feature activation+0.349
covers
Token covers
Feature activation+0.000
can
Token can
Feature activation+0.000
change
Token change
Feature activation+0.000
at
Token at
Feature activation+0.154
the
Token the
Feature activation+0.011
data
Token data
Feature activation+0.230
,
Token,
Feature activation+0.035
the
Token the
Feature activation+0.228
more
Token more
Feature activation+0.640
we
Token we
Feature activation+1.282
are
Token are
Feature activation+1.019
convinced
Token convinced
Feature activation+0.887
your
Token your
Feature activation+0.995
logo
Token logo
Feature activation+0.324
showing
Token showing
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
judged
Token judged
Feature activation+0.000
more
Token more
Feature activation+0.547
harshly
Token harshly
Feature activation+0.609
and
Token and
Feature activation+0.136
paid
Token paid
Feature activation+0.000
less
Token less
Feature activation+0.110
than
Token than
Feature activation+0.059
men
Token men
Feature activation+0.000

INTERVAL 0.367 - 0.551
CONTAINS 0.038%

ve
Tokenve
Feature activation+0.000
had
Token had
Feature activation+0.000
,
Token,
Feature activation+0.000
tasting
Token tasting
Feature activation+0.000
more
Token more
Feature activation+0.000
finished
Token finished
Feature activation+0.512
.
Token.
Feature activation+0.181
The
Token The
Feature activation+0.038
other
Token other
Feature activation+0.341
Cant
Token Cant
Feature activation+0.045
illon
Tokenillon
Feature activation+0.000
become
Token become
Feature activation+0.000
slower
Token slower
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.006
lot
Token lot
Feature activation+0.001
more
Token more
Feature activation+0.462
predictable
Token predictable
Feature activation+0.309
:
Token:
Feature activation+0.108
either
Token either
Feature activation+0.152
through
Token through
Feature activation+0.000
a
Token a
Feature activation+0.000
),
Token),
Feature activation+0.000
their
Token their
Feature activation+0.000
quest
Token quest
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.175
honorable
Token honorable
Feature activation+0.529
journey
Token journey
Feature activation+0.140
,
Token,
Feature activation+0.167
and
Token and
Feature activation+0.017
Gand
Token Gand
Feature activation+0.000
alf
Tokenalf
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
are
Token are
Feature activation+0.000
now
Token now
Feature activation+0.000
more
Token more
Feature activation+0.000
stable
Token stable
Feature activation+0.399
,
Token,
Feature activation+0.064
(
Token (
Feature activation+0.000
yet
Tokenyet
Feature activation+1.076
)
Token)
Feature activation+0.000
people
Token people
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
more
Token more
Feature activation+0.221
or
Token or
Feature activation+0.155
less
Token less
Feature activation+0.000
complete
Token complete
Feature activation+0.409
chang
Token chang
Feature activation+0.597
el
Tokenel
Feature activation+0.000
og
Tokenog
Feature activation+0.000
can
Token can
Feature activation+0.378
be
Token be
Feature activation+0.113

INTERVAL 0.184 - 0.367
CONTAINS 0.090%

Guys
Token Guys
Feature activation+0.000
are
Token are
Feature activation+0.000
relying
Token relying
Feature activation+0.000
more
Token more
Feature activation+0.094
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.201
on
Token on
Feature activation+0.000
these
Token these
Feature activation+0.420
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
virtual
Tokenvirtual
Feature activation+0.000
better
Token better
Feature activation+0.000
team
Token team
Feature activation+0.000
player
Tokenplayer
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.293
effective
Token effective
Feature activation+0.418
player
Token player
Feature activation+0.484
and
Token and
Feature activation+0.382
that
Token that
Feature activation+0.262
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
secure
Token secure
Feature activation+0.000
option
Token option
Feature activation+0.355
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.294
again
Token again
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
unp
Token unp
Feature activation+0.060
added
Tokenadded
Feature activation+0.000
is
Token is
Feature activation+0.000
possible
Token possible
Feature activation+0.000
there
Token there
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
more
Token more
Feature activation+0.326
defect
Token defect
Feature activation+0.162
ions
Tokenions
Feature activation+0.000
.
Token.
Feature activation+0.006
But
Token But
Feature activation+0.090
he
Token he
Feature activation+0.000
weaker
Token weaker
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
older
Token older
Feature activation+0.000
,
Token,
Feature activation+0.000
multi
Token multi
Feature activation+0.305
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
ice
Token ice
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000

INTERVAL 0.000 - 0.184
CONTAINS 99.846%

not
Token not
Feature activation+0.000
think
Token think
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
skill
Token skill
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
most
Token most
Feature activation+0.000
North
Token North
Feature activation+0.000
ative
Tokenative
Feature activation+0.000
and
Token and
Feature activation+0.000
poorly
Token poorly
Feature activation+0.000
executed
Token executed
Feature activation+0.000
.
Token.
Feature activation+0.000
Gone
Token Gone
Feature activation+0.000
are
Token are
Feature activation+0.000
sleek
Token sleek
Feature activation+0.000
lines
Token lines
Feature activation+0.000
to
Token to
Feature activation+0.000
match
Token match
Feature activation+0.000
so
Token so
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
too
Token too
Feature activation+0.000
crazy
Token crazy
Feature activation+0.000
.
Token.
Feature activation+0.000
What
Token What
Feature activation+0.000
was
Token was
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
box
Token box
Feature activation+0.000
has
Token has
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
you
Token you
Feature activation+0.000
're
Token're
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
midst
Token midst
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
season
Token season
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
her
Token her
Feature activation+0.000
new
Token new
Feature activation+0.000
accessory
Token accessory
Feature activation+0.000
line
Token line
Feature activation+0.000
with
Token with
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
arming
Tokenarming
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H2.0: (feature 6295)

TOP ACTIVATIONS
MAX = 1.479

W
TokenW
Feature activation+0.000
old
Tokenold
Feature activation+0.000
then
Token then
Feature activation+0.000
threw
Token threw
Feature activation+0.000
the
Token the
Feature activation+0.000
plans
Token plans
Feature activation+1.479
down
Token down
Feature activation+0.276
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
planning
Token planning
Feature activation+0.000
table
Token table
Feature activation+0.000
public
Token public
Feature activation+0.000
lands
Token lands
Feature activation+0.000
that
Token that
Feature activation+0.000
can
Token can
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
experiences
Token experiences
Feature activation+1.327
on
Token on
Feature activation+0.000
par
Token par
Feature activation+0.000
with
Token with
Feature activation+0.000
those
Token those
Feature activation+0.000
in
Token in
Feature activation+0.000
so
Token so
Feature activation+0.000
they
Token they
Feature activation+0.000
took
Token took
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.613
window
Token window
Feature activation+1.093
out
Token out
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
done
Token done
Feature activation+0.237
John
Token John
Feature activation+0.000
Scal
Token Scal
Feature activation+0.000
zi
Tokenzi
Feature activation+0.000
donated
Token donated
Feature activation+0.000
was
Token was
Feature activation+0.291
going
Token going
Feature activation+1.068
into
Token into
Feature activation+0.075
an
Token an
Feature activation+0.000
auction
Token auction
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
bought
Token bought
Feature activation+0.000
the
Token the
Feature activation+0.000
business
Token business
Feature activation+1.056
from
Token from
Feature activation+0.000
her
Token her
Feature activation+0.000
in
Token in
Feature activation+0.000
1968
Token 1968
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
His
TokenHis
Feature activation+0.000
directing
Token directing
Feature activation+0.000
debut
Token debut
Feature activation+1.022
was
Token was
Feature activation+0.267
the
Token the
Feature activation+0.132
acclaimed
Token acclaimed
Feature activation+0.251
Wh
Token Wh
Feature activation+0.000
istle
Tokenistle
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+0.000
visited
Token visited
Feature activation+0.000
the
Token the
Feature activation+0.000
key
Token key
Feature activation+0.977
early
Token early
Feature activation+0.023
voting
Token voting
Feature activation+0.008
states
Token states
Feature activation+0.000
of
Token of
Feature activation+0.000
Iowa
Token Iowa
Feature activation+0.000
whoever
Token whoever
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
take
Token take
Feature activation+0.000
his
Token his
Feature activation+0.000
cross
Token cross
Feature activation+0.968
and
Token and
Feature activation+0.000
follow
Token follow
Feature activation+0.000
me
Token me
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
Israeli
TokenIsraeli
Feature activation+0.000
strikes
Token strikes
Feature activation+0.000
have
Token have
Feature activation+0.000
hit
Token hit
Feature activation+0.000
an
Token an
Feature activation+0.000
arms
Token arms
Feature activation+0.953
depot
Token depot
Feature activation+0.125
operated
Token operated
Feature activation+0.356
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Lebanese
Token Lebanese
Feature activation+0.000
a
Token a
Feature activation+0.000
second
Token second
Feature activation+0.000
.
Token.
Feature activation+0.000
Yang
Token Yang
Feature activation+0.000
fell
Token fell
Feature activation+0.000
forward
Token forward
Feature activation+0.949
into
Token into
Feature activation+0.000
Salem
Token Salem
Feature activation+0.000
who
Token who
Feature activation+0.000
happily
Token happily
Feature activation+0.000
caught
Token caught
Feature activation+0.000
Wang
Token Wang
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
offered
Token offered
Feature activation+0.000
a
Token a
Feature activation+0.000
job
Token job
Feature activation+0.941
at
Token at
Feature activation+0.101
a
Token a
Feature activation+0.000
college
Token college
Feature activation+0.000
in
Token in
Feature activation+0.000
Beijing
Token Beijing
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
center
Token center
Feature activation+0.000
provides
Token provides
Feature activation+0.000
jobs
Token jobs
Feature activation+0.925
for
Token for
Feature activation+0.000
adults
Token adults
Feature activation+0.000
with
Token with
Feature activation+0.000
intellectual
Token intellectual
Feature activation+0.000
disabilities
Token disabilities
Feature activation+0.000
pin
Tokenpin
Feature activation+0.000
allegedly
Token allegedly
Feature activation+0.000
threw
Token threw
Feature activation+0.000
Gray
Token Gray
Feature activation+0.000
's
Token's
Feature activation+0.178
laptop
Token laptop
Feature activation+0.915
against
Token against
Feature activation+0.294
a
Token a
Feature activation+0.000
wall
Token wall
Feature activation+0.000
and
Token and
Feature activation+0.000
punched
Token punched
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ryan
TokenRyan
Feature activation+0.000
Bundy
Token Bundy
Feature activation+0.000
takes
Token takes
Feature activation+0.000
a
Token a
Feature activation+0.000
phone
Token phone
Feature activation+0.914
call
Token call
Feature activation+0.037
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
entrance
Token entrance
Feature activation+0.000
of
Token of
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+0.000
has
Token has
Feature activation+0.000
also
Token also
Feature activation+0.000
submitted
Token submitted
Feature activation+0.000
proven
Token proven
Feature activation+0.896
reports
Token reports
Feature activation+0.000
on
Token on
Feature activation+0.098
murder
Token murder
Feature activation+0.000
,
Token,
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
have
Token have
Feature activation+0.000
alternating
Token alternating
Feature activation+0.000
raised
Token raised
Feature activation+0.001
and
Token and
Feature activation+0.000
lowered
Token lowered
Feature activation+0.000
rid
Token rid
Feature activation+0.874
ges
Tokenges
Feature activation+0.380
along
Token along
Feature activation+0.271
the
Token the
Feature activation+0.000
outer
Token outer
Feature activation+0.000
rim
Token rim
Feature activation+0.000
aggress
Token aggress
Feature activation+0.000
ors
Tokenors
Feature activation+0.000
broke
Token broke
Feature activation+0.000
open
Token open
Feature activation+0.000
the
Token the
Feature activation+0.000
safe
Token safe
Feature activation+0.873
and
Token and
Feature activation+0.000
made
Token made
Feature activation+0.000
off
Token off
Feature activation+0.248
with
Token with
Feature activation+0.000
two
Token two
Feature activation+0.000
finished
Token finished
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.010
offered
Token offered
Feature activation+0.000
my
Token my
Feature activation+0.000
part
Token part
Feature activation+0.847
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.091
told
Token told
Feature activation+0.000
him
Token him
Feature activation+0.000
nobody
Token nobody
Feature activation+0.000
but
Token but
Feature activation+0.000
often
Token often
Feature activation+0.000
get
Token get
Feature activation+0.000
sent
Token sent
Feature activation+0.000
interesting
Token interesting
Feature activation+0.837
stories
Token stories
Feature activation+0.844
from
Token from
Feature activation+0.000
it
Token it
Feature activation+0.000
-
Token -
Feature activation+0.000
eg
Token eg
Feature activation+0.000
the
Token the
Feature activation+0.000
't
Token't
Feature activation+0.000
but
Token but
Feature activation+0.000
often
Token often
Feature activation+0.000
get
Token get
Feature activation+0.000
sent
Token sent
Feature activation+0.000
interesting
Token interesting
Feature activation+0.837
stories
Token stories
Feature activation+0.844
from
Token from
Feature activation+0.000
it
Token it
Feature activation+0.000
-
Token -
Feature activation+0.000
eg
Token eg
Feature activation+0.000

Top DFA by src position
MAX = 1.877

Ċ
TokenĊ
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.015
Top resid features:
W
TokenW
Feature activation+0.016
Top resid features:
old
Tokenold
Feature activation-0.006
Top resid features:
then
Token then
Feature activation+0.026
Top resid features:
threw
Token threw
Feature activation+1.707
Top resid features:
the
Token the
Feature activation+0.210
Top resid features:
plans
Token plans
Feature activation+0.030
Top resid features:
down
Token down
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
incredible
Token incredible
Feature activation+0.019
Top resid features:
public
Token public
Feature activation-0.004
Top resid features:
lands
Token lands
Feature activation-0.005
Top resid features:
that
Token that
Feature activation+0.031
Top resid features:
can
Token can
Feature activation+0.009
Top resid features:
deliver
Token deliver
Feature activation+1.701
Top resid features:
experiences
Token experiences
Feature activation+0.003
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
par
Token par
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
shatter
Token shatter
Feature activation+0.054
Top resid features:
proof
Tokenproof
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
so
Token so
Feature activation+0.044
Top resid features:
they
Token they
Feature activation+0.036
Top resid features:
took
Token took
Feature activation+1.215
Top resid features:
the
Token the
Feature activation+0.147
Top resid features:
whole
Token whole
Feature activation+0.065
Top resid features:
window
Token window
Feature activation+0.084
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
shirts
Tokenshirts
Feature activation+0.009
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
John
Token John
Feature activation+0.012
Top resid features:
Scal
Token Scal
Feature activation+0.027
Top resid features:
zi
Tokenzi
Feature activation+0.010
Top resid features:
donated
Token donated
Feature activation+1.412
Top resid features:
was
Token was
Feature activation+0.132
Top resid features:
going
Token going
Feature activation+0.070
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
auction
Token auction
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.064
Top resid features:
.
Token.
Feature activation-0.015
Top resid features:
He
Token He
Feature activation+0.040
Top resid features:
bought
Token bought
Feature activation+1.381
Top resid features:
the
Token the
Feature activation+0.183
Top resid features:
business
Token business
Feature activation+0.114
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
robbery
Token robbery
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.045
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
His
TokenHis
Feature activation+0.161
Top resid features:
directing
Token directing
Feature activation+1.299
Top resid features:
debut
Token debut
Feature activation+0.065
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
acclaimed
Token acclaimed
Feature activation+0.000
Top resid features:
Wh
Token Wh
Feature activation+0.000
Top resid features:
nomination
Token nomination
Feature activation+0.003
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.044
Top resid features:
Ċ
TokenĊ
Feature activation-0.051
Top resid features:
She
TokenShe
Feature activation+0.019
Top resid features:
visited
Token visited
Feature activation+1.446
Top resid features:
the
Token the
Feature activation+0.129
Top resid features:
key
Token key
Feature activation-0.017
Top resid features:
early
Token early
Feature activation+0.000
Top resid features:
voting
Token voting
Feature activation+0.000
Top resid features:
states
Token states
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.028
Top resid features:
And
Token And
Feature activation+0.015
Top resid features:
whoever
Token whoever
Feature activation-0.003
Top resid features:
does
Token does
Feature activation+0.045
Top resid features:
not
Token not
Feature activation+0.007
Top resid features:
take
Token take
Feature activation+1.080
Top resid features:
his
Token his
Feature activation+0.336
Top resid features:
cross
Token cross
Feature activation+0.102
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
follow
Token follow
Feature activation+0.000
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.067
Top resid features:
Israeli
TokenIsraeli
Feature activation-0.019
Top resid features:
strikes
Token strikes
Feature activation+0.150
Top resid features:
have
Token have
Feature activation+0.046
Top resid features:
hit
Token hit
Feature activation+1.157
Top resid features:
an
Token an
Feature activation+0.208
Top resid features:
arms
Token arms
Feature activation+0.019
Top resid features:
depot
Token depot
Feature activation+0.000
Top resid features:
operated
Token operated
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
just
Token just
Feature activation+0.009
Top resid features:
a
Token a
Feature activation+0.043
Top resid features:
second
Token second
Feature activation+0.034
Top resid features:
.
Token.
Feature activation+0.041
Top resid features:
Yang
Token Yang
Feature activation+0.031
Top resid features:
fell
Token fell
Feature activation+1.272
Top resid features:
forward
Token forward
Feature activation+0.142
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
Salem
Token Salem
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
happily
Token happily
Feature activation+0.000
Top resid features:
hua
Tokenhua
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
Wang
Token Wang
Feature activation+0.008
Top resid features:
has
Token has
Feature activation+0.040
Top resid features:
been
Token been
Feature activation+0.048
Top resid features:
offered
Token offered
Feature activation+1.163
Top resid features:
a
Token a
Feature activation+0.075
Top resid features:
job
Token job
Feature activation+0.059
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
college
Token college
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.030
Top resid features:
Ċ
TokenĊ
Feature activation-0.033
Top resid features:
The
TokenThe
Feature activation+0.044
Top resid features:
center
Token center
Feature activation+0.022
Top resid features:
provides
Token provides
Feature activation+1.406
Top resid features:
jobs
Token jobs
Feature activation+0.017
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
adults
Token adults
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
intellectual
Token intellectual
Feature activation+0.000
Top resid features:
Sentinel
Token Sentinel
Feature activation+0.014
Top resid features:
reported
Token reported
Feature activation+0.050
Top resid features:
Tur
Token Tur
Feature activation+0.015
Top resid features:
pin
Tokenpin
Feature activation+0.005
Top resid features:
allegedly
Token allegedly
Feature activation-0.013
Top resid features:
threw
Token threw
Feature activation+1.261
Top resid features:
Gray
Token Gray
Feature activation+0.018
Top resid features:
's
Token's
Feature activation+0.130
Top resid features:
laptop
Token laptop
Feature activation-0.011
Top resid features:
against
Token against
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
photo
Tokenphoto
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.019
Top resid features:
Ryan
TokenRyan
Feature activation+0.018
Top resid features:
Bundy
Token Bundy
Feature activation-0.000
Top resid features:
takes
Token takes
Feature activation+1.241
Top resid features:
a
Token a
Feature activation+0.116
Top resid features:
phone
Token phone
Feature activation+0.051
Top resid features:
call
Token call
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.054
Top resid features:
Ċ
TokenĊ
Feature activation-0.063
Top resid features:
She
TokenShe
Feature activation+0.000
Top resid features:
has
Token has
Feature activation-0.031
Top resid features:
also
Token also
Feature activation-0.072
Top resid features:
submitted
Token submitted
Feature activation+1.877
Top resid features:
proven
Token proven
Feature activation-0.098
Top resid features:
reports
Token reports
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
murder
Token murder
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
The
Token The
Feature activation+0.048
Top resid features:
rounds
Token rounds
Feature activation+0.051
Top resid features:
have
Token have
Feature activation+0.056
Top resid features:
alternating
Token alternating
Feature activation+0.039
Top resid features:
raised
Token raised
Feature activation+0.618
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
lowered
Token lowered
Feature activation+0.507
Top resid features:
rid
Token rid
Feature activation+0.050
Top resid features:
ges
Tokenges
Feature activation+0.000
Top resid features:
along
Token along
Feature activation+0.000
Top resid features:
orius
Tokenorius
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.041
Top resid features:
aggress
Token aggress
Feature activation+0.048
Top resid features:
ors
Tokenors
Feature activation-0.011
Top resid features:
broke
Token broke
Feature activation+0.631
Top resid features:
open
Token open
Feature activation+0.422
Top resid features:
the
Token the
Feature activation+0.304
Top resid features:
safe
Token safe
Feature activation+0.040
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
made
Token made
Feature activation+0.000
Top resid features:
Once
Token Once
Feature activation-0.011
Top resid features:
he
Token he
Feature activation+0.004
Top resid features:
finished
Token finished
Feature activation+0.441
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
I
Token I
Feature activation-0.001
Top resid features:
offered
Token offered
Feature activation+0.709
Top resid features:
my
Token my
Feature activation+0.169
Top resid features:
part
Token part
Feature activation+0.052
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
told
Token told
Feature activation+0.000
Top resid features:
don
Token don
Feature activation-0.001
Top resid features:
't
Token't
Feature activation-0.013
Top resid features:
but
Token but
Feature activation+0.035
Top resid features:
often
Token often
Feature activation-0.024
Top resid features:
get
Token get
Feature activation+0.187
Top resid features:
sent
Token sent
Feature activation+1.241
Top resid features:
interesting
Token interesting
Feature activation-0.003
Top resid features:
stories
Token stories
Feature activation+0.025
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
don
Token don
Feature activation-0.001
Top resid features:
't
Token't
Feature activation-0.023
Top resid features:
but
Token but
Feature activation+0.025
Top resid features:
often
Token often
Feature activation-0.042
Top resid features:
get
Token get
Feature activation+0.049
Top resid features:
sent
Token sent
Feature activation+1.368
Top resid features:
interesting
Token interesting
Feature activation+0.054
Top resid features:
stories
Token stories
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.30

Head 1: 0.02

Head 2: 0.05

Head 3: 0.07

Head 4: 0.02

Head 5: 0.06

Head 6: 0.04

Head 7: 0.08

Head 8: 0.05

Head 9: 0.07

Head 10: 0.15

Head 11: 0.08

Positive logits

rouse1.99

infl1.68

don1.49

orah1.48

ow1.44

rib1.43

hent1.43

Nap1.36

onto1.35

ritic1.33

Smith1.33

raft1.31

act1.31

weekly1.30

mt1.29

dro1.27

manic1.27

Fan1.27

scl1.25

Wo1.24

Negative logits

constitu-1.65

behavi-1.52

sovere-1.47

GOODMAN-1.46

Subtle-1.44

Attribution-1.44

itect-1.42

-1.41

ITNESS-1.40

organis-1.40

/>-1.38

arrang-1.36

pects-1.35

Caucasus-1.35

��-1.35

Defenders-1.35

physic-1.35

و-1.34

Cyborg-1.34

dB-1.33

INTERVAL 1.331 - 1.479
CONTAINS 0.000%

W
TokenW
Feature activation+0.000
old
Tokenold
Feature activation+0.000
then
Token then
Feature activation+0.000
threw
Token threw
Feature activation+0.000
the
Token the
Feature activation+0.000
plans
Token plans
Feature activation+1.479
down
Token down
Feature activation+0.276
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
planning
Token planning
Feature activation+0.000
table
Token table
Feature activation+0.000

INTERVAL 1.183 - 1.331
CONTAINS 0.000%

public
Token public
Feature activation+0.000
lands
Token lands
Feature activation+0.000
that
Token that
Feature activation+0.000
can
Token can
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
experiences
Token experiences
Feature activation+1.327
on
Token on
Feature activation+0.000
par
Token par
Feature activation+0.000
with
Token with
Feature activation+0.000
those
Token those
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 1.035 - 1.183
CONTAINS 0.000%

so
Token so
Feature activation+0.000
they
Token they
Feature activation+0.000
took
Token took
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.613
window
Token window
Feature activation+1.093
out
Token out
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
done
Token done
Feature activation+0.237
John
Token John
Feature activation+0.000
Scal
Token Scal
Feature activation+0.000
zi
Tokenzi
Feature activation+0.000
donated
Token donated
Feature activation+0.000
was
Token was
Feature activation+0.291
going
Token going
Feature activation+1.068
into
Token into
Feature activation+0.075
an
Token an
Feature activation+0.000
auction
Token auction
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
bought
Token bought
Feature activation+0.000
the
Token the
Feature activation+0.000
business
Token business
Feature activation+1.056
from
Token from
Feature activation+0.000
her
Token her
Feature activation+0.000
in
Token in
Feature activation+0.000
1968
Token 1968
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.888 - 1.035
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+0.000
has
Token has
Feature activation+0.000
also
Token also
Feature activation+0.000
submitted
Token submitted
Feature activation+0.000
proven
Token proven
Feature activation+0.896
reports
Token reports
Feature activation+0.000
on
Token on
Feature activation+0.098
murder
Token murder
Feature activation+0.000
,
Token,
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
a
Token a
Feature activation+0.000
second
Token second
Feature activation+0.000
.
Token.
Feature activation+0.000
Yang
Token Yang
Feature activation+0.000
fell
Token fell
Feature activation+0.000
forward
Token forward
Feature activation+0.949
into
Token into
Feature activation+0.000
Salem
Token Salem
Feature activation+0.000
who
Token who
Feature activation+0.000
happily
Token happily
Feature activation+0.000
caught
Token caught
Feature activation+0.000
Wang
Token Wang
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
offered
Token offered
Feature activation+0.000
a
Token a
Feature activation+0.000
job
Token job
Feature activation+0.941
at
Token at
Feature activation+0.101
a
Token a
Feature activation+0.000
college
Token college
Feature activation+0.000
in
Token in
Feature activation+0.000
Beijing
Token Beijing
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
His
TokenHis
Feature activation+0.000
directing
Token directing
Feature activation+0.000
debut
Token debut
Feature activation+1.022
was
Token was
Feature activation+0.267
the
Token the
Feature activation+0.132
acclaimed
Token acclaimed
Feature activation+0.251
Wh
Token Wh
Feature activation+0.000
istle
Tokenistle
Feature activation+0.000
whoever
Token whoever
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
take
Token take
Feature activation+0.000
his
Token his
Feature activation+0.000
cross
Token cross
Feature activation+0.968
and
Token and
Feature activation+0.000
follow
Token follow
Feature activation+0.000
me
Token me
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000

INTERVAL 0.740 - 0.888
CONTAINS 0.003%

When
Token When
Feature activation+0.000
someone
Token someone
Feature activation+0.000
else
Token else
Feature activation+0.000
buys
Token buys
Feature activation+0.000
your
Token your
Feature activation+0.000
work
Token work
Feature activation+0.781
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
do
Token do
Feature activation+0.000
have
Token have
Feature activation+0.091
a
Token a
Feature activation+0.000
professional
Token professional
Feature activation+0.000
baseball
Token baseball
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
struck
Token struck
Feature activation+0.000
out
Token out
Feature activation+0.777
38
Token 38
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
's
Token's
Feature activation+0.000
46
Token 46
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.073
repeatedly
Token repeatedly
Feature activation+0.000
struck
Token struck
Feature activation+0.000
his
Token his
Feature activation+0.044
son
Token son
Feature activation+0.826
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
tree
Token tree
Feature activation+0.092
branch
Token branch
Feature activation+0.028
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
assailants
Token assailants
Feature activation+0.000
,
Token,
Feature activation+0.228
who
Token who
Feature activation+0.000
fled
Token fled
Feature activation+0.000
back
Token back
Feature activation+0.820
inside
Token inside
Feature activation+0.033
the
Token the
Feature activation+0.000
compound
Token compound
Feature activation+0.000
and
Token and
Feature activation+0.000
exchanged
Token exchanged
Feature activation+0.000
release
Token release
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
it
Token it
Feature activation+0.071
is
Token is
Feature activation+0.745
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
ded
Tokended
Feature activation+0.000
icated
Tokenicated
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.592 - 0.740
CONTAINS 0.005%

od
Tokenod
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
Taylor
Token Taylor
Feature activation+0.000
scored
Token scored
Feature activation+0.000
a
Token a
Feature activation+0.000
hat
Token hat
Feature activation+0.646
-
Token-
Feature activation+0.000
tr
Tokentr
Feature activation+0.000
ick
Tokenick
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
The
Token The
Feature activation+0.000
company
Token company
Feature activation+0.000
also
Token also
Feature activation+0.000
mined
Token mined
Feature activation+0.000
the
Token the
Feature activation+0.000
comment
Token comment
Feature activation+0.644
sections
Token sections
Feature activation+0.561
of
Token of
Feature activation+0.051
Wikipedia
Token Wikipedia
Feature activation+0.000
and
Token and
Feature activation+0.000
collected
Token collected
Feature activation+0.000
But
Token But
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+0.000
also
Token also
Feature activation+0.000
brought
Token brought
Feature activation+0.000
risks
Token risks
Feature activation+0.730
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+0.000
they
Token they
Feature activation+0.000
took
Token took
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.613
window
Token window
Feature activation+1.093
out
Token out
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
verse
Tokenverse
Feature activation+0.000
City
Token City
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
returned
Token returned
Feature activation+0.000
this
Token this
Feature activation+0.688
year
Token year
Feature activation+0.000
because
Token because
Feature activation+0.000
she
Token she
Feature activation+0.000
wanted
Token wanted
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.444 - 0.592
CONTAINS 0.013%

my
Token my
Feature activation+0.000
chances
Token chances
Feature activation+0.340
and
Token and
Feature activation+0.000
placed
Token placed
Feature activation+0.000
my
Token my
Feature activation+0.000
purse
Token purse
Feature activation+0.537
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
locker
Token locker
Feature activation+0.145
.
Token.
Feature activation+0.000
Why
Token Why
Feature activation+0.000
Union
Token Union
Feature activation+0.000
shall
Token shall
Feature activation+0.355
have
Token have
Feature activation+0.449
the
Token the
Feature activation+0.175
sole
Token sole
Feature activation+0.632
right
Token right
Feature activation+0.458
and
Token and
Feature activation+0.000
discretion
Token discretion
Feature activation+0.000
to
Token to
Feature activation+0.000
determine
Token determine
Feature activation+0.000
whether
Token whether
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
function
Tokenfunction
Feature activation+0.000
send
Token send
Feature activation+0.000
Score
TokenScore
Feature activation+0.493
To
TokenTo
Feature activation+0.000
SC
TokenSC
Feature activation+0.000
OR
TokenOR
Feature activation+0.000
M
TokenM
Feature activation+0.000
(
Token(
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
caught
Token caught
Feature activation+0.000
sending
Token sending
Feature activation+0.000
a
Token a
Feature activation+0.000
suggestive
Token suggestive
Feature activation+0.584
photo
Token photo
Feature activation+0.007
of
Token of
Feature activation+0.000
himself
Token himself
Feature activation+0.000
to
Token to
Feature activation+0.000
another
Token another
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
draft
Token draft
Feature activation+0.000
showed
Token showed
Feature activation+0.172
key
Token key
Feature activation+0.475
budget
Token budget
Feature activation+0.181
areas
Token areas
Feature activation+0.024
âĢĵ
Token âĢĵ
Feature activation+0.000
the
Token the
Feature activation+0.000
Common
Token Common
Feature activation+0.000

INTERVAL 0.296 - 0.444
CONTAINS 0.037%

have
Token have
Feature activation+0.000
released
Token released
Feature activation+0.000
the
Token the
Feature activation+0.000
man
Token man
Feature activation+0.010
's
Token's
Feature activation+0.000
identity
Token identity
Feature activation+0.330
.
Token.
Feature activation+0.000
NBC
Token NBC
Feature activation+0.000
6
Token 6
Feature activation+0.000
's
Token's
Feature activation+0.000
Christina
Token Christina
Feature activation+0.000
ships
Token ships
Feature activation+0.000
super
Token super
Feature activation+0.000
fast
Token fast
Feature activation+0.000
,
Token,
Feature activation+0.000
got
Token got
Feature activation+0.000
mine
Token mine
Feature activation+0.313
within
Token within
Feature activation+0.000
6
Token 6
Feature activation+0.000
days
Token days
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
iers
Tokeniers
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
return
Token return
Feature activation+0.000
calls
Token calls
Feature activation+0.000
seeking
Token seeking
Feature activation+0.342
comment
Token comment
Feature activation+0.253
on
Token on
Feature activation+0.569
any
Token any
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.000
with
Token with
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
resh
Token resh
Feature activation+0.000
aping
Tokenaping
Feature activation+0.000
the
Token the
Feature activation+0.000
controversy
Token controversy
Feature activation+0.348
hammer
Token hammer
Feature activation+0.125
ing
Tokening
Feature activation+0.000
Moore
Token Moore
Feature activation+0.000
,
Token,
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
alternating
Token alternating
Feature activation+0.000
raised
Token raised
Feature activation+0.001
and
Token and
Feature activation+0.000
lowered
Token lowered
Feature activation+0.000
rid
Token rid
Feature activation+0.874
ges
Tokenges
Feature activation+0.380
along
Token along
Feature activation+0.271
the
Token the
Feature activation+0.000
outer
Token outer
Feature activation+0.000
rim
Token rim
Feature activation+0.000
which
Token which
Feature activation+0.071

INTERVAL 0.148 - 0.296
CONTAINS 0.108%

two
Token two
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000
left
Token left
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
goal
Token goal
Feature activation+0.164
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
raise
Token raise
Feature activation+0.000
45
Token 45
Feature activation+0.000
,
Token,
Feature activation+0.000
Eston
Token Eston
Feature activation+0.000
Koh
Token Koh
Feature activation+0.000
ver
Tokenver
Feature activation+0.000
is
Token is
Feature activation+0.000
released
Token released
Feature activation+0.000
in
Token in
Feature activation+0.211
exchange
Token exchange
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
is
Token is
Feature activation+0.000
fine
Token fine
Feature activation+0.000
,
Token,
Feature activation+0.000
given
Token given
Feature activation+0.000
our
Token our
Feature activation+0.000
comfortable
Token comfortable
Feature activation+0.149
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
to
Token to
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
important
Token important
Feature activation+0.000
issues
Token issues
Feature activation+0.199
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
from
Token from
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
enabled
Token enabled
Feature activation+0.000
a
Token a
Feature activation+0.172
side
Token side
Feature activation+0.272
-
Token-
Feature activation+0.000
by
Tokenby
Feature activation+0.000
-
Token-
Feature activation+0.000
side
Tokenside
Feature activation+0.000

INTERVAL 0.000 - 0.148
CONTAINS 99.833%

Donald
Token Donald
Feature activation+0.000
tweeted
Token tweeted
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
felt
Token felt
Feature activation+0.000
sorry
Token sorry
Feature activation+0.000
for
Token for
Feature activation+0.000
her
Token her
Feature activation+0.000
new
Token new
Feature activation+0.000
partner
Token partner
Feature activation+0.000
in
Token in
Feature activation+0.000
up
Token up
Feature activation+0.000
faster
Token faster
Feature activation+0.000
than
Token than
Feature activation+0.000
a
Token a
Feature activation+0.000
strawberry
Token strawberry
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Tokenand
Feature activation+0.000
-
Token-
Feature activation+0.000
van
Tokenvan
Feature activation+0.000
illa
Tokenilla
Feature activation+0.000
-
Token-
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
got
Token got
Feature activation+0.000
a
Token a
Feature activation+0.000
plank
Token plank
Feature activation+0.000
perpendicular
Token perpendicular
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
edge
Token edge
Feature activation+0.000
of
Token of
Feature activation+0.000
to
Token to
Feature activation+0.000
propel
Token propel
Feature activation+0.000
coal
Token coal
Feature activation+0.000
past
Token past
Feature activation+0.000
oil
Token oil
Feature activation+0.000
by
Token by
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
decade
Token decade
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
(
Token (
Feature activation+0.000
which
Tokenwhich
Feature activation+0.000
covers
Token covers
Feature activation+0.000
testing
Token testing
Feature activation+0.000
sites
Token sites
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
Fort
Token Fort
Feature activation+0.000
Det
Token Det
Feature activation+0.000
rick
Tokenrick
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

,
Token,
Feature activation+0.000
a
Token a
Feature 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
Organisation
Token Organisation
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
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+0.158
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+0.158
by
Token by
Feature activation+0.000
headed
Token headed
Feature activation+0.158
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.158
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
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+0.158
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.158
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.158
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.158
by
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+0.158
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+0.158
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 7 in H2.0: (feature 9409)

TOP ACTIVATIONS
MAX = 1.489

Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+0.000
has
Token has
Feature activation+0.000
also
Token also
Feature activation+0.000
submitted
Token submitted
Feature activation+0.000
proven
Token proven
Feature activation+1.489
reports
Token reports
Feature activation+0.281
on
Token on
Feature activation+0.759
murder
Token murder
Feature activation+0.000
,
Token,
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
,
Token,
Feature activation+0.000
President
Token President
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
gave
Token gave
Feature activation+0.000
a
Token a
Feature activation+0.000
moving
Token moving
Feature activation+1.340
speech
Token speech
Feature activation+0.073
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
in
Token in
Feature activation+0.000
said
Token said
Feature activation+0.000
she
Token she
Feature activation+0.000
has
Token has
Feature activation+0.000
received
Token received
Feature activation+0.015
requests
Token requests
Feature activation+0.555
for
Token for
Feature activation+1.047
death
Token death
Feature activation+0.000
certificates
Token certificates
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
proprietary
Token proprietary
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
.
Token.
Feature activation+0.000
Ag
Token Ag
Feature activation+0.000
ile
Tokenile
Feature activation+0.000
pushes
Token pushes
Feature activation+0.000
responsibility
Token responsibility
Feature activation+0.977
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
teams
Token teams
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
would
Token would
Feature activation+0.000
bring
Token bring
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
more
Token more
Feature activation+0.000
pressure
Token pressure
Feature activation+0.942
on
Token on
Feature activation+0.000
McGregor
Token McGregor
Feature activation+0.000
right
Token right
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+0.000
responded
Token responded
Feature activation+0.000
saying
Token saying
Feature activation+0.938
that
Token that
Feature activation+0.374
Russia
Token Russia
Feature activation+0.000
was
Token was
Feature activation+0.132
only
Token only
Feature activation+0.000
interested
Token interested
Feature activation+0.000
Finland
Token Finland
Feature activation+0.000
,
Token,
Feature activation+0.000
submitted
Token submitted
Feature activation+0.000
a
Token a
Feature activation+0.000
report
Token report
Feature activation+0.000
on
Token on
Feature activation+0.834
basic
Token basic
Feature activation+0.000
income
Token income
Feature activation+0.000
experiments
Token experiments
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
Abbas
Token Abbas
Feature activation+0.000
submitted
Token submitted
Feature activation+0.145
a
Token a
Feature activation+0.162
request
Token request
Feature activation+0.412
for
Token for
Feature activation+0.831
an
Token an
Feature activation+0.000
emergency
Token emergency
Feature activation+0.047
meeting
Token meeting
Feature activation+0.042
in
Token in
Feature activation+0.011
the
Token the
Feature activation+0.000
Serv
Token Serv
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
have
Token have
Feature activation+0.000
committed
Token committed
Feature activation+0.000
widespread
Token widespread
Feature activation+0.821
fraud
Token fraud
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
foreclosure
Token foreclosure
Feature activation+0.000
process
Token process
Feature activation+0.000
reason
Token reason
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
hired
Token hired
Feature activation+0.000
us
Token us
Feature activation+0.000
is
Token is
Feature activation+0.809
that
Token that
Feature activation+0.529
they
Token they
Feature activation+0.000
want
Token want
Feature activation+0.122
to
Token to
Feature activation+0.000
show
Token show
Feature activation+0.000
then
Token then
Feature activation+0.000
donated
Token donated
Feature activation+0.187
the
Token the
Feature activation+0.168
maximum
Token maximum
Feature activation+0.414
amount
Token amount
Feature activation+0.138
allowed
Token allowed
Feature activation+0.803
to
Token to
Feature activation+0.102
both
Token both
Feature activation+0.000
Sanders
Token Sanders
Feature activation+0.000
and
Token and
Feature activation+0.000
Hillary
Token Hillary
Feature activation+0.000
tries
Token tries
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
sent
Token sent
Feature activation+0.000
the
Token the
Feature activation+0.000
hardest
Token hardest
Feature activation+0.802
project
Token project
Feature activation+0.365
I
Token I
Feature activation+0.125
ever
Token ever
Feature activation+0.156
tried
Token tried
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
sends
Token sends
Feature activation+0.000
a
Token a
Feature activation+0.000
disturbing
Token disturbing
Feature activation+0.792
message
Token message
Feature activation+0.000
that
Token that
Feature activation+0.338
their
Token their
Feature activation+0.000
lives
Token lives
Feature activation+0.041
have
Token have
Feature activation+0.077
the
Token the
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
Amber
Token Amber
Feature activation+0.000
Heard
Token Heard
Feature activation+0.000
received
Token received
Feature activation+0.000
for
Token for
Feature activation+0.790
being
Token being
Feature activation+0.198
bisexual
Token bisexual
Feature activation+0.000
were
Token were
Feature activation+0.034
entirely
Token entirely
Feature activation+0.000
expected
Token expected
Feature activation+0.000
war
Token war
Feature activation+0.000
in
Token in
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
which
Token which
Feature activation+0.000
killed
Token killed
Feature activation+0.000
around
Token around
Feature activation+0.774
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.000
100
Token100
Feature activation+0.000
Palestinians
Token Palestinians
Feature activation+0.000
,
Token,
Feature activation+0.000
subsequent
Token subsequent
Feature activation+0.000
beating
Token beating
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
fell
Token fell
Feature activation+0.000
forward
Token forward
Feature activation+0.770
on
Token on
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
camp
Token camp
Feature activation+0.000
Command
Token Command
Feature activation+0.000
ner
Tokenner
Feature activation+0.000
ino
Tokenino
Feature activation+0.000
gave
Token gave
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
a
Token a
Feature activation+0.000
copy
Token copy
Feature activation+0.762
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
2008
Token 2008
Feature activation+0.000
calendar
Token calendar
Feature activation+0.195
when
Token when
Feature activation+0.000
Israeli
TokenIsraeli
Feature activation+0.000
strikes
Token strikes
Feature activation+0.000
have
Token have
Feature activation+0.000
hit
Token hit
Feature activation+0.000
an
Token an
Feature activation+0.000
arms
Token arms
Feature activation+0.762
depot
Token depot
Feature activation+0.000
operated
Token operated
Feature activation+0.346
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Lebanese
Token Lebanese
Feature activation+0.000
has
Token has
Feature activation+0.000
also
Token also
Feature activation+0.000
submitted
Token submitted
Feature activation+0.000
proven
Token proven
Feature activation+1.489
reports
Token reports
Feature activation+0.281
on
Token on
Feature activation+0.759
murder
Token murder
Feature activation+0.000
,
Token,
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
detention
Token detention
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.119
,
Token,
Feature activation+0.000
gave
Token gave
Feature activation+0.048
liquor
Token liquor
Feature activation+0.188
business
Token business
Feature activation+0.757
a
Token a
Feature activation+0.000
boost
Token boost
Feature activation+0.049
.
Token.
Feature activation+0.087
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Public
TokenPublic
Feature activation+0.000

Top DFA by src position
MAX = 2.055

Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
She
TokenShe
Feature activation+0.040
Top resid features:
has
Token has
Feature activation+0.009
Top resid features:
also
Token also
Feature activation+0.019
Top resid features:
submitted
Token submitted
Feature activation+2.055
Top resid features:
proven
Token proven
Feature activation-0.036
Top resid features:
reports
Token reports
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
murder
Token murder
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation-0.001
Top resid features:
Tonight
TokenTonight
Feature activation+0.033
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
President
Token President
Feature activation+0.017
Top resid features:
Trump
Token Trump
Feature activation-0.002
Top resid features:
gave
Token gave
Feature activation+1.687
Top resid features:
a
Token a
Feature activation+0.106
Top resid features:
moving
Token moving
Feature activation+0.166
Top resid features:
speech
Token speech
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:
Aure
Token Aure
Feature activation+0.017
Top resid features:
lia
Tokenlia
Feature activation+0.006
Top resid features:
said
Token said
Feature activation+0.050
Top resid features:
she
Token she
Feature activation+0.047
Top resid features:
has
Token has
Feature activation+0.056
Top resid features:
received
Token received
Feature activation+1.482
Top resid features:
requests
Token requests
Feature activation+0.003
Top resid features:
for
Token for
Feature activation+0.001
Top resid features:
death
Token death
Feature activation+0.000
Top resid features:
certificates
Token certificates
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.044
Top resid features:
leaders
Token leaders
Feature activation+0.018
Top resid features:
.
Token.
Feature activation+0.066
Top resid features:
Ag
Token Ag
Feature activation+0.031
Top resid features:
ile
Tokenile
Feature activation+0.060
Top resid features:
pushes
Token pushes
Feature activation+1.309
Top resid features:
responsibility
Token responsibility
Feature activation+0.050
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
teams
Token teams
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-0.001
Top resid features:
"
Token"
Feature activation+0.016
Top resid features:
I
TokenI
Feature activation+0.026
Top resid features:
would
Token would
Feature activation+0.027
Top resid features:
bring
Token bring
Feature activation+1.285
Top resid features:
a
Token a
Feature activation+0.142
Top resid features:
lot
Token lot
Feature activation+0.040
Top resid features:
more
Token more
Feature activation+0.050
Top resid features:
pressure
Token pressure
Feature activation+0.025
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
But
TokenBut
Feature activation+0.039
Top resid features:
Ukraine
Token Ukraine
Feature activation+0.055
Top resid features:
responded
Token responded
Feature activation+1.114
Top resid features:
saying
Token saying
Feature activation+0.263
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
Russia
Token Russia
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
Insurance
Token Insurance
Feature activation-0.004
Top resid features:
Institution
Token Institution
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.018
Top resid features:
Finland
Token Finland
Feature activation+0.020
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
submitted
Token submitted
Feature activation+1.237
Top resid features:
a
Token a
Feature activation+0.139
Top resid features:
report
Token report
Feature activation-0.010
Top resid features:
on
Token on
Feature activation+0.031
Top resid features:
basic
Token basic
Feature activation+0.000
Top resid features:
income
Token income
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
attempted
Token attempted
Feature activation+0.046
Top resid features:
assassination
Token assassination
Feature activation+0.056
Top resid features:
,
Token,
Feature activation+0.052
Top resid features:
Abbas
Token Abbas
Feature activation+0.012
Top resid features:
submitted
Token submitted
Feature activation+1.176
Top resid features:
a
Token a
Feature activation+0.135
Top resid features:
request
Token request
Feature activation+0.004
Top resid features:
for
Token for
Feature activation-0.012
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
emergency
Token emergency
Feature activation+0.000
Top resid features:
."
Token."
Feature activation-0.021
Top resid features:
Serv
Token Serv
Feature activation+0.041
Top resid features:
ic
Tokenic
Feature activation-0.000
Top resid features:
ers
Tokeners
Feature activation-0.017
Top resid features:
have
Token have
Feature activation+0.077
Top resid features:
committed
Token committed
Feature activation+1.411
Top resid features:
widespread
Token widespread
Feature activation+0.027
Top resid features:
fraud
Token fraud
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:
foreclosure
Token foreclosure
Feature activation+0.000
Top resid features:
think
Token think
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
reason
Token reason
Feature activation+0.038
Top resid features:
they
Token they
Feature activation+0.004
Top resid features:
have
Token have
Feature activation+0.114
Top resid features:
hired
Token hired
Feature activation+1.226
Top resid features:
us
Token us
Feature activation+0.008
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
want
Token want
Feature activation+0.000
Top resid features:
openly
Token openly
Feature activation+0.027
Top resid features:
gay
Token gay
Feature activation+0.005
Top resid features:
Hollywood
Token Hollywood
Feature activation+0.009
Top resid features:
executive
Token executive
Feature activation+0.014
Top resid features:
then
Token then
Feature activation+0.014
Top resid features:
donated
Token donated
Feature activation+1.033
Top resid features:
the
Token the
Feature activation+0.083
Top resid features:
maximum
Token maximum
Feature activation+0.125
Top resid features:
amount
Token amount
Feature activation+0.063
Top resid features:
allowed
Token allowed
Feature activation+0.100
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
lot
Token lot
Feature activation+0.031
Top resid features:
of
Token of
Feature activation-0.046
Top resid features:
tries
Token tries
Feature activation-0.021
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
I
Token I
Feature activation+0.024
Top resid features:
sent
Token sent
Feature activation+1.300
Top resid features:
the
Token the
Feature activation+0.066
Top resid features:
hardest
Token hardest
Feature activation+0.063
Top resid features:
project
Token project
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
ever
Token ever
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.019
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
âĢ
Token âĢ
Feature activation+0.016
Top resid features:
ľ
Tokenľ
Feature activation-0.008
Top resid features:
This
TokenThis
Feature activation+0.051
Top resid features:
sends
Token sends
Feature activation+1.254
Top resid features:
a
Token a
Feature activation+0.064
Top resid features:
disturbing
Token disturbing
Feature activation+0.078
Top resid features:
message
Token message
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
But
TokenBut
Feature activation+0.035
Top resid features:
the
Token the
Feature activation+0.047
Top resid features:
attacks
Token attacks
Feature activation+0.145
Top resid features:
Amber
Token Amber
Feature activation+0.031
Top resid features:
Heard
Token Heard
Feature activation+0.006
Top resid features:
received
Token received
Feature activation+1.193
Top resid features:
for
Token for
Feature activation-0.007
Top resid features:
being
Token being
Feature activation+0.000
Top resid features:
bisexual
Token bisexual
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
entirely
Token entirely
Feature activation+0.000
Top resid features:
Palestinian
TokenPalestinian
Feature activation-0.001
Top resid features:
war
Token war
Feature activation+0.017
Top resid features:
in
Token in
Feature activation-0.017
Top resid features:
2014
Token 2014
Feature activation+0.037
Top resid features:
which
Token which
Feature activation-0.016
Top resid features:
killed
Token killed
Feature activation+1.315
Top resid features:
around
Token around
Feature activation+0.032
Top resid features:
2
Token 2
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
100
Token100
Feature activation+0.000
Top resid features:
Palestinians
Token Palestinians
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
subsequent
Token subsequent
Feature activation-0.008
Top resid features:
beating
Token beating
Feature activation+0.064
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
he
Token he
Feature activation-0.003
Top resid features:
fell
Token fell
Feature activation+1.251
Top resid features:
forward
Token forward
Feature activation+0.072
Top resid features:
on
Token on
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:
camp
Token camp
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
An
TokenAn
Feature activation+0.023
Top resid features:
ner
Tokenner
Feature activation-0.007
Top resid features:
ino
Tokenino
Feature activation-0.001
Top resid features:
gave
Token gave
Feature activation+1.274
Top resid features:
Paul
Token Paul
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.079
Top resid features:
copy
Token copy
Feature activation+0.131
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.015
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.022
Top resid features:
Israeli
TokenIsraeli
Feature activation+0.005
Top resid features:
strikes
Token strikes
Feature activation+0.140
Top resid features:
have
Token have
Feature activation+0.028
Top resid features:
hit
Token hit
Feature activation+1.233
Top resid features:
an
Token an
Feature activation+0.167
Top resid features:
arms
Token arms
Feature activation-0.004
Top resid features:
depot
Token depot
Feature activation+0.000
Top resid features:
operated
Token operated
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
She
TokenShe
Feature activation+0.027
Top resid features:
has
Token has
Feature activation+0.020
Top resid features:
also
Token also
Feature activation+0.015
Top resid features:
submitted
Token submitted
Feature activation+1.215
Top resid features:
proven
Token proven
Feature activation+0.124
Top resid features:
reports
Token reports
Feature activation-0.001
Top resid features:
on
Token on
Feature activation+0.019
Top resid features:
murder
Token murder
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
influx
Token influx
Feature activation+0.038
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
he
Token he
Feature activation+0.010
Top resid features:
said
Token said
Feature activation+0.037
Top resid features:
,
Token,
Feature activation+0.055
Top resid features:
gave
Token gave
Feature activation+1.099
Top resid features:
liquor
Token liquor
Feature activation+0.066
Top resid features:
business
Token business
Feature activation+0.066
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
boost
Token boost
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.29

Head 1: 0.03

Head 2: 0.04

Head 3: 0.07

Head 4: 0.02

Head 5: 0.06

Head 6: 0.05

Head 7: 0.08

Head 8: 0.06

Head 9: 0.07

Head 10: 0.15

Head 11: 0.08

Positive logits

rouse1.85

infl1.51

Fan1.41

orah1.40

Nap1.37

scl1.34

Smith1.34

don1.33

Church1.32

fre1.30

ft1.27

ow1.27

Nov1.27

mog1.26

rib1.25

dro1.24

venge1.23

bol1.22

Wars1.22

manic1.22

Negative logits

constitu-1.61

itect-1.51

Attribution-1.45

Subtle-1.39

destro-1.34

pherd-1.33

GOODMAN-1.32

/>-1.30

GGGGGGGG-1.30

INCLUD-1.29

ット-1.29

sovere-1.27

ocally-1.27

behavi-1.26

INESS-1.23

distinguishing-1.22

~~~~~~~~-1.20

''.-1.20

Defenders-1.20

-1.19

INTERVAL 1.340 - 1.489
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+0.000
has
Token has
Feature activation+0.000
also
Token also
Feature activation+0.000
submitted
Token submitted
Feature activation+0.000
proven
Token proven
Feature activation+1.489
reports
Token reports
Feature activation+0.281
on
Token on
Feature activation+0.759
murder
Token murder
Feature activation+0.000
,
Token,
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000

INTERVAL 1.191 - 1.340
CONTAINS 0.000%

,
Token,
Feature activation+0.000
President
Token President
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
gave
Token gave
Feature activation+0.000
a
Token a
Feature activation+0.000
moving
Token moving
Feature activation+1.340
speech
Token speech
Feature activation+0.073
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 1.042 - 1.191
CONTAINS 0.000%

said
Token said
Feature activation+0.000
she
Token she
Feature activation+0.000
has
Token has
Feature activation+0.000
received
Token received
Feature activation+0.015
requests
Token requests
Feature activation+0.555
for
Token for
Feature activation+1.047
death
Token death
Feature activation+0.000
certificates
Token certificates
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
proprietary
Token proprietary
Feature activation+0.000

INTERVAL 0.893 - 1.042
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+0.000
responded
Token responded
Feature activation+0.000
saying
Token saying
Feature activation+0.938
that
Token that
Feature activation+0.374
Russia
Token Russia
Feature activation+0.000
was
Token was
Feature activation+0.132
only
Token only
Feature activation+0.000
interested
Token interested
Feature activation+0.000
would
Token would
Feature activation+0.000
bring
Token bring
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
more
Token more
Feature activation+0.000
pressure
Token pressure
Feature activation+0.942
on
Token on
Feature activation+0.000
McGregor
Token McGregor
Feature activation+0.000
right
Token right
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
leaders
Token leaders
Feature activation+0.000
.
Token.
Feature activation+0.000
Ag
Token Ag
Feature activation+0.000
ile
Tokenile
Feature activation+0.000
pushes
Token pushes
Feature activation+0.000
responsibility
Token responsibility
Feature activation+0.977
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
teams
Token teams
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.744 - 0.893
CONTAINS 0.002%

reason
Token reason
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
hired
Token hired
Feature activation+0.000
us
Token us
Feature activation+0.000
is
Token is
Feature activation+0.809
that
Token that
Feature activation+0.529
they
Token they
Feature activation+0.000
want
Token want
Feature activation+0.122
to
Token to
Feature activation+0.000
show
Token show
Feature activation+0.000
Serv
Token Serv
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
have
Token have
Feature activation+0.000
committed
Token committed
Feature activation+0.000
widespread
Token widespread
Feature activation+0.821
fraud
Token fraud
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
foreclosure
Token foreclosure
Feature activation+0.000
process
Token process
Feature activation+0.000
Israeli
TokenIsraeli
Feature activation+0.000
strikes
Token strikes
Feature activation+0.000
have
Token have
Feature activation+0.000
hit
Token hit
Feature activation+0.000
an
Token an
Feature activation+0.000
arms
Token arms
Feature activation+0.762
depot
Token depot
Feature activation+0.000
operated
Token operated
Feature activation+0.346
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Lebanese
Token Lebanese
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.119
,
Token,
Feature activation+0.000
gave
Token gave
Feature activation+0.048
liquor
Token liquor
Feature activation+0.188
business
Token business
Feature activation+0.757
a
Token a
Feature activation+0.000
boost
Token boost
Feature activation+0.049
.
Token.
Feature activation+0.087
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Public
TokenPublic
Feature activation+0.000
then
Token then
Feature activation+0.000
donated
Token donated
Feature activation+0.187
the
Token the
Feature activation+0.168
maximum
Token maximum
Feature activation+0.414
amount
Token amount
Feature activation+0.138
allowed
Token allowed
Feature activation+0.803
to
Token to
Feature activation+0.102
both
Token both
Feature activation+0.000
Sanders
Token Sanders
Feature activation+0.000
and
Token and
Feature activation+0.000
Hillary
Token Hillary
Feature activation+0.000

INTERVAL 0.595 - 0.744
CONTAINS 0.005%

Coffee
Token Coffee
Feature activation+0.000
Ro
Token Ro
Feature activation+0.000
asters
Tokenasters
Feature activation+0.000
also
Token also
Feature activation+0.000
offers
Token offers
Feature activation+0.000
records
Token records
Feature activation+0.618
for
Token for
Feature activation+0.000
sale
Token sale
Feature activation+0.000
through
Token through
Feature activation+0.000
a
Token a
Feature activation+0.000
partnership
Token partnership
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
turning
Token turning
Feature activation+0.000
point
Token point
Feature activation+0.634
,
Token,
Feature activation+0.132
for
Token for
Feature activation+0.004
me
Token me
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
war
Token war
Feature activation+0.000
in
Token in
Feature activation+0.000
Yemen
Token Yemen
Feature activation+0.000
has
Token has
Feature activation+0.000
killed
Token killed
Feature activation+0.000
over
Token over
Feature activation+0.651
10
Token 10
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
people
Token people
Feature activation+0.000
and
Token and
Feature activation+0.000
"
Token "
Feature activation+0.000
I
TokenI
Feature activation+0.000
have
Token have
Feature activation+0.000
lost
Token lost
Feature activation+0.052
my
Token my
Feature activation+0.000
best
Token best
Feature activation+0.701
friend
Token friend
Feature activation+0.000
and
Token and
Feature activation+0.000
my
Token my
Feature activation+0.000
soul
Token soul
Feature activation+0.000
mate
Token mate
Feature activation+0.000
data
Token data
Feature activation+0.074
showing
Token showing
Feature activation+0.067
that
Token that
Feature activation+0.000
read
Token read
Feature activation+0.224
missions
Tokenmissions
Feature activation+0.331
have
Token have
Feature activation+0.677
fallen
Token fallen
Feature activation+0.131
since
Token since
Feature activation+0.146
the
Token the
Feature activation+0.000
penalties
Token penalties
Feature activation+0.000
took
Token took
Feature activation+0.000

INTERVAL 0.447 - 0.595
CONTAINS 0.013%

second
Token second
Feature activation+0.000
factor
Token factor
Feature activation+0.000
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
changed
Token changed
Feature activation+0.000
is
Token is
Feature activation+0.584
that
Token that
Feature activation+0.162
the
Token the
Feature activation+0.000
German
Token German
Feature activation+0.000
government
Token government
Feature activation+0.000
now
Token now
Feature activation+0.000
sharing
Tokensharing
Feature activation+0.000
icon
Token icon
Feature activation+0.000
.
Token.
Feature activation+0.000
People
Token People
Feature activation+0.000
got
Token got
Feature activation+0.056
used
Token used
Feature activation+0.474
to
Token to
Feature activation+0.074
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
that
Token that
Feature activation+0.000
Brune
Token Brune
Feature activation+0.000
i
Tokeni
Feature activation+0.000
reached
Token reached
Feature activation+0.000
its
Token its
Feature activation+0.000
greatest
Token greatest
Feature activation+0.535
extent
Token extent
Feature activation+0.000
,
Token,
Feature activation+0.000
never
Token never
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
have
Token have
Feature activation+0.000
SDL
Token SDL
Feature activation+0.000
working
Token working
Feature activation+0.000
,
Token,
Feature activation+0.000
give
Token give
Feature activation+0.062
link
Token link
Feature activation+0.491
er
Tokener
Feature activation+0.066
a
Token a
Feature activation+0.000
clue
Token clue
Feature activation+0.000
where
Token where
Feature activation+0.000
to
Token to
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
received
Token received
Feature activation+0.000
the
Token the
Feature activation+0.000
letter
Token letter
Feature activation+0.499
yesterday
Token yesterday
Feature activation+0.189
âĢ¦
TokenâĢ¦
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
today
Token today
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.298 - 0.447
CONTAINS 0.038%

was
Token was
Feature activation+0.000
shot
Token shot
Feature activation+0.000
and
Token and
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
killed
Token killed
Feature activation+0.000
on
Token on
Feature activation+0.351
Monday
Token Monday
Feature activation+0.000
after
Token after
Feature activation+0.000
escaping
Token escaping
Feature activation+0.000
with
Token with
Feature activation+0.000
another
Token another
Feature activation+0.000
protesters
Token protesters
Feature activation+0.000
chanted
Token chanted
Feature activation+0.000
and
Token and
Feature activation+0.000
shouted
Token shouted
Feature activation+0.000
their
Token their
Feature activation+0.000
way
Token way
Feature activation+0.352
through
Token through
Feature activation+0.072
a
Token a
Feature activation+0.000
town
Token town
Feature activation+0.000
hall
Token hall
Feature activation+0.000
hosted
Token hosted
Feature activation+0.000
told
Token told
Feature activation+0.000
Yahoo
Token Yahoo
Feature activation+0.000
News
Token News
Feature activation+0.000
that
Token that
Feature activation+0.000
stopping
Token stopping
Feature activation+0.000
future
Token future
Feature activation+0.376
atrocities
Token atrocities
Feature activation+0.000
like
Token like
Feature activation+0.000
the
Token the
Feature activation+0.000
mass
Token mass
Feature activation+0.000
shooting
Token shooting
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Its
TokenIts
Feature activation+0.000
vulnerable
Token vulnerable
Feature activation+0.000
position
Token position
Feature activation+0.302
was
Token was
Feature activation+0.163
laid
Token laid
Feature activation+0.160
bare
Token bare
Feature activation+0.000
in
Token in
Feature activation+0.210
an
Token an
Feature activation+0.000
know
Token know
Feature activation+0.000
to
Token to
Feature activation+0.000
hold
Token hold
Feature activation+0.000
the
Token the
Feature activation+0.000
option
Token option
Feature activation+0.632
button
Token button
Feature activation+0.433
or
Token or
Feature activation+0.000
hit
Token hit
Feature activation+0.000
Expand
Token Expand
Feature activation+0.000
by
Token by
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000

INTERVAL 0.149 - 0.298
CONTAINS 0.118%

,
Token,
Feature activation+0.000
local
Token local
Feature activation+0.000
commanders
Token commanders
Feature activation+0.000
bypass
Token bypass
Feature activation+0.000
ed
Tokened
Feature activation+0.000
established
Token established
Feature activation+0.156
protocols
Token protocols
Feature activation+0.278
for
Token for
Feature activation+0.133
reporting
Token reporting
Feature activation+0.000
and
Token and
Feature activation+0.000
requesting
Token requesting
Feature activation+0.000
Air
Token Air
Feature activation+0.000
space
Tokenspace
Feature activation+0.000
is
Token is
Feature activation+0.000
launching
Token launching
Feature activation+0.000
a
Token a
Feature activation+0.000
bounty
Token bounty
Feature activation+0.194
hunter
Token hunter
Feature activation+0.000
drone
Token drone
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
wore
Token wore
Feature activation+0.000
No
Token No
Feature activation+0.000
13
Token13
Feature activation+0.000
with
Token with
Feature activation+0.000
some
Token some
Feature activation+0.000
success
Token success
Feature activation+0.236
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
Six
Token Six
Feature activation+0.000
Nations
Token Nations
Feature activation+0.000
but
Token but
Feature activation+0.000
may
Token may
Feature activation+0.000
think
Token think
Feature activation+0.000
he
Token he
Feature activation+0.000
can
Token can
Feature activation+0.000
take
Token take
Feature activation+0.000
arms
Token arms
Feature activation+0.158
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
sl
Token sl
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
and
Token and
Feature activation+0.000
its
Token its
Feature activation+0.000
government
Token government
Feature activation+0.000
to
Token to
Feature activation+0.000
detain
Token detain
Feature activation+0.000
the
Token the
Feature activation+0.000
admitted
Token admitted
Feature activation+0.196
le
Token le
Feature activation+0.000
aker
Tokenaker
Feature activation+0.000
of
Token of
Feature activation+0.000
documents
Token documents
Feature activation+0.000
about
Token about
Feature activation+0.000

INTERVAL 0.000 - 0.149
CONTAINS 99.824%

pie
Tokenpie
Feature activation+0.000
in
Token in
Feature activation+0.000
system
Token system
Feature activation+0.000
but
Token but
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
see
Token see
Feature activation+0.000
anything
Token anything
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
that
Token that
Feature activation+0.000
day
Token day
Feature activation+0.000
,"
Token,"
Feature activation+0.000
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
.
Token.
Feature activation+0.000
game
Token game
Feature activation+0.000
,
Token,
Feature activation+0.000
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
rules
Token rules
Feature activation+0.000
work
Token work
Feature activation+0.000
in
Token in
Feature activation+0.000
actual
Token actual
Feature activation+0.000
play
Token play
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
ardent
Token ardent
Feature activation+0.000
advocate
Token advocate
Feature activation+0.000
of
Token of
Feature activation+0.000
drastically
Token drastically
Feature activation+0.000
reducing
Token reducing
Feature activation+0.000
government
Token government
Feature activation+0.000
programs
Token programs
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
food
Token food
Feature activation+0.000
stamps
Token stamps
Feature activation+0.000
.
Token.
Feature activation+0.000
Constitution
Token Constitution
Feature activation+0.000
explicitly
Token explicitly
Feature activation+0.000
states
Token states
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+0.000
Justice
Token Justice
Feature activation+0.000
that
Token that
Feature activation+0.000
"
Token "
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 8 in H2.0: (feature 14712)

TOP ACTIVATIONS
MAX = 1.313

describe
Token describe
Feature activation+0.000
the
Token the
Feature activation+0.000
Conservative
Token Conservative
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
brain
Token brain
Feature activation+0.000
trust
Token trust
Feature activation+1.313
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
mid
Token mid
Feature activation+0.000
point
Tokenpoint
Feature activation+0.000
of
Token of
Feature activation+0.000
better
Token better
Feature activation+0.000
construction
Token construction
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
opinion
Token opinion
Feature activation+0.000
noted
Token noted
Feature activation+0.975
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
word
Token word
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
domestic
Token domestic
Feature activation+0.000
grain
Token grain
Feature activation+0.000
price
Token price
Feature activation+0.865
supports
Token supports
Feature activation+0.000
exceeded
Token exceeded
Feature activation+0.000
agreed
Token agreed
Feature activation+0.000
upon
Token upon
Feature activation+0.000
limits
Token limits
Feature activation+0.000
prime
Tokenprime
Feature activation+0.000
mortgages
Token mortgages
Feature activation+0.000
than
Token than
Feature activation+0.000
sub
Token sub
Feature activation+0.000
prime
Tokenprime
Feature activation+0.000
leadership
Token leadership
Feature activation+0.816
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Washington
TokenWashington
Feature activation+0.000
has
Token has
Feature activation+0.000
A
TokenA
Feature activation+0.000
TV
Token TV
Feature activation+0.000
screen
Token screen
Feature activation+0.000
shows
Token shows
Feature activation+0.000
a
Token a
Feature activation+0.000
news
Token news
Feature activation+0.801
report
Token report
Feature activation+0.419
of
Token of
Feature activation+0.000
Edward
Token Edward
Feature activation+0.000
Snowden
Token Snowden
Feature activation+0.000
,
Token,
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
the
Token the
Feature activation+0.000
apparent
Token apparent
Feature activation+0.000
suicide
Token suicide
Feature activation+0.000
bomb
Token bomb
Feature activation+0.000
belt
Token belt
Feature activation+0.782
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
taken
Token taken
Feature activation+0.000
away
Token away
Feature activation+0.000
from
Token from
Feature activation+0.000
publishing
Token publishing
Feature activation+0.000
the
Token the
Feature activation+0.000
cancer
Token cancer
Feature activation+0.000
assessment
Token assessment
Feature activation+0.327
review
Token review
Feature activation+0.728
committee
Token committee
Feature activation+0.746
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
report
Token report
Feature activation+0.000
was
Token was
Feature activation+0.000
that
Token that
Feature activation+0.000
publishing
Token publishing
Feature activation+0.000
the
Token the
Feature activation+0.000
cancer
Token cancer
Feature activation+0.000
assessment
Token assessment
Feature activation+0.327
review
Token review
Feature activation+0.728
committee
Token committee
Feature activation+0.746
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
report
Token report
Feature activation+0.000
ense
Tokenense
Feature activation+0.000
.
Token.
Feature activation+0.000
An
Token An
Feature activation+0.000
alien
Token alien
Feature activation+0.000
invasion
Token invasion
Feature activation+0.029
story
Token story
Feature activation+0.722
.
Token.
Feature activation+0.000
Start
Token Start
Feature activation+0.000
with
Token with
Feature activation+0.000
X
Token X
Feature activation+0.000
-
Token-
Feature activation+0.000
.
Token.
Feature activation+0.000
Yet
Token Yet
Feature activation+0.000
the
Token the
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
billionaires
Token billionaires
Feature activation+0.000
report
Token report
Feature activation+0.713
compiled
Token compiled
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Swiss
Token Swiss
Feature activation+0.000
bank
Token bank
Feature activation+0.000
the
Token the
Feature activation+0.000
public
Token public
Feature activation+0.000
thought
Token thought
Feature activation+0.000
that
Token that
Feature activation+0.000
lunch
Token lunch
Feature activation+0.000
counter
Token counter
Feature activation+0.691
sit
Token sit
Feature activation+0.000
-
Token-
Feature activation+0.000
ins
Tokenins
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
understand
Token understand
Feature activation+0.000
why
Token why
Feature activation+0.000
government
Token government
Feature activation+0.000
bureaucr
Token bureaucr
Feature activation+0.000
acies
Tokenacies
Feature activation+0.027
do
Token do
Feature activation+0.680
some
Token some
Feature activation+0.336
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.036
things
Token things
Feature activation+0.000
they
Token they
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Indian
Token Indian
Feature activation+0.000
engineering
Token engineering
Feature activation+0.000
group
Token group
Feature activation+0.676
Pun
Token Pun
Feature activation+0.000
ji
Tokenji
Feature activation+0.000
Lloyd
Token Lloyd
Feature activation+0.000
are
Token are
Feature activation+0.000
partnering
Token partnering
Feature activation+0.000
.
Token.
Feature activation+0.000
What
Token What
Feature activation+0.000
business
Token business
Feature activation+0.000
does
Token does
Feature activation+0.364
the
Token the
Feature activation+0.136
government
Token government
Feature activation+0.669
have
Token have
Feature activation+0.000
making
Token making
Feature activation+0.000
rules
Token rules
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
costly
Token costly
Feature activation+0.000
added
Token added
Feature activation+0.000
extras
Token extras
Feature activation+0.000
(
Token (
Feature activation+0.000
music
Tokenmusic
Feature activation+0.000
lessons
Token lessons
Feature activation+0.668
,
Token,
Feature activation+0.124
coaching
Token coaching
Feature activation+0.274
and
Token and
Feature activation+0.000
tut
Token tut
Feature activation+0.000
oring
Tokenoring
Feature activation+0.000
,
Token,
Feature activation+0.000
utility
Token utility
Feature activation+0.000
bills
Token bills
Feature activation+0.000
,
Token,
Feature activation+0.000
council
Token council
Feature activation+0.000
tax
Token tax
Feature activation+0.663
and
Token and
Feature activation+0.000
mortgage
Token mortgage
Feature activation+0.000
interest
Token interest
Feature activation+0.000
-
Token -
Feature activation+0.000
subject
Token subject
Feature activation+0.000
The
Token The
Feature activation+0.000
hotel
Token hotel
Feature activation+0.000
and
Token and
Feature activation+0.091
restaurant
Token restaurant
Feature activation+0.000
industries
Token industries
Feature activation+0.425
mirror
Token mirror
Feature activation+0.654
state
Token state
Feature activation+0.092
demographics
Token demographics
Feature activation+0.273
on
Token on
Feature activation+0.038
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.000
cious
Tokencious
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
breath
Token breath
Feature activation+0.000
science
Token science
Feature activation+0.647
must
Token must
Feature activation+0.000
use
Token use
Feature activation+0.027
if
Token if
Feature activation+0.000
it
Token it
Feature activation+0.000
wants
Token wants
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
state
Token state
Feature activation+0.000
constitution
Token constitution
Feature activation+0.639
also
Token also
Feature activation+0.036
provides
Token provides
Feature activation+0.000
another
Token another
Feature activation+0.000
route
Token route
Feature activation+0.000
to
Token to
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
powers
Token powers
Feature activation+0.000
not
Token not
Feature activation+0.629
delegated
Token delegated
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000

Top DFA by src position
MAX = 1.435

to
Token to
Feature activation-0.090
Top resid features:
describe
Token describe
Feature activation-0.023
Top resid features:
the
Token the
Feature activation+0.164
Top resid features:
Conservative
Token Conservative
Feature activation+0.060
Top resid features:
campaign
Token campaign
Feature activation+0.139
Top resid features:
brain
Token brain
Feature activation+1.435
Top resid features:
trust
Token trust
Feature activation-0.061
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
mid
Token mid
Feature activation+0.000
Top resid features:
point
Tokenpoint
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
better
Token better
Feature activation+0.012
Top resid features:
construction
Token construction
Feature activation+0.083
Top resid features:
.
Token.
Feature activation-0.033
Top resid features:
The
Token The
Feature activation+0.150
Top resid features:
opinion
Token opinion
Feature activation+1.149
Top resid features:
noted
Token noted
Feature activation-0.041
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
word
Token word
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
China
Token China
Feature activation+0.040
Top resid features:
âĢ
TokenâĢ
Feature activation-0.008
Top resid features:
Ļ
TokenĻ
Feature activation-0.022
Top resid features:
s
Tokens
Feature activation+0.011
Top resid features:
domestic
Token domestic
Feature activation+0.105
Top resid features:
grain
Token grain
Feature activation+1.176
Top resid features:
price
Token price
Feature activation-0.017
Top resid features:
supports
Token supports
Feature activation+0.000
Top resid features:
exceeded
Token exceeded
Feature activation+0.000
Top resid features:
agreed
Token agreed
Feature activation+0.000
Top resid features:
upon
Token upon
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.014
Top resid features:
matter
Token matter
Feature activation+0.018
Top resid features:
of
Token of
Feature activation-0.065
Top resid features:
sub
Token sub
Feature activation+0.022
Top resid features:
prime
Tokenprime
Feature activation+0.132
Top resid features:
mortgages
Token mortgages
Feature activation+0.514
Top resid features:
than
Token than
Feature activation-0.030
Top resid features:
sub
Token sub
Feature activation-0.016
Top resid features:
prime
Tokenprime
Feature activation+0.458
Top resid features:
leadership
Token leadership
Feature activation+0.025
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Nam
Token Nam
Feature activation+0.014
Top resid features:
uted
Tokenuted
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.082
Top resid features:
A
TokenA
Feature activation+0.025
Top resid features:
TV
Token TV
Feature activation+0.176
Top resid features:
screen
Token screen
Feature activation+0.422
Top resid features:
shows
Token shows
Feature activation+0.310
Top resid features:
a
Token a
Feature activation+0.251
Top resid features:
news
Token news
Feature activation+0.059
Top resid features:
report
Token report
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.128
Top resid features:
the
Token the
Feature activation+0.038
Top resid features:
apparent
Token apparent
Feature activation+0.021
Top resid features:
suicide
Token suicide
Feature activation+0.439
Top resid features:
bomb
Token bomb
Feature activation+0.692
Top resid features:
belt
Token belt
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
taken
Token taken
Feature activation+0.000
Top resid features:
away
Token away
Feature activation+0.000
Top resid features:
agency
Token agency
Feature activation+0.012
Top resid features:
said
Token said
Feature activation-0.041
Top resid features:
that
Token that
Feature activation-0.059
Top resid features:
publishing
Token publishing
Feature activation+0.049
Top resid features:
the
Token the
Feature activation+0.173
Top resid features:
cancer
Token cancer
Feature activation+0.773
Top resid features:
assessment
Token assessment
Feature activation+0.213
Top resid features:
review
Token review
Feature activation+0.030
Top resid features:
committee
Token committee
Feature activation-0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
agency
Token agency
Feature activation+0.009
Top resid features:
said
Token said
Feature activation-0.041
Top resid features:
that
Token that
Feature activation-0.077
Top resid features:
publishing
Token publishing
Feature activation+0.034
Top resid features:
the
Token the
Feature activation+0.088
Top resid features:
cancer
Token cancer
Feature activation+0.998
Top resid features:
assessment
Token assessment
Feature activation+0.148
Top resid features:
review
Token review
Feature activation-0.003
Top resid features:
committee
Token committee
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+0.011
Top resid features:
usp
Tokenusp
Feature activation+0.062
Top resid features:
ense
Tokenense
Feature activation+0.034
Top resid features:
.
Token.
Feature activation-0.057
Top resid features:
An
Token An
Feature activation+0.167
Top resid features:
alien
Token alien
Feature activation+0.616
Top resid features:
invasion
Token invasion
Feature activation+0.267
Top resid features:
story
Token story
Feature activation+0.051
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Start
Token Start
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
again
Token again
Feature activation-0.020
Top resid features:
.
Token.
Feature activation-0.035
Top resid features:
Yet
Token Yet
Feature activation-0.025
Top resid features:
the
Token the
Feature activation+0.213
Top resid features:
2017
Token 2017
Feature activation+0.024
Top resid features:
billionaires
Token billionaires
Feature activation+0.866
Top resid features:
report
Token report
Feature activation+0.076
Top resid features:
compiled
Token compiled
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Swiss
Token Swiss
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.087
Top resid features:
the
Token the
Feature activation+0.059
Top resid features:
public
Token public
Feature activation+0.050
Top resid features:
thought
Token thought
Feature activation+0.054
Top resid features:
that
Token that
Feature activation-0.136
Top resid features:
lunch
Token lunch
Feature activation+0.970
Top resid features:
counter
Token counter
Feature activation+0.066
Top resid features:
sit
Token sit
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
ins
Tokenins
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.115
Top resid features:
understand
Token understand
Feature activation+0.069
Top resid features:
why
Token why
Feature activation+0.047
Top resid features:
government
Token government
Feature activation+0.275
Top resid features:
bureaucr
Token bureaucr
Feature activation+0.340
Top resid features:
acies
Tokenacies
Feature activation+0.463
Top resid features:
do
Token do
Feature activation-0.066
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
things
Token things
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.015
Top resid features:
however
Token however
Feature activation-0.014
Top resid features:
,
Token,
Feature activation-0.041
Top resid features:
the
Token the
Feature activation+0.169
Top resid features:
Indian
Token Indian
Feature activation+0.171
Top resid features:
engineering
Token engineering
Feature activation+0.726
Top resid features:
group
Token group
Feature activation+0.065
Top resid features:
Pun
Token Pun
Feature activation+0.000
Top resid features:
ji
Tokenji
Feature activation+0.000
Top resid features:
Lloyd
Token Lloyd
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.083
Top resid features:
libertarian
Token libertarian
Feature activation+0.195
Top resid features:
arguments
Token arguments
Feature activation+0.141
Top resid features:
.
Token.
Feature activation-0.088
Top resid features:
What
Token What
Feature activation+0.038
Top resid features:
business
Token business
Feature activation+0.408
Top resid features:
does
Token does
Feature activation-0.066
Top resid features:
the
Token the
Feature activation+0.194
Top resid features:
government
Token government
Feature activation+0.299
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
making
Token making
Feature activation+0.000
Top resid features:
So
Token So
Feature activation-0.007
Top resid features:
costly
Token costly
Feature activation+0.086
Top resid features:
added
Token added
Feature activation+0.005
Top resid features:
extras
Token extras
Feature activation+0.287
Top resid features:
(
Token (
Feature activation+0.024
Top resid features:
music
Tokenmusic
Feature activation+0.655
Top resid features:
lessons
Token lessons
Feature activation+0.061
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
coaching
Token coaching
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
tut
Token tut
Feature activation+0.000
Top resid features:
rent
Token rent
Feature activation+0.214
Top resid features:
,
Token,
Feature activation-0.047
Top resid features:
utility
Token utility
Feature activation+0.127
Top resid features:
bills
Token bills
Feature activation+0.101
Top resid features:
,
Token,
Feature activation-0.214
Top resid features:
council
Token council
Feature activation+0.804
Top resid features:
tax
Token tax
Feature activation+0.096
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
mortgage
Token mortgage
Feature activation+0.000
Top resid features:
interest
Token interest
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
ters
Tokenters
Feature activation+0.001
Top resid features:
'
Token'
Feature activation-0.001
Top resid features:
aims
Token aims
Feature activation+0.019
Top resid features:
.
Token.
Feature activation-0.060
Top resid features:
The
Token The
Feature activation+0.135
Top resid features:
hotel
Token hotel
Feature activation+0.534
Top resid features:
and
Token and
Feature activation-0.198
Top resid features:
restaurant
Token restaurant
Feature activation+0.288
Top resid features:
industries
Token industries
Feature activation+0.213
Top resid features:
mirror
Token mirror
Feature activation+0.015
Top resid features:
state
Token state
Feature activation+0.000
Top resid features:
Cons
TokenCons
Feature activation+0.049
Top resid features:
cious
Tokencious
Feature activation+0.040
Top resid features:
ness
Tokenness
Feature activation+0.132
Top resid features:
is
Token is
Feature activation-0.173
Top resid features:
the
Token the
Feature activation+0.253
Top resid features:
breath
Token breath
Feature activation+0.791
Top resid features:
science
Token science
Feature activation+0.152
Top resid features:
must
Token must
Feature activation+0.000
Top resid features:
use
Token use
Feature activation+0.000
Top resid features:
if
Token if
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
held
Token held
Feature activation-0.010
Top resid features:
.
Token.
Feature activation-0.050
Top resid features:
Ċ
TokenĊ
Feature activation-0.053
Top resid features:
Ċ
TokenĊ
Feature activation-0.065
Top resid features:
The
TokenThe
Feature activation+0.165
Top resid features:
state
Token state
Feature activation+0.767
Top resid features:
constitution
Token constitution
Feature activation+0.153
Top resid features:
also
Token also
Feature activation+0.000
Top resid features:
provides
Token provides
Feature activation+0.000
Top resid features:
another
Token another
Feature activation+0.000
Top resid features:
route
Token route
Feature activation+0.000
Top resid features:
following
Token following
Feature activation-0.048
Top resid features:
:
Token:
Feature activation-0.045
Top resid features:
Ċ
TokenĊ
Feature activation-0.048
Top resid features:
Ċ
TokenĊ
Feature activation-0.067
Top resid features:
The
TokenThe
Feature activation+0.092
Top resid features:
powers
Token powers
Feature activation+0.908
Top resid features:
not
Token not
Feature activation+0.009
Top resid features:
delegated
Token delegated
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:
United
Token United
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.29

Head 1: 0.05

Head 2: 0.08

Head 3: 0.10

Head 4: 0.03

Head 5: 0.09

Head 6: 0.05

Head 7: 0.03

Head 8: 0.06

Head 9: 0.12

Head 10: 0.07

Head 11: 0.03

Positive logits

mole1.70

DH1.56

caster1.51

Stanton1.50

SS1.47

Stoke1.45

circa1.41

Fr1.39

slumped1.38

gel1.37

Dudley1.36

cat1.36

plant1.35

dr1.34

Sev1.33

aka1.33

Sor1.33

angler1.33

Norris1.31

GP1.31

Negative logits

conclud-2.31

yss-2.00

acknow-1.98

behavi-1.92

arrang-1.89

iblical-1.86

awa-1.85

ailable-1.84

fundament-1.84

xual-1.81

GGGGGGGG-1.80

notor-1.80

ydia-1.80

confir-1.78

agre-1.77

misunder-1.74

#$#$-1.72

astical-1.71

horizont-1.70

theless-1.70

INTERVAL 1.181 - 1.313
CONTAINS 0.000%

describe
Token describe
Feature activation+0.000
the
Token the
Feature activation+0.000
Conservative
Token Conservative
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
brain
Token brain
Feature activation+0.000
trust
Token trust
Feature activation+1.313
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
mid
Token mid
Feature activation+0.000
point
Tokenpoint
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.050 - 1.181
CONTAINS 0.000%

INTERVAL 0.919 - 1.050
CONTAINS 0.000%

better
Token better
Feature activation+0.000
construction
Token construction
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
opinion
Token opinion
Feature activation+0.000
noted
Token noted
Feature activation+0.975
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
word
Token word
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000

INTERVAL 0.788 - 0.919
CONTAINS 0.000%

A
TokenA
Feature activation+0.000
TV
Token TV
Feature activation+0.000
screen
Token screen
Feature activation+0.000
shows
Token shows
Feature activation+0.000
a
Token a
Feature activation+0.000
news
Token news
Feature activation+0.801
report
Token report
Feature activation+0.419
of
Token of
Feature activation+0.000
Edward
Token Edward
Feature activation+0.000
Snowden
Token Snowden
Feature activation+0.000
,
Token,
Feature activation+0.000
prime
Tokenprime
Feature activation+0.000
mortgages
Token mortgages
Feature activation+0.000
than
Token than
Feature activation+0.000
sub
Token sub
Feature activation+0.000
prime
Tokenprime
Feature activation+0.000
leadership
Token leadership
Feature activation+0.816
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Washington
TokenWashington
Feature activation+0.000
has
Token has
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
domestic
Token domestic
Feature activation+0.000
grain
Token grain
Feature activation+0.000
price
Token price
Feature activation+0.865
supports
Token supports
Feature activation+0.000
exceeded
Token exceeded
Feature activation+0.000
agreed
Token agreed
Feature activation+0.000
upon
Token upon
Feature activation+0.000
limits
Token limits
Feature activation+0.000

INTERVAL 0.656 - 0.788
CONTAINS 0.001%

that
Token that
Feature activation+0.000
publishing
Token publishing
Feature activation+0.000
the
Token the
Feature activation+0.000
cancer
Token cancer
Feature activation+0.000
assessment
Token assessment
Feature activation+0.327
review
Token review
Feature activation+0.728
committee
Token committee
Feature activation+0.746
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
report
Token report
Feature activation+0.000
,
Token,
Feature activation+0.000
utility
Token utility
Feature activation+0.000
bills
Token bills
Feature activation+0.000
,
Token,
Feature activation+0.000
council
Token council
Feature activation+0.000
tax
Token tax
Feature activation+0.663
and
Token and
Feature activation+0.000
mortgage
Token mortgage
Feature activation+0.000
interest
Token interest
Feature activation+0.000
-
Token -
Feature activation+0.000
subject
Token subject
Feature activation+0.000
publishing
Token publishing
Feature activation+0.000
the
Token the
Feature activation+0.000
cancer
Token cancer
Feature activation+0.000
assessment
Token assessment
Feature activation+0.327
review
Token review
Feature activation+0.728
committee
Token committee
Feature activation+0.746
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
report
Token report
Feature activation+0.000
was
Token was
Feature activation+0.000
understand
Token understand
Feature activation+0.000
why
Token why
Feature activation+0.000
government
Token government
Feature activation+0.000
bureaucr
Token bureaucr
Feature activation+0.000
acies
Tokenacies
Feature activation+0.027
do
Token do
Feature activation+0.680
some
Token some
Feature activation+0.336
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.036
things
Token things
Feature activation+0.000
they
Token they
Feature activation+0.000
the
Token the
Feature activation+0.000
public
Token public
Feature activation+0.000
thought
Token thought
Feature activation+0.000
that
Token that
Feature activation+0.000
lunch
Token lunch
Feature activation+0.000
counter
Token counter
Feature activation+0.691
sit
Token sit
Feature activation+0.000
-
Token-
Feature activation+0.000
ins
Tokenins
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000

INTERVAL 0.525 - 0.656
CONTAINS 0.003%

plans
Token plans
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
medical
Token medical
Feature activation+0.000
device
Token device
Feature activation+0.000
tax
Token tax
Feature activation+0.578
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
those
Token those
Feature activation+0.000
news
Token news
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
medieval
Token medieval
Feature activation+0.000
history
Token history
Feature activation+0.155
edition
Token edition
Feature activation+0.550
.
Token.
Feature activation+0.002
Everything
Token Everything
Feature activation+0.125
is
Token is
Feature activation+0.000
framed
Token framed
Feature activation+0.000
as
Token as
Feature activation+0.000
and
Token and
Feature activation+0.000
campaigning
Token campaigning
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
transit
Token transit
Feature activation+0.000
tax
Token tax
Feature activation+0.542
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
mayors
Token mayors
Feature activation+0.143
have
Token have
Feature activation+0.007
made
Token made
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
ones
Token ones
Feature activation+0.000
our
Token our
Feature activation+0.000
bodies
Token bodies
Feature activation+0.000
produce
Token produce
Feature activation+0.555
naturally
Token naturally
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
are
Tokenare
Feature activation+0.000
in
Token in
Feature activation+0.000
fact
Token fact
Feature activation+0.000
into
Token into
Feature activation+0.000
context
Token context
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
bedroom
Token bedroom
Feature activation+0.000
tax
Token tax
Feature activation+0.629
was
Token was
Feature activation+0.000
projected
Token projected
Feature activation+0.000
to
Token to
Feature activation+0.000
save
Token save
Feature activation+0.000
£
Token £
Feature activation+0.000

INTERVAL 0.394 - 0.525
CONTAINS 0.011%

,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
July
Token July
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
PlayStation
Token PlayStation
Feature activation+0.000
Store
Token Store
Feature activation+0.427
Flash
Token Flash
Feature activation+0.000
Sale
Token Sale
Feature activation+0.065
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
live
Token live
Feature activation+0.000
,
Token,
Feature activation+0.000
roads
Token roads
Feature activation+0.000
,
Token,
Feature activation+0.000
railways
Token railways
Feature activation+0.000
,
Token,
Feature activation+0.000
power
Token power
Feature activation+0.442
stations
Token stations
Feature activation+0.000
,
Token,
Feature activation+0.000
hospitals
Token hospitals
Feature activation+0.000
and
Token and
Feature activation+0.000
centres
Token centres
Feature activation+0.000
AFP
TokenAFP
Feature activation+0.000
),
Token),
Feature activation+0.000
the
Token the
Feature activation+0.000
Freedom
Token Freedom
Feature activation+0.000
Partners
Token Partners
Feature activation+0.000
Action
Token Action
Feature activation+0.489
Fund
Token Fund
Feature activation+0.000
,
Token,
Feature activation+0.000
Concern
Token Concern
Feature activation+0.000
ed
Tokened
Feature activation+0.000
Veterans
Token Veterans
Feature activation+0.000
was
Token was
Feature activation+0.000
clear
Token clear
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
guests
Token guests
Feature activation+0.000
how
Token how
Feature activation+0.415
aware
Token aware
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
was
Token was
Feature activation+0.000
dialogue
Token dialogue
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Hayes
Token Hayes
Feature activation+0.000
Production
Token Production
Feature activation+0.181
Code
Token Code
Feature activation+0.398
made
Token made
Feature activation+0.028
it
Token it
Feature activation+0.000
harder
Token harder
Feature activation+0.000
to
Token to
Feature activation+0.000
convey
Token convey
Feature activation+0.000

INTERVAL 0.263 - 0.394
CONTAINS 0.031%

called
Token called
Feature activation+0.000
the
Token the
Feature activation+0.000
Child
Token Child
Feature activation+0.000
Soldiers
Token Soldiers
Feature activation+0.000
Prevention
Token Prevention
Feature activation+0.201
Act
Token Act
Feature activation+0.319
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
C
Token C
Feature activation+0.000
SPA
TokenSPA
Feature activation+0.000
,
Token,
Feature activation+0.000
own
Token own
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
party
Token party
Feature activation+0.000
line
Token line
Feature activation+0.000
vote
Token vote
Feature activation+0.353
forced
Token forced
Feature activation+0.121
her
Token her
Feature activation+0.000
off
Token off
Feature activation+0.000
the
Token the
Feature activation+0.000
floor
Token floor
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
An
TokenAn
Feature activation+0.000
Insight
Token Insight
Feature activation+0.000
rix
Tokenrix
Feature activation+0.000
Research
Token Research
Feature activation+0.236
poll
Token poll
Feature activation+0.343
done
Token done
Feature activation+0.000
for
Token for
Feature activation+0.000
Global
Token Global
Feature activation+0.000
News
Token News
Feature activation+0.000
and
Token and
Feature activation+0.000
Metropolitan
Token Metropolitan
Feature activation+0.000
police
Token police
Feature activation+0.000
's
Token's
Feature activation+0.000
road
Token road
Feature activation+0.000
death
Token death
Feature activation+0.094
investigation
Token investigation
Feature activation+0.375
unit
Token unit
Feature activation+0.171
is
Token is
Feature activation+0.000
looking
Token looking
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Service
Token Service
Feature activation+0.000
once
Token once
Feature activation+0.000
the
Token the
Feature activation+0.000
federal
Token federal
Feature activation+0.000
conservation
Token conservation
Feature activation+0.000
funds
Token funds
Feature activation+0.302
become
Token become
Feature activation+0.000
available
Token available
Feature activation+0.000
again
Token again
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
something
Tokensomething
Feature activation+0.000

INTERVAL 0.131 - 0.263
CONTAINS 0.093%

New
Token New
Feature activation+0.000
Jersey
Token Jersey
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
state
Token state
Feature activation+0.000
legislature
Token legislature
Feature activation+0.181
legalized
Token legalized
Feature activation+0.000
cannabis
Token cannabis
Feature activation+0.000
to
Token to
Feature activation+0.000
treat
Token treat
Feature activation+0.000
certain
Token certain
Feature activation+0.000
's
Token's
Feature activation+0.000
bullshit
Token bullshit
Feature activation+0.000
:
Token:
Feature activation+0.000
Manufact
Token Manufact
Feature activation+0.000
urers
Tokenurers
Feature activation+0.000
don
Token don
Feature activation+0.191
't
Token't
Feature activation+0.000
tell
Token tell
Feature activation+0.000
you
Token you
Feature activation+0.000
this
Token this
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
problematic
Token problematic
Feature activation+0.000
relationship
Token relationship
Feature activation+0.055
between
Token between
Feature activation+0.190
correlation
Token correlation
Feature activation+0.000
and
Token and
Feature activation+0.000
causation
Token causation
Feature activation+0.000
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.000
mandates
Token mandates
Feature activation+0.000
that
Token that
Feature activation+0.000
schools
Token schools
Feature activation+0.006
receiving
Token receiving
Feature activation+0.246
federal
Token federal
Feature activation+0.337
funding
Token funding
Feature activation+0.243
must
Token must
Feature activation+0.000
'
Token '
Feature activation+0.000
t
Tokent
Feature activation+0.000
reat
Tokenreat
Feature activation+0.000
a
Token a
Feature activation+0.000
revenge
Token revenge
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
wife
Token wife
Feature activation+0.000
never
Token never
Feature activation+0.000
heard
Token heard
Feature activation+0.202
from
Token from
Feature activation+0.000
him
Token him
Feature activation+0.000
again
Token again
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.000 - 0.131
CONTAINS 99.860%

Junior
Token Junior
Feature activation+0.000
)
Token)
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
a
Token a
Feature activation+0.000
timeout
Token timeout
Feature activation+0.000
for
Token for
Feature activation+0.000
another
Token another
Feature activation+0.000
gig
Token gig
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Giants
Token Giants
Feature activation+0.000
will
Token will
Feature activation+0.000
release
Token release
Feature activation+0.000
running
Token running
Feature activation+0.000
back
Token back
Feature activation+0.000
Brandon
Token Brandon
Feature activation+0.000
Jacobs
Token Jacobs
Feature activation+0.000
today
Token today
Feature activation+0.000
after
Token after
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Now
TokenNow
Feature activation+0.000
Westbrook
Token Westbrook
Feature activation+0.000
is
Token is
Feature activation+0.000
30
Token 30
Feature activation+0.000
(
Token (
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
'll
Token'll
Feature activation+0.000
be
Token be
Feature activation+0.000
31
Token 31
Feature activation+0.000
before
Token before
Feature activation+0.000
lower
Token lower
Feature activation+0.000
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
recent
Token recent
Feature activation+0.000
history
Token history
Feature activation+0.000
suggests
Token suggests
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
on
Token on
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
bar
Token bar
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
Ded
Token Ded
Feature activation+0.000
ry
Tokenry
Feature activation+0.000
ck
Tokenck
Feature activation+0.000
Boy
Token Boy
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

,
Token,
Feature activation+0.000
a
Token a
Feature 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
Organisation
Token Organisation
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
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+0.245
<|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+0.245
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+0.245
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
committee
Token committee
Feature activation+0.245
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
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+0.245
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.245
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.245
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.245
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
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+0.245
headed
Token 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+0.245
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 9 in H2.0: (feature 23731)

TOP ACTIVATIONS
MAX = 1.756

These
Token These
Feature activation+0.000
women
Token women
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+1.756
welfare
Token welfare
Feature activation+0.000
queens
Token queens
Feature activation+0.128
as
Token as
Feature activation+0.860
mat
Token mat
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.182
a
Token a
Feature activation+0.489
story
Token story
Feature activation+1.358
for
Token for
Feature activation+0.749
the
Token the
Feature activation+0.370
fe
Token fe
Feature activation+0.145
int
Tokenint
Feature activation+0.000
of
Token of
Feature activation+0.035
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.345
hard
Token hard
Feature activation+1.343
to
Token to
Feature activation+0.431
see
Token see
Feature activation+0.026
why
Token why
Feature activation+0.000
the
Token the
Feature activation+0.000
copyright
Token copyright
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.085
case
Token case
Feature activation+1.330
of
Token of
Feature activation+0.533
a
Token a
Feature activation+0.269
stranger
Token stranger
Feature activation+0.610
hitting
Token hitting
Feature activation+0.070
someone
Token someone
Feature activation+0.000
"
Token"
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.054
fantastic
Token fantastic
Feature activation+1.260
compromise
Token compromise
Feature activation+0.000
deal
Token deal
Feature activation+0.220
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.188
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.003
a
Token a
Feature activation+0.162
nationally
Token nationally
Feature activation+0.710
representative
Token representative
Feature activation+0.504
sample
Token sample
Feature activation+1.243
,
Token,
Feature activation+0.778
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
results
Token results
Feature activation+0.000
provide
Token provide
Feature activation+0.000
only
Token only
Feature activation+0.000
been
Token been
Feature activation+0.000
delayed
Token delayed
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.011
aborted
Token aborted
Feature activation+1.232
.
Token.
Feature activation+0.194
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Several
TokenSeveral
Feature activation+0.057
days
Token days
Feature activation+0.000
as
Token as
Feature activation+0.000
my
Token my
Feature activation+0.000
writing
Token writing
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
pure
Token pure
Feature activation+1.225
tourism
Token tourism
Feature activation+0.115
propaganda
Token propaganda
Feature activation+0.311
,
Token,
Feature activation+0.691
rather
Token rather
Feature activation+0.799
,
Token,
Feature activation+0.194
of
Token of
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+1.162
because
Token because
Feature activation+0.000
some
Token some
Feature activation+0.185
white
Token white
Feature activation+0.000
feminists
Token feminists
Feature activation+0.000
urged
Token urged
Feature activation+0.000
project
Token project
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.444
necessary
Token necessary
Feature activation+1.115
that
Token that
Feature activation+0.263
you
Token you
Feature activation+0.564
can
Token can
Feature activation+0.712
only
Token only
Feature activation+0.034
add
Token add
Feature activation+0.000
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+0.000
his
Token his
Feature activation+0.183
place
Token place
Feature activation+0.393
"
Token "
Feature activation+0.494
to
Tokento
Feature activation+1.100
judge
Token judge
Feature activation+0.233
our
Token our
Feature activation+0.000
current
Token current
Feature activation+0.000
congressman
Token congressman
Feature activation+0.000
or
Token or
Feature activation+0.000
Pit
Token Pit
Feature activation+0.000
uka
Tokenuka
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.075
far
Token far
Feature activation+0.000
from
Token from
Feature activation+1.080
a
Token a
Feature activation+0.109
female
Token female
Feature activation+0.204
P
Token P
Feature activation+0.165
uch
Tokenuch
Feature activation+0.000
o
Tokeno
Feature activation+0.000
The
TokenThe
Feature activation+0.000
clock
Token clock
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.220
converted
Token converted
Feature activation+1.057
to
Token to
Feature activation+0.334
an
Token an
Feature activation+0.105
electric
Token electric
Feature activation+0.353
system
Token system
Feature activation+0.000
,
Token,
Feature activation+0.406
other
Token other
Feature activation+0.000
,
Token,
Feature activation+0.000
tragedy
Token tragedy
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
aver
Token aver
Feature activation+1.053
ted
Tokented
Feature activation+1.004
when
Token when
Feature activation+0.047
teenager
Token teenager
Feature activation+0.000
Louis
Token Louis
Feature activation+0.000
Low
Token Low
Feature activation+0.000
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+0.000
a
Token a
Feature activation+0.000
typical
Token typical
Feature activation+0.283
business
Token business
Feature activation+0.000
and
Token and
Feature activation+1.050
analysts
Token analysts
Feature activation+0.039
are
Token are
Feature activation+0.709
applaud
Token applaud
Feature activation+0.093
ing
Tokening
Feature activation+0.000
the
Token the
Feature activation+0.000
true
Token true
Feature activation+0.000
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.000
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
dismantled
Token dismantled
Feature activation+1.040
the
Token the
Feature activation+0.186
financial
Token financial
Feature activation+0.020
system
Token system
Feature activation+0.124
,
Token,
Feature activation+0.626
and
Token and
Feature activation+0.642
"
Token"
Feature activation+0.000
This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.106
a
Token a
Feature activation+0.270
victory
Token victory
Feature activation+1.029
yet
Token yet
Feature activation+0.023
,"
Token,"
Feature activation+0.084
she
Token she
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
marriage
Token marriage
Feature activation+0.272
.
Token.
Feature activation+0.335
He
Token He
Feature activation+0.194
was
Token was
Feature activation+0.108
not
Token not
Feature activation+0.293
ready
Token ready
Feature activation+1.024
to
Token to
Feature activation+0.560
marry
Token marry
Feature activation+0.358
that
Token that
Feature activation+0.099
girl
Token girl
Feature activation+0.030
.
Token.
Feature activation+0.166
Porter
Token Porter
Feature activation+0.000
Ranch
Token Ranch
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.002
far
Token far
Feature activation+0.000
from
Token from
Feature activation+1.022
the
Token the
Feature activation+0.000
shut
Token shut
Feature activation+0.244
tered
Tokentered
Feature activation+0.179
well
Token well
Feature activation+0.102
that
Token that
Feature activation+0.092
-
Token -
Feature activation+0.000
we
Token we
Feature activation+0.000
're
Token're
Feature activation+0.000
not
Token not
Feature activation+0.262
the
Token the
Feature activation+0.408
finished
Token finished
Feature activation+1.007
product
Token product
Feature activation+0.351
yet
Token yet
Feature activation+0.188
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Samp
Token Samp
Feature activation+0.000

Top DFA by src position
MAX = 2.241

right
Token right
Feature activation+0.031
Top resid features:
.
Token.
Feature activation+0.069
Top resid features:
These
Token These
Feature activation+0.039
Top resid features:
women
Token women
Feature activation+0.065
Top resid features:
are
Token are
Feature activation+0.092
Top resid features:
not
Token not
Feature activation+2.241
Top resid features:
so
Token so
Feature activation+0.088
Top resid features:
much
Token much
Feature activation+0.086
Top resid features:
welfare
Token welfare
Feature activation+0.000
Top resid features:
queens
Token queens
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.049
Top resid features:
trial
Token trial
Feature activation+0.046
Top resid features:
.
Token.
Feature activation+0.036
Top resid features:
This
Token This
Feature activation+0.024
Top resid features:
is
Token is
Feature activation+0.072
Top resid features:
not
Token not
Feature activation+1.818
Top resid features:
a
Token a
Feature activation+0.103
Top resid features:
story
Token story
Feature activation+0.142
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
fe
Token fe
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.029
Top resid features:
Ċ
TokenĊ
Feature activation+0.059
Top resid features:
Ċ
TokenĊ
Feature activation+0.064
Top resid features:
It
TokenIt
Feature activation-0.002
Top resid features:
is
Token is
Feature activation+0.077
Top resid features:
not
Token not
Feature activation+1.831
Top resid features:
hard
Token hard
Feature activation+0.155
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
see
Token see
Feature activation+0.000
Top resid features:
why
Token why
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
âĢ
TokenâĢ
Feature activation+0.012
Top resid features:
ľ
Tokenľ
Feature activation+0.026
Top resid features:
This
TokenThis
Feature activation-0.004
Top resid features:
is
Token is
Feature activation+0.060
Top resid features:
not
Token not
Feature activation+1.867
Top resid features:
a
Token a
Feature activation+0.093
Top resid features:
case
Token case
Feature activation+0.164
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
stranger
Token stranger
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.040
Top resid features:
Ċ
TokenĊ
Feature activation+0.046
Top resid features:
"
Token"
Feature activation+0.045
Top resid features:
It
TokenIt
Feature activation-0.036
Top resid features:
is
Token is
Feature activation+0.033
Top resid features:
not
Token not
Feature activation+1.959
Top resid features:
a
Token a
Feature activation+0.126
Top resid features:
fantastic
Token fantastic
Feature activation+0.081
Top resid features:
compromise
Token compromise
Feature activation+0.000
Top resid features:
deal
Token deal
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
email
Token email
Feature activation+0.037
Top resid features:
list
Token list
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
which
Token which
Feature activation+0.083
Top resid features:
is
Token is
Feature activation+0.071
Top resid features:
not
Token not
Feature activation+1.613
Top resid features:
a
Token a
Feature activation+0.110
Top resid features:
nationally
Token nationally
Feature activation+0.022
Top resid features:
representative
Token representative
Feature activation+0.074
Top resid features:
sample
Token sample
Feature activation+0.060
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.038
Top resid features:
only
Token only
Feature activation+0.086
Top resid features:
been
Token been
Feature activation+0.053
Top resid features:
delayed
Token delayed
Feature activation+0.070
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
not
Token not
Feature activation+1.783
Top resid features:
aborted
Token aborted
Feature activation+0.072
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:
Several
TokenSeveral
Feature activation+0.000
Top resid features:
surprised
Token surprised
Feature activation+0.113
Top resid features:
as
Token as
Feature activation+0.061
Top resid features:
my
Token my
Feature activation+0.065
Top resid features:
writing
Token writing
Feature activation+0.054
Top resid features:
is
Token is
Feature activation+0.050
Top resid features:
not
Token not
Feature activation+1.656
Top resid features:
pure
Token pure
Feature activation+0.091
Top resid features:
tourism
Token tourism
Feature activation+0.000
Top resid features:
propaganda
Token propaganda
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
rather
Token rather
Feature activation+0.000
Top resid features:
last
Token last
Feature activation+0.004
Top resid features:
couple
Token couple
Feature activation+0.029
Top resid features:
of
Token of
Feature activation+0.038
Top resid features:
years
Token years
Feature activation+0.034
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
not
Token not
Feature activation+1.899
Top resid features:
so
Token so
Feature activation+0.032
Top resid features:
much
Token much
Feature activation+0.030
Top resid features:
because
Token because
Feature activation+0.000
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
white
Token white
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.029
Top resid features:
project
Token project
Feature activation+0.038
Top resid features:
.
Token.
Feature activation+0.068
Top resid features:
It
Token It
Feature activation+0.018
Top resid features:
is
Token is
Feature activation+0.038
Top resid features:
not
Token not
Feature activation+1.598
Top resid features:
necessary
Token necessary
Feature activation+0.113
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
seat
Token seat
Feature activation+0.027
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
said
Token said
Feature activation+0.018
Top resid features:
it
Token it
Feature activation+0.063
Top resid features:
isn
Token isn
Feature activation+0.148
Top resid features:
't
Token't
Feature activation+1.320
Top resid features:
his
Token his
Feature activation+0.137
Top resid features:
place
Token place
Feature activation+0.097
Top resid features:
"
Token "
Feature activation+0.067
Top resid features:
to
Tokento
Feature activation+0.116
Top resid features:
judge
Token judge
Feature activation+0.000
Top resid features:
uka
Tokenuka
Feature activation+0.022
Top resid features:
:
Token:
Feature activation+0.052
Top resid features:
Pit
Token Pit
Feature activation+0.053
Top resid features:
uka
Tokenuka
Feature activation+0.048
Top resid features:
is
Token is
Feature activation+0.077
Top resid features:
not
Token not
Feature activation+1.608
Top resid features:
far
Token far
Feature activation-0.088
Top resid features:
from
Token from
Feature activation+0.212
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
female
Token female
Feature activation+0.000
Top resid features:
P
Token P
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.046
Top resid features:
Ċ
TokenĊ
Feature activation+0.053
Top resid features:
The
TokenThe
Feature activation+0.050
Top resid features:
clock
Token clock
Feature activation+0.067
Top resid features:
has
Token has
Feature activation+0.036
Top resid features:
not
Token not
Feature activation+1.583
Top resid features:
been
Token been
Feature activation-0.039
Top resid features:
converted
Token converted
Feature activation+0.160
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
electric
Token electric
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.050
Top resid features:
other
Token other
Feature activation+0.027
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
tragedy
Token tragedy
Feature activation+0.048
Top resid features:
was
Token was
Feature activation+0.011
Top resid features:
not
Token not
Feature activation+1.651
Top resid features:
aver
Token aver
Feature activation+0.050
Top resid features:
ted
Tokented
Feature activation+0.000
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
teenager
Token teenager
Feature activation+0.000
Top resid features:
Louis
Token Louis
Feature activation+0.000
Top resid features:
recent
Token recent
Feature activation+0.012
Top resid features:
history
Token history
Feature activation+0.038
Top resid features:
suggests
Token suggests
Feature activation+0.043
Top resid features:
,
Token,
Feature activation+0.053
Top resid features:
isn
Token isn
Feature activation+0.140
Top resid features:
't
Token't
Feature activation+1.276
Top resid features:
a
Token a
Feature activation+0.105
Top resid features:
typical
Token typical
Feature activation+0.099
Top resid features:
business
Token business
Feature activation+0.165
Top resid features:
and
Token and
Feature activation+0.082
Top resid features:
analysts
Token analysts
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.056
Top resid features:
true
Token true
Feature activation+0.085
Top resid features:
that
Token that
Feature activation+0.126
Top resid features:
we
Token we
Feature activation+0.055
Top resid features:
have
Token have
Feature activation+0.021
Top resid features:
not
Token not
Feature activation+1.434
Top resid features:
dismantled
Token dismantled
Feature activation+0.109
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
financial
Token financial
Feature activation+0.000
Top resid features:
system
Token system
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.044
Top resid features:
Ċ
TokenĊ
Feature activation+0.043
Top resid features:
"
Token"
Feature activation+0.064
Top resid features:
This
TokenThis
Feature activation+0.042
Top resid features:
is
Token is
Feature activation+0.095
Top resid features:
not
Token not
Feature activation+1.439
Top resid features:
a
Token a
Feature activation+0.134
Top resid features:
victory
Token victory
Feature activation+0.153
Top resid features:
yet
Token yet
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:
the
Token the
Feature activation+0.045
Top resid features:
marriage
Token marriage
Feature activation+0.066
Top resid features:
.
Token.
Feature activation+0.043
Top resid features:
He
Token He
Feature activation+0.085
Top resid features:
was
Token was
Feature activation+0.015
Top resid features:
not
Token not
Feature activation+1.291
Top resid features:
ready
Token ready
Feature activation+0.147
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
marry
Token marry
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
girl
Token girl
Feature activation+0.000
Top resid features:
Saturday
Token Saturday
Feature activation+0.037
Top resid features:
near
Token near
Feature activation+0.091
Top resid features:
Porter
Token Porter
Feature activation+0.023
Top resid features:
Ranch
Token Ranch
Feature activation+0.028
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
not
Token not
Feature activation+1.633
Top resid features:
far
Token far
Feature activation-0.121
Top resid features:
from
Token from
Feature activation+0.176
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
shut
Token shut
Feature activation+0.000
Top resid features:
tered
Tokentered
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.047
Top resid features:
progress
Token progress
Feature activation+0.051
Top resid features:
-
Token -
Feature activation+0.050
Top resid features:
we
Token we
Feature activation+0.049
Top resid features:
're
Token're
Feature activation+0.054
Top resid features:
not
Token not
Feature activation+1.305
Top resid features:
the
Token the
Feature activation+0.166
Top resid features:
finished
Token finished
Feature activation+0.078
Top resid features:
product
Token product
Feature activation+0.000
Top resid features:
yet
Token yet
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.28

Head 1: 0.03

Head 2: 0.06

Head 3: 0.07

Head 4: 0.05

Head 5: 0.06

Head 6: 0.04

Head 7: 0.07

Head 8: 0.08

Head 9: 0.05

Head 10: 0.14

Head 11: 0.07

Positive logits

nor3.16

anymore3.09

yet2.37

necessarily2.07

whatsoever2.01

nor1.97

yet1.84

anything1.81

slightest1.79

any1.72

anybody1.70

anywhere1.69

unless1.66

unless1.59

Nor1.55

anyone1.48

Yet1.48

altogether1.43

anytime1.43

EVER1.40

Negative logits

soDeliveryDate-1.54

redes-1.50

assorted-1.27

atari-1.25

elig-1.18

unforgettable-1.15

hilar-1.14

LAN-1.05

accompanied-1.05

eleph-1.04

-1.03

legged-1.03

Booster-0.99

newcom-0.98

iland-0.98

oided-0.97

asionally-0.97

brace-0.96

periodically-0.96

brainstorm-0.96

INTERVAL 1.580 - 1.756
CONTAINS 0.000%

These
Token These
Feature activation+0.000
women
Token women
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+1.756
welfare
Token welfare
Feature activation+0.000
queens
Token queens
Feature activation+0.128
as
Token as
Feature activation+0.860
mat
Token mat
Feature activation+0.000
ri
Tokenri
Feature activation+0.000

INTERVAL 1.405 - 1.580
CONTAINS 0.000%

INTERVAL 1.229 - 1.405
CONTAINS 0.001%

"
Token"
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.054
fantastic
Token fantastic
Feature activation+1.260
compromise
Token compromise
Feature activation+0.000
deal
Token deal
Feature activation+0.220
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.188
ľ
Tokenľ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.085
case
Token case
Feature activation+1.330
of
Token of
Feature activation+0.533
a
Token a
Feature activation+0.269
stranger
Token stranger
Feature activation+0.610
hitting
Token hitting
Feature activation+0.070
someone
Token someone
Feature activation+0.000
only
Token only
Feature activation+0.000
been
Token been
Feature activation+0.000
delayed
Token delayed
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.011
aborted
Token aborted
Feature activation+1.232
.
Token.
Feature activation+0.194
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Several
TokenSeveral
Feature activation+0.057
days
Token days
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.182
a
Token a
Feature activation+0.489
story
Token story
Feature activation+1.358
for
Token for
Feature activation+0.749
the
Token the
Feature activation+0.370
fe
Token fe
Feature activation+0.145
int
Tokenint
Feature activation+0.000
of
Token of
Feature activation+0.035
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.345
hard
Token hard
Feature activation+1.343
to
Token to
Feature activation+0.431
see
Token see
Feature activation+0.026
why
Token why
Feature activation+0.000
the
Token the
Feature activation+0.000
copyright
Token copyright
Feature activation+0.000

INTERVAL 1.053 - 1.229
CONTAINS 0.001%

The
TokenThe
Feature activation+0.000
clock
Token clock
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.000
been
Token been
Feature activation+0.220
converted
Token converted
Feature activation+1.057
to
Token to
Feature activation+0.334
an
Token an
Feature activation+0.105
electric
Token electric
Feature activation+0.353
system
Token system
Feature activation+0.000
,
Token,
Feature activation+0.406
as
Token as
Feature activation+0.000
my
Token my
Feature activation+0.000
writing
Token writing
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
pure
Token pure
Feature activation+1.225
tourism
Token tourism
Feature activation+0.115
propaganda
Token propaganda
Feature activation+0.311
,
Token,
Feature activation+0.691
rather
Token rather
Feature activation+0.799
,
Token,
Feature activation+0.194
isn
Token isn
Feature activation+0.000
't
Token't
Feature activation+0.000
his
Token his
Feature activation+0.183
place
Token place
Feature activation+0.393
"
Token "
Feature activation+0.494
to
Tokento
Feature activation+1.100
judge
Token judge
Feature activation+0.233
our
Token our
Feature activation+0.000
current
Token current
Feature activation+0.000
congressman
Token congressman
Feature activation+0.000
or
Token or
Feature activation+0.000
of
Token of
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+1.162
because
Token because
Feature activation+0.000
some
Token some
Feature activation+0.185
white
Token white
Feature activation+0.000
feminists
Token feminists
Feature activation+0.000
urged
Token urged
Feature activation+0.000
project
Token project
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.444
necessary
Token necessary
Feature activation+1.115
that
Token that
Feature activation+0.263
you
Token you
Feature activation+0.564
can
Token can
Feature activation+0.712
only
Token only
Feature activation+0.034
add
Token add
Feature activation+0.000

INTERVAL 0.878 - 1.053
CONTAINS 0.002%

ours
Token ours
Feature activation+0.000
would
Token would
Feature activation+0.000
not
Token not
Feature activation+0.000
have
Token have
Feature activation+0.404
the
Token the
Feature activation+0.172
optional
Token optional
Feature activation+0.937
frame
Token frame
Feature activation+0.120
mounted
Token mounted
Feature activation+0.281
safety
Token safety
Feature activation+0.073
.
Token.
Feature activation+0.228
Personal
Token Personal
Feature activation+0.000
other
Token other
Feature activation+0.000
,
Token,
Feature activation+0.000
tragedy
Token tragedy
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
aver
Token aver
Feature activation+1.053
ted
Tokented
Feature activation+1.004
when
Token when
Feature activation+0.047
teenager
Token teenager
Feature activation+0.000
Louis
Token Louis
Feature activation+0.000
Low
Token Low
Feature activation+0.000
outcome
Token outcome
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.084
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.212
matter
Token matter
Feature activation+0.964
of
Token of
Feature activation+0.494
family
Token family
Feature activation+0.042
politics
Token politics
Feature activation+0.144
;
Token;
Feature activation+0.450
the
Token the
Feature activation+0.000
that
Token that
Feature activation+0.000
end
Token end
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
an
Token an
Feature activation+0.124
end
Token end
Feature activation+0.987
in
Token in
Feature activation+0.228
itself
Token itself
Feature activation+0.157
.
Token.
Feature activation+0.279
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
tragedy
Token tragedy
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
aver
Token aver
Feature activation+1.053
ted
Tokented
Feature activation+1.004
when
Token when
Feature activation+0.047
teenager
Token teenager
Feature activation+0.000
Louis
Token Louis
Feature activation+0.000
Low
Token Low
Feature activation+0.000
enthal
Tokenenthal
Feature activation+0.000

INTERVAL 0.702 - 0.878
CONTAINS 0.009%

,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
not
Token not
Feature activation+0.173
their
Token their
Feature activation+0.461
territory
Token territory
Feature activation+0.751
under
Token under
Feature activation+0.675
international
Token international
Feature activation+0.000
law
Token law
Feature activation+0.053
.
Token.
Feature activation+0.095
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
footsteps
Token footsteps
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.077
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.712
the
Token the
Feature activation+0.266
body
Token body
Feature activation+0.293
,
Token,
Feature activation+0.656
and
Token and
Feature activation+0.749
are
Token are
Feature activation+0.420
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
one
Token one
Feature activation+0.383
of
Token of
Feature activation+0.725
them
Token them
Feature activation+0.419
.
Token.
Feature activation+0.257
He
Token He
Feature activation+0.142
moved
Token moved
Feature activation+0.061
to
Token to
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.408
perk
Token perk
Feature activation+0.449
that
Token that
Feature activation+0.670
most
Token most
Feature activation+0.779
Spons
Token Spons
Feature activation+0.000
ors
Tokenors
Feature activation+0.069
wanted
Token wanted
Feature activation+0.248
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
team
Token team
Feature activation+0.000
has
Token has
Feature activation+0.000
not
Token not
Feature activation+0.040
had
Token had
Feature activation+0.130
the
Token the
Feature activation+0.214
kind
Token kind
Feature activation+0.767
of
Token of
Feature activation+0.673
results
Token results
Feature activation+0.321
that
Token that
Feature activation+0.156
I
Token I
Feature activation+0.122
believe
Token believe
Feature activation+0.061

INTERVAL 0.527 - 0.702
CONTAINS 0.021%

not
Token not
Feature activation+0.286
surprising
Token surprising
Feature activation+0.000
that
Token that
Feature activation+0.130
the
Token the
Feature activation+0.017
bill
Token bill
Feature activation+0.173
then
Token then
Feature activation+0.569
moved
Token moved
Feature activation+0.112
to
Token to
Feature activation+0.000
ALEC
Token ALEC
Feature activation+0.000
and
Token and
Feature activation+0.000
became
Token became
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
have
Token have
Feature activation+0.143
acc
Token acc
Feature activation+0.000
reditation
Tokenreditation
Feature activation+0.000
from
Token from
Feature activation+0.560
an
Token an
Feature activation+0.000
acc
Token acc
Feature activation+0.000
red
Tokenred
Feature activation+0.000
itor
Tokenitor
Feature activation+0.000
recognized
Token recognized
Feature activation+0.150
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.026
unemployed
Token unemployed
Feature activation+0.594
.
Token.
Feature activation+0.151
It
Token It
Feature activation+0.089
is
Token is
Feature activation+0.423
only
Token only
Feature activation+0.218
once
Token once
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
trying
Token trying
Feature activation+0.415
to
Token to
Feature activation+0.589
be
Token be
Feature activation+0.222
traditional
Token traditional
Feature activation+0.000
in
Token in
Feature activation+0.000
any
Token any
Feature activation+0.000
sense
Token sense
Feature activation+0.000
much
Token much
Feature activation+0.000
of
Token of
Feature activation+0.230
an
Token an
Feature activation+0.098
argument
Token argument
Feature activation+0.433
,
Token,
Feature activation+0.559
either
Token either
Feature activation+0.532
.
Token.
Feature activation+0.096
The
Token The
Feature activation+0.000
majority
Token majority
Feature activation+0.000
of
Token of
Feature activation+0.000
Germans
Token Germans
Feature activation+0.000

INTERVAL 0.351 - 0.527
CONTAINS 0.062%

secretly
Token secretly
Feature activation+0.335
funding
Token funding
Feature activation+0.000
any
Token any
Feature activation+0.000
terrorist
Token terrorist
Feature activation+0.000
organizations
Token organizations
Feature activation+0.000
and
Token and
Feature activation+0.497
I
Token I
Feature activation+0.272
'm
Token'm
Feature activation+0.176
fairly
Token fairly
Feature activation+0.337
certain
Token certain
Feature activation+0.000
the
Token the
Feature activation+0.000
comment
Token comment
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.053
not
Token not
Feature activation+0.208
clear
Token clear
Feature activation+0.458
from
Token from
Feature activation+0.671
online
Token online
Feature activation+0.113
court
Token court
Feature activation+0.261
records
Token records
Feature activation+0.205
whether
Token whether
Feature activation+0.203
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
mean
Token mean
Feature activation+0.192
we
Token we
Feature activation+0.105
are
Token are
Feature activation+0.706
a
Token a
Feature activation+0.522
defensive
Token defensive
Feature activation+0.210
team
Token team
Feature activation+0.430
,
Token,
Feature activation+0.642
âĢ
TokenâĢ
Feature activation+0.097
Ŀ
TokenĿ
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
one
Token one
Feature activation+0.383
of
Token of
Feature activation+0.725
them
Token them
Feature activation+0.419
.
Token.
Feature activation+0.257
He
Token He
Feature activation+0.142
moved
Token moved
Feature activation+0.061
not
Token not
Feature activation+0.276
clear
Token clear
Feature activation+0.418
from
Token from
Feature activation+0.652
our
Token our
Feature activation+0.000
results
Token results
Feature activation+0.217
whether
Token whether
Feature activation+0.494
the
Token the
Feature activation+0.000
cle
Token cle
Feature activation+0.000
avage
Tokenavage
Feature activation+0.000
happened
Token happened
Feature activation+0.000
immediately
Token immediately
Feature activation+0.000

INTERVAL 0.176 - 0.351
CONTAINS 0.149%

will
Token will
Feature activation+0.000
not
Token not
Feature activation+0.002
be
Token be
Feature activation+0.544
thinking
Token thinking
Feature activation+0.530
âĢ
Token âĢ
Feature activation+0.253
ľ
Tokenľ
Feature activation+0.183
aa
Tokenaa
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
gh
Tokengh
Feature activation+0.000
hex
Token hex
Feature activation+0.000
es
Tokenes
Feature activation+0.000
executives
Token executives
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
would
Token would
Feature activation+0.000
not
Token not
Feature activation+0.000
commit
Token commit
Feature activation+0.327
to
Token to
Feature activation+0.016
abol
Token abol
Feature activation+0.128
ishing
Tokenishing
Feature activation+0.025
trans
Token trans
Feature activation+0.000
ph
Tokenph
Feature activation+0.000
it
Token it
Feature activation+0.000
would
Token would
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.599
appropriate
Token appropriate
Feature activation+0.631
to
Token to
Feature activation+0.341
extend
Token extend
Feature activation+0.001
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
to
Token to
Feature activation+0.000
refuse
Token refuse
Feature activation+0.000
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
only
Token only
Feature activation+0.000
been
Token been
Feature activation+0.000
cheap
Token cheap
Feature activation+0.107
,
Token,
Feature activation+0.222
but
Token but
Feature activation+0.000
have
Token have
Feature activation+0.000
had
Token had
Feature activation+0.000
service
Token service
Feature activation+0.000
time
Token time
Feature activation+0.000
nor
Token nor
Feature activation+0.000
are
Token are
Feature activation+0.000
they
Token they
Feature activation+0.197
"
Token "
Feature activation+0.445
Nazis
TokenNazis
Feature activation+0.293
and
Token and
Feature activation+0.247
US
Token US
Feature activation+0.000
pupp
Token pupp
Feature activation+0.002
ets
Tokenets
Feature activation+0.120
"
Token"
Feature activation+0.106
Ċ
TokenĊ
Feature activation+0.094

INTERVAL 0.000 - 0.176
CONTAINS 99.756%

Already
Token Already
Feature activation+0.000
,
Token,
Feature activation+0.000
hundreds
Token hundreds
Feature activation+0.000
of
Token of
Feature activation+0.000
candidates
Token candidates
Feature activation+0.000
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
of
Token of
Feature activation+0.000
whom
Token whom
Feature activation+0.000
are
Token are
Feature activation+0.000
brand
Token brand
Feature activation+0.000
start
Token start
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
presidency
Token presidency
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
ve
Token ve
Feature activation+0.000
hem
Tokenhem
Feature activation+0.000
ence
Tokenence
Feature activation+0.000
with
Token with
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
four
Token four
Feature activation+0.000
postponed
Token postponed
Feature activation+0.000
concerts
Token concerts
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
valid
Token valid
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
make
Token make
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
on
Token on
Feature activation+0.000
CNN
Token CNN
Feature activation+0.000
's
Token's
Feature activation+0.000
"
Token "
Feature activation+0.000
State
TokenState
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Union
Token Union
Feature activation+0.000
"
Token"
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
for
Token for
Feature activation+0.000
release
Token release
Feature activation+0.000
in
Token in
Feature activation+0.000
late
Token late
Feature activation+0.000
June
Token June
Feature activation+0.000
/
Token/
Feature activation+0.000
early
Tokenearly
Feature activation+0.000
July
Token July
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
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