H3.5 top features

Top feature 0 in H3.5: (feature 14930)

TOP ACTIVATIONS
MAX = 5.645

block
Token block
Feature activation+0.000
is
Token is
Feature activation+0.000
made
Token made
Feature activation+0.000
from
Token from
Feature activation+0.550
a
Token a
Feature activation+2.276
different
Token different
Feature activation+5.645
substance
Token substance
Feature activation+0.900
,
Token,
Feature activation+0.582
and
Token and
Feature activation+0.538
they
Token they
Feature activation+0.619
all
Token all
Feature activation+0.434
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
methods
Token methods
Feature activation+0.000
has
Token has
Feature activation+0.071
its
Token its
Feature activation+3.594
own
Token own
Feature activation+5.361
advantages
Token advantages
Feature activation+1.332
and
Token and
Feature activation+0.486
disadvantages
Token disadvantages
Feature activation+0.491
,
Token,
Feature activation+0.123
and
Token and
Feature activation+0.080
the
Token the
Feature activation+0.137
releases
Token releases
Feature activation+0.000
will
Token will
Feature activation+0.186
get
Token get
Feature activation+0.393
its
Token its
Feature activation+3.287
own
Token own
Feature activation+4.032
name
Token name
Feature activation+1.168
from
Token from
Feature activation+0.759
a
Token a
Feature activation+1.929
list
Token list
Feature activation+0.982
of
Token of
Feature activation+0.355
being
Token being
Feature activation+0.000
more
Token more
Feature activation+0.000
elaborate
Token elaborate
Feature activation+0.319
than
Token than
Feature activation+0.393
the
Token the
Feature activation+0.679
last
Token last
Feature activation+3.649
.
Token.
Feature activation+0.060
We
Token We
Feature activation+0.144
were
Token were
Feature activation+0.000
even
Token even
Feature activation+0.000
featured
Token featured
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.141
check
Token check
Feature activation+0.634
out
Token out
Feature activation+0.233
a
Token a
Feature activation+2.259
number
Token number
Feature activation+3.613
of
Token of
Feature activation+0.626
Internet
Token Internet
Feature activation+0.153
news
Token news
Feature activation+0.000
reports
Token reports
Feature activation+0.357
and
Token and
Feature activation+0.300
(
Token (
Feature activation+0.000
each
Tokeneach
Feature activation+0.000
town
Token town
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+1.068
separate
Token separate
Feature activation+3.601
region
Token region
Feature activation+0.527
as
Token as
Feature activation+0.331
are
Token are
Feature activation+0.058
areas
Token areas
Feature activation+0.030
such
Token such
Feature activation+0.180
Each
TokenEach
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
methods
Token methods
Feature activation+0.000
has
Token has
Feature activation+0.071
its
Token its
Feature activation+3.594
own
Token own
Feature activation+5.361
advantages
Token advantages
Feature activation+1.332
and
Token and
Feature activation+0.486
disadvantages
Token disadvantages
Feature activation+0.491
,
Token,
Feature activation+0.123
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.137
releases
Token releases
Feature activation+0.000
will
Token will
Feature activation+0.186
get
Token get
Feature activation+0.393
its
Token its
Feature activation+3.287
own
Token own
Feature activation+4.032
name
Token name
Feature activation+1.168
from
Token from
Feature activation+0.759
a
Token a
Feature activation+1.929
list
Token list
Feature activation+0.982
and
Token and
Feature activation+0.000
each
Token each
Feature activation+0.000
har
Token har
Feature activation+0.000
bors
Tokenbors
Feature activation+0.085
its
Token its
Feature activation+2.068
own
Token own
Feature activation+3.103
ambitions
Token ambitions
Feature activation+0.096
and
Token and
Feature activation+0.212
grievances
Token grievances
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
size
Token size
Feature activation+0.000
requires
Token requires
Feature activation+0.000
a
Token a
Feature activation+0.595
different
Token different
Feature activation+3.099
size
Token size
Feature activation+0.000
sole
Token sole
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
used
Token used
Feature activation+0.000
come
Token come
Feature activation+0.000
about
Token about
Feature activation+0.000
because
Token because
Feature activation+0.000
each
Token each
Feature activation+0.000
expected
Token expected
Feature activation+0.000
different
Token different
Feature activation+3.079
things
Token things
Feature activation+0.067
from
Token from
Feature activation+0.007
it
Token it
Feature activation+0.853
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.003
to
Token to
Feature activation+0.211
be
Token be
Feature activation+0.011
stored
Token stored
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+2.929
own
Token own
Feature activation+3.024
server
Token server
Feature activation+0.018
,
Token,
Feature activation+0.123
but
Token but
Feature activation+0.637
Imran
Token Imran
Feature activation+0.000
moved
Token moved
Feature activation+0.008
condition
Token condition
Feature activation+0.000
exists
Token exists
Feature activation+0.000
exclusive
Token exclusive
Feature activation+1.353
of
Token of
Feature activation+0.002
the
Token the
Feature activation+0.615
other
Token other
Feature activation+2.999
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sexual
TokenSexual
Feature activation+0.000
and
Token and
Feature activation+0.000
supposed
Token supposed
Feature activation+0.308
to
Token to
Feature activation+0.211
be
Token be
Feature activation+0.011
stored
Token stored
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+2.929
own
Token own
Feature activation+3.024
server
Token server
Feature activation+0.018
,
Token,
Feature activation+0.123
but
Token but
Feature activation+0.637
Imran
Token Imran
Feature activation+0.000
bags
Token bags
Feature activation+0.000
.
Token.
Feature activation+0.000
Each
Token Each
Feature activation+0.000
trial
Token trial
Feature activation+0.000
rewards
Token rewards
Feature activation+0.000
different
Token different
Feature activation+2.804
parts
Token parts
Feature activation+0.525
:
Token:
Feature activation+0.348
Ċ
TokenĊ
Feature activation+0.322
Ċ
TokenĊ
Feature activation+0.262
AA
TokenAA
Feature activation+0.000
Met
Token Met
Feature activation+0.163
el
Tokenel
Feature activation+0.000
ka
Tokenka
Feature activation+0.000
suggested
Token suggested
Feature activation+0.191
a
Token a
Feature activation+1.782
new
Token new
Feature activation+2.796
sport
Token sport
Feature activation+0.589
,
Token,
Feature activation+0.149
the
Token the
Feature activation+0.254
team
Token team
Feature activation+0.000
designed
Token designed
Feature activation+0.000
s
Tokens
Feature activation+0.443
legs
Token legs
Feature activation+0.525
arrives
Token arrives
Feature activation+0.251
with
Token with
Feature activation+1.062
a
Token a
Feature activation+2.408
particular
Token particular
Feature activation+2.572
design
Token design
Feature activation+0.144
challenge
Token challenge
Feature activation+0.949
.
Token.
Feature activation+0.657
Weight
Token Weight
Feature activation+0.000
,
Token,
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
).
Token).
Feature activation+0.000
Each
Token Each
Feature activation+0.000
biome
Token biome
Feature activation+0.000
contains
Token contains
Feature activation+0.329
a
Token a
Feature activation+2.513
fully
Token fully
Feature activation+2.134
functional
Token functional
Feature activation+1.073
society
Token society
Feature activation+0.771
making
Token making
Feature activation+0.181
up
Token up
Feature activation+0.000
,
Token,
Feature activation+0.000
each
Token each
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.034
vastly
Token vastly
Feature activation+0.180
different
Token different
Feature activation+2.504
style
Token style
Feature activation+0.179
âĢĶ
TokenâĢĶ
Feature activation+0.027
she
Tokenshe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
the
Token the
Feature activation+0.000
Torah
Token Torah
Feature activation+0.000
is
Token is
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+1.174
same
Token same
Feature activation+2.503
length
Token length
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 5.985

on
Token on
Feature activation+0.001
Top resid features:
some
Token some
Feature activation+0.005
Top resid features:
virtual
Token virtual
Feature activation+0.004
Top resid features:
blocks
Token blocks
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.036
Top resid features:
Each
Token Each
Feature activation+5.985
Top resid features:
block
Token block
Feature activation+0.015
Top resid features:
is
Token is
Feature activation+0.026
Top resid features:
made
Token made
Feature activation+0.036
Top resid features:
from
Token from
Feature activation+0.006
Top resid features:
a
Token a
Feature activation+0.101
Top resid features:
network
Token network
Feature activation+0.002
Top resid features:
users
Token users
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Each
TokenEach
Feature activation+5.645
Top resid features:
of
Token of
Feature activation+0.016
Top resid features:
these
Token these
Feature activation+0.018
Top resid features:
methods
Token methods
Feature activation+0.019
Top resid features:
has
Token has
Feature activation-0.051
Top resid features:
its
Token its
Feature activation+0.173
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.009
Top resid features:
rolling
Token rolling
Feature activation-0.001
Top resid features:
one
Token one
Feature activation+0.007
Top resid features:
where
Token where
Feature activation-0.008
Top resid features:
each
Token each
Feature activation+4.364
Top resid features:
of
Token of
Feature activation+0.026
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
releases
Token releases
Feature activation+0.003
Top resid features:
will
Token will
Feature activation+0.010
Top resid features:
get
Token get
Feature activation-0.039
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.358
Top resid features:
our
Token our
Feature activation+0.002
Top resid features:
belt
Token belt
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
each
Token each
Feature activation+4.166
Top resid features:
being
Token being
Feature activation+0.039
Top resid features:
more
Token more
Feature activation+0.036
Top resid features:
elaborate
Token elaborate
Feature activation+0.030
Top resid features:
than
Token than
Feature activation-0.094
Top resid features:
the
Token the
Feature activation+0.058
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
age
Token age
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.027
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Each
TokenEach
Feature activation+3.740
Top resid features:
morning
Token morning
Feature activation+0.172
Top resid features:
,
Token,
Feature activation+0.030
Top resid features:
I
Token I
Feature activation+0.064
Top resid features:
check
Token check
Feature activation+0.023
Top resid features:
out
Token out
Feature activation+0.014
Top resid features:
is
Token is
Feature activation+0.006
Top resid features:
divided
Token divided
Feature activation+0.051
Top resid features:
into
Token into
Feature activation+0.011
Top resid features:
regions
Token regions
Feature activation+0.003
Top resid features:
(
Token (
Feature activation+0.003
Top resid features:
each
Tokeneach
Feature activation+4.062
Top resid features:
town
Token town
Feature activation-0.028
Top resid features:
is
Token is
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.086
Top resid features:
separate
Token separate
Feature activation-0.001
Top resid features:
region
Token region
Feature activation+0.000
Top resid features:
network
Token network
Feature activation+0.001
Top resid features:
users
Token users
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Each
TokenEach
Feature activation+3.814
Top resid features:
of
Token of
Feature activation+0.095
Top resid features:
these
Token these
Feature activation+0.029
Top resid features:
methods
Token methods
Feature activation+0.031
Top resid features:
has
Token has
Feature activation+0.019
Top resid features:
its
Token its
Feature activation+0.128
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
a
Token a
Feature activation+0.013
Top resid features:
rolling
Token rolling
Feature activation-0.005
Top resid features:
one
Token one
Feature activation+0.012
Top resid features:
where
Token where
Feature activation+0.001
Top resid features:
each
Token each
Feature activation+3.627
Top resid features:
of
Token of
Feature activation+0.090
Top resid features:
the
Token the
Feature activation+0.030
Top resid features:
releases
Token releases
Feature activation+0.008
Top resid features:
will
Token will
Feature activation+0.024
Top resid features:
get
Token get
Feature activation-0.048
Top resid features:
Ļ
TokenĻ
Feature activation-0.001
Top resid features:
s
Tokens
Feature activation+0.004
Top resid features:
daughter
Token daughter
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
each
Token each
Feature activation+3.491
Top resid features:
har
Token har
Feature activation+0.006
Top resid features:
bors
Tokenbors
Feature activation-0.035
Top resid features:
its
Token its
Feature activation+0.126
Top resid features:
own
Token own
Feature activation+0.032
Top resid features:
ambitions
Token ambitions
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.374
Top resid features:
that
Token that
Feature activation+0.028
Top resid features:
every
Token every
Feature activation+3.551
Top resid features:
size
Token size
Feature activation+0.054
Top resid features:
requires
Token requires
Feature activation-0.045
Top resid features:
a
Token a
Feature activation+0.098
Top resid features:
different
Token different
Feature activation-0.024
Top resid features:
size
Token size
Feature activation+0.000
Top resid features:
did
Token did
Feature activation-0.009
Top resid features:
not
Token not
Feature activation-0.004
Top resid features:
come
Token come
Feature activation-0.003
Top resid features:
about
Token about
Feature activation-0.007
Top resid features:
because
Token because
Feature activation+0.036
Top resid features:
each
Token each
Feature activation+3.540
Top resid features:
expected
Token expected
Feature activation+0.073
Top resid features:
different
Token different
Feature activation+0.061
Top resid features:
things
Token things
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:
official
Token official
Feature activation+0.001
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Each
TokenEach
Feature activation+3.338
Top resid features:
House
Token House
Feature activation+0.026
Top resid features:
member
Token member
Feature activation+0.019
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation+0.007
Top resid features:
lack
Token lack
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
clothing
Token clothing
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
though
Token though
Feature activation-0.004
Top resid features:
each
Token each
Feature activation+3.619
Top resid features:
condition
Token condition
Feature activation+0.025
Top resid features:
exists
Token exists
Feature activation+0.008
Top resid features:
exclusive
Token exclusive
Feature activation+0.019
Top resid features:
of
Token of
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
official
Token official
Feature activation+0.003
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Each
TokenEach
Feature activation+3.132
Top resid features:
House
Token House
Feature activation+0.032
Top resid features:
member
Token member
Feature activation+0.091
Top resid features:
âĢ
TokenâĢ
Feature activation+0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.009
Top resid features:
s
Tokens
Feature activation+0.027
Top resid features:
from
Token from
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
reward
Token reward
Feature activation+0.004
Top resid features:
bags
Token bags
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.052
Top resid features:
Each
Token Each
Feature activation+3.256
Top resid features:
trial
Token trial
Feature activation+0.053
Top resid features:
rewards
Token rewards
Feature activation-0.061
Top resid features:
different
Token different
Feature activation+0.139
Top resid features:
parts
Token parts
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
roller
Token roller
Feature activation+0.001
Top resid features:
bl
Tokenbl
Feature activation+0.000
Top resid features:
ading
Tokenading
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
Each
Token Each
Feature activation+3.020
Top resid features:
time
Token time
Feature activation+0.135
Top resid features:
Met
Token Met
Feature activation+0.021
Top resid features:
el
Tokenel
Feature activation-0.009
Top resid features:
ka
Tokenka
Feature activation-0.011
Top resid features:
suggested
Token suggested
Feature activation+0.096
Top resid features:
specific
Token specific
Feature activation+0.013
Top resid features:
goals
Token goals
Feature activation+0.008
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
mind
Token mind
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.024
Top resid features:
Each
Token Each
Feature activation+2.776
Top resid features:
of
Token of
Feature activation+0.052
Top resid features:
Met
Token Met
Feature activation+0.005
Top resid features:
el
Tokenel
Feature activation-0.006
Top resid features:
ka
Tokenka
Feature activation-0.006
Top resid features:
âĢ
TokenâĢ
Feature activation+0.013
Top resid features:
between
Token between
Feature activation+0.005
Top resid features:
weight
Token weight
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
fuel
Token fuel
Feature activation+0.001
Top resid features:
).
Token).
Feature activation+0.036
Top resid features:
Each
Token Each
Feature activation+2.709
Top resid features:
biome
Token biome
Feature activation+0.176
Top resid features:
contains
Token contains
Feature activation+0.006
Top resid features:
a
Token a
Feature activation+0.111
Top resid features:
fully
Token fully
Feature activation+0.000
Top resid features:
functional
Token functional
Feature activation+0.000
Top resid features:
No
Token No
Feature activation-0.004
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
1
Token 1
Feature activation-0.011
Top resid features:
songs
Token songs
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
each
Token each
Feature activation+2.960
Top resid features:
in
Token in
Feature activation-0.006
Top resid features:
a
Token a
Feature activation+0.058
Top resid features:
vastly
Token vastly
Feature activation+0.013
Top resid features:
different
Token different
Feature activation+0.019
Top resid features:
style
Token style
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
Torah
Token Torah
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
assuming
Token assuming
Feature activation+0.009
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
each
Token each
Feature activation+2.757
Top resid features:
book
Token book
Feature activation+0.027
Top resid features:
of
Token of
Feature activation+0.101
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
Torah
Token Torah
Feature activation+0.001
Top resid features:
is
Token is
Feature activation+0.062
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.05

Head 2: 0.05

Head 3: 0.02

Head 4: 0.03

Head 5: 0.49

Head 6: 0.06

Head 7: 0.04

Head 8: 0.03

Head 9: 0.04

Head 10: 0.05

Head 11: 0.12

Positive logits

individually2.88

each2.63

respective2.57

each2.54

Each2.38

separately2.36

predetermined2.32

increments2.26

Each2.21

corresponding2.08

varying2.08

preset2.06

mutually2.02

ividually2.01

individual1.98

acters1.96

distinct1.90

allotted1.89

fortnight1.88

randomly1.87

Negative logits

ÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂ-1.91

haven-1.89

jam-1.86

-1.86

olis-1.85

video-1.84

-1.81

��-1.78

audi-1.75

hai-1.75

usa-1.72

CONCLUS-1.70

heed-1.70

advertising-1.69

ansas-1.68

-1.67

د-1.66

\\\\-1.65

ب-1.63

ÃÂÃÂ-1.63

INTERVAL 5.081 - 5.645
CONTAINS 0.000%

block
Token block
Feature activation+0.000
is
Token is
Feature activation+0.000
made
Token made
Feature activation+0.000
from
Token from
Feature activation+0.550
a
Token a
Feature activation+2.276
different
Token different
Feature activation+5.645
substance
Token substance
Feature activation+0.900
,
Token,
Feature activation+0.582
and
Token and
Feature activation+0.538
they
Token they
Feature activation+0.619
all
Token all
Feature activation+0.434
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
methods
Token methods
Feature activation+0.000
has
Token has
Feature activation+0.071
its
Token its
Feature activation+3.594
own
Token own
Feature activation+5.361
advantages
Token advantages
Feature activation+1.332
and
Token and
Feature activation+0.486
disadvantages
Token disadvantages
Feature activation+0.491
,
Token,
Feature activation+0.123
and
Token and
Feature activation+0.080

INTERVAL 4.516 - 5.081
CONTAINS 0.000%

INTERVAL 3.952 - 4.516
CONTAINS 0.000%

the
Token the
Feature activation+0.137
releases
Token releases
Feature activation+0.000
will
Token will
Feature activation+0.186
get
Token get
Feature activation+0.393
its
Token its
Feature activation+3.287
own
Token own
Feature activation+4.032
name
Token name
Feature activation+1.168
from
Token from
Feature activation+0.759
a
Token a
Feature activation+1.929
list
Token list
Feature activation+0.982
of
Token of
Feature activation+0.355

INTERVAL 3.387 - 3.952
CONTAINS 0.000%

(
Token (
Feature activation+0.000
each
Tokeneach
Feature activation+0.000
town
Token town
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+1.068
separate
Token separate
Feature activation+3.601
region
Token region
Feature activation+0.527
as
Token as
Feature activation+0.331
are
Token are
Feature activation+0.058
areas
Token areas
Feature activation+0.030
such
Token such
Feature activation+0.180
being
Token being
Feature activation+0.000
more
Token more
Feature activation+0.000
elaborate
Token elaborate
Feature activation+0.319
than
Token than
Feature activation+0.393
the
Token the
Feature activation+0.679
last
Token last
Feature activation+3.649
.
Token.
Feature activation+0.060
We
Token We
Feature activation+0.144
were
Token were
Feature activation+0.000
even
Token even
Feature activation+0.000
featured
Token featured
Feature activation+0.000
Each
TokenEach
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
methods
Token methods
Feature activation+0.000
has
Token has
Feature activation+0.071
its
Token its
Feature activation+3.594
own
Token own
Feature activation+5.361
advantages
Token advantages
Feature activation+1.332
and
Token and
Feature activation+0.486
disadvantages
Token disadvantages
Feature activation+0.491
,
Token,
Feature activation+0.123
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.141
check
Token check
Feature activation+0.634
out
Token out
Feature activation+0.233
a
Token a
Feature activation+2.259
number
Token number
Feature activation+3.613
of
Token of
Feature activation+0.626
Internet
Token Internet
Feature activation+0.153
news
Token news
Feature activation+0.000
reports
Token reports
Feature activation+0.357
and
Token and
Feature activation+0.300

INTERVAL 2.823 - 3.387
CONTAINS 0.001%

supposed
Token supposed
Feature activation+0.308
to
Token to
Feature activation+0.211
be
Token be
Feature activation+0.011
stored
Token stored
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+2.929
own
Token own
Feature activation+3.024
server
Token server
Feature activation+0.018
,
Token,
Feature activation+0.123
but
Token but
Feature activation+0.637
Imran
Token Imran
Feature activation+0.000
come
Token come
Feature activation+0.000
about
Token about
Feature activation+0.000
because
Token because
Feature activation+0.000
each
Token each
Feature activation+0.000
expected
Token expected
Feature activation+0.000
different
Token different
Feature activation+3.079
things
Token things
Feature activation+0.067
from
Token from
Feature activation+0.007
it
Token it
Feature activation+0.853
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.003
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.137
releases
Token releases
Feature activation+0.000
will
Token will
Feature activation+0.186
get
Token get
Feature activation+0.393
its
Token its
Feature activation+3.287
own
Token own
Feature activation+4.032
name
Token name
Feature activation+1.168
from
Token from
Feature activation+0.759
a
Token a
Feature activation+1.929
list
Token list
Feature activation+0.982
and
Token and
Feature activation+0.000
each
Token each
Feature activation+0.000
har
Token har
Feature activation+0.000
bors
Tokenbors
Feature activation+0.085
its
Token its
Feature activation+2.068
own
Token own
Feature activation+3.103
ambitions
Token ambitions
Feature activation+0.096
and
Token and
Feature activation+0.212
grievances
Token grievances
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
size
Token size
Feature activation+0.000
requires
Token requires
Feature activation+0.000
a
Token a
Feature activation+0.595
different
Token different
Feature activation+3.099
size
Token size
Feature activation+0.000
sole
Token sole
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
used
Token used
Feature activation+0.000

INTERVAL 2.258 - 2.823
CONTAINS 0.001%

fuel
Token fuel
Feature activation+0.000
).
Token).
Feature activation+0.000
Each
Token Each
Feature activation+0.000
biome
Token biome
Feature activation+0.000
contains
Token contains
Feature activation+0.329
a
Token a
Feature activation+2.513
fully
Token fully
Feature activation+2.134
functional
Token functional
Feature activation+1.073
society
Token society
Feature activation+0.771
making
Token making
Feature activation+0.181
up
Token up
Feature activation+0.000
Met
Token Met
Feature activation+0.163
el
Tokenel
Feature activation+0.000
ka
Tokenka
Feature activation+0.000
suggested
Token suggested
Feature activation+0.191
a
Token a
Feature activation+1.782
new
Token new
Feature activation+2.796
sport
Token sport
Feature activation+0.589
,
Token,
Feature activation+0.149
the
Token the
Feature activation+0.254
team
Token team
Feature activation+0.000
designed
Token designed
Feature activation+0.000
do
Token do
Feature activation+0.323
od
Tokenod
Feature activation+0.126
les
Tokenles
Feature activation+0.000
pertaining
Token pertaining
Feature activation+0.643
to
Token to
Feature activation+0.495
one
Token one
Feature activation+2.260
of
Token of
Feature activation+0.861
the
Token the
Feature activation+0.648
interests
Token interests
Feature activation+0.000
I
Token I
Feature activation+0.261
listed
Token listed
Feature activation+0.158
s
Tokens
Feature activation+0.443
legs
Token legs
Feature activation+0.525
arrives
Token arrives
Feature activation+0.251
with
Token with
Feature activation+1.062
a
Token a
Feature activation+2.408
particular
Token particular
Feature activation+2.572
design
Token design
Feature activation+0.144
challenge
Token challenge
Feature activation+0.949
.
Token.
Feature activation+0.657
Weight
Token Weight
Feature activation+0.000
,
Token,
Feature activation+0.000
Each
Token Each
Feature activation+0.000
block
Token block
Feature activation+0.000
is
Token is
Feature activation+0.000
made
Token made
Feature activation+0.000
from
Token from
Feature activation+0.550
a
Token a
Feature activation+2.276
different
Token different
Feature activation+5.645
substance
Token substance
Feature activation+0.900
,
Token,
Feature activation+0.582
and
Token and
Feature activation+0.538
they
Token they
Feature activation+0.619

INTERVAL 1.694 - 2.258
CONTAINS 0.003%

position
Token position
Feature activation+0.000
in
Token in
Feature activation+0.067
the
Token the
Feature activation+0.108
pack
Token pack
Feature activation+0.110
represents
Token represents
Feature activation+0.607
a
Token a
Feature activation+1.979
1
Token 1
Feature activation+1.009
or
Token or
Feature activation+0.386
0
Token 0
Feature activation+0.219
.
Token.
Feature activation+0.218
If
Token If
Feature activation+0.278
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
every
Token every
Feature activation+0.000
situation
Token situation
Feature activation+0.000
is
Token is
Feature activation+0.000
different
Token different
Feature activation+1.927
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
might
Token might
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
from
Token from
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
each
Token each
Feature activation+0.000
har
Token har
Feature activation+0.000
bors
Tokenbors
Feature activation+0.085
its
Token its
Feature activation+2.068
own
Token own
Feature activation+3.103
ambitions
Token ambitions
Feature activation+0.096
and
Token and
Feature activation+0.212
grievances
Token grievances
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
how
Token how
Feature activation+0.000
each
Token each
Feature activation+0.000
country
Token country
Feature activation+0.000
packs
Token packs
Feature activation+0.000
its
Token its
Feature activation+2.252
culture
Token culture
Feature activation+0.109
with
Token with
Feature activation+0.352
them
Token them
Feature activation+0.679
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.400
boxes
Token boxes
Feature activation+0.000
,
Token,
Feature activation+0.000
each
Token each
Feature activation+0.028
containing
Token containing
Feature activation+0.000
a
Token a
Feature activation+1.032
random
Token random
Feature activation+1.805
and
Token and
Feature activation+0.111
unknown
Token unknown
Feature activation+0.486
Pokémon
Token Pokémon
Feature activation+0.000
just
Token just
Feature activation+0.455
waiting
Token waiting
Feature activation+0.138

INTERVAL 1.129 - 1.694
CONTAINS 0.006%

present
Token present
Feature activation+0.455
the
Token the
Feature activation+1.123
block
Token block
Feature activation+0.275
and
Token and
Feature activation+0.198
give
Token give
Feature activation+0.120
a
Token a
Feature activation+1.262
demonstration
Token demonstration
Feature activation+0.222
(
Token (
Feature activation+0.487
of
Tokenof
Feature activation+0.011
what
Token what
Feature activation+0.000
NOT
Token NOT
Feature activation+0.000
some
Token some
Feature activation+0.863
changes
Token changes
Feature activation+0.000
relative
Token relative
Feature activation+0.099
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.183
previous
Token previous
Feature activation+1.527
amended
Token amended
Feature activation+0.000
copy
Token copy
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.092
tree
Token tree
Feature activation+0.000
itself
Token itself
Feature activation+0.000
.
Token.
Feature activation+0.000
Each
Token Each
Feature activation+0.000
wave
Token wave
Feature activation+0.000
has
Token has
Feature activation+0.000
two
Token two
Feature activation+1.683
dimensions
Token dimensions
Feature activation+0.369
:
Token:
Feature activation+0.965
a
Token a
Feature activation+1.369
creative
Token creative
Feature activation+0.032
one
Token one
Feature activation+0.713
releases
Token releases
Feature activation+0.000
will
Token will
Feature activation+0.186
get
Token get
Feature activation+0.393
its
Token its
Feature activation+3.287
own
Token own
Feature activation+4.032
name
Token name
Feature activation+1.168
from
Token from
Feature activation+0.759
a
Token a
Feature activation+1.929
list
Token list
Feature activation+0.982
of
Token of
Feature activation+0.355
coffee
Token coffee
Feature activation+0.000
weigh
Token weigh
Feature activation+0.000
the
Token the
Feature activation+0.000
cost
Token cost
Feature activation+0.000
of
Token of
Feature activation+0.000
each
Token each
Feature activation+0.000
individual
Token individual
Feature activation+1.263
ride
Token ride
Feature activation+0.000
may
Token may
Feature activation+0.000
encourage
Token encourage
Feature activation+0.000
people
Token people
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.565 - 1.129
CONTAINS 0.019%

two
Token two
Feature activation+1.683
dimensions
Token dimensions
Feature activation+0.369
:
Token:
Feature activation+0.965
a
Token a
Feature activation+1.369
creative
Token creative
Feature activation+0.032
one
Token one
Feature activation+0.713
in
Token in
Feature activation+0.197
which
Token which
Feature activation+0.000
new
Token new
Feature activation+0.515
possibilities
Token possibilities
Feature activation+0.000
,
Token,
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.000
each
Token each
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.974
eight
Token eight
Feature activation+0.000
seasons
Token seasons
Feature activation+0.000
for
Token for
Feature activation+0.000
Pr
Token Pr
Feature activation+0.000
ado
Tokenado
Feature activation+0.000
every
Token every
Feature activation+0.000
contributor
Token contributor
Feature activation+0.000
do
Token do
Feature activation+0.000
ff
Tokenff
Feature activation+0.000
ed
Tokened
Feature activation+0.000
a
Token a
Feature activation+0.666
cap
Token cap
Feature activation+0.140
toward
Token toward
Feature activation+0.000
Taylor
Token Taylor
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.062
Belgium
Token Belgium
Feature activation+0.000
,
Token,
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
can
Token can
Feature activation+0.000
chose
Token chose
Feature activation+0.000
his
Token his
Feature activation+0.620
or
Token or
Feature activation+0.000
her
Token her
Feature activation+0.000
partner
Token partner
Feature activation+0.000
,
Token,
Feature activation+0.000
whom
Token whom
Feature activation+0.000
at
Token at
Feature activation+0.000
each
Token each
Feature activation+0.000
shop
Token shop
Feature activation+0.000
will
Token will
Feature activation+0.000
use
Token use
Feature activation+0.000
the
Token the
Feature activation+0.582
technology
Token technology
Feature activation+0.194
that
Token that
Feature activation+0.167
was
Token was
Feature activation+0.322
co
Token co
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 0.000 - 0.565
CONTAINS 99.969%

Rush
Token Rush
Feature activation+0.000
die
Tokendie
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
placed
Token placed
Feature activation+0.000
under
Token under
Feature activation+0.000
police
Token police
Feature activation+0.000
protection
Token protection
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Some
Token Some
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
valued
Token valued
Feature activation+0.000
at
Token at
Feature activation+0.000
millions
Token millions
Feature activation+0.000
of
Token of
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
.
Token.
Feature activation+0.000
Upon
Token Upon
Feature activation+0.000
learning
Token learning
Feature activation+0.000
a
Token a
Feature activation+0.000
violation
Token violation
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Egyptian
Token Egyptian
Feature activation+0.000
Constitution
Token Constitution
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
article
Token article
Feature activation+0.000
calls
Token calls
Feature activation+0.000
for
Token for
Feature activation+0.000
basket
Token basket
Feature activation+0.000
for
Token for
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
five
Token five
Feature activation+0.000
seconds
Token seconds
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
below
Token below
Feature activation+0.000
the
Token the
Feature activation+0.000
and
Token and
Feature activation+0.000
illusion
Token illusion
Feature activation+0.000
becomes
Token becomes
Feature activation+0.000
king
Token king
Feature activation+0.000
,
Token,
Feature activation+0.000
just
Token just
Feature activation+0.000
as
Token as
Feature activation+0.000
Dr
Token Dr
Feature activation+0.000
.
Token.
Feature activation+0.000
Stan
Token Stan
Feature activation+0.000
Monte
Token Monte
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 H3.5: (feature 10105)

TOP ACTIVATIONS
MAX = 3.046

man
Token man
Feature activation+0.000
#
Token #
Feature activation+0.147
C
TokenC
Feature activation+0.000
razy
Tokenrazy
Feature activation+0.000
World
TokenWorld
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+3.046
Tre
Token Tre
Feature activation+0.000
on
Tokenon
Feature activation+0.000
Harris
Token Harris
Feature activation+0.000
(@
Token (@
Feature activation+0.304
t
Tokent
Feature activation+0.000
the
Token the
Feature activation+0.235
Open
Token Open
Feature activation+0.000
Build
Token Build
Feature activation+0.000
Se
Token Se
Feature activation+0.000
vice
Tokenvice
Feature activation+0.000
?
Token?
Feature activation+3.042
Ċ
TokenĊ
Feature activation+1.520
Ċ
TokenĊ
Feature activation+0.857
4
Token4
Feature activation+0.000
.
Token.
Feature activation+0.000
How
Token How
Feature activation+0.000
Where
TokenWhere
Feature activation+0.000
can
Token can
Feature activation+0.000
I
Token I
Feature activation+0.000
find
Token find
Feature activation+0.000
it
Token it
Feature activation+0.000
?
Token?
Feature activation+2.906
Ċ
TokenĊ
Feature activation+1.066
Ċ
TokenĊ
Feature activation+0.467
The
TokenThe
Feature activation+0.000
Common
Token Common
Feature activation+0.000
Mark
TokenMark
Feature activation+0.000
How
TokenHow
Feature activation+0.407
do
Token do
Feature activation+0.000
I
Token I
Feature activation+0.000
improv
Token improv
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
?
Token?
Feature activation+2.474
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.045
so
Token so
Feature activation+0.000
I
Token I
Feature activation+0.000
figured
Token figured
Feature activation+0.000
be
Token be
Feature activation+0.000
received
Token received
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.079
public
Token public
Feature activation+0.444
?
Token?
Feature activation+2.311
Does
Token Does
Feature activation+0.725
this
Token this
Feature activation+0.000
mean
Token mean
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
step
Token step
Feature activation+0.000
down
Token down
Feature activation+0.000
as
Token as
Feature activation+0.000
CEO
Token CEO
Feature activation+0.145
.
Token.
Feature activation+0.519
âĢĶ
Token âĢĶ
Feature activation+2.095
John
Token John
Feature activation+0.000
Be
Token Be
Feature activation+0.000
van
Tokenvan
Feature activation+0.000
(@
Token (@
Feature activation+0.000
be
Tokenbe
Feature activation+0.000
t
Tokent
Feature activation+0.000
I
Token I
Feature activation+0.000
get
Token get
Feature activation+0.000
stack
Token stack
Feature activation+0.000
traces
Token traces
Feature activation+0.138
?
Token?
Feature activation+2.028
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
presentation
Token presentation
Feature activation+0.000
).
Token).
Feature activation+0.000
Output
Token Output
Feature activation+0.000
thereof
Token thereof
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.110
expert
Token expert
Feature activation+0.000
report
Token report
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.900
boiled
Token boiled
Feature activation+0.000
down
Token down
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
inter
Token inter
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
will
Token will
Feature activation+0.000
my
Token my
Feature activation+0.256
friends
Token friends
Feature activation+0.000
think
Token think
Feature activation+0.000
?
Token?
Feature activation+1.888
How
Token How
Feature activation+0.225
will
Token will
Feature activation+0.062
I
Token I
Feature activation+0.506
be
Token be
Feature activation+0.000
received
Token received
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Love
TokenLove
Feature activation+0.000
my
Token my
Feature activation+0.000
WordPress
Token WordPress
Feature activation+0.000
theme
Token theme
Feature activation+0.000
?
Token?
Feature activation+1.834
I
Token I
Feature activation+0.651
'm
Token'm
Feature activation+0.027
using
Token using
Feature activation+0.000
the
Token the
Feature activation+0.000
T
Token T
Feature activation+0.000
been
Token been
Feature activation+0.000
Formula
Token Formula
Feature activation+0.000
1
Token 1
Feature activation+0.000
for
Token for
Feature activation+0.000
me
Token me
Feature activation+0.000
,"
Token,"
Feature activation+1.815
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
I
TokenI
Feature activation+0.000
house
Token house
Feature activation+0.000
and
Token and
Feature activation+0.000
ripped
Token ripped
Feature activation+0.000
my
Token my
Feature activation+0.030
clothes
Token clothes
Feature activation+0.000
,"
Token,"
Feature activation+1.794
the
Token the
Feature activation+0.000
woman
Token woman
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
requested
Token requested
Feature activation+0.000
I
Token I
Feature activation+0.000
clean
Token clean
Feature activation+0.000
up
Token up
Feature activation+0.000
this
Token this
Feature activation+0.210
mess
Token mess
Feature activation+0.000
?
Token?
Feature activation+1.743
Ċ
TokenĊ
Feature activation+1.035
Ċ
TokenĊ
Feature activation+0.682
Let
TokenLet
Feature activation+0.018
me
Token me
Feature activation+0.000
try
Token try
Feature activation+0.000
my
Token my
Feature activation+0.000
tenure
Token tenure
Feature activation+0.000
in
Token in
Feature activation+0.000
public
Token public
Feature activation+0.000
office
Token office
Feature activation+0.000
,"
Token,"
Feature activation+1.737
Ger
Token Ger
Feature activation+0.000
l
Tokenl
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
face
Token face
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.022
party
Token party
Feature activation+0.054
?
Token?
Feature activation+1.691
âĢ
TokenâĢ
Feature activation+0.082
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.783
Ċ
TokenĊ
Feature activation+0.157
âĢ
TokenâĢ
Feature activation+0.000
how
Token how
Feature activation+0.000
do
Token do
Feature activation+0.000
I
Token I
Feature activation+0.000
get
Token get
Feature activation+0.000
apps
Token apps
Feature activation+0.000
?
Token?
Feature activation+1.685
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Here
Token Here
Feature activation+0.125
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
is
Token is
Feature activation+0.000
my
Token my
Feature activation+0.000
only
Token only
Feature activation+0.000
true
Token true
Feature activation+0.000
revenge
Token revenge
Feature activation+0.000
,"
Token,"
Feature activation+1.685
Amanda
Token Amanda
Feature activation+0.000
(
Token (
Feature activation+0.040
Emily
TokenEmily
Feature activation+0.000
Van
Token Van
Feature activation+0.000
Camp
TokenCamp
Feature activation+0.000
them
Token them
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
teeth
Token teeth
Feature activation+0.000
.
Token.
Feature activation+0.817
Ċ
TokenĊ
Feature activation+1.616
Ċ
TokenĊ
Feature activation+1.110
Put
TokenPut
Feature activation+0.000
this
Token this
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.085
or
Token or
Feature activation+0.000
East
Token East
Feature activation+0.000
Asian
Token Asian
Feature activation+0.000
-
Token-
Feature activation+0.000
er
Tokener
Feature activation+0.000
?
Token?
Feature activation+1.601
Do
Token Do
Feature activation+0.837
I
Token I
Feature activation+0.349
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
even
Token even
Feature activation+0.000
funny
Token funny
Feature activation+0.000
or
Token or
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
?
Token?
Feature activation+1.372
âĢĶ
Token âĢĶ
Feature activation+1.596
Mike
Token Mike
Feature activation+0.000
Mach
Token Mach
Feature activation+0.000
ado
Tokenado
Feature activation+0.000
(@
Token (@
Feature activation+0.256
mm
Tokenmm
Feature activation+0.000

Top DFA by src position
MAX = 3.352

Ċ
TokenĊ
Feature activation+0.032
Top resid features:
P
TokenP
Feature activation+0.008
Top resid features:
ray
Tokenray
Feature activation+0.001
Top resid features:
ing
Tokening
Feature activation+0.001
Top resid features:
For
Token For
Feature activation+0.006
Top resid features:
my
Token my
Feature activation+3.352
Top resid features:
lil
Token lil
Feature activation+0.021
Top resid features:
cousin
Token cousin
Feature activation+0.016
Top resid features:
man
Token man
Feature activation+0.008
Top resid features:
#
Token #
Feature activation+0.006
Top resid features:
C
TokenC
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
3
Token3
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
How
Token How
Feature activation+0.005
Top resid features:
can
Token can
Feature activation+0.035
Top resid features:
I
Token I
Feature activation+2.861
Top resid features:
package
Token package
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
deploy
Token deploy
Feature activation-0.001
Top resid features:
my
Token my
Feature activation+0.537
Top resid features:
own
Token own
Feature activation+0.019
Top resid features:
?
Token?
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Where
TokenWhere
Feature activation+0.032
Top resid features:
can
Token can
Feature activation+0.018
Top resid features:
I
Token I
Feature activation+3.169
Top resid features:
find
Token find
Feature activation+0.040
Top resid features:
it
Token it
Feature activation-0.006
Top resid features:
?
Token?
Feature activation+0.046
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
on
Token on
Feature activation-0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.041
Top resid features:
ľ
Tokenľ
Feature activation+0.013
Top resid features:
How
TokenHow
Feature activation+0.033
Top resid features:
do
Token do
Feature activation+0.009
Top resid features:
I
Token I
Feature activation+1.443
Top resid features:
improv
Token improv
Feature activation+0.031
Top resid features:
ise
Tokenise
Feature activation-0.013
Top resid features:
?
Token?
Feature activation+0.037
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
What
TokenWhat
Feature activation-0.005
Top resid features:
will
Token will
Feature activation+0.005
Top resid features:
my
Token my
Feature activation+1.611
Top resid features:
friends
Token friends
Feature activation-0.009
Top resid features:
think
Token think
Feature activation-0.002
Top resid features:
?
Token?
Feature activation+0.003
Top resid features:
How
Token How
Feature activation+0.039
Top resid features:
will
Token will
Feature activation+0.014
Top resid features:
Mozilla
Token Mozilla
Feature activation+0.000
Top resid features:
Foundation
Token Foundation
Feature activation-0.001
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
I
TokenI
Feature activation+1.561
Top resid features:
'm
Token'm
Feature activation+0.237
Top resid features:
an
Token an
Feature activation+0.058
Top resid features:
employee
Token employee
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
@
Token @
Feature activation+0.069
Top resid features:
Why
TokenWhy
Feature activation+0.013
Top resid features:
can
Token can
Feature activation+0.017
Top resid features:
âĢ
TokenâĢ
Feature activation+0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.022
Top resid features:
t
Tokent
Feature activation+0.008
Top resid features:
I
Token I
Feature activation+2.183
Top resid features:
get
Token get
Feature activation+0.055
Top resid features:
stack
Token stack
Feature activation+0.058
Top resid features:
traces
Token traces
Feature activation+0.008
Top resid features:
?
Token?
Feature activation+0.044
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.051
Top resid features:
thereof
Token thereof
Feature activation+0.010
Top resid features:
in
Token in
Feature activation+0.048
Top resid features:
my
Token my
Feature activation+2.068
Top resid features:
expert
Token expert
Feature activation+0.075
Top resid features:
report
Token report
Feature activation-0.009
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.116
Top resid features:
boiled
Token boiled
Feature activation+0.000
Top resid features:
down
Token down
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.032
Top resid features:
What
TokenWhat
Feature activation-0.018
Top resid features:
will
Token will
Feature activation+0.037
Top resid features:
my
Token my
Feature activation+2.154
Top resid features:
friends
Token friends
Feature activation+0.013
Top resid features:
think
Token think
Feature activation+0.002
Top resid features:
?
Token?
Feature activation+0.075
Top resid features:
How
Token How
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
imported
Token imported
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Love
TokenLove
Feature activation-0.095
Top resid features:
my
Token my
Feature activation+2.322
Top resid features:
WordPress
Token WordPress
Feature activation+0.003
Top resid features:
theme
Token theme
Feature activation+0.001
Top resid features:
?
Token?
Feature activation+0.072
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
'm
Token'm
Feature activation+0.000
Top resid features:
always
Token always
Feature activation-0.006
Top resid features:
been
Token been
Feature activation-0.002
Top resid features:
Formula
Token Formula
Feature activation+0.023
Top resid features:
1
Token 1
Feature activation+0.006
Top resid features:
for
Token for
Feature activation-0.012
Top resid features:
me
Token me
Feature activation+2.815
Top resid features:
,"
Token,"
Feature activation-0.043
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
went
Token went
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
dragged
Token dragged
Feature activation+0.011
Top resid features:
me
Token me
Feature activation+1.581
Top resid features:
out
Token out
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
threw
Token threw
Feature activation+0.001
Top resid features:
me
Token me
Feature activation+0.544
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
!"
Token!"
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
How
TokenHow
Feature activation+0.011
Top resid features:
do
Token do
Feature activation-0.009
Top resid features:
I
Token I
Feature activation+1.800
Top resid features:
clean
Token clean
Feature activation+0.017
Top resid features:
up
Token up
Feature activation+0.010
Top resid features:
this
Token this
Feature activation+0.063
Top resid features:
mess
Token mess
Feature activation+0.021
Top resid features:
?
Token?
Feature activation+0.056
Top resid features:
N
TokenN
Feature activation+0.003
Top resid features:
earing
Tokenearing
Feature activation-0.012
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
end
Token end
Feature activation-0.006
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
my
Token my
Feature activation+1.011
Top resid features:
sixth
Token sixth
Feature activation+0.002
Top resid features:
term
Token term
Feature activation+0.004
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
House
Token House
Feature activation+0.001
Top resid features:
trapped
Token trapped
Feature activation+0.014
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
But
Token But
Feature activation+0.013
Top resid features:
lie
Token lie
Feature activation+0.028
Top resid features:
to
Token to
Feature activation+0.021
Top resid features:
my
Token my
Feature activation+1.878
Top resid features:
face
Token face
Feature activation+0.041
Top resid features:
at
Token at
Feature activation+0.020
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
party
Token party
Feature activation-0.010
Top resid features:
?
Token?
Feature activation+0.078
Top resid features:
ľ
Tokenľ
Feature activation+0.014
Top resid features:
So
TokenSo
Feature activation+0.167
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
how
Token how
Feature activation+0.039
Top resid features:
do
Token do
Feature activation+0.008
Top resid features:
I
Token I
Feature activation+1.827
Top resid features:
get
Token get
Feature activation+0.011
Top resid features:
apps
Token apps
Feature activation-0.018
Top resid features:
?
Token?
Feature activation+0.028
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.050
Top resid features:
death
Token death
Feature activation-0.009
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
my
Token my
Feature activation+2.036
Top resid features:
only
Token only
Feature activation+0.030
Top resid features:
true
Token true
Feature activation+0.005
Top resid features:
revenge
Token revenge
Feature activation-0.021
Top resid features:
,"
Token,"
Feature activation+0.053
Top resid features:
Amanda
Token Amanda
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.045
Top resid features:
and
Token and
Feature activation+0.012
Top resid features:
I
Token I
Feature activation+2.077
Top resid features:
punch
Token punch
Feature activation+0.009
Top resid features:
them
Token them
Feature activation-0.018
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
teeth
Token teeth
Feature activation-0.003
Top resid features:
public
Token public
Feature activation-0.007
Top resid features:
?
Token?
Feature activation+0.009
Top resid features:
Does
Token Does
Feature activation+0.082
Top resid features:
this
Token this
Feature activation+0.015
Top resid features:
mean
Token mean
Feature activation-0.023
Top resid features:
I
Token I
Feature activation+0.794
Top resid features:
have
Token have
Feature activation+0.030
Top resid features:
to
Token to
Feature activation+0.021
Top resid features:
start
Token start
Feature activation+0.008
Top resid features:
dressing
Token dressing
Feature activation+0.010
Top resid features:
like
Token like
Feature activation+0.048
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.043
Top resid features:
my
Token my
Feature activation+1.797
Top resid features:
timeline
Token timeline
Feature activation+0.017
Top resid features:
but
Token but
Feature activation+0.069
Top resid features:
really
Token really
Feature activation+0.031
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
was
Token was
Feature activation+0.007
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.04

Head 2: 0.05

Head 3: 0.02

Head 4: 0.05

Head 5: 0.48

Head 6: 0.06

Head 7: 0.04

Head 8: 0.05

Head 9: 0.04

Head 10: 0.09

Head 11: 0.04

Positive logits

my2.85

myself2.67

My2.18

MY1.89

My1.88

mathemat1.87

teness1.80

millenn1.78

frustrations1.73

injust1.72

unlaw1.71

majesty1.71

professionalism1.70

diapers1.70

FTWARE1.69

~~~~1.68

:(1.60

sunscreen1.60

OUR1.60

my1.60

Negative logits

sidx-1.97

ğ-1.90

roth-1.85

imura-1.81

anwhile-1.79

atis-1.78

ulus-1.76

Purg-1.76

staking-1.74

Spiegel-1.68

ELS-1.67

ivably-1.66

uador-1.66

oglu-1.63

Pwr-1.62

arbon-1.62

ived-1.62

independent-1.60

exclusive-1.60

usat-1.59

INTERVAL 2.741 - 3.046
CONTAINS 0.000%

the
Token the
Feature activation+0.235
Open
Token Open
Feature activation+0.000
Build
Token Build
Feature activation+0.000
Se
Token Se
Feature activation+0.000
vice
Tokenvice
Feature activation+0.000
?
Token?
Feature activation+3.042
Ċ
TokenĊ
Feature activation+1.520
Ċ
TokenĊ
Feature activation+0.857
4
Token4
Feature activation+0.000
.
Token.
Feature activation+0.000
How
Token How
Feature activation+0.000
Where
TokenWhere
Feature activation+0.000
can
Token can
Feature activation+0.000
I
Token I
Feature activation+0.000
find
Token find
Feature activation+0.000
it
Token it
Feature activation+0.000
?
Token?
Feature activation+2.906
Ċ
TokenĊ
Feature activation+1.066
Ċ
TokenĊ
Feature activation+0.467
The
TokenThe
Feature activation+0.000
Common
Token Common
Feature activation+0.000
Mark
TokenMark
Feature activation+0.000
man
Token man
Feature activation+0.000
#
Token #
Feature activation+0.147
C
TokenC
Feature activation+0.000
razy
Tokenrazy
Feature activation+0.000
World
TokenWorld
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+3.046
Tre
Token Tre
Feature activation+0.000
on
Tokenon
Feature activation+0.000
Harris
Token Harris
Feature activation+0.000
(@
Token (@
Feature activation+0.304
t
Tokent
Feature activation+0.000

INTERVAL 2.437 - 2.741
CONTAINS 0.000%

How
TokenHow
Feature activation+0.407
do
Token do
Feature activation+0.000
I
Token I
Feature activation+0.000
improv
Token improv
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
?
Token?
Feature activation+2.474
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.045
so
Token so
Feature activation+0.000
I
Token I
Feature activation+0.000
figured
Token figured
Feature activation+0.000

INTERVAL 2.132 - 2.437
CONTAINS 0.000%

be
Token be
Feature activation+0.000
received
Token received
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.079
public
Token public
Feature activation+0.444
?
Token?
Feature activation+2.311
Does
Token Does
Feature activation+0.725
this
Token this
Feature activation+0.000
mean
Token mean
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000

INTERVAL 1.828 - 2.132
CONTAINS 0.001%

step
Token step
Feature activation+0.000
down
Token down
Feature activation+0.000
as
Token as
Feature activation+0.000
CEO
Token CEO
Feature activation+0.145
.
Token.
Feature activation+0.519
âĢĶ
Token âĢĶ
Feature activation+2.095
John
Token John
Feature activation+0.000
Be
Token Be
Feature activation+0.000
van
Tokenvan
Feature activation+0.000
(@
Token (@
Feature activation+0.000
be
Tokenbe
Feature activation+0.000
t
Tokent
Feature activation+0.000
I
Token I
Feature activation+0.000
get
Token get
Feature activation+0.000
stack
Token stack
Feature activation+0.000
traces
Token traces
Feature activation+0.138
?
Token?
Feature activation+2.028
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
presentation
Token presentation
Feature activation+0.000
).
Token).
Feature activation+0.000
Output
Token Output
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
will
Token will
Feature activation+0.000
my
Token my
Feature activation+0.256
friends
Token friends
Feature activation+0.000
think
Token think
Feature activation+0.000
?
Token?
Feature activation+1.888
How
Token How
Feature activation+0.225
will
Token will
Feature activation+0.062
I
Token I
Feature activation+0.506
be
Token be
Feature activation+0.000
received
Token received
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Love
TokenLove
Feature activation+0.000
my
Token my
Feature activation+0.000
WordPress
Token WordPress
Feature activation+0.000
theme
Token theme
Feature activation+0.000
?
Token?
Feature activation+1.834
I
Token I
Feature activation+0.651
'm
Token'm
Feature activation+0.027
using
Token using
Feature activation+0.000
the
Token the
Feature activation+0.000
T
Token T
Feature activation+0.000
thereof
Token thereof
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.110
expert
Token expert
Feature activation+0.000
report
Token report
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.900
boiled
Token boiled
Feature activation+0.000
down
Token down
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
inter
Token inter
Feature activation+0.000

INTERVAL 1.523 - 1.828
CONTAINS 0.001%

house
Token house
Feature activation+0.000
and
Token and
Feature activation+0.000
ripped
Token ripped
Feature activation+0.000
my
Token my
Feature activation+0.030
clothes
Token clothes
Feature activation+0.000
,"
Token,"
Feature activation+1.794
the
Token the
Feature activation+0.000
woman
Token woman
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
requested
Token requested
Feature activation+0.000
my
Token my
Feature activation+0.000
tenure
Token tenure
Feature activation+0.000
in
Token in
Feature activation+0.000
public
Token public
Feature activation+0.000
office
Token office
Feature activation+0.000
,"
Token,"
Feature activation+1.737
Ger
Token Ger
Feature activation+0.000
l
Tokenl
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
or
Token or
Feature activation+0.000
the
Token the
Feature activation+0.000
money
Token money
Feature activation+0.000
I
Token I
Feature activation+0.087
owe
Token owe
Feature activation+0.000
?
Token?
Feature activation+1.563
Ċ
TokenĊ
Feature activation+1.241
Ċ
TokenĊ
Feature activation+0.773
S
TokenS
Feature activation+0.000
inn
Tokeninn
Feature activation+0.000
F
Token F
Feature activation+0.000
clothes
Token clothes
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.197
charity
Token charity
Feature activation+0.179
.
Token.
Feature activation+1.220
Ċ
TokenĊ
Feature activation+1.564
Ċ
TokenĊ
Feature activation+1.070
More
TokenMore
Feature activation+0.000
than
Token than
Feature activation+0.000
once
Token once
Feature activation+0.000
I
Token I
Feature activation+0.000
my
Token my
Feature activation+0.000
face
Token face
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.022
party
Token party
Feature activation+0.054
?
Token?
Feature activation+1.691
âĢ
TokenâĢ
Feature activation+0.082
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.783
Ċ
TokenĊ
Feature activation+0.157
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 1.218 - 1.523
CONTAINS 0.003%

for
Token for
Feature activation+0.000
my
Token my
Feature activation+0.192
wife
Token wife
Feature activation+0.000
backstage
Token backstage
Feature activation+0.000
after
Token after
Feature activation+0.021
...
Token...
Feature activation+1.258
Posted
Token Posted
Feature activation+1.037
by
Token by
Feature activation+0.000
George
Token George
Feature activation+0.000
Moss
Token Moss
Feature activation+0.000
on
Token on
Feature activation+0.000
When
TokenWhen
Feature activation+0.000
I
Token I
Feature activation+0.000
started
Token started
Feature activation+0.000
my
Token my
Feature activation+0.199
career
Token career
Feature activation+0.000
we
Token we
Feature activation+1.328
didn
Token didn
Feature activation+0.213
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
even
Token even
Feature activation+0.000
the
Token the
Feature activation+0.000
money
Token money
Feature activation+0.000
I
Token I
Feature activation+0.087
owe
Token owe
Feature activation+0.000
?
Token?
Feature activation+1.563
Ċ
TokenĊ
Feature activation+1.241
Ċ
TokenĊ
Feature activation+0.773
S
TokenS
Feature activation+0.000
inn
Tokeninn
Feature activation+0.000
F
Token F
Feature activation+0.000
é
Tokené
Feature activation+0.000
Open
Token Open
Feature activation+0.000
Build
Token Build
Feature activation+0.000
Se
Token Se
Feature activation+0.000
vice
Tokenvice
Feature activation+0.000
?
Token?
Feature activation+3.042
Ċ
TokenĊ
Feature activation+1.520
Ċ
TokenĊ
Feature activation+0.857
4
Token4
Feature activation+0.000
.
Token.
Feature activation+0.000
How
Token How
Feature activation+0.000
does
Token does
Feature activation+0.000
beer
Token beer
Feature activation+0.000
.
Token.
Feature activation+0.254
As
Token As
Feature activation+0.068
a
Token a
Feature activation+0.000
beer
Token beer
Feature activation+0.000
journalist
Token journalist
Feature activation+1.243
and
Token and
Feature activation+0.000
author
Token author
Feature activation+0.097
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000

INTERVAL 0.914 - 1.218
CONTAINS 0.008%

be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
Winn
Token Winn
Feature activation+0.000
ipe
Tokenipe
Feature activation+0.000
gger
Tokengger
Feature activation+0.000
,"
Token,"
Feature activation+1.157
said
Token said
Feature activation+0.000
Fisher
Token Fisher
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
I
TokenI
Feature activation+0.000
management
Token management
Feature activation+0.000
problem
Token problem
Feature activation+0.000
,
Token,
Feature activation+0.089
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.924
Keller
Token Keller
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Union
TokenUnion
Feature activation+0.000
get
Token get
Feature activation+0.000
back
Token back
Feature activation+0.000
healthy
Token healthy
Feature activation+0.000
.
Token.
Feature activation+0.967
Ċ
TokenĊ
Feature activation+1.199
Ċ
TokenĊ
Feature activation+0.914
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Sometimes
TokenSometimes
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.206
,
Token,
Feature activation+0.069
and
Token and
Feature activation+0.045
we
Token we
Feature activation+0.942
are
Token are
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.006
make
Token make
Feature activation+0.000
our
Token our
Feature activation+0.461
told
Token told
Feature activation+0.000
me
Token me
Feature activation+0.000
everything
Token everything
Feature activation+0.000
was
Token was
Feature activation+0.000
good
Token good
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.031
Tre
Token Tre
Feature activation+0.000
on
Tokenon
Feature activation+0.000
Harris
Token Harris
Feature activation+0.000
(@
Token (@
Feature activation+0.233
t
Tokent
Feature activation+0.000

INTERVAL 0.609 - 0.914
CONTAINS 0.027%

to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
my
Token my
Feature activation+0.626
family
Token family
Feature activation+0.008
safe
Token safe
Feature activation+0.000
.
Token.
Feature activation+0.622
I
Token I
Feature activation+0.006
am
Token am
Feature activation+0.000
proud
Token proud
Feature activation+0.000
to
Token to
Feature activation+0.000
support
Token support
Feature activation+0.000
the
Token the
Feature activation+0.000
backfield
Token backfield
Feature activation+0.000
.
Token.
Feature activation+0.298
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.776
Ċ
TokenĊ
Feature activation+0.168
Johnson
TokenJohnson
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
get
Token get
Feature activation+0.000
my
Token my
Feature activation+0.221
arm
Token arm
Feature activation+0.000
up
Token up
Feature activation+0.000
over
Token over
Feature activation+0.000
our
Token our
Feature activation+0.699
next
Token next
Feature activation+0.000
volunteer
Token volunteer
Feature activation+0.182
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.134
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
started
Token started
Feature activation+0.000
to
Token to
Feature activation+0.000
pray
Token pray
Feature activation+0.000
,"
Token,"
Feature activation+0.624
Kam
Token Kam
Feature activation+0.000
y
Tokeny
Feature activation+0.000
lla
Tokenlla
Feature activation+0.000
told
Token told
Feature activation+0.000
me
Token me
Feature activation+0.000
a
Token a
Feature activation+0.000
one
Token one
Feature activation+0.000
stop
Token stop
Feature activation+0.000
shop
Token shop
Feature activation+0.000
where
Token where
Feature activation+0.250
I
Token I
Feature activation+0.901
can
Token can
Feature activation+0.475
find
Token find
Feature activation+0.375
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
NRA
Token NRA
Feature activation+0.000

INTERVAL 0.305 - 0.609
CONTAINS 0.121%

great
Token great
Feature activation+0.000
thing
Token thing
Feature activation+0.000
for
Token for
Feature activation+0.000
me
Token me
Feature activation+0.000
then
Token then
Feature activation+0.000
.
Token.
Feature activation+0.573
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.744
Ċ
TokenĊ
Feature activation+0.356
These
TokenThese
Feature activation+0.000
American
Token American
Feature activation+0.000
student
Token student
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Mr
Token Mr
Feature activation+0.382
.
Token.
Feature activation+0.000
Earn
Token Earn
Feature activation+0.000
est
Tokenest
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
favour
Token favour
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Yes
Token Yes
Feature activation+0.025
vote
Token vote
Feature activation+0.000
.
Token.
Feature activation+0.507
âĢ
TokenâĢ
Feature activation+0.177
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.528
Ċ
TokenĊ
Feature activation+0.049
Business
TokenBusiness
Feature activation+0.000
is
Token is
Feature activation+0.132
because
Token because
Feature activation+0.000
the
Token the
Feature activation+0.035
cars
Token cars
Feature activation+0.000
give
Token give
Feature activation+0.000
me
Token me
Feature activation+0.424
a
Token a
Feature activation+0.000
feeling
Token feeling
Feature activation+0.000
that
Token that
Feature activation+0.000
I
Token I
Feature activation+0.074
can
Token can
Feature activation+0.000
t
Tokent
Feature activation+0.000
damage
Token damage
Feature activation+0.000
my
Token my
Feature activation+0.387
car
Token car
Feature activation+0.002
because
Token because
Feature activation+0.070
I
Token I
Feature activation+0.403
was
Token was
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
too
Token too
Feature activation+0.000

INTERVAL 0.000 - 0.305
CONTAINS 99.839%

his
Token his
Feature activation+0.000
dream
Token dream
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
piece
Token piece
Feature activation+0.000
of
Token of
Feature activation+0.000
rolling
Token rolling
Feature activation+0.000
farmland
Token farmland
Feature activation+0.000
bordering
Token bordering
Feature activation+0.000
Les
Token Les
Feature activation+0.000
oth
Tokenoth
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Just
TokenJust
Feature activation+0.000
days
Token days
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
attempted
Token attempted
Feature activation+0.000
assassination
Token assassination
Feature activation+0.000
7
Token7
Feature activation+0.000
/
Token/
Feature activation+0.000
2014
Token2014
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
These
TokenThese
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
latest
Token latest
Feature activation+0.000
hole
Token hole
Feature activation+0.000
pictures
Token pictures
Feature activation+0.000
about
Token about
Feature activation+0.000
our
Token our
Feature activation+0.000
incoming
Token incoming
Feature activation+0.000
features
Token features
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
RA
TokenRA
Feature activation+0.000
GG
TokenGG
Feature activation+0.000
ED
TokenED
Feature activation+0.000
ED
Token ED
Feature activation+0.000
ved
Tokenved
Feature activation+0.000
it
Token it
Feature activation+0.000
a
Token a
Feature activation+0.000
couple
Token couple
Feature activation+0.000
years
Token years
Feature activation+0.000
ago
Token ago
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
I
Token I
Feature activation+0.000
've
Token've
Feature activation+0.000
decided
Token decided
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 H3.5: (feature 5635)

TOP ACTIVATIONS
MAX = 3.119

not
Token not
Feature activation+0.000
all
Token all
Feature activation+0.124
the
Token the
Feature activation+0.000
paths
Token paths
Feature activation+0.000
are
Token are
Feature activation+0.000
equally
Token equally
Feature activation+3.119
likely
Token likely
Feature activation+0.000
.
Token.
Feature activation+0.000
Winning
Token Winning
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
may
Token may
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
size
Token size
Feature activation+0.000
requires
Token requires
Feature activation+0.210
a
Token a
Feature activation+0.853
different
Token different
Feature activation+3.085
size
Token size
Feature activation+0.000
sole
Token sole
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
used
Token used
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
items
Token items
Feature activation+0.000
have
Token have
Feature activation+0.003
the
Token the
Feature activation+0.485
same
Token same
Feature activation+2.465
value
Token value
Feature activation+0.000
and
Token and
Feature activation+0.040
are
Token are
Feature activation+0.000
mutually
Token mutually
Feature activation+1.262
interchangeable
Token interchangeable
Feature activation+0.530
one
Token one
Feature activation+0.824
time
Token time
Feature activation+0.000
zone
Token zone
Feature activation+0.000
have
Token have
Feature activation+0.310
the
Token the
Feature activation+0.426
same
Token same
Feature activation+2.111
time
Token time
Feature activation+0.261
.
Token.
Feature activation+0.235
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
decided
Token decided
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
all
Tokenall
Feature activation+0.000
men
Token men
Feature activation+0.000
are
Token are
Feature activation+0.000
created
Token created
Feature activation+0.000
equal
Token equal
Feature activation+2.029
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
every
Token every
Feature activation+0.000
company
Token company
Feature activation+0.000
is
Token is
Feature activation+0.000
unique
Token unique
Feature activation+1.964
,
Token,
Feature activation+0.000
almost
Token almost
Feature activation+0.019
all
Token all
Feature activation+0.013
go
Token go
Feature activation+0.000
through
Token through
Feature activation+0.000
of
Token of
Feature activation+0.000
us
Token us
Feature activation+0.000
at
Token at
Feature activation+0.000
Geek
Token Geek
Feature activation+0.000
net
Tokennet
Feature activation+0.000
agree
Token agree
Feature activation+1.726
that
Token that
Feature activation+0.402
this
Token this
Feature activation+0.000
site
Token site
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
every
Token every
Feature activation+0.000
situation
Token situation
Feature activation+0.000
is
Token is
Feature activation+0.000
different
Token different
Feature activation+1.725
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
might
Token might
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
from
Token from
Feature activation+0.000
Belgium
Token Belgium
Feature activation+0.000
,
Token,
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
can
Token can
Feature activation+0.000
chose
Token chose
Feature activation+0.000
his
Token his
Feature activation+1.672
or
Token or
Feature activation+0.000
her
Token her
Feature activation+0.000
partner
Token partner
Feature activation+0.000
,
Token,
Feature activation+0.000
whom
Token whom
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
culture
Token culture
Feature activation+0.000
is
Token is
Feature activation+0.000
equal
Token equal
Feature activation+1.661
âĢĶ
Token âĢĶ
Feature activation+0.000
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
not
Token not
Feature activation+0.000
objectively
Token objectively
Feature activation+0.018
.
Token.
Feature activation+0.000
Every
Token Every
Feature activation+0.000
brewery
Token brewery
Feature activation+0.000
has
Token has
Feature activation+0.000
served
Token served
Feature activation+0.000
some
Token some
Feature activation+1.653
less
Token less
Feature activation+0.571
fortunate
Token fortunate
Feature activation+0.033
or
Token or
Feature activation+0.000
even
Token even
Feature activation+0.000
und
Token und
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
day
Token day
Feature activation+0.000
brings
Token brings
Feature activation+0.000
a
Token a
Feature activation+0.555
new
Token new
Feature activation+1.644
revelation
Token revelation
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
scope
Token scope
Feature activation+0.000
of
Token of
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
at
Token at
Feature activation+0.022
risk
Token risk
Feature activation+0.000
in
Token in
Feature activation+0.000
some
Token some
Feature activation+1.623
way
Token way
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ser
TokenSer
Feature activation+0.000
vers
Tokenvers
Feature activation+0.000
,
Token,
Feature activation+0.000
because
Token because
Feature activation+0.000
every
Token every
Feature activation+0.000
season
Token season
Feature activation+0.000
is
Token is
Feature activation+0.000
different
Token different
Feature activation+1.606
and
Token and
Feature activation+0.001
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
circumstances
Token circumstances
Feature activation+0.000
of
Token of
Feature activation+0.000
every
Token every
Feature activation+0.000
confrontation
Token confrontation
Feature activation+0.000
are
Token are
Feature activation+0.000
different
Token different
Feature activation+1.588
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
B
TokenB
Feature activation+0.000
RI
TokenRI
Feature activation+0.000
item
Token item
Feature activation+0.000
I
Token I
Feature activation+0.000
can
Token can
Feature activation+0.000
give
Token give
Feature activation+0.000
a
Token a
Feature activation+0.532
new
Token new
Feature activation+1.586
purpose
Token purpose
Feature activation+0.000
to
Token to
Feature activation+0.000
is
Token is
Feature activation+0.000
similar
Token similar
Feature activation+1.083
to
Token to
Feature activation+0.000
Every
Token Every
Feature activation+0.000
time
Token time
Feature activation+0.000
they
Token they
Feature activation+0.000
launch
Token launch
Feature activation+0.000
a
Token a
Feature activation+0.660
new
Token new
Feature activation+1.559
game
Token game
Feature activation+0.017
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.249
s
Tokens
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
table
Token table
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
similar
Token similar
Feature activation+1.536
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
chips
Token chips
Feature activation+0.000
at
Token at
Feature activation+0.000
round
Token round
Feature activation+0.000
can
Token can
Feature activation+0.000
find
Token find
Feature activation+0.000
rape
Token rape
Feature activation+0.000
clubs
Token clubs
Feature activation+0.000
,
Token,
Feature activation+0.067
some
Token some
Feature activation+1.501
of
Token of
Feature activation+0.023
them
Token them
Feature activation+0.000
dating
Token dating
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+0.000
characters
Token characters
Feature activation+0.000
exist
Token exist
Feature activation+0.000
out
Token out
Feature activation+0.000
there
Token there
Feature activation+0.258
,
Token,
Feature activation+0.000
somewhere
Token somewhere
Feature activation+1.491
,
Token,
Feature activation+0.035
for
Token for
Feature activation+0.056
real
Token real
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 3.451

are
Token are
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
Second
Token Second
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
not
Token not
Feature activation+0.075
Top resid features:
all
Token all
Feature activation+3.451
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
paths
Token paths
Feature activation+0.004
Top resid features:
are
Token are
Feature activation+0.003
Top resid features:
equally
Token equally
Feature activation+0.072
Top resid features:
likely
Token likely
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.175
Top resid features:
that
Token that
Feature activation+0.026
Top resid features:
every
Token every
Feature activation+3.428
Top resid features:
size
Token size
Feature activation-0.009
Top resid features:
requires
Token requires
Feature activation+0.034
Top resid features:
a
Token a
Feature activation+0.076
Top resid features:
different
Token different
Feature activation+0.026
Top resid features:
size
Token size
Feature activation+0.000
Top resid features:
ible
Tokenible
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
if
Token if
Feature activation+0.008
Top resid features:
all
Token all
Feature activation+2.681
Top resid features:
of
Token of
Feature activation+0.117
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
items
Token items
Feature activation-0.011
Top resid features:
have
Token have
Feature activation-0.022
Top resid features:
the
Token the
Feature activation+0.051
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.155
Top resid features:
time
Token time
Feature activation+0.003
Top resid features:
zones
Token zones
Feature activation+0.022
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
All
Token All
Feature activation+2.296
Top resid features:
places
Token places
Feature activation+0.082
Top resid features:
within
Token within
Feature activation+0.103
Top resid features:
one
Token one
Feature activation+0.004
Top resid features:
time
Token time
Feature activation+0.003
Top resid features:
zone
Token zone
Feature activation+0.011
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
phrase
Token phrase
Feature activation+0.010
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
âĢ
Token âĢ
Feature activation-0.003
Top resid features:
ľ
Tokenľ
Feature activation+0.004
Top resid features:
all
Tokenall
Feature activation+2.432
Top resid features:
men
Token men
Feature activation+0.142
Top resid features:
are
Token are
Feature activation+0.019
Top resid features:
created
Token created
Feature activation+0.001
Top resid features:
equal
Token equal
Feature activation+0.055
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
phases
Token phases
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
While
TokenWhile
Feature activation+0.085
Top resid features:
every
Token every
Feature activation+2.328
Top resid features:
company
Token company
Feature activation+0.009
Top resid features:
is
Token is
Feature activation+0.019
Top resid features:
unique
Token unique
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
almost
Token almost
Feature activation+0.000
Top resid features:
on
Token on
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Since
TokenSince
Feature activation-0.079
Top resid features:
all
Token all
Feature activation+1.721
Top resid features:
of
Token of
Feature activation+0.286
Top resid features:
us
Token us
Feature activation+0.255
Top resid features:
at
Token at
Feature activation+0.048
Top resid features:
Geek
Token Geek
Feature activation-0.012
Top resid features:
net
Tokennet
Feature activation-0.017
Top resid features:
our
Token our
Feature activation+0.002
Top resid features:
fictional
Token fictional
Feature activation-0.012
Top resid features:
family
Token family
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
While
Token While
Feature activation+0.035
Top resid features:
every
Token every
Feature activation+2.179
Top resid features:
situation
Token situation
Feature activation-0.002
Top resid features:
is
Token is
Feature activation+0.022
Top resid features:
different
Token different
Feature activation+0.042
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
'
Token'
Feature activation-0.011
Top resid features:
In
TokenIn
Feature activation-0.000
Top resid features:
Belgium
Token Belgium
Feature activation-0.023
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
everyone
Token everyone
Feature activation+2.065
Top resid features:
can
Token can
Feature activation+0.040
Top resid features:
chose
Token chose
Feature activation-0.009
Top resid features:
his
Token his
Feature activation+0.111
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.030
Top resid features:
multicultural
Token multicultural
Feature activation+0.016
Top resid features:
ism
Tokenism
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
that
Token that
Feature activation+0.017
Top resid features:
every
Token every
Feature activation+2.006
Top resid features:
culture
Token culture
Feature activation+0.045
Top resid features:
is
Token is
Feature activation+0.032
Top resid features:
equal
Token equal
Feature activation+0.055
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
Bore
Token Bore
Feature activation-0.001
Top resid features:
fts
Tokenfts
Feature activation-0.004
Top resid features:
at
Token at
Feature activation-0.002
Top resid features:
all
Token all
Feature activation+0.058
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Every
Token Every
Feature activation+1.809
Top resid features:
brewery
Token brewery
Feature activation+0.060
Top resid features:
has
Token has
Feature activation+0.024
Top resid features:
served
Token served
Feature activation+0.085
Top resid features:
some
Token some
Feature activation+0.097
Top resid features:
less
Token less
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:
It
TokenIt
Feature activation+0.002
Top resid features:
seems
Token seems
Feature activation+0.028
Top resid features:
that
Token that
Feature activation+0.019
Top resid features:
every
Token every
Feature activation+1.831
Top resid features:
day
Token day
Feature activation+0.162
Top resid features:
brings
Token brings
Feature activation+0.040
Top resid features:
a
Token a
Feature activation+0.080
Top resid features:
new
Token new
Feature activation-0.009
Top resid features:
revelation
Token revelation
Feature activation+0.000
Top resid features:
affected
Token affected
Feature activation-0.003
Top resid features:
-
Token -
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
experts
Token experts
Feature activation+0.029
Top resid features:
say
Token say
Feature activation+0.008
Top resid features:
all
Token all
Feature activation+1.821
Top resid features:
web
Token web
Feature activation+0.013
Top resid features:
users
Token users
Feature activation+0.007
Top resid features:
will
Token will
Feature activation+0.020
Top resid features:
be
Token be
Feature activation+0.015
Top resid features:
at
Token at
Feature activation+0.008
Top resid features:
Not
Token Not
Feature activation+0.013
Top resid features:
one
Token one
Feature activation-0.013
Top resid features:
bit
Token bit
Feature activation-0.006
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
because
Token because
Feature activation+0.006
Top resid features:
every
Token every
Feature activation+2.037
Top resid features:
season
Token season
Feature activation+0.031
Top resid features:
is
Token is
Feature activation+0.041
Top resid features:
different
Token different
Feature activation+0.035
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
es
Tokenes
Feature activation-0.000
Top resid features:
said
Token said
Feature activation+0.019
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
circumstances
Token circumstances
Feature activation-0.091
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
every
Token every
Feature activation+2.148
Top resid features:
confrontation
Token confrontation
Feature activation-0.007
Top resid features:
are
Token are
Feature activation+0.018
Top resid features:
different
Token different
Feature activation+0.034
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
H
TokenH
Feature activation+0.002
Top resid features:
mmm
Tokenmmm
Feature activation-0.005
Top resid features:
...
Token...
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Every
TokenEvery
Feature activation+2.007
Top resid features:
item
Token item
Feature activation-0.009
Top resid features:
I
Token I
Feature activation+0.017
Top resid features:
can
Token can
Feature activation+0.041
Top resid features:
give
Token give
Feature activation-0.013
Top resid features:
a
Token a
Feature activation+0.078
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.178
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Every
Token Every
Feature activation+1.989
Top resid features:
time
Token time
Feature activation-0.069
Top resid features:
they
Token they
Feature activation+0.021
Top resid features:
launch
Token launch
Feature activation+0.065
Top resid features:
a
Token a
Feature activation+0.078
Top resid features:
new
Token new
Feature activation-0.033
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
It
TokenIt
Feature activation+0.015
Top resid features:
ought
Token ought
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
mean
Token mean
Feature activation-0.009
Top resid features:
all
Token all
Feature activation+1.838
Top resid features:
teams
Token teams
Feature activation+0.031
Top resid features:
come
Token come
Feature activation+0.015
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
table
Token table
Feature activation+0.014
Top resid features:
clubs
Token clubs
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
On
TokenOn
Feature activation+0.003
Top resid features:
almost
Token almost
Feature activation+0.120
Top resid features:
every
Token every
Feature activation+1.659
Top resid features:
college
Token college
Feature activation+0.007
Top resid features:
campus
Token campus
Feature activation+0.033
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
you
Token you
Feature activation+0.047
Top resid features:
can
Token can
Feature activation+0.037
Top resid features:
Real
Token Real
Feature activation+0.002
Top resid features:
ism
Tokenism
Feature activation+0.001
Top resid features:
that
Token that
Feature activation+0.016
Top resid features:
asserts
Token asserts
Feature activation+0.005
Top resid features:
that
Token that
Feature activation+0.021
Top resid features:
all
Token all
Feature activation+1.743
Top resid features:
fictional
Token fictional
Feature activation-0.001
Top resid features:
characters
Token characters
Feature activation-0.001
Top resid features:
exist
Token exist
Feature activation+0.047
Top resid features:
out
Token out
Feature activation+0.073
Top resid features:
there
Token there
Feature activation+0.014
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.04

Head 2: 0.05

Head 3: 0.03

Head 4: 0.03

Head 5: 0.48

Head 6: 0.05

Head 7: 0.04

Head 8: 0.04

Head 9: 0.05

Head 10: 0.07

Head 11: 0.09

Positive logits

each2.02

umerable1.95

collectively1.94

selves1.94

pmwiki1.88

annabin1.87

ifiable1.87

acters1.86

respective1.86

nces1.85

individually1.83

soever1.83

estine1.79

except1.79

utations1.77

okemon1.76

ements1.72

estial1.72

measurable1.72

ixture1.70

Negative logits

aggravated-1.73

blackmail-1.73

angered-1.71

escalated-1.67

surfaced-1.63

escalate-1.63

abruptly-1.62

-1.59

deputy-1.57

reopened-1.57

cut-1.56

captcha-1.55

shortly-1.55

redirect-1.54

spying-1.54

retrieving-1.54

opener-1.53

deputies-1.53

provoked-1.50

ASA-1.49

INTERVAL 2.807 - 3.119
CONTAINS 0.000%

that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
size
Token size
Feature activation+0.000
requires
Token requires
Feature activation+0.210
a
Token a
Feature activation+0.853
different
Token different
Feature activation+3.085
size
Token size
Feature activation+0.000
sole
Token sole
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
used
Token used
Feature activation+0.000
not
Token not
Feature activation+0.000
all
Token all
Feature activation+0.124
the
Token the
Feature activation+0.000
paths
Token paths
Feature activation+0.000
are
Token are
Feature activation+0.000
equally
Token equally
Feature activation+3.119
likely
Token likely
Feature activation+0.000
.
Token.
Feature activation+0.000
Winning
Token Winning
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
may
Token may
Feature activation+0.000

INTERVAL 2.495 - 2.807
CONTAINS 0.000%

INTERVAL 2.183 - 2.495
CONTAINS 0.000%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
items
Token items
Feature activation+0.000
have
Token have
Feature activation+0.003
the
Token the
Feature activation+0.485
same
Token same
Feature activation+2.465
value
Token value
Feature activation+0.000
and
Token and
Feature activation+0.040
are
Token are
Feature activation+0.000
mutually
Token mutually
Feature activation+1.262
interchangeable
Token interchangeable
Feature activation+0.530

INTERVAL 1.871 - 2.183
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
every
Token every
Feature activation+0.000
company
Token company
Feature activation+0.000
is
Token is
Feature activation+0.000
unique
Token unique
Feature activation+1.964
,
Token,
Feature activation+0.000
almost
Token almost
Feature activation+0.019
all
Token all
Feature activation+0.013
go
Token go
Feature activation+0.000
through
Token through
Feature activation+0.000
one
Token one
Feature activation+0.824
time
Token time
Feature activation+0.000
zone
Token zone
Feature activation+0.000
have
Token have
Feature activation+0.310
the
Token the
Feature activation+0.426
same
Token same
Feature activation+2.111
time
Token time
Feature activation+0.261
.
Token.
Feature activation+0.235
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
decided
Token decided
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
all
Tokenall
Feature activation+0.000
men
Token men
Feature activation+0.000
are
Token are
Feature activation+0.000
created
Token created
Feature activation+0.000
equal
Token equal
Feature activation+2.029
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.000

INTERVAL 1.559 - 1.871
CONTAINS 0.001%

Belgium
Token Belgium
Feature activation+0.000
,
Token,
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
can
Token can
Feature activation+0.000
chose
Token chose
Feature activation+0.000
his
Token his
Feature activation+1.672
or
Token or
Feature activation+0.000
her
Token her
Feature activation+0.000
partner
Token partner
Feature activation+0.000
,
Token,
Feature activation+0.000
whom
Token whom
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
day
Token day
Feature activation+0.000
brings
Token brings
Feature activation+0.000
a
Token a
Feature activation+0.555
new
Token new
Feature activation+1.644
revelation
Token revelation
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
scope
Token scope
Feature activation+0.000
of
Token of
Feature activation+0.000
of
Token of
Feature activation+0.000
us
Token us
Feature activation+0.000
at
Token at
Feature activation+0.000
Geek
Token Geek
Feature activation+0.000
net
Tokennet
Feature activation+0.000
agree
Token agree
Feature activation+1.726
that
Token that
Feature activation+0.402
this
Token this
Feature activation+0.000
site
Token site
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
While
Token While
Feature activation+0.000
every
Token every
Feature activation+0.000
situation
Token situation
Feature activation+0.000
is
Token is
Feature activation+0.000
different
Token different
Feature activation+1.725
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
might
Token might
Feature activation+0.000
benefit
Token benefit
Feature activation+0.000
from
Token from
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
culture
Token culture
Feature activation+0.000
is
Token is
Feature activation+0.000
equal
Token equal
Feature activation+1.661
âĢĶ
Token âĢĶ
Feature activation+0.000
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
not
Token not
Feature activation+0.000
objectively
Token objectively
Feature activation+0.018

INTERVAL 1.248 - 1.559
CONTAINS 0.002%

all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
us
Token us
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.316
just
Token just
Feature activation+1.352
the
Token the
Feature activation+0.000
1
Token 1
Feature activation+0.072
percent
Token percent
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
handled
Token handled
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+1.414
processor
Token processor
Feature activation+0.000
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
running
Token running
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.485
same
Token same
Feature activation+2.465
value
Token value
Feature activation+0.000
and
Token and
Feature activation+0.040
are
Token are
Feature activation+0.000
mutually
Token mutually
Feature activation+1.262
interchangeable
Token interchangeable
Feature activation+0.530
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
example
Token example
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
urge
Token urge
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
both
Token both
Feature activation+1.446
critics
Token critics
Feature activation+0.000
and
Token and
Feature activation+0.002
supporters
Token supporters
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.239
facing
Token facing
Feature activation+0.000
outsourcing
Token outsourcing
Feature activation+0.000
when
Token when
Feature activation+0.000
we
Token we
Feature activation+0.000
all
Token all
Feature activation+0.000
agree
Token agree
Feature activation+1.331
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.936 - 1.248
CONTAINS 0.004%

can
Token can
Feature activation+0.000
use
Token use
Feature activation+0.000
Skype
Token Skype
Feature activation+0.245
just
Token just
Feature activation+0.306
with
Token with
Feature activation+0.000
their
Token their
Feature activation+1.060
mobile
Token mobile
Feature activation+0.000
number
Token number
Feature activation+0.000
.
Token.
Feature activation+0.039
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ber
TokenBer
Feature activation+0.000
belongs
Token belongs
Feature activation+0.000
to
Token to
Feature activation+0.000
all
Token all
Feature activation+0.000
Berlin
Token Berlin
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
alike
Token alike
Feature activation+1.048
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
can
Token can
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
possibilities
Token possibilities
Feature activation+0.000
that
Token that
Feature activation+0.000
all
Token all
Feature activation+0.000
followed
Token followed
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+1.108
theme
Token theme
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
ways
Tokenways
Feature activation+0.000
X
Token X
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
there
Token there
Feature activation+0.602
is
Token is
Feature activation+0.148
a
Token a
Feature activation+1.216
âĢ
Token âĢ
Feature activation+0.104
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.096
ath
Tokenath
Feature activation+0.000
starts
Token starts
Feature activation+0.037
out
Token out
Feature activation+0.000
with
Token with
Feature activation+0.062
roughly
Token roughly
Feature activation+0.126
equal
Token equal
Feature activation+1.104
resources
Token resources
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

INTERVAL 0.624 - 0.936
CONTAINS 0.008%

ro
Token ro
Feature activation+0.000
sy
Tokensy
Feature activation+0.000
economic
Token economic
Feature activation+0.000
projections
Token projections
Feature activation+0.000
,
Token,
Feature activation+0.000
none
Token none
Feature activation+0.681
of
Token of
Feature activation+0.000
which
Token which
Feature activation+0.000
has
Token has
Feature activation+0.000
come
Token come
Feature activation+0.000
true
Token true
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
included
Token included
Feature activation+0.000
,
Token,
Feature activation+0.000
involve
Token involve
Feature activation+0.023
opening
Token opening
Feature activation+0.000
one
Token one
Feature activation+0.644
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
mind
Token mind
Feature activation+0.000
up
Token up
Feature activation+0.000
body
Tokenbody
Feature activation+0.000
around
Token around
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
knows
Token knows
Feature activation+0.292
he
Token he
Feature activation+0.888
's
Token's
Feature activation+0.430
not
Token not
Feature activation+0.396
stable
Token stable
Feature activation+0.058
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
size
Token size
Feature activation+0.000
requires
Token requires
Feature activation+0.210
a
Token a
Feature activation+0.853
different
Token different
Feature activation+3.085
size
Token size
Feature activation+0.000
sole
Token sole
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
nation
Token nation
Feature activation+0.000
should
Token should
Feature activation+0.000
have
Token have
Feature activation+0.000
an
Token an
Feature activation+0.689
opportunity
Token opportunity
Feature activation+0.206
to
Token to
Feature activation+0.202
participate
Token participate
Feature activation+0.119
in
Token in
Feature activation+0.021
a
Token a
Feature activation+0.787

INTERVAL 0.312 - 0.624
CONTAINS 0.025%

be
Token be
Feature activation+0.059
in
Token in
Feature activation+0.129
violation
Token violation
Feature activation+0.163
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.336
amendment
Token amendment
Feature activation+0.000
,
Token,
Feature activation+0.060
and
Token and
Feature activation+0.127
a
Token a
Feature activation+0.255
fifth
Token fifth
Feature activation+0.380
discontin
Token discontin
Feature activation+0.000
u
Tokenu
Feature activation+0.000
ities
Tokenities
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.501
thousand
Token thousand
Feature activation+0.000
examples
Token examples
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
an
Token an
Feature activation+0.000
inter
Token inter
Feature activation+0.000
related
Tokenrelated
Feature activation+0.000
ideas
Token ideas
Feature activation+0.000
through
Token through
Feature activation+0.000
which
Token which
Feature activation+0.000
we
Token we
Feature activation+0.358
interpret
Token interpret
Feature activation+0.000
information
Token information
Feature activation+0.000
and
Token and
Feature activation+0.000
communication
Token communication
Feature activation+0.000
.
Token.
Feature activation+0.118
data
Token data
Feature activation+0.000
pack
Token pack
Feature activation+0.000
together
Token together
Feature activation+0.325
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
one
Token one
Feature activation+0.617
unstoppable
Token unstoppable
Feature activation+0.000
god
Token god
Feature activation+0.000
-
Token-
Feature activation+0.000
deck
Tokendeck
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
bottles
Token bottles
Feature activation+0.000
ranged
Token ranged
Feature activation+0.000
from
Token from
Feature activation+0.000
12
Token 12
Feature activation+0.326
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
to
Token to
Feature activation+0.000
13
Token 13
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.312
CONTAINS 99.961%

In
TokenIn
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
those
Token those
Feature activation+0.000
things
Token things
Feature activation+0.000
are
Token are
Feature activation+0.000
complementary
Token complementary
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.000
contradictory
Token contradictory
Feature activation+0.000
.
Token.
Feature activation+0.000
for
Token for
Feature activation+0.000
reelection
Token reelection
Feature activation+0.000
in
Token in
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Church
TokenChurch
Feature activation+0.000
and
Token and
Feature activation+0.000
state
Token state
Feature activation+0.000
separated
Token separated
Feature activation+0.000
despite
Token despite
Feature activation+0.000
having
Token having
Feature activation+0.000
passed
Token passed
Feature activation+0.000
away
Token away
Feature activation+0.000
,
Token,
Feature activation+0.000
still
Token still
Feature activation+0.000
command
Token command
Feature activation+0.000
influence
Token influence
Feature activation+0.000
;
Token;
Feature activation+0.000
next
Token next
Feature activation+0.000
are
Token are
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
observer
Token observer
Feature activation+0.000
of
Token of
Feature activation+0.000
what
Token what
Feature activation+0.000
has
Token has
Feature activation+0.000
happened
Token happened
Feature activation+0.000
this
Token this
Feature activation+0.000
week
Token week
Feature activation+0.000
must
Token must
Feature activation+0.468
appreciate
Token appreciate
Feature activation+0.000
the
Token the
Feature activation+0.000
latest
Token latest
Feature activation+0.000
reincarn
Token reincarn
Feature activation+0.000
ation
Tokenation
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
savior
Token savior
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 3 in H3.5: (feature 15285)

TOP ACTIVATIONS
MAX = 3.561

Listen
Token Listen
Feature activation+0.307
to
Token to
Feature activation+0.000
them
Token them
Feature activation+0.000
first
Token first
Feature activation+0.000
.
Token.
Feature activation+0.018
Then
Token Then
Feature activation+3.561
,
Token,
Feature activation+0.120
after
Token after
Feature activation+0.734
they
Token they
Feature activation+0.000
're
Token're
Feature activation+0.000
all
Token all
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
full
Token full
Feature activation+0.000
fitness
Token fitness
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+3.296
improve
Token improve
Feature activation+0.000
the
Token the
Feature activation+0.000
bike
Token bike
Feature activation+0.000
step
Token step
Feature activation+0.000
-
Token-
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Towers
Token Towers
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+3.187
to
Token to
Feature activation+0.064
become
Token become
Feature activation+0.341
aware
Token aware
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
scanned
Token scanned
Feature activation+0.000
the
Token the
Feature activation+0.000
metal
Token metal
Feature activation+0.000
box
Token box
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+3.078
took
Token took
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
building
Token building
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
set
Token set
Feature activation+0.000
date
Token date
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+2.760
we
Token we
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
paintings
Token paintings
Feature activation+0.000
and
Token and
Feature activation+0.000
first
Token first
Feature activation+0.000
Amendment
Token Amendment
Feature activation+0.000
fallen
Token fallen
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+2.675
and
Token and
Feature activation+0.000
those
Token those
Feature activation+0.000
that
Token that
Feature activation+0.000
follow
Token follow
Feature activation+0.000
can
Token can
Feature activation+0.000
healthy
Token healthy
Feature activation+0.000
and
Token and
Feature activation+0.000
abundant
Token abundant
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
second
Token second
Feature activation+2.610
basket
Token basket
Feature activation+0.000
rests
Token rests
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
of
Token of
Feature activation+0.000
passing
Token passing
Feature activation+0.000
repeal
Token repeal
Feature activation+0.000
first
Token first
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+2.528
separately
Token separately
Feature activation+0.000
working
Token working
Feature activation+0.000
on
Token on
Feature activation+0.000
replacement
Token replacement
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+0.000
Wyoming
Token Wyoming
Feature activation+0.000
and
Token and
Feature activation+0.000
Montana
Token Montana
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+2.433
more
Token more
Feature activation+0.170
challenges
Token challenges
Feature activation+0.012
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
drilling
Token drilling
Feature activation+0.000
s
Tokens
Feature activation+0.000
tv
Token tv
Feature activation+0.000
show
Token show
Feature activation+0.000
simulator
Token simulator
Feature activation+0.000
but
Token but
Feature activation+0.275
then
Token then
Feature activation+2.393
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
not
Token not
Feature activation+0.000
appeal
Token appeal
Feature activation+0.000
to
Token to
Feature activation+0.000
First
Token First
Feature activation+0.000
we
Token we
Feature activation+0.000
guess
Token guess
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+2.291
we
Token we
Feature activation+0.000
compute
Token compute
Feature activation+0.000
the
Token the
Feature activation+0.000
consequences
Token consequences
Feature activation+0.000
of
Token of
Feature activation+0.000
capabilities
Token capabilities
Feature activation+0.000
built
Token built
Feature activation+0.000
in
Token in
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.173
second
Token second
Feature activation+2.263
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
attach
Token attach
Feature activation+0.000
a
Token a
Feature activation+0.000
printer
Token printer
Feature activation+0.000
everything
Token everything
Feature activation+0.000
continue
Token continue
Feature activation+0.000
its
Token its
Feature activation+0.000
course
Token course
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+2.222
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
reported
Token reported
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
the
Token the
Feature activation+0.000
fragments
Token fragments
Feature activation+0.000
bearing
Token bearing
Feature activation+0.000
the
Token the
Feature activation+0.000
structures
Token structures
Feature activation+0.000
then
Token then
Feature activation+1.953
s
Token s
Feature activation+0.000
ieved
Tokenieved
Feature activation+0.000
to
Token to
Feature activation+0.000
concentrate
Token concentrate
Feature activation+0.000
parts
Token parts
Feature activation+0.000
of
Token of
Feature activation+0.000
unemployed
Token unemployed
Feature activation+0.000
workers
Token workers
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.390
then
Token then
Feature activation+1.938
came
Token came
Feature activation+0.316
the
Token the
Feature activation+0.151
first
Token first
Feature activation+0.000
factory
Token factory
Feature activation+0.000
occupations
Token occupations
Feature activation+0.000
itated
Tokenitated
Feature activation+0.000
King
Token King
Feature activation+0.000
Fah
Token Fah
Feature activation+0.000
d
Tokend
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+1.929
as
Token as
Feature activation+0.000
king
Token king
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
own
Token own
Feature activation+0.000
ging
Tokenging
Feature activation+0.000
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
Tories
Token Tories
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+1.880
bulldo
Token bulldo
Feature activation+0.000
zing
Tokenzing
Feature activation+0.000
Labour
Token Labour
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
%
Token %
Feature activation+0.000
Desktop
TokenDesktop
Feature activation+0.000
%
Token%
Feature activation+0.000
first
Token first
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+1.876
encrypt
Token encrypt
Feature activation+0.000
other
Token other
Feature activation+0.001
folders
Token folders
Feature activation+0.000
.
Token.
Feature activation+0.077
The
Token The
Feature activation+0.048
see
Token see
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
place
Token place
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+1.786
you
Token you
Feature activation+0.000
negotiate
Token negotiate
Feature activation+0.000
later
Token later
Feature activation+0.191
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Free
Token Free
Feature activation+0.000
Syrian
Token Syrian
Feature activation+0.000
Army
Token Army
Feature activation+0.000
,
Token,
Feature activation+0.000
switched
Token switched
Feature activation+0.000
then
Token then
Feature activation+1.711
to
Token to
Feature activation+0.000
Al
Token Al
Feature activation+0.000
-
Token-
Feature activation+0.000
Nusra
TokenNusra
Feature activation+0.000
and
Token and
Feature activation+0.000

Top DFA by src position
MAX = 3.615

you
Token you
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Listen
Token Listen
Feature activation+0.028
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
them
Token them
Feature activation+0.018
Top resid features:
first
Token first
Feature activation+3.030
Top resid features:
.
Token.
Feature activation+0.052
Top resid features:
Then
Token Then
Feature activation+0.163
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
after
Token after
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.059
Top resid features:
step
Token step
Feature activation+0.011
Top resid features:
at
Token at
Feature activation+0.004
Top resid features:
time
Token time
Feature activation+0.020
Top resid features:
-
Token -
Feature activation+0.021
Top resid features:
first
Token first
Feature activation+3.589
Top resid features:
to
Token to
Feature activation+0.037
Top resid features:
get
Token get
Feature activation+0.017
Top resid features:
full
Token full
Feature activation-0.002
Top resid features:
fitness
Token fitness
Feature activation+0.021
Top resid features:
and
Token and
Feature activation-0.072
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
it
Token it
Feature activation-0.006
Top resid features:
is
Token is
Feature activation-0.003
Top resid features:
helpful
Token helpful
Feature activation-0.002
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
first
Token first
Feature activation+3.615
Top resid features:
have
Token have
Feature activation+0.024
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
basic
Token basic
Feature activation+0.010
Top resid features:
understanding
Token understanding
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
home
Token home
Feature activation-0.001
Top resid features:
early
Token early
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
while
Token while
Feature activation+0.025
Top resid features:
officers
Token officers
Feature activation-0.001
Top resid features:
first
Token first
Feature activation+3.467
Top resid features:
scanned
Token scanned
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
metal
Token metal
Feature activation+0.002
Top resid features:
box
Token box
Feature activation-0.003
Top resid features:
and
Token and
Feature activation-0.025
Top resid features:
as
Token as
Feature activation+0.003
Top resid features:
he
Token he
Feature activation-0.002
Top resid features:
explains
Token explains
Feature activation-0.002
Top resid features:
:
Token:
Feature activation-0.002
Top resid features:
"
Token "
Feature activation-0.020
Top resid features:
First
TokenFirst
Feature activation+3.209
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:
all
Token all
Feature activation+0.005
Top resid features:
we
Token we
Feature activation-0.000
Top resid features:
can
Token can
Feature activation+0.002
Top resid features:
look
Token look
Feature activation-0.005
Top resid features:
safe
Token safe
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.033
Top resid features:
For
Token For
Feature activation+0.016
Top resid features:
with
Token with
Feature activation-0.012
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
first
Token first
Feature activation+2.998
Top resid features:
Amendment
Token Amendment
Feature activation+0.004
Top resid features:
fallen
Token fallen
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+0.087
Top resid features:
the
Token the
Feature activation-0.073
Top resid features:
second
Token second
Feature activation+0.231
Top resid features:
In
TokenIn
Feature activation+0.007
Top resid features:
this
Token this
Feature activation-0.002
Top resid features:
model
Token model
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
first
Token first
Feature activation+3.056
Top resid features:
basket
Token basket
Feature activation+0.002
Top resid features:
represents
Token represents
Feature activation+0.016
Top resid features:
earth
Token earth
Feature activation-0.011
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
idea
Token idea
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
passing
Token passing
Feature activation-0.002
Top resid features:
repeal
Token repeal
Feature activation+0.020
Top resid features:
first
Token first
Feature activation+2.952
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
then
Token then
Feature activation+0.131
Top resid features:
separately
Token separately
Feature activation+0.000
Top resid features:
working
Token working
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
methane
Token methane
Feature activation-0.001
Top resid features:
rule
Token rule
Feature activation-0.003
Top resid features:
land
Token land
Feature activation-0.006
Top resid features:
.
Token.
Feature activation+0.038
Top resid features:
First
Token First
Feature activation+2.804
Top resid features:
came
Token came
Feature activation+0.097
Top resid features:
challenges
Token challenges
Feature activation-0.004
Top resid features:
from
Token from
Feature activation+0.006
Top resid features:
drill
Token drill
Feature activation-0.006
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
color
Token color
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
game
Token game
Feature activation-0.002
Top resid features:
at
Token at
Feature activation+0.001
Top resid features:
first
Token first
Feature activation+2.919
Top resid features:
was
Token was
Feature activation+0.071
Top resid features:
going
Token going
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.015
Top resid features:
be
Token be
Feature activation+0.018
Top resid features:
a
Token a
Feature activation-0.010
Top resid features:
by
Token by
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
following
Token following
Feature activation+0.026
Top resid features:
process
Token process
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
First
Token First
Feature activation+2.772
Top resid features:
we
Token we
Feature activation+0.015
Top resid features:
guess
Token guess
Feature activation-0.158
Top resid features:
it
Token it
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.049
Top resid features:
Then
Token Then
Feature activation+0.165
Top resid features:
on
Token on
Feature activation-0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
network
Token network
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
The
Token The
Feature activation+0.010
Top resid features:
first
Token first
Feature activation+2.561
Top resid features:
is
Token is
Feature activation+0.064
Top resid features:
to
Token to
Feature activation+0.016
Top resid features:
use
Token use
Feature activation-0.001
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
printer
Token printer
Feature activation-0.001
Top resid features:
uther
Tokenuther
Feature activation-0.003
Top resid features:
an
Tokenan
Feature activation-0.001
Top resid features:
scandal
Token scandal
Feature activation+0.001
Top resid features:
',
Token',
Feature activation+0.002
Top resid features:
at
Token at
Feature activation+0.003
Top resid features:
first
Token first
Feature activation+2.397
Top resid features:
I
Token I
Feature activation+0.030
Top resid features:
let
Token let
Feature activation+0.290
Top resid features:
everything
Token everything
Feature activation+0.015
Top resid features:
continue
Token continue
Feature activation-0.006
Top resid features:
its
Token its
Feature activation-0.004
Top resid features:
ret
Tokenret
Feature activation-0.000
Top resid features:
aceous
Tokenaceous
Feature activation-0.000
Top resid features:
beast
Token beast
Feature activation-0.003
Top resid features:
ies
Tokenies
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
first
Token first
Feature activation+2.496
Top resid features:
they
Token they
Feature activation-0.002
Top resid features:
had
Token had
Feature activation+0.052
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
be
Token be
Feature activation+0.006
Top resid features:
dem
Token dem
Feature activation+0.003
Top resid features:
factories
Token factories
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
The
TokenThe
Feature activation+0.009
Top resid features:
first
Token first
Feature activation+2.391
Top resid features:
response
Token response
Feature activation+0.024
Top resid features:
came
Token came
Feature activation+0.095
Top resid features:
from
Token from
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
organizations
Token organizations
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
ruling
Token ruling
Feature activation-0.008
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
kingdom
Token kingdom
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
first
Token first
Feature activation+2.235
Top resid features:
as
Token as
Feature activation+0.042
Top resid features:
crown
Token crown
Feature activation-0.003
Top resid features:
prince
Token prince
Feature activation-0.005
Top resid features:
filling
Token filling
Feature activation-0.004
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.156
Top resid features:
Ļ
TokenĻ
Feature activation-0.001
Top resid features:
s
Tokens
Feature activation-0.008
Top resid features:
history
Token history
Feature activation-0.015
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
first
Token first
Feature activation+2.396
Top resid features:
ed
Token ed
Feature activation+0.033
Top resid features:
ging
Tokenging
Feature activation+0.013
Top resid features:
out
Token out
Feature activation-0.025
Top resid features:
the
Token the
Feature activation-0.012
Top resid features:
Tories
Token Tories
Feature activation-0.045
Top resid features:
target
Token target
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
%
Token %
Feature activation+0.009
Top resid features:
Desktop
TokenDesktop
Feature activation-0.008
Top resid features:
%
Token%
Feature activation-0.011
Top resid features:
first
Token first
Feature activation+2.159
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
then
Token then
Feature activation+0.168
Top resid features:
encrypt
Token encrypt
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
folders
Token folders
Feature activation+0.000
Top resid features:
permanent
Token permanent
Feature activation-0.000
Top resid features:
part
Token part
Feature activation+0.005
Top resid features:
has
Token has
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.006
Top resid features:
come
Token come
Feature activation+0.005
Top resid features:
first
Token first
Feature activation+2.243
Top resid features:
,
Token,
Feature activation+0.024
Top resid features:
you
Token you
Feature activation-0.018
Top resid features:
see
Token see
Feature activation+0.040
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
that
Token that
Feature activation+0.024
Top resid features:
stated
Token stated
Feature activation+0.024
Top resid features:
that
Token that
Feature activation+0.016
Top resid features:
he
Token he
Feature activation+0.001
Top resid features:
joined
Token joined
Feature activation+0.011
Top resid features:
at
Token at
Feature activation+0.004
Top resid features:
first
Token first
Feature activation+1.985
Top resid features:
the
Token the
Feature activation+0.020
Top resid features:
Free
Token Free
Feature activation-0.006
Top resid features:
Syrian
Token Syrian
Feature activation+0.000
Top resid features:
Army
Token Army
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.073
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.06

Head 3: 0.02

Head 4: 0.03

Head 5: 0.46

Head 6: 0.07

Head 7: 0.04

Head 8: 0.05

Head 9: 0.05

Head 10: 0.09

Head 11: 0.06

Positive logits

preceded1.83

cific1.83

followed1.82

byn1.73

Weeks1.71

illin1.65

ciation1.65

ophy1.57

diarr1.56

Ashton1.56

Vag1.55

romy1.54

ussion1.54

loosely1.53

Groups1.53

ften1.53

Modern1.53

osterone1.52

oyer1.52

oti1.51

Negative logits

quir-1.85

safest-1.84

steals-1.72

auder-1.71

VIDIA-1.66

equipped-1.66

shielded-1.66

NetMessage-1.65

puter-1.65

vending-1.63

Silver-1.63

safer-1.62

saf-1.60

estate-1.60

Featured-1.60

hover-1.60

LAND-1.60

limits-1.60

awaru-1.59

.$-1.59

INTERVAL 3.205 - 3.561
CONTAINS 0.000%

Listen
Token Listen
Feature activation+0.307
to
Token to
Feature activation+0.000
them
Token them
Feature activation+0.000
first
Token first
Feature activation+0.000
.
Token.
Feature activation+0.018
Then
Token Then
Feature activation+3.561
,
Token,
Feature activation+0.120
after
Token after
Feature activation+0.734
they
Token they
Feature activation+0.000
're
Token're
Feature activation+0.000
all
Token all
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.000
full
Token full
Feature activation+0.000
fitness
Token fitness
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+3.296
improve
Token improve
Feature activation+0.000
the
Token the
Feature activation+0.000
bike
Token bike
Feature activation+0.000
step
Token step
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 2.849 - 3.205
CONTAINS 0.000%

scanned
Token scanned
Feature activation+0.000
the
Token the
Feature activation+0.000
metal
Token metal
Feature activation+0.000
box
Token box
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+3.078
took
Token took
Feature activation+0.000
it
Token it
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
building
Token building
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Towers
Token Towers
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+3.187
to
Token to
Feature activation+0.064
become
Token become
Feature activation+0.341
aware
Token aware
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.493 - 2.849
CONTAINS 0.001%

of
Token of
Feature activation+0.000
passing
Token passing
Feature activation+0.000
repeal
Token repeal
Feature activation+0.000
first
Token first
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+2.528
separately
Token separately
Feature activation+0.000
working
Token working
Feature activation+0.000
on
Token on
Feature activation+0.000
replacement
Token replacement
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
set
Token set
Feature activation+0.000
date
Token date
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+2.760
we
Token we
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
paintings
Token paintings
Feature activation+0.000
and
Token and
Feature activation+0.000
first
Token first
Feature activation+0.000
Amendment
Token Amendment
Feature activation+0.000
fallen
Token fallen
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+2.675
and
Token and
Feature activation+0.000
those
Token those
Feature activation+0.000
that
Token that
Feature activation+0.000
follow
Token follow
Feature activation+0.000
can
Token can
Feature activation+0.000
healthy
Token healthy
Feature activation+0.000
and
Token and
Feature activation+0.000
abundant
Token abundant
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
second
Token second
Feature activation+2.610
basket
Token basket
Feature activation+0.000
rests
Token rests
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000

INTERVAL 2.137 - 2.493
CONTAINS 0.001%

like
Token like
Feature activation+0.000
Wyoming
Token Wyoming
Feature activation+0.000
and
Token and
Feature activation+0.000
Montana
Token Montana
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+2.433
more
Token more
Feature activation+0.170
challenges
Token challenges
Feature activation+0.012
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
drilling
Token drilling
Feature activation+0.000
everything
Token everything
Feature activation+0.000
continue
Token continue
Feature activation+0.000
its
Token its
Feature activation+0.000
course
Token course
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+2.222
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
reported
Token reported
Feature activation+0.000
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
capabilities
Token capabilities
Feature activation+0.000
built
Token built
Feature activation+0.000
in
Token in
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.173
second
Token second
Feature activation+2.263
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
attach
Token attach
Feature activation+0.000
a
Token a
Feature activation+0.000
printer
Token printer
Feature activation+0.000
s
Tokens
Feature activation+0.000
tv
Token tv
Feature activation+0.000
show
Token show
Feature activation+0.000
simulator
Token simulator
Feature activation+0.000
but
Token but
Feature activation+0.275
then
Token then
Feature activation+2.393
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
not
Token not
Feature activation+0.000
appeal
Token appeal
Feature activation+0.000
to
Token to
Feature activation+0.000
First
Token First
Feature activation+0.000
we
Token we
Feature activation+0.000
guess
Token guess
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+2.291
we
Token we
Feature activation+0.000
compute
Token compute
Feature activation+0.000
the
Token the
Feature activation+0.000
consequences
Token consequences
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.781 - 2.137
CONTAINS 0.001%

ging
Tokenging
Feature activation+0.000
out
Token out
Feature activation+0.000
the
Token the
Feature activation+0.000
Tories
Token Tories
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+1.880
bulldo
Token bulldo
Feature activation+0.000
zing
Tokenzing
Feature activation+0.000
Labour
Token Labour
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
of
Token of
Feature activation+0.000
unemployed
Token unemployed
Feature activation+0.000
workers
Token workers
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.390
then
Token then
Feature activation+1.938
came
Token came
Feature activation+0.316
the
Token the
Feature activation+0.151
first
Token first
Feature activation+0.000
factory
Token factory
Feature activation+0.000
occupations
Token occupations
Feature activation+0.000
see
Token see
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
place
Token place
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+1.786
you
Token you
Feature activation+0.000
negotiate
Token negotiate
Feature activation+0.000
later
Token later
Feature activation+0.191
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
the
Token the
Feature activation+0.000
fragments
Token fragments
Feature activation+0.000
bearing
Token bearing
Feature activation+0.000
the
Token the
Feature activation+0.000
structures
Token structures
Feature activation+0.000
then
Token then
Feature activation+1.953
s
Token s
Feature activation+0.000
ieved
Tokenieved
Feature activation+0.000
to
Token to
Feature activation+0.000
concentrate
Token concentrate
Feature activation+0.000
parts
Token parts
Feature activation+0.000
%
Token %
Feature activation+0.000
Desktop
TokenDesktop
Feature activation+0.000
%
Token%
Feature activation+0.000
first
Token first
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+1.876
encrypt
Token encrypt
Feature activation+0.000
other
Token other
Feature activation+0.001
folders
Token folders
Feature activation+0.000
.
Token.
Feature activation+0.077
The
Token The
Feature activation+0.048

INTERVAL 1.424 - 1.781
CONTAINS 0.001%

are
Token are
Feature activation+0.000
unusually
Token unusually
Feature activation+0.000
arbitrary
Token arbitrary
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
second
Token second
Feature activation+1.516
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
in
Token in
Feature activation+0.000
1987
Token 1987
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.003
the
Token the
Feature activation+0.000
second
Token second
Feature activation+1.471
being
Token being
Feature activation+0.000
completed
Token completed
Feature activation+0.000
in
Token in
Feature activation+0.000
January
Token January
Feature activation+0.000
1988
Token 1988
Feature activation+0.000
we
Token we
Feature activation+0.000
guessed
Token guessed
Feature activation+0.000
is
Token is
Feature activation+0.000
right
Token right
Feature activation+0.000
.
Token.
Feature activation+0.000
Then
Token Then
Feature activation+1.489
we
Token we
Feature activation+0.000
compare
Token compare
Feature activation+0.000
the
Token the
Feature activation+0.000
result
Token result
Feature activation+0.000
of
Token of
Feature activation+0.000
sectors
Token sectors
Feature activation+0.000
of
Token of
Feature activation+0.000
Argentine
Token Argentine
Feature activation+0.000
society
Token society
Feature activation+0.000
;
Token;
Feature activation+0.000
second
Token second
Feature activation+1.441
,
Token,
Feature activation+0.000
Mac
Token Mac
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Free
Token Free
Feature activation+0.000
Syrian
Token Syrian
Feature activation+0.000
Army
Token Army
Feature activation+0.000
,
Token,
Feature activation+0.000
switched
Token switched
Feature activation+0.000
then
Token then
Feature activation+1.711
to
Token to
Feature activation+0.000
Al
Token Al
Feature activation+0.000
-
Token-
Feature activation+0.000
Nusra
TokenNusra
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.068 - 1.424
CONTAINS 0.002%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
me
Token me
Feature activation+0.000
at
Token at
Feature activation+0.000
first
Token first
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+1.304
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.089
persistent
Token persistent
Feature activation+0.000
.
Token.
Feature activation+0.000
Several
Token Several
Feature activation+0.000
a
Token a
Feature activation+0.000
third
Token third
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
Democrats
Token Democrats
Feature activation+0.000
then
Token then
Feature activation+1.126
in
Token in
Feature activation+0.000
Congress
Token Congress
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
residential
Token residential
Feature activation+0.000
neighborhood
Token neighborhood
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+1.073
the
Token the
Feature activation+0.000
officer
Token officer
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
spotted
Token spotted
Feature activation+0.000
and
Token and
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
to
Token to
Feature activation+0.000
this
Token this
Feature activation+0.000
invasion
Token invasion
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+1.151
he
Token he
Feature activation+0.000
won
Token won
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
by
Token by
Feature activation+0.000
CNN
Token CNN
Feature activation+0.000
on
Token on
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
and
Token and
Feature activation+0.000
later
Token later
Feature activation+1.424
released
Token released
Feature activation+0.000
on
Token on
Feature activation+0.000
social
Token social
Feature activation+0.000
media
Token media
Feature activation+0.000
by
Token by
Feature activation+0.000

INTERVAL 0.712 - 1.068
CONTAINS 0.003%

counted
Token counted
Feature activation+0.000
for
Token for
Feature activation+0.000
either
Token either
Feature activation+0.000
candidate
Token candidate
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+1.067
the
Token the
Feature activation+0.000
recount
Token recount
Feature activation+0.000
official
Token official
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
that
Token that
Feature activation+0.000
irted
Tokenirted
Feature activation+0.000
his
Token his
Feature activation+0.000
first
Token first
Feature activation+0.000
year
Token year
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.734
saw
Token saw
Feature activation+0.000
most
Token most
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
playing
Token playing
Feature activation+0.000
an
Token an
Feature activation+0.000
agreement
Token agreement
Feature activation+0.000
or
Token or
Feature activation+0.000
strike
Token strike
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.878
held
Token held
Feature activation+0.186
off
Token off
Feature activation+0.000
to
Token to
Feature activation+0.000
continue
Token continue
Feature activation+0.000
negotiations
Token negotiations
Feature activation+0.000
8
Token8
Feature activation+0.000
After
Token After
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
and
Token and
Feature activation+0.000
second
Token second
Feature activation+1.022
appointed
Token appointed
Feature activation+0.000
Brexit
Token Brexit
Feature activation+0.000
secretaries
Token secretaries
Feature activation+0.000
resigned
Token resigned
Feature activation+0.000
(
Token (
Feature activation+0.000
restaurant
Token restaurant
Feature activation+0.000
in
Token in
Feature activation+0.000
Los
Token Los
Feature activation+0.000
Angeles
Token Angeles
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.797
instead
Token instead
Feature activation+0.242
he
Token he
Feature activation+0.000
offered
Token offered
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000

INTERVAL 0.356 - 0.712
CONTAINS 0.008%

first
Token first
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
videos
Token videos
Feature activation+0.000
,
Token,
Feature activation+0.000
released
Token released
Feature activation+0.579
today
Token today
Feature activation+0.229
,
Token,
Feature activation+0.000
focuses
Token focuses
Feature activation+0.000
on
Token on
Feature activation+0.000
X
Token X
Feature activation+0.000
start
Token start
Feature activation+0.000
in
Token in
Feature activation+0.000
immersion
Token immersion
Feature activation+0.000
preschool
Token preschool
Feature activation+0.000
have
Token have
Feature activation+0.248
now
Token now
Feature activation+0.358
graduated
Token graduated
Feature activation+0.000
from
Token from
Feature activation+0.000
college
Token college
Feature activation+0.000
and
Token and
Feature activation+0.000
many
Token many
Feature activation+0.000
Sun
Token Sun
Feature activation+0.017
's
Token's
Feature activation+0.000
spectrum
Token spectrum
Feature activation+0.000
.
Token.
Feature activation+0.198
Ċ
TokenĊ
Feature activation+0.492
Ċ
TokenĊ
Feature activation+0.410
3
Token3
Feature activation+0.315
Lith
Token Lith
Feature activation+0.000
ium
Tokenium
Feature activation+0.000
Li
Token Li
Feature activation+0.000
Greek
Token Greek
Feature activation+0.000
city
Token city
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
air
Token air
Feature activation+0.000
.
Token.
Feature activation+0.000
On
Token On
Feature activation+0.622
6
Token 6
Feature activation+0.000
August
Token August
Feature activation+0.000
1914
Token 1914
Feature activation+0.000
a
Token a
Feature activation+0.000
German
Token German
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
IB
TokenIB
Feature activation+0.000
M
TokenM
Feature activation+0.000
equipment
Token equipment
Feature activation+0.000
until
Token until
Feature activation+0.613
1980
Token 1980
Feature activation+0.000
.[
Token.[
Feature activation+0.000
14
Token14
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.000 - 0.356
CONTAINS 99.984%

better
Token better
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
apparently
Token apparently
Feature activation+0.000
an
Token an
Feature activation+0.000
emphasis
Token emphasis
Feature activation+0.000
on
Token on
Feature activation+0.000
droid
Token droid
Feature activation+0.000
support
Token support
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Aqu
Token Aqu
Feature activation+0.000
arius
Tokenarius
Feature activation+0.000
recovered
Token recovered
Feature activation+0.000
five
Token five
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Advertisement
TokenAdvertisement
Feature activation+0.000
-
Token -
Feature activation+0.000
Continue
Token Continue
Feature activation+0.000
Reading
Token Reading
Feature activation+0.000
Below
Token Below
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Charlie
TokenCharlie
Feature activation+0.000
Mage
Token Mage
Feature activation+0.000
Germany
TokenGermany
Feature activation+0.000
)
Token)
Feature activation+0.000
in
Token in
Feature activation+0.000
18
Token 18
Feature activation+0.000
68
Token68
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
a
Token a
Feature activation+0.000
parallel
Token parallel
Feature activation+0.000
where
Token where
Feature activation+0.000
even
Token even
Feature activation+0.000
if
Token if
Feature activation+0.000
we
Token we
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
get
Token get
Feature activation+0.000
it
Token it
Feature activation+0.000
exactly
Token exactly
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 H3.5: (feature 15566)

TOP ACTIVATIONS
MAX = 1.506

the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
13
Token 13
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+1.506
established
Token established
Feature activation+0.037
White
Token White
Feature activation+0.000
Oy
Token Oy
Feature activation+0.000
ster
Tokenster
Feature activation+0.000
Inter
Token Inter
Feature activation+0.000
weighs
Token weighs
Feature activation+0.194
quality
Token quality
Feature activation+0.000
and
Token and
Feature activation+0.000
quantity
Token quantity
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+1.484
consideration
Token consideration
Feature activation+0.000
of
Token of
Feature activation+0.000
Mercury
Token Mercury
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
be
Token be
Feature activation+0.000
returning
Token returning
Feature activation+0.000
,
Token,
Feature activation+0.000
although
Token although
Feature activation+0.000
whether
Token whether
Feature activation+0.000
she
Token she
Feature activation+1.445
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
Cos
Token Cos
Feature activation+0.000
mo
Tokenmo
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.047
She
TokenShe
Feature activation+1.429
can
Token can
Feature activation+0.128
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.295
t
Tokent
Feature activation+0.155
stop
Token stop
Feature activation+0.002
Valerie
Token Valerie
Feature activation+0.000
Sax
Token Sax
Feature activation+0.000
ion
Tokenion
Feature activation+0.000
stated
Token stated
Feature activation+0.000
that
Token that
Feature activation+0.000
she
Token she
Feature activation+1.421
received
Token received
Feature activation+0.000
her
Token her
Feature activation+0.082
doctor
Token doctor
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
in
Token in
Feature activation+0.000
D
Token D
Feature activation+0.000
rey
Tokenrey
Feature activation+0.000
f
Tokenf
Feature activation+0.000
uss
Tokenuss
Feature activation+0.000
kept
Token kept
Feature activation+0.000
her
Token her
Feature activation+1.299
entire
Token entire
Feature activation+0.000
Elaine
Token Elaine
Feature activation+0.000
wardrobe
Token wardrobe
Feature activation+0.000
from
Token from
Feature activation+0.000
Se
Token Se
Feature activation+0.000
the
Token the
Feature activation+0.000
legislature
Token legislature
Feature activation+0.000
grounds
Token grounds
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+1.257
was
Token was
Feature activation+0.000
all
Token all
Feature activation+0.000
smiles
Token smiles
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
Mass
Token Mass
Feature activation+0.000
.,
Token.,
Feature activation+0.000
gases
Token gases
Feature activation+0.000
up
Token up
Feature activation+0.000
her
Token her
Feature activation+1.245
car
Token car
Feature activation+0.054
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
Gulf
Token Gulf
Feature activation+0.000
station
Token station
Feature activation+0.000
orio
Tokenorio
Feature activation+0.000
ph
Token ph
Feature activation+0.000
oned
Tokenoned
Feature activation+0.000
to
Token to
Feature activation+0.000
tell
Token tell
Feature activation+0.000
her
Token her
Feature activation+1.201
they
Token they
Feature activation+0.038
had
Token had
Feature activation+0.000
arrived
Token arrived
Feature activation+0.000
safely
Token safely
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
news
Token news
Feature activation+0.000
this
Token this
Feature activation+0.000
week
Token week
Feature activation+0.000
because
Token because
Feature activation+0.000
she
Token she
Feature activation+1.154
said
Token said
Feature activation+0.000
Bernie
Token Bernie
Feature activation+0.000
will
Token will
Feature activation+0.000
stop
Token stop
Feature activation+0.000
the
Token the
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
fragmentation
Token fragmentation
Feature activation+0.000
notwithstanding
Token notwithstanding
Feature activation+0.000
,
Token,
Feature activation+0.000
her
Token her
Feature activation+1.145
candidacy
Token candidacy
Feature activation+0.254
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Buenos
Token Buenos
Feature activation+0.000
Aires
Token Aires
Feature activation+0.000
Cab
Token Cab
Feature activation+0.000
ral
Tokenral
Feature activation+0.000
a
Token a
Feature activation+0.000
taste
Token taste
Feature activation+0.000
of
Token of
Feature activation+0.000
her
Token her
Feature activation+1.130
daily
Token daily
Feature activation+0.010
commute
Token commute
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
85
Token 85
Feature activation+0.000
th
Tokenth
Feature activation+0.000
birthday
Token birthday
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
he
Token he
Feature activation+1.124
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
the
Token the
Feature activation+0.000
head
Token head
Feature activation+0.000
grounds
Token grounds
Feature activation+0.000
hard
Token hard
Feature activation+0.000
working
Tokenworking
Feature activation+0.000
and
Token and
Feature activation+0.000
trustworthy
Token trustworthy
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+1.113
works
Token works
Feature activation+0.176
four
Token four
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000
road
Token road
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
for
Token for
Feature activation+0.000
that
Token that
Feature activation+0.000
she
Token she
Feature activation+1.101
deserves
Token deserves
Feature activation+0.000
praise
Token praise
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
just
Token just
Feature activation+0.000
Houston
Token Houston
Feature activation+0.000
Chronicle
Token Chronicle
Feature activation+0.000
on
Token on
Feature activation+0.000
Sunday
Token Sunday
Feature activation+0.000
that
Token that
Feature activation+0.000
she
Token she
Feature activation+1.091
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
organize
Token organize
Feature activation+0.000
the
Token the
Feature activation+0.000
event
Token event
Feature activation+0.000
12
Token 12
Feature activation+0.000
student
Token student
Feature activation+0.000
Claudia
Token Claudia
Feature activation+0.120
Saunders
Token Saunders
Feature activation+0.000
says
Token says
Feature activation+0.000
she
Token she
Feature activation+1.071
hopes
Token hopes
Feature activation+0.000
the
Token the
Feature activation+0.000
ban
Token ban
Feature activation+0.000
will
Token will
Feature activation+0.000
do
Token do
Feature activation+0.000
much
Token much
Feature activation+0.000
worse
Token worse
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+1.056
told
Token told
Feature activation+0.000
The
Token The
Feature activation+0.000
Low
Token Low
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
lder
Tokenlder
Feature activation+0.000
came
Token came
Feature activation+0.000
quite
Token quite
Feature activation+0.000
by
Token by
Feature activation+0.000
accident
Token accident
Feature activation+0.000
.
Token.
Feature activation+0.000
Her
Token Her
Feature activation+1.044
simple
Token simple
Feature activation+0.215
lab
Token lab
Feature activation+0.034
error
Token error
Feature activation+0.000
has
Token has
Feature activation+0.000
uncovered
Token uncovered
Feature activation+0.000
Moh
Token Moh
Feature activation+0.000
ave
Tokenave
Feature activation+0.000
Desert
Token Desert
Feature activation+0.000
To
Token To
Feature activation+0.000
Update
Token Update
Feature activation+0.001
Her
Token Her
Feature activation+1.037
On
Token On
Feature activation+0.218
Alien
Token Alien
Feature activation+0.122
Activity
Token Activity
Feature activation+0.000
?
Token?
Feature activation+0.269
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 1.578

Author
Token Author
Feature activation+0.012
Top resid features:
:-
Token:-
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Am
TokenAm
Feature activation+0.025
Top resid features:
anda
Tokenanda
Feature activation+0.936
Top resid features:
He
Token He
Feature activation+0.009
Top resid features:
yn
Tokenyn
Feature activation+0.423
Top resid features:
en
Tokenen
Feature activation+0.340
Top resid features:
-
Token -
Feature activation+0.016
Top resid features:
Professional
Token Professional
Feature activation-0.003
Top resid features:
Alert
TokenAlert
Feature activation-0.002
Top resid features:
Me
TokenMe
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.020
Top resid features:
Len
TokenLen
Feature activation+0.163
Top resid features:
Wall
Token Wall
Feature activation+0.097
Top resid features:
ick
Tokenick
Feature activation+1.485
Top resid features:
weighs
Token weighs
Feature activation+0.089
Top resid features:
quality
Token quality
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+0.055
Top resid features:
quantity
Token quantity
Feature activation+0.005
Top resid features:
in
Token in
Feature activation+0.011
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.027
Top resid features:
bring
Token bring
Feature activation-0.003
Top resid features:
confirmation
Token confirmation
Feature activation-0.004
Top resid features:
that
Token that
Feature activation-0.012
Top resid features:
Clement
Token Clement
Feature activation+0.191
Top resid features:
ine
Tokenine
Feature activation+1.578
Top resid features:
will
Token will
Feature activation+0.008
Top resid features:
be
Token be
Feature activation+0.002
Top resid features:
returning
Token returning
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
although
Token although
Feature activation+0.013
Top resid features:
ASHINGTON
TokenASHINGTON
Feature activation+0.002
Top resid features:
POST
Token POST
Feature activation+0.006
Top resid features:
)
Token)
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Jennifer
TokenJennifer
Feature activation+0.764
Top resid features:
T
Token T
Feature activation+0.161
Top resid features:
ress
Tokenress
Feature activation+0.617
Top resid features:
can
Token can
Feature activation+0.033
Top resid features:
âĢ
TokenâĢ
Feature activation+0.009
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
her
Tokenher
Feature activation-0.013
Top resid features:
]
Token]
Feature activation-0.001
Top resid features:
website
Token website
Feature activation-0.017
Top resid features:
âĢ¦
Token âĢ¦
Feature activation+0.008
Top resid features:
defendant
Token defendant
Feature activation+0.056
Top resid features:
Valerie
Token Valerie
Feature activation+1.510
Top resid features:
Sax
Token Sax
Feature activation+0.075
Top resid features:
ion
Tokenion
Feature activation+0.251
Top resid features:
stated
Token stated
Feature activation+0.002
Top resid features:
that
Token that
Feature activation-0.020
Top resid features:
she
Token she
Feature activation+0.083
Top resid features:
favourite
Token favourite
Feature activation-0.001
Top resid features:
props
Token props
Feature activation-0.000
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
costumes
Token costumes
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
Julia
Token Julia
Feature activation+1.135
Top resid features:
Louis
Token Louis
Feature activation+0.149
Top resid features:
D
Token D
Feature activation+0.107
Top resid features:
rey
Tokenrey
Feature activation+0.100
Top resid features:
f
Tokenf
Feature activation+0.084
Top resid features:
uss
Tokenuss
Feature activation+0.150
Top resid features:
revealed
Token revealed
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.008
Top resid features:
When
TokenWhen
Feature activation+0.126
Top resid features:
Premier
Token Premier
Feature activation+0.011
Top resid features:
Rachel
Token Rachel
Feature activation+1.172
Top resid features:
Not
Token Not
Feature activation+0.033
Top resid features:
ley
Tokenley
Feature activation+0.251
Top resid features:
turned
Token turned
Feature activation+0.051
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
for
Token for
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
2012
Token 2012
Feature activation-0.002
Top resid features:
file
Token file
Feature activation+0.004
Top resid features:
photo
Token photo
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
Suzanne
Token Suzanne
Feature activation+0.931
Top resid features:
Meredith
Token Meredith
Feature activation+0.610
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+0.056
Top resid features:
Wal
Token Wal
Feature activation+0.037
Top resid features:
pole
Tokenpole
Feature activation+0.048
Top resid features:
kidn
Token kidn
Feature activation-0.000
Top resid features:
appings
Tokenappings
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
Cel
Token Cel
Feature activation+0.231
Top resid features:
er
Tokener
Feature activation+0.122
Top resid features:
ina
Tokenina
Feature activation+0.871
Top resid features:
's
Token's
Feature activation+0.021
Top resid features:
husband
Token husband
Feature activation+0.090
Top resid features:
Nem
Token Nem
Feature activation+0.114
Top resid features:
orio
Tokenorio
Feature activation+0.063
Top resid features:
ph
Token ph
Feature activation+0.032
Top resid features:
said
Token said
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
E
TokenE
Feature activation+0.038
Top resid features:
rika
Tokenrika
Feature activation+0.692
Top resid features:
And
Token And
Feature activation+0.087
Top resid features:
iola
Tokeniola
Feature activation+0.377
Top resid features:
was
Token was
Feature activation+0.064
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
Christina
Token Christina
Feature activation+0.457
Top resid features:
Kir
Token Kir
Feature activation+0.351
Top resid features:
ch
Tokench
Feature activation+0.029
Top resid features:
ner
Tokenner
Feature activation+0.037
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Kir
Token Kir
Feature activation+0.514
Top resid features:
ch
Tokench
Feature activation+0.045
Top resid features:
ner
Tokenner
Feature activation+0.066
Top resid features:
had
Token had
Feature activation+0.040
Top resid features:
gamb
Token gamb
Feature activation+0.007
Top resid features:
led
Tokenled
Feature activation-0.006
Top resid features:
your
Token your
Feature activation+0.001
Top resid features:
device
Token device
Feature activation-0.001
Top resid features:
Media
Token Media
Feature activation+0.001
Top resid features:
caption
Token caption
Feature activation-0.001
Top resid features:
Fab
Token Fab
Feature activation+0.090
Top resid features:
iana
Tokeniana
Feature activation+0.953
Top resid features:
C
Token C
Feature activation+0.079
Top resid features:
resp
Tokenresp
Feature activation+0.033
Top resid features:
o
Tokeno
Feature activation+0.068
Top resid features:
gives
Token gives
Feature activation+0.035
Top resid features:
Paulo
Token Paulo
Feature activation+0.241
Top resid features:
be
Token be
Feature activation-0.003
Top resid features:
played
Token played
Feature activation-0.005
Top resid features:
here
Token here
Feature activation-0.007
Top resid features:
Sunday
Token Sunday
Feature activation+0.006
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
Tom
Token Tom
Feature activation+0.831
Top resid features:
a
Tokena
Feature activation+0.563
Top resid features:
âĢ
TokenâĢ
Feature activation+0.016
Top resid features:
Ļ
TokenĻ
Feature activation+0.052
Top resid features:
s
Tokens
Feature activation+0.015
Top resid features:
85
Token 85
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.018
Top resid features:
ľ
Tokenľ
Feature activation+0.031
Top resid features:
K
TokenK
Feature activation+0.061
Top resid features:
aren
Tokenaren
Feature activation+1.274
Top resid features:
is
Token is
Feature activation+0.058
Top resid features:
hard
Token hard
Feature activation+0.007
Top resid features:
working
Tokenworking
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.025
Top resid features:
trustworthy
Token trustworthy
Feature activation+0.014
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
S
TokenS
Feature activation+0.018
Top resid features:
cha
Tokencha
Feature activation+1.098
Top resid features:
af
Tokenaf
Feature activation+0.051
Top resid features:
was
Token was
Feature activation+0.183
Top resid features:
willing
Token willing
Feature activation-0.003
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
take
Token take
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
UT
TokenUT
Feature activation+0.012
Top resid features:
alum
Token alum
Feature activation+0.112
Top resid features:
na
Tokenna
Feature activation+0.166
Top resid features:
Jessica
Token Jessica
Feature activation+0.867
Top resid features:
Jin
Token Jin
Feature activation+0.282
Top resid features:
told
Token told
Feature activation+0.074
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
Houston
Token Houston
Feature activation+0.014
Top resid features:
Chronicle
Token Chronicle
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Year
TokenYear
Feature activation+0.028
Top resid features:
12
Token 12
Feature activation+0.024
Top resid features:
student
Token student
Feature activation+0.061
Top resid features:
Claudia
Token Claudia
Feature activation+1.178
Top resid features:
Saunders
Token Saunders
Feature activation+0.229
Top resid features:
says
Token says
Feature activation-0.043
Top resid features:
she
Token she
Feature activation+0.081
Top resid features:
hopes
Token hopes
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
latest
Token latest
Feature activation-0.004
Top resid features:
farm
Token farm
Feature activation+0.010
Top resid features:
attack
Token attack
Feature activation+0.003
Top resid features:
survivor
Token survivor
Feature activation+0.069
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
Sue
Token Sue
Feature activation+0.695
Top resid features:
H
Token H
Feature activation+0.152
Top resid features:
adi
Tokenadi
Feature activation+0.218
Top resid features:
aris
Tokenaris
Feature activation+0.127
Top resid features:
(
Token (
Feature activation+0.016
Top resid features:
49
Token49
Feature activation+0.005
Top resid features:
State
Token State
Feature activation+0.005
Top resid features:
University
Token University
Feature activation+0.010
Top resid features:
doctoral
Token doctoral
Feature activation+0.015
Top resid features:
student
Token student
Feature activation+0.006
Top resid features:
Marian
Token Marian
Feature activation+0.477
Top resid features:
ne
Tokenne
Feature activation+0.569
Top resid features:
Tar
Token Tar
Feature activation+0.104
Top resid features:
un
Tokenun
Feature activation+0.069
Top resid features:
's
Token's
Feature activation+0.011
Top resid features:
discovery
Token discovery
Feature activation-0.016
Top resid features:
came
Token came
Feature activation+0.020
Top resid features:
it
Token it
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.003
Top resid features:
R
TokenR
Feature activation+0.015
Top resid features:
ih
Tokenih
Feature activation+0.186
Top resid features:
anna
Tokenanna
Feature activation+0.863
Top resid features:
Pay
Token Pay
Feature activation+0.015
Top resid features:
ing
Tokening
Feature activation+0.006
Top resid features:
UFO
Token UFO
Feature activation+0.009
Top resid features:
Wat
Token Wat
Feature activation+0.029
Top resid features:
cher
Tokencher
Feature activation+0.046
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.05

Head 2: 0.05

Head 3: 0.02

Head 4: 0.06

Head 5: 0.46

Head 6: 0.09

Head 7: 0.05

Head 8: 0.04

Head 9: 0.03

Head 10: 0.08

Head 11: 0.03

Positive logits

His2.36

Miko2.11

his2.10

wrote1.98

grandson1.94

His1.93

Founder1.92

He1.91

himself1.88

1.83

ドラゴン1.81

Daughter1.79

Kul1.78

Himself1.75

Kut1.74

Ala1.73

chair1.73

1.73

[&1.72

JA1.71

Negative logits

ggle-2.04

azard-2.02

aggress-1.96

deterrent-1.95

isks-1.90

��-1.88

superpower-1.84

selves-1.80

metics-1.79

ensity-1.75

merce-1.75

wards-1.73

disposable-1.73

urance-1.72

disadvantage-1.72

increments-1.70

.–-1.70

ento-1.69

��-1.64

uncontrolled-1.62

INTERVAL 1.355 - 1.506
CONTAINS 0.001%

weighs
Token weighs
Feature activation+0.194
quality
Token quality
Feature activation+0.000
and
Token and
Feature activation+0.000
quantity
Token quantity
Feature activation+0.000
in
Token in
Feature activation+0.000
his
Token his
Feature activation+1.484
consideration
Token consideration
Feature activation+0.000
of
Token of
Feature activation+0.000
Mercury
Token Mercury
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Valerie
Token Valerie
Feature activation+0.000
Sax
Token Sax
Feature activation+0.000
ion
Tokenion
Feature activation+0.000
stated
Token stated
Feature activation+0.000
that
Token that
Feature activation+0.000
she
Token she
Feature activation+1.421
received
Token received
Feature activation+0.000
her
Token her
Feature activation+0.082
doctor
Token doctor
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
in
Token in
Feature activation+0.000
Cos
Token Cos
Feature activation+0.000
mo
Tokenmo
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.047
She
TokenShe
Feature activation+1.429
can
Token can
Feature activation+0.128
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.295
t
Tokent
Feature activation+0.155
stop
Token stop
Feature activation+0.002
be
Token be
Feature activation+0.000
returning
Token returning
Feature activation+0.000
,
Token,
Feature activation+0.000
although
Token although
Feature activation+0.000
whether
Token whether
Feature activation+0.000
she
Token she
Feature activation+1.445
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.000
past
Token past
Feature activation+0.000
13
Token 13
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+1.506
established
Token established
Feature activation+0.037
White
Token White
Feature activation+0.000
Oy
Token Oy
Feature activation+0.000
ster
Tokenster
Feature activation+0.000
Inter
Token Inter
Feature activation+0.000

INTERVAL 1.205 - 1.355
CONTAINS 0.000%

the
Token the
Feature activation+0.000
legislature
Token legislature
Feature activation+0.000
grounds
Token grounds
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+1.257
was
Token was
Feature activation+0.000
all
Token all
Feature activation+0.000
smiles
Token smiles
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
D
Token D
Feature activation+0.000
rey
Tokenrey
Feature activation+0.000
f
Tokenf
Feature activation+0.000
uss
Tokenuss
Feature activation+0.000
kept
Token kept
Feature activation+0.000
her
Token her
Feature activation+1.299
entire
Token entire
Feature activation+0.000
Elaine
Token Elaine
Feature activation+0.000
wardrobe
Token wardrobe
Feature activation+0.000
from
Token from
Feature activation+0.000
Se
Token Se
Feature activation+0.000
,
Token,
Feature activation+0.000
Mass
Token Mass
Feature activation+0.000
.,
Token.,
Feature activation+0.000
gases
Token gases
Feature activation+0.000
up
Token up
Feature activation+0.000
her
Token her
Feature activation+1.245
car
Token car
Feature activation+0.054
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
Gulf
Token Gulf
Feature activation+0.000
station
Token station
Feature activation+0.000

INTERVAL 1.054 - 1.205
CONTAINS 0.001%

orio
Tokenorio
Feature activation+0.000
ph
Token ph
Feature activation+0.000
oned
Tokenoned
Feature activation+0.000
to
Token to
Feature activation+0.000
tell
Token tell
Feature activation+0.000
her
Token her
Feature activation+1.201
they
Token they
Feature activation+0.038
had
Token had
Feature activation+0.000
arrived
Token arrived
Feature activation+0.000
safely
Token safely
Feature activation+0.000
.
Token.
Feature activation+0.000
much
Token much
Feature activation+0.000
worse
Token worse
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
She
TokenShe
Feature activation+1.056
told
Token told
Feature activation+0.000
The
Token The
Feature activation+0.000
Low
Token Low
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
lder
Tokenlder
Feature activation+0.000
12
Token 12
Feature activation+0.000
student
Token student
Feature activation+0.000
Claudia
Token Claudia
Feature activation+0.120
Saunders
Token Saunders
Feature activation+0.000
says
Token says
Feature activation+0.000
she
Token she
Feature activation+1.071
hopes
Token hopes
Feature activation+0.000
the
Token the
Feature activation+0.000
ban
Token ban
Feature activation+0.000
will
Token will
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
news
Token news
Feature activation+0.000
this
Token this
Feature activation+0.000
week
Token week
Feature activation+0.000
because
Token because
Feature activation+0.000
she
Token she
Feature activation+1.154
said
Token said
Feature activation+0.000
Bernie
Token Bernie
Feature activation+0.000
will
Token will
Feature activation+0.000
stop
Token stop
Feature activation+0.000
the
Token the
Feature activation+0.000
hard
Token hard
Feature activation+0.000
working
Tokenworking
Feature activation+0.000
and
Token and
Feature activation+0.000
trustworthy
Token trustworthy
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+1.113
works
Token works
Feature activation+0.176
four
Token four
Feature activation+0.000
jobs
Token jobs
Feature activation+0.000
in
Token in
Feature activation+0.000
order
Token order
Feature activation+0.000

INTERVAL 0.903 - 1.054
CONTAINS 0.001%

id
Tokenid
Feature activation+0.000
always
Token always
Feature activation+0.000
stepped
Token stepped
Feature activation+0.091
up
Token up
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.915
never
Token never
Feature activation+0.020
backed
Token backed
Feature activation+0.000
down
Token down
Feature activation+0.000
.
Token.
Feature activation+0.000
Rahul
Token Rahul
Feature activation+0.000
in
Token in
Feature activation+0.000
numerous
Token numerous
Feature activation+0.000
public
Token public
Feature activation+0.000
letters
Token letters
Feature activation+0.132
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.949
local
Token local
Feature activation+0.000
newspaper
Token newspaper
Feature activation+0.085
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
taxes
Token taxes
Feature activation+0.000
there
Token there
Feature activation+0.000
âĢ¦
Token âĢ¦
Feature activation+0.000
should
Token should
Feature activation+0.000
they
Token they
Feature activation+0.069
take
Token take
Feature activation+0.000
him
Token him
Feature activation+0.932
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
say
Token say
Feature activation+0.000
Moh
Token Moh
Feature activation+0.000
ave
Tokenave
Feature activation+0.000
Desert
Token Desert
Feature activation+0.000
To
Token To
Feature activation+0.000
Update
Token Update
Feature activation+0.001
Her
Token Her
Feature activation+1.037
On
Token On
Feature activation+0.218
Alien
Token Alien
Feature activation+0.122
Activity
Token Activity
Feature activation+0.000
?
Token?
Feature activation+0.269
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Amy
TokenAmy
Feature activation+0.000
P
Token P
Feature activation+0.000
urdy
Tokenurdy
Feature activation+0.000
swaps
Token swaps
Feature activation+0.000
her
Token her
Feature activation+0.915
prost
Token prost
Feature activation+0.078
hetic
Tokenhetic
Feature activation+0.000
legs
Token legs
Feature activation+0.127
as
Token as
Feature activation+0.000
she
Token she
Feature activation+0.605

INTERVAL 0.753 - 0.903
CONTAINS 0.004%

providing
Token providing
Feature activation+0.000
higher
Token higher
Feature activation+0.000
value
Token value
Feature activation+0.000
products
Token products
Feature activation+0.000
.
Token.
Feature activation+0.004
He
Token He
Feature activation+0.821
says
Token says
Feature activation+0.120
importing
Token importing
Feature activation+0.000
biomass
Token biomass
Feature activation+0.000
suggests
Token suggests
Feature activation+0.000
the
Token the
Feature activation+0.000
is
Token is
Feature activation+0.000
making
Token making
Feature activation+0.000
headlines
Token headlines
Feature activation+0.000
for
Token for
Feature activation+0.000
listing
Token listing
Feature activation+0.000
her
Token her
Feature activation+0.826
white
Token white
Feature activation+0.000
2006
Token 2006
Feature activation+0.000
J
Token J
Feature activation+0.000
etta
Tokenetta
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
moon
Token moon
Feature activation+0.000
at
Token at
Feature activation+0.000
night
Token night
Feature activation+0.000
,
Token,
Feature activation+0.020
he
Token he
Feature activation+0.831
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
see
Token see
Feature activation+0.000
magic
Token magic
Feature activation+0.000
or
Token or
Feature activation+0.000
Keen
Token Keen
Feature activation+0.000
an
Tokenan
Feature activation+0.000
Beng
Token Beng
Feature activation+0.000
ts
Tokents
Feature activation+0.000
presented
Token presented
Feature activation+0.000
her
Token her
Feature activation+0.847
annual
Token annual
Feature activation+0.034
report
Token report
Feature activation+0.000
at
Token at
Feature activation+0.130
the
Token the
Feature activation+0.000
Legislative
Token Legislative
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.031
head
Token head
Feature activation+0.778
of
Token of
Feature activation+0.136
sustainable
Token sustainable
Feature activation+0.000
development
Token development
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.602 - 0.753
CONTAINS 0.009%

by
Token by
Feature activation+0.000
doing
Token doing
Feature activation+0.048
just
Token just
Feature activation+0.000
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.147
His
Token His
Feature activation+0.614
bar
Token bar
Feature activation+0.153
is
Token is
Feature activation+0.000
called
Token called
Feature activation+0.000
Bob
Token Bob
Feature activation+0.000
a
Tokena
Feature activation+0.000
stays
Token stays
Feature activation+0.000
home
Token home
Feature activation+0.024
alone
Token alone
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
she
Token she
Feature activation+0.624
g
Token g
Feature activation+0.000
rie
Tokenrie
Feature activation+0.000
ves
Tokenves
Feature activation+0.000
her
Token her
Feature activation+0.119
husband
Token husband
Feature activation+0.245
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Lat
TokenLat
Feature activation+0.000
asha
Tokenasha
Feature activation+0.000
said
Token said
Feature activation+0.000
her
Token her
Feature activation+0.645
15
Token 15
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
Mirror
Token Mirror
Feature activation+0.000
,
Token,
Feature activation+0.000
Amanda
Token Amanda
Feature activation+0.000
PL
Token PL
Feature activation+0.000
said
Token said
Feature activation+0.000
she
Token she
Feature activation+0.616
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
been
Token been
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
being
Token being
Feature activation+0.000
unclear
Token unclear
Feature activation+0.000
to
Token to
Feature activation+0.000
MPs
Token MPs
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.605
discussed
Token discussed
Feature activation+0.000
the
Token the
Feature activation+0.000
matter
Token matter
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.452 - 0.602
CONTAINS 0.017%

cuts
Token cuts
Feature activation+0.000
.
Token.
Feature activation+0.080
Ċ
TokenĊ
Feature activation+0.099
Ċ
TokenĊ
Feature activation+0.119
Like
TokenLike
Feature activation+0.000
her
Token her
Feature activation+0.477
,
Token,
Feature activation+0.000
other
Token other
Feature activation+0.000
unhappy
Token unhappy
Feature activation+0.000
parents
Token parents
Feature activation+0.000
plan
Token plan
Feature activation+0.000
al
Tokenal
Feature activation+0.000
ke
Tokenke
Feature activation+0.000
Award
Token Award
Feature activation+0.000
entit
Token entit
Feature activation+0.000
les
Tokenles
Feature activation+0.000
him
Token him
Feature activation+0.475
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
Sw
Token Sw
Feature activation+0.000
arn
Tokenarn
Feature activation+0.000
Kam
Token Kam
Feature activation+0.000
Schwarzenegger
Token Schwarzenegger
Feature activation+0.152
.
Token.
Feature activation+0.000
At
Token At
Feature activation+0.052
this
Token this
Feature activation+0.000
time
Token time
Feature activation+0.000
he
Token he
Feature activation+0.487
was
Token was
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
bench
Token bench
Feature activation+0.025
press
Token press
Feature activation+0.051
.
Token.
Feature activation+0.000
Get
Token Get
Feature activation+0.000
over
Token over
Feature activation+0.000
it
Token it
Feature activation+0.000
."
Token."
Feature activation+0.000
He
Token He
Feature activation+0.504
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
partner
Token partner
Feature activation+0.000
regard
Token regard
Feature activation+0.000
the
Token the
Feature activation+0.000
Bart
Token Bart
Feature activation+0.000
el
Tokenel
Feature activation+0.000
is
Token is
Feature activation+0.000
known
Token known
Feature activation+0.000
for
Token for
Feature activation+0.000
her
Token her
Feature activation+0.478
candy
Token candy
Feature activation+0.000
-
Token-
Feature activation+0.000
colored
Tokencolored
Feature activation+0.000
illustrations
Token illustrations
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 0.301 - 0.452
CONTAINS 0.043%

of
Token of
Feature activation+0.000
Ney
Token Ney
Feature activation+0.000
ret
Tokenret
Feature activation+0.000
,
Token,
Feature activation+0.000
calling
Token calling
Feature activation+0.000
him
Token him
Feature activation+0.369
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
inc
Tokeninc
Feature activation+0.000
or
Tokenor
Feature activation+0.000
rupt
Tokenrupt
Feature activation+0.000
J
TokenJ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
facilities
Token facilities
Feature activation+0.000
manager
Token manager
Feature activation+0.315
,
Token,
Feature activation+0.000
all
Token all
Feature activation+0.000
schools
Token schools
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Jeff
Token Jeff
Feature activation+0.000
describes
Token describes
Feature activation+0.000
the
Token the
Feature activation+0.000
status
Token status
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.423
forfeiture
Token forfeiture
Feature activation+0.000
case
Token case
Feature activation+0.000
:
Token:
Feature activation+0.027
"
Token "
Feature activation+0.066
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
looking
Token looking
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
bigger
Token bigger
Feature activation+0.000
ball
Token ball
Feature activation+0.316
carrier
Token carrier
Feature activation+0.000
as
Token as
Feature activation+0.055
a
Token a
Feature activation+0.000
blind
Token blind
Feature activation+0.000
side
Tokenside
Feature activation+0.000
June
Token June
Feature activation+0.000
16
Token 16
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.404
stated
Token stated
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

INTERVAL 0.151 - 0.301
CONTAINS 0.103%

)
Token)
Feature activation+0.000
could
Token could
Feature activation+0.130
return
Token return
Feature activation+0.000
and
Token and
Feature activation+0.000
position
Token position
Feature activation+0.025
himself
Token himself
Feature activation+0.179
as
Token as
Feature activation+0.010
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
long
Token long
Feature activation+0.000
Thomas
Token Thomas
Feature activation+0.000
Mon
Token Mon
Feature activation+0.000
ath
Tokenath
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
doctor
Token doctor
Feature activation+0.165
who
Token who
Feature activation+0.000
had
Token had
Feature activation+0.000
just
Token just
Feature activation+0.000
unravel
Token unravel
Feature activation+0.000
ed
Tokened
Feature activation+0.000
a
Token a
Feature activation+0.000
deal
Token deal
Feature activation+0.000
done
Token done
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.152
White
Token White
Feature activation+0.007
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
the
Token the
Feature activation+0.000
story
Token story
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
gay
Token gay
Feature activation+0.000
man
Token man
Feature activation+0.258
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
military
Token military
Feature activation+0.000
,
Token,
Feature activation+0.000
despite
Token despite
Feature activation+0.000
left
Token left
Feature activation+0.000
it
Token it
Feature activation+0.000
in
Token in
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.166
spent
Token spent
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.151
CONTAINS 99.822%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Green
Token Green
Feature activation+0.000
Lantern
Token Lantern
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
the
Token the
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
never
Token never
Feature activation+0.000
really
Token really
Feature activation+0.000
recovered
Token recovered
Feature activation+0.000
any
Token any
Feature activation+0.000
other
Token other
Feature activation+0.000
iTunes
Token iTunes
Feature activation+0.000
Store
Token Store
Feature activation+0.000
content
Token content
Feature activation+0.000
.
Token.
Feature activation+0.000
The
TokenThe
Feature activation+0.000
App
Token App
Feature activation+0.000
Store
Token Store
Feature activation+0.000
took
Token took
Feature activation+0.000
a
Token a
Feature activation+0.000
?
Token?
Feature activation+0.000
They
Token They
Feature activation+0.000
must
Token must
Feature activation+0.000
not
Token not
Feature activation+0.000
know
Token know
Feature activation+0.000
their
Token their
Feature activation+0.000
audience
Token audience
Feature activation+0.000
#
Token #
Feature activation+0.000
MAG
TokenMAG
Feature activation+0.000
A
TokenA
Feature activation+0.000
#
Token #
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
infrastructure
Token infrastructure
Feature activation+0.000
for
Token for
Feature activation+0.000
network
Token network
Feature activation+0.000
database
Token database
Feature activation+0.000
storage
Token storage
Feature activation+0.000
,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.000
implementing
Token implementing
Feature activation+0.000
a
Token a
Feature activation+0.000
simplified
Token simplified
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
Ok
Token Ok
Feature activation+0.000
azaki
Tokenazaki
Feature activation+0.000
,
Token,
Feature activation+0.000
A
Token A
Feature activation+0.000
ichi
Tokenichi
Feature activation+0.000
Pre
Token Pre
Feature activation+0.000
fecture
Tokenfecture
Feature activation+0.000
,
Token,
Feature activation+0.000
stressed
Token stressed
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 H3.5: (feature 5823)

TOP ACTIVATIONS
MAX = 4.890

your
Token your
Feature activation+0.000
team
Token team
Feature activation+0.000
gives
Token gives
Feature activation+0.216
,
Token,
Feature activation+0.000
the
Token the
Feature activation+1.692
higher
Token higher
Feature activation+4.890
amount
Token amount
Feature activation+0.038
of
Token of
Feature activation+0.000
balls
Token balls
Feature activation+0.000
of
Token of
Feature activation+0.000
Premier
Token Premier
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
reach
Token reach
Feature activation+0.162
,
Token,
Feature activation+0.000
the
Token the
Feature activation+1.612
stronger
Token stronger
Feature activation+4.544
the
Token the
Feature activation+0.937
64
Token 64
Feature activation+0.000
community
Token community
Feature activation+0.000
becomes
Token becomes
Feature activation+1.724
.
Token.
Feature activation+0.002
number
Token number
Feature activation+0.000
on
Token on
Feature activation+0.000
defense
Token defense
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.651
better
Token better
Feature activation+4.141
the
Token the
Feature activation+0.378
defense
Token defense
Feature activation+0.000
.
Token.
Feature activation+0.000
Why
Token Why
Feature activation+0.000
the
Token the
Feature activation+0.000
collisions
Token collisions
Feature activation+0.000
they
Token they
Feature activation+0.000
undergo
Token undergo
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+1.522
slower
Token slower
Feature activation+4.008
they
Token they
Feature activation+0.000
go
Token go
Feature activation+0.325
.
Token.
Feature activation+0.021
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
alcohol
Token alcohol
Feature activation+0.000
is
Token is
Feature activation+0.000
consumed
Token consumed
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.698
higher
Token higher
Feature activation+3.761
the
Token the
Feature activation+0.601
risk
Token risk
Feature activation+0.000
of
Token of
Feature activation+0.000
early
Token early
Feature activation+0.000
death
Token death
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
,
Token,
Feature activation+0.072
the
Token the
Feature activation+1.988
more
Token more
Feature activation+3.432
you
Token you
Feature activation+0.075
will
Token will
Feature activation+0.856
realise
Token realise
Feature activation+0.206
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
damage
Token damage
Feature activation+0.000
you
Token you
Feature activation+0.000
give
Token give
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.908
higher
Token higher
Feature activation+3.427
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
balls
Token balls
Feature activation+0.000
of
Token of
Feature activation+0.000
Premier
Token Premier
Feature activation+0.000
or
Token or
Feature activation+0.183
contact
Token contact
Feature activation+0.362
lenses
Token lenses
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.632
more
Token more
Feature activation+3.349
you
Token you
Feature activation+0.033
need
Token need
Feature activation+0.000
the
Token the
Feature activation+0.883
cloud
Token cloud
Feature activation+0.000
to
Token to
Feature activation+0.143
people
Token people
Feature activation+0.000
reporting
Token reporting
Feature activation+0.000
are
Token are
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+1.495
more
Token more
Feature activation+3.200
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.633
continue
Token continue
Feature activation+0.059
to
Token to
Feature activation+0.000
pursue
Token pursue
Feature activation+0.000
the
Token the
Feature activation+0.000
post
Token post
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.690
more
Token more
Feature activation+2.870
likely
Token likely
Feature activation+0.456
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
shared
Token shared
Feature activation+0.000
.
Token.
Feature activation+0.000
depressed
Token depressed
Feature activation+0.000
they
Token they
Feature activation+0.000
feel
Token feel
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.773
more
Token more
Feature activation+2.704
chocolate
Token chocolate
Feature activation+0.000
they
Token they
Feature activation+0.000
tend
Token tend
Feature activation+1.030
to
Token to
Feature activation+0.028
eat
Token eat
Feature activation+0.145
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
data
Token data
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+1.057
more
Token more
Feature activation+2.451
we
Token we
Feature activation+0.040
are
Token are
Feature activation+0.069
convinced
Token convinced
Feature activation+0.211
your
Token your
Feature activation+0.102
logo
Token logo
Feature activation+0.000
arger
Tokenarger
Feature activation+0.000
areas
Token areas
Feature activation+0.000
will
Token will
Feature activation+0.152
give
Token give
Feature activation+0.089
you
Token you
Feature activation+0.139
more
Token more
Feature activation+2.388
flexibility
Token flexibility
Feature activation+0.054
for
Token for
Feature activation+0.000
navigation
Token navigation
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.121
away
Token away
Feature activation+0.000
a
Token a
Feature activation+0.000
release
Token release
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.412
less
Token less
Feature activation+2.309
certain
Token certain
Feature activation+0.000
is
Token is
Feature activation+0.083
the
Token the
Feature activation+0.593
information
Token information
Feature activation+0.238
,
Token,
Feature activation+0.158
,
Token,
Feature activation+0.000
fewer
Token fewer
Feature activation+1.036
jobs
Token jobs
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.304
less
Token less
Feature activation+2.152
protection
Token protection
Feature activation+0.000
of
Token of
Feature activation+0.000
religious
Token religious
Feature activation+0.000
freedom
Token freedom
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
movement
Token movement
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.726
more
Token more
Feature activation+2.113
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.381
creep
Token creep
Feature activation+0.188
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
with
Token with
Feature activation+0.000
slightly
Token slightly
Feature activation+0.000
fewer
Token fewer
Feature activation+0.453
guns
Token guns
Feature activation+0.000
and
Token and
Feature activation+0.122
more
Token more
Feature activation+2.112
missiles
Token missiles
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
a
Token a
Feature activation+0.237
person
Token person
Feature activation+0.000
is
Token is
Feature activation+0.095
,
Token,
Feature activation+0.209
the
Token the
Feature activation+0.646
better
Token better
Feature activation+2.027
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
likely
Token likely
Feature activation+0.260
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
better
Token better
Feature activation+1.905
informed
Token informed
Feature activation+0.000
on
Token on
Feature activation+0.000
policy
Token policy
Feature activation+0.000
,
Token,
Feature activation+0.000
more
Token more
Feature activation+2.006
self
Token self
Feature activation+0.000
-
Token-
Feature activation+0.000
dis
Tokendis
Feature activation+0.000
cipl
Tokencipl
Feature activation+0.000
ined
Tokenined
Feature activation+0.000
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
,
Token,
Feature activation+0.072
the
Token the
Feature activation+1.988
more
Token more
Feature activation+3.432
you
Token you
Feature activation+0.075
will
Token will
Feature activation+0.856
realise
Token realise
Feature activation+0.206
if
Token if
Feature activation+0.000

Top DFA by src position
MAX = 4.990

inflicted
Token inflicted
Feature activation-0.002
Top resid features:
by
Token by
Feature activation+0.001
Top resid features:
teams
Token teams
Feature activation-0.004
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
The
Token The
Feature activation-0.014
Top resid features:
more
Token more
Feature activation+4.990
Top resid features:
damage
Token damage
Feature activation+0.006
Top resid features:
your
Token your
Feature activation-0.002
Top resid features:
team
Token team
Feature activation+0.002
Top resid features:
gives
Token gives
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.162
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
huge
Token huge
Feature activation+0.003
Top resid features:
favor
Token favor
Feature activation-0.001
Top resid features:
!
Token!
Feature activation+0.008
Top resid features:
The
Token The
Feature activation+0.001
Top resid features:
more
Token more
Feature activation+4.672
Top resid features:
people
Token people
Feature activation+0.007
Top resid features:
we
Token we
Feature activation-0.001
Top resid features:
can
Token can
Feature activation+0.008
Top resid features:
reach
Token reach
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.127
Top resid features:
offense
Token offense
Feature activation-0.011
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Conversely
Token Conversely
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
more
Token more
Feature activation+4.455
Top resid features:
negative
Token negative
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
DV
Token DV
Feature activation-0.015
Top resid features:
OA
TokenOA
Feature activation-0.012
Top resid features:
number
Token number
Feature activation-0.005
Top resid features:
continued
Token continued
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
âĢ
Token âĢ
Feature activation+0.013
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation-0.003
Top resid features:
more
Token more
Feature activation+4.211
Top resid features:
collisions
Token collisions
Feature activation-0.009
Top resid features:
they
Token they
Feature activation+0.003
Top resid features:
undergo
Token undergo
Feature activation-0.012
Top resid features:
,
Token,
Feature activation+0.126
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
cancer
Token cancer
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
And
Token And
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
more
Token more
Feature activation+3.842
Top resid features:
alcohol
Token alcohol
Feature activation-0.001
Top resid features:
is
Token is
Feature activation-0.002
Top resid features:
consumed
Token consumed
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.127
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
comes
Token comes
Feature activation-0.002
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
love
Token love
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
The
Token The
Feature activation+0.001
Top resid features:
more
Token more
Feature activation+2.458
Top resid features:
you
Token you
Feature activation-0.001
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
know
Token know
Feature activation+0.002
Top resid features:
a
Token a
Feature activation+0.011
Top resid features:
inflicted
Token inflicted
Feature activation-0.002
Top resid features:
by
Token by
Feature activation+0.003
Top resid features:
teams
Token teams
Feature activation-0.004
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.004
Top resid features:
The
Token The
Feature activation-0.001
Top resid features:
more
Token more
Feature activation+2.170
Top resid features:
damage
Token damage
Feature activation+0.003
Top resid features:
your
Token your
Feature activation-0.001
Top resid features:
team
Token team
Feature activation-0.000
Top resid features:
gives
Token gives
Feature activation+0.002
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
working
Token working
Feature activation-0.003
Top resid features:
on
Token on
Feature activation-0.000
Top resid features:
AR
Token AR
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
The
Token The
Feature activation+0.002
Top resid features:
closer
Token closer
Feature activation+3.486
Top resid features:
you
Token you
Feature activation+0.001
Top resid features:
get
Token get
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
wearable
Token wearable
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
ľ
Tokenľ
Feature activation-0.002
Top resid features:
The
TokenThe
Feature activation-0.004
Top resid features:
more
Token more
Feature activation+2.184
Top resid features:
principled
Token principled
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
reporting
Token reporting
Feature activation-0.000
Top resid features:
are
Token are
Feature activation-0.001
Top resid features:
...
Token...
Feature activation-0.002
Top resid features:
odds
Token odds
Feature activation-0.017
Top resid features:
are
Token are
Feature activation-0.010
Top resid features:
that
Token that
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
more
Token more
Feature activation+1.598
Top resid features:
embarrassing
Token embarrassing
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
post
Token post
Feature activation+0.008
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.118
Top resid features:
ressed
Tokenressed
Feature activation+0.001
Top resid features:
peers
Token peers
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
And
Token And
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
more
Token more
Feature activation+1.713
Top resid features:
depressed
Token depressed
Feature activation+0.013
Top resid features:
they
Token they
Feature activation+0.005
Top resid features:
feel
Token feel
Feature activation-0.007
Top resid features:
,
Token,
Feature activation+0.114
Top resid features:
the
Token the
Feature activation-0.025
Top resid features:
AT
TokenAT
Feature activation-0.004
Top resid features:
&
Token&
Feature activation-0.001
Top resid features:
T
TokenT
Feature activation-0.004
Top resid features:
-
Token -
Feature activation+0.004
Top resid features:
The
Token The
Feature activation-0.004
Top resid features:
more
Token more
Feature activation+1.595
Top resid features:
we
Token we
Feature activation+0.004
Top resid features:
look
Token look
Feature activation+0.012
Top resid features:
at
Token at
Feature activation+0.018
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
data
Token data
Feature activation-0.005
Top resid features:
want
Token want
Feature activation-0.002
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
download
Token download
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
L
Token L
Feature activation+0.012
Top resid features:
arger
Tokenarger
Feature activation+2.624
Top resid features:
areas
Token areas
Feature activation+0.018
Top resid features:
will
Token will
Feature activation+0.022
Top resid features:
give
Token give
Feature activation-0.006
Top resid features:
you
Token you
Feature activation+0.020
Top resid features:
more
Token more
Feature activation+0.091
Top resid features:
come
Token come
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Remember
Token Remember
Feature activation-0.019
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
further
Token further
Feature activation+2.466
Top resid features:
away
Token away
Feature activation+0.084
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
release
Token release
Feature activation-0.017
Top resid features:
is
Token is
Feature activation+0.064
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
exchanges
Token exchanges
Feature activation-0.010
Top resid features:
mean
Token mean
Feature activation-0.029
Top resid features:
higher
Token higher
Feature activation+1.068
Top resid features:
taxes
Token taxes
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
fewer
Token fewer
Feature activation+1.415
Top resid features:
jobs
Token jobs
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.087
Top resid features:
and
Token and
Feature activation+0.051
Top resid features:
less
Token less
Feature activation-0.041
Top resid features:
protection
Token protection
Feature activation+0.000
Top resid features:
where
Token where
Feature activation+0.007
Top resid features:
it
Token it
Feature activation-0.004
Top resid features:
starts
Token starts
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
The
Token The
Feature activation+0.002
Top resid features:
more
Token more
Feature activation+1.470
Top resid features:
society
Token society
Feature activation+0.006
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
general
Token general
Feature activation+0.001
Top resid features:
becomes
Token becomes
Feature activation+0.027
Top resid features:
aware
Token aware
Feature activation-0.006
Top resid features:
rugged
Token rugged
Feature activation-0.014
Top resid features:
combat
Token combat
Feature activation-0.003
Top resid features:
ship
Token ship
Feature activation-0.001
Top resid features:
with
Token with
Feature activation+0.068
Top resid features:
slightly
Token slightly
Feature activation+0.014
Top resid features:
fewer
Token fewer
Feature activation+1.234
Top resid features:
guns
Token guns
Feature activation+0.022
Top resid features:
and
Token and
Feature activation+0.089
Top resid features:
more
Token more
Feature activation-0.029
Top resid features:
missiles
Token missiles
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.001
Top resid features:
vocabulary
Token vocabulary
Feature activation-0.005
Top resid features:
range
Token range
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
The
Token The
Feature activation-0.003
Top resid features:
higher
Token higher
Feature activation+2.034
Top resid features:
up
Token up
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
social
Token social
Feature activation+0.001
Top resid features:
or
Token or
Feature activation+0.001
Top resid features:
management
Token management
Feature activation-0.010
Top resid features:
to
Token to
Feature activation+0.017
Top resid features:
be
Token be
Feature activation-0.017
Top resid features:
more
Token more
Feature activation+0.361
Top resid features:
presidential
Token presidential
Feature activation+0.003
Top resid features:
:
Token:
Feature activation+0.066
Top resid features:
better
Token better
Feature activation+1.461
Top resid features:
informed
Token informed
Feature activation-0.026
Top resid features:
on
Token on
Feature activation+0.016
Top resid features:
policy
Token policy
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.092
Top resid features:
more
Token more
Feature activation+0.420
Top resid features:
comes
Token comes
Feature activation-0.007
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
love
Token love
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
The
Token The
Feature activation-0.012
Top resid features:
more
Token more
Feature activation+2.251
Top resid features:
you
Token you
Feature activation-0.007
Top resid features:
get
Token get
Feature activation+0.010
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
know
Token know
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.019
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.04

Head 2: 0.05

Head 3: 0.05

Head 4: 0.03

Head 5: 0.46

Head 6: 0.07

Head 7: 0.05

Head 8: 0.06

Head 9: 0.03

Head 10: 0.08

Head 11: 0.06

Positive logits

izons2.24

inventoryQuantity2.21

decreases1.98

increases1.97

efficiency1.90

vitamins1.87

decrease1.83

reductions1.82

absorb1.79

gains1.77

antioxidant1.75

ripple1.74

increase1.73

Decre1.71

esity1.69

reorgan1.68

changes1.68

antioxidants1.67

Increase1.66

Recession1.66

Negative logits

agent-1.93

andise-1.90

submit-1.82

agents-1.80

asta-1.73

brance-1.69

authorized-1.68

swearing-1.68

andestine-1.67

intent-1.67

usb-1.66

iverpool-1.66

awoke-1.65

beer-1.64

amera-1.64

Bastard-1.63

NOTICE-1.63

WARNING-1.60

irlf-1.59

afety-1.57

INTERVAL 4.401 - 4.890
CONTAINS 0.000%

we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
reach
Token reach
Feature activation+0.162
,
Token,
Feature activation+0.000
the
Token the
Feature activation+1.612
stronger
Token stronger
Feature activation+4.544
the
Token the
Feature activation+0.937
64
Token 64
Feature activation+0.000
community
Token community
Feature activation+0.000
becomes
Token becomes
Feature activation+1.724
.
Token.
Feature activation+0.002
your
Token your
Feature activation+0.000
team
Token team
Feature activation+0.000
gives
Token gives
Feature activation+0.216
,
Token,
Feature activation+0.000
the
Token the
Feature activation+1.692
higher
Token higher
Feature activation+4.890
amount
Token amount
Feature activation+0.038
of
Token of
Feature activation+0.000
balls
Token balls
Feature activation+0.000
of
Token of
Feature activation+0.000
Premier
Token Premier
Feature activation+0.000

INTERVAL 3.912 - 4.401
CONTAINS 0.000%

number
Token number
Feature activation+0.000
on
Token on
Feature activation+0.000
defense
Token defense
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.651
better
Token better
Feature activation+4.141
the
Token the
Feature activation+0.378
defense
Token defense
Feature activation+0.000
.
Token.
Feature activation+0.000
Why
Token Why
Feature activation+0.000
the
Token the
Feature activation+0.000
collisions
Token collisions
Feature activation+0.000
they
Token they
Feature activation+0.000
undergo
Token undergo
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+1.522
slower
Token slower
Feature activation+4.008
they
Token they
Feature activation+0.000
go
Token go
Feature activation+0.325
.
Token.
Feature activation+0.021
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000

INTERVAL 3.423 - 3.912
CONTAINS 0.000%

alcohol
Token alcohol
Feature activation+0.000
is
Token is
Feature activation+0.000
consumed
Token consumed
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.698
higher
Token higher
Feature activation+3.761
the
Token the
Feature activation+0.601
risk
Token risk
Feature activation+0.000
of
Token of
Feature activation+0.000
early
Token early
Feature activation+0.000
death
Token death
Feature activation+0.000
damage
Token damage
Feature activation+0.000
you
Token you
Feature activation+0.000
give
Token give
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.908
higher
Token higher
Feature activation+3.427
amount
Token amount
Feature activation+0.000
of
Token of
Feature activation+0.000
balls
Token balls
Feature activation+0.000
of
Token of
Feature activation+0.000
Premier
Token Premier
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
,
Token,
Feature activation+0.072
the
Token the
Feature activation+1.988
more
Token more
Feature activation+3.432
you
Token you
Feature activation+0.075
will
Token will
Feature activation+0.856
realise
Token realise
Feature activation+0.206
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000

INTERVAL 2.934 - 3.423
CONTAINS 0.000%

or
Token or
Feature activation+0.183
contact
Token contact
Feature activation+0.362
lenses
Token lenses
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.632
more
Token more
Feature activation+3.349
you
Token you
Feature activation+0.033
need
Token need
Feature activation+0.000
the
Token the
Feature activation+0.883
cloud
Token cloud
Feature activation+0.000
to
Token to
Feature activation+0.143
people
Token people
Feature activation+0.000
reporting
Token reporting
Feature activation+0.000
are
Token are
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+1.495
more
Token more
Feature activation+3.200
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.633
continue
Token continue
Feature activation+0.059
to
Token to
Feature activation+0.000
pursue
Token pursue
Feature activation+0.000

INTERVAL 2.445 - 2.934
CONTAINS 0.000%

depressed
Token depressed
Feature activation+0.000
they
Token they
Feature activation+0.000
feel
Token feel
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.773
more
Token more
Feature activation+2.704
chocolate
Token chocolate
Feature activation+0.000
they
Token they
Feature activation+0.000
tend
Token tend
Feature activation+1.030
to
Token to
Feature activation+0.028
eat
Token eat
Feature activation+0.145
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
data
Token data
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+1.057
more
Token more
Feature activation+2.451
we
Token we
Feature activation+0.040
are
Token are
Feature activation+0.069
convinced
Token convinced
Feature activation+0.211
your
Token your
Feature activation+0.102
logo
Token logo
Feature activation+0.000
the
Token the
Feature activation+0.000
post
Token post
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.690
more
Token more
Feature activation+2.870
likely
Token likely
Feature activation+0.456
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
shared
Token shared
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.956 - 2.445
CONTAINS 0.001%

arger
Tokenarger
Feature activation+0.000
areas
Token areas
Feature activation+0.000
will
Token will
Feature activation+0.152
give
Token give
Feature activation+0.089
you
Token you
Feature activation+0.139
more
Token more
Feature activation+2.388
flexibility
Token flexibility
Feature activation+0.054
for
Token for
Feature activation+0.000
navigation
Token navigation
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.121
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
movement
Token movement
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.726
more
Token more
Feature activation+2.113
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.381
creep
Token creep
Feature activation+0.188
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
with
Token with
Feature activation+0.000
slightly
Token slightly
Feature activation+0.000
fewer
Token fewer
Feature activation+0.453
guns
Token guns
Feature activation+0.000
and
Token and
Feature activation+0.122
more
Token more
Feature activation+2.112
missiles
Token missiles
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
mer
Tokenmer
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.456
easier
Token easier
Feature activation+1.966
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.498
be
Token be
Feature activation+0.100
to
Token to
Feature activation+0.000
re
Token re
Feature activation+0.232
a
Token a
Feature activation+0.237
person
Token person
Feature activation+0.000
is
Token is
Feature activation+0.095
,
Token,
Feature activation+0.209
the
Token the
Feature activation+0.646
better
Token better
Feature activation+2.027
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
likely
Token likely
Feature activation+0.260
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000

INTERVAL 1.467 - 1.956
CONTAINS 0.002%

-
Token-
Feature activation+0.000
dis
Tokendis
Feature activation+0.000
cipl
Tokencipl
Feature activation+0.000
ined
Tokenined
Feature activation+0.000
and
Token and
Feature activation+0.000
less
Token less
Feature activation+1.788
thin
Token thin
Feature activation+0.007
-
Token-
Feature activation+0.000
skinned
Tokenskinned
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
elegant
Token elegant
Feature activation+0.000
,
Token,
Feature activation+0.000
lower
Token lower
Feature activation+1.575
-
Token-
Feature activation+0.000
alcohol
Tokenalcohol
Feature activation+0.000
style
Token style
Feature activation+0.000
of
Token of
Feature activation+0.000
wine
Token wine
Feature activation+0.000
more
Token more
Feature activation+0.039
collisions
Token collisions
Feature activation+0.000
they
Token they
Feature activation+0.000
undergo
Token undergo
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+1.522
slower
Token slower
Feature activation+4.008
they
Token they
Feature activation+0.000
go
Token go
Feature activation+0.325
.
Token.
Feature activation+0.021
âĢ
TokenâĢ
Feature activation+0.000
damage
Token damage
Feature activation+0.000
your
Token your
Feature activation+0.000
team
Token team
Feature activation+0.000
gives
Token gives
Feature activation+0.216
,
Token,
Feature activation+0.000
the
Token the
Feature activation+1.692
higher
Token higher
Feature activation+4.890
amount
Token amount
Feature activation+0.038
of
Token of
Feature activation+0.000
balls
Token balls
Feature activation+0.000
of
Token of
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
more
Token more
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
:
Token:
Feature activation+0.000
better
Token better
Feature activation+1.905
informed
Token informed
Feature activation+0.000
on
Token on
Feature activation+0.000
policy
Token policy
Feature activation+0.000
,
Token,
Feature activation+0.000
more
Token more
Feature activation+2.006

INTERVAL 0.978 - 1.467
CONTAINS 0.005%

are
Token are
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
buy
Token buy
Feature activation+0.000
less
Token less
Feature activation+1.038
furniture
Token furniture
Feature activation+0.000
,
Token,
Feature activation+0.062
far
Token far
Feature activation+0.487
less
Token less
Feature activation+0.806
lawn
Token lawn
Feature activation+0.000
readily
Token readily
Feature activation+0.000
to
Token to
Feature activation+0.000
winds
Token winds
Feature activation+0.000
and
Token and
Feature activation+0.107
is
Token is
Feature activation+0.019
more
Token more
Feature activation+1.014
easily
Token easily
Feature activation+0.425
broken
Token broken
Feature activation+0.217
up
Token up
Feature activation+0.000
,
Token,
Feature activation+0.020
âĢ
TokenâĢ
Feature activation+0.000
people
Token people
Feature activation+0.000
with
Token with
Feature activation+0.000
disabilities
Token disabilities
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
less
Token less
Feature activation+1.365
congest
Token congest
Feature activation+0.000
ed
Tokened
Feature activation+0.000
road
Token road
Feature activation+0.000
ways
Tokenways
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
finding
Token finding
Feature activation+0.000
better
Token better
Feature activation+0.962
and
Token and
Feature activation+0.000
more
Token more
Feature activation+1.168
proportion
Token proportion
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
ways
Token ways
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
pitchers
Token pitchers
Feature activation+0.000
are
Token are
Feature activation+0.000
considerably
Token considerably
Feature activation+0.000
narrower
Token narrower
Feature activation+0.000
,
Token,
Feature activation+0.000
less
Token less
Feature activation+1.284
sc
Token sc
Feature activation+0.000
ented
Tokenented
Feature activation+0.000
,
Token,
Feature activation+0.000
contain
Token contain
Feature activation+0.000
less
Token less
Feature activation+0.801

INTERVAL 0.489 - 0.978
CONTAINS 0.013%

used
Token used
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
faster
Token faster
Feature activation+0.000
,
Token,
Feature activation+0.000
better
Token better
Feature activation+0.785
,
Token,
Feature activation+0.000
smarter
Token smarter
Feature activation+0.562
,
Token,
Feature activation+0.000
cheaper
Token cheaper
Feature activation+0.948
,
Token,
Feature activation+0.000
Tuesday
TokenTuesday
Feature activation+0.000
:
Token:
Feature activation+0.000
More
Token More
Feature activation+0.095
heat
Token heat
Feature activation+0.000
,
Token,
Feature activation+0.000
more
Token more
Feature activation+0.911
humidity
Token humidity
Feature activation+0.000
.
Token.
Feature activation+0.228
High
Token High
Feature activation+0.181
s
Tokens
Feature activation+0.000
88
Token 88
Feature activation+0.000
are
Token are
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.456
easier
Token easier
Feature activation+1.966
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.498
be
Token be
Feature activation+0.100
to
Token to
Feature activation+0.000
re
Token re
Feature activation+0.232
int
Tokenint
Feature activation+0.000
igrate
Tokenigrate
Feature activation+0.004
likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.000
use
Token use
Feature activation+0.000
drones
Token drones
Feature activation+0.000
,
Token,
Feature activation+0.000
more
Token more
Feature activation+0.758
likely
Token likely
Feature activation+0.408
to
Token to
Feature activation+0.000
bomb
Token bomb
Feature activation+0.000
our
Token our
Feature activation+0.000
enemies
Token enemies
Feature activation+0.000
be
Token be
Feature activation+0.000
replaced
Token replaced
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
higher
Token higher
Feature activation+0.525
availability
Token availability
Feature activation+0.000
and
Token and
Feature activation+0.000
ease
Token ease
Feature activation+0.008
of
Token of
Feature activation+0.000
switching
Token switching
Feature activation+0.000

INTERVAL 0.000 - 0.489
CONTAINS 99.978%

game
Token game
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Redskins
Token Redskins
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Through
TokenThrough
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
fine
Token fine
Feature activation+0.000
leg
Token leg
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
I
Token I
Feature activation+0.000
never
Token never
Feature activation+0.000
knew
Token knew
Feature activation+0.000
before
Token before
Feature activation+0.000
!
Token!
Feature activation+0.000
The
Token The
Feature activation+0.000
pageant
Token pageant
Feature activation+0.000
make
Token make
Feature activation+0.000
sure
Token sure
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
backup
Token backup
Feature activation+0.000
plans
Token plans
Feature activation+0.000
.
Token.
Feature activation+0.000
David
Token David
Feature activation+0.000
Var
Token Var
Feature activation+0.000
ric
Tokenric
Feature activation+0.000
chio
Tokenchio
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
by
Token by
Feature activation+0.000
The
Token The
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Times
Token Times
Feature activation+0.000
has
Token has
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
tour
Token tour
Feature activation+0.000
party
Token party
Feature activation+0.000
that
Token that
Feature activation+0.000
travels
Token travels
Feature activation+0.000
to
Token to
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 6 in H3.5: (feature 1823)

TOP ACTIVATIONS
MAX = 4.124

from
Token from
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
,
Token,
Feature activation+0.000
Eck
Token Eck
Feature activation+0.470
ert
Tokenert
Feature activation+0.184
responded
Token responded
Feature activation+4.124
:
Token:
Feature activation+0.974
"
Token "
Feature activation+0.783
We
TokenWe
Feature activation+0.000
're
Token're
Feature activation+0.000
going
Token going
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
solution
Token solution
Feature activation+0.066
,
Token,
Feature activation+0.744
he
Token he
Feature activation+1.642
replied
Token replied
Feature activation+4.065
:
Token:
Feature activation+1.300
âĢ
Token âĢ
Feature activation+0.256
ľ
Tokenľ
Feature activation+0.004
Well
TokenWell
Feature activation+1.128
âĢ¦
TokenâĢ¦
Feature activation+0.000
real
Token real
Feature activation+0.000
health
Token health
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
,
Token,
Feature activation+0.530
he
Token he
Feature activation+1.777
said
Token said
Feature activation+3.944
:
Token:
Feature activation+1.376
``
Token ``
Feature activation+1.213
I
TokenI
Feature activation+0.000
believe
Token believe
Feature activation+0.000
they
Token they
Feature activation+0.000
a
Token a
Feature activation+0.000
solo
Token solo
Feature activation+0.000
album
Token album
Feature activation+0.000
,
Token,
Feature activation+0.437
Phil
Token Phil
Feature activation+0.746
responded
Token responded
Feature activation+3.881
:
Token:
Feature activation+1.546
"
Token "
Feature activation+1.084
Yes
TokenYes
Feature activation+0.748
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
Tower
Token Tower
Feature activation+0.000
,
Token,
Feature activation+0.380
Chaff
Token Chaff
Feature activation+1.756
etz
Tokenetz
Feature activation+3.043
said
Token said
Feature activation+3.663
he
Token he
Feature activation+1.360
would
Token would
Feature activation+0.657
not
Token not
Feature activation+0.000
presupp
Token presupp
Feature activation+0.087
ose
Tokenose
Feature activation+0.318
the
Token the
Feature activation+0.197
upcoming
Token upcoming
Feature activation+0.000
movies
Token movies
Feature activation+0.000
,
Token,
Feature activation+0.803
Johnson
Token Johnson
Feature activation+1.976
said
Token said
Feature activation+3.284
,
Token,
Feature activation+1.214
âĢ
Token âĢ
Feature activation+0.046
ľ
Tokenľ
Feature activation+0.073
I
TokenI
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
to
Token to
Feature activation+0.000
Face
Token Face
Feature activation+0.000
,
Token,
Feature activation+0.288
W
Token W
Feature activation+1.074
augh
Tokenaugh
Feature activation+0.804
replies
Token replies
Feature activation+3.247
"
Token "
Feature activation+1.081
P
TokenP
Feature activation+0.000
overty
Tokenoverty
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
orted
Tokenorted
Feature activation+0.146
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.314
Ŀ
TokenĿ
Feature activation+0.378
Podesta
Token Podesta
Feature activation+1.961
said
Token said
Feature activation+3.203
:
Token:
Feature activation+1.224
âĢ
Token âĢ
Feature activation+0.926
ľ
Tokenľ
Feature activation+0.305
A
TokenA
Feature activation+0.178
foreign
Token foreign
Feature activation+0.000
for
Token for
Feature activation+0.000
exploration
Token exploration
Feature activation+0.000
currently
Token currently
Feature activation+0.402
,
Token,
Feature activation+0.464
he
Token he
Feature activation+1.537
told
Token told
Feature activation+3.138
us
Token us
Feature activation+1.210
he
Token he
Feature activation+1.339
favors
Token favors
Feature activation+0.500
Chile
Token Chile
Feature activation+0.000
,
Token,
Feature activation+0.197
von
Token von
Feature activation+1.374
Hol
Token Hol
Feature activation+0.396
z
Tokenz
Feature activation+0.475
haus
Tokenhaus
Feature activation+0.251
en
Tokenen
Feature activation+1.087
explained
Token explained
Feature activation+3.116
what
Token what
Feature activation+1.209
made
Token made
Feature activation+0.000
it
Token it
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
and
Token and
Feature activation+0.000
illed
Tokenilled
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
Tower
Token Tower
Feature activation+0.000
,
Token,
Feature activation+0.380
Chaff
Token Chaff
Feature activation+1.756
etz
Tokenetz
Feature activation+3.043
said
Token said
Feature activation+3.663
he
Token he
Feature activation+1.360
would
Token would
Feature activation+0.657
not
Token not
Feature activation+0.000
presupp
Token presupp
Feature activation+0.087
such
Token such
Feature activation+0.000
dri
Token dri
Feature activation+0.000
vel
Tokenvel
Feature activation+0.000
,
Token,
Feature activation+0.438
she
Token she
Feature activation+0.955
said
Token said
Feature activation+3.022
that
Token that
Feature activation+0.947
her
Token her
Feature activation+0.000
teacher
Token teacher
Feature activation+0.000
had
Token had
Feature activation+0.320
asked
Token asked
Feature activation+0.000
caused
Token caused
Feature activation+0.000
the
Token the
Feature activation+0.000
deaths
Token deaths
Feature activation+0.000
,
Token,
Feature activation+0.241
Gupta
Token Gupta
Feature activation+0.165
replied
Token replied
Feature activation+2.865
,
Token,
Feature activation+0.437
"
Token "
Feature activation+0.715
In
TokenIn
Feature activation+0.029
adequ
Tokenadequ
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
drone
Token drone
Feature activation+0.000
stunt
Token stunt
Feature activation+0.000
,
Token,
Feature activation+0.290
Tah
Token Tah
Feature activation+0.878
iri
Tokeniri
Feature activation+1.364
told
Token told
Feature activation+2.857
Reuters
Token Reuters
Feature activation+0.000
:
Token:
Feature activation+0.737
âĢ
Token âĢ
Feature activation+0.166
ľ
Tokenľ
Feature activation+0.000
Not
TokenNot
Feature activation+0.000
this
Token this
Feature activation+0.036
contradiction
Token contradiction
Feature activation+0.000
,
Token,
Feature activation+0.269
and
Token and
Feature activation+0.509
he
Token he
Feature activation+0.713
said
Token said
Feature activation+2.618
Sam
Token Sam
Feature activation+0.000
was
Token was
Feature activation+0.334
lying
Token lying
Feature activation+0.161
to
Token to
Feature activation+0.000
Dean
Token Dean
Feature activation+0.000
sometime
Token sometime
Feature activation+0.000
soon
Token soon
Feature activation+0.000
,
Token,
Feature activation+0.180
Lo
Token Lo
Feature activation+0.000
eb
Tokeneb
Feature activation+0.000
said
Token said
Feature activation+2.458
:
Token:
Feature activation+0.835
Ċ
TokenĊ
Feature activation+0.778
Ċ
TokenĊ
Feature activation+0.494
âĢ
TokenâĢ
Feature activation+0.105
ľ
Tokenľ
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
managed
Token managed
Feature activation+0.000
,
Token,
Feature activation+0.388
they
Token they
Feature activation+1.025
found
Token found
Feature activation+2.415
that
Token that
Feature activation+1.021
the
Token the
Feature activation+0.000
citizen
Token citizen
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
had
Token had
Feature activation+0.350
-
Token-
Feature activation+0.000
zone
Tokenzone
Feature activation+0.000
pronounce
Token pronounce
Feature activation+0.381
ments
Tokenments
Feature activation+0.000
,
Token,
Feature activation+0.265
Mr
Token Mr
Feature activation+2.278
.
Token.
Feature activation+1.086
Sch
Token Sch
Feature activation+0.410
ull
Tokenull
Feature activation+0.000
er
Tokener
Feature activation+0.000
,
Token,
Feature activation+0.822
Gaza
Token Gaza
Feature activation+0.000
,
Token,
Feature activation+0.502
had
Token had
Feature activation+0.441
two
Token two
Feature activation+0.000
standard
Token standard
Feature activation+0.144
responses
Token responses
Feature activation+2.123
:
Token:
Feature activation+0.678
irritation
Token irritation
Feature activation+0.411
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
else
Token else
Feature activation+0.000
a
Token a
Feature activation+0.000
question
Token question
Feature activation+0.174
about
Token about
Feature activation+0.608
terrorism
Token terrorism
Feature activation+0.000
,
Token,
Feature activation+0.966
Cohen
Token Cohen
Feature activation+2.066
had
Token had
Feature activation+1.733
this
Token this
Feature activation+0.555
to
Token to
Feature activation+0.155
say
Token say
Feature activation+1.059
as
Token as
Feature activation+0.162

Top DFA by src position
MAX = 4.326

ny
Tokenny
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Asked
TokenAsked
Feature activation+4.132
Top resid features:
about
Token about
Feature activation+0.367
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
legal
Token legal
Feature activation+0.002
Top resid features:
risks
Token risks
Feature activation+0.006
Top resid features:
contractors
Token contractors
Feature activation+0.004
Top resid features:
minority
Token minority
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
When
TokenWhen
Feature activation+0.051
Top resid features:
asked
Token asked
Feature activation+4.326
Top resid features:
for
Token for
Feature activation+0.134
Top resid features:
a
Token a
Feature activation+0.016
Top resid features:
solution
Token solution
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.119
Top resid features:
he
Token he
Feature activation+0.075
Top resid features:
another
Token another
Feature activation+0.000
Top resid features:
form
Token form
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Asked
TokenAsked
Feature activation+3.969
Top resid features:
why
Token why
Feature activation+0.355
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
former
Token former
Feature activation-0.020
Top resid features:
State
Token State
Feature activation-0.001
Top resid features:
Government
Token Government
Feature activation+0.000
Top resid features:
worth
Token worth
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.000
Top resid features:
."
Token."
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Asked
TokenAsked
Feature activation+3.831
Top resid features:
in
Token in
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.030
Top resid features:
2012
Token 2012
Feature activation-0.008
Top resid features:
interview
Token interview
Feature activation+0.253
Top resid features:
if
Token if
Feature activation+0.314
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
."
Token."
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Asked
TokenAsked
Feature activation+3.598
Top resid features:
whether
Token whether
Feature activation+0.401
Top resid features:
he
Token he
Feature activation+0.018
Top resid features:
believes
Token believes
Feature activation+0.023
Top resid features:
Obama
Token Obama
Feature activation+0.013
Top resid features:
illegally
Token illegally
Feature activation+0.010
Top resid features:
).
Token).
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
When
TokenWhen
Feature activation+0.067
Top resid features:
first
Token first
Feature activation-0.029
Top resid features:
asked
Token asked
Feature activation+3.251
Top resid features:
about
Token about
Feature activation+0.434
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
upcoming
Token upcoming
Feature activation+0.005
Top resid features:
movies
Token movies
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.093
Top resid features:
ease
Token ease
Feature activation+0.004
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
studio
Token studio
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.016
Top resid features:
Asked
Token Asked
Feature activation+3.210
Top resid features:
by
Token by
Feature activation+0.086
Top resid features:
John
Token John
Feature activation+0.005
Top resid features:
Freeman
Token Freeman
Feature activation+0.003
Top resid features:
why
Token why
Feature activation+0.500
Top resid features:
he
Token he
Feature activation+0.010
Top resid features:
Podesta
Token Podesta
Feature activation-0.023
Top resid features:
responded
Token responded
Feature activation+0.057
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Asked
TokenAsked
Feature activation+3.387
Top resid features:
what
Token what
Feature activation+0.107
Top resid features:
he
Token he
Feature activation+0.024
Top resid features:
meant
Token meant
Feature activation+0.040
Top resid features:
by
Token by
Feature activation+0.004
Top resid features:
âĢ
Token âĢ
Feature activation+0.005
Top resid features:
later
Token later
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
When
TokenWhen
Feature activation+0.051
Top resid features:
asked
Token asked
Feature activation+3.128
Top resid features:
about
Token about
Feature activation+0.376
Top resid features:
his
Token his
Feature activation+0.021
Top resid features:
favourite
Token favourite
Feature activation+0.017
Top resid features:
jurisdictions
Token jurisdictions
Feature activation+0.002
Top resid features:
for
Token for
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Advertisement
TokenAdvertisement
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
When
TokenWhen
Feature activation+0.052
Top resid features:
asked
Token asked
Feature activation+2.965
Top resid features:
about
Token about
Feature activation+0.569
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
design
Token design
Feature activation-0.013
Top resid features:
challenges
Token challenges
Feature activation+0.008
Top resid features:
for
Token for
Feature activation+0.013
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
."
Token."
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Asked
TokenAsked
Feature activation+2.846
Top resid features:
whether
Token whether
Feature activation+0.492
Top resid features:
he
Token he
Feature activation+0.062
Top resid features:
believes
Token believes
Feature activation+0.021
Top resid features:
Obama
Token Obama
Feature activation+0.030
Top resid features:
illegally
Token illegally
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
âĢ
TokenâĢ
Feature activation+0.031
Top resid features:
Ŀ
TokenĿ
Feature activation-0.006
Top resid features:
When
Token When
Feature activation+0.061
Top resid features:
I
Token I
Feature activation-0.018
Top resid features:
asked
Token asked
Feature activation+3.435
Top resid features:
her
Token her
Feature activation+0.004
Top resid features:
where
Token where
Feature activation+0.098
Top resid features:
she
Token she
Feature activation+0.009
Top resid features:
got
Token got
Feature activation+0.006
Top resid features:
such
Token such
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
When
TokenWhen
Feature activation+0.050
Top resid features:
our
Token our
Feature activation-0.012
Top resid features:
reported
Token reported
Feature activation+0.007
Top resid features:
asked
Token asked
Feature activation+3.133
Top resid features:
what
Token what
Feature activation+0.210
Top resid features:
caused
Token caused
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
deaths
Token deaths
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+0.098
Top resid features:
Bel
Token Bel
Feature activation+0.000
Top resid features:
grade
Tokengrade
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Asked
TokenAsked
Feature activation+2.684
Top resid features:
if
Token if
Feature activation+0.502
Top resid features:
he
Token he
Feature activation+0.033
Top resid features:
had
Token had
Feature activation+0.009
Top resid features:
been
Token been
Feature activation+0.009
Top resid features:
arrested
Token arrested
Feature activation+0.001
Top resid features:
save
Token save
Feature activation-0.006
Top resid features:
demon
Token demon
Feature activation-0.002
Top resid features:
Dean
Token Dean
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
We
Token We
Feature activation-0.000
Top resid features:
asked
Token asked
Feature activation+2.736
Top resid features:
Pad
Token Pad
Feature activation-0.001
Top resid features:
ale
Tokenale
Feature activation-0.000
Top resid features:
cki
Tokencki
Feature activation+0.005
Top resid features:
about
Token about
Feature activation+0.431
Top resid features:
this
Token this
Feature activation-0.016
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
In
TokenIn
Feature activation+0.010
Top resid features:
fact
Token fact
Feature activation-0.027
Top resid features:
,
Token,
Feature activation-0.017
Top resid features:
when
Token when
Feature activation+0.043
Top resid features:
asked
Token asked
Feature activation+2.781
Top resid features:
if
Token if
Feature activation+0.220
Top resid features:
fans
Token fans
Feature activation-0.003
Top resid features:
can
Token can
Feature activation-0.001
Top resid features:
expect
Token expect
Feature activation+0.018
Top resid features:
to
Token to
Feature activation+0.007
Top resid features:
effects
Token effects
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
When
Token When
Feature activation+0.048
Top resid features:
Australian
Token Australian
Feature activation-0.004
Top resid features:
scientists
Token scientists
Feature activation+0.010
Top resid features:
asked
Token asked
Feature activation+2.688
Top resid features:
people
Token people
Feature activation+0.001
Top resid features:
who
Token who
Feature activation+0.044
Top resid features:
had
Token had
Feature activation+0.014
Top resid features:
volunteered
Token volunteered
Feature activation+0.023
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
more
Token more
Feature activation-0.002
Top resid features:
surreal
Token surreal
Feature activation+0.004
Top resid features:
:
Token:
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
Asked
TokenAsked
Feature activation+1.834
Top resid features:
whether
Token whether
Feature activation+0.958
Top resid features:
such
Token such
Feature activation-0.016
Top resid features:
deliberate
Token deliberate
Feature activation+0.015
Top resid features:
misinformation
Token misinformation
Feature activation+0.010
Top resid features:
would
Token would
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Democrats
TokenDemocrats
Feature activation+0.009
Top resid features:
,
Token,
Feature activation-0.015
Top resid features:
when
Token when
Feature activation+0.039
Top resid features:
asked
Token asked
Feature activation+1.488
Top resid features:
a
Token a
Feature activation+0.021
Top resid features:
question
Token question
Feature activation+0.468
Top resid features:
about
Token about
Feature activation+0.319
Top resid features:
Israeli
Token Israeli
Feature activation+0.006
Top resid features:
operations
Token operations
Feature activation-0.005
Top resid features:
Georgia
Token Georgia
Feature activation-0.002
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Athens
Token Athens
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.033
Top resid features:
When
Token When
Feature activation+0.100
Top resid features:
asked
Token asked
Feature activation+1.706
Top resid features:
a
Token a
Feature activation+0.060
Top resid features:
question
Token question
Feature activation+0.266
Top resid features:
about
Token about
Feature activation+0.278
Top resid features:
terrorism
Token terrorism
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.175
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.05

Head 2: 0.06

Head 3: 0.02

Head 4: 0.05

Head 5: 0.46

Head 6: 0.05

Head 7: 0.05

Head 8: 0.05

Head 9: 0.05

Head 10: 0.09

Head 11: 0.04

Positive logits

answer3.12

Answer3.00

swer2.92

reply2.72

swers2.65

interviewer2.61

question2.61

replies2.56

Answer2.51

answered2.50

incred2.48

answering2.46

Answers2.42

replied2.39

rompt2.39

Response2.38

Ask2.35

asking2.35

answ2.28

answered2.26

Negative logits

domest-2.41

rebuilt-2.41

geographically-2.35

Travels-2.20

transpl-2.15

forestation-2.14

kefeller-2.11

relocated-2.04

surviving-1.99

compens-1.97

migr-1.91

nurt-1.88

conserv-1.87

civilization-1.87

brates-1.87

Yellowstone-1.86

Gutenberg-1.86

biodiversity-1.86

densely-1.86

rebuild-1.85

INTERVAL 3.712 - 4.124
CONTAINS 0.000%

real
Token real
Feature activation+0.000
health
Token health
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
,
Token,
Feature activation+0.530
he
Token he
Feature activation+1.777
said
Token said
Feature activation+3.944
:
Token:
Feature activation+1.376
``
Token ``
Feature activation+1.213
I
TokenI
Feature activation+0.000
believe
Token believe
Feature activation+0.000
they
Token they
Feature activation+0.000
a
Token a
Feature activation+0.000
solo
Token solo
Feature activation+0.000
album
Token album
Feature activation+0.000
,
Token,
Feature activation+0.437
Phil
Token Phil
Feature activation+0.746
responded
Token responded
Feature activation+3.881
:
Token:
Feature activation+1.546
"
Token "
Feature activation+1.084
Yes
TokenYes
Feature activation+0.748
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
from
Token from
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
,
Token,
Feature activation+0.000
Eck
Token Eck
Feature activation+0.470
ert
Tokenert
Feature activation+0.184
responded
Token responded
Feature activation+4.124
:
Token:
Feature activation+0.974
"
Token "
Feature activation+0.783
We
TokenWe
Feature activation+0.000
're
Token're
Feature activation+0.000
going
Token going
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
solution
Token solution
Feature activation+0.066
,
Token,
Feature activation+0.744
he
Token he
Feature activation+1.642
replied
Token replied
Feature activation+4.065
:
Token:
Feature activation+1.300
âĢ
Token âĢ
Feature activation+0.256
ľ
Tokenľ
Feature activation+0.004
Well
TokenWell
Feature activation+1.128
âĢ¦
TokenâĢ¦
Feature activation+0.000

INTERVAL 3.299 - 3.712
CONTAINS 0.000%

Trump
Token Trump
Feature activation+0.000
Tower
Token Tower
Feature activation+0.000
,
Token,
Feature activation+0.380
Chaff
Token Chaff
Feature activation+1.756
etz
Tokenetz
Feature activation+3.043
said
Token said
Feature activation+3.663
he
Token he
Feature activation+1.360
would
Token would
Feature activation+0.657
not
Token not
Feature activation+0.000
presupp
Token presupp
Feature activation+0.087
ose
Tokenose
Feature activation+0.318

INTERVAL 2.887 - 3.299
CONTAINS 0.001%

orted
Tokenorted
Feature activation+0.146
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.314
Ŀ
TokenĿ
Feature activation+0.378
Podesta
Token Podesta
Feature activation+1.961
said
Token said
Feature activation+3.203
:
Token:
Feature activation+1.224
âĢ
Token âĢ
Feature activation+0.926
ľ
Tokenľ
Feature activation+0.305
A
TokenA
Feature activation+0.178
foreign
Token foreign
Feature activation+0.000
the
Token the
Feature activation+0.197
upcoming
Token upcoming
Feature activation+0.000
movies
Token movies
Feature activation+0.000
,
Token,
Feature activation+0.803
Johnson
Token Johnson
Feature activation+1.976
said
Token said
Feature activation+3.284
,
Token,
Feature activation+1.214
âĢ
Token âĢ
Feature activation+0.046
ľ
Tokenľ
Feature activation+0.073
I
TokenI
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
illed
Tokenilled
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
Tower
Token Tower
Feature activation+0.000
,
Token,
Feature activation+0.380
Chaff
Token Chaff
Feature activation+1.756
etz
Tokenetz
Feature activation+3.043
said
Token said
Feature activation+3.663
he
Token he
Feature activation+1.360
would
Token would
Feature activation+0.657
not
Token not
Feature activation+0.000
presupp
Token presupp
Feature activation+0.087
for
Token for
Feature activation+0.000
exploration
Token exploration
Feature activation+0.000
currently
Token currently
Feature activation+0.402
,
Token,
Feature activation+0.464
he
Token he
Feature activation+1.537
told
Token told
Feature activation+3.138
us
Token us
Feature activation+1.210
he
Token he
Feature activation+1.339
favors
Token favors
Feature activation+0.500
Chile
Token Chile
Feature activation+0.000
,
Token,
Feature activation+0.197
such
Token such
Feature activation+0.000
dri
Token dri
Feature activation+0.000
vel
Tokenvel
Feature activation+0.000
,
Token,
Feature activation+0.438
she
Token she
Feature activation+0.955
said
Token said
Feature activation+3.022
that
Token that
Feature activation+0.947
her
Token her
Feature activation+0.000
teacher
Token teacher
Feature activation+0.000
had
Token had
Feature activation+0.320
asked
Token asked
Feature activation+0.000

INTERVAL 2.474 - 2.887
CONTAINS 0.000%

caused
Token caused
Feature activation+0.000
the
Token the
Feature activation+0.000
deaths
Token deaths
Feature activation+0.000
,
Token,
Feature activation+0.241
Gupta
Token Gupta
Feature activation+0.165
replied
Token replied
Feature activation+2.865
,
Token,
Feature activation+0.437
"
Token "
Feature activation+0.715
In
TokenIn
Feature activation+0.029
adequ
Tokenadequ
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
this
Token this
Feature activation+0.036
contradiction
Token contradiction
Feature activation+0.000
,
Token,
Feature activation+0.269
and
Token and
Feature activation+0.509
he
Token he
Feature activation+0.713
said
Token said
Feature activation+2.618
Sam
Token Sam
Feature activation+0.000
was
Token was
Feature activation+0.334
lying
Token lying
Feature activation+0.161
to
Token to
Feature activation+0.000
Dean
Token Dean
Feature activation+0.000
drone
Token drone
Feature activation+0.000
stunt
Token stunt
Feature activation+0.000
,
Token,
Feature activation+0.290
Tah
Token Tah
Feature activation+0.878
iri
Tokeniri
Feature activation+1.364
told
Token told
Feature activation+2.857
Reuters
Token Reuters
Feature activation+0.000
:
Token:
Feature activation+0.737
âĢ
Token âĢ
Feature activation+0.166
ľ
Tokenľ
Feature activation+0.000
Not
TokenNot
Feature activation+0.000

INTERVAL 2.062 - 2.474
CONTAINS 0.001%

commission
Token commission
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
matter
Token matter
Feature activation+0.000
they
Token they
Feature activation+0.419
responded
Token responded
Feature activation+2.064
by
Token by
Feature activation+0.000
saying
Token saying
Feature activation+1.487
that
Token that
Feature activation+0.656
they
Token they
Feature activation+0.280
had
Token had
Feature activation+0.432
Gaza
Token Gaza
Feature activation+0.000
,
Token,
Feature activation+0.502
had
Token had
Feature activation+0.441
two
Token two
Feature activation+0.000
standard
Token standard
Feature activation+0.144
responses
Token responses
Feature activation+2.123
:
Token:
Feature activation+0.678
irritation
Token irritation
Feature activation+0.411
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
else
Token else
Feature activation+0.000
-
Token-
Feature activation+0.000
zone
Tokenzone
Feature activation+0.000
pronounce
Token pronounce
Feature activation+0.381
ments
Tokenments
Feature activation+0.000
,
Token,
Feature activation+0.265
Mr
Token Mr
Feature activation+2.278
.
Token.
Feature activation+1.086
Sch
Token Sch
Feature activation+0.410
ull
Tokenull
Feature activation+0.000
er
Tokener
Feature activation+0.000
,
Token,
Feature activation+0.822
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
managed
Token managed
Feature activation+0.000
,
Token,
Feature activation+0.388
they
Token they
Feature activation+1.025
found
Token found
Feature activation+2.415
that
Token that
Feature activation+1.021
the
Token the
Feature activation+0.000
citizen
Token citizen
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
had
Token had
Feature activation+0.350
sometime
Token sometime
Feature activation+0.000
soon
Token soon
Feature activation+0.000
,
Token,
Feature activation+0.180
Lo
Token Lo
Feature activation+0.000
eb
Tokeneb
Feature activation+0.000
said
Token said
Feature activation+2.458
:
Token:
Feature activation+0.835
Ċ
TokenĊ
Feature activation+0.778
Ċ
TokenĊ
Feature activation+0.494
âĢ
TokenâĢ
Feature activation+0.105
ľ
Tokenľ
Feature activation+0.000

INTERVAL 1.650 - 2.062
CONTAINS 0.002%

were
Token were
Feature activation+0.000
real
Token real
Feature activation+0.000
health
Token health
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
,
Token,
Feature activation+0.530
he
Token he
Feature activation+1.777
said
Token said
Feature activation+3.944
:
Token:
Feature activation+1.376
``
Token ``
Feature activation+1.213
I
TokenI
Feature activation+0.000
believe
Token believe
Feature activation+0.000
,
Token,
Feature activation+0.938
only
Token only
Feature activation+0.852
12
Token 12
Feature activation+0.740
per
Token per
Feature activation+0.749
cent
Token cent
Feature activation+1.232
said
Token said
Feature activation+1.772
the
Token the
Feature activation+0.882
leader
Token leader
Feature activation+0.436
.
Token.
Feature activation+0.805
Fifty
Token Fifty
Feature activation+0.230
three
Token three
Feature activation+0.000
.
Token.
Feature activation+0.000
citizen
Token citizen
Feature activation+0.000
,
Token,
Feature activation+0.711
54
Token 54
Feature activation+0.621
percent
Token percent
Feature activation+0.832
said
Token said
Feature activation+1.816
no
Token no
Feature activation+0.755
.
Token.
Feature activation+0.346
Current
Token Current
Feature activation+0.140
laws
Token laws
Feature activation+0.000
permit
Token permit
Feature activation+0.000
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+0.079
Dmitry
Token Dmitry
Feature activation+0.000
Koz
Token Koz
Feature activation+0.000
ak
Tokenak
Feature activation+0.000
insisted
Token insisted
Feature activation+1.793
that
Token that
Feature activation+0.783
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.096
no
Token no
Feature activation+0.000
discrimination
Token discrimination
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.197
upcoming
Token upcoming
Feature activation+0.000
movies
Token movies
Feature activation+0.000
,
Token,
Feature activation+0.803
Johnson
Token Johnson
Feature activation+1.976
said
Token said
Feature activation+3.284
,
Token,
Feature activation+1.214
âĢ
Token âĢ
Feature activation+0.046
ľ
Tokenľ
Feature activation+0.073
I
TokenI
Feature activation+0.000

INTERVAL 1.237 - 1.650
CONTAINS 0.003%

solo
Token solo
Feature activation+0.000
album
Token album
Feature activation+0.000
,
Token,
Feature activation+0.437
Phil
Token Phil
Feature activation+0.746
responded
Token responded
Feature activation+3.881
:
Token:
Feature activation+1.546
"
Token "
Feature activation+1.084
Yes
TokenYes
Feature activation+0.748
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
jurisdictions
Token jurisdictions
Feature activation+0.000
for
Token for
Feature activation+0.000
exploration
Token exploration
Feature activation+0.000
currently
Token currently
Feature activation+0.402
,
Token,
Feature activation+0.464
he
Token he
Feature activation+1.537
told
Token told
Feature activation+3.138
us
Token us
Feature activation+1.210
he
Token he
Feature activation+1.339
favors
Token favors
Feature activation+0.500
Chile
Token Chile
Feature activation+0.000
,
Token,
Feature activation+0.007
they
Token they
Feature activation+0.085
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.609
respond
Token respond
Feature activation+1.240
differently
Token differently
Feature activation+0.195
depending
Token depending
Feature activation+0.000
on
Token on
Feature activation+0.007
what
Token what
Feature activation+0.007
size
Token size
Feature activation+0.000
Catal
Token Catal
Feature activation+0.000
ans
Tokenans
Feature activation+0.000
.
Token.
Feature activation+0.108
Ċ
TokenĊ
Feature activation+0.206
Ċ
TokenĊ
Feature activation+0.232
"
Token"
Feature activation+1.430
If
TokenIf
Feature activation+0.180
we
Token we
Feature activation+0.000
need
Token need
Feature activation+0.000
a
Token a
Feature activation+0.000
right
Token right
Feature activation+0.000
Tower
Token Tower
Feature activation+0.000
,
Token,
Feature activation+0.380
Chaff
Token Chaff
Feature activation+1.756
etz
Tokenetz
Feature activation+3.043
said
Token said
Feature activation+3.663
he
Token he
Feature activation+1.360
would
Token would
Feature activation+0.657
not
Token not
Feature activation+0.000
presupp
Token presupp
Feature activation+0.087
ose
Tokenose
Feature activation+0.318
the
Token the
Feature activation+0.026

INTERVAL 0.825 - 1.237
CONTAINS 0.006%

an
Tokenan
Feature activation+0.000
human
Token human
Feature activation+0.000
rights
Token rights
Feature activation+0.000
abuses
Token abuses
Feature activation+0.000
,
Token,
Feature activation+0.000
Mr
Token Mr
Feature activation+0.961
Morrison
Token Morrison
Feature activation+0.187
said
Token said
Feature activation+0.827
he
Token he
Feature activation+0.158
would
Token would
Feature activation+0.000
not
Token not
Feature activation+0.000
DNA
Token DNA
Feature activation+0.000
,
Token,
Feature activation+0.000
Ar
Token Ar
Feature activation+0.000
sy
Tokensy
Feature activation+0.000
an
Tokenan
Feature activation+0.000
claimed
Token claimed
Feature activation+1.018
that
Token that
Feature activation+0.469
the
Token the
Feature activation+0.000
estimated
Token estimated
Feature activation+0.000
monthly
Token monthly
Feature activation+0.000
sales
Token sales
Feature activation+0.000
,
Token,
Feature activation+0.941
von
Token von
Feature activation+1.374
Hol
Token Hol
Feature activation+0.396
z
Tokenz
Feature activation+0.475
haus
Tokenhaus
Feature activation+0.251
en
Tokenen
Feature activation+1.087
explained
Token explained
Feature activation+3.116
what
Token what
Feature activation+1.209
made
Token made
Feature activation+0.000
it
Token it
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
they
Token they
Feature activation+0.000
gave
Token gave
Feature activation+0.000
.
Token.
Feature activation+0.000
Unfortunately
Token Unfortunately
Feature activation+0.873
,
Token,
Feature activation+0.088
the
Token the
Feature activation+0.000
Army
Token Army
Feature activation+0.000
made
Token made
Feature activation+0.000
an
Token an
Feature activation+0.000
soon
Token soon
Feature activation+0.000
,
Token,
Feature activation+0.180
Lo
Token Lo
Feature activation+0.000
eb
Tokeneb
Feature activation+0.000
said
Token said
Feature activation+2.458
:
Token:
Feature activation+0.835
Ċ
TokenĊ
Feature activation+0.778
Ċ
TokenĊ
Feature activation+0.494
âĢ
TokenâĢ
Feature activation+0.105
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

INTERVAL 0.412 - 0.825
CONTAINS 0.023%

decide
Token decide
Feature activation+0.000
what
Token what
Feature activation+0.000
beer
Token beer
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
?
Token?
Feature activation+0.789
Are
Token Are
Feature activation+0.419
you
Token you
Feature activation+0.000
not
Token not
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
to
Token to
Feature activation+0.000
dismiss
Token dismiss
Feature activation+0.000
the
Token the
Feature activation+0.000
journalist
Token journalist
Feature activation+0.000
he
Token he
Feature activation+0.028
continued
Token continued
Feature activation+0.607
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
this
Tokenthis
Feature activation+0.000
is
Token is
Feature activation+0.019
too
Token too
Feature activation+0.000
wearing
Token wearing
Feature activation+0.000
a
Token a
Feature activation+0.000
"
Token "
Feature activation+0.115
rug
Tokenrug
Feature activation+0.000
";
Token";
Feature activation+0.292
never
Token never
Feature activation+0.557
missing
Token missing
Feature activation+0.281
the
Token the
Feature activation+0.000
opportunity
Token opportunity
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
asked
Token asked
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
the
Token the
Feature activation+0.000
question
Token question
Feature activation+0.000
,
Token,
Feature activation+0.157
told
Token told
Feature activation+0.696
me
Token me
Feature activation+0.398
.
Token.
Feature activation+0.231
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.081
favourite
Token favourite
Feature activation+0.000
jurisdictions
Token jurisdictions
Feature activation+0.000
for
Token for
Feature activation+0.000
exploration
Token exploration
Feature activation+0.000
currently
Token currently
Feature activation+0.402
,
Token,
Feature activation+0.464
he
Token he
Feature activation+1.537
told
Token told
Feature activation+3.138
us
Token us
Feature activation+1.210
he
Token he
Feature activation+1.339
favors
Token favors
Feature activation+0.500

INTERVAL 0.000 - 0.412
CONTAINS 99.964%

unity
Token unity
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Fort
TokenFort
Feature activation+0.000
y
Tokeny
Feature activation+0.000
years
Token years
Feature activation+0.000
on
Token on
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
may
Token may
Feature activation+0.000
AG
TokenAG
Feature activation+0.000
O
TokenO
Feature activation+0.000
AT
TokenAT
Feature activation+0.000
(
Token (
Feature activation+0.000
great
Tokengreat
Feature activation+0.000
est
Tokenest
Feature activation+0.000
animated
Token animated
Feature activation+0.000
gif
Token gif
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
time
Token time
Feature activation+0.000
ou
Tokenou
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
all
Token all
Feature activation+0.000
done
Token done
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
/
Token /
Feature activation+0.000
PAL
Token PAL
Feature activation+0.000
O
TokenO
Feature activation+0.000
AL
Token AL
Feature activation+0.000
TO
TokenTO
Feature activation+0.000
,
Token,
Feature activation+0.000
Calif
Token Calif
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Panasonic
Token Panasonic
Feature activation+0.000
Corporation
Token Corporation
Feature activation+0.000
some
Token some
Feature activation+0.000
fire
Token fire
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
team
Token team
Feature activation+0.000
when
Token when
Feature activation+0.000
necessary
Token necessary
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
NBA
Token NBA
Feature activation+0.000
Finals
Token Finals
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 7 in H3.5: (feature 18719)

TOP ACTIVATIONS
MAX = 4.177

and
Token and
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
nominee
Token nominee
Feature activation+0.000
Hillary
Token Hillary
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
each
Token each
Feature activation+4.177
garnered
Token garnered
Feature activation+0.794
more
Token more
Feature activation+0.000
votes
Token votes
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
yer
Tokenyer
Feature activation+0.000
and
Token and
Feature activation+0.049
Alexandra
Token Alexandra
Feature activation+0.000
Pole
Token Pole
Feature activation+0.000
tto
Tokentto
Feature activation+0.000
all
Token all
Feature activation+4.055
had
Token had
Feature activation+1.541
eight
Token eight
Feature activation+1.429
kills
Token kills
Feature activation+0.293
each
Token each
Feature activation+1.272
,
Token,
Feature activation+0.000
roy
Tokenroy
Feature activation+0.000
and
Token and
Feature activation+0.019
Kathy
Token Kathy
Feature activation+0.000
Bates
Token Bates
Feature activation+0.000
,
Token,
Feature activation+0.665
each
Token each
Feature activation+4.000
playing
Token playing
Feature activation+0.210
performers
Token performers
Feature activation+0.379
that
Token that
Feature activation+0.000
Lange
Token Lange
Feature activation+0.000
's
Token's
Feature activation+0.000
and
Token and
Feature activation+0.000
S
Token S
Feature activation+0.000
utter
Tokenutter
Feature activation+0.000
streets
Token streets
Feature activation+0.619
were
Token were
Feature activation+0.937
both
Token both
Feature activation+3.866
closed
Token closed
Feature activation+0.436
as
Token as
Feature activation+0.408
authorities
Token authorities
Feature activation+0.350
investigated
Token investigated
Feature activation+0.000
the
Token the
Feature activation+0.000
Al
Token Al
Feature activation+0.000
me
Tokenme
Feature activation+0.000
yd
Tokenyd
Feature activation+0.000
a
Tokena
Feature activation+0.000
have
Token have
Feature activation+1.288
both
Token both
Feature activation+3.803
sculpt
Token sculpt
Feature activation+1.067
ed
Tokened
Feature activation+0.360
teams
Token teams
Feature activation+0.488
that
Token that
Feature activation+0.000
take
Token take
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Donnell
TokenDonnell
Feature activation+0.000
and
Token and
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
,
Token,
Feature activation+0.026
both
Token both
Feature activation+3.773
outspoken
Token outspoken
Feature activation+0.773
celebrities
Token celebrities
Feature activation+0.119
,
Token,
Feature activation+0.000
have
Token have
Feature activation+0.417
been
Token been
Feature activation+0.000
State
Token State
Feature activation+0.000
head
Token head
Feature activation+0.581
Mike
Token Mike
Feature activation+0.000
Gund
Token Gund
Feature activation+0.000
y
Tokeny
Feature activation+0.000
both
Token both
Feature activation+3.697
have
Token have
Feature activation+0.809
7
Token 7
Feature activation+0.181
/
Token/
Feature activation+0.000
2
Token2
Feature activation+0.000
odds
Token odds
Feature activation+0.056
Logan
Token Logan
Feature activation+0.000
Taylor
Token Taylor
Feature activation+0.000
and
Token and
Feature activation+0.000
Ronnie
Token Ronnie
Feature activation+0.000
Gideon
Token Gideon
Feature activation+0.000
each
Token each
Feature activation+3.671
knocked
Token knocked
Feature activation+0.611
in
Token in
Feature activation+0.293
two
Token two
Feature activation+1.086
runs
Token runs
Feature activation+0.000
to
Token to
Feature activation+0.000
John
Token John
Feature activation+0.000
F
Token F
Feature activation+0.000
.
Token.
Feature activation+0.000
Kennedy
Token Kennedy
Feature activation+0.019
were
Token were
Feature activation+1.793
both
Token both
Feature activation+3.642
sons
Token sons
Feature activation+1.007
of
Token of
Feature activation+0.000
privileged
Token privileged
Feature activation+0.000
,
Token,
Feature activation+0.000
politically
Token politically
Feature activation+0.000
.
Token.
Feature activation+0.000
Collins
Token Collins
Feature activation+0.000
and
Token and
Feature activation+0.000
S
Token S
Feature activation+0.000
ager
Tokenager
Feature activation+0.000
each
Token each
Feature activation+3.568
take
Token take
Feature activation+0.997
on
Token on
Feature activation+0.295
his
Token his
Feature activation+0.236
fifth
Token fifth
Feature activation+0.032
consecutive
Token consecutive
Feature activation+0.057
Tuesday
Token Tuesday
Feature activation+0.000
,
Token,
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
and
Token and
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
both
Token both
Feature activation+3.483
held
Token held
Feature activation+1.252
rallies
Token rallies
Feature activation+0.404
in
Token in
Feature activation+0.000
Florida
Token Florida
Feature activation+0.000
as
Token as
Feature activation+0.019
App
Token App
Feature activation+0.000
Store
Token Store
Feature activation+0.000
and
Token and
Feature activation+0.000
Google
Token Google
Feature activation+0.000
Play
Token Play
Feature activation+0.000
both
Token both
Feature activation+3.452
count
Token count
Feature activation+1.020
their
Token their
Feature activation+0.455
offerings
Token offerings
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
raise
Tokenraise
Feature activation+0.238
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
both
Token both
Feature activation+3.429
begin
Token begin
Feature activation+1.413
with
Token with
Feature activation+0.286
the
Token the
Feature activation+0.000
letter
Token letter
Feature activation+0.000
r
Token r
Feature activation+0.000
and
Token and
Feature activation+0.100
Chris
Token Chris
Feature activation+0.000
G
Token G
Feature activation+0.000
iv
Tokeniv
Feature activation+0.000
ens
Tokenens
Feature activation+0.000
all
Token all
Feature activation+3.407
finished
Token finished
Feature activation+1.488
the
Token the
Feature activation+0.723
year
Token year
Feature activation+0.000
with
Token with
Feature activation+0.469
fewer
Token fewer
Feature activation+0.000
.
Token.
Feature activation+0.000
United
Token United
Feature activation+0.000
and
Token and
Feature activation+0.000
American
Token American
Feature activation+0.000
Airlines
Token Airlines
Feature activation+0.000
both
Token both
Feature activation+3.382
suffered
Token suffered
Feature activation+0.156
computer
Token computer
Feature activation+0.000
-
Token-
Feature activation+0.000
system
Tokensystem
Feature activation+0.000
problems
Token problems
Feature activation+0.000
Davis
Token Davis
Feature activation+0.000
and
Token and
Feature activation+0.000
Dominic
Token Dominic
Feature activation+0.000
Ra
Token Ra
Feature activation+0.000
ab
Tokenab
Feature activation+0.000
respectively
Token respectively
Feature activation+3.329
),
Token),
Feature activation+0.071
Stephen
Token Stephen
Feature activation+0.000
Barcl
Token Barcl
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
is
Token is
Feature activation+0.000
at
Tokenat
Feature activation+0.000
ore
Tokenore
Feature activation+0.000
Camb
Token Camb
Feature activation+0.000
ria
Tokenria
Feature activation+0.451
,
Token,
Feature activation+0.609
both
Token both
Feature activation+3.305
of
Token of
Feature activation+0.234
Suff
Token Suff
Feature activation+0.000
ern
Tokenern
Feature activation+0.000
,
Token,
Feature activation+0.127
Rock
Token Rock
Feature activation+0.000
uli
Tokenuli
Feature activation+0.000
Bar
Token Bar
Feature activation+0.000
z
Tokenz
Feature activation+0.000
il
Tokenil
Feature activation+0.000
ai
Tokenai
Feature activation+0.000
hold
Token hold
Feature activation+3.302
a
Token a
Feature activation+1.273
copy
Token copy
Feature activation+0.646
of
Token of
Feature activation+0.404
the
Token the
Feature activation+0.143
Birds
Token Birds
Feature activation+0.000
pan
Tokenpan
Feature activation+0.000
and
Token and
Feature activation+0.000
Bern
Token Bern
Feature activation+0.000
anke
Tokenanke
Feature activation+0.000
are
Token are
Feature activation+1.163
both
Token both
Feature activation+3.251
mixed
Token mixed
Feature activation+1.181
bags
Token bags
Feature activation+0.223
.
Token.
Feature activation+0.452
Obviously
Token Obviously
Feature activation+0.028
Greens
Token Greens
Feature activation+0.203
ir
Tokenir
Feature activation+0.000
and
Token and
Feature activation+0.015
Som
Token Som
Feature activation+0.000
erville
Tokenerville
Feature activation+0.000
have
Token have
Feature activation+1.814
all
Token all
Feature activation+3.092
said
Token said
Feature activation+1.339
that
Token that
Feature activation+0.231
evidence
Token evidence
Feature activation+0.000
tying
Token tying
Feature activation+0.000
Vancouver
Token Vancouver
Feature activation+0.000

Top DFA by src position
MAX = 4.380

primary
Token primary
Feature activation-0.007
Top resid features:
candidate
Token candidate
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
although
Token although
Feature activation+0.070
Top resid features:
Sanders
Token Sanders
Feature activation+0.015
Top resid features:
and
Token and
Feature activation+4.380
Top resid features:
Democratic
Token Democratic
Feature activation+0.006
Top resid features:
nominee
Token nominee
Feature activation-0.007
Top resid features:
Hillary
Token Hillary
Feature activation+0.014
Top resid features:
Clinton
Token Clinton
Feature activation-0.055
Top resid features:
each
Token each
Feature activation+0.059
Top resid features:
,
Token,
Feature activation+0.066
Top resid features:
Kirst
Token Kirst
Feature activation-0.003
Top resid features:
ie
Tokenie
Feature activation-0.000
Top resid features:
Hill
Token Hill
Feature activation-0.003
Top resid features:
yer
Tokenyer
Feature activation-0.003
Top resid features:
and
Token and
Feature activation+4.257
Top resid features:
Alexandra
Token Alexandra
Feature activation+0.018
Top resid features:
Pole
Token Pole
Feature activation-0.032
Top resid features:
tto
Tokentto
Feature activation-0.001
Top resid features:
all
Token all
Feature activation+0.017
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
ett
Tokenett
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
Frances
Token Frances
Feature activation+0.002
Top resid features:
Con
Token Con
Feature activation-0.002
Top resid features:
roy
Tokenroy
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+4.296
Top resid features:
Kathy
Token Kathy
Feature activation-0.004
Top resid features:
Bates
Token Bates
Feature activation-0.027
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
each
Token each
Feature activation-0.003
Top resid features:
playing
Token playing
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
S
TokenS
Feature activation+0.003
Top resid features:
ans
Tokenans
Feature activation+0.004
Top resid features:
ome
Tokenome
Feature activation+0.012
Top resid features:
and
Token and
Feature activation+4.203
Top resid features:
S
Token S
Feature activation+0.003
Top resid features:
utter
Tokenutter
Feature activation+0.003
Top resid features:
streets
Token streets
Feature activation-0.030
Top resid features:
were
Token were
Feature activation-0.060
Top resid features:
both
Token both
Feature activation-0.013
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Al
TokenAl
Feature activation+0.000
Top resid features:
onso
Tokenonso
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+3.615
Top resid features:
Al
Token Al
Feature activation+0.001
Top resid features:
me
Tokenme
Feature activation+0.006
Top resid features:
yd
Tokenyd
Feature activation+0.002
Top resid features:
a
Tokena
Feature activation-0.001
Top resid features:
have
Token have
Feature activation+0.046
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.021
Top resid features:
âĢ
TokenâĢ
Feature activation+0.008
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
Donnell
TokenDonnell
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+4.182
Top resid features:
Donald
Token Donald
Feature activation-0.038
Top resid features:
,
Token,
Feature activation-0.075
Top resid features:
both
Token both
Feature activation-0.060
Top resid features:
outspoken
Token outspoken
Feature activation+0.000
Top resid features:
celebrities
Token celebrities
Feature activation+0.000
Top resid features:
head
Token head
Feature activation-0.001
Top resid features:
coach
Token coach
Feature activation-0.020
Top resid features:
But
Token But
Feature activation+0.003
Top resid features:
ch
Tokench
Feature activation+0.005
Top resid features:
Jones
Token Jones
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+3.987
Top resid features:
Oklahoma
Token Oklahoma
Feature activation-0.003
Top resid features:
State
Token State
Feature activation-0.004
Top resid features:
head
Token head
Feature activation+0.007
Top resid features:
Mike
Token Mike
Feature activation+0.004
Top resid features:
Gund
Token Gund
Feature activation-0.022
Top resid features:
lem
Tokenlem
Feature activation+0.001
Top resid features:
and
Tokenand
Feature activation+0.001
Top resid features:
,
Token ,
Feature activation+0.021
Top resid features:
Logan
Token Logan
Feature activation-0.003
Top resid features:
Taylor
Token Taylor
Feature activation-0.011
Top resid features:
and
Token and
Feature activation+3.741
Top resid features:
Ronnie
Token Ronnie
Feature activation-0.001
Top resid features:
Gideon
Token Gideon
Feature activation-0.025
Top resid features:
each
Token each
Feature activation+0.055
Top resid features:
knocked
Token knocked
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
H
Token H
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
W
TokenW
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Bush
Token Bush
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+3.792
Top resid features:
John
Token John
Feature activation+0.010
Top resid features:
F
Token F
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Kennedy
Token Kennedy
Feature activation-0.011
Top resid features:
were
Token were
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.343
Top resid features:
2000
Token 2000
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Collins
Token Collins
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+3.569
Top resid features:
S
Token S
Feature activation-0.008
Top resid features:
ager
Tokenager
Feature activation-0.099
Top resid features:
each
Token each
Feature activation+0.040
Top resid features:
take
Token take
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Earlier
TokenEarlier
Feature activation-0.009
Top resid features:
Tuesday
Token Tuesday
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.026
Top resid features:
Clinton
Token Clinton
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+3.845
Top resid features:
Trump
Token Trump
Feature activation-0.137
Top resid features:
both
Token both
Feature activation+0.014
Top resid features:
held
Token held
Feature activation+0.000
Top resid features:
rallies
Token rallies
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
counterparts
Token counterparts
Feature activation+0.005
Top resid features:
;
Token;
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
App
Token App
Feature activation-0.003
Top resid features:
Store
Token Store
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+3.684
Top resid features:
Google
Token Google
Feature activation+0.026
Top resid features:
Play
Token Play
Feature activation+0.008
Top resid features:
both
Token both
Feature activation+0.012
Top resid features:
count
Token count
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.005
Top resid features:
R
TokenR
Feature activation-0.007
Top resid features:
uffle
Tokenuffle
Feature activation+0.001
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ŀ
TokenĿ
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+3.610
Top resid features:
âĢ
Token âĢ
Feature activation-0.002
Top resid features:
ľ
Tokenľ
Feature activation+0.008
Top resid features:
raise
Tokenraise
Feature activation-0.013
Top resid features:
âĢ
TokenâĢ
Feature activation-0.008
Top resid features:
Ŀ
TokenĿ
Feature activation+0.027
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.036
Top resid features:
Tav
Token Tav
Feature activation-0.012
Top resid features:
on
Tokenon
Feature activation+0.004
Top resid features:
Austin
Token Austin
Feature activation-0.006
Top resid features:
and
Token and
Feature activation+3.695
Top resid features:
Chris
Token Chris
Feature activation+0.010
Top resid features:
G
Token G
Feature activation-0.007
Top resid features:
iv
Tokeniv
Feature activation-0.031
Top resid features:
ens
Tokenens
Feature activation-0.016
Top resid features:
all
Token all
Feature activation-0.005
Top resid features:
failed
Token failed
Feature activation-0.003
Top resid features:
network
Token network
Feature activation-0.003
Top resid features:
router
Token router
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
United
Token United
Feature activation+0.017
Top resid features:
and
Token and
Feature activation+3.840
Top resid features:
American
Token American
Feature activation+0.008
Top resid features:
Airlines
Token Airlines
Feature activation-0.114
Top resid features:
both
Token both
Feature activation+0.009
Top resid features:
suffered
Token suffered
Feature activation+0.000
Top resid features:
computer
Token computer
Feature activation+0.000
Top resid features:
secretaries
Token secretaries
Feature activation+0.010
Top resid features:
resigned
Token resigned
Feature activation-0.006
Top resid features:
(
Token (
Feature activation+0.010
Top resid features:
David
TokenDavid
Feature activation-0.001
Top resid features:
Davis
Token Davis
Feature activation-0.013
Top resid features:
and
Token and
Feature activation+3.492
Top resid features:
Dominic
Token Dominic
Feature activation-0.018
Top resid features:
Ra
Token Ra
Feature activation-0.054
Top resid features:
ab
Tokenab
Feature activation-0.027
Top resid features:
respectively
Token respectively
Feature activation-0.006
Top resid features:
),
Token),
Feature activation+0.000
Top resid features:
E
TokenE
Feature activation+0.000
Top resid features:
rick
Tokenrick
Feature activation+0.002
Top resid features:
On
Token On
Feature activation+0.003
Top resid features:
y
Tokeny
Feature activation+0.002
Top resid features:
ango
Tokenango
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+3.614
Top resid features:
Salv
Token Salv
Feature activation-0.001
Top resid features:
at
Tokenat
Feature activation+0.004
Top resid features:
ore
Tokenore
Feature activation+0.002
Top resid features:
Camb
Token Camb
Feature activation-0.010
Top resid features:
ria
Tokenria
Feature activation+0.002
Top resid features:
13
Token 13
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
2016
Token 2016
Feature activation-0.012
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
Eli
Token Eli
Feature activation-0.014
Top resid features:
and
Token and
Feature activation+3.609
Top resid features:
Sh
Token Sh
Feature activation+0.001
Top resid features:
uli
Tokenuli
Feature activation-0.008
Top resid features:
Bar
Token Bar
Feature activation-0.015
Top resid features:
z
Tokenz
Feature activation+0.013
Top resid features:
il
Tokenil
Feature activation-0.014
Top resid features:
curb
Token curb
Feature activation-0.005
Top resid features:
inflation
Token inflation
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Greens
Token Greens
Feature activation+0.004
Top resid features:
pan
Tokenpan
Feature activation-0.003
Top resid features:
and
Token and
Feature activation+2.549
Top resid features:
Bern
Token Bern
Feature activation-0.003
Top resid features:
anke
Tokenanke
Feature activation-0.041
Top resid features:
are
Token are
Feature activation+0.012
Top resid features:
both
Token both
Feature activation-0.006
Top resid features:
mixed
Token mixed
Feature activation+0.000
Top resid features:
ans
Tokenans
Feature activation+0.003
Top resid features:
ford
Tokenford
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.062
Top resid features:
Mu
Token Mu
Feature activation-0.016
Top resid features:
ir
Tokenir
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+3.149
Top resid features:
Som
Token Som
Feature activation-0.006
Top resid features:
erville
Tokenerville
Feature activation-0.008
Top resid features:
have
Token have
Feature activation+0.094
Top resid features:
all
Token all
Feature activation+0.010
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.04

Head 2: 0.07

Head 3: 0.02

Head 4: 0.02

Head 5: 0.45

Head 6: 0.08

Head 7: 0.06

Head 8: 0.06

Head 9: 0.04

Head 10: 0.09

Head 11: 0.05

Positive logits

respectively4.12

together2.61

respective2.55

Together2.52

together2.50

apiece2.24

Together2.22

alike2.14

theirs2.00

their1.99

THEIR1.97

collectively1.96

each1.91

Ys1.90

yourselves1.86

atures1.85

collide1.80

aucuses1.80

themselves1.79

Their1.79

Negative logits

itiz-1.77

irreversible-1.63

erection-1.58

:/-1.54

ire-1.53

granite-1.52

legraph-1.48

erect-1.46

heres-1.46

vernment-1.44

oxygen-1.43

fertil-1.43

inhal-1.42

iji-1.42

practicable-1.41

flush-1.40

inflic-1.40

depri-1.39

deems-1.39

chie-1.39

INTERVAL 3.759 - 4.177
CONTAINS 0.001%

and
Token and
Feature activation+0.000
S
Token S
Feature activation+0.000
utter
Tokenutter
Feature activation+0.000
streets
Token streets
Feature activation+0.619
were
Token were
Feature activation+0.937
both
Token both
Feature activation+3.866
closed
Token closed
Feature activation+0.436
as
Token as
Feature activation+0.408
authorities
Token authorities
Feature activation+0.350
investigated
Token investigated
Feature activation+0.000
the
Token the
Feature activation+0.000
Al
Token Al
Feature activation+0.000
me
Tokenme
Feature activation+0.000
yd
Tokenyd
Feature activation+0.000
a
Tokena
Feature activation+0.000
have
Token have
Feature activation+1.288
both
Token both
Feature activation+3.803
sculpt
Token sculpt
Feature activation+1.067
ed
Tokened
Feature activation+0.360
teams
Token teams
Feature activation+0.488
that
Token that
Feature activation+0.000
take
Token take
Feature activation+0.000
roy
Tokenroy
Feature activation+0.000
and
Token and
Feature activation+0.019
Kathy
Token Kathy
Feature activation+0.000
Bates
Token Bates
Feature activation+0.000
,
Token,
Feature activation+0.665
each
Token each
Feature activation+4.000
playing
Token playing
Feature activation+0.210
performers
Token performers
Feature activation+0.379
that
Token that
Feature activation+0.000
Lange
Token Lange
Feature activation+0.000
's
Token's
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Donnell
TokenDonnell
Feature activation+0.000
and
Token and
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
,
Token,
Feature activation+0.026
both
Token both
Feature activation+3.773
outspoken
Token outspoken
Feature activation+0.773
celebrities
Token celebrities
Feature activation+0.119
,
Token,
Feature activation+0.000
have
Token have
Feature activation+0.417
been
Token been
Feature activation+0.000
yer
Tokenyer
Feature activation+0.000
and
Token and
Feature activation+0.049
Alexandra
Token Alexandra
Feature activation+0.000
Pole
Token Pole
Feature activation+0.000
tto
Tokentto
Feature activation+0.000
all
Token all
Feature activation+4.055
had
Token had
Feature activation+1.541
eight
Token eight
Feature activation+1.429
kills
Token kills
Feature activation+0.293
each
Token each
Feature activation+1.272
,
Token,
Feature activation+0.000

INTERVAL 3.341 - 3.759
CONTAINS 0.001%

App
Token App
Feature activation+0.000
Store
Token Store
Feature activation+0.000
and
Token and
Feature activation+0.000
Google
Token Google
Feature activation+0.000
Play
Token Play
Feature activation+0.000
both
Token both
Feature activation+3.452
count
Token count
Feature activation+1.020
their
Token their
Feature activation+0.455
offerings
Token offerings
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
raise
Tokenraise
Feature activation+0.238
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
both
Token both
Feature activation+3.429
begin
Token begin
Feature activation+1.413
with
Token with
Feature activation+0.286
the
Token the
Feature activation+0.000
letter
Token letter
Feature activation+0.000
r
Token r
Feature activation+0.000
.
Token.
Feature activation+0.000
Collins
Token Collins
Feature activation+0.000
and
Token and
Feature activation+0.000
S
Token S
Feature activation+0.000
ager
Tokenager
Feature activation+0.000
each
Token each
Feature activation+3.568
take
Token take
Feature activation+0.997
on
Token on
Feature activation+0.295
his
Token his
Feature activation+0.236
fifth
Token fifth
Feature activation+0.032
consecutive
Token consecutive
Feature activation+0.057
John
Token John
Feature activation+0.000
F
Token F
Feature activation+0.000
.
Token.
Feature activation+0.000
Kennedy
Token Kennedy
Feature activation+0.019
were
Token were
Feature activation+1.793
both
Token both
Feature activation+3.642
sons
Token sons
Feature activation+1.007
of
Token of
Feature activation+0.000
privileged
Token privileged
Feature activation+0.000
,
Token,
Feature activation+0.000
politically
Token politically
Feature activation+0.000
State
Token State
Feature activation+0.000
head
Token head
Feature activation+0.581
Mike
Token Mike
Feature activation+0.000
Gund
Token Gund
Feature activation+0.000
y
Tokeny
Feature activation+0.000
both
Token both
Feature activation+3.697
have
Token have
Feature activation+0.809
7
Token 7
Feature activation+0.181
/
Token/
Feature activation+0.000
2
Token2
Feature activation+0.000
odds
Token odds
Feature activation+0.056

INTERVAL 2.924 - 3.341
CONTAINS 0.001%

ir
Tokenir
Feature activation+0.000
and
Token and
Feature activation+0.015
Som
Token Som
Feature activation+0.000
erville
Tokenerville
Feature activation+0.000
have
Token have
Feature activation+1.814
all
Token all
Feature activation+3.092
said
Token said
Feature activation+1.339
that
Token that
Feature activation+0.231
evidence
Token evidence
Feature activation+0.000
tying
Token tying
Feature activation+0.000
Vancouver
Token Vancouver
Feature activation+0.000
Davis
Token Davis
Feature activation+0.000
and
Token and
Feature activation+0.000
Dominic
Token Dominic
Feature activation+0.000
Ra
Token Ra
Feature activation+0.000
ab
Tokenab
Feature activation+0.000
respectively
Token respectively
Feature activation+3.329
),
Token),
Feature activation+0.071
Stephen
Token Stephen
Feature activation+0.000
Barcl
Token Barcl
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
is
Token is
Feature activation+0.000
"
Token"
Feature activation+0.000
Canada
TokenCanada
Feature activation+0.000
and
Token and
Feature activation+0.000
Australia
Token Australia
Feature activation+0.000
are
Token are
Feature activation+1.306
two
Token two
Feature activation+2.943
very
Token very
Feature activation+0.195
different
Token different
Feature activation+2.180
countries
Token countries
Feature activation+0.287
with
Token with
Feature activation+0.000
different
Token different
Feature activation+0.566
depression
Token depression
Feature activation+0.000
.
Token.
Feature activation+0.074
Burns
Token Burns
Feature activation+0.000
and
Token and
Feature activation+0.000
Miller
Token Miller
Feature activation+0.004
both
Token both
Feature activation+3.041
refused
Token refused
Feature activation+0.560
to
Token to
Feature activation+0.487
curb
Token curb
Feature activation+0.061
inflation
Token inflation
Feature activation+0.000
.
Token.
Feature activation+0.266
uli
Tokenuli
Feature activation+0.000
Bar
Token Bar
Feature activation+0.000
z
Tokenz
Feature activation+0.000
il
Tokenil
Feature activation+0.000
ai
Tokenai
Feature activation+0.000
hold
Token hold
Feature activation+3.302
a
Token a
Feature activation+1.273
copy
Token copy
Feature activation+0.646
of
Token of
Feature activation+0.404
the
Token the
Feature activation+0.143
Birds
Token Birds
Feature activation+0.000

INTERVAL 2.506 - 2.924
CONTAINS 0.002%

and
Token and
Feature activation+0.000
Fel
Token Fel
Feature activation+0.000
ipe
Tokenipe
Feature activation+0.000
Mass
Token Mass
Feature activation+0.000
a
Tokena
Feature activation+0.000
collided
Token collided
Feature activation+2.510
on
Token on
Feature activation+0.120
the
Token the
Feature activation+0.041
opening
Token opening
Feature activation+0.001
lap
Token lap
Feature activation+0.000
.
Token.
Feature activation+0.008
Bryant
Token Bryant
Feature activation+0.000
,
Token,
Feature activation+0.311
for
Token for
Feature activation+0.556
example
Token example
Feature activation+0.000
.
Token.
Feature activation+0.512
Both
Token Both
Feature activation+2.675
are
Token are
Feature activation+0.342
superst
Token superst
Feature activation+0.000
ars
Tokenars
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
Ang
TokenAng
Feature activation+0.000
ela
Tokenela
Feature activation+0.000
Merkel
Token Merkel
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
both
Token both
Feature activation+2.736
agreed
Token agreed
Feature activation+1.031
that
Token that
Feature activation+0.332
it
Token it
Feature activation+1.139
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
and
Token and
Feature activation+0.000
women
Token women
Feature activation+0.000
in
Token in
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
are
Token are
Feature activation+0.585
equally
Token equally
Feature activation+2.668
as
Token as
Feature activation+0.323
likely
Token likely
Feature activation+0.139
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.096
each
Token each
Feature activation+0.630
stone
Tokenstone
Feature activation+0.000
and
Token and
Feature activation+0.000
R
Token R
Feature activation+0.000
aul
Tokenaul
Feature activation+0.000
Chaser
Token Chaser
Feature activation+0.000
respectively
Token respectively
Feature activation+2.602
.
Token.
Feature activation+0.194
Z
Token Z
Feature activation+0.000
A
TokenA
Feature activation+0.000
Q
TokenQ
Feature activation+0.000
performed
Token performed
Feature activation+0.154

INTERVAL 2.088 - 2.506
CONTAINS 0.002%

.
Token.
Feature activation+0.000
B
Token B
Feature activation+0.000
anc
Tokenanc
Feature activation+0.000
orp
Tokenorp
Feature activation+0.000
,
Token,
Feature activation+0.295
two
Token two
Feature activation+2.449
large
Token large
Feature activation+0.000
Berkshire
Token Berkshire
Feature activation+0.214
holdings
Token holdings
Feature activation+0.323
,
Token,
Feature activation+0.127
should
Token should
Feature activation+0.489
and
Token and
Feature activation+0.000
Against
Token Against
Feature activation+0.000
Marc
Token Marc
Feature activation+0.000
ion
Tokenion
Feature activation+0.000
,
Token,
Feature activation+0.177
respectively
Token respectively
Feature activation+2.365
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Besides
TokenBesides
Feature activation+0.000
Marc
Token Marc
Feature activation+0.000
UPS
Token UPS
Feature activation+0.000
and
Token and
Feature activation+0.000
Lockheed
Token Lockheed
Feature activation+0.000
Martin
Token Martin
Feature activation+0.000
,
Token,
Feature activation+0.196
among
Token among
Feature activation+2.449
others
Token others
Feature activation+0.000
.
Token.
Feature activation+0.111
Ċ
TokenĊ
Feature activation+0.184
Ċ
TokenĊ
Feature activation+0.095
âĢ
TokenâĢ
Feature activation+0.000
First
Token First
Feature activation+0.000
Female
Token Female
Feature activation+0.000
Super
Token Super
Feature activation+0.000
hero
Tokenhero
Feature activation+0.000
âĦ¢
TokenâĦ¢
Feature activation+0.000
both
Token both
Feature activation+2.163
fost
Token fost
Feature activation+0.000
ered
Tokenered
Feature activation+0.000
an
Token an
Feature activation+0.000
atmosphere
Token atmosphere
Feature activation+0.000
of
Token of
Feature activation+0.000
He
Token He
Feature activation+0.000
and
Token and
Feature activation+0.000
Bryan
Token Bryan
Feature activation+0.000
Cran
Token Cran
Feature activation+0.000
ston
Tokenston
Feature activation+0.000
shared
Token shared
Feature activation+2.448
a
Token a
Feature activation+0.690
moment
Token moment
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
hug
Token hug
Feature activation+0.221

INTERVAL 1.671 - 2.088
CONTAINS 0.005%

,
Token,
Feature activation+0.000
austerity
Token austerity
Feature activation+0.000
and
Token and
Feature activation+0.000
misinformation
Token misinformation
Feature activation+0.000
have
Token have
Feature activation+0.283
all
Token all
Feature activation+1.748
been
Token been
Feature activation+0.001
blamed
Token blamed
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
polar
Token polar
Feature activation+0.000
uss
Tokenuss
Feature activation+0.000
on
Tokenon
Feature activation+0.000
and
Token and
Feature activation+0.000
John
Token John
Feature activation+0.000
Scott
Token Scott
Feature activation+0.000
make
Token make
Feature activation+1.971
up
Token up
Feature activation+0.679
the
Token the
Feature activation+0.505
top
Token top
Feature activation+0.825
five
Token five
Feature activation+0.248
claimants
Token claimants
Feature activation+0.120
her
Token her
Feature activation+0.200
chancellor
Token chancellor
Feature activation+0.081
Sir
Token Sir
Feature activation+0.000
Geoffrey
Token Geoffrey
Feature activation+0.000
Howe
Token Howe
Feature activation+0.000
were
Token were
Feature activation+1.897
behind
Token behind
Feature activation+0.486
a
Token a
Feature activation+0.331
politically
Token politically
Feature activation+0.000
toxic
Token toxic
Feature activation+0.000
plan
Token plan
Feature activation+0.040
ion
Tokenion
Feature activation+0.000
and
Token and
Feature activation+0.000
Patt
Token Patt
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
Ray
Token Ray
Feature activation+0.000
are
Token are
Feature activation+1.784
part
Token part
Feature activation+1.498
of
Token of
Feature activation+0.854
a
Token a
Feature activation+0.404
family
Token family
Feature activation+0.328
that
Token that
Feature activation+0.000
friends
Token friends
Feature activation+0.233
return
Token return
Feature activation+1.631
to
Token to
Feature activation+0.321
Earth
Token Earth
Feature activation+0.000
,
Token,
Feature activation+0.770
he
Token he
Feature activation+1.789
was
Token was
Feature activation+0.308
more
Token more
Feature activation+0.027
happy
Token happy
Feature activation+0.073
than
Token than
Feature activation+0.000
he
Token he
Feature activation+0.259

INTERVAL 1.253 - 1.671
CONTAINS 0.015%

Bar
Token Bar
Feature activation+0.000
z
Tokenz
Feature activation+0.000
il
Tokenil
Feature activation+0.000
ai
Tokenai
Feature activation+0.000
hold
Token hold
Feature activation+3.302
a
Token a
Feature activation+1.273
copy
Token copy
Feature activation+0.646
of
Token of
Feature activation+0.404
the
Token the
Feature activation+0.143
Birds
Token Birds
Feature activation+0.000
'
Token'
Feature activation+0.000
his
Token his
Feature activation+0.097
crew
Token crew
Feature activation+0.000
must
Token must
Feature activation+0.181
make
Token make
Feature activation+0.000
sure
Token sure
Feature activation+0.000
each
Token each
Feature activation+1.371
of
Token of
Feature activation+0.000
Met
Token Met
Feature activation+0.000
Life
TokenLife
Feature activation+0.000
Stadium
Token Stadium
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
to
Token to
Feature activation+0.000
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+0.000
8
Token8
Feature activation+0.000
%
Token%
Feature activation+0.000
respectively
Token respectively
Feature activation+1.430
between
Token between
Feature activation+0.178
18
Token 18
Feature activation+0.000
81
Token81
Feature activation+0.000
and
Token and
Feature activation+0.000
1941
Token 1941
Feature activation+0.000
Albert
Token Albert
Feature activation+0.000
McC
Token McC
Feature activation+0.000
le
Tokenle
Feature activation+0.000
llan
Tokenllan
Feature activation+0.000
as
Token as
Feature activation+0.284
their
Token their
Feature activation+1.302
outside
Token outside
Feature activation+0.000
linebackers
Token linebackers
Feature activation+0.000
on
Token on
Feature activation+0.000
some
Token some
Feature activation+0.000
plays
Token plays
Feature activation+0.000
i
Tokeni
Feature activation+0.000
and
Token and
Feature activation+0.000
Cobra
Token Cobra
Feature activation+0.000
were
Token were
Feature activation+1.725
first
Token first
Feature activation+0.796
linked
Token linked
Feature activation+1.459
in
Token in
Feature activation+0.111
1993
Token 1993
Feature activation+0.000
to
Token to
Feature activation+0.049
create
Token create
Feature activation+0.379
No
Token No
Feature activation+0.000

INTERVAL 0.835 - 1.253
CONTAINS 0.029%

and
Token and
Feature activation+0.000
Eric
Token Eric
Feature activation+0.000
Sk
Token Sk
Feature activation+0.000
ogl
Tokenogl
Feature activation+0.000
und
Tokenund
Feature activation+0.000
.
Token.
Feature activation+0.970
The
Token The
Feature activation+0.971
Tigers
Token Tigers
Feature activation+0.133
had
Token had
Feature activation+0.482
a
Token a
Feature activation+0.470
4
Token 4
Feature activation+0.250
Ign
TokenIgn
Feature activation+0.000
or
Tokenor
Feature activation+0.000
ance
Tokenance
Feature activation+0.000
and
Token and
Feature activation+0.000
delusion
Token delusion
Feature activation+0.000
are
Token are
Feature activation+0.891
considered
Token considered
Feature activation+0.060
to
Token to
Feature activation+0.004
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.142
starting
Token starting
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Fred
TokenFred
Feature activation+0.000
and
Token and
Feature activation+0.000
Bunny
Token Bunny
Feature activation+0.000
were
Token were
Feature activation+0.991
political
Token political
Feature activation+0.885
insiders
Token insiders
Feature activation+0.621
of
Token of
Feature activation+0.000
[
Token [
Feature activation+0.000
M
TokenM
Feature activation+0.000
hotel
Token hotel
Feature activation+0.000
and
Token and
Feature activation+0.000
restaurant
Token restaurant
Feature activation+0.000
industries
Token industries
Feature activation+0.148
mirror
Token mirror
Feature activation+1.418
state
Token state
Feature activation+1.008
demographics
Token demographics
Feature activation+0.580
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.283
,
Token,
Feature activation+0.114
the
Token the
Feature activation+0.000
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.000
Warriors
Token Warriors
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.839
now
Token now
Feature activation+0.000
join
Token join
Feature activation+0.201
former
Token former
Feature activation+0.669
Warriors
Token Warriors
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 0.418 - 0.835
CONTAINS 0.094%

Sanders
Token Sanders
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
democratic
Token democratic
Feature activation+0.000
socialism
Token socialism
Feature activation+0.000
are
Token are
Feature activation+0.540
just
Token just
Feature activation+0.066
too
Token too
Feature activation+0.000
far
Token far
Feature activation+0.000
left
Token left
Feature activation+0.000
for
Token for
Feature activation+0.000
Play
Token Play
Feature activation+0.000
Store
Token Store
Feature activation+0.000
and
Token and
Feature activation+0.000
iTunes
Token iTunes
Feature activation+0.000
,
Token,
Feature activation+0.000
each
Token each
Feature activation+0.752
of
Token of
Feature activation+0.000
Yo
Token Yo
Feature activation+0.000
's
Token's
Feature activation+0.000
users
Token users
Feature activation+0.000
had
Token had
Feature activation+0.000
him
Token him
Feature activation+0.000
than
Token than
Feature activation+0.000
they
Token they
Feature activation+0.109
were
Token were
Feature activation+0.000
to
Token to
Feature activation+0.000
each
Token each
Feature activation+0.574
other
Token other
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
there
Token there
Feature activation+0.000
were
Token were
Feature activation+0.000
and
Token and
Feature activation+0.000
central
Token central
Feature activation+0.000
Co
Token Co
Feature activation+0.000
quit
Tokenquit
Feature activation+0.000
lam
Tokenlam
Feature activation+0.000
were
Token were
Feature activation+0.431
probably
Token probably
Feature activation+0.000
separate
Token separate
Feature activation+1.965
islands
Token islands
Feature activation+0.000
at
Token at
Feature activation+0.000
one
Token one
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ne
TokenNe
Feature activation+0.000
gan
Tokengan
Feature activation+0.000
and
Token and
Feature activation+0.000
Carl
Token Carl
Feature activation+0.000
have
Token have
Feature activation+0.483
a
Token a
Feature activation+0.429
unique
Token unique
Feature activation+0.000
relationship
Token relationship
Feature activation+0.966
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.418
CONTAINS 99.850%

of
Token of
Feature activation+0.000
residents
Token residents
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
and
Token and
Feature activation+0.000
least
Token least
Feature activation+0.000
vulnerable
Token vulnerable
Feature activation+0.000
ages
Token ages
Feature activation+0.000
for
Token for
Feature activation+0.000
committing
Token committing
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
three
Token three
Feature activation+0.000
foreigners
Token foreigners
Feature activation+0.000
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
since
Token since
Feature activation+0.000
been
Token been
Feature activation+0.000
deported
Token deported
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
told
Token told
Feature activation+0.000
Sky
Token Sky
Feature activation+0.000
Sports
Token Sports
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
He
TokenHe
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
't
Token't
Feature activation+0.000
look
Token look
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
These
TokenThese
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
gang
Token gang
Feature activation+0.000
sters
Tokensters
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
of
Token of
Feature activation+0.000
Poly
Token Poly
Feature activation+0.000
Psych
Token Psych
Feature activation+0.000
oph
Tokenoph
Feature activation+0.000
armac
Tokenarmac
Feature activation+0.000
ology
Tokenology
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
You
TokenYou
Feature activation+0.000
think
Token think
Feature activation+0.000
maybe
Token maybe
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 H3.5: (feature 18929)

TOP ACTIVATIONS
MAX = 7.553

perjury
Token perjury
Feature activation+0.000
,
Token,
Feature activation+0.000
obstruction
Token obstruction
Feature activation+0.000
of
Token of
Feature activation+0.000
justice
Token justice
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.553
Ċ
TokenĊ
Feature activation+7.514
300
Token300
Feature activation+0.000
drug
Token drug
Feature activation+0.000
convictions
Token convictions
Feature activation+0.000
have
Token have
Feature activation+0.000
,
Token,
Feature activation+0.000
obstruction
Token obstruction
Feature activation+0.000
of
Token of
Feature activation+0.000
justice
Token justice
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.553
Ċ
TokenĊ
Feature activation+7.514
300
Token300
Feature activation+0.000
drug
Token drug
Feature activation+0.000
convictions
Token convictions
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
's
Token's
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
communications
Token communications
Feature activation+0.000
director
Token director
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.389
Ċ
TokenĊ
Feature activation+7.319
He
TokenHe
Feature activation+0.000
said
Token said
Feature activation+0.000
Rubio
Token Rubio
Feature activation+0.000
's
Token's
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
communications
Token communications
Feature activation+0.000
director
Token director
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.389
Ċ
TokenĊ
Feature activation+7.319
He
TokenHe
Feature activation+0.000
said
Token said
Feature activation+0.000
Rubio
Token Rubio
Feature activation+0.000
's
Token's
Feature activation+0.000
primary
Token primary
Feature activation+0.000
beat
Token beat
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
in
Token in
Feature activation+0.000
Ohio
Token Ohio
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.772
Ċ
TokenĊ
Feature activation+5.534
(
Token(
Feature activation+0.000
CNN
TokenCNN
Feature activation+0.000
)
Token)
Feature activation+0.000
Marco
Token Marco
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
in
Token in
Feature activation+0.000
Ohio
Token Ohio
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.772
Ċ
TokenĊ
Feature activation+5.534
(
Token(
Feature activation+0.000
CNN
TokenCNN
Feature activation+0.000
)
Token)
Feature activation+0.000
Marco
Token Marco
Feature activation+0.000
Rubio
Token Rubio
Feature activation+0.000
will
Token will
Feature activation+0.000
feature
Token feature
Feature activation+0.000
seven
Token seven
Feature activation+0.000
primaries
Token primaries
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.028
Ċ
TokenĊ
Feature activation+4.038
Spring
TokenSpring
Feature activation+0.000
Valley
Token Valley
Feature activation+0.000
,
Token,
Feature activation+0.000
Ram
Token Ram
Feature activation+0.000
apo
Tokenapo
Feature activation+0.000
season
Token season
Feature activation+0.000
will
Token will
Feature activation+0.000
feature
Token feature
Feature activation+0.000
seven
Token seven
Feature activation+0.000
primaries
Token primaries
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.028
Ċ
TokenĊ
Feature activation+4.038
Spring
TokenSpring
Feature activation+0.000
Valley
Token Valley
Feature activation+0.000
,
Token,
Feature activation+0.000
Ram
Token Ram
Feature activation+0.000
is
Token is
Feature activation+0.000
possible
Token possible
Feature activation+0.000
after
Token after
Feature activation+0.000
heart
Token heart
Feature activation+0.000
attack
Token attack
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.896
Ċ
TokenĊ
Feature activation+3.805
Sexual
TokenSexual
Feature activation+0.000
health
Token health
Feature activation+0.000
is
Token is
Feature activation+0.000
important
Token important
Feature activation+0.000
possible
Token possible
Feature activation+0.000
after
Token after
Feature activation+0.000
heart
Token heart
Feature activation+0.000
attack
Token attack
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.896
Ċ
TokenĊ
Feature activation+3.805
Sexual
TokenSexual
Feature activation+0.000
health
Token health
Feature activation+0.000
is
Token is
Feature activation+0.000
important
Token important
Feature activation+0.000
,
Token,
Feature activation+0.000
likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
restored
Token restored
Feature activation+0.000
quickly
Token quickly
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.792
Ċ
TokenĊ
Feature activation+3.681
Defense
TokenDefense
Feature activation+0.000
Department
Token Department
Feature activation+0.000
had
Token had
Feature activation+0.000
said
Token said
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
restored
Token restored
Feature activation+0.000
quickly
Token quickly
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.792
Ċ
TokenĊ
Feature activation+3.681
Defense
TokenDefense
Feature activation+0.000
Department
Token Department
Feature activation+0.000
had
Token had
Feature activation+0.000
said
Token said
Feature activation+0.000
government
Token government
Feature activation+0.000
state
Token state
Feature activation+0.000
Assembly
Token Assembly
Feature activation+0.000
districts
Token districts
Feature activation+0.000
have
Token have
Feature activation+0.000
primaries
Token primaries
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.431
Ċ
TokenĊ
Feature activation+3.162
The
TokenThe
Feature activation+0.000
primary
Token primary
Feature activation+0.000
is
Token is
Feature activation+0.000
Sept
Token Sept
Feature activation+0.000
Assembly
Token Assembly
Feature activation+0.000
districts
Token districts
Feature activation+0.000
have
Token have
Feature activation+0.000
primaries
Token primaries
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.431
Ċ
TokenĊ
Feature activation+3.162
The
TokenThe
Feature activation+0.000
primary
Token primary
Feature activation+0.000
is
Token is
Feature activation+0.000
Sept
Token Sept
Feature activation+0.000
.
Token.
Feature activation+0.000
prevented
Token prevented
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
from
Token from
Feature activation+0.000
being
Token being
Feature activation+0.000
paid
Token paid
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.958
Ċ
TokenĊ
Feature activation+2.769
F
TokenF
Feature activation+0.000
am
Tokenam
Feature activation+0.000
ilies
Tokenilies
Feature activation+0.000
due
Token due
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
from
Token from
Feature activation+0.000
being
Token being
Feature activation+0.000
paid
Token paid
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.958
Ċ
TokenĊ
Feature activation+2.769
F
TokenF
Feature activation+0.000
am
Tokenam
Feature activation+0.000
ilies
Tokenilies
Feature activation+0.000
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
is
Token is
Feature activation+0.000
important
Token important
Feature activation+0.000
,
Token,
Feature activation+0.000
researcher
Token researcher
Feature activation+0.000
says
Token says
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.609
Ċ
TokenĊ
Feature activation+2.049
Adv
TokenAdv
Feature activation+0.000
ice
Tokenice
Feature activation+0.000
depends
Token depends
Feature activation+0.000
on
Token on
Feature activation+0.000
one
Token one
Feature activation+0.000
's
Token's
Feature activation+0.000
death
Token death
Feature activation+0.000
in
Token in
Feature activation+0.000
war
Token war
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.340
Ċ
TokenĊ
Feature activation+2.006
Out
TokenOut
Feature activation+0.000
rage
Tokenrage
Feature activation+0.000
over
Token over
Feature activation+0.000
a
Token a
Feature activation+0.000
important
Token important
Feature activation+0.000
,
Token,
Feature activation+0.000
researcher
Token researcher
Feature activation+0.000
says
Token says
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.609
Ċ
TokenĊ
Feature activation+2.049
Adv
TokenAdv
Feature activation+0.000
ice
Tokenice
Feature activation+0.000
depends
Token depends
Feature activation+0.000
on
Token on
Feature activation+0.000
patient
Token patient
Feature activation+0.000
's
Token's
Feature activation+0.000
death
Token death
Feature activation+0.000
in
Token in
Feature activation+0.000
war
Token war
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.340
Ċ
TokenĊ
Feature activation+2.006
Out
TokenOut
Feature activation+0.000
rage
Tokenrage
Feature activation+0.000
over
Token over
Feature activation+0.000
a
Token a
Feature activation+0.000
delay
Token delay
Feature activation+0.000

Top DFA by src position
MAX = 8.660

Led
Token Led
Feature activation-0.000
Top resid features:
gard
Tokengard
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.102
Top resid features:
Story
TokenStory
Feature activation+0.072
Top resid features:
highlights
Token highlights
Feature activation+8.660
Top resid features:
Annie
Token Annie
Feature activation-0.016
Top resid features:
D
Token D
Feature activation-0.007
Top resid features:
ook
Tokenook
Feature activation-0.000
Top resid features:
han
Tokenhan
Feature activation-0.014
Top resid features:
ple
Token ple
Feature activation+0.005
Top resid features:
Led
Token Led
Feature activation-0.000
Top resid features:
gard
Tokengard
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.094
Top resid features:
Story
TokenStory
Feature activation+0.034
Top resid features:
highlights
Token highlights
Feature activation+8.400
Top resid features:
Annie
Token Annie
Feature activation-0.003
Top resid features:
D
Token D
Feature activation-0.007
Top resid features:
ook
Tokenook
Feature activation-0.004
Top resid features:
han
Tokenhan
Feature activation-0.009
Top resid features:
ple
Token ple
Feature activation+0.009
Top resid features:
cling
Tokencling
Feature activation-0.000
Top resid features:
Association
Token Association
Feature activation-0.000
Top resid features:
)
Token)
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.083
Top resid features:
Story
TokenStory
Feature activation+0.071
Top resid features:
highlights
Token highlights
Feature activation+8.148
Top resid features:
Alex
Token Alex
Feature activation+0.015
Top resid features:
Con
Token Con
Feature activation-0.010
Top resid features:
ant
Tokenant
Feature activation+0.002
Top resid features:
is
Token is
Feature activation+0.034
Top resid features:
Marco
Token Marco
Feature activation+0.039
Top resid features:
cling
Tokencling
Feature activation-0.000
Top resid features:
Association
Token Association
Feature activation-0.000
Top resid features:
)
Token)
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.094
Top resid features:
Story
TokenStory
Feature activation+0.023
Top resid features:
highlights
Token highlights
Feature activation+8.042
Top resid features:
Alex
Token Alex
Feature activation+0.017
Top resid features:
Con
Token Con
Feature activation-0.011
Top resid features:
ant
Tokenant
Feature activation+0.002
Top resid features:
is
Token is
Feature activation+0.023
Top resid features:
Marco
Token Marco
Feature activation+0.031
Top resid features:
cling
Tokencling
Feature activation-0.000
Top resid features:
Association
Token Association
Feature activation-0.000
Top resid features:
)
Token)
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.084
Top resid features:
Story
TokenStory
Feature activation-0.005
Top resid features:
highlights
Token highlights
Feature activation+6.377
Top resid features:
Alex
Token Alex
Feature activation+0.002
Top resid features:
Con
Token Con
Feature activation-0.004
Top resid features:
ant
Tokenant
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.008
Top resid features:
Marco
Token Marco
Feature activation+0.001
Top resid features:
cling
Tokencling
Feature activation-0.000
Top resid features:
Association
Token Association
Feature activation-0.000
Top resid features:
)
Token)
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.090
Top resid features:
Story
TokenStory
Feature activation-0.016
Top resid features:
highlights
Token highlights
Feature activation+5.986
Top resid features:
Alex
Token Alex
Feature activation+0.002
Top resid features:
Con
Token Con
Feature activation-0.006
Top resid features:
ant
Tokenant
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.010
Top resid features:
Marco
Token Marco
Feature activation+0.001
Top resid features:
N
TokenN
Feature activation+0.000
Top resid features:
file
Token file
Feature activation-0.011
Top resid features:
photo
Token photo
Feature activation-0.008
Top resid features:
)
Token)
Feature activation-0.000
Top resid features:
Story
Token Story
Feature activation+0.003
Top resid features:
Highlights
Token Highlights
Feature activation+5.265
Top resid features:
The
Token The
Feature activation-0.040
Top resid features:
2014
Token 2014
Feature activation+0.004
Top resid features:
election
Token election
Feature activation+0.025
Top resid features:
season
Token season
Feature activation+0.020
Top resid features:
will
Token will
Feature activation-0.003
Top resid features:
N
TokenN
Feature activation-0.001
Top resid features:
file
Token file
Feature activation-0.010
Top resid features:
photo
Token photo
Feature activation-0.010
Top resid features:
)
Token)
Feature activation+0.001
Top resid features:
Story
Token Story
Feature activation+0.011
Top resid features:
Highlights
Token Highlights
Feature activation+5.308
Top resid features:
The
Token The
Feature activation-0.031
Top resid features:
2014
Token 2014
Feature activation+0.009
Top resid features:
election
Token election
Feature activation+0.030
Top resid features:
season
Token season
Feature activation+0.027
Top resid features:
will
Token will
Feature activation+0.008
Top resid features:
:
Token:
Feature activation-0.014
Top resid features:
Getty
Token Getty
Feature activation-0.016
Top resid features:
Images
Token Images
Feature activation-0.010
Top resid features:
)
Token)
Feature activation-0.001
Top resid features:
Story
Token Story
Feature activation-0.001
Top resid features:
Highlights
Token Highlights
Feature activation+5.538
Top resid features:
Groups
Token Groups
Feature activation+0.103
Top resid features:
:
Token:
Feature activation-0.005
Top resid features:
Int
Token Int
Feature activation-0.035
Top resid features:
im
Tokenim
Feature activation-0.004
Top resid features:
acy
Tokenacy
Feature activation+0.006
Top resid features:
:
Token:
Feature activation-0.014
Top resid features:
Getty
Token Getty
Feature activation-0.014
Top resid features:
Images
Token Images
Feature activation-0.007
Top resid features:
)
Token)
Feature activation-0.001
Top resid features:
Story
Token Story
Feature activation-0.003
Top resid features:
Highlights
Token Highlights
Feature activation+5.390
Top resid features:
Groups
Token Groups
Feature activation+0.083
Top resid features:
:
Token:
Feature activation-0.019
Top resid features:
Int
Token Int
Feature activation-0.026
Top resid features:
im
Tokenim
Feature activation-0.004
Top resid features:
acy
Tokenacy
Feature activation+0.005
Top resid features:
ark
Tokenark
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
AP
Token AP
Feature activation-0.008
Top resid features:
)
Token)
Feature activation+0.002
Top resid features:
Story
Token Story
Feature activation-0.001
Top resid features:
Highlights
Token Highlights
Feature activation+5.521
Top resid features:
Death
Token Death
Feature activation-0.089
Top resid features:
benefits
Token benefits
Feature activation-0.017
Top resid features:
for
Token for
Feature activation-0.000
Top resid features:
families
Token families
Feature activation+0.007
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
ark
Tokenark
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
AP
Token AP
Feature activation-0.007
Top resid features:
)
Token)
Feature activation+0.001
Top resid features:
Story
Token Story
Feature activation-0.005
Top resid features:
Highlights
Token Highlights
Feature activation+5.456
Top resid features:
Death
Token Death
Feature activation-0.081
Top resid features:
benefits
Token benefits
Feature activation-0.015
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
families
Token families
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
N
TokenN
Feature activation-0.000
Top resid features:
file
Token file
Feature activation-0.009
Top resid features:
photo
Token photo
Feature activation-0.006
Top resid features:
)
Token)
Feature activation+0.001
Top resid features:
Story
Token Story
Feature activation-0.005
Top resid features:
Highlights
Token Highlights
Feature activation+4.635
Top resid features:
The
Token The
Feature activation-0.036
Top resid features:
2014
Token 2014
Feature activation-0.018
Top resid features:
election
Token election
Feature activation-0.004
Top resid features:
season
Token season
Feature activation-0.001
Top resid features:
will
Token will
Feature activation-0.007
Top resid features:
N
TokenN
Feature activation+0.000
Top resid features:
file
Token file
Feature activation-0.010
Top resid features:
photo
Token photo
Feature activation-0.006
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
Story
Token Story
Feature activation-0.006
Top resid features:
Highlights
Token Highlights
Feature activation+4.397
Top resid features:
The
Token The
Feature activation-0.052
Top resid features:
2014
Token 2014
Feature activation-0.024
Top resid features:
election
Token election
Feature activation-0.005
Top resid features:
season
Token season
Feature activation-0.002
Top resid features:
will
Token will
Feature activation-0.010
Top resid features:
ark
Tokenark
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
AP
Token AP
Feature activation-0.003
Top resid features:
)
Token)
Feature activation+0.001
Top resid features:
Story
Token Story
Feature activation-0.007
Top resid features:
Highlights
Token Highlights
Feature activation+4.293
Top resid features:
Death
Token Death
Feature activation-0.036
Top resid features:
benefits
Token benefits
Feature activation-0.003
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
families
Token families
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
ark
Tokenark
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
AP
Token AP
Feature activation-0.003
Top resid features:
)
Token)
Feature activation+0.001
Top resid features:
Story
Token Story
Feature activation-0.008
Top resid features:
Highlights
Token Highlights
Feature activation+4.069
Top resid features:
Death
Token Death
Feature activation-0.038
Top resid features:
benefits
Token benefits
Feature activation-0.003
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
families
Token families
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
:
Token:
Feature activation-0.008
Top resid features:
Getty
Token Getty
Feature activation-0.008
Top resid features:
Images
Token Images
Feature activation-0.002
Top resid features:
)
Token)
Feature activation-0.001
Top resid features:
Story
Token Story
Feature activation-0.005
Top resid features:
Highlights
Token Highlights
Feature activation+3.614
Top resid features:
Groups
Token Groups
Feature activation-0.013
Top resid features:
:
Token:
Feature activation-0.047
Top resid features:
Int
Token Int
Feature activation-0.002
Top resid features:
im
Tokenim
Feature activation-0.002
Top resid features:
acy
Tokenacy
Feature activation+0.001
Top resid features:
ark
Tokenark
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
AP
Token AP
Feature activation-0.003
Top resid features:
)
Token)
Feature activation+0.003
Top resid features:
Story
Token Story
Feature activation-0.008
Top resid features:
Highlights
Token Highlights
Feature activation+3.465
Top resid features:
Death
Token Death
Feature activation-0.034
Top resid features:
benefits
Token benefits
Feature activation-0.001
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
families
Token families
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
:
Token:
Feature activation-0.009
Top resid features:
Getty
Token Getty
Feature activation-0.008
Top resid features:
Images
Token Images
Feature activation-0.002
Top resid features:
)
Token)
Feature activation-0.001
Top resid features:
Story
Token Story
Feature activation-0.004
Top resid features:
Highlights
Token Highlights
Feature activation+3.127
Top resid features:
Groups
Token Groups
Feature activation-0.016
Top resid features:
:
Token:
Feature activation-0.054
Top resid features:
Int
Token Int
Feature activation-0.002
Top resid features:
im
Tokenim
Feature activation-0.002
Top resid features:
acy
Tokenacy
Feature activation+0.001
Top resid features:
ark
Tokenark
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
AP
Token AP
Feature activation-0.004
Top resid features:
)
Token)
Feature activation+0.003
Top resid features:
Story
Token Story
Feature activation-0.009
Top resid features:
Highlights
Token Highlights
Feature activation+3.116
Top resid features:
Death
Token Death
Feature activation-0.040
Top resid features:
benefits
Token benefits
Feature activation-0.001
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
families
Token families
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.06

Head 2: 0.05

Head 3: 0.02

Head 4: 0.04

Head 5: 0.43

Head 6: 0.04

Head 7: 0.03

Head 8: 0.04

Head 9: 0.16

Head 10: 0.04

Head 11: 0.05

Positive logits

underestimate2.42

underest2.24

overhe1.98

shocking1.97

alarming1.93

misunderstand1.91

surpr1.88

misconceptions1.86

overest1.86

spoil1.86

angering1.85

mistakes1.82

dangers1.82

underestimated1.81

carbohyd1.81

intens1.81

injuring1.80

risks1.80

questioning1.78

worsening1.77

Negative logits

SourceFile-2.25

Merchant-2.11

Clan-2.05

issance-2.05

LLP-1.99

GUI-1.91

Resident-1.84

ICLE-1.81

wark-1.81

ASCII-1.79

Unix-1.78

alog-1.78

tein-1.77

Zo-1.77

listed-1.76

Lod-1.75

Signed-1.71

Unicode-1.70

Wo-1.67

uler-1.67

INTERVAL 6.798 - 7.553
CONTAINS 0.000%

perjury
Token perjury
Feature activation+0.000
,
Token,
Feature activation+0.000
obstruction
Token obstruction
Feature activation+0.000
of
Token of
Feature activation+0.000
justice
Token justice
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.553
Ċ
TokenĊ
Feature activation+7.514
300
Token300
Feature activation+0.000
drug
Token drug
Feature activation+0.000
convictions
Token convictions
Feature activation+0.000
have
Token have
Feature activation+0.000
,
Token,
Feature activation+0.000
obstruction
Token obstruction
Feature activation+0.000
of
Token of
Feature activation+0.000
justice
Token justice
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.553
Ċ
TokenĊ
Feature activation+7.514
300
Token300
Feature activation+0.000
drug
Token drug
Feature activation+0.000
convictions
Token convictions
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
's
Token's
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
communications
Token communications
Feature activation+0.000
director
Token director
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.389
Ċ
TokenĊ
Feature activation+7.319
He
TokenHe
Feature activation+0.000
said
Token said
Feature activation+0.000
Rubio
Token Rubio
Feature activation+0.000
's
Token's
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
communications
Token communications
Feature activation+0.000
director
Token director
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.389
Ċ
TokenĊ
Feature activation+7.319
He
TokenHe
Feature activation+0.000
said
Token said
Feature activation+0.000
Rubio
Token Rubio
Feature activation+0.000
's
Token's
Feature activation+0.000
primary
Token primary
Feature activation+0.000

INTERVAL 6.042 - 6.798
CONTAINS 0.000%

INTERVAL 5.287 - 6.042
CONTAINS 0.000%

beat
Token beat
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
in
Token in
Feature activation+0.000
Ohio
Token Ohio
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.772
Ċ
TokenĊ
Feature activation+5.534
(
Token(
Feature activation+0.000
CNN
TokenCNN
Feature activation+0.000
)
Token)
Feature activation+0.000
Marco
Token Marco
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
in
Token in
Feature activation+0.000
Ohio
Token Ohio
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.772
Ċ
TokenĊ
Feature activation+5.534
(
Token(
Feature activation+0.000
CNN
TokenCNN
Feature activation+0.000
)
Token)
Feature activation+0.000
Marco
Token Marco
Feature activation+0.000
Rubio
Token Rubio
Feature activation+0.000

INTERVAL 4.532 - 5.287
CONTAINS 0.000%

INTERVAL 3.776 - 4.532
CONTAINS 0.001%

likely
Token likely
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
restored
Token restored
Feature activation+0.000
quickly
Token quickly
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.792
Ċ
TokenĊ
Feature activation+3.681
Defense
TokenDefense
Feature activation+0.000
Department
Token Department
Feature activation+0.000
had
Token had
Feature activation+0.000
said
Token said
Feature activation+0.000
season
Token season
Feature activation+0.000
will
Token will
Feature activation+0.000
feature
Token feature
Feature activation+0.000
seven
Token seven
Feature activation+0.000
primaries
Token primaries
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.028
Ċ
TokenĊ
Feature activation+4.038
Spring
TokenSpring
Feature activation+0.000
Valley
Token Valley
Feature activation+0.000
,
Token,
Feature activation+0.000
Ram
Token Ram
Feature activation+0.000
will
Token will
Feature activation+0.000
feature
Token feature
Feature activation+0.000
seven
Token seven
Feature activation+0.000
primaries
Token primaries
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.028
Ċ
TokenĊ
Feature activation+4.038
Spring
TokenSpring
Feature activation+0.000
Valley
Token Valley
Feature activation+0.000
,
Token,
Feature activation+0.000
Ram
Token Ram
Feature activation+0.000
apo
Tokenapo
Feature activation+0.000
is
Token is
Feature activation+0.000
possible
Token possible
Feature activation+0.000
after
Token after
Feature activation+0.000
heart
Token heart
Feature activation+0.000
attack
Token attack
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.896
Ċ
TokenĊ
Feature activation+3.805
Sexual
TokenSexual
Feature activation+0.000
health
Token health
Feature activation+0.000
is
Token is
Feature activation+0.000
important
Token important
Feature activation+0.000
possible
Token possible
Feature activation+0.000
after
Token after
Feature activation+0.000
heart
Token heart
Feature activation+0.000
attack
Token attack
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.896
Ċ
TokenĊ
Feature activation+3.805
Sexual
TokenSexual
Feature activation+0.000
health
Token health
Feature activation+0.000
is
Token is
Feature activation+0.000
important
Token important
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 3.021 - 3.776
CONTAINS 0.001%

to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
restored
Token restored
Feature activation+0.000
quickly
Token quickly
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.792
Ċ
TokenĊ
Feature activation+3.681
Defense
TokenDefense
Feature activation+0.000
Department
Token Department
Feature activation+0.000
had
Token had
Feature activation+0.000
said
Token said
Feature activation+0.000
government
Token government
Feature activation+0.000
state
Token state
Feature activation+0.000
Assembly
Token Assembly
Feature activation+0.000
districts
Token districts
Feature activation+0.000
have
Token have
Feature activation+0.000
primaries
Token primaries
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.431
Ċ
TokenĊ
Feature activation+3.162
The
TokenThe
Feature activation+0.000
primary
Token primary
Feature activation+0.000
is
Token is
Feature activation+0.000
Sept
Token Sept
Feature activation+0.000
Assembly
Token Assembly
Feature activation+0.000
districts
Token districts
Feature activation+0.000
have
Token have
Feature activation+0.000
primaries
Token primaries
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.431
Ċ
TokenĊ
Feature activation+3.162
The
TokenThe
Feature activation+0.000
primary
Token primary
Feature activation+0.000
is
Token is
Feature activation+0.000
Sept
Token Sept
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 2.266 - 3.021
CONTAINS 0.000%

prevented
Token prevented
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
from
Token from
Feature activation+0.000
being
Token being
Feature activation+0.000
paid
Token paid
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.958
Ċ
TokenĊ
Feature activation+2.769
F
TokenF
Feature activation+0.000
am
Tokenam
Feature activation+0.000
ilies
Tokenilies
Feature activation+0.000
due
Token due
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
from
Token from
Feature activation+0.000
being
Token being
Feature activation+0.000
paid
Token paid
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.958
Ċ
TokenĊ
Feature activation+2.769
F
TokenF
Feature activation+0.000
am
Tokenam
Feature activation+0.000
ilies
Tokenilies
Feature activation+0.000
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
one
Token one
Feature activation+0.000
's
Token's
Feature activation+0.000
death
Token death
Feature activation+0.000
in
Token in
Feature activation+0.000
war
Token war
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.340
Ċ
TokenĊ
Feature activation+2.006
Out
TokenOut
Feature activation+0.000
rage
Tokenrage
Feature activation+0.000
over
Token over
Feature activation+0.000
a
Token a
Feature activation+0.000
is
Token is
Feature activation+0.000
important
Token important
Feature activation+0.000
,
Token,
Feature activation+0.000
researcher
Token researcher
Feature activation+0.000
says
Token says
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.609
Ċ
TokenĊ
Feature activation+2.049
Adv
TokenAdv
Feature activation+0.000
ice
Tokenice
Feature activation+0.000
depends
Token depends
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 1.511 - 2.266
CONTAINS 0.000%

's
Token's
Feature activation+0.000
death
Token death
Feature activation+0.000
in
Token in
Feature activation+0.000
war
Token war
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.340
Ċ
TokenĊ
Feature activation+2.006
Out
TokenOut
Feature activation+0.000
rage
Tokenrage
Feature activation+0.000
over
Token over
Feature activation+0.000
a
Token a
Feature activation+0.000
delay
Token delay
Feature activation+0.000
important
Token important
Feature activation+0.000
,
Token,
Feature activation+0.000
researcher
Token researcher
Feature activation+0.000
says
Token says
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.609
Ċ
TokenĊ
Feature activation+2.049
Adv
TokenAdv
Feature activation+0.000
ice
Tokenice
Feature activation+0.000
depends
Token depends
Feature activation+0.000
on
Token on
Feature activation+0.000
patient
Token patient
Feature activation+0.000
on
Token on
Feature activation+0.000
patient
Token patient
Feature activation+0.000
's
Token's
Feature activation+0.000
overall
Token overall
Feature activation+0.000
health
Token health
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.618
Ċ
TokenĊ
Feature activation+1.035
CH
TokenCH
Feature activation+0.000
IC
TokenIC
Feature activation+0.000
AG
TokenAG
Feature activation+0.000
O
TokenO
Feature activation+0.000

INTERVAL 0.755 - 1.511
CONTAINS 0.001%

primary
Token primary
Feature activation+0.000
is
Token is
Feature activation+0.000
Sept
Token Sept
Feature activation+0.000
.
Token.
Feature activation+0.000
9
Token 9
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.323
Ċ
TokenĊ
Feature activation+0.924
The
TokenThe
Feature activation+0.000
general
Token general
Feature activation+0.000
election
Token election
Feature activation+0.000
is
Token is
Feature activation+0.000
is
Token is
Feature activation+0.000
Sept
Token Sept
Feature activation+0.000
.
Token.
Feature activation+0.000
9
Token 9
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.323
Ċ
TokenĊ
Feature activation+0.924
The
TokenThe
Feature activation+0.000
general
Token general
Feature activation+0.000
election
Token election
Feature activation+0.000
is
Token is
Feature activation+0.000
Nov
Token Nov
Feature activation+0.000
profiles
Token profiles
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.462
Ċ
TokenĊ
Feature activation+1.104
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.462
Ċ
TokenĊ
Feature activation+1.104
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
patient
Token patient
Feature activation+0.000
's
Token's
Feature activation+0.000
overall
Token overall
Feature activation+0.000
health
Token health
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.618
Ċ
TokenĊ
Feature activation+1.035
CH
TokenCH
Feature activation+0.000
IC
TokenIC
Feature activation+0.000
AG
TokenAG
Feature activation+0.000
O
TokenO
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000

INTERVAL 0.000 - 0.755
CONTAINS 99.997%

his
Token his
Feature activation+0.000
work
Token work
Feature activation+0.000
building
Token building
Feature activation+0.000
a
Token a
Feature activation+0.000
start
Token start
Feature activation+0.000
-
Token-
Feature activation+0.000
up
Tokenup
Feature activation+0.000
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
undis
Token undis
Feature activation+0.000
puted
Tokenputed
Feature activation+0.000
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
People
TokenPeople
Feature activation+0.000
getting
Token getting
Feature activation+0.000
organized
Token organized
Feature activation+0.000
against
Token against
Feature activation+0.000
fascist
Token fascist
Feature activation+0.000
'
Token '
Feature activation+0.000
P
TokenP
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
WASHINGTON
TokenWASHINGTON
Feature activation+0.000
,
Token,
Feature activation+0.000
DC
Token DC
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
Senator
Token Senator
Feature activation+0.000
James
Token James
Feature activation+0.000
Lank
Token Lank
Feature activation+0.000
ford
Tokenford
Feature activation+0.000
today
Token today
Feature activation+0.000
politics
Token politics
Feature activation+0.000
in
Token in
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
weeks
Token weeks
Feature activation+0.000
,
Token,
Feature activation+0.000
using
Token using
Feature activation+0.000
his
Token his
Feature activation+0.000
f
Token f
Feature activation+0.000
irt
Tokenirt
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
professional
Token professional
Feature activation+0.000
scientific
Token scientific
Feature activation+0.000
community
Token community
Feature activation+0.000
is
Token is
Feature activation+0.000
already
Token already
Feature activation+0.000
wrestling
Token wrestling
Feature activation+0.000
with
Token with
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 9 in H3.5: (feature 24069)

TOP ACTIVATIONS
MAX = 3.157

information
Token information
Feature activation+0.714
about
Token about
Feature activation+0.075
the
Token the
Feature activation+0.360
incident
Token incident
Feature activation+0.574
to
Token to
Feature activation+1.097
contact
Token contact
Feature activation+3.157
Crime
Token Crime
Feature activation+0.386
St
Token St
Feature activation+0.000
oppers
Tokenoppers
Feature activation+0.000
.
Token.
Feature activation+0.064
Ċ
TokenĊ
Feature activation+0.000
information
Token information
Feature activation+0.548
about
Token about
Feature activation+0.221
this
Token this
Feature activation+0.110
attack
Token attack
Feature activation+0.104
to
Token to
Feature activation+1.094
contact
Token contact
Feature activation+3.038
appropriate
Token appropriate
Feature activation+0.439
law
Token law
Feature activation+0.033
enforcement
Token enforcement
Feature activation+0.339
authorities
Token authorities
Feature activation+0.397
."
Token."
Feature activation+0.000
the
Token the
Feature activation+0.072
suspect
Token suspect
Feature activation+0.418
is
Token is
Feature activation+0.798
asked
Token asked
Feature activation+1.540
to
Token to
Feature activation+1.298
call
Token call
Feature activation+2.768
Phoenix
Token Phoenix
Feature activation+0.000
police
Token police
Feature activation+0.597
or
Token or
Feature activation+0.582
Silent
Token Silent
Feature activation+0.068
Witness
Token Witness
Feature activation+0.000
the
Token the
Feature activation+0.473
case
Token case
Feature activation+0.117
is
Token is
Feature activation+1.043
asked
Token asked
Feature activation+1.812
to
Token to
Feature activation+1.464
contact
Token contact
Feature activation+2.668
police
Token police
Feature activation+0.955
at
Token at
Feature activation+0.480
416
Token 416
Feature activation+0.000
-
Token-
Feature activation+0.000
808
Token808
Feature activation+0.000
seen
Token seen
Feature activation+0.000
Martinez
Token Martinez
Feature activation+0.000
is
Token is
Feature activation+0.587
asked
Token asked
Feature activation+1.131
to
Token to
Feature activation+1.035
call
Token call
Feature activation+2.170
the
Token the
Feature activation+0.460
Detroit
Token Detroit
Feature activation+0.000
Police
Token Police
Feature activation+0.000
investigation
Token investigation
Feature activation+0.021
unit
Token unit
Feature activation+0.457
of
Token of
Feature activation+0.000
misunderstood
Token misunderstood
Feature activation+0.000
terms
Token terms
Feature activation+0.000
,
Token,
Feature activation+0.000
will
Token will
Feature activation+0.900
appreciate
Token appreciate
Feature activation+2.011
the
Token the
Feature activation+0.062
Sig
Token Sig
Feature activation+0.000
mo
Tokenmo
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.000
Pakistan
Token Pakistan
Feature activation+0.000
is
Tokenis
Feature activation+0.000
or
Token or
Feature activation+0.558
Afghans
Token Afghans
Feature activation+0.000
joking
Token joking
Feature activation+0.000
knows
Token knows
Feature activation+1.894
that
Token that
Feature activation+0.425
same
Token same
Feature activation+0.082
-
Token-
Feature activation+0.000
sex
Tokensex
Feature activation+0.000
attraction
Token attraction
Feature activation+0.000
information
Token information
Feature activation+0.127
about
Token about
Feature activation+0.132
the
Token the
Feature activation+0.473
case
Token case
Feature activation+0.117
is
Token is
Feature activation+1.043
asked
Token asked
Feature activation+1.812
to
Token to
Feature activation+1.464
contact
Token contact
Feature activation+2.668
police
Token police
Feature activation+0.955
at
Token at
Feature activation+0.480
416
Token 416
Feature activation+0.000
far
Token far
Feature activation+0.000
away
Tokenaway
Feature activation+0.000
planet
Token planet
Feature activation+0.000
would
Token would
Feature activation+0.710
die
Token die
Feature activation+0.173
a
Token a
Feature activation+1.587
speedy
Token speedy
Feature activation+0.016
death
Token death
Feature activation+0.101
.
Token.
Feature activation+0.062
Nevertheless
Token Nevertheless
Feature activation+0.000
,
Token,
Feature activation+0.000
information
Token information
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.072
suspect
Token suspect
Feature activation+0.418
is
Token is
Feature activation+0.798
asked
Token asked
Feature activation+1.540
to
Token to
Feature activation+1.298
call
Token call
Feature activation+2.768
Phoenix
Token Phoenix
Feature activation+0.000
police
Token police
Feature activation+0.597
or
Token or
Feature activation+0.582
,
Token,
Feature activation+0.000
now
Token now
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
can
Token can
Feature activation+0.000
convert
Token convert
Feature activation+0.000
their
Token their
Feature activation+1.498
Game
Token Game
Feature activation+0.000
boy
Tokenboy
Feature activation+0.000
into
Token into
Feature activation+0.173
a
Token a
Feature activation+0.409
retro
Token retro
Feature activation+0.000
about
Token about
Feature activation+0.132
the
Token the
Feature activation+0.473
case
Token case
Feature activation+0.117
is
Token is
Feature activation+1.043
asked
Token asked
Feature activation+1.812
to
Token to
Feature activation+1.464
contact
Token contact
Feature activation+2.668
police
Token police
Feature activation+0.955
at
Token at
Feature activation+0.480
416
Token 416
Feature activation+0.000
-
Token-
Feature activation+0.000
is
Token is
Feature activation+0.984
being
Token being
Feature activation+0.812
encouraged
Token encouraged
Feature activation+0.444
to
Token to
Feature activation+0.490
debate
Token debate
Feature activation+0.154
their
Token their
Feature activation+1.446
cardboard
Token cardboard
Feature activation+0.000
congressman
Token congressman
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
published
Token published
Feature activation+0.000
within
Token within
Feature activation+0.000
48
Token 48
Feature activation+0.013
hours
Token hours
Feature activation+0.000
will
Token will
Feature activation+1.049
pay
Token pay
Feature activation+1.338
up
Token up
Feature activation+0.643
to
Token to
Feature activation+0.512
âĤ¬
Token âĤ¬
Feature activation+0.437
12
Token12
Feature activation+0.376
,
Token,
Feature activation+0.227
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.072
suspect
Token suspect
Feature activation+0.418
is
Token is
Feature activation+0.798
asked
Token asked
Feature activation+1.540
to
Token to
Feature activation+1.298
call
Token call
Feature activation+2.768
Phoenix
Token Phoenix
Feature activation+0.000
police
Token police
Feature activation+0.597
or
Token or
Feature activation+0.582
Silent
Token Silent
Feature activation+0.068
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.404
10
Token 10
Feature activation+0.000
bucks
Token bucks
Feature activation+0.371
has
Token has
Feature activation+1.038
a
Token a
Feature activation+1.245
chance
Token chance
Feature activation+0.757
of
Token of
Feature activation+0.081
winning
Token winning
Feature activation+0.156
it
Token it
Feature activation+0.631
.
Token.
Feature activation+0.000
Zer
Token Zer
Feature activation+0.000
O
TokenO
Feature activation+0.000
or
Token or
Feature activation+0.000
free
Token free
Feature activation+0.343
if
Token if
Feature activation+0.417
they
Token they
Feature activation+1.216
heard
Token heard
Feature activation+0.000
anything
Token anything
Feature activation+0.000
from
Token from
Feature activation+0.000
their
Token their
Feature activation+0.717
former
Token former
Feature activation+0.020
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
demonstration
Token demonstration
Feature activation+0.000
should
Token should
Feature activation+1.149
be
Token be
Feature activation+1.159
fired
Token fired
Feature activation+1.215
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
his
Token his
Feature activation+0.000
read
Token read
Feature activation+0.000
any
Token any
Feature activation+0.022
Persian
Token Persian
Feature activation+0.000
poetry
Token poetry
Feature activation+0.000
,
Token,
Feature activation+0.015
read
Token read
Feature activation+1.178
a
Token a
Feature activation+0.814
forth
Token forth
Feature activation+0.000
right
Tokenright
Feature activation+0.000
travel
Token travel
Feature activation+0.145
guide
Token guide
Feature activation+0.222
stay
Token stay
Feature activation+0.141
at
Token at
Feature activation+0.052
home
Token home
Feature activation+0.333
and
Token and
Feature activation+0.000
phone
Token phone
Feature activation+0.518
their
Token their
Feature activation+1.177
GP
Token GP
Feature activation+0.204
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
It
TokenIt
Feature activation+0.000

Top DFA by src position
MAX = 3.070

and
Token and
Feature activation+0.006
Top resid features:
officers
Token officers
Feature activation+0.001
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
still
Token still
Feature activation+0.007
Top resid features:
urging
Token urging
Feature activation+0.026
Top resid features:
anyone
Token anyone
Feature activation+3.070
Top resid features:
who
Token who
Feature activation+0.289
Top resid features:
might
Token might
Feature activation+0.019
Top resid features:
have
Token have
Feature activation+0.019
Top resid features:
information
Token information
Feature activation+0.025
Top resid features:
about
Token about
Feature activation+0.006
Top resid features:
statement
Token statement
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
"
Token "
Feature activation-0.002
Top resid features:
We
TokenWe
Feature activation+0.006
Top resid features:
ask
Token ask
Feature activation+0.024
Top resid features:
anyone
Token anyone
Feature activation+3.047
Top resid features:
with
Token with
Feature activation+0.206
Top resid features:
information
Token information
Feature activation+0.141
Top resid features:
about
Token about
Feature activation+0.006
Top resid features:
this
Token this
Feature activation+0.022
Top resid features:
attack
Token attack
Feature activation-0.023
Top resid features:
related
Tokenrelated
Feature activation-0.001
Top resid features:
deaths
Token deaths
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Anyone
TokenAnyone
Feature activation+2.606
Top resid features:
with
Token with
Feature activation+0.263
Top resid features:
information
Token information
Feature activation+0.137
Top resid features:
on
Token on
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.013
Top resid features:
suspect
Token suspect
Feature activation+0.034
Top resid features:
common
Token common
Feature activation+0.000
Top resid features:
nuisance
Token nuisance
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Anyone
TokenAnyone
Feature activation+2.529
Top resid features:
with
Token with
Feature activation+0.251
Top resid features:
information
Token information
Feature activation+0.094
Top resid features:
about
Token about
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
case
Token case
Feature activation+0.013
Top resid features:
she
Token she
Feature activation-0.001
Top resid features:
said
Token said
Feature activation-0.004
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Anyone
TokenAnyone
Feature activation+1.748
Top resid features:
who
Token who
Feature activation+0.581
Top resid features:
's
Token's
Feature activation+0.034
Top resid features:
seen
Token seen
Feature activation+0.034
Top resid features:
Martinez
Token Martinez
Feature activation+0.012
Top resid features:
is
Token is
Feature activation+0.060
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.123
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Anyone
TokenAnyone
Feature activation+1.777
Top resid features:
who
Token who
Feature activation+0.596
Top resid features:
's
Token's
Feature activation+0.006
Top resid features:
ever
Token ever
Feature activation+0.030
Top resid features:
found
Token found
Feature activation+0.006
Top resid features:
themselves
Token themselves
Feature activation-0.008
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
position
Token position
Feature activation-0.002
Top resid features:
on
Token on
Feature activation-0.001
Top resid features:
homosexuality
Token homosexuality
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Anyone
Token Anyone
Feature activation+1.791
Top resid features:
who
Token who
Feature activation+0.465
Top resid features:
has
Token has
Feature activation+0.047
Top resid features:
read
Token read
Feature activation-0.009
Top resid features:
any
Token any
Feature activation+0.107
Top resid features:
Persian
Token Persian
Feature activation+0.004
Top resid features:
common
Token common
Feature activation+0.000
Top resid features:
nuisance
Token nuisance
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.014
Top resid features:
Anyone
TokenAnyone
Feature activation+1.871
Top resid features:
with
Token with
Feature activation+0.230
Top resid features:
information
Token information
Feature activation+0.059
Top resid features:
about
Token about
Feature activation-0.009
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
case
Token case
Feature activation+0.018
Top resid features:
toxic
Token toxic
Feature activation-0.002
Top resid features:
gas
Token gas
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Anyone
TokenAnyone
Feature activation+2.001
Top resid features:
setting
Token setting
Feature activation-0.009
Top resid features:
foot
Token foot
Feature activation+0.012
Top resid features:
on
Token on
Feature activation+0.025
Top resid features:
this
Token this
Feature activation+0.016
Top resid features:
far
Token far
Feature activation-0.001
Top resid features:
related
Tokenrelated
Feature activation-0.001
Top resid features:
deaths
Token deaths
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Anyone
TokenAnyone
Feature activation+1.443
Top resid features:
with
Token with
Feature activation+0.263
Top resid features:
information
Token information
Feature activation+0.108
Top resid features:
on
Token on
Feature activation+0.032
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
suspect
Token suspect
Feature activation+0.033
Top resid features:
new
Token new
Feature activation-0.017
Top resid features:
Mono
Token Mono
Feature activation-0.014
Top resid features:
cartridge
Token cartridge
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
now
Token now
Feature activation-0.017
Top resid features:
anyone
Token anyone
Feature activation+1.846
Top resid features:
can
Token can
Feature activation+0.084
Top resid features:
convert
Token convert
Feature activation+0.077
Top resid features:
their
Token their
Feature activation+0.041
Top resid features:
Game
Token Game
Feature activation+0.000
Top resid features:
boy
Tokenboy
Feature activation+0.000
Top resid features:
common
Token common
Feature activation+0.000
Top resid features:
nuisance
Token nuisance
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
Anyone
TokenAnyone
Feature activation+1.429
Top resid features:
with
Token with
Feature activation+0.195
Top resid features:
information
Token information
Feature activation+0.056
Top resid features:
about
Token about
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
case
Token case
Feature activation+0.013
Top resid features:
hall
Token hall
Feature activation-0.000
Top resid features:
on
Token on
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
calendar
Token calendar
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
Anyone
Token Anyone
Feature activation+1.407
Top resid features:
who
Token who
Feature activation+0.438
Top resid features:
is
Token is
Feature activation+0.047
Top resid features:
feeling
Token feeling
Feature activation+0.002
Top resid features:
especially
Token especially
Feature activation-0.011
Top resid features:
theat
Token theat
Feature activation-0.002
Top resid features:
no
Token no
Feature activation+0.004
Top resid features:
chance
Token chance
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
reply
Token reply
Feature activation+0.040
Top resid features:
:
Token:
Feature activation-0.030
Top resid features:
anyone
Token anyone
Feature activation+1.278
Top resid features:
who
Token who
Feature activation+0.412
Top resid features:
does
Token does
Feature activation+0.056
Top resid features:
not
Token not
Feature activation+0.007
Top resid features:
rect
Token rect
Feature activation-0.001
Top resid features:
ify
Tokenify
Feature activation-0.019
Top resid features:
related
Tokenrelated
Feature activation-0.001
Top resid features:
deaths
Token deaths
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Anyone
TokenAnyone
Feature activation+1.213
Top resid features:
with
Token with
Feature activation+0.237
Top resid features:
information
Token information
Feature activation+0.114
Top resid features:
on
Token on
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
suspect
Token suspect
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
general
Token general
Feature activation+0.003
Top resid features:
lottery
Token lottery
Feature activation+0.010
Top resid features:
so
Token so
Feature activation+0.005
Top resid features:
that
Token that
Feature activation+0.018
Top resid features:
anyone
Token anyone
Feature activation+0.838
Top resid features:
who
Token who
Feature activation+0.500
Top resid features:
don
Token don
Feature activation+0.005
Top resid features:
ates
Tokenates
Feature activation+0.054
Top resid features:
at
Token at
Feature activation+0.019
Top resid features:
least
Token least
Feature activation-0.002
Top resid features:
knowledge
Token knowledge
Feature activation+0.004
Top resid features:
confirm
Token confirm
Feature activation+0.004
Top resid features:
this
Token this
Feature activation+0.002
Top resid features:
?
Token?
Feature activation+0.006
Top resid features:
Can
Token Can
Feature activation+0.025
Top resid features:
someone
Token someone
Feature activation+0.664
Top resid features:
with
Token with
Feature activation+0.070
Top resid features:
access
Token access
Feature activation+0.027
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
Af
Token Af
Feature activation-0.000
Top resid features:
ree
Tokenree
Feature activation-0.001
Top resid features:
Friday
Token Friday
Feature activation+0.011
Top resid features:
when
Token when
Feature activation-0.013
Top resid features:
he
Token he
Feature activation-0.002
Top resid features:
said
Token said
Feature activation-0.057
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
anyone
Token anyone
Feature activation+1.428
Top resid features:
taking
Token taking
Feature activation+0.151
Top resid features:
part
Token part
Feature activation-0.004
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
demonstration
Token demonstration
Feature activation-0.010
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
position
Token position
Feature activation-0.004
Top resid features:
on
Token on
Feature activation-0.002
Top resid features:
homosexuality
Token homosexuality
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.041
Top resid features:
Anyone
Token Anyone
Feature activation+0.940
Top resid features:
who
Token who
Feature activation+0.506
Top resid features:
has
Token has
Feature activation+0.069
Top resid features:
read
Token read
Feature activation+0.033
Top resid features:
any
Token any
Feature activation+0.170
Top resid features:
Persian
Token Persian
Feature activation+0.005
Top resid features:
were
Token were
Feature activation-0.016
Top resid features:
recovering
Token recovering
Feature activation-0.002
Top resid features:
well
Token well
Feature activation-0.002
Top resid features:
and
Token and
Feature activation-0.011
Top resid features:
advised
Token advised
Feature activation-0.004
Top resid features:
anyone
Token anyone
Feature activation+1.469
Top resid features:
with
Token with
Feature activation+0.102
Top resid features:
symptoms
Token symptoms
Feature activation-0.015
Top resid features:
"
Token "
Feature activation-0.018
Top resid features:
to
Tokento
Feature activation+0.064
Top resid features:
stay
Token stay
Feature activation+0.010
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.06

Head 2: 0.05

Head 3: 0.02

Head 4: 0.03

Head 5: 0.43

Head 6: 0.07

Head 7: 0.04

Head 8: 0.05

Head 9: 0.05

Head 10: 0.08

Head 11: 0.07

Positive logits

ombat2.35

elig2.23

ewitness2.21

accuser2.00

forfeit1.99

spouse1.97

irgin1.91

onym1.85

hereby1.80

shalt1.78

forfe1.77

chwitz1.77

Answer1.71

bilt1.70

llah1.70

obyl1.69

Height1.69

ardless1.68

ociate1.66

Registrar1.66

Negative logits

inspired-1.95

introdu-1.80

{:-1.72

isSpecialOrderable-1.70

metaphors-1.66

almost-1.65

among-1.63

Struct-1.62

-1.62

needed-1.62

Rory-1.60

-1.58

Republicans-1.58

signalling-1.57

Rog-1.57

mostly-1.56

underpin-1.56

-1.56

introduced-1.56

Translation-1.55

INTERVAL 2.841 - 3.157
CONTAINS 0.000%

information
Token information
Feature activation+0.714
about
Token about
Feature activation+0.075
the
Token the
Feature activation+0.360
incident
Token incident
Feature activation+0.574
to
Token to
Feature activation+1.097
contact
Token contact
Feature activation+3.157
Crime
Token Crime
Feature activation+0.386
St
Token St
Feature activation+0.000
oppers
Tokenoppers
Feature activation+0.000
.
Token.
Feature activation+0.064
Ċ
TokenĊ
Feature activation+0.000
information
Token information
Feature activation+0.548
about
Token about
Feature activation+0.221
this
Token this
Feature activation+0.110
attack
Token attack
Feature activation+0.104
to
Token to
Feature activation+1.094
contact
Token contact
Feature activation+3.038
appropriate
Token appropriate
Feature activation+0.439
law
Token law
Feature activation+0.033
enforcement
Token enforcement
Feature activation+0.339
authorities
Token authorities
Feature activation+0.397
."
Token."
Feature activation+0.000

INTERVAL 2.525 - 2.841
CONTAINS 0.000%

the
Token the
Feature activation+0.473
case
Token case
Feature activation+0.117
is
Token is
Feature activation+1.043
asked
Token asked
Feature activation+1.812
to
Token to
Feature activation+1.464
contact
Token contact
Feature activation+2.668
police
Token police
Feature activation+0.955
at
Token at
Feature activation+0.480
416
Token 416
Feature activation+0.000
-
Token-
Feature activation+0.000
808
Token808
Feature activation+0.000
the
Token the
Feature activation+0.072
suspect
Token suspect
Feature activation+0.418
is
Token is
Feature activation+0.798
asked
Token asked
Feature activation+1.540
to
Token to
Feature activation+1.298
call
Token call
Feature activation+2.768
Phoenix
Token Phoenix
Feature activation+0.000
police
Token police
Feature activation+0.597
or
Token or
Feature activation+0.582
Silent
Token Silent
Feature activation+0.068
Witness
Token Witness
Feature activation+0.000

INTERVAL 2.210 - 2.525
CONTAINS 0.000%

INTERVAL 1.894 - 2.210
CONTAINS 0.000%

Pakistan
Token Pakistan
Feature activation+0.000
is
Tokenis
Feature activation+0.000
or
Token or
Feature activation+0.558
Afghans
Token Afghans
Feature activation+0.000
joking
Token joking
Feature activation+0.000
knows
Token knows
Feature activation+1.894
that
Token that
Feature activation+0.425
same
Token same
Feature activation+0.082
-
Token-
Feature activation+0.000
sex
Tokensex
Feature activation+0.000
attraction
Token attraction
Feature activation+0.000
seen
Token seen
Feature activation+0.000
Martinez
Token Martinez
Feature activation+0.000
is
Token is
Feature activation+0.587
asked
Token asked
Feature activation+1.131
to
Token to
Feature activation+1.035
call
Token call
Feature activation+2.170
the
Token the
Feature activation+0.460
Detroit
Token Detroit
Feature activation+0.000
Police
Token Police
Feature activation+0.000
investigation
Token investigation
Feature activation+0.021
unit
Token unit
Feature activation+0.457
of
Token of
Feature activation+0.000
misunderstood
Token misunderstood
Feature activation+0.000
terms
Token terms
Feature activation+0.000
,
Token,
Feature activation+0.000
will
Token will
Feature activation+0.900
appreciate
Token appreciate
Feature activation+2.011
the
Token the
Feature activation+0.062
Sig
Token Sig
Feature activation+0.000
mo
Tokenmo
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.000

INTERVAL 1.578 - 1.894
CONTAINS 0.000%

information
Token information
Feature activation+0.127
about
Token about
Feature activation+0.132
the
Token the
Feature activation+0.473
case
Token case
Feature activation+0.117
is
Token is
Feature activation+1.043
asked
Token asked
Feature activation+1.812
to
Token to
Feature activation+1.464
contact
Token contact
Feature activation+2.668
police
Token police
Feature activation+0.955
at
Token at
Feature activation+0.480
416
Token 416
Feature activation+0.000
far
Token far
Feature activation+0.000
away
Tokenaway
Feature activation+0.000
planet
Token planet
Feature activation+0.000
would
Token would
Feature activation+0.710
die
Token die
Feature activation+0.173
a
Token a
Feature activation+1.587
speedy
Token speedy
Feature activation+0.016
death
Token death
Feature activation+0.101
.
Token.
Feature activation+0.062
Nevertheless
Token Nevertheless
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.263 - 1.578
CONTAINS 0.001%

published
Token published
Feature activation+0.000
within
Token within
Feature activation+0.000
48
Token 48
Feature activation+0.013
hours
Token hours
Feature activation+0.000
will
Token will
Feature activation+1.049
pay
Token pay
Feature activation+1.338
up
Token up
Feature activation+0.643
to
Token to
Feature activation+0.512
âĤ¬
Token âĤ¬
Feature activation+0.437
12
Token12
Feature activation+0.376
,
Token,
Feature activation+0.227
,
Token,
Feature activation+0.000
now
Token now
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
can
Token can
Feature activation+0.000
convert
Token convert
Feature activation+0.000
their
Token their
Feature activation+1.498
Game
Token Game
Feature activation+0.000
boy
Tokenboy
Feature activation+0.000
into
Token into
Feature activation+0.173
a
Token a
Feature activation+0.409
retro
Token retro
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.072
suspect
Token suspect
Feature activation+0.418
is
Token is
Feature activation+0.798
asked
Token asked
Feature activation+1.540
to
Token to
Feature activation+1.298
call
Token call
Feature activation+2.768
Phoenix
Token Phoenix
Feature activation+0.000
police
Token police
Feature activation+0.597
or
Token or
Feature activation+0.582
Silent
Token Silent
Feature activation+0.068
information
Token information
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.072
suspect
Token suspect
Feature activation+0.418
is
Token is
Feature activation+0.798
asked
Token asked
Feature activation+1.540
to
Token to
Feature activation+1.298
call
Token call
Feature activation+2.768
Phoenix
Token Phoenix
Feature activation+0.000
police
Token police
Feature activation+0.597
or
Token or
Feature activation+0.582
is
Token is
Feature activation+0.984
being
Token being
Feature activation+0.812
encouraged
Token encouraged
Feature activation+0.444
to
Token to
Feature activation+0.490
debate
Token debate
Feature activation+0.154
their
Token their
Feature activation+1.446
cardboard
Token cardboard
Feature activation+0.000
congressman
Token congressman
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.947 - 1.263
CONTAINS 0.003%

have
Token have
Feature activation+0.000
published
Token published
Feature activation+0.000
within
Token within
Feature activation+0.000
48
Token 48
Feature activation+0.013
hours
Token hours
Feature activation+0.000
will
Token will
Feature activation+1.049
pay
Token pay
Feature activation+1.338
up
Token up
Feature activation+0.643
to
Token to
Feature activation+0.512
âĤ¬
Token âĤ¬
Feature activation+0.437
12
Token12
Feature activation+0.376
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.404
10
Token 10
Feature activation+0.000
bucks
Token bucks
Feature activation+0.371
has
Token has
Feature activation+1.038
a
Token a
Feature activation+1.245
chance
Token chance
Feature activation+0.757
of
Token of
Feature activation+0.081
winning
Token winning
Feature activation+0.156
it
Token it
Feature activation+0.631
.
Token.
Feature activation+0.000
have
Token have
Feature activation+0.000
information
Token information
Feature activation+0.714
about
Token about
Feature activation+0.075
the
Token the
Feature activation+0.360
incident
Token incident
Feature activation+0.574
to
Token to
Feature activation+1.097
contact
Token contact
Feature activation+3.157
Crime
Token Crime
Feature activation+0.386
St
Token St
Feature activation+0.000
oppers
Tokenoppers
Feature activation+0.000
.
Token.
Feature activation+0.064
connection
Token connection
Feature activation+0.000
can
Token can
Feature activation+0.311
literally
Token literally
Feature activation+0.450
broadcast
Token broadcast
Feature activation+0.060
whatever
Token whatever
Feature activation+0.436
they
Token they
Feature activation+1.067
want
Token want
Feature activation+0.092
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
school
Token school
Feature activation+0.000
property
Token property
Feature activation+0.000
selling
Token selling
Feature activation+0.000
drugs
Token drugs
Feature activation+0.000
and
Token and
Feature activation+0.070
they
Token they
Feature activation+1.020
are
Token are
Feature activation+0.152
a
Token a
Feature activation+0.512
student
Token student
Feature activation+0.024
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.326

INTERVAL 0.631 - 0.947
CONTAINS 0.007%

that
Token that
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
wearing
Token wearing
Feature activation+0.000
one
Token one
Feature activation+0.000
is
Token is
Feature activation+0.378
a
Token a
Feature activation+0.734
terrorist
Token terrorist
Feature activation+0.295
...
Token...
Feature activation+0.000
but
Token but
Feature activation+0.000
...
Token...
Feature activation+0.000
we
Token we
Feature activation+0.000
t
Tokent
Feature activation+0.000
imagine
Token imagine
Feature activation+0.000
anybody
Token anybody
Feature activation+0.000
would
Token would
Feature activation+0.258
do
Token do
Feature activation+0.362
something
Token something
Feature activation+0.869
like
Token like
Feature activation+0.120
that
Token that
Feature activation+0.146
,
Token,
Feature activation+0.145
come
Token come
Feature activation+0.061
to
Token to
Feature activation+0.239
out
Token out
Feature activation+0.244
my
Token my
Feature activation+0.441
best
Token best
Feature activation+0.185
friend
Token friend
Feature activation+0.132
âĢ¦
TokenâĢ¦
Feature activation+0.000
he
Tokenhe
Feature activation+0.859
set
Token set
Feature activation+0.000
her
Token her
Feature activation+0.069
place
Token place
Feature activation+0.000
on
Token on
Feature activation+0.000
fire
Token fire
Feature activation+0.000
expression
Token expression
Feature activation+0.000
of
Token of
Feature activation+0.000
any
Token any
Feature activation+0.000
view
Token view
Feature activation+0.000
is
Token is
Feature activation+0.275
needed
Token needed
Feature activation+0.927
content
Token content
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
struggle
Token struggle
Feature activation+0.000
for
Token for
Feature activation+0.000
ath
Tokenath
Feature activation+0.000
starts
Token starts
Feature activation+0.000
out
Token out
Feature activation+0.000
with
Token with
Feature activation+0.000
roughly
Token roughly
Feature activation+0.000
equal
Token equal
Feature activation+0.636
resources
Token resources
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000

INTERVAL 0.316 - 0.631
CONTAINS 0.021%

authorized
Token authorized
Feature activation+0.120
by
Token by
Feature activation+0.054
a
Token a
Feature activation+0.697
religious
Token religious
Feature activation+0.267
organization
Token organization
Feature activation+0.165
to
Token to
Feature activation+0.622
offic
Token offic
Feature activation+0.154
iate
Tokeniate
Feature activation+0.144
marriages
Token marriages
Feature activation+0.215
,
Token,
Feature activation+0.677
such
Token such
Feature activation+0.782
âĢ
TokenâĢ
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
find
Token find
Feature activation+0.344
they
Token they
Feature activation+0.183
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
very
Token very
Feature activation+0.011
someone
Token someone
Feature activation+0.000
else
Token else
Feature activation+0.000
had
Token had
Feature activation+0.000
secretly
Token secretly
Feature activation+0.000
written
Token written
Feature activation+0.000
his
Token his
Feature activation+0.589
most
Token most
Feature activation+0.000
famous
Token famous
Feature activation+0.000
compositions
Token compositions
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
-
Token-
Feature activation+0.000
808
Token808
Feature activation+0.000
-
Token-
Feature activation+0.000
4
Token4
Feature activation+0.000
100
Token100
Feature activation+0.000
or
Token or
Feature activation+0.533
Crime
Token Crime
Feature activation+0.000
St
Token St
Feature activation+0.000
oppers
Tokenoppers
Feature activation+0.000
anonymously
Token anonymously
Feature activation+0.232
at
Token at
Feature activation+0.516
like
Token like
Feature activation+0.120
that
Token that
Feature activation+0.146
,
Token,
Feature activation+0.145
come
Token come
Feature activation+0.061
to
Token to
Feature activation+0.239
find
Token find
Feature activation+0.381
out
Token out
Feature activation+0.244
my
Token my
Feature activation+0.441
best
Token best
Feature activation+0.185
friend
Token friend
Feature activation+0.132
âĢ¦
TokenâĢ¦
Feature activation+0.000

INTERVAL 0.000 - 0.316
CONTAINS 99.967%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
offense
Token offense
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
the
Token the
Feature activation+0.000
A
Token A
Feature activation+0.000
-
Token-
Feature activation+0.000
g
Tokeng
Feature activation+0.000
aps
Tokenaps
Feature activation+0.000
saved
Token saved
Feature activation+0.000
already
Token already
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sir
TokenSir
Feature activation+0.000
Ian
Token Ian
Feature activation+0.000
,
Token,
Feature activation+0.000
chairman
Token chairman
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
black
Token black
Feature activation+0.000
civil
Token civil
Feature activation+0.000
rights
Token rights
Feature activation+0.000
organization
Token organization
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Movement
Token Movement
Feature activation+0.000
for
Token for
Feature activation+0.000
Black
Token Black
Feature activation+0.000
Lives
Token Lives
Feature activation+0.000
Ob
TokenOb
Feature activation+0.000
taining
Tokentaining
Feature activation+0.000
samples
Token samples
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Vol
TokenVol
Feature activation+0.000
unte
Tokenunte
Feature activation+0.000
er
Tokener
Feature activation+0.000
fish
Token fish
Feature activation+0.000
sle
Token sle
Feature activation+0.000
uth
Tokenuth
Feature activation+0.000
Apple
Token Apple
Feature activation+0.000
allows
Token allows
Feature activation+0.000
iPad
Token iPad
Feature activation+0.000
owners
Token owners
Feature activation+0.000
to
Token to
Feature activation+0.000
download
Token download
Feature activation+0.000
Kindle
Token Kindle
Feature activation+0.000
apps
Token apps
Feature activation+0.000
onto
Token onto
Feature activation+0.000
their
Token their
Feature activation+0.000
iPads
Token iPads
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