H5.5 top features

Top feature 0 in H5.5: (feature 27535)

TOP ACTIVATIONS
MAX = 3.884

F
TokenF
Feature activation+0.000
sponsored
Token sponsored
Feature activation+0.000
its
Token its
Feature activation+0.000
first
Token first
Feature activation+0.000
CH
Token CH
Feature activation+0.000
D
TokenD
Feature activation+3.884
research
Token research
Feature activation+0.000
project
Token project
Feature activation+0.000
in
Token in
Feature activation+0.000
1965
Token 1965
Feature activation+0.000
,
Token,
Feature activation+0.000
3
Token 3
Feature activation+0.000
-
Token-
Feature activation+0.000
category
Tokencategory
Feature activation+0.639
G
Token G
Feature activation+0.000
SR
TokenSR
Feature activation+0.057
H
TokenH
Feature activation+3.732
variable
Token variable
Feature activation+0.500
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
participant
Token participant
Feature activation+0.099
-
Token-
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
between
Token between
Feature activation+0.000
those
Token those
Feature activation+0.000
peaks
Token peaks
Feature activation+3.582
and
Token and
Feature activation+0.000
trough
Token trough
Feature activation+0.000
s
Tokens
Feature activation+0.000
is
Token is
Feature activation+0.000
changed
Token changed
Feature activation+0.000
cost
Token cost
Feature activation+0.000
of
Token of
Feature activation+0.000
phot
Token phot
Feature activation+0.000
ov
Tokenov
Feature activation+0.000
olt
Tokenolt
Feature activation+0.000
aic
Tokenaic
Feature activation+3.555
power
Token power
Feature activation+0.000
supply
Token supply
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
for
Token for
Feature activation+0.000
private
Token private
Feature activation+0.000
universities
Token universities
Feature activation+0.000
to
Token to
Feature activation+0.000
not
Token not
Feature activation+0.000
record
Token record
Feature activation+3.460
the
Token the
Feature activation+0.024
testimonies
Token testimonies
Feature activation+0.000
of
Token of
Feature activation+0.000
students
Token students
Feature activation+1.797
involved
Token involved
Feature activation+0.000
the
Token the
Feature activation+0.000
name
Token name
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
genus
Token genus
Feature activation+3.423
and
Token and
Feature activation+0.000
species
Token species
Feature activation+0.000
of
Token of
Feature activation+0.000
frog
Token frog
Feature activation+0.000
fish
Tokenfish
Feature activation+0.000
text
Token text
Feature activation+0.000
came
Token came
Feature activation+0.000
from
Token from
Feature activation+0.000
this
Token this
Feature activation+0.000
press
Token press
Feature activation+0.006
release
Token release
Feature activation+3.393
in
Token in
Feature activation+0.000
E
Token E
Feature activation+0.000
ure
Tokenure
Feature activation+0.000
ka
Tokenka
Feature activation+0.000
Alert
TokenAlert
Feature activation+0.000
trans
Token trans
Feature activation+0.000
people
Token people
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
want
Token want
Feature activation+0.000
drag
Token drag
Feature activation+3.365
queens
Token queens
Feature activation+0.000
using
Token using
Feature activation+0.000
certain
Token certain
Feature activation+0.000
words
Token words
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
enjoy
Token enjoy
Feature activation+0.000
this
Token this
Feature activation+0.000
fine
Token fine
Feature activation+0.000
Mod
Token Mod
Feature activation+0.000
ification
Tokenification
Feature activation+3.319
as
Token as
Feature activation+0.000
long
Token long
Feature activation+0.000
as
Token as
Feature activation+0.000
possible
Token possible
Feature activation+0.000
.
Token.
Feature activation+0.000
According
Token According
Feature activation+0.000
to
Token to
Feature activation+0.000
Alex
Token Alex
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
Bill
TokenBill
Feature activation+3.307
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Winter
Token Winter
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
who
Token who
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
rate
Token rate
Feature activation+0.000
of
Token of
Feature activation+0.000
sc
Token sc
Feature activation+0.000
abies
Tokenabies
Feature activation+3.305
was
Token was
Feature activation+0.000
35
Token 35
Feature activation+0.000
%
Token%
Feature activation+0.000
and
Token and
Feature activation+0.000
25
Token 25
Feature activation+0.000
be
Token be
Feature activation+0.000
served
Token served
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
subsequent
Token subsequent
Feature activation+0.000
GET
Token GET
Feature activation+3.298
request
Token request
Feature activation+0.076
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
POST
Token POST
Feature activation+0.000
request
Token request
Feature activation+0.000
er
Tokener
Feature activation+0.000
app
Token app
Feature activation+0.000
requires
Token requires
Feature activation+0.000
a
Token a
Feature activation+0.000
valid
Token valid
Feature activation+0.000
subscription
Token subscription
Feature activation+3.287
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
subscription
Token subscription
Feature activation+1.243
Ċ
TokenĊ
Feature activation+0.000
Def
TokenDef
Feature activation+0.000
ining
Tokenining
Feature activation+0.000
the
Token the
Feature activation+0.000
Data
Token Data
Feature activation+0.000
Source
Token Source
Feature activation+3.275
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Step
TokenStep
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
P
Token P
Feature activation+0.000
ressed
Tokenressed
Feature activation+0.000
al
Token al
Feature activation+0.000
f
Tokenf
Feature activation+0.000
alf
Tokenalf
Feature activation+0.000
a
Tokena
Feature activation+3.272
hay
Token hay
Feature activation+0.076
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
remaining
Token remaining
Feature activation+0.000
sol
Token sol
Feature activation+0.000
bruised
Token bruised
Feature activation+0.000
and
Token and
Feature activation+0.000
bright
Token bright
Feature activation+0.000
red
Token red
Feature activation+0.000
sp
Token sp
Feature activation+0.000
anked
Tokenanked
Feature activation+3.262
buttocks
Token buttocks
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
well
Token well
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
comes
Token comes
Feature activation+0.000
to
Token to
Feature activation+0.000
giving
Token giving
Feature activation+3.242
and
Token and
Feature activation+0.131
receiving
Token receiving
Feature activation+0.000
feedback
Token feedback
Feature activation+0.000
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
quick
Token quick
Feature activation+0.000
overview
Token overview
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
syll
Token syll
Feature activation+0.073
abus
Tokenabus
Feature activation+3.226
,
Token,
Feature activation+0.505
course
Token course
Feature activation+0.000
,
Token,
Feature activation+0.047
and
Token and
Feature activation+0.000
what
Token what
Feature activation+0.000
6
Token 6
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
Known
Token Known
Feature activation+0.000
issues
Token issues
Feature activation+3.209
¶
Token¶
Feature activation+0.000
J
Token J
Feature activation+0.000
I
TokenI
Feature activation+0.000
RA
TokenRA
Feature activation+0.000
T
Token T
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
contin
Tokencontin
Feature activation+0.265
uation
Tokenuation
Feature activation+3.201
version
Token version
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

Top DFA by src position
MAX = 4.073

dietary
Token dietary
Feature activation+0.011
Top resid features:
causes
Token causes
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
CH
Token CH
Feature activation-0.003
Top resid features:
D
TokenD
Feature activation-0.022
Top resid features:
and
Token and
Feature activation+4.073
Top resid features:
assembled
Token assembled
Feature activation-0.001
Top resid features:
findings
Token findings
Feature activation+0.001
Top resid features:
chron
Token chron
Feature activation-0.002
Top resid features:
ologically
Tokenologically
Feature activation+0.001
Top resid features:
into
Token into
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
G
Token G
Feature activation+0.000
Top resid features:
SR
TokenSR
Feature activation+0.002
Top resid features:
H
TokenH
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+3.904
Top resid features:
physician
Token physician
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
ass
Tokenass
Feature activation+0.001
Top resid features:
essed
Tokenessed
Feature activation+0.005
Top resid features:
health
Token health
Feature activation-0.001
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
wave
Token wave
Feature activation-0.010
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
with
Token with
Feature activation+0.001
Top resid features:
peaks
Token peaks
Feature activation-0.004
Top resid features:
and
Token and
Feature activation+3.733
Top resid features:
trough
Token trough
Feature activation+0.012
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.048
Top resid features:
When
Token When
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
phot
Token phot
Feature activation-0.000
Top resid features:
ov
Tokenov
Feature activation-0.002
Top resid features:
olt
Tokenolt
Feature activation-0.001
Top resid features:
aic
Tokenaic
Feature activation-0.000
Top resid features:
and
Token and
Feature activation+3.806
Top resid features:
water
Token water
Feature activation+0.041
Top resid features:
reuse
Token reuse
Feature activation+0.006
Top resid features:
systems
Token systems
Feature activation+0.007
Top resid features:
necessary
Token necessary
Feature activation+0.000
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
investigators
Token investigators
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
recording
Token recording
Feature activation+0.003
Top resid features:
or
Token or
Feature activation+3.641
Top resid features:
ver
Token ver
Feature activation+0.022
Top resid features:
bat
Tokenbat
Feature activation-0.001
Top resid features:
im
Tokenim
Feature activation+0.000
Top resid features:
transcript
Token transcript
Feature activation+0.030
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
".
Token ".
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.019
Top resid features:
New
TokenNew
Feature activation+0.001
Top resid features:
fish
Token fish
Feature activation+0.014
Top resid features:
genus
Token genus
Feature activation+0.029
Top resid features:
and
Token and
Feature activation+3.430
Top resid features:
species
Token species
Feature activation+0.062
Top resid features:
named
Token named
Feature activation+0.021
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
its
Token its
Feature activation+0.001
Top resid features:
red
Token red
Feature activation+0.003
Top resid features:
relying
Token relying
Feature activation-0.001
Top resid features:
heavily
Token heavily
Feature activation-0.001
Top resid features:
on
Token on
Feature activation-0.000
Top resid features:
press
Token press
Feature activation-0.001
Top resid features:
releases
Token releases
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+3.449
Top resid features:
study
Token study
Feature activation+0.015
Top resid features:
summ
Token summ
Feature activation+0.001
Top resid features:
aries
Tokenaries
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
For
Token For
Feature activation+0.001
Top resid features:
ask
Token ask
Feature activation+0.000
Top resid features:
members
Token members
Feature activation+0.001
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
drag
Token drag
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+3.468
Top resid features:
L
Token L
Feature activation+0.066
Top resid features:
GB
TokenGB
Feature activation+0.008
Top resid features:
communities
Token communities
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
stop
Token stop
Feature activation+0.001
Top resid features:
required
Token required
Feature activation+0.001
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
Mod
Token Mod
Feature activation+0.009
Top resid features:
ification
Tokenification
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+3.408
Top resid features:
its
Token its
Feature activation+0.075
Top resid features:
Exp
Token Exp
Feature activation+0.003
Top resid features:
ans
Tokenans
Feature activation+0.001
Top resid features:
ions
Tokenions
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.021
Top resid features:
forth
Token forth
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
third
Token third
Feature activation+0.004
Top resid features:
Bill
Token Bill
Feature activation+0.004
Top resid features:
&
Token &
Feature activation+3.331
Top resid features:
Ted
Token Ted
Feature activation+0.164
Top resid features:
adventure
Token adventure
Feature activation+0.010
Top resid features:
has
Token has
Feature activation+0.005
Top resid features:
officially
Token officially
Feature activation-0.000
Top resid features:
been
Token been
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
Sc
TokenSc
Feature activation-0.000
Top resid features:
abies
Tokenabies
Feature activation+0.010
Top resid features:
and
Token and
Feature activation+3.509
Top resid features:
l
Token l
Feature activation+0.039
Top resid features:
ice
Tokenice
Feature activation+0.015
Top resid features:
are
Token are
Feature activation+0.008
Top resid features:
quickly
Token quickly
Feature activation-0.003
Top resid features:
spreading
Token spreading
Feature activation-0.000
Top resid features:
able
Tokenable
Feature activation+0.003
Top resid features:
Methods
Token Methods
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
GET
TokenGET
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+3.474
Top resid features:
HEAD
Token HEAD
Feature activation+0.012
Top resid features:
responses
Token responses
Feature activation+0.017
Top resid features:
may
Token may
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
cache
Token cache
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Sub
TokenSub
Feature activation+0.000
Top resid features:
script
Tokenscript
Feature activation+0.000
Top resid features:
ions
Tokenions
Feature activation-0.002
Top resid features:
&
Token &
Feature activation+3.449
Top resid features:
Terms
Token Terms
Feature activation+0.040
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
****************
Token****************
Feature activation+0.001
Top resid features:
********
Token********
Feature activation+0.000
Top resid features:
Windows
Token Windows
Feature activation+0.000
Top resid features:
Phone
Token Phone
Feature activation+0.000
Top resid features:
Tool
Token Tool
Feature activation+0.002
Top resid features:
kit
Tokenkit
Feature activation+0.001
Top resid features:
Source
Token Source
Feature activation-0.005
Top resid features:
&
Token &
Feature activation+3.480
Top resid features:
Sample
Token Sample
Feature activation+0.016
Top resid features:
-
Token -
Feature activation-0.000
Top resid features:
Aug
Token Aug
Feature activation-0.000
Top resid features:
2011
Token 2011
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
al
Token al
Feature activation-0.000
Top resid features:
f
Tokenf
Feature activation-0.000
Top resid features:
alf
Tokenalf
Feature activation-0.002
Top resid features:
a
Tokena
Feature activation+0.012
Top resid features:
and
Token and
Feature activation+2.171
Top resid features:
/
Token/
Feature activation+0.008
Top resid features:
or
Tokenor
Feature activation+0.179
Top resid features:
cotton
Token cotton
Feature activation+0.022
Top resid features:
seed
Tokenseed
Feature activation+0.017
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
e
Tokene
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
be
Token be
Feature activation-0.000
Top resid features:
sp
Token sp
Feature activation-0.001
Top resid features:
anked
Tokenanked
Feature activation+0.062
Top resid features:
&
Token &
Feature activation+3.315
Top resid features:
kiss
Token kiss
Feature activation+0.001
Top resid features:
one
Token one
Feature activation+0.013
Top resid features:
another
Token another
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
After
Token After
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Diff
TokenDiff
Feature activation-0.001
Top resid features:
iculty
Tokeniculty
Feature activation-0.004
Top resid features:
giving
Token giving
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+3.525
Top resid features:
receiving
Token receiving
Feature activation+0.000
Top resid features:
negative
Token negative
Feature activation+0.035
Top resid features:
feedback
Token feedback
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
At
Token At
Feature activation-0.003
Top resid features:
--
Token --
Feature activation-0.002
Top resid features:
[
Token[
Feature activation+0.000
Top resid features:
Sy
Token Sy
Feature activation+0.001
Top resid features:
ll
Tokenll
Feature activation-0.000
Top resid features:
abus
Tokenabus
Feature activation-0.003
Top resid features:
and
Token and
Feature activation+3.531
Top resid features:
Review
Token Review
Feature activation+0.008
Top resid features:
|
Token |
Feature activation+0.013
Top resid features:
|
Token |
Feature activation+0.000
Top resid features:
|
Token |
Feature activation-0.000
Top resid features:
--------------------------------
Token --------------------------------
Feature activation-0.001
Top resid features:
Known
Token Known
Feature activation+0.005
Top resid features:
Lim
Token Lim
Feature activation+0.009
Top resid features:
itations
Tokenitations
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.025
Top resid features:
Issues
Token Issues
Feature activation+0.032
Top resid features:
and
Token and
Feature activation+3.355
Top resid features:
Work
Token Work
Feature activation+0.042
Top resid features:
ar
Tokenar
Feature activation+0.000
Top resid features:
ounds
Tokenounds
Feature activation+0.000
Top resid features:
¶
Token¶
Feature activation+0.054
Top resid features:
6
Token 6
Feature activation-0.028
Top resid features:
makes
Token makes
Feature activation+0.000
Top resid features:
use
Token use
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
contin
Token contin
Feature activation-0.003
Top resid features:
uations
Tokenuations
Feature activation-0.010
Top resid features:
and
Token and
Feature activation+3.405
Top resid features:
one
Token one
Feature activation+0.020
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
does
Token does
Feature activation-0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.03

Head 2: 0.02

Head 3: 0.02

Head 4: 0.02

Head 5: 0.62

Head 6: 0.02

Head 7: 0.02

Head 8: 0.05

Head 9: 0.08

Head 10: 0.06

Head 11: 0.03

Positive logits

and2.18

&2.10

1.74

ands1.69

AND1.63

CTR1.62

±1.61

/​1.60

or1.60

ihara1.58

ever1.57

Luxembourg1.55

1.54

1.53

tel1.53

/1.53

COUR1.52

ilaterally1.52

oeuv1.51

ORS1.51

Negative logits

sonic-1.50

obe-1.48

Mug-1.45

constitu-1.44

Balt-1.38

Sleeping-1.36

20439-1.34

Rock-1.33

Negro-1.32

Tup-1.32

senal-1.31

aucuses-1.31

heastern-1.30

suscept-1.30

oğan-1.29

eneg-1.29

rolet-1.28

Moto-1.28

musical-1.28

Anth-1.26

INTERVAL 3.495 - 3.884
CONTAINS 0.000%

,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
between
Token between
Feature activation+0.000
those
Token those
Feature activation+0.000
peaks
Token peaks
Feature activation+3.582
and
Token and
Feature activation+0.000
trough
Token trough
Feature activation+0.000
s
Tokens
Feature activation+0.000
is
Token is
Feature activation+0.000
changed
Token changed
Feature activation+0.000
3
Token 3
Feature activation+0.000
-
Token-
Feature activation+0.000
category
Tokencategory
Feature activation+0.639
G
Token G
Feature activation+0.000
SR
TokenSR
Feature activation+0.057
H
TokenH
Feature activation+3.732
variable
Token variable
Feature activation+0.500
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
participant
Token participant
Feature activation+0.099
-
Token-
Feature activation+0.000
F
TokenF
Feature activation+0.000
sponsored
Token sponsored
Feature activation+0.000
its
Token its
Feature activation+0.000
first
Token first
Feature activation+0.000
CH
Token CH
Feature activation+0.000
D
TokenD
Feature activation+3.884
research
Token research
Feature activation+0.000
project
Token project
Feature activation+0.000
in
Token in
Feature activation+0.000
1965
Token 1965
Feature activation+0.000
,
Token,
Feature activation+0.000
cost
Token cost
Feature activation+0.000
of
Token of
Feature activation+0.000
phot
Token phot
Feature activation+0.000
ov
Tokenov
Feature activation+0.000
olt
Tokenolt
Feature activation+0.000
aic
Tokenaic
Feature activation+3.555
power
Token power
Feature activation+0.000
supply
Token supply
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 3.107 - 3.495
CONTAINS 0.002%

5
Token 5
Feature activation+0.000
more
Token more
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
why
Token why
Feature activation+0.000
Newport
Token Newport
Feature activation+0.000
News
Token News
Feature activation+3.159
doesn
Token doesn
Feature activation+0.455
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
suck
Token suck
Feature activation+0.000
6
Token 6
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000
Known
Token Known
Feature activation+0.000
issues
Token issues
Feature activation+3.209
¶
Token¶
Feature activation+0.000
J
Token J
Feature activation+0.000
I
TokenI
Feature activation+0.000
RA
TokenRA
Feature activation+0.000
T
Token T
Feature activation+0.000
and
Token and
Feature activation+0.000
enjoy
Token enjoy
Feature activation+0.000
this
Token this
Feature activation+0.000
fine
Token fine
Feature activation+0.000
Mod
Token Mod
Feature activation+0.000
ification
Tokenification
Feature activation+3.319
as
Token as
Feature activation+0.000
long
Token long
Feature activation+0.000
as
Token as
Feature activation+0.000
possible
Token possible
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
rate
Token rate
Feature activation+0.000
of
Token of
Feature activation+0.000
sc
Token sc
Feature activation+0.000
abies
Tokenabies
Feature activation+3.305
was
Token was
Feature activation+0.000
35
Token 35
Feature activation+0.000
%
Token%
Feature activation+0.000
and
Token and
Feature activation+0.000
25
Token 25
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Def
TokenDef
Feature activation+0.000
ining
Tokenining
Feature activation+0.000
the
Token the
Feature activation+0.000
Data
Token Data
Feature activation+0.000
Source
Token Source
Feature activation+3.275
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Step
TokenStep
Feature activation+0.000
1
Token1
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 2.718 - 3.107
CONTAINS 0.007%

young
Token young
Feature activation+0.000
people
Token people
Feature activation+0.000
were
Token were
Feature activation+0.000
debating
Token debating
Feature activation+0.000
the
Token the
Feature activation+0.000
pros
Token pros
Feature activation+2.894
and
Token and
Feature activation+0.000
cons
Token cons
Feature activation+0.000
of
Token of
Feature activation+0.000
exams
Token exams
Feature activation+0.000
.
Token.
Feature activation+0.000
and
Token and
Feature activation+0.000
development
Token development
Feature activation+0.000
centre
Token centre
Feature activation+1.052
focusing
Token focusing
Feature activation+0.000
on
Token on
Feature activation+0.000
autonomous
Token autonomous
Feature activation+2.827
and
Token and
Feature activation+0.000
remote
Token remote
Feature activation+0.000
-
Token-
Feature activation+0.000
controlled
Tokencontrolled
Feature activation+0.000
shipping
Token shipping
Feature activation+0.000
looked
Token looked
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
saw
Token saw
Feature activation+0.000
tribal
Token tribal
Feature activation+0.000
councils
Token councils
Feature activation+2.787
.
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
Glass
TokenGlass
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
serves
Token serves
Feature activation+0.000
Victor
Token Victor
Feature activation+2.782
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
debut
Token debut
Feature activation+0.000
as
Token as
Feature activation+0.000
Imagine
Token Imagine
Feature activation+0.000
if
Token if
Feature activation+0.000
every
Token every
Feature activation+0.000
time
Token time
Feature activation+0.000
you
Token you
Feature activation+0.000
ordered
Token ordered
Feature activation+2.958
something
Token something
Feature activation+0.000
on
Token on
Feature activation+0.000
Amazon
Token Amazon
Feature activation+0.000
,
Token,
Feature activation+0.000
instead
Token instead
Feature activation+0.000

INTERVAL 2.330 - 2.718
CONTAINS 0.012%

as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
creator
Token creator
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
C
Token C
Feature activation+2.519
programming
Token programming
Feature activation+0.000
language
Token language
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
key
Token key
Feature activation+0.000
through
Token through
Feature activation+0.000
cities
Token cities
Feature activation+0.000
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
racial
Token racial
Feature activation+0.000
barriers
Token barriers
Feature activation+2.484
and
Token and
Feature activation+0.000
segregation
Token segregation
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
we
Token we
Feature activation+0.000
we
Token we
Feature activation+0.000
're
Token're
Feature activation+0.000
watching
Token watching
Feature activation+0.000
in
Token in
Feature activation+0.000
pools
Token pools
Feature activation+2.336
.
Token.
Feature activation+0.000
Me
TokenMe
Feature activation+0.000
lee
Tokenlee
Feature activation+0.000
is
Token is
Feature activation+0.000
much
Token much
Feature activation+0.000
found
Token found
Feature activation+0.000
that
Token that
Feature activation+0.000
discrete
Token discrete
Feature activation+0.000
NA
Token NA
Feature activation+0.071
c
Tokenc
Feature activation+0.000
core
Token core
Feature activation+2.689
and
Token and
Feature activation+0.000
shell
Token shell
Feature activation+0.000
lesions
Token lesions
Feature activation+0.000
produced
Token produced
Feature activation+0.000
26
Token 26
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
method
Token method
Feature activation+0.000
of
Token of
Feature activation+0.000
reviewing
Token reviewing
Feature activation+2.347
new
Token new
Feature activation+0.000
sets
Token sets
Feature activation+0.000
.
Token.
Feature activation+0.000
Rather
Token Rather
Feature activation+0.000
than
Token than
Feature activation+0.000

INTERVAL 1.942 - 2.330
CONTAINS 0.023%

their
Token their
Feature activation+0.000
twenties
Token twenties
Feature activation+0.000
,
Token,
Feature activation+0.000
well
Token well
Feature activation+0.000
-
Token-
Feature activation+0.000
educated
Tokeneducated
Feature activation+1.951
and
Token and
Feature activation+0.000
looking
Token looking
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
and
Token and
Feature activation+0.000
Constantinople
Token Constantinople
Feature activation+0.012
.
Token.
Feature activation+0.000
Byz
Token Byz
Feature activation+0.663
ant
Tokenant
Feature activation+0.000
ium
Tokenium
Feature activation+1.990
is
Token is
Feature activation+1.335
occurring
Token occurring
Feature activation+0.000
at
Token at
Feature activation+0.000
block
Token block
Feature activation+0.000
number
Token number
Feature activation+0.000
idea
Token idea
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ĺ
Tokenĺ
Feature activation+0.000
where
Tokenwhere
Feature activation+0.000
does
Token does
Feature activation+0.000
Matt
Token Matt
Feature activation+2.266
Hardy
Token Hardy
Feature activation+0.000
end
Token end
Feature activation+0.000
and
Token and
Feature activation+0.000
Broken
Token Broken
Feature activation+0.000
Matt
Token Matt
Feature activation+0.111
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
drive
Token drive
Feature activation+0.000
the
Token the
Feature activation+0.000
pop
Token pop
Feature activation+0.000
ulating
Tokenulating
Feature activation+1.997
of
Token of
Feature activation+0.238
specific
Token specific
Feature activation+0.000
,
Token,
Feature activation+0.000
national
Token national
Feature activation+0.000
areas
Token areas
Feature activation+0.000
and
Token and
Feature activation+0.000
time
Token time
Feature activation+0.000
again
Token again
Feature activation+0.000
to
Token to
Feature activation+0.000
burden
Token burden
Feature activation+0.000
Thor
Token Thor
Feature activation+2.207
.
Token.
Feature activation+0.254
Mal
Token Mal
Feature activation+0.000
ek
Tokenek
Feature activation+0.000
ith
Tokenith
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.553 - 1.942
CONTAINS 0.036%

000
Token000
Feature activation+0.000
annually
Token annually
Feature activation+0.000
from
Token from
Feature activation+0.000
its
Token its
Feature activation+0.000
general
Token general
Feature activation+0.000
fund
Token fund
Feature activation+1.646
and
Token and
Feature activation+0.000
$
Token $
Feature activation+0.000
4
Token4
Feature activation+0.000
million
Token million
Feature activation+0.000
grants
Token grants
Feature activation+0.000
margins
Token margins
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
these
Token these
Feature activation+0.000
,
Token,
Feature activation+0.000
recounts
Token recounts
Feature activation+1.762
ensure
Token ensure
Feature activation+0.000
that
Token that
Feature activation+0.000
every
Token every
Feature activation+0.000
vote
Token vote
Feature activation+0.000
is
Token is
Feature activation+0.000
enhanced
Token enhanced
Feature activation+0.000
15
Token 15
Feature activation+0.000
min
Token min
Feature activation+0.000
following
Token following
Feature activation+0.000
protein
Token protein
Feature activation+0.000
ingestion
Token ingestion
Feature activation+1.646
.
Token.
Feature activation+0.000
S
Token S
Feature activation+0.000
ixty
Tokenixty
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
post
Token post
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
purposes
Token purposes
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
logic
Token logic
Feature activation+1.761
puzzle
Token puzzle
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
highly
Tokenhighly
Feature activation+0.000
between
Token between
Feature activation+0.000
flare
Token flare
Feature activation+1.061
and
Token and
Feature activation+0.000
non
Token non
Feature activation+0.000
fl
Tokenfl
Feature activation+1.907
are
Tokenare
Feature activation+1.613
groups
Token groups
Feature activation+0.000
for
Token for
Feature activation+0.000
presence
Token presence
Feature activation+0.000
or
Token or
Feature activation+0.000
number
Token number
Feature activation+0.000

INTERVAL 1.165 - 1.553
CONTAINS 0.045%

computation
Token computation
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
tree
Token tree
Feature activation+0.000
whose
Token whose
Feature activation+0.000
root
Token root
Feature activation+1.518
is
Token is
Feature activation+0.543
$
Token $
Feature activation+0.000
+
Token+
Feature activation+0.000
$
Token$
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
sector
Token sector
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
bitcoin
Token bitcoin
Feature activation+1.430
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
image
Token image
Feature activation+0.000
was
Token was
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
D
TokenD
Feature activation+1.685
HS
TokenHS
Feature activation+1.962
is
Token is
Feature activation+1.444
specifically
Token specifically
Feature activation+0.000
reviewing
Token reviewing
Feature activation+0.000
policies
Token policies
Feature activation+0.000
on
Token on
Feature activation+0.000
when
Token when
Feature activation+0.000
a
Token a
Feature activation+0.000
digital
Token digital
Feature activation+0.000
copy
Token copy
Feature activation+0.000
of
Token of
Feature activation+0.000
Lock
Token Lock
Feature activation+0.000
down
Tokendown
Feature activation+1.318
to
Token to
Feature activation+0.000
pass
Token pass
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
in
Token in
Feature activation+0.000
generates
Token generates
Feature activation+0.000
oscill
Token oscill
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
in
Token in
Feature activation+0.000
mitochondrial
Token mitochondrial
Feature activation+0.000
energy
Token energy
Feature activation+1.351
capacity
Token capacity
Feature activation+0.000
through
Token through
Feature activation+0.000
rhyth
Token rhyth
Feature activation+0.000
mic
Tokenmic
Feature activation+0.000
regulation
Token regulation
Feature activation+0.000

INTERVAL 0.777 - 1.165
CONTAINS 0.066%

the
Token the
Feature activation+0.000
scientific
Token scientific
Feature activation+0.000
foundation
Token foundation
Feature activation+0.000
for
Token for
Feature activation+0.000
educational
Token educational
Feature activation+0.000
psychology
Token psychology
Feature activation+1.100
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
also
Token also
Feature activation+0.000
worked
Token worked
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
stronger
Token stronger
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+1.099
.
Token.
Feature activation+1.163
dollar
Token dollar
Feature activation+0.000
and
Token and
Feature activation+0.000
persistent
Token persistent
Feature activation+0.000
worries
Token worries
Feature activation+0.000
about
Token about
Feature activation+0.000
peer
Tokenpeer
Feature activation+0.000
platform
Token platform
Feature activation+0.000
-
Token -
Feature activation+0.000
has
Token has
Feature activation+0.000
made
Token made
Feature activation+0.000
household
Token household
Feature activation+0.819
names
Token names
Feature activation+0.000
of
Token of
Feature activation+0.000
Airbnb
Token Airbnb
Feature activation+0.000
and
Token and
Feature activation+0.000
Uber
Token Uber
Feature activation+0.000
(
Token (
Feature activation+0.000
ca
Tokenca
Feature activation+0.000
used
Tokenused
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
left
Token left
Feature activation+1.057
âĢĵ
TokenâĢĵ
Feature activation+0.000
right
Tokenright
Feature activation+0.000
asymm
Token asymm
Feature activation+0.000
etric
Tokenetric
Feature activation+0.000
expression
Token expression
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
act
Token act
Feature activation+0.000
of
Token of
Feature activation+0.000
offering
Token offering
Feature activation+0.976
ob
Token ob
Feature activation+0.000
lations
Tokenlations
Feature activation+0.000
to
Token to
Feature activation+0.000
prop
Token prop
Feature activation+0.000
iti
Tokeniti
Feature activation+0.000

INTERVAL 0.388 - 0.777
CONTAINS 0.118%

November
Token November
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
of
Token of
Feature activation+0.000
September
Token September
Feature activation+1.448
,
Token,
Feature activation+0.650
the
Token the
Feature activation+0.000
E
Token E
Feature activation+0.000
IA
TokenIA
Feature activation+0.000
all
Token all
Feature activation+0.000
liquids
Token liquids
Feature activation+0.000
work
Token work
Feature activation+0.000
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
dad
Token dad
Feature activation+0.486
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.094
hard
Token hard
Feature activation+0.000
earned
Token earned
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
administration
Token administration
Feature activation+0.000
now
Token now
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
galvan
Token galvan
Feature activation+0.438
ize
Tokenize
Feature activation+0.661
volunteers
Token volunteers
Feature activation+0.000
through
Token through
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
the
Token the
Feature activation+0.000
Sub
Token Sub
Feature activation+0.000
t
Tokent
Feature activation+0.000
ract
Tokenract
Feature activation+0.000
From
Token From
Feature activation+0.000
Shape
Token Shape
Feature activation+0.670
Area
Token Area
Feature activation+0.000
button
Token button
Feature activation+0.000
.
Token.
Feature activation+0.000
Obviously
Token Obviously
Feature activation+0.000
,
Token,
Feature activation+0.000
9
Token9
Feature activation+0.000
-
Token-
Feature activation+0.000
11
Token11
Feature activation+0.000
Pentagon
Token Pentagon
Feature activation+0.000
De
Token De
Feature activation+0.000
bris
Tokenbris
Feature activation+0.766
1
Token 1
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
It
Token It
Feature activation+0.000

INTERVAL 0.000 - 0.388
CONTAINS 99.691%

often
Token often
Feature activation+0.000
isn
Token isn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
glamorous
Token glamorous
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
isn
Token isn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
,
Token,
Feature activation+0.000
Judge
Token Judge
Feature activation+0.000
Jed
Token Jed
Feature activation+0.000
S
Token S
Feature activation+0.000
.
Token.
Feature activation+0.000
Rak
Token Rak
Feature activation+0.000
off
Tokenoff
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
7
Token 7
Feature activation+0.000
,
Token,
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
B
TokenB
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
mann
Tokenmann
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
POST
Token POST
Feature activation+0.000
request
Token request
Feature activation+0.000
will
Token will
Feature activation+0.000
never
Token never
Feature activation+0.000
receive
Token receive
Feature activation+0.000
a
Token a
Feature activation+0.000
cached
Token cached
Feature activation+0.000
response
Token response
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Last
TokenLast
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
little
Token little
Feature activation+0.000
fan
Token fan
Feature activation+0.000
fare
Tokenfare
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H5.5: (feature 35744)

TOP ACTIVATIONS
MAX = 4.185

aly
Tokenaly
Feature activation+0.000
day
Tokenday
Feature activation+0.000
e
Tokene
Feature activation+0.000
"
Token"
Feature activation+0.000
in
Token in
Feature activation+0.000
Grand
Token Grand
Feature activation+4.185
Rapids
Token Rapids
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
real
Token real
Feature activation+0.000
me
Tokenme
Feature activation+0.000
Civil
Token Civil
Feature activation+0.000
Rights
Token Rights
Feature activation+0.000
Project
Token Project
Feature activation+0.000
found
Token found
Feature activation+0.000
that
Token that
Feature activation+0.000
out
Token out
Feature activation+3.848
-
Token-
Feature activation+0.000
of
Tokenof
Feature activation+0.000
school
Token school
Feature activation+0.000
suspensions
Token suspensions
Feature activation+0.000
are
Token are
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
N
Token N
Feature activation+0.000
ader
Tokenader
Feature activation+3.802
memory
Token memory
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
one
Token one
Feature activation+0.000
standard
Token standard
Feature activation+0.000
elastic
Token elastic
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
corners
Token corners
Feature activation+0.000
,
Token,
Feature activation+0.000
convenience
Token convenience
Feature activation+3.776
sheets
Token sheets
Feature activation+0.000
will
Token will
Feature activation+0.000
cost
Token cost
Feature activation+0.000
you
Token you
Feature activation+0.000
at
Token at
Feature activation+0.000
this
Token this
Feature activation+0.000
situation
Token situation
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Stra
TokenStra
Feature activation+3.711
uss
Tokenuss
Feature activation+1.835
-
Token-
Feature activation+0.122
K
TokenK
Feature activation+0.000
ahn
Tokenahn
Feature activation+0.000
repeatedly
Token repeatedly
Feature activation+0.000
the
Token the
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mc
TokenMc
Feature activation+3.633
K
TokenK
Feature activation+2.550
enzie
Tokenenzie
Feature activation+2.149
-
Token-
Feature activation+0.000
G
TokenG
Feature activation+0.000
ude
Tokenude
Feature activation+0.000
een
Tokeneen
Feature activation+0.000
an
Tokenan
Feature activation+0.000
Beng
Token Beng
Feature activation+0.000
ts
Tokents
Feature activation+0.000
says
Token says
Feature activation+0.000
access
Token access
Feature activation+3.412
-
Token-
Feature activation+0.117
to
Tokento
Feature activation+0.000
-
Token-
Feature activation+0.000
information
Tokeninformation
Feature activation+0.000
laws
Token laws
Feature activation+0.000
ended
Token ended
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
2
Token 2
Feature activation+0.000
-
Token-
Feature activation+0.000
2
Token2
Feature activation+3.400
draw
Token draw
Feature activation+0.000
--
Token --
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
have
Token have
Feature activation+0.000
Pul
Token Pul
Feature activation+0.000
au
Tokenau
Feature activation+0.000
-
Token-
Feature activation+0.000
p
Tokenp
Feature activation+0.000
ul
Tokenul
Feature activation+0.000
au
Tokenau
Feature activation+3.386
B
Token B
Feature activation+0.000
omp
Tokenomp
Feature activation+0.000
a
Tokena
Feature activation+0.000
situated
Token situated
Feature activation+0.000
in
Token in
Feature activation+0.000
ON
TokenON
Feature activation+0.000
J
Token J
Feature activation+0.000
ELL
TokenELL
Feature activation+0.000
Y
TokenY
Feature activation+0.000
F
TokenF
Feature activation+0.276
ISH
TokenISH
Feature activation+3.378
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Moon
TokenMoon
Feature activation+0.000
Jelly
Token Jelly
Feature activation+0.000
fish
Tokenfish
Feature activation+0.000
REM
Token REM
Feature activation+0.000
O
TokenO
Feature activation+0.000
VE
TokenVE
Feature activation+0.000
YOU
Token YOU
Feature activation+0.000
RS
TokenRS
Feature activation+0.000
ELF
TokenELF
Feature activation+3.367
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
community
Token community
Feature activation+0.000
's
Token's
Feature activation+0.000
page
Token page
Feature activation+0.000
build
Tokenbuild
Feature activation+0.000
to
Token to
Feature activation+0.000
build
Token build
Feature activation+0.000
the
Token the
Feature activation+0.000
logging
Token logging
Feature activation+0.000
sub
Token sub
Feature activation+3.289
-
Token-
Feature activation+0.000
project
Tokenproject
Feature activation+0.000
,
Token,
Feature activation+0.000
within
Token within
Feature activation+0.000
the
Token the
Feature activation+0.000
1
Token 1
Feature activation+0.000
of
Token of
Feature activation+0.000
2
Token 2
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Low
TokenLow
Feature activation+3.283
-
Token-
Feature activation+0.000
Poly
TokenPoly
Feature activation+0.000
Mod
Token Mod
Feature activation+0.000
elling
Tokenelling
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
global
Token global
Feature activation+0.000
system
Token system
Feature activation+0.000
....
Token....
Feature activation+0.000
Stra
TokenStra
Feature activation+3.259
uss
Tokenuss
Feature activation+2.434
-
Token-
Feature activation+0.008
K
TokenK
Feature activation+0.000
ahn
Tokenahn
Feature activation+0.000
saw
Token saw
Feature activation+0.000
at
Tokenat
Feature activation+0.000
-
Token-
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
el
Tokenel
Feature activation+0.000
,
Token,
Feature activation+0.000
down
Token down
Feature activation+3.246
-
Token-
Feature activation+0.153
on
Tokenon
Feature activation+0.000
-
Token-
Feature activation+0.000
its
Tokenits
Feature activation+0.000
luck
Token luck
Feature activation+0.000
invoking
Token invoking
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Stra
TokenStra
Feature activation+3.202
uss
Tokenuss
Feature activation+1.830
-
Token-
Feature activation+0.000
K
TokenK
Feature activation+0.000
ahn
Tokenahn
Feature activation+0.000
told
Token told
Feature activation+0.000
12
Token12
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
optional
Token optional
Feature activation+0.000
CL
Token CL
Feature activation+3.198
-
Token-
Feature activation+0.000
12
Token12
Feature activation+0.000
linear
Token linear
Feature activation+0.000
f
Token f
Feature activation+0.000
ader
Tokenader
Feature activation+0.000
ESS
TokenESS
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Real
TokenReal
Feature activation+0.000
istic
Tokenistic
Feature activation+0.000
self
Token self
Feature activation+3.189
-
Token-
Feature activation+1.019
confidence
Tokenconfidence
Feature activation+0.000
:
Token:
Feature activation+0.000
You
Token You
Feature activation+0.000
understand
Token understand
Feature activation+0.000
flip
Token flip
Feature activation+0.000
side
Tokenside
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+3.100
couple
Token couple
Feature activation+0.000
of
Token of
Feature activation+0.000
days
Token days
Feature activation+0.000
later
Token later
Feature activation+0.000
George
Token George
Feature activation+0.000
FC
TokenFC
Feature activation+0.000
's
Token's
Feature activation+0.000
thrilling
Token thrilling
Feature activation+0.000
4
Token 4
Feature activation+0.000
-
Token-
Feature activation+0.000
4
Token4
Feature activation+3.089
draw
Token draw
Feature activation+0.000
with
Token with
Feature activation+0.000
Toronto
Token Toronto
Feature activation+0.000
FC
Token FC
Feature activation+0.000
due
Token due
Feature activation+0.000

Top DFA by src position
MAX = 4.120

me
Tokenme
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
visit
Token visit
Feature activation+0.001
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
grand
Token grand
Feature activation+0.005
Top resid features:
-
Token-
Feature activation+3.416
Top resid features:
d
Tokend
Feature activation+0.932
Top resid features:
ame
Tokename
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
The
Token The
Feature activation+0.001
Top resid features:
re
Token re
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
high
Token high
Feature activation+0.008
Top resid features:
correlation
Token correlation
Feature activation+0.010
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
out
Token out
Feature activation+0.002
Top resid features:
-
Token-
Feature activation+3.294
Top resid features:
of
Tokenof
Feature activation+0.570
Top resid features:
-
Token-
Feature activation+0.165
Top resid features:
school
Tokenschool
Feature activation+0.008
Top resid features:
suspensions
Token suspensions
Feature activation+0.012
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
be
Token be
Feature activation-0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
Ralph
Token Ralph
Feature activation+0.015
Top resid features:
N
Token N
Feature activation+0.022
Top resid features:
ader
Tokenader
Feature activation-0.008
Top resid features:
-
Token-
Feature activation+3.826
Top resid features:
type
Tokentype
Feature activation+0.317
Top resid features:
person
Token person
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
It
Token It
Feature activation-0.001
Top resid features:
should
Token should
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Con
TokenCon
Feature activation-0.000
Top resid features:
ven
Tokenven
Feature activation+0.000
Top resid features:
ience
Tokenience
Feature activation-0.004
Top resid features:
-
Token-
Feature activation+3.830
Top resid features:
Feature
TokenFeature
Feature activation+0.094
Top resid features:
She
Token She
Feature activation+0.005
Top resid features:
ets
Tokenets
Feature activation+0.013
Top resid features:
:
Token:
Feature activation+0.031
Top resid features:
Character
Token Character
Feature activation+0.006
Top resid features:
IMF
Token IMF
Feature activation+0.028
Top resid features:
has
Token has
Feature activation+0.004
Top resid features:
said
Token said
Feature activation-0.001
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
Strauss
Token Strauss
Feature activation-0.120
Top resid features:
-
Token-
Feature activation+3.422
Top resid features:
K
TokenK
Feature activation+0.537
Top resid features:
ahn
Tokenahn
Feature activation+0.073
Top resid features:
would
Token would
Feature activation-0.001
Top resid features:
have
Token have
Feature activation-0.000
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
anything
Token anything
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
they
Token they
Feature activation-0.000
Top resid features:
think
Token think
Feature activation+0.000
Top resid features:
McKenzie
Token McKenzie
Feature activation+0.011
Top resid features:
-
Token-
Feature activation+3.452
Top resid features:
G
TokenG
Feature activation+0.412
Top resid features:
ude
Tokenude
Feature activation+0.010
Top resid features:
planned
Token planned
Feature activation-0.011
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
do
Token do
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
same
Token same
Feature activation+0.001
Top resid features:
privacy
Token privacy
Feature activation+0.041
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
access
Token access
Feature activation-0.025
Top resid features:
-
Token-
Feature activation+3.231
Top resid features:
to
Tokento
Feature activation+0.263
Top resid features:
-
Token-
Feature activation+0.130
Top resid features:
information
Tokeninformation
Feature activation-0.065
Top resid features:
rules
Token rules
Feature activation+0.024
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.012
Top resid features:
ended
Token ended
Feature activation-0.003
Top resid features:
in
Token in
Feature activation+0.014
Top resid features:
a
Token a
Feature activation-0.009
Top resid features:
2
Token 2
Feature activation-0.235
Top resid features:
-
Token-
Feature activation+4.120
Top resid features:
2
Token2
Feature activation-0.084
Top resid features:
draw
Token draw
Feature activation+0.000
Top resid features:
--
Token --
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
US
Token US
Feature activation+0.000
Top resid features:
volcanic
Token volcanic
Feature activation-0.003
Top resid features:
island
Token island
Feature activation-0.008
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
Pul
Token Pul
Feature activation-0.002
Top resid features:
au
Tokenau
Feature activation-0.003
Top resid features:
-
Token-
Feature activation+3.781
Top resid features:
p
Tokenp
Feature activation+0.036
Top resid features:
ul
Tokenul
Feature activation-0.057
Top resid features:
au
Tokenau
Feature activation-0.015
Top resid features:
B
Token B
Feature activation+0.000
Top resid features:
omp
Tokenomp
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.008
Top resid features:
Moon
TokenMoon
Feature activation+0.017
Top resid features:
Jelly
Token Jelly
Feature activation+0.045
Top resid features:
fish
Tokenfish
Feature activation-0.002
Top resid features:
-
Token-
Feature activation+3.516
Top resid features:
F
TokenF
Feature activation+0.084
Top resid features:
acts
Tokenacts
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
Photograph
Token Photograph
Feature activation+0.001
Top resid features:
s
Tokens
Feature activation+0.006
Top resid features:
:
Token:
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
S
TokenS
Feature activation-0.004
Top resid features:
ELF
TokenELF
Feature activation-0.002
Top resid features:
-
Token-
Feature activation+3.152
Top resid features:
SER
TokenSER
Feature activation+0.445
Top resid features:
VICE
TokenVICE
Feature activation+0.011
Top resid features:
REM
Token REM
Feature activation+0.014
Top resid features:
O
TokenO
Feature activation+0.001
Top resid features:
VE
TokenVE
Feature activation-0.017
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
simply
Token simply
Feature activation+0.000
Top resid features:
use
Token use
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
sub
Token sub
Feature activation+0.002
Top resid features:
-
Token-
Feature activation+2.398
Top resid features:
project
Tokenproject
Feature activation-0.006
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
path
Token path
Feature activation-0.001
Top resid features:
detail
Token detail
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Low
TokenLow
Feature activation+0.010
Top resid features:
-
Token-
Feature activation+3.189
Top resid features:
Poly
TokenPoly
Feature activation+0.146
Top resid features:
Mod
Token Mod
Feature activation+0.020
Top resid features:
elling
Tokenelling
Feature activation+0.013
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.033
Top resid features:
Making
Token Making
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
"
Token"
Feature activation+0.001
Top resid features:
Domin
TokenDomin
Feature activation+0.003
Top resid features:
ique
Tokenique
Feature activation+0.001
Top resid features:
Strauss
Token Strauss
Feature activation-0.058
Top resid features:
-
Token-
Feature activation+3.098
Top resid features:
K
TokenK
Feature activation+0.415
Top resid features:
ahn
Tokenahn
Feature activation+0.020
Top resid features:
,
Token,
Feature activation+0.056
Top resid features:
managing
Token managing
Feature activation-0.021
Top resid features:
director
Token director
Feature activation+0.001
Top resid features:
ians
Tokenians
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
A
Token A
Feature activation-0.021
Top resid features:
once
Token once
Feature activation+0.001
Top resid features:
down
Token down
Feature activation-0.001
Top resid features:
âĢij
TokenâĢij
Feature activation+3.210
Top resid features:
at
Tokenat
Feature activation+0.288
Top resid features:
-
Token-
Feature activation+0.033
Top resid features:
he
Tokenhe
Feature activation+0.018
Top resid features:
el
Tokenel
Feature activation-0.026
Top resid features:
,
Token,
Feature activation+0.104
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
Domin
Token Domin
Feature activation-0.002
Top resid features:
ique
Tokenique
Feature activation+0.002
Top resid features:
Strauss
Token Strauss
Feature activation-0.075
Top resid features:
-
Token-
Feature activation+2.878
Top resid features:
K
TokenK
Feature activation+0.596
Top resid features:
ahn
Tokenahn
Feature activation+0.032
Top resid features:
case
Token case
Feature activation-0.021
Top resid features:
reveals
Token reveals
Feature activation-0.001
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.011
Top resid features:
CL
TokenCL
Feature activation-0.002
Top resid features:
-
Token-
Feature activation+3.361
Top resid features:
12
Token12
Feature activation+0.153
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
The
TokenThe
Feature activation+0.012
Top resid features:
optional
Token optional
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
1
Token1
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
S
Token S
Feature activation+0.003
Top resid features:
ELF
TokenELF
Feature activation+0.005
Top resid features:
-
Token-
Feature activation+2.885
Top resid features:
AW
TokenAW
Feature activation+0.466
Top resid features:
AR
TokenAR
Feature activation+0.002
Top resid features:
EN
TokenEN
Feature activation+0.001
Top resid features:
ESS
TokenESS
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
customary
Token customary
Feature activation+0.004
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
couple
Token couple
Feature activation-0.001
Top resid features:
an
Token an
Feature activation+0.001
Top resid features:
A
Token A
Feature activation-0.003
Top resid features:
-
Token-
Feature activation+3.113
Top resid features:
side
Tokenside
Feature activation+0.256
Top resid features:
with
Token with
Feature activation-0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
never
Token never
Feature activation+0.003
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
NYC
Token NYC
Feature activation+0.005
Top resid features:
FC
TokenFC
Feature activation-0.005
Top resid features:
's
Token's
Feature activation+0.003
Top resid features:
thrilling
Token thrilling
Feature activation-0.018
Top resid features:
4
Token 4
Feature activation-0.220
Top resid features:
-
Token-
Feature activation+3.818
Top resid features:
4
Token4
Feature activation-0.111
Top resid features:
draw
Token draw
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
Toronto
Token Toronto
Feature activation+0.000
Top resid features:
FC
Token FC
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.05

Head 2: 0.03

Head 3: 0.02

Head 4: 0.02

Head 5: 0.58

Head 6: 0.02

Head 7: 0.02

Head 8: 0.08

Head 9: 0.07

Head 10: 0.04

Head 11: 0.03

Positive logits

-2.33

1.93

-(1.78

-'1.74

-$1.72

\-1.71

-"1.69

-)1.59

-.1.56

.-1.55

\\1.52

-|1.49

Courier1.49

±1.49

-[1.45

ْ1.40

_-1.40

%-1.38

'-1.38

-,1.37

Negative logits

oko-1.59

onom-1.53

milo-1.47

urations-1.44

ania-1.43

tten-1.42

ok-1.42

olia-1.38

OK-1.35

assetsadobe-1.35

onomy-1.28

-1.28

istle-1.27

Tina-1.26

Shutterstock-1.26

saf-1.25

mble-1.25

chen-1.25

luck-1.25

Sik-1.25

INTERVAL 3.766 - 4.185
CONTAINS 0.000%

Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
N
Token N
Feature activation+0.000
ader
Tokenader
Feature activation+3.802
memory
Token memory
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
one
Token one
Feature activation+0.000
standard
Token standard
Feature activation+0.000
elastic
Token elastic
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
corners
Token corners
Feature activation+0.000
,
Token,
Feature activation+0.000
convenience
Token convenience
Feature activation+3.776
sheets
Token sheets
Feature activation+0.000
will
Token will
Feature activation+0.000
cost
Token cost
Feature activation+0.000
you
Token you
Feature activation+0.000
at
Token at
Feature activation+0.000
Civil
Token Civil
Feature activation+0.000
Rights
Token Rights
Feature activation+0.000
Project
Token Project
Feature activation+0.000
found
Token found
Feature activation+0.000
that
Token that
Feature activation+0.000
out
Token out
Feature activation+3.848
-
Token-
Feature activation+0.000
of
Tokenof
Feature activation+0.000
school
Token school
Feature activation+0.000
suspensions
Token suspensions
Feature activation+0.000
are
Token are
Feature activation+0.000
aly
Tokenaly
Feature activation+0.000
day
Tokenday
Feature activation+0.000
e
Tokene
Feature activation+0.000
"
Token"
Feature activation+0.000
in
Token in
Feature activation+0.000
Grand
Token Grand
Feature activation+4.185
Rapids
Token Rapids
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
real
Token real
Feature activation+0.000
me
Tokenme
Feature activation+0.000

INTERVAL 3.348 - 3.766
CONTAINS 0.001%

REM
Token REM
Feature activation+0.000
O
TokenO
Feature activation+0.000
VE
TokenVE
Feature activation+0.000
YOU
Token YOU
Feature activation+0.000
RS
TokenRS
Feature activation+0.000
ELF
TokenELF
Feature activation+3.367
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
community
Token community
Feature activation+0.000
's
Token's
Feature activation+0.000
page
Token page
Feature activation+0.000
ON
TokenON
Feature activation+0.000
J
Token J
Feature activation+0.000
ELL
TokenELL
Feature activation+0.000
Y
TokenY
Feature activation+0.000
F
TokenF
Feature activation+0.276
ISH
TokenISH
Feature activation+3.378
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Moon
TokenMoon
Feature activation+0.000
Jelly
Token Jelly
Feature activation+0.000
fish
Tokenfish
Feature activation+0.000
the
Token the
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mc
TokenMc
Feature activation+3.633
K
TokenK
Feature activation+2.550
enzie
Tokenenzie
Feature activation+2.149
-
Token-
Feature activation+0.000
G
TokenG
Feature activation+0.000
ude
Tokenude
Feature activation+0.000
ended
Token ended
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
2
Token 2
Feature activation+0.000
-
Token-
Feature activation+0.000
2
Token2
Feature activation+3.400
draw
Token draw
Feature activation+0.000
--
Token --
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
have
Token have
Feature activation+0.000
this
Token this
Feature activation+0.000
situation
Token situation
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Stra
TokenStra
Feature activation+3.711
uss
Tokenuss
Feature activation+1.835
-
Token-
Feature activation+0.122
K
TokenK
Feature activation+0.000
ahn
Tokenahn
Feature activation+0.000
repeatedly
Token repeatedly
Feature activation+0.000

INTERVAL 2.929 - 3.348
CONTAINS 0.002%

1
Token 1
Feature activation+0.000
of
Token of
Feature activation+0.000
2
Token 2
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Low
TokenLow
Feature activation+3.283
-
Token-
Feature activation+0.000
Poly
TokenPoly
Feature activation+0.000
Mod
Token Mod
Feature activation+0.000
elling
Tokenelling
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
ESS
TokenESS
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Real
TokenReal
Feature activation+0.000
istic
Tokenistic
Feature activation+0.000
self
Token self
Feature activation+3.189
-
Token-
Feature activation+1.019
confidence
Tokenconfidence
Feature activation+0.000
:
Token:
Feature activation+0.000
You
Token You
Feature activation+0.000
understand
Token understand
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
global
Token global
Feature activation+0.000
system
Token system
Feature activation+0.000
....
Token....
Feature activation+0.000
Stra
TokenStra
Feature activation+3.259
uss
Tokenuss
Feature activation+2.434
-
Token-
Feature activation+0.008
K
TokenK
Feature activation+0.000
ahn
Tokenahn
Feature activation+0.000
saw
Token saw
Feature activation+0.000
12
Token12
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
optional
Token optional
Feature activation+0.000
CL
Token CL
Feature activation+3.198
-
Token-
Feature activation+0.000
12
Token12
Feature activation+0.000
linear
Token linear
Feature activation+0.000
f
Token f
Feature activation+0.000
ader
Tokenader
Feature activation+0.000
EC
TokenEC
Feature activation+0.000
CS
TokenCS
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
even
Token even
Feature activation+0.000
negative
Token negative
Feature activation+3.071
-
Token-
Feature activation+0.810
em
Tokenem
Feature activation+0.000
ission
Tokenission
Feature activation+0.000
technologies
Token technologies
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.511 - 2.929
CONTAINS 0.004%

shipping
Token shipping
Feature activation+0.000
:
Token :
Feature activation+0.000
u
Token u
Feature activation+0.000
k
Tokenk
Feature activation+1.142
-
Token-
Feature activation+0.000
per
Tokenper
Feature activation+2.804
-
Token-
Feature activation+0.000
item
Tokenitem
Feature activation+0.000
(
Token (
Feature activation+0.000
item
Token item
Feature activation+0.000
-
Token-
Feature activation+0.000
,
Token,
Feature activation+0.000
giving
Token giving
Feature activation+0.000
his
Token his
Feature activation+0.000
party
Token party
Feature activation+0.000
a
Token a
Feature activation+0.000
3
Token 3
Feature activation+2.612
-
Token-
Feature activation+0.000
2
Token2
Feature activation+0.000
majority
Token majority
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
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
Their
TokenTheir
Feature activation+0.000
micro
Token micro
Feature activation+2.692
-
Token-
Feature activation+0.310
mir
Tokenmir
Feature activation+0.000
ror
Tokenror
Feature activation+0.000
array
Token array
Feature activation+0.000
can
Token can
Feature activation+0.000
talks
Token talks
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Reb
TokenReb
Feature activation+0.329
els
Tokenels
Feature activation+2.617
participating
Token participating
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Ast
Token Ast
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
zero
Token zero
Feature activation+0.000
-
Token-
Feature activation+0.000
gravity
Tokengravity
Feature activation+0.000
experience
Token experience
Feature activation+0.000
and
Token and
Feature activation+0.000
out
Token out
Feature activation+2.904
-
Token-
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
-
Token-
Feature activation+0.000
window
Tokenwindow
Feature activation+0.000
views
Token views
Feature activation+0.000

INTERVAL 2.092 - 2.511
CONTAINS 0.005%

.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
example
Token example
Feature activation+0.000
when
Token when
Feature activation+0.000
one
Token one
Feature activation+0.000
zero
Token zero
Feature activation+2.332
-
Token-
Feature activation+0.000
day
Tokenday
Feature activation+0.000
vulnerability
Token vulnerability
Feature activation+0.000
gets
Token gets
Feature activation+0.000
patched
Token patched
Feature activation+0.000
v
Token v
Feature activation+0.000
ox
Tokenox
Feature activation+0.000
-
Token-
Feature activation+0.000
mark
Tokenmark
Feature activation+0.000
v
Token v
Feature activation+0.000
ox
Tokenox
Feature activation+2.198
-
Token-
Feature activation+0.000
mark
Tokenmark
Feature activation+0.000
v
Token v
Feature activation+0.000
ox
Tokenox
Feature activation+1.047
-
Token-
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
suit
Token suit
Feature activation+0.000
received
Token received
Feature activation+0.000
class
Token class
Feature activation+2.170
-
Token-
Feature activation+0.000
action
Tokenaction
Feature activation+0.000
status
Token status
Feature activation+0.000
in
Token in
Feature activation+0.000
March
Token March
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
simply
Token simply
Feature activation+0.000
use
Token use
Feature activation+0.000
a
Token a
Feature activation+0.000
sub
Token sub
Feature activation+2.292
-
Token-
Feature activation+0.000
project
Tokenproject
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
-
Token-
Feature activation+0.000
general
Tokengeneral
Feature activation+0.000
spells
Token spells
Feature activation+0.000
with
Token with
Feature activation+0.000
their
Token their
Feature activation+0.000
non
Token non
Feature activation+2.189
-
Token-
Feature activation+0.280
linear
Tokenlinear
Feature activation+0.000
progression
Token progression
Feature activation+0.000
of
Token of
Feature activation+0.000
power
Token power
Feature activation+0.000

INTERVAL 1.674 - 2.092
CONTAINS 0.009%

.
Token.
Feature activation+0.000
if
Token if
Feature activation+0.000
your
Token your
Feature activation+0.000
Volunteer
Token Volunteer
Feature activation+0.000
association
Token association
Feature activation+0.000
can
Token can
Feature activation+1.800
-
Token-
Feature activation+0.000
please
Tokenplease
Feature activation+0.000
donate
Token donate
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
him
Token him
Feature activation+0.000
in
Token in
Feature activation+0.000
private
Token private
Feature activation+0.000
.
Token.
Feature activation+0.000
Because
Token Because
Feature activation+0.000
13
Token 13
Feature activation+1.888
-
Token-
Feature activation+0.042
year
Tokenyear
Feature activation+0.782
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
children
Token children
Feature activation+0.000
organized
Token organized
Feature activation+0.000
labor
Token labor
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
advocating
Token advocating
Feature activation+0.000
worker
Token worker
Feature activation+1.794
control
Token control
Feature activation+0.000
and
Token and
Feature activation+0.000
anarchist
Token anarchist
Feature activation+0.333
organizing
Token organizing
Feature activation+0.000
to
Token to
Feature activation+0.000
and
Token and
Feature activation+0.000
another
Token another
Feature activation+0.000
one
Token one
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
long
Token long
Feature activation+1.762
-
Token-
Feature activation+0.315
range
Tokenrange
Feature activation+0.000
kicks
Token kicks
Feature activation+0.000
,
Token,
Feature activation+0.000
before
Token before
Feature activation+0.000
final
Token final
Feature activation+0.000
two
Token two
Feature activation+0.000
games
Token games
Feature activation+0.000
to
Token to
Feature activation+0.000
finish
Token finish
Feature activation+0.000
9
Token 9
Feature activation+1.754
-
Token-
Feature activation+0.000
7
Token7
Feature activation+0.000
and
Token and
Feature activation+0.000
tie
Token tie
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 1.255 - 1.674
CONTAINS 0.012%

II
Token II
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
between
Token between
Feature activation+0.000
Catholicism
Token Catholicism
Feature activation+1.399
and
Token and
Feature activation+0.000
what
Token what
Feature activation+0.000
Pope
Token Pope
Feature activation+0.000
John
Token John
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
this
Token this
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
holiday
Token holiday
Feature activation+0.000
giving
Token giving
Feature activation+1.381
spirit
Token spirit
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
trick
Token trick
Feature activation+0.000
here
Token here
Feature activation+0.000
If
TokenIf
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
with
Token with
Feature activation+0.000
bipolar
Token bipolar
Feature activation+1.566
disorder
Token disorder
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
covers
Token covers
Feature activation+0.000
of
Token of
Feature activation+0.000
two
Token two
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
7
Token 7
Feature activation+1.444
âĢ³
TokenâĢ³
Feature activation+0.000
Club
Token Club
Feature activation+0.000
releases
Token releases
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Vikings
Token Vikings
Feature activation+0.000
in
Token in
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
one
Token one
Feature activation+1.610
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
deal
Token deal
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000

INTERVAL 0.837 - 1.255
CONTAINS 0.019%

Prin
TokenPrin
Feature activation+0.000
cess
Tokencess
Feature activation+0.000
Mak
Token Mak
Feature activation+0.000
o
Tokeno
Feature activation+0.000
,
Token,
Feature activation+0.000
25
Token 25
Feature activation+1.027
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
eldest
Token eldest
Feature activation+0.000
child
Token child
Feature activation+0.000
_
Token_
Feature activation+0.000
ptr
Tokenptr
Feature activation+0.000
<
Token <
Feature activation+0.000
boost
Tokenboost
Feature activation+0.000
/
Token/
Feature activation+0.000
weak
Tokenweak
Feature activation+0.980
_
Token_
Feature activation+0.000
ptr
Tokenptr
Feature activation+0.000
.
Token.
Feature activation+0.000
h
Tokenh
Feature activation+0.000
pp
Tokenpp
Feature activation+0.000
Lanka
Token Lanka
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
the
Token the
Feature activation+0.000
West
Token West
Feature activation+1.167
Indies
Token Indies
Feature activation+0.000
,
Token,
Feature activation+0.000
are
Token are
Feature activation+0.000
taking
Token taking
Feature activation+0.000
part
Token part
Feature activation+0.000
manage
Token manage
Feature activation+0.000
your
Token your
Feature activation+0.000
form
Token form
Feature activation+0.000
state
Token state
Feature activation+0.000
in
Token in
Feature activation+0.000
Redux
Token Redux
Feature activation+1.237
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
provides
Token provides
Feature activation+0.000
a
Token a
Feature activation+0.000
higher
Token higher
Feature activation+0.000
-
Token-
Feature activation+0.000
way
Tokenway
Feature activation+0.000
opening
Token opening
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Canadian
Token Canadian
Feature activation+1.010
auto
Token auto
Feature activation+0.000
market
Token market
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000

INTERVAL 0.418 - 0.837
CONTAINS 0.034%

w
Tokenw
Feature activation+0.000
alls
Tokenalls
Feature activation+0.000
(
Token (
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Fire
TokenFire
Feature activation+0.532
wall
Tokenwall
Feature activation+0.000
Operations
Token Operations
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
)
Token)
Feature activation+0.000
-
Token-
Feature activation+0.000
called
Tokencalled
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
morning
Tokenmorning
Feature activation+0.000
-
Token-
Feature activation+0.577
after
Tokenafter
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
pills
Token pills
Feature activation+0.000
,
Token,
Feature activation+0.000
containers
Token containers
Feature activation+0.000
are
Token are
Feature activation+0.000
a
Token a
Feature activation+0.000
no
Token no
Feature activation+0.000
-
Token-
Feature activation+0.000
no
Tokenno
Feature activation+0.564
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
4
Token4
Feature activation+0.000
.
Token.
Feature activation+0.000
over
Token over
Feature activation+0.000
Gaza
Token Gaza
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Democrats
TokenDemocrats
Feature activation+0.575
,
Token,
Feature activation+0.000
when
Token when
Feature activation+0.000
asked
Token asked
Feature activation+0.000
a
Token a
Feature activation+0.000
question
Token question
Feature activation+0.000
and
Token and
Feature activation+0.000
checkpoints
Token checkpoints
Feature activation+0.000
that
Token that
Feature activation+0.000
ring
Token ring
Feature activation+0.000
the
Token the
Feature activation+0.000
Palestinian
Token Palestinian
Feature activation+0.481
town
Token town
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
However
TokenHowever
Feature activation+0.000

INTERVAL 0.000 - 0.418
CONTAINS 99.914%

the
Token the
Feature activation+0.000
string
Token string
Feature activation+0.000
for
Token for
Feature activation+0.000
.
Token .
Feature activation+0.000
per
Tokenper
Feature activation+0.000
l
Tokenl
Feature activation+0.000
,
Token ,
Feature activation+0.000
but
Token but
Feature activation+0.000
also
Token also
Feature activation+0.000
slightly
Token slightly
Feature activation+0.000
different
Token different
Feature activation+0.000
left
Token left
Feature activation+0.000
in
Token in
Feature activation+0.000
no
Token no
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
All
Token All
Feature activation+0.000
i
Tokeni
Feature activation+0.000
was
Token was
Feature activation+0.000
destined
Token destined
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
consult
Token consult
Feature activation+0.000
with
Token with
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
Jewish
Token Jewish
Feature activation+0.000
organizations
Token organizations
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
year
Token year
Feature activation+0.000
following
Token following
Feature activation+0.000
the
Token the
Feature activation+0.000
launch
Token launch
Feature activation+0.000
of
Token of
Feature activation+0.000
academia
Token academia
Feature activation+0.000
with
Token with
Feature activation+0.000
some
Token some
Feature activation+0.000
frequency
Token frequency
Feature activation+0.000
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
measuring
Token measuring
Feature activation+0.000
the
Token the
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
the
Token the
Feature activation+0.000
Green
Token Green
Feature activation+0.000
Party
Token Party
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Jill
Token Jill
Feature activation+0.000
Stein
Token Stein
Feature activation+0.000
has
Token has
Feature activation+0.000
3
Token 3
Feature activation+0.000
percent
Token percent
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 H5.5: (feature 40519)

TOP ACTIVATIONS
MAX = 3.865

Ċ
TokenĊ
Feature activation+0.000
Story
TokenStory
Feature activation+0.000
continues
Token continues
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dun
TokenDun
Feature activation+3.865
can
Tokencan
Feature activation+1.912
earned
Token earned
Feature activation+0.250
over
Token over
Feature activation+0.000
$
Token $
Feature activation+0.000
240
Token240
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
January
Token January
Feature activation+0.000
,
Token,
Feature activation+0.000
Raiders
Token Raiders
Feature activation+3.256
owner
Token owner
Feature activation+0.036
Mark
Token Mark
Feature activation+0.000
Davis
Token Davis
Feature activation+0.000
piv
Token piv
Feature activation+0.000
oted
Tokenoted
Feature activation+0.000
any
Token any
Feature activation+0.000
further
Token further
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
J
TokenJ
Feature activation+3.236
ared
Tokenared
Feature activation+0.000
Let
Token Let
Feature activation+0.000
o
Tokeno
Feature activation+0.000
has
Token has
Feature activation+0.485
been
Token been
Feature activation+0.418
t
Tokent
Feature activation+0.000
know
Token know
Feature activation+0.000
about
Token about
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
don
Token don
Feature activation+3.137
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
necessarily
Token necessarily
Feature activation+0.000
know
Token know
Feature activation+0.000
town
Token town
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.425
isn
Token isn
Feature activation+3.101
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
about
Token about
Feature activation+0.000
questioning
Token questioning
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
cocktails
Token cocktails
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
Nicholas
Token Nicholas
Feature activation+3.084
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
favorite
Token favorite
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
for
Token for
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.000
club
Token club
Feature activation+0.000
and
Token and
Feature activation+0.000
Stewart
Token Stewart
Feature activation+3.074
,
Token,
Feature activation+0.956
but
Token but
Feature activation+0.000
we
Token we
Feature activation+0.000
will
Token will
Feature activation+0.000
support
Token support
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
M
TokenM
Feature activation+0.000
eryl
Tokeneryl
Feature activation+0.000
Stre
Token Stre
Feature activation+0.000
ep
Tokenep
Feature activation+3.030
changes
Token changes
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
by
Token by
Feature activation+0.000
waking
Token waking
Feature activation+0.000
sticking
Token sticking
Feature activation+0.000
around
Token around
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Don
TokenDon
Feature activation+3.028
walked
Token walked
Feature activation+0.000
in
Token in
Feature activation+0.000
and
Token and
Feature activation+0.000
asked
Token asked
Feature activation+0.000
his
Token his
Feature activation+0.000
guard
Token guard
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
C
TokenC
Feature activation+2.242
incinnati
Tokenincinnati
Feature activation+3.013
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
attempt
Token attempt
Feature activation+0.000
to
Token to
Feature activation+0.000
war
Tokenwar
Feature activation+0.000
on
Token on
Feature activation+0.000
terror
Token terror
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Bush
Token Bush
Feature activation+3.006
had
Token had
Feature activation+0.541
launched
Token launched
Feature activation+0.000
in
Token in
Feature activation+0.000
2001
Token 2001
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Most
TokenMost
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
suspected
Token suspected
Feature activation+3.000
cases
Token cases
Feature activation+0.000
turn
Token turn
Feature activation+0.000
out
Token out
Feature activation+0.915
to
Token to
Feature activation+0.109
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.000
him
Token him
Feature activation+2.985
the
Token the
Feature activation+0.140
opportunity
Token opportunity
Feature activation+0.000
to
Token to
Feature activation+0.000
pursue
Token pursue
Feature activation+0.000
that
Token that
Feature activation+0.000
risk
Token risk
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sk
TokenSk
Feature activation+0.000
unk
Tokenunk
Feature activation+2.980
is
Token is
Feature activation+1.486
now
Token now
Feature activation+0.000
sold
Token sold
Feature activation+0.000
without
Token without
Feature activation+0.000
any
Token any
Feature activation+0.000
unity
Token unity
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
the
Token the
Feature activation+0.000
death
Token death
Feature activation+0.000
of
Token of
Feature activation+0.000
Martin
Token Martin
Feature activation+2.948
,
Token,
Feature activation+0.419
urging
Token urging
Feature activation+0.000
protesters
Token protesters
Feature activation+0.000
to
Token to
Feature activation+0.000
allow
Token allow
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
give
Token give
Feature activation+0.000
them
Token them
Feature activation+2.911
$
Token $
Feature activation+0.000
2
Token2
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
if
Token if
Feature activation+0.000
t
Tokent
Feature activation+0.000
drink
Token drink
Feature activation+0.000
so
Token so
Feature activation+0.000
much
Token much
Feature activation+0.000
or
Token or
Feature activation+0.000
don
Token don
Feature activation+2.893
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
wear
Token wear
Feature activation+0.000
short
Token short
Feature activation+0.000
GL
Token GL
Feature activation+0.000
A
TokenA
Feature activation+0.000
AD
TokenAD
Feature activation+0.000
gives
Token gives
Feature activation+0.000
Cly
Token Cly
Feature activation+0.000
burn
Tokenburn
Feature activation+2.890
a
Token a
Feature activation+0.352
real
Token real
Feature activation+0.000
run
Token run
Feature activation+0.000
for
Token for
Feature activation+0.000
her
Token her
Feature activation+0.028
state
Token state
Feature activation+0.539
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
simply
Token simply
Feature activation+0.000
a
Token a
Feature activation+0.000
myth
Token myth
Feature activation+2.876
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
such
Token such
Feature activation+0.000
made
Token made
Feature activation+0.000
this
Token this
Feature activation+0.000
thing
Token thing
Feature activation+0.000
happen
Token happen
Feature activation+0.000
.
Token.
Feature activation+0.000
Cory
Token Cory
Feature activation+2.861
has
Token has
Feature activation+0.207
been
Token been
Feature activation+0.041
tearing
Token tearing
Feature activation+0.000
it
Token it
Feature activation+0.000
up
Token up
Feature activation+0.000

Top DFA by src position
MAX = 3.982

that
Token that
Feature activation+0.001
Top resid features:
signature
Token signature
Feature activation+0.011
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
increase
Token increase
Feature activation+0.001
Top resid features:
Duncan
Token Duncan
Feature activation+0.077
Top resid features:
âĢ
TokenâĢ
Feature activation+3.982
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation+0.004
Top resid features:
guarantee
Token guarantee
Feature activation+0.012
Top resid features:
exposure
Token exposure
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.246
Top resid features:
."
Token."
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.036
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
Raiders
Token Raiders
Feature activation+0.028
Top resid features:
âĢ
TokenâĢ
Feature activation+3.393
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
long
Token long
Feature activation+0.005
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
disc
Tokendisc
Feature activation+0.001
Top resid features:
ussed
Tokenussed
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.199
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
Joker
Token Joker
Feature activation+0.122
Top resid features:
âĢ
TokenâĢ
Feature activation+3.518
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation+0.019
Top resid features:
involvement
Token involvement
Feature activation+0.012
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
Suicide
Token Suicide
Feature activation+0.026
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.169
Top resid features:
people
Token people
Feature activation+0.083
Top resid features:
don
Token don
Feature activation+0.009
Top resid features:
âĢ
TokenâĢ
Feature activation+3.782
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
t
Tokent
Feature activation-0.020
Top resid features:
know
Token know
Feature activation-0.061
Top resid features:
about
Token about
Feature activation-0.100
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Clearly
TokenClearly
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
this
Token this
Feature activation+0.009
Top resid features:
isn
Token isn
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+3.137
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
t
Tokent
Feature activation+0.020
Top resid features:
your
Token your
Feature activation-0.014
Top resid features:
normal
Token normal
Feature activation+0.008
Top resid features:
protocol
Token protocol
Feature activation+0.023
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.237
Top resid features:
Nicholas
Token Nicholas
Feature activation+0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+3.237
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
estate
Token estate
Feature activation+0.032
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
The
Token The
Feature activation-0.004
Top resid features:
billionaire
Token billionaire
Feature activation+0.047
Top resid features:
it
Token it
Feature activation+0.004
Top resid features:
will
Token will
Feature activation-0.000
Top resid features:
dramatically
Token dramatically
Feature activation+0.001
Top resid features:
improve
Token improve
Feature activation+0.000
Top resid features:
Stewart
Token Stewart
Feature activation+0.018
Top resid features:
âĢ
TokenâĢ
Feature activation+3.357
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
s
Tokens
Feature activation+0.032
Top resid features:
function
Token function
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
performance
Token performance
Feature activation-0.001
Top resid features:
celebrities
Token celebrities
Feature activation+0.042
Top resid features:
reacted
Token reacted
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
Stre
Token Stre
Feature activation+0.018
Top resid features:
ep
Tokenep
Feature activation+0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+2.132
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
s
Tokens
Feature activation+0.036
Top resid features:
acceptance
Token acceptance
Feature activation+0.049
Top resid features:
speech
Token speech
Feature activation+0.018
Top resid features:
at
Token at
Feature activation+0.021
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.168
Top resid features:
at
Token at
Feature activation+0.012
Top resid features:
Don
Token Don
Feature activation+0.012
Top resid features:
âĢ
TokenâĢ
Feature activation+3.386
Top resid features:
Ļ
TokenĻ
Feature activation+0.007
Top resid features:
s
Tokens
Feature activation+0.029
Top resid features:
house
Token house
Feature activation+0.011
Top resid features:
that
Token that
Feature activation+0.004
Top resid features:
night
Token night
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.279
Top resid features:
role
Token role
Feature activation+0.010
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
limiting
Token limiting
Feature activation+0.002
Top resid features:
Cincinnati
Token Cincinnati
Feature activation+0.011
Top resid features:
âĢ
TokenâĢ
Feature activation+2.586
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation+0.012
Top resid features:
run
Token run
Feature activation+0.009
Top resid features:
game
Token game
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
continuing
Token continuing
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
bulk
Token bulk
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Bush
Token Bush
Feature activation+0.009
Top resid features:
âĢ
TokenâĢ
Feature activation+3.227
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation+0.004
Top resid features:
approach
Token approach
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Indeed
Token Indeed
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.236
Top resid features:
pected
Tokenpected
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+3.410
Top resid features:
Ŀ
TokenĿ
Feature activation+0.001
Top resid features:
cases
Token cases
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+0.014
Top resid features:
Ebola
Token Ebola
Feature activation+0.074
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.248
Top resid features:
ľ
Tokenľ
Feature activation-0.005
Top resid features:
He
TokenHe
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+3.161
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
s
Tokens
Feature activation+0.022
Top resid features:
an
Token an
Feature activation-0.009
Top resid features:
Olympic
Token Olympic
Feature activation+0.014
Top resid features:
-
Token-
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.229
Top resid features:
âĢ
Token âĢ
Feature activation+0.001
Top resid features:
ľ
Tokenľ
Feature activation+0.002
Top resid features:
sk
Tokensk
Feature activation+0.004
Top resid features:
unk
Tokenunk
Feature activation+0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+3.195
Top resid features:
Ŀ
TokenĿ
Feature activation+0.001
Top resid features:
was
Token was
Feature activation+0.035
Top resid features:
a
Token a
Feature activation+0.037
Top resid features:
factor
Token factor
Feature activation+0.011
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.266
Top resid features:
Martin
Token Martin
Feature activation+0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+3.149
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation+0.037
Top resid features:
shooting
Token shooting
Feature activation+0.036
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
It
Token It
Feature activation+0.007
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.228
Top resid features:
they
Token they
Feature activation-0.017
Top resid features:
âĢ
TokenâĢ
Feature activation+3.493
Top resid features:
Ļ
TokenĻ
Feature activation-0.005
Top resid features:
d
Tokend
Feature activation-0.052
Top resid features:
give
Token give
Feature activation-0.001
Top resid features:
them
Token them
Feature activation+0.008
Top resid features:
$
Token $
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Suggest
TokenSuggest
Feature activation+0.020
Top resid features:
ing
Tokening
Feature activation+0.024
Top resid features:
women
Token women
Feature activation+0.028
Top resid features:
don
Token don
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+3.551
Top resid features:
Ļ
TokenĻ
Feature activation-0.008
Top resid features:
t
Tokent
Feature activation-0.020
Top resid features:
drink
Token drink
Feature activation-0.210
Top resid features:
so
Token so
Feature activation-0.010
Top resid features:
much
Token much
Feature activation+0.013
Top resid features:
M
Token M
Feature activation+0.007
Top resid features:
ign
Tokenign
Feature activation+0.001
Top resid features:
on
Tokenon
Feature activation+0.015
Top resid features:
Cly
Token Cly
Feature activation+0.043
Top resid features:
burn
Tokenburn
Feature activation-0.015
Top resid features:
âĢ
TokenâĢ
Feature activation+3.023
Top resid features:
Ļ
TokenĻ
Feature activation+0.009
Top resid features:
s
Tokens
Feature activation+0.013
Top resid features:
ridiculous
Token ridiculous
Feature activation-0.004
Top resid features:
assertion
Token assertion
Feature activation+0.002
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.244
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
myth
Token myth
Feature activation-0.008
Top resid features:
âĢ
TokenâĢ
Feature activation+3.035
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation+0.026
Top resid features:
danger
Token danger
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
For
Token For
Feature activation+0.001
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
b
Tokenb
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.047
Top resid features:
C
TokenC
Feature activation+0.003
Top resid features:
ory
Tokenory
Feature activation+0.011
Top resid features:
âĢ
TokenâĢ
Feature activation+3.096
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation+0.088
Top resid features:
been
Token been
Feature activation+0.001
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
my
Token my
Feature activation+0.013
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.07

Head 2: 0.02

Head 3: 0.03

Head 4: 0.02

Head 5: 0.57

Head 6: 0.02

Head 7: 0.01

Head 8: 0.06

Head 9: 0.08

Head 10: 0.06

Head 11: 0.02

Positive logits

sup1.94

Ur1.91

yu1.80

Nar1.78

Squ1.74

mobile1.72

Dar1.70

Dur1.70

Mania1.67

ukong1.65

Rod1.64

Root1.64

Sel1.61

Ear1.61

Tab1.61

enum1.60

Pod1.58

Us1.58

nda1.56

vim1.56

Negative logits

assetsadobe-2.35

stakes-1.64

ocratic-1.55

ote-1.54

ocation-1.48

lished-1.45

iaries-1.43

kW-1.42

atography-1.42

940-1.41

Kraken-1.40

atform-1.37

magnification-1.36

Cosmos-1.34

composite-1.33

iator-1.32

weather-1.32

metic-1.31

mandate-1.31

whipping-1.31

INTERVAL 3.479 - 3.865
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Story
TokenStory
Feature activation+0.000
continues
Token continues
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dun
TokenDun
Feature activation+3.865
can
Tokencan
Feature activation+1.912
earned
Token earned
Feature activation+0.250
over
Token over
Feature activation+0.000
$
Token $
Feature activation+0.000
240
Token240
Feature activation+0.000

INTERVAL 3.092 - 3.479
CONTAINS 0.000%

the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
January
Token January
Feature activation+0.000
,
Token,
Feature activation+0.000
Raiders
Token Raiders
Feature activation+3.256
owner
Token owner
Feature activation+0.036
Mark
Token Mark
Feature activation+0.000
Davis
Token Davis
Feature activation+0.000
piv
Token piv
Feature activation+0.000
oted
Tokenoted
Feature activation+0.000
t
Tokent
Feature activation+0.000
know
Token know
Feature activation+0.000
about
Token about
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
don
Token don
Feature activation+3.137
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
necessarily
Token necessarily
Feature activation+0.000
know
Token know
Feature activation+0.000
town
Token town
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.425
isn
Token isn
Feature activation+3.101
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
about
Token about
Feature activation+0.000
questioning
Token questioning
Feature activation+0.000
any
Token any
Feature activation+0.000
further
Token further
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
J
TokenJ
Feature activation+3.236
ared
Tokenared
Feature activation+0.000
Let
Token Let
Feature activation+0.000
o
Tokeno
Feature activation+0.000
has
Token has
Feature activation+0.485
been
Token been
Feature activation+0.418

INTERVAL 2.706 - 3.092
CONTAINS 0.003%

three
Token three
Feature activation+0.000
thousand
Token thousand
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Alex
TokenAlex
Feature activation+2.764
a
Tokena
Feature activation+2.017
still
Token still
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
unity
Token unity
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
the
Token the
Feature activation+0.000
death
Token death
Feature activation+0.000
of
Token of
Feature activation+0.000
Martin
Token Martin
Feature activation+2.948
,
Token,
Feature activation+0.419
urging
Token urging
Feature activation+0.000
protesters
Token protesters
Feature activation+0.000
to
Token to
Feature activation+0.000
allow
Token allow
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Most
TokenMost
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
suspected
Token suspected
Feature activation+3.000
cases
Token cases
Feature activation+0.000
turn
Token turn
Feature activation+0.000
out
Token out
Feature activation+0.915
to
Token to
Feature activation+0.109
be
Token be
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
told
Token told
Feature activation+0.000
us
Token us
Feature activation+0.000
that
Token that
Feature activation+0.000
Carey
Token Carey
Feature activation+2.725
is
Token is
Feature activation+1.114
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
several
Token several
Feature activation+0.000
celebrities
Token celebrities
Feature activation+0.000
made
Token made
Feature activation+0.000
this
Token this
Feature activation+0.000
thing
Token thing
Feature activation+0.000
happen
Token happen
Feature activation+0.000
.
Token.
Feature activation+0.000
Cory
Token Cory
Feature activation+2.861
has
Token has
Feature activation+0.207
been
Token been
Feature activation+0.041
tearing
Token tearing
Feature activation+0.000
it
Token it
Feature activation+0.000
up
Token up
Feature activation+0.000

INTERVAL 2.319 - 2.706
CONTAINS 0.006%

.
Token.
Feature activation+0.000
Ho
Token Ho
Feature activation+0.000
ek
Tokenek
Feature activation+0.000
stra
Tokenstra
Feature activation+0.000
accused
Token accused
Feature activation+0.000
CIA
Token CIA
Feature activation+2.626
director
Token director
Feature activation+0.366
Ten
Token Ten
Feature activation+0.000
et
Tokenet
Feature activation+0.000
with
Token with
Feature activation+0.000
misleading
Token misleading
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+0.000
issue
Token issue
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
timing
Token timing
Feature activation+2.340
of
Token of
Feature activation+0.255
the
Token the
Feature activation+0.000
vote
Token vote
Feature activation+0.000
itself
Token itself
Feature activation+0.000
,
Token,
Feature activation+0.000
punishment
Token punishment
Feature activation+0.000
seems
Token seems
Feature activation+0.000
awfully
Token awfully
Feature activation+0.000
bizarre
Token bizarre
Feature activation+0.000
.
Token.
Feature activation+0.000
Law
Token Law
Feature activation+2.482
did
Token did
Feature activation+0.085
not
Token not
Feature activation+0.000
seem
Token seem
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
sm
Token sm
Feature activation+0.000
og
Tokenog
Feature activation+0.000
of
Token of
Feature activation+0.000
L
Token L
Feature activation+0.000
.
Token.
Feature activation+0.000
A
TokenA
Feature activation+2.326
.
Token.
Feature activation+1.475
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
iconic
Token iconic
Feature activation+0.000
as
Token as
Feature activation+0.000
improved
Token improved
Feature activation+0.000
service
Token service
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
R
TokenR
Feature activation+2.371
ipple
Tokenipple
Feature activation+1.402
adds
Token adds
Feature activation+0.166
new
Token new
Feature activation+0.000
banks
Token banks
Feature activation+0.225
to
Token to
Feature activation+0.000

INTERVAL 1.933 - 2.319
CONTAINS 0.013%

On
Token On
Feature activation+0.000
health
Token health
Feature activation+0.000
care
Token care
Feature activation+0.000
,
Token,
Feature activation+0.000
Obama
Token Obama
Feature activation+1.180
is
Token is
Feature activation+1.984
seen
Token seen
Feature activation+0.000
as
Token as
Feature activation+0.000
having
Token having
Feature activation+0.000
strengthened
Token strengthened
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Or
TokenOr
Feature activation+0.000
ger
Tokenger
Feature activation+0.000
on
Tokenon
Feature activation+2.049
wasn
Token wasn
Feature activation+1.140
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
told
Token told
Feature activation+0.000
us
Token us
Feature activation+0.000
he
Token he
Feature activation+2.281
will
Token will
Feature activation+0.503
be
Token be
Feature activation+0.272
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
he
Token he
Feature activation+0.424
withdrawing
Token withdrawing
Feature activation+0.000
their
Token their
Feature activation+0.000
support
Token support
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Oculus
Token Oculus
Feature activation+2.124
platform
Token platform
Feature activation+0.000
as
Token as
Feature activation+0.000
long
Token long
Feature activation+0.000
as
Token as
Feature activation+0.000
Luc
Token Luc
Feature activation+0.000
when
Token when
Feature activation+0.000
Watson
Token Watson
Feature activation+0.632
-
Token-
Feature activation+0.000
W
TokenW
Feature activation+1.054
att
Tokenatt
Feature activation+1.821
was
Token was
Feature activation+2.067
in
Token in
Feature activation+0.000
his
Token his
Feature activation+0.000
60
Token 60
Feature activation+0.000
s
Tokens
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.546 - 1.933
CONTAINS 0.021%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
created
Token created
Feature activation+0.000
order
Token order
Feature activation+0.000
.
Token.
Feature activation+0.000
God
Token God
Feature activation+1.554
established
Token established
Feature activation+0.000
man
Token man
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
head
Token head
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
small
Token small
Feature activation+0.000
enough
Token enough
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+1.576
will
Token will
Feature activation+0.449
send
Token send
Feature activation+0.000
a
Token a
Feature activation+0.000
message
Token message
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hardware
TokenHardware
Feature activation+0.000
wise
Token wise
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.971
isn
Token isn
Feature activation+1.819
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.170
as
Token as
Feature activation+0.000
much
Token much
Feature activation+0.000
Iranian
Token Iranian
Feature activation+0.000
"
Token "
Feature activation+0.000
corruption
Tokencorruption
Feature activation+0.000
."
Token."
Feature activation+0.000
Lev
Token Lev
Feature activation+0.000
inson
Tokeninson
Feature activation+1.766
was
Token was
Feature activation+0.491
tasked
Token tasked
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Ill
Token Ill
Feature activation+0.000
turned
Token turned
Feature activation+0.000
on
Token on
Feature activation+0.000
.-
Token.-
Feature activation+0.000
Removed
Token Removed
Feature activation+0.000
:
Token:
Feature activation+0.000
My
Token My
Feature activation+1.665
Wi
TokenWi
Feature activation+0.000
On
Token On
Feature activation+0.000
Demand
TokenDemand
Feature activation+0.000
-
Token-
Feature activation+0.000
Removed
Token Removed
Feature activation+0.000

INTERVAL 1.160 - 1.546
CONTAINS 0.030%

,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
we
Token we
Feature activation+1.395
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
start
Token start
Feature activation+0.000
with
Token with
Feature activation+0.000
on
Token on
Feature activation+0.000
TV
Token TV
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
see
Token see
Feature activation+0.000
what
Token what
Feature activation+1.481
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
trending
Token trending
Feature activation+0.000
within
Token within
Feature activation+0.000
to
Token to
Feature activation+0.000
end
Token end
Feature activation+0.000
the
Token the
Feature activation+0.000
wedding
Token wedding
Feature activation+0.000
.
Token.
Feature activation+0.000
Girl
Token Girl
Feature activation+1.198
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
father
Token father
Feature activation+0.000
returned
Token returned
Feature activation+0.000
-
Token-
Feature activation+0.000
man
Tokenman
Feature activation+0.000
rot
Token rot
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+1.186
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
pretty
Token pretty
Feature activation+0.000
be
Token be
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
.
Token.
Feature activation+0.000
Yes
Token Yes
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+1.409
know
Token know
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 0.773 - 1.160
CONTAINS 0.048%

aren
Token aren
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
dedicated
Token dedicated
Feature activation+0.000
left
Token left
Feature activation+0.825
eye
Token eye
Feature activation+0.000
or
Token or
Feature activation+0.000
right
Token right
Feature activation+0.226
eye
Token eye
Feature activation+0.000
;
Token;
Feature activation+0.000
quality
Token quality
Feature activation+0.000
scholarship
Token scholarship
Feature activation+0.000
has
Token has
Feature activation+0.000
demonstrated
Token demonstrated
Feature activation+0.000
that
Token that
Feature activation+0.000
Islam
Token Islam
Feature activation+0.893
,
Token,
Feature activation+0.784
Muslim
Token Muslim
Feature activation+0.000
societies
Token societies
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Red
TokenRed
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
was
Token was
Feature activation+0.923
a
Token a
Feature activation+0.000
staple
Token staple
Feature activation+0.000
of
Token of
Feature activation+0.000
Route
Token Route
Feature activation+0.000
66
Token 66
Feature activation+0.000
u
Tokenu
Feature activation+0.000
and
Token and
Feature activation+0.000
other
Token other
Feature activation+0.000
Oakland
Token Oakland
Feature activation+0.000
Police
Token Police
Feature activation+0.000
officers
Token officers
Feature activation+1.028
brutally
Token brutally
Feature activation+0.000
beat
Token beat
Feature activation+0.000
and
Token and
Feature activation+0.000
arrested
Token arrested
Feature activation+0.000
him
Token him
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
inside
Token inside
Feature activation+0.000
flap
Token flap
Feature activation+0.000
),
Token),
Feature activation+0.000
I
Token I
Feature activation+1.089
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
gonna
Token gonna
Feature activation+0.000
like
Token like
Feature activation+0.000

INTERVAL 0.387 - 0.773
CONTAINS 0.103%

not
Token not
Feature activation+0.000
yet
Token yet
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
prosecutor
Token prosecutor
Feature activation+0.503
was
Token was
Feature activation+0.423
saying
Token saying
Feature activation+0.000
that
Token that
Feature activation+0.000
his
Token his
Feature activation+0.137
release
Token release
Feature activation+0.000
from
Token from
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Comp
TokenComp
Feature activation+0.000
aring
Tokenaring
Feature activation+0.000
the
Token the
Feature activation+0.000
road
Token road
Feature activation+0.663
toward
Token toward
Feature activation+0.000
same
Token same
Feature activation+0.000
-
Token-
Feature activation+0.000
sex
Tokensex
Feature activation+0.000
marriage
Token marriage
Feature activation+0.000
or
Token or
Feature activation+0.000
worse
Token worse
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.014
takes
Token takes
Feature activation+0.000
it
Token it
Feature activation+0.542
for
Token for
Feature activation+0.000
granted
Token granted
Feature activation+0.000
that
Token that
Feature activation+0.175
in
Token in
Feature activation+0.043
a
Token a
Feature activation+0.000
Dance
Token Dance
Feature activation+0.000
Revolution
Token Revolution
Feature activation+0.000
"
Token"
Feature activation+0.000
in
Token in
Feature activation+0.000
Russell
Token Russell
Feature activation+0.370
's
Token's
Feature activation+0.733
parents
Token parents
Feature activation+0.000
'
Token'
Feature activation+0.000
basement
Token basement
Feature activation+0.000
when
Token when
Feature activation+0.000
Hear
Token Hear
Feature activation+0.000
com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+0.000
m
Tokenm
Feature activation+0.000
Y
TokenY
Feature activation+0.000
i
Tokeni
Feature activation+0.000
Queen
TokenQueen
Feature activation+0.401
E
TokenE
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Su
TokenSu
Feature activation+0.000
ppy
Tokenppy
Feature activation+0.000

INTERVAL 0.000 - 0.387
CONTAINS 99.776%

A
Token A
Feature activation+0.000
more
Token more
Feature activation+0.000
or
Token or
Feature activation+0.000
less
Token less
Feature activation+0.000
complete
Token complete
Feature activation+0.000
chang
Token chang
Feature activation+0.000
el
Tokenel
Feature activation+0.000
og
Tokenog
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
found
Token found
Feature activation+0.000
.
Token.
Feature activation+0.000
03
Token03
Feature activation+0.000
trillion
Token trillion
Feature activation+0.000
)
Token)
Feature activation+0.000
debt
Token debt
Feature activation+0.000
limit
Token limit
Feature activation+0.000
by
Token by
Feature activation+0.000
enough
Token enough
Feature activation+0.000
to
Token to
Feature activation+0.000
tide
Token tide
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
~
Token ~
Feature activation+0.000
May
TokenMay
Feature activation+0.000
a
Tokena
Feature activation+0.000
Angel
Token Angel
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
can
Token can
Feature activation+0.000
later
Token later
Feature activation+0.000
be
Token be
Feature activation+0.000
restored
Token restored
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
its
Token its
Feature activation+0.000
menu
Token menu
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
microwave
Token microwave
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
meant
Token meant
Feature activation+0.000
to
Token to
Feature activation+0.000
suggest
Token suggest
Feature activation+0.000
a
Token a
Feature activation+0.000
wavelength
Token wavelength
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
mic
Token mic
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 H5.5: (feature 12297)

TOP ACTIVATIONS
MAX = 2.589

a
Token a
Feature activation+0.000
FAQ
Token FAQ
Feature activation+0.000
posted
Token posted
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Bald
Token Bald
Feature activation+2.589
ur
Tokenur
Feature activation+1.192
's
Token's
Feature activation+1.414
Gate
Token Gate
Feature activation+0.307
site
Token site
Feature activation+0.000
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
repeal
Token repeal
Feature activation+0.000
of
Token of
Feature activation+0.000
#
Token #
Feature activation+0.000
Net
TokenNet
Feature activation+2.310
Ne
TokenNe
Feature activation+0.000
utral
Tokenutral
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
jury
Token jury
Feature activation+0.000
decided
Token decided
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
Rolling
Token Rolling
Feature activation+2.245
Stone
Token Stone
Feature activation+0.000
journalist
Token journalist
Feature activation+0.000
def
Token def
Feature activation+0.000
amed
Tokenamed
Feature activation+0.000
a
Token a
Feature activation+0.000
going
Token going
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
for
Token for
Feature activation+0.000
Bald
Token Bald
Feature activation+2.188
ur
Tokenur
Feature activation+1.318
's
Token's
Feature activation+1.249
Gate
Token Gate
Feature activation+0.000
II
Token II
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
developing
Token developing
Feature activation+0.000
Bald
Token Bald
Feature activation+2.130
ur
Tokenur
Feature activation+0.984
's
Token's
Feature activation+1.177
Gate
Token Gate
Feature activation+0.112
II
Token II
Feature activation+0.000
:
Token:
Feature activation+0.000
were
Token were
Feature activation+0.000
to
Token to
Feature activation+0.000
ask
Token ask
Feature activation+0.000
me
Token me
Feature activation+0.000
what
Token what
Feature activation+0.000
Life
Token Life
Feature activation+2.129
is
Token is
Feature activation+0.254
Strange
Token Strange
Feature activation+0.000
is
Token is
Feature activation+0.000
like
Token like
Feature activation+0.000
without
Token without
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.000
sides
Token sides
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
the
Token the
Feature activation+0.000
Hard
Token Hard
Feature activation+2.051
Rock
Token Rock
Feature activation+0.000
and
Token and
Feature activation+0.000
Spring
Token Spring
Feature activation+0.000
steen
Tokensteen
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Happy
TokenHappy
Feature activation+0.000
birthday
Token birthday
Feature activation+0.000
Half
Token Half
Feature activation+2.042
-
Token-
Feature activation+0.862
Life
TokenLife
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
wonderful
Token wonderful
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
time
Token time
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
Ron
TokenRon
Feature activation+2.038
Paul
Token Paul
Feature activation+0.000
really
Token really
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
't
Token't
Feature activation+0.000
think
Token think
Feature activation+0.000
to
Token to
Feature activation+0.000
back
Token back
Feature activation+0.000
Sanders
Token Sanders
Feature activation+0.000
yet
Token yet
Feature activation+0.000
.
Token.
Feature activation+0.000
C
Token C
Feature activation+1.976
WA
TokenWA
Feature activation+0.188
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
endorsement
Token endorsement
Feature activation+0.000
?
Token?
Feature activation+0.000
There
Token There
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
stylish
Token stylish
Feature activation+0.000
first
Token first
Feature activation+1.975
ladies
Token ladies
Feature activation+0.000
throughout
Token throughout
Feature activation+0.000
the
Token the
Feature activation+0.000
history
Token history
Feature activation+0.000
of
Token of
Feature activation+0.000
will
Token will
Feature activation+0.000
bring
Token bring
Feature activation+0.000
the
Token the
Feature activation+0.000
petition
Token petition
Feature activation+0.000
to
Token to
Feature activation+0.000
B
Token B
Feature activation+1.966
.
Token.
Feature activation+0.652
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
Environment
Token Environment
Feature activation+0.000
Minister
Token Minister
Feature activation+0.000
newly
Token newly
Feature activation+0.000
appointed
Token appointed
Feature activation+0.000
director
Token director
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Secret
Token Secret
Feature activation+1.961
Service
Token Service
Feature activation+0.021
,
Token,
Feature activation+0.000
Joseph
Token Joseph
Feature activation+0.000
P
Token P
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
distribution
Token distribution
Feature activation+0.000
rights
Token rights
Feature activation+0.000
for
Token for
Feature activation+0.000
Premier
Token Premier
Feature activation+1.950
League
Token League
Feature activation+0.106
games
Token games
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
your
Token your
Feature activation+0.000
betting
Token betting
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Post
TokenPost
Feature activation+0.000
Premier
Token Premier
Feature activation+1.933
League
Token League
Feature activation+0.000
tips
Token tips
Feature activation+0.000
for
Token for
Feature activation+0.000
free
Token free
Feature activation+0.000
and
Token and
Feature activation+0.000
clubs
Token clubs
Feature activation+0.000
have
Token have
Feature activation+0.000
lifted
Token lifted
Feature activation+0.000
the
Token the
Feature activation+0.000
coveted
Token coveted
Feature activation+0.000
Premier
Token Premier
Feature activation+1.912
League
Token League
Feature activation+0.159
trophy
Token trophy
Feature activation+0.000
.
Token.
Feature activation+0.000
Manchester
Token Manchester
Feature activation+0.000
United
Token United
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
R
Token R
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.000
Star
Token Star
Feature activation+1.888
Wars
Token Wars
Feature activation+0.000
8
Token 8
Feature activation+0.000
quotes
Token quotes
Feature activation+0.000
came
Token came
Feature activation+0.000
from
Token from
Feature activation+0.000
.
Token.
Feature activation+0.000
m
Tokenm
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Red
TokenRed
Feature activation+1.886
Bulls
Token Bulls
Feature activation+0.125
II
Token II
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
the
Token the
Feature activation+0.000
sixth
Token sixth
Feature activation+0.000
member
Token member
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
3
Token 3
Feature activation+1.874
DS
TokenDS
Feature activation+0.028
family
Token family
Feature activation+0.000
released
Token released
Feature activation+0.000
in
Token in
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
board
Token board
Feature activation+0.000
chair
Token chair
Feature activation+0.000
of
Token of
Feature activation+0.000
S
Token S
Feature activation+1.861
AND
TokenAND
Feature activation+0.336
AG
TokenAG
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000

Top DFA by src position
MAX = 2.889

launch
Token launch
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Bald
Token Bald
Feature activation+0.003
Top resid features:
ur
Tokenur
Feature activation-0.124
Top resid features:
's
Token's
Feature activation+0.006
Top resid features:
Gate
Token Gate
Feature activation+2.889
Top resid features:
II
Token II
Feature activation+0.003
Top resid features:
:
Token:
Feature activation+0.002
Top resid features:
Enhanced
Token Enhanced
Feature activation+0.002
Top resid features:
Edition
Token Edition
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
ridiculous
Token ridiculous
Feature activation+0.001
Top resid features:
assertion
Token assertion
Feature activation-0.001
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
Net
Token Net
Feature activation+0.011
Top resid features:
Neutral
Token Neutral
Feature activation+2.450
Top resid features:
ity
Tokenity
Feature activation+0.004
Top resid features:
repeal
Token repeal
Feature activation+0.005
Top resid features:
would
Token would
Feature activation+0.001
Top resid features:
usher
Token usher
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Thompson
Token Thompson
Feature activation-0.000
Top resid features:
Member
Token Member
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.011
Top resid features:
Roll
TokenRoll
Feature activation+0.005
Top resid features:
ing
Tokening
Feature activation-0.002
Top resid features:
Stone
Token Stone
Feature activation+1.590
Top resid features:
contributing
Token contributing
Feature activation-0.000
Top resid features:
editor
Token editor
Feature activation-0.000
Top resid features:
Sab
Token Sab
Feature activation+0.002
Top resid features:
rina
Tokenrina
Feature activation+0.003
Top resid features:
Rubin
Token Rubin
Feature activation+0.005
Top resid features:
launch
Token launch
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Bald
Token Bald
Feature activation+0.004
Top resid features:
ur
Tokenur
Feature activation-0.124
Top resid features:
's
Token's
Feature activation-0.001
Top resid features:
Gate
Token Gate
Feature activation+1.424
Top resid features:
II
Token II
Feature activation+0.001
Top resid features:
:
Token:
Feature activation+0.001
Top resid features:
Enhanced
Token Enhanced
Feature activation+0.001
Top resid features:
Edition
Token Edition
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
launch
Token launch
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Bald
Token Bald
Feature activation+0.003
Top resid features:
ur
Tokenur
Feature activation-0.074
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
Gate
Token Gate
Feature activation+1.054
Top resid features:
II
Token II
Feature activation+0.002
Top resid features:
:
Token:
Feature activation+0.001
Top resid features:
Enhanced
Token Enhanced
Feature activation+0.002
Top resid features:
Edition
Token Edition
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Life
TokenLife
Feature activation+0.003
Top resid features:
is
Token is
Feature activation+0.015
Top resid features:
Strange
Token Strange
Feature activation+2.290
Top resid features:
is
Token is
Feature activation-0.008
Top resid features:
not
Token not
Feature activation+0.001
Top resid features:
what
Token what
Feature activation+0.002
Top resid features:
one
Token one
Feature activation+0.002
Top resid features:
would
Token would
Feature activation-0.000
Top resid features:
The
Token The
Feature activation+0.009
Top resid features:
Joint
Token Joint
Feature activation+0.008
Top resid features:
at
Token at
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
Hard
Token Hard
Feature activation+0.004
Top resid features:
Rock
Token Rock
Feature activation+2.256
Top resid features:
Casino
Token Casino
Feature activation-0.003
Top resid features:
&
Token &
Feature activation+0.002
Top resid features:
Hotel
Token Hotel
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
has
Token has
Feature activation-0.005
Top resid features:
round
Token round
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Half
Token Half
Feature activation+0.005
Top resid features:
-
Token-
Feature activation+0.047
Top resid features:
Life
TokenLife
Feature activation+2.029
Top resid features:
âĢ
TokenâĢ
Feature activation-0.007
Top resid features:
Ļ
TokenĻ
Feature activation-0.000
Top resid features:
s
Tokens
Feature activation+0.003
Top resid features:
notable
Token notable
Feature activation+0.002
Top resid features:
mods
Token mods
Feature activation-0.001
Top resid features:
I
Token I
Feature activation-0.000
Top resid features:
heard
Token heard
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Ron
Token Ron
Feature activation-0.000
Top resid features:
Paul
Token Paul
Feature activation+2.281
Top resid features:
speeches
Token speeches
Feature activation+0.004
Top resid features:
was
Token was
Feature activation-0.000
Top resid features:
'
Token '
Feature activation-0.001
Top resid features:
The
TokenThe
Feature activation+0.008
Top resid features:
Constitution
Token Constitution
Feature activation+0.034
Top resid features:
Thursday
Token Thursday
Feature activation-0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
powerful
Token powerful
Feature activation+0.001
Top resid features:
Communications
Token Communications
Feature activation+0.008
Top resid features:
Workers
Token Workers
Feature activation+2.172
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
America
Token America
Feature activation+0.011
Top resid features:
union
Token union
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
sources
Token sources
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
H
Token H
Feature activation+0.007
Top resid features:
OTT
TokenOTT
Feature activation+0.004
Top resid features:
EST
TokenEST
Feature activation+0.006
Top resid features:
first
Token first
Feature activation+0.005
Top resid features:
lady
Token lady
Feature activation+2.276
Top resid features:
ever
Token ever
Feature activation-0.008
Top resid features:
?
Token?
Feature activation+0.036
Top resid features:
There
Token There
Feature activation-0.010
Top resid features:
have
Token have
Feature activation+0.004
Top resid features:
been
Token been
Feature activation+0.007
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
pressure
Token pressure
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
B
Token B
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
C
TokenC
Feature activation+1.089
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
government
Token government
Feature activation+0.007
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
charge
Token charge
Feature activation+0.002
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
)
Token)
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Two
TokenTwo
Feature activation+0.001
Top resid features:
Secret
Token Secret
Feature activation-0.000
Top resid features:
Service
Token Service
Feature activation+2.058
Top resid features:
agents
Token agents
Feature activation+0.015
Top resid features:
suspected
Token suspected
Feature activation-0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
being
Token being
Feature activation-0.000
Top resid features:
under
Token under
Feature activation-0.000
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
many
Token many
Feature activation-0.000
Top resid features:
years
Token years
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
Premier
Token Premier
Feature activation+0.003
Top resid features:
League
Token League
Feature activation+2.128
Top resid features:
games
Token games
Feature activation+0.004
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.001
Top resid features:
shown
Token shown
Feature activation-0.001
Top resid features:
detail
Token detail
Feature activation+0.001
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
posting
Token posting
Feature activation-0.003
Top resid features:
their
Token their
Feature activation-0.001
Top resid features:
Premier
Token Premier
Feature activation+0.002
Top resid features:
League
Token League
Feature activation+1.175
Top resid features:
predictions
Token predictions
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
Follow
Token Follow
Feature activation-0.000
Top resid features:
our
Token our
Feature activation-0.000
Top resid features:
best
Token best
Feature activation+0.001
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
1992
Token 1992
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
Premier
Token Premier
Feature activation+0.002
Top resid features:
League
Token League
Feature activation+2.080
Top resid features:
has
Token has
Feature activation+0.002
Top resid features:
become
Token become
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
most
Token most
Feature activation-0.000
Top resid features:
popular
Token popular
Feature activation+0.000
Top resid features:
R
Token R
Feature activation+0.004
Top resid features:
ian
Tokenian
Feature activation+0.004
Top resid features:
Johnson
Token Johnson
Feature activation-0.004
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
Star
Token Star
Feature activation+0.006
Top resid features:
Wars
Token Wars
Feature activation+2.206
Top resid features:
8
Token 8
Feature activation+0.007
Top resid features:
below
Token below
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.026
Top resid features:
New
TokenNew
Feature activation+0.007
Top resid features:
York
Token York
Feature activation-0.012
Top resid features:
Red
Token Red
Feature activation+0.010
Top resid features:
Bulls
Token Bulls
Feature activation+1.608
Top resid features:
II
Token II
Feature activation+0.004
Top resid features:
is
Token is
Feature activation-0.009
Top resid features:
ready
Token ready
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
take
Token take
Feature activation+0.000
Top resid features:
NHS
Token NHS
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.007
Top resid features:
Nintendo
TokenNintendo
Feature activation+0.004
Top resid features:
's
Token's
Feature activation+0.001
Top resid features:
3
Token 3
Feature activation+0.002
Top resid features:
DS
TokenDS
Feature activation+2.006
Top resid features:
line
Token line
Feature activation+0.005
Top resid features:
might
Token might
Feature activation-0.000
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
board
Token board
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
San
Token San
Feature activation+0.001
Top resid features:
Diego
Token Diego
Feature activation+1.919
Top resid features:
Association
Token Association
Feature activation+0.015
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
Governments
Token Governments
Feature activation+0.006
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.04

Head 2: 0.03

Head 3: 0.03

Head 4: 0.03

Head 5: 0.56

Head 6: 0.02

Head 7: 0.02

Head 8: 0.04

Head 9: 0.10

Head 10: 0.08

Head 11: 0.03

Positive logits

Tex1.62

1.54

1.47

1.46

QC1.39

wiser1.37

STON1.35

Official1.34

shin1.32

LV1.31

LAPD1.29

��1.29

DOD1.28

TX1.28

HQ1.28

DHS1.27

metic1.27

Psycho1.26

MBA1.26

DOJ1.25

Negative logits

nown-1.85

resent-1.79

[&-1.65

lication-1.65

iona-1.63

ynthesis-1.60

hello-1.56

tein-1.56

ategory-1.54

perate-1.52

addons-1.52

20439-1.52

Attach-1.51

orem-1.51

tera-1.50

inev-1.50

guiActiveUnfocused-1.50

nikov-1.49

suff-1.48

heter-1.47

INTERVAL 2.330 - 2.589
CONTAINS 0.000%

a
Token a
Feature activation+0.000
FAQ
Token FAQ
Feature activation+0.000
posted
Token posted
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Bald
Token Bald
Feature activation+2.589
ur
Tokenur
Feature activation+1.192
's
Token's
Feature activation+1.414
Gate
Token Gate
Feature activation+0.307
site
Token site
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 2.071 - 2.330
CONTAINS 0.001%

going
Token going
Feature activation+0.000
on
Token on
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
for
Token for
Feature activation+0.000
Bald
Token Bald
Feature activation+2.188
ur
Tokenur
Feature activation+1.318
's
Token's
Feature activation+1.249
Gate
Token Gate
Feature activation+0.000
II
Token II
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
developing
Token developing
Feature activation+0.000
Bald
Token Bald
Feature activation+2.130
ur
Tokenur
Feature activation+0.984
's
Token's
Feature activation+1.177
Gate
Token Gate
Feature activation+0.112
II
Token II
Feature activation+0.000
:
Token:
Feature activation+0.000
jury
Token jury
Feature activation+0.000
decided
Token decided
Feature activation+0.000
Friday
Token Friday
Feature activation+0.000
that
Token that
Feature activation+0.000
a
Token a
Feature activation+0.000
Rolling
Token Rolling
Feature activation+2.245
Stone
Token Stone
Feature activation+0.000
journalist
Token journalist
Feature activation+0.000
def
Token def
Feature activation+0.000
amed
Tokenamed
Feature activation+0.000
a
Token a
Feature activation+0.000
were
Token were
Feature activation+0.000
to
Token to
Feature activation+0.000
ask
Token ask
Feature activation+0.000
me
Token me
Feature activation+0.000
what
Token what
Feature activation+0.000
Life
Token Life
Feature activation+2.129
is
Token is
Feature activation+0.254
Strange
Token Strange
Feature activation+0.000
is
Token is
Feature activation+0.000
like
Token like
Feature activation+0.000
without
Token without
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
repeal
Token repeal
Feature activation+0.000
of
Token of
Feature activation+0.000
#
Token #
Feature activation+0.000
Net
TokenNet
Feature activation+2.310
Ne
TokenNe
Feature activation+0.000
utral
Tokenutral
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000

INTERVAL 1.812 - 2.071
CONTAINS 0.002%

?
Token?
Feature activation+0.000
There
Token There
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
stylish
Token stylish
Feature activation+0.000
first
Token first
Feature activation+1.975
ladies
Token ladies
Feature activation+0.000
throughout
Token throughout
Feature activation+0.000
the
Token the
Feature activation+0.000
history
Token history
Feature activation+0.000
of
Token of
Feature activation+0.000
will
Token will
Feature activation+0.000
bring
Token bring
Feature activation+0.000
the
Token the
Feature activation+0.000
petition
Token petition
Feature activation+0.000
to
Token to
Feature activation+0.000
B
Token B
Feature activation+1.966
.
Token.
Feature activation+0.652
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
Environment
Token Environment
Feature activation+0.000
Minister
Token Minister
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
R
Token R
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.000
Star
Token Star
Feature activation+1.888
Wars
Token Wars
Feature activation+0.000
8
Token 8
Feature activation+0.000
quotes
Token quotes
Feature activation+0.000
came
Token came
Feature activation+0.000
from
Token from
Feature activation+0.000
to
Token to
Feature activation+0.000
back
Token back
Feature activation+0.000
Sanders
Token Sanders
Feature activation+0.000
yet
Token yet
Feature activation+0.000
.
Token.
Feature activation+0.000
C
Token C
Feature activation+1.976
WA
TokenWA
Feature activation+0.188
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
endorsement
Token endorsement
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Happy
TokenHappy
Feature activation+0.000
birthday
Token birthday
Feature activation+0.000
Half
Token Half
Feature activation+2.042
-
Token-
Feature activation+0.862
Life
TokenLife
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
wonderful
Token wonderful
Feature activation+0.000

INTERVAL 1.553 - 1.812
CONTAINS 0.004%

Palo
Token Palo
Feature activation+0.000
Alto
Token Alto
Feature activation+0.000
Weekly
Token Weekly
Feature activation+0.000
/
Token/
Feature activation+0.000
P
TokenP
Feature activation+1.528
alo
Tokenalo
Feature activation+1.658
Alto
Token Alto
Feature activation+0.311
Online
Token Online
Feature activation+0.000
on
Token on
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
@
Token @
Feature activation+0.000
counties
Token counties
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
food
Token food
Feature activation+1.567
stamp
Token stamp
Feature activation+0.000
recipients
Token recipients
Feature activation+0.000
doubled
Token doubled
Feature activation+0.000
between
Token between
Feature activation+0.000
2007
Token 2007
Feature activation+0.000
oyd
Tokenoyd
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
represents
Token represents
Feature activation+0.000
former
Token former
Feature activation+0.000
Ole
Token Ole
Feature activation+1.632
Miss
Token Miss
Feature activation+0.000
staffer
Token staffer
Feature activation+0.000
Barney
Token Barney
Feature activation+0.000
F
Token F
Feature activation+0.000
arr
Tokenarr
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Week
Token Week
Feature activation+0.000
:
Token:
Feature activation+0.000
Op
Token Op
Feature activation+0.000
ens
Tokenens
Feature activation+1.725
hot
Tokenhot
Feature activation+0.000
Video
Token Video
Feature activation+0.000
Editor
Token Editor
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
s
Tokens
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
to
Token to
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
Star
Token Star
Feature activation+1.652
Wars
Token Wars
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
you
Token you
Feature activation+0.000
did
Token did
Feature activation+0.000

INTERVAL 1.294 - 1.553
CONTAINS 0.009%

sw
Token sw
Feature activation+0.000
immers
Tokenimmers
Feature activation+0.000
,
Token,
Feature activation+0.000
led
Token led
Feature activation+0.000
by
Token by
Feature activation+0.000
pop
Token pop
Feature activation+1.363
singer
Token singer
Feature activation+0.000
Kim
Token Kim
Feature activation+0.000
J
Token J
Feature activation+0.000
ang
Tokenang
Feature activation+0.000
-
Token-
Feature activation+0.000
are
Token are
Feature activation+0.000
many
Token many
Feature activation+0.000
prominent
Token prominent
Feature activation+0.000
examples
Token examples
Feature activation+0.000
of
Token of
Feature activation+0.000
science
Token science
Feature activation+1.548
fiction
Token fiction
Feature activation+0.000
thrill
Token thrill
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
or
Token or
Feature activation+0.000
science
Token science
Feature activation+0.974
with
Token with
Feature activation+0.000
tired
Token tired
Feature activation+0.000
insults
Token insults
Feature activation+0.000
,
Token,
Feature activation+0.000
Pac
Token Pac
Feature activation+1.413
-
Token-
Feature activation+1.421
12
Token12
Feature activation+0.000
folks
Token folks
Feature activation+0.000
now
Token now
Feature activation+0.000
can
Token can
Feature activation+0.000
show
Token show
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
response
Token response
Feature activation+0.000
of
Token of
Feature activation+0.000
Pirate
Token Pirate
Feature activation+1.469
Bay
Token Bay
Feature activation+0.000
admin
Token admin
Feature activation+0.000
Bro
Token Bro
Feature activation+0.000
ke
Tokenke
Feature activation+0.000
p
Tokenp
Feature activation+0.000
-
Token-
Feature activation+0.000
Jump
TokenJump
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dragon
TokenDragon
Feature activation+1.514
Ball
Token Ball
Feature activation+0.000
Fighter
Token Fighter
Feature activation+0.000
Z
TokenZ
Feature activation+0.000
will
Token will
Feature activation+0.000
launch
Token launch
Feature activation+0.000

INTERVAL 1.036 - 1.294
CONTAINS 0.017%

the
Token the
Feature activation+0.000
moment
Token moment
Feature activation+0.000
you
Token you
Feature activation+0.000
slip
Token slip
Feature activation+0.000
on
Token on
Feature activation+0.000
PlayStation
Token PlayStation
Feature activation+1.042
VR
Token VR
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
Virtual
Token Virtual
Feature activation+0.000
and
Token and
Feature activation+0.000
Services
Token Services
Feature activation+0.000
Tax
Token Tax
Feature activation+0.000
(
Token (
Feature activation+0.000
G
TokenG
Feature activation+0.580
ST
TokenST
Feature activation+1.077
),
Token),
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
t
Tokent
Feature activation+0.000
often
Token often
Feature activation+0.000
singled
Token singled
Feature activation+0.000
out
Token out
Feature activation+0.000
in
Token in
Feature activation+0.000
Doctor
Token Doctor
Feature activation+1.197
Who
Token Who
Feature activation+0.000
write
Token write
Feature activation+0.000
-
Token-
Feature activation+0.000
ups
Tokenups
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
included
Token included
Feature activation+0.000
major
Token major
Feature activation+0.000
contributions
Token contributions
Feature activation+0.000
from
Token from
Feature activation+0.000
Las
Token Las
Feature activation+1.145
Vegas
Token Vegas
Feature activation+0.000
Sands
Token Sands
Feature activation+0.000
Corporation
Token Corporation
Feature activation+0.000
CEO
Token CEO
Feature activation+0.000
Sheldon
Token Sheldon
Feature activation+0.000
Fire
Token Fire
Feature activation+0.000
works
Tokenworks
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ind
TokenInd
Feature activation+1.348
ependence
Tokenependence
Feature activation+1.085
Day
Token Day
Feature activation+0.000
Facts
Token Facts
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Why
TokenWhy
Feature activation+0.000

INTERVAL 0.777 - 1.036
CONTAINS 0.029%

Marvel
Token Marvel
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Captain
Token Captain
Feature activation+0.789
now
Token now
Feature activation+0.000
begins
Token begins
Feature activation+0.000
to
Token to
Feature activation+0.000
root
Token root
Feature activation+0.000
out
Token out
Feature activation+0.000
sometimes
Token sometimes
Feature activation+0.000
silly
Token silly
Feature activation+0.000
,
Token,
Feature activation+0.000
take
Token take
Feature activation+0.000
on
Token on
Feature activation+0.000
Mega
Token Mega
Feature activation+0.863
Man
Token Man
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
that
Token that
Feature activation+0.000
$
Token $
Feature activation+0.000
29
Token29
Feature activation+0.000
,
Token,
Feature activation+0.000
402
Token402
Feature activation+0.000
.
Token.
Feature activation+0.000
U
Token U
Feature activation+0.852
H
TokenH
Feature activation+0.000
H
Token H
Feature activation+0.000
ilo
Tokenilo
Feature activation+0.000
charges
Token charges
Feature activation+0.000
$
Token $
Feature activation+0.000
with
Token with
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
earliest
Token earliest
Feature activation+0.000
Hip
Token Hip
Feature activation+0.813
Hop
Token Hop
Feature activation+0.000
records
Token records
Feature activation+0.000
ever
Token ever
Feature activation+0.000
made
Token made
Feature activation+0.000
being
Token being
Feature activation+0.000
warned
Token warned
Feature activation+0.000
that
Token that
Feature activation+0.000
parts
Token parts
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Y
Token Y
Feature activation+0.810
onge
Tokenonge
Feature activation+0.000
subway
Token subway
Feature activation+0.000
line
Token line
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000

INTERVAL 0.518 - 0.777
CONTAINS 0.065%

is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
such
Token such
Feature activation+0.000
equivalent
Token equivalent
Feature activation+0.000
in
Token in
Feature activation+0.000
English
Token English
Feature activation+0.681
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
Fog
Token Fog
Feature activation+0.000
el
Tokenel
Feature activation+0.000
says
Token says
Feature activation+0.000
46
Token46
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.567
States
Token States
Feature activation+0.000
received
Token received
Feature activation+0.000
the
Token the
Feature activation+0.000
vast
Token vast
Feature activation+0.000
exp
Token exp
Feature activation+0.000
vital
Token vital
Feature activation+0.000
that
Token that
Feature activation+0.000
they
Token they
Feature activation+0.000
keep
Token keep
Feature activation+0.000
everyday
Token everyday
Feature activation+0.000
New
Token New
Feature activation+0.563
Yorkers
Token Yorkers
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
of
Token of
Feature activation+0.000
ler
Tokenler
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.614
community
Token community
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
efforts
Token efforts
Feature activation+0.000
.
Token.
Feature activation+0.000
All
Token All
Feature activation+0.000
places
Token places
Feature activation+0.000
within
Token within
Feature activation+0.000
one
Token one
Feature activation+0.000
time
Token time
Feature activation+0.685
zone
Token zone
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
time
Token time
Feature activation+0.776

INTERVAL 0.259 - 0.518
CONTAINS 0.122%

ambient
Token ambient
Feature activation+0.000
temperature
Token temperature
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
specific
Token specific
Feature activation+0.000
residence
Token residence
Feature activation+0.326
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
water
Token water
Feature activation+0.000
ch
Token ch
Feature activation+0.000
iller
Tokeniller
Feature activation+0.000
some
Token some
Feature activation+0.000
reason
Token reason
Feature activation+0.000
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
D
TokenD
Feature activation+0.489
aw
Tokenaw
Feature activation+0.000
kins
Tokenkins
Feature activation+0.000
'
Token'
Feature activation+0.000
religious
Token religious
Feature activation+0.000
ferv
Token ferv
Feature activation+0.000
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
man
Token man
Feature activation+0.000
,
Token,
Feature activation+0.000
good
Token good
Feature activation+0.295
solid
Token solid
Feature activation+0.000
fighter
Token fighter
Feature activation+0.000
,
Token,
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
but
Token but
Feature activation+0.000
teams
Token teams
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
interested
Token interested
Feature activation+0.000
in
Token in
Feature activation+0.000
A
Token A
Feature activation+0.267
du
Tokendu
Feature activation+0.000
at
Token at
Feature activation+0.000
this
Token this
Feature activation+0.000
point
Token point
Feature activation+0.000
?
Token?
Feature activation+0.000
of
Token of
Feature activation+0.000
liquor
Token liquor
Feature activation+0.000
imported
Token imported
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Czech
Token Czech
Feature activation+0.440
Republic
Token Republic
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.000
countries
Token countries
Feature activation+0.000
border
Token border
Feature activation+0.000

INTERVAL 0.000 - 0.259
CONTAINS 99.750%

a
Token a
Feature activation+0.000
way
Token way
Feature activation+0.000
that
Token that
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000
how
Token how
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
touch
Token touch
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
House
Token House
Feature activation+0.000
culture
Token culture
Feature activation+0.000
revival
Token revival
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
ways
Token ways
Feature activation+0.000
to
Token to
Feature activation+0.000
enjoy
Token enjoy
Feature activation+0.000
bourbon
Token bourbon
Feature activation+0.000
have
Token have
Feature activation+0.000
expanded
Token expanded
Feature activation+0.000
exponentially
Token exponentially
Feature activation+0.000
has
Token has
Feature activation+0.000
defended
Token defended
Feature activation+0.000
Gerry
Token Gerry
Feature activation+0.000
Adams
Token Adams
Feature activation+0.000
and
Token and
Feature activation+0.000
said
Token said
Feature activation+0.000
controversy
Token controversy
Feature activation+0.000
surrounding
Token surrounding
Feature activation+0.000
his
Token his
Feature activation+0.000
alleged
Token alleged
Feature activation+0.000
involvement
Token involvement
Feature activation+0.000
and
Token and
Feature activation+0.000
Disney
Token Disney
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
work
Token work
Feature activation+0.000
,
Token,
Feature activation+0.000
respectively
Token respectively
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
Christopher
Token Christopher
Feature activation+0.000
Burk
Token Burk
Feature activation+0.000
hardt
Tokenhardt
Feature activation+0.000
,
Token,
Feature activation+0.000
27
Token 27
Feature activation+0.000
,
Token,
Feature activation+0.000
unlawful
Token unlawful
Feature activation+0.000
conduct
Token conduct
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+0.203
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+0.203
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+0.203
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature 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+0.203
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 H5.5: (feature 18070)

TOP ACTIVATIONS
MAX = 3.153

.
Token.
Feature activation+0.000
E
TokenE
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+3.153
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
enforcement
Token enforcement
Feature activation+0.000
director
Token director
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
Snowden
Token Snowden
Feature activation+0.000
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+3.032
ľ
Tokenľ
Feature activation+0.000
security
Tokensecurity
Feature activation+0.000
situation
Token situation
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.693
Ŀ
TokenĿ
Feature activation+0.000
host
Token host
Feature activation+0.000
introduced
Token introduced
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
âĢ
Token âĢ
Feature activation+3.000
ľ
Tokenľ
Feature activation+0.000
activ
Tokenactiv
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
,
Token,
Feature activation+0.000
thought
Token thought
Feature activation+0.000
essential
Token essential
Feature activation+0.000
health
Token health
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
âĢ
Token âĢ
Feature activation+2.786
ľ
Tokenľ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
aternity
Tokenaternity
Feature activation+0.000
care
Token care
Feature activation+0.000
,
Token,
Feature activation+0.000
1940
Token 1940
Feature activation+0.000
,
Token,
Feature activation+0.000
Ad
Token Ad
Feature activation+0.000
olph
Tokenolph
Feature activation+0.000
Hitler
Token Hitler
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.770
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Nazi
Token Nazi
Feature activation+0.000
troops
Token troops
Feature activation+0.000
invaded
Token invaded
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Buy
TokenBuy
Feature activation+0.000
er
Tokener
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.762
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
drought
Token drought
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Rom
TokenRom
Feature activation+0.000
án
Tokenán
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.761
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
team
Token team
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
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
Clinton
TokenClinton
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.753
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
circle
Token circle
Feature activation+0.000
of
Token of
Feature activation+0.000
friends
Token friends
Feature activation+0.000
economic
Token economic
Feature activation+0.000
warfare
Token warfare
Feature activation+0.000
.
Token.
Feature activation+0.000
Rob
Token Rob
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+2.736
ľ
Tokenľ
Feature activation+0.000
G
TokenG
Feature activation+0.000
oy
Tokenoy
Feature activation+0.000
im
Tokenim
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.214
man
Token man
Feature activation+0.000
in
Token in
Feature activation+0.000
question
Token question
Feature activation+0.000
replied
Token replied
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+2.717
ľ
Tokenľ
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
gh
Tokengh
Feature activation+0.000
bl
Token bl
Feature activation+0.000
arg
Tokenarg
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+3.032
ľ
Tokenľ
Feature activation+0.000
security
Tokensecurity
Feature activation+0.000
situation
Token situation
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.693
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ass
TokenAss
Feature activation+0.000
sarcastic
Token sarcastic
Feature activation+0.000
statement
Token statement
Feature activation+0.000
about
Token about
Feature activation+0.000
Man
Token Man
Feature activation+0.000
chin
Tokenchin
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.679
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
absence
Token absence
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Moff
Token Moff
Feature activation+0.000
att
Tokenatt
Feature activation+0.000
admitted
Token admitted
Feature activation+0.000
he
Token he
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.663
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
speak
Token speak
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
nominee
Token nominee
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+2.628
ľ
Tokenľ
Feature activation+0.000
wh
Tokenwh
Feature activation+0.000
olly
Tokenolly
Feature activation+0.000
unacceptable
Token unacceptable
Feature activation+0.000
.
Token.
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Some
TokenSome
Feature activation+0.000
think
Token think
Feature activation+0.000
there
Token there
Feature activation+0.000
won
Token won
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.615
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
room
Token room
Feature activation+0.000
for
Token for
Feature activation+0.000
Hip
Token Hip
Feature activation+0.000
camp
Tokencamp
Feature activation+0.000
has
Token has
Feature activation+0.000
launched
Token launched
Feature activation+0.000
its
Token its
Feature activation+0.000
âĢ
Token âĢ
Feature activation+2.572
ľ
Tokenľ
Feature activation+0.000
land
Tokenland
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.775
Ŀ
TokenĿ
Feature activation+0.000
of
Token of
Feature activation+0.000
Sh
Token Sh
Feature activation+0.000
auna
Tokenauna
Feature activation+0.000
Aura
Token Aura
Feature activation+0.000
Knight
Token Knight
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.559
ĺ
Tokenĺ
Feature activation+0.000
s
Tokens
Feature activation+0.000
personal
Token personal
Feature activation+0.000
strategy
Token strategy
Feature activation+0.000
:
Token:
Feature activation+0.000
Y
Token Y
Feature activation+0.000
ellen
Tokenellen
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
âĢ
Token âĢ
Feature activation+2.509
ľ
Tokenľ
Feature activation+0.000
opt
Tokenopt
Feature activation+0.000
imal
Tokenimal
Feature activation+0.000
control
Token control
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.055
Warcraft
Token Warcraft
Feature activation+0.000
,
Token,
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
Blizzard
Token Blizzard
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.508
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
most
Token most
Feature activation+0.000
popular
Token popular
Feature activation+0.000
franchises
Token franchises
Feature activation+0.000
Constitution
Token Constitution
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
begins
Token begins
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+2.492
ľ
Tokenľ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
Name
Token Name
Feature activation+0.000
of
Token of
Feature activation+0.000

Top DFA by src position
MAX = 4.629

be
Token be
Feature activation-0.000
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
effective
Token effective
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+4.629
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
S
TokenS
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
E
TokenE
Feature activation+0.001
Top resid features:
them
Token them
Feature activation+0.001
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
broadly
Token broadly
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+4.417
Top resid features:
Assange
Token Assange
Feature activation-0.050
Top resid features:
said
Token said
Feature activation-0.004
Top resid features:
he
Token he
Feature activation-0.000
Top resid features:
kept
Token kept
Feature activation+0.001
Top resid features:
close
Token close
Feature activation+0.002
Top resid features:
demand
Token demand
Feature activation+0.001
Top resid features:
our
Token our
Feature activation+0.002
Top resid features:
attention
Token attention
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation-0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+4.453
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
The
TokenThe
Feature activation+0.001
Top resid features:
event
Token event
Feature activation-0.000
Top resid features:
was
Token was
Feature activation-0.001
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+4.158
Top resid features:
Ċ
TokenĊ
Feature activation+0.043
Top resid features:
Ċ
TokenĊ
Feature activation+0.039
Top resid features:
Further
TokenFurther
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
undis
Token undis
Feature activation+0.001
Top resid features:
puted
Tokenputed
Feature activation+0.000
Top resid features:
possession
Token possession
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+4.242
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Flash
TokenFlash
Feature activation+0.004
Top resid features:
forward
Token forward
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
im
Token im
Feature activation-0.001
Top resid features:
min
Tokenmin
Feature activation-0.000
Top resid features:
ently
Tokenently
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation-0.005
Top resid features:
Ŀ
TokenĿ
Feature activation+4.461
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
Buy
TokenBuy
Feature activation-0.019
Top resid features:
er
Tokener
Feature activation-0.015
Top resid features:
âĢ
TokenâĢ
Feature activation-0.026
Top resid features:
moon
Token moon
Feature activation+0.004
Top resid features:
light
Tokenlight
Feature activation-0.003
Top resid features:
conditions
Token conditions
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.016
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ŀ
TokenĿ
Feature activation+4.264
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
Rom
TokenRom
Feature activation+0.035
Top resid features:
án
Tokenán
Feature activation+0.042
Top resid features:
âĢ
TokenâĢ
Feature activation-0.011
Top resid features:
prepared
Token prepared
Feature activation+0.001
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
embrace
Token embrace
Feature activation+0.002
Top resid features:
.
Token.
Feature activation-0.019
Top resid features:
âĢ
TokenâĢ
Feature activation-0.008
Top resid features:
Ŀ
TokenĿ
Feature activation+4.460
Top resid features:
Ċ
TokenĊ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
Clinton
TokenClinton
Feature activation-0.013
Top resid features:
âĢ
TokenâĢ
Feature activation-0.020
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
great
Token great
Feature activation-0.003
Top resid features:
political
Token political
Feature activation-0.000
Top resid features:
smash
Token smash
Feature activation-0.000
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ŀ
TokenĿ
Feature activation+4.155
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
21
Token21
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Use
Token Use
Feature activation+0.015
Top resid features:
hardcore
Token hardcore
Feature activation-0.001
Top resid features:
stands
Token stands
Feature activation+0.002
Top resid features:
for
Token for
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+4.206
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
When
TokenWhen
Feature activation+0.006
Top resid features:
reached
Token reached
Feature activation+0.013
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
them
Token them
Feature activation+0.001
Top resid features:
more
Token more
Feature activation-0.001
Top resid features:
broadly
Token broadly
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ŀ
TokenĿ
Feature activation+4.226
Top resid features:
Assange
Token Assange
Feature activation-0.047
Top resid features:
said
Token said
Feature activation-0.003
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
kept
Token kept
Feature activation+0.001
Top resid features:
close
Token close
Feature activation+0.001
Top resid features:
what
Token what
Feature activation-0.001
Top resid features:
Christmas
Token Christmas
Feature activation+0.005
Top resid features:
means
Token means
Feature activation-0.005
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+4.265
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
Which
TokenWhich
Feature activation-0.019
Top resid features:
might
Token might
Feature activation-0.002
Top resid features:
be
Token be
Feature activation-0.003
Top resid features:
is
Token is
Feature activation-0.003
Top resid features:
plainly
Token plainly
Feature activation-0.002
Top resid features:
unfair
Token unfair
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ŀ
TokenĿ
Feature activation+4.339
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.025
Top resid features:
The
TokenThe
Feature activation-0.003
Top resid features:
Coalition
Token Coalition
Feature activation+0.001
Top resid features:
came
Token came
Feature activation-0.002
Top resid features:
vote
Token vote
Feature activation+0.001
Top resid features:
for
Token for
Feature activation+0.001
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.002
Top resid features:
Ŀ
TokenĿ
Feature activation+4.227
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
In
TokenIn
Feature activation-0.004
Top resid features:
addition
Token addition
Feature activation-0.002
Top resid features:
to
Token to
Feature activation-0.010
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
this
Token this
Feature activation+0.001
Top resid features:
matter
Token matter
Feature activation+0.010
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation-0.001
Top resid features:
Ŀ
TokenĿ
Feature activation+4.421
Top resid features:
Ernest
Token Ernest
Feature activation-0.009
Top resid features:
o
Tokeno
Feature activation-0.001
Top resid features:
Zed
Token Zed
Feature activation-0.004
Top resid features:
illo
Tokenillo
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
this
Token this
Feature activation+0.001
Top resid features:
land
Token land
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
âĢ
TokenâĢ
Feature activation-0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+4.152
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.038
Top resid features:
Right
TokenRight
Feature activation-0.006
Top resid features:
now
Token now
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
high
Token high
Feature activation-0.001
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
sugar
Token sugar
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ŀ
TokenĿ
Feature activation+4.298
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.045
Top resid features:
Food
TokenFood
Feature activation+0.014
Top resid features:
s
Tokens
Feature activation+0.005
Top resid features:
are
Token are
Feature activation-0.008
Top resid features:
expectation
Token expectation
Feature activation-0.001
Top resid features:
well
Token well
Feature activation-0.000
Top resid features:
anchored
Token anchored
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+3.899
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
And
TokenAnd
Feature activation+0.002
Top resid features:
note
Token note
Feature activation+0.000
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
types
Token types
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
platforms
Token platforms
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ŀ
TokenĿ
Feature activation+4.057
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
We
TokenWe
Feature activation-0.045
Top resid features:
also
Token also
Feature activation-0.006
Top resid features:
asked
Token asked
Feature activation-0.018
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
any
Token any
Feature activation+0.000
Top resid features:
religion
Token religion
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+3.830
Top resid features:
Ċ
TokenĊ
Feature activation+0.068
Top resid features:
Ċ
TokenĊ
Feature activation+0.040
Top resid features:
Human
TokenHuman
Feature activation+0.001
Top resid features:
ists
Tokenists
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.05

Head 2: 0.03

Head 3: 0.05

Head 4: 0.03

Head 5: 0.55

Head 6: 0.04

Head 7: 0.02

Head 8: 0.06

Head 9: 0.06

Head 10: 0.05

Head 11: 0.03

Positive logits

ijn1.47

arnaev1.46

branches1.41

Cards1.38

provocative1.35

favors1.35

Button1.34

owship1.33

alert1.30

nominees1.30

Term1.29

Herod1.29

symbolism1.29

fodder1.28

tyr1.27

Blow1.27

addle1.27

orthy1.26

Hare1.25

aki1.24

Negative logits

assetsadobe-1.91

Manit-1.88

Glac-1.69

Ther-1.64

originals-1.54

imil-1.54

suff-1.54

�醒-1.48

stood-1.43

lycer-1.43

GDP-1.42

Glacier-1.42

stable-1.41

pent-1.40

Unic-1.38

copy-1.37

mop-1.36

FS-1.36

-1.36

Scotia-1.36

INTERVAL 2.838 - 3.153
CONTAINS 0.000%

host
Token host
Feature activation+0.000
introduced
Token introduced
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
âĢ
Token âĢ
Feature activation+3.000
ľ
Tokenľ
Feature activation+0.000
activ
Tokenactiv
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
,
Token,
Feature activation+0.000
thought
Token thought
Feature activation+0.000
.
Token.
Feature activation+0.000
E
TokenE
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+3.153
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
enforcement
Token enforcement
Feature activation+0.000
director
Token director
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
Snowden
Token Snowden
Feature activation+0.000
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+3.032
ľ
Tokenľ
Feature activation+0.000
security
Tokensecurity
Feature activation+0.000
situation
Token situation
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.693
Ŀ
TokenĿ
Feature activation+0.000

INTERVAL 2.522 - 2.838
CONTAINS 0.001%

Hip
Token Hip
Feature activation+0.000
camp
Tokencamp
Feature activation+0.000
has
Token has
Feature activation+0.000
launched
Token launched
Feature activation+0.000
its
Token its
Feature activation+0.000
âĢ
Token âĢ
Feature activation+2.572
ľ
Tokenľ
Feature activation+0.000
land
Tokenland
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.775
Ŀ
TokenĿ
Feature activation+0.000
1940
Token 1940
Feature activation+0.000
,
Token,
Feature activation+0.000
Ad
Token Ad
Feature activation+0.000
olph
Tokenolph
Feature activation+0.000
Hitler
Token Hitler
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.770
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Nazi
Token Nazi
Feature activation+0.000
troops
Token troops
Feature activation+0.000
invaded
Token invaded
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Democratic
Token Democratic
Feature activation+0.000
nominee
Token nominee
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+2.628
ľ
Tokenľ
Feature activation+0.000
wh
Tokenwh
Feature activation+0.000
olly
Tokenolly
Feature activation+0.000
unacceptable
Token unacceptable
Feature activation+0.000
.
Token.
Feature activation+0.000
economic
Token economic
Feature activation+0.000
warfare
Token warfare
Feature activation+0.000
.
Token.
Feature activation+0.000
Rob
Token Rob
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+2.736
ľ
Tokenľ
Feature activation+0.000
G
TokenG
Feature activation+0.000
oy
Tokenoy
Feature activation+0.000
im
Tokenim
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.214
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+3.032
ľ
Tokenľ
Feature activation+0.000
security
Tokensecurity
Feature activation+0.000
situation
Token situation
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.693
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ass
TokenAss
Feature activation+0.000

INTERVAL 2.207 - 2.522
CONTAINS 0.003%

in
Token in
Feature activation+0.000
G
Token G
Feature activation+0.000
ue
Tokenue
Feature activation+0.000
v
Tokenv
Feature activation+0.000
ara
Tokenara
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.422
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
death
Token death
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
one
Token one
Feature activation+0.000
in
Token in
Feature activation+0.000
Our
Token Our
Feature activation+0.000
Lady
Token Lady
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.269
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.442
ľ
Tokenľ
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
unlike
Token unlike
Feature activation+0.000
,
Token,
Feature activation+0.000
let
Token let
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.278
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
say
Token say
Feature activation+0.000
,
Token,
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Money
TokenMoney
Feature activation+0.000
That
Token That
Feature activation+0.000
Doesn
Token Doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.284
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
Die
Token Die
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
what
Token what
Feature activation+0.000
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
issue
Token issue
Feature activation+0.000
isn
Token isn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.352
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
whether
Token whether
Feature activation+0.000
Sessions
Token Sessions
Feature activation+0.000
spoke
Token spoke
Feature activation+0.000

INTERVAL 1.892 - 2.207
CONTAINS 0.003%

registrations
Token registrations
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
China
TokenChina
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.048
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
top
Token top
Feature activation+0.000
bitcoin
Token bitcoin
Feature activation+0.000
exchanges
Token exchanges
Feature activation+0.000
in
Token in
Feature activation+0.000
cases
Token cases
Feature activation+0.000
where
Token where
Feature activation+0.000
consent
Token consent
Feature activation+0.000
isn
Token isn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.935
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
involved
Token involved
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
ling
Tokenling
Feature activation+0.000
thought
Token thought
Feature activation+0.000
fully
Tokenfully
Feature activation+0.000
responded
Token responded
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+1.951
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.188
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
would
Token would
Feature activation+0.000
say
Token say
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.032
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
an
Token an
Feature activation+0.000
independent
Token independent
Feature activation+0.000
film
Token film
Feature activation+0.000
,
Token,
Feature activation+0.000
acid
Token acid
Feature activation+0.000
-
Token-
Feature activation+0.000
like
Tokenlike
Feature activation+0.000
smell
Token smell
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+2.092
Ŀ
TokenĿ
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000

INTERVAL 1.576 - 1.892
CONTAINS 0.007%

mer
Tokenmer
Feature activation+0.000
has
Token has
Feature activation+0.000
previously
Token previously
Feature activation+0.000
criticized
Token criticized
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.665
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
decision
Token decision
Feature activation+0.000
to
Token to
Feature activation+0.000
fire
Token fire
Feature activation+0.000
Ak
Token Ak
Feature activation+0.000
it
Tokenit
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+1.739
ľ
Tokenľ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
way
Token way
Feature activation+0.000
she
Token she
Feature activation+0.000
bought
Token bought
Feature activation+0.000
him
Token him
Feature activation+0.000
and
Token and
Feature activation+0.000
he
Token he
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.602
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
never
Token never
Feature activation+0.000
shown
Token shown
Feature activation+0.000
lam
Token lam
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.920
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.763
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
really
Token really
Feature activation+0.000
happy
Token happy
Feature activation+0.000
with
Token with
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
and
Token and
Feature activation+0.000
2013
Token 2013
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.817
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
received
Token received
Feature activation+0.000
across
Token across
Feature activation+0.000
-
Token-
Feature activation+0.000

INTERVAL 1.261 - 1.576
CONTAINS 0.012%

odd
Token odd
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.000
other
Token other
Feature activation+0.000
circuits
Token circuits
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.326
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
K
TokenK
Feature activation+0.000
May
Token May
Feature activation+0.000
13
Token 13
Feature activation+0.000
,
Token,
Feature activation+0.000
calling
Token calling
Feature activation+0.000
Howell
Token Howell
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.433
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
e
Token e
Feature activation+0.000
-
Token-
Feature activation+0.000
mail
Tokenmail
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
bet
Token bet
Feature activation+0.000
they
Token they
Feature activation+0.000
weren
Token weren
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.445
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
white
Token white
Feature activation+0.000
.
Token.
Feature activation+0.000
Yet
Token Yet
Feature activation+0.000
,
Token,
Feature activation+0.000
not
Token not
Feature activation+0.000
this
Token this
Feature activation+0.000
shit
Token shit
Feature activation+0.000
again
Token again
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.397
Ŀ
TokenĿ
Feature activation+0.000
of
Token of
Feature activation+0.000
unwanted
Token unwanted
Feature activation+0.000
and
Token and
Feature activation+0.000
disrespectful
Token disrespectful
Feature activation+0.000
grape
Token grape
Feature activation+0.000
pin
Token pin
Feature activation+0.000
ched
Tokenched
Feature activation+0.000
my
Token my
Feature activation+0.000
dad
Token dad
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.533
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
ass
Token ass
Feature activation+0.000
and
Token and
Feature activation+0.000
then
Token then
Feature activation+0.000

INTERVAL 0.946 - 1.261
CONTAINS 0.018%

to
Token to
Feature activation+0.000
respect
Token respect
Feature activation+0.000
their
Token their
Feature activation+0.000
differences
Token differences
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.200
Ŀ
TokenĿ
Feature activation+0.000
Imam
Token Imam
Feature activation+0.000
F
Token F
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
al
Tokenal
Feature activation+0.000
process
Token process
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.916
ľ
Tokenľ
Feature activation+0.000
Let
TokenLet
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.964
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
be
Token be
Feature activation+0.000
honest
Token honest
Feature activation+0.000
,
Token,
Feature activation+0.000
termed
Token termed
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.694
ľ
Tokenľ
Feature activation+0.000
exper
Tokenexper
Feature activation+0.000
imental
Tokenimental
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.011
Ŀ
TokenĿ
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
marked
Token marked
Feature activation+0.000
on
Token on
Feature activation+0.000
statement
Token statement
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Congress
TokenCongress
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.949
Ļ
TokenĻ
Feature activation+0.000
refusal
Token refusal
Feature activation+0.000
in
Token in
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
to
Token to
Feature activation+0.000
Pl
TokenPl
Feature activation+0.000
á
Tokená
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ás
Tokenás
Feature activation+0.000
/
Token /
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.011
Ļ
TokenĻ
Feature activation+0.000
pl
Tokenpl
Feature activation+0.000
É
TokenÉ
Feature activation+0.000
Ķ
TokenĶ
Feature activation+0.000
:
Token:
Feature activation+0.000

INTERVAL 0.631 - 0.946
CONTAINS 0.027%

and
Token and
Feature activation+0.000
was
Token was
Feature activation+0.000
convinced
Token convinced
Feature activation+0.000
they
Token they
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.698
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
winner
Token winner
Feature activation+0.000
oe
Tokenoe
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.812
ľ
Tokenľ
Feature activation+0.000
exper
Tokenexper
Feature activation+0.000
iment
Tokeniment
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.684
Ŀ
TokenĿ
Feature activation+0.000
blew
Token blew
Feature activation+0.000
up
Token up
Feature activation+0.000
.
Token.
Feature activation+0.000
Instead
Token Instead
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
county
Token county
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.718
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
public
Token public
Feature activation+0.000
information
Token information
Feature activation+0.000
officer
Token officer
Feature activation+0.000
lets
Tokenlets
Feature activation+0.000
in
Token in
Feature activation+0.000
violence
Token violence
Feature activation+0.000
that
Token that
Feature activation+0.000
Hamburg
Token Hamburg
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.684
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
interior
Token interior
Feature activation+0.000
minister
Token minister
Feature activation+0.000
called
Token called
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.770
ľ
Tokenľ
Feature activation+0.000
ought
Tokenought
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.853
Ŀ
TokenĿ
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
suggestion
Token suggestion
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000

INTERVAL 0.315 - 0.631
CONTAINS 0.049%

hasn
Token hasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.232
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.535
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Watch
TokenWatch
Feature activation+0.000
below
Token below
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
feel
Token feel
Feature activation+0.000
right
Token right
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.472
Ŀ
TokenĿ
Feature activation+0.000
she
Token she
Feature activation+0.000
added
Token added
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
it
Token it
Feature activation+0.000
suggests
Token suggests
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+0.529
ľ
Tokenľ
Feature activation+0.000
It
TokenIt
Feature activation+0.000
still
Token still
Feature activation+0.000
treats
Token treats
Feature activation+0.000
secular
Token secular
Feature activation+0.000
talk
Token talk
Feature activation+0.000
of
Token of
Feature activation+0.000
drafting
Token drafting
Feature activation+0.000
articles
Token articles
Feature activation+0.000
of
Token of
Feature activation+0.000
impeachment
Token impeachment
Feature activation+0.449
has
Token has
Feature activation+0.000
remained
Token remained
Feature activation+0.000
limited
Token limited
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
Summers
Token Summers
Feature activation+0.000
are
Token are
Feature activation+0.000
declaring
Token declaring
Feature activation+0.000
income
Token income
Feature activation+0.000
inequality
Token inequality
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.411
ľ
Tokenľ
Feature activation+0.000
a
Tokena
Feature activation+0.000
major
Token major
Feature activation+0.000
economic
Token economic
Feature activation+0.000
issue
Token issue
Feature activation+0.000

INTERVAL 0.000 - 0.315
CONTAINS 99.880%

Cal
Token Cal
Feature activation+0.000
cut
Tokencut
Feature activation+0.000
ta
Tokenta
Feature activation+0.000
or
Token or
Feature activation+0.000
Bombay
Token Bombay
Feature activation+0.000
(
Token (
Feature activation+0.000
different
Tokendifferent
Feature activation+0.000
Liverpool
Token Liverpool
Feature activation+0.000
newspapers
Token newspapers
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
Cook
Token Cook
Feature activation+0.000
also
Token also
Feature activation+0.000
emphasized
Token emphasized
Feature activation+0.000
that
Token that
Feature activation+0.000
although
Token although
Feature activation+0.000
iPad
Token iPad
Feature activation+0.000
sales
Token sales
Feature activation+0.000
were
Token were
Feature activation+0.000
having
Token having
Feature activation+0.000
negative
Token negative
Feature activation+0.000
impact
Token impact
Feature activation+0.000
should
Token should
Feature activation+0.000
reserve
Token reserve
Feature activation+0.000
judgment
Token judgment
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
't
Token't
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
had
Token had
Feature activation+0.000
running
Token running
Feature activation+0.000
trains
Token trains
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
repl
Token repl
Feature activation+0.000
icas
Tokenicas
Feature activation+0.000
ourselves
Token ourselves
Feature activation+0.000
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
can
Token can
Feature activation+0.000
't
Token't
Feature activation+0.000
test
Token test
Feature activation+0.000
the
Token the
Feature activation+0.000
ideas
Token ideas
Feature activation+0.000
we
Token we
Feature activation+0.000
've
Token've
Feature activation+0.000
come
Token come
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 H5.5: (feature 39609)

TOP ACTIVATIONS
MAX = 2.909

terrorist
Token terrorist
Feature activation+0.000
organisation
Token organisation
Feature activation+0.000
.
Token.
Feature activation+0.000
Because
Token Because
Feature activation+0.000
a
Token a
Feature activation+0.000
censored
Token censored
Feature activation+2.909
bank
Token bank
Feature activation+0.000
account
Token account
Feature activation+0.000
is
Token is
Feature activation+0.000
useless
Token useless
Feature activation+0.000
,
Token,
Feature activation+0.000
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
he
Token he
Feature activation+2.683
can
Token can
Feature activation+0.000
meet
Token meet
Feature activation+0.000
through
Token through
Feature activation+0.000
a
Token a
Feature activation+0.000
friend
Token friend
Feature activation+0.000
000
Token000
Feature activation+0.000
who
Token who
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
natural
Token natural
Feature activation+0.000
ized
Tokenized
Feature activation+2.591
in
Token in
Feature activation+0.715
the
Token the
Feature activation+0.000
coming
Token coming
Feature activation+0.000
year
Token year
Feature activation+0.000
.
Token.
Feature activation+0.000
Israel
TokenIsrael
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
National
Token National
Feature activation+0.000
Cyber
Token Cyber
Feature activation+2.538
Defense
Token Defense
Feature activation+0.000
Auth
Token Auth
Feature activation+0.000
ort
Tokenort
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
helps
Token helps
Feature activation+0.000
comes
Token comes
Feature activation+0.000
with
Token with
Feature activation+0.000
built
Token built
Feature activation+0.000
-
Token-
Feature activation+0.000
in
Tokenin
Feature activation+0.000
json
Token json
Feature activation+2.526
and
Token and
Feature activation+0.000
xml
Token xml
Feature activation+0.000
modules
Token modules
Feature activation+0.000
that
Token that
Feature activation+0.000
can
Token can
Feature activation+0.000
world
Token world
Feature activation+0.000
:
Token:
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
harassment
Token harassment
Feature activation+0.000
.
Token.
Feature activation+0.000
Germans
Token Germans
Feature activation+2.489
have
Token have
Feature activation+0.000
only
Token only
Feature activation+0.000
to
Token to
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
read
Token read
Feature activation+0.000
as
Token as
Feature activation+0.000
cis
Token cis
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
passing
Token passing
Feature activation+2.474
term
Token term
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
problematic
Token problematic
Feature activation+0.000
.
Token.
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
of
Token of
Feature activation+0.000
hacking
Token hacking
Feature activation+2.455
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+0.000
even
Token even
Feature activation+0.000
or
Token or
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
like
Token like
Feature activation+2.449
the
Token the
Feature activation+0.000
candidate
Token candidate
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
huge
Token huge
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
to
Token to
Feature activation+0.000
meet
Token meet
Feature activation+2.375
him
Token him
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
first
Token first
Feature activation+0.000
time
Token time
Feature activation+0.000
P
Token P
Feature activation+0.000
N
TokenN
Feature activation+0.000
HP
TokenHP
Feature activation+0.000
explained
Token explained
Feature activation+0.000
the
Token the
Feature activation+0.000
conservative
Token conservative
Feature activation+2.361
argument
Token argument
Feature activation+0.000
for
Token for
Feature activation+0.000
single
Token single
Feature activation+0.000
pay
Token pay
Feature activation+0.000
er
Tokener
Feature activation+0.000
impose
Token impose
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
entry
Token entry
Feature activation+0.000
of
Token of
Feature activation+0.000
aliens
Token aliens
Feature activation+2.325
any
Token any
Feature activation+0.000
restrictions
Token restrictions
Feature activation+0.000
he
Token he
Feature activation+0.000
may
Token may
Feature activation+0.000
deem
Token deem
Feature activation+0.000
interests
Token interests
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+0.000
Find
Token Find
Feature activation+0.000
a
Token a
Feature activation+0.000
drug
Token drug
Feature activation+2.304
»
Token »
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Find
TokenFind
Feature activation+0.000
out
Token out
Feature activation+0.000
asked
Token asked
Feature activation+0.000
if
Token if
Feature activation+0.000
war
Token war
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
illegal
Token illegal
Feature activation+2.287
,
Token,
Feature activation+1.483
and
Token and
Feature activation+0.000
only
Token only
Feature activation+0.000
5
Token 5
Feature activation+0.000
percent
Token percent
Feature activation+0.000
3
Token3
Feature activation+0.000
of
Token of
Feature activation+0.000
any
Token any
Feature activation+0.000
song
Token song
Feature activation+0.000
.
Token.
Feature activation+0.000
CDs
Token CDs
Feature activation+2.282
and
Token and
Feature activation+0.000
MP
Token MP
Feature activation+0.216
3
Token3
Feature activation+0.000
s
Tokens
Feature activation+0.000
are
Token are
Feature activation+0.000
devised
Token devised
Feature activation+0.000
having
Token having
Feature activation+0.000
people
Token people
Feature activation+0.000
with
Token with
Feature activation+0.000
no
Token no
Feature activation+0.000
internet
Token internet
Feature activation+2.254
access
Token access
Feature activation+0.040
in
Token in
Feature activation+0.000
mind
Token mind
Feature activation+0.000
Iris
Token Iris
Feature activation+0.000
Guard
TokenGuard
Feature activation+0.000
Driver
TokenDriver
Feature activation+0.000
's
Token's
Feature activation+0.000
licenses
Token licenses
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
suspended
Token suspended
Feature activation+2.245
or
Token or
Feature activation+0.000
revoked
Token revoked
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
variety
Token variety
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
public
Token public
Feature activation+0.000
forum
Token forum
Feature activation+0.000
.
Token.
Feature activation+0.000
Facebook
Token Facebook
Feature activation+2.210
has
Token has
Feature activation+0.975
just
Token just
Feature activation+0.000
revamped
Token revamped
Feature activation+0.000
its
Token its
Feature activation+0.000
third
Token third
Feature activation+0.000
So
Token So
Feature activation+0.000
don
Token don
Feature activation+0.000
't
Token't
Feature activation+0.000
make
Token make
Feature activation+0.000
anything
Token anything
Feature activation+0.000
dear
Token dear
Feature activation+2.195
,
Token,
Feature activation+0.610
for
Token for
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
dreadful
Token dreadful
Feature activation+0.000
17
Token17
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
Roth
Token Roth
Feature activation+2.186
401
Token 401
Feature activation+0.000
(
Token(
Feature activation+0.000
k
Tokenk
Feature activation+0.000
)
Token)
Feature activation+0.000
plan
Token plan
Feature activation+0.000

Top DFA by src position
MAX = 3.324

are
Token are
Feature activation+0.002
Top resid features:
likely
Token likely
Feature activation+0.012
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
be
Token be
Feature activation+0.001
Top resid features:
censored
Token censored
Feature activation+0.001
Top resid features:
or
Token or
Feature activation+3.324
Top resid features:
locked
Token locked
Feature activation+0.016
Top resid features:
by
Token by
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
US
Token US
Feature activation+0.002
Top resid features:
government
Token government
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
everyone
Token everyone
Feature activation+0.005
Top resid features:
can
Token can
Feature activation+0.005
Top resid features:
chose
Token chose
Feature activation-0.010
Top resid features:
his
Token his
Feature activation+0.041
Top resid features:
or
Token or
Feature activation+3.035
Top resid features:
her
Token her
Feature activation+0.056
Top resid features:
partner
Token partner
Feature activation+0.048
Top resid features:
,
Token,
Feature activation+0.042
Top resid features:
whom
Token whom
Feature activation+0.011
Top resid features:
he
Token he
Feature activation+0.042
Top resid features:
today
Token today
Feature activation+0.002
Top resid features:
for
Token for
Feature activation+0.007
Top resid features:
eventual
Token eventual
Feature activation+0.004
Top resid features:
natural
Token natural
Feature activation+0.001
Top resid features:
ization
Tokenization
Feature activation+0.002
Top resid features:
or
Token or
Feature activation+3.052
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
750
Token 750
Feature activation+0.022
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
000
Token000
Feature activation+0.009
Top resid features:
who
Token who
Feature activation+0.016
Top resid features:
when
Token when
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
talk
Token talk
Feature activation+0.001
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
cyber
Token cyber
Feature activation+0.007
Top resid features:
or
Token or
Feature activation+2.789
Top resid features:
advanced
Token advanced
Feature activation+0.007
Top resid features:
technologies
Token technologies
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
you
Token you
Feature activation-0.002
Top resid features:
are
Token are
Feature activation+0.001
Top resid features:
familiar
Token familiar
Feature activation+0.004
Top resid features:
with
Token with
Feature activation+0.007
Top resid features:
JSON
Token JSON
Feature activation+0.018
Top resid features:
or
Token or
Feature activation+2.680
Top resid features:
XML
Token XML
Feature activation+0.047
Top resid features:
,
Token,
Feature activation+0.046
Top resid features:
Python
Token Python
Feature activation+0.013
Top resid features:
comes
Token comes
Feature activation+0.010
Top resid features:
with
Token with
Feature activation+0.016
Top resid features:
game
Token game
Feature activation+0.002
Top resid features:
a
Tokena
Feature activation+0.004
Top resid features:
"
Token"
Feature activation+0.005
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
German
Token German
Feature activation+0.011
Top resid features:
or
Token or
Feature activation+2.946
Top resid features:
English
Token English
Feature activation+0.008
Top resid features:
is
Token is
Feature activation+0.003
Top resid features:
bizarre
Token bizarre
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
As
Token As
Feature activation+0.002
Top resid features:
ize
Tokenize
Feature activation+0.077
Top resid features:
anyone
Token anyone
Feature activation+0.032
Top resid features:
who
Token who
Feature activation+0.014
Top resid features:
might
Token might
Feature activation+0.005
Top resid features:
pass
Token pass
Feature activation+0.013
Top resid features:
or
Token or
Feature activation+2.722
Top resid features:
blend
Token blend
Feature activation+0.054
Top resid features:
in
Token in
Feature activation+0.019
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
as
Token as
Feature activation+0.002
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
present
Token present
Feature activation+0.002
Top resid features:
evidence
Token evidence
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.008
Top resid features:
hacking
Token hacking
Feature activation+0.027
Top resid features:
or
Token or
Feature activation+2.732
Top resid features:
voter
Token voter
Feature activation+0.017
Top resid features:
fraud
Token fraud
Feature activation+0.040
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
former
Token former
Feature activation+0.002
Top resid features:
as
Token as
Feature activation+0.008
Top resid features:
âĢ
Token âĢ
Feature activation-0.023
Top resid features:
ľ
Tokenľ
Feature activation+0.002
Top resid features:
I
TokenI
Feature activation-0.011
Top resid features:
liked
Token liked
Feature activation+0.041
Top resid features:
or
Token or
Feature activation+2.810
Top resid features:
didn
Token didn
Feature activation+0.026
Top resid features:
âĢ
TokenâĢ
Feature activation+0.014
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
t
Tokent
Feature activation+0.009
Top resid features:
like
Token like
Feature activation+0.055
Top resid features:
First
TokenFirst
Feature activation+0.000
Top resid features:
Famous
Token Famous
Feature activation-0.002
Top resid features:
Player
Token Player
Feature activation+0.010
Top resid features:
You
Token You
Feature activation+0.002
Top resid features:
Met
Token Met
Feature activation+0.006
Top resid features:
Or
Token Or
Feature activation+2.681
Top resid features:
En
Token En
Feature activation+0.002
Top resid features:
count
Tokencount
Feature activation+0.002
Top resid features:
ered
Tokenered
Feature activation+0.005
Top resid features:
:
Token:
Feature activation+0.001
Top resid features:
âĢ
Token âĢ
Feature activation-0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
conservative
Token conservative
Feature activation-0.005
Top resid features:
or
Token or
Feature activation+2.747
Top resid features:
liberal
Token liberal
Feature activation+0.009
Top resid features:
issue
Token issue
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
fact
Token fact
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
entry
Token entry
Feature activation-0.003
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
all
Token all
Feature activation+0.007
Top resid features:
aliens
Token aliens
Feature activation+0.013
Top resid features:
or
Token or
Feature activation+2.444
Top resid features:
any
Token any
Feature activation+0.010
Top resid features:
class
Token class
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
aliens
Token aliens
Feature activation+0.002
Top resid features:
as
Token as
Feature activation+0.153
Top resid features:
2010
Token 2010
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
for
Token for
Feature activation+0.001
Top resid features:
any
Token any
Feature activation+0.003
Top resid features:
drug
Token drug
Feature activation+0.025
Top resid features:
or
Token or
Feature activation+2.567
Top resid features:
B
Token B
Feature activation+0.069
Top resid features:
NF
TokenNF
Feature activation+0.004
Top resid features:
section
Token section
Feature activation+0.018
Top resid features:
that
Token that
Feature activation+0.010
Top resid features:
interests
Token interests
Feature activation+0.005
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
believed
Token believed
Feature activation+0.002
Top resid features:
war
Token war
Feature activation+0.056
Top resid features:
was
Token was
Feature activation+0.018
Top resid features:
illegal
Token illegal
Feature activation+0.018
Top resid features:
or
Token or
Feature activation+2.517
Top resid features:
if
Token if
Feature activation+0.012
Top resid features:
they
Token they
Feature activation+0.001
Top resid features:
had
Token had
Feature activation+0.002
Top resid features:
ever
Token ever
Feature activation+0.002
Top resid features:
heard
Token heard
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.002
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
your
Token your
Feature activation+0.005
Top resid features:
CD
Token CD
Feature activation-0.042
Top resid features:
or
Token or
Feature activation+2.643
Top resid features:
MP
Token MP
Feature activation-0.004
Top resid features:
3
Token3
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.032
Top resid features:
any
Token any
Feature activation+0.018
Top resid features:
song
Token song
Feature activation+0.029
Top resid features:
have
Token have
Feature activation-0.001
Top resid features:
access
Token access
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
internet
Token internet
Feature activation+0.001
Top resid features:
or
Token or
Feature activation+2.407
Top resid features:
a
Token a
Feature activation+0.046
Top resid features:
smartphone
Token smartphone
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
was
Token was
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
having
Token having
Feature activation+0.001
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
licenses
Token licenses
Feature activation-0.008
Top resid features:
suspended
Token suspended
Feature activation+0.001
Top resid features:
or
Token or
Feature activation+2.369
Top resid features:
revoked
Token revoked
Feature activation+0.017
Top resid features:
doesn
Token doesn
Feature activation+0.023
Top resid features:
't
Token't
Feature activation+0.002
Top resid features:
seem
Token seem
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
commenters
Token commenters
Feature activation+0.006
Top resid features:
log
Token log
Feature activation-0.004
Top resid features:
in
Token in
Feature activation+0.004
Top resid features:
with
Token with
Feature activation+0.002
Top resid features:
Facebook
Token Facebook
Feature activation+0.007
Top resid features:
or
Token or
Feature activation+2.586
Top resid features:
some
Token some
Feature activation+0.044
Top resid features:
equivalent
Token equivalent
Feature activation+0.005
Top resid features:
third
Token third
Feature activation+0.009
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
party
Tokenparty
Feature activation+0.023
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
see
Token see
Feature activation-0.000
Top resid features:
what
Token what
Feature activation+0.012
Top resid features:
's
Token's
Feature activation+0.007
Top resid features:
dear
Token dear
Feature activation+0.008
Top resid features:
or
Token or
Feature activation+1.480
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
see
Token see
Feature activation+0.000
Top resid features:
what
Token what
Feature activation+0.007
Top resid features:
's
Token's
Feature activation+0.006
Top resid features:
not
Token not
Feature activation+0.006
Top resid features:
âĢ
TokenâĢ
Feature activation+0.008
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
Roth
Token Roth
Feature activation+0.002
Top resid features:
or
Token or
Feature activation+2.700
Top resid features:
a
Token a
Feature activation+0.204
Top resid features:
Traditional
Token Traditional
Feature activation-0.015
Top resid features:
401
Token 401
Feature activation+0.022
Top resid features:
(
Token(
Feature activation+0.003
Top resid features:
k
Tokenk
Feature activation+0.004
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.03

Head 3: 0.04

Head 4: 0.03

Head 5: 0.55

Head 6: 0.03

Head 7: 0.03

Head 8: 0.07

Head 9: 0.06

Head 10: 0.04

Head 11: 0.03

Positive logits

or2.19

Or2.08

or1.98

/1.86

lawy1.82

/"1.77

OR1.76

/?1.74

/#1.73

+1.70

Or1.70

ORS1.68

+)1.67

1.66

orship1.65

ibble1.65

OR1.64

/$1.57

iola1.56

/,1.55

Negative logits

Pwr-1.47

Balt-1.46

Detail-1.43

emen-1.43

emy-1.42

venth-1.41

inth-1.36

humidity-1.32

hon-1.31

amina-1.28

Downs-1.25

Domain-1.25

flaw-1.24

llah-1.24

emies-1.23

Bal-1.23

setbacks-1.22

poorest-1.22

senal-1.21

nder-1.19

INTERVAL 2.618 - 2.909
CONTAINS 0.000%

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
he
Token he
Feature activation+2.683
can
Token can
Feature activation+0.000
meet
Token meet
Feature activation+0.000
through
Token through
Feature activation+0.000
a
Token a
Feature activation+0.000
friend
Token friend
Feature activation+0.000
terrorist
Token terrorist
Feature activation+0.000
organisation
Token organisation
Feature activation+0.000
.
Token.
Feature activation+0.000
Because
Token Because
Feature activation+0.000
a
Token a
Feature activation+0.000
censored
Token censored
Feature activation+2.909
bank
Token bank
Feature activation+0.000
account
Token account
Feature activation+0.000
is
Token is
Feature activation+0.000
useless
Token useless
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.327 - 2.618
CONTAINS 0.001%

P
Token P
Feature activation+0.000
N
TokenN
Feature activation+0.000
HP
TokenHP
Feature activation+0.000
explained
Token explained
Feature activation+0.000
the
Token the
Feature activation+0.000
conservative
Token conservative
Feature activation+2.361
argument
Token argument
Feature activation+0.000
for
Token for
Feature activation+0.000
single
Token single
Feature activation+0.000
pay
Token pay
Feature activation+0.000
er
Tokener
Feature activation+0.000
world
Token world
Feature activation+0.000
:
Token:
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
harassment
Token harassment
Feature activation+0.000
.
Token.
Feature activation+0.000
Germans
Token Germans
Feature activation+2.489
have
Token have
Feature activation+0.000
only
Token only
Feature activation+0.000
to
Token to
Feature activation+0.000
look
Token look
Feature activation+0.000
at
Token at
Feature activation+0.000
Israel
TokenIsrael
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
National
Token National
Feature activation+0.000
Cyber
Token Cyber
Feature activation+2.538
Defense
Token Defense
Feature activation+0.000
Auth
Token Auth
Feature activation+0.000
ort
Tokenort
Feature activation+0.000
ity
Tokenity
Feature activation+0.000
helps
Token helps
Feature activation+0.000
or
Token or
Feature activation+0.000
didn
Token didn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
like
Token like
Feature activation+2.449
the
Token the
Feature activation+0.000
candidate
Token candidate
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
read
Token read
Feature activation+0.000
as
Token as
Feature activation+0.000
cis
Token cis
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
passing
Token passing
Feature activation+2.474
term
Token term
Feature activation+0.000
is
Token is
Feature activation+0.000
so
Token so
Feature activation+0.000
problematic
Token problematic
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 2.036 - 2.327
CONTAINS 0.003%

including
Token including
Feature activation+0.000
those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
were
Token were
Feature activation+0.000
neither
Token neither
Feature activation+0.000
Jewish
Token Jewish
Feature activation+2.107
nor
Token nor
Feature activation+0.000
Black
Token Black
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
a
Token a
Feature activation+0.000
The
Token The
Feature activation+0.000
Marvel
Token Marvel
Feature activation+0.000
ous
Tokenous
Feature activation+0.000
Cou
Token Cou
Feature activation+0.000
der
Tokender
Feature activation+0.000
c
Tokenc
Feature activation+2.129
.
Token.
Feature activation+0.000
Wikipedia
Token Wikipedia
Feature activation+0.000
says
Token says
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
public
Token public
Feature activation+0.000
forum
Token forum
Feature activation+0.000
.
Token.
Feature activation+0.000
Facebook
Token Facebook
Feature activation+2.210
has
Token has
Feature activation+0.975
just
Token just
Feature activation+0.000
revamped
Token revamped
Feature activation+0.000
its
Token its
Feature activation+0.000
third
Token third
Feature activation+0.000
for
Token for
Feature activation+0.000
private
Token private
Feature activation+0.000
universities
Token universities
Feature activation+0.000
to
Token to
Feature activation+0.000
not
Token not
Feature activation+0.000
record
Token record
Feature activation+2.110
the
Token the
Feature activation+0.000
testimonies
Token testimonies
Feature activation+0.000
of
Token of
Feature activation+0.000
students
Token students
Feature activation+0.000
involved
Token involved
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
future
Token future
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
Chiefs
Token Chiefs
Feature activation+2.124
or
Token or
Feature activation+0.387
any
Token any
Feature activation+0.000
other
Token other
Feature activation+0.000
teams
Token teams
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.745 - 2.036
CONTAINS 0.003%

Ċ
TokenĊ
Feature activation+0.000
Often
TokenOften
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
donated
Token donated
Feature activation+0.000
goods
Token goods
Feature activation+1.793
or
Token or
Feature activation+0.000
clothes
Token clothes
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
charity
Token charity
Feature activation+0.195
34
Token34
Feature activation+0.000
,
Token,
Feature activation+0.000
8
Token8
Feature activation+0.000
76
Token76
Feature activation+0.000
Staff
Token Staff
Feature activation+0.000
nurse
Token nurse
Feature activation+1.918
,
Token,
Feature activation+0.438
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
theatre
Token theatre
Feature activation+0.000
nurse
Token nurse
Feature activation+0.801
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
political
Token political
Feature activation+0.000
king
Token king
Feature activation+0.000
or
Token or
Feature activation+0.000
king
Token king
Feature activation+1.887
maker
Tokenmaker
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
pres
Token pres
Feature activation+0.000
ides
Tokenides
Feature activation+0.000
decision
Token decision
Feature activation+0.000
between
Token between
Feature activation+0.000
offshore
Token offshore
Feature activation+0.000
or
Token or
Feature activation+0.000
on
Token on
Feature activation+0.000
shore
Tokenshore
Feature activation+1.916
oil
Token oil
Feature activation+0.000
,
Token,
Feature activation+0.000
wind
Token wind
Feature activation+0.000
,
Token,
Feature activation+0.000
solar
Token solar
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
understood
Token understood
Feature activation+0.000
as
Token as
Feature activation+0.000
any
Token any
Feature activation+0.000
action
Token action
Feature activation+1.824
done
Token done
Feature activation+0.279
with
Token with
Feature activation+0.131
the
Token the
Feature activation+0.000
sense
Token sense
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 1.455 - 1.745
CONTAINS 0.004%

you
Token you
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
like
Token like
Feature activation+1.556
what
Token what
Feature activation+0.000
Christians
Token Christians
Feature activation+0.000
believe
Token believe
Feature activation+0.000
.
Token.
Feature activation+0.000
Total
Token Total
Feature activation+0.000
look
Token look
Feature activation+0.000
back
Token back
Feature activation+0.000
on
Token on
Feature activation+0.000
to
Token to
Feature activation+0.000
clarify
Token clarify
Feature activation+0.000
thoughts
Token thoughts
Feature activation+1.726
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Link
TokenLink
Feature activation+0.000
:
Token:
Feature activation+0.000
T
Token T
Feature activation+0.000
Appeal
Token Appeal
Feature activation+0.000
or
Token or
Feature activation+0.000
elements
Token elements
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Appeal
Token Appeal
Feature activation+1.694
are
Token are
Feature activation+0.000
successful
Token successful
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Court
Token Court
Feature activation+0.000
one
Token one
Feature activation+0.000
for
Token for
Feature activation+0.000
wiping
Token wiping
Feature activation+0.000
out
Token out
Feature activation+0.000
all
Token all
Feature activation+0.000
tanks
Token tanks
Feature activation+1.651
,
Token,
Feature activation+0.696
but
Token but
Feature activation+0.000
this
Token this
Feature activation+0.000
one
Token one
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
completely
Token completely
Feature activation+0.000
free
Token free
Feature activation+0.000
tert
Token tert
Feature activation+0.000
iary
Tokeniary
Feature activation+0.000
education
Token education
Feature activation+1.513
system
Token system
Feature activation+0.000
.
Token.
Feature activation+0.000
NZ
Token NZ
Feature activation+0.000
First
Token First
Feature activation+0.000
wants
Token wants
Feature activation+0.000

INTERVAL 1.164 - 1.455
CONTAINS 0.004%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Cooking
Token Cooking
Feature activation+0.000
Corner
Token Corner
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+1.256
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
name
Token name
Feature activation+0.000
percent
Token percent
Feature activation+0.000
,
Token,
Feature activation+0.000
strongly
Token strongly
Feature activation+0.000
or
Token or
Feature activation+0.000
somewhat
Token somewhat
Feature activation+0.000
support
Token support
Feature activation+1.181
the
Token the
Feature activation+0.000
plan
Token plan
Feature activation+0.000
while
Token while
Feature activation+0.000
31
Token 31
Feature activation+0.000
.
Token.
Feature activation+0.000
federal
Token federal
Feature activation+0.000
government
Token government
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
State
Token State
Feature activation+1.310
in
Token in
Feature activation+0.000
Iraq
Token Iraq
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Levant
Token Levant
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
zero
Token zero
Feature activation+1.434
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
simultaneously
Token simultaneously
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
signature
Token signature
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
or
Token or
Feature activation+0.000
her
Token her
Feature activation+0.000
parent
Token parent
Feature activation+1.256
or
Token or
Feature activation+0.000
legal
Token legal
Feature activation+0.000
guardian
Token guardian
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.873 - 1.164
CONTAINS 0.007%

stuff
Token stuff
Feature activation+0.000
shows
Token shows
Feature activation+0.000
or
Token or
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
't
Token't
Feature activation+0.000
show
Token show
Feature activation+0.963
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
And
TokenAnd
Feature activation+0.000
I
Token I
Feature activation+0.000
so
Token so
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
sounds
Token sounds
Feature activation+0.000
like
Token like
Feature activation+0.000
door
Token door
Feature activation+1.073
rr
Tokenrr
Feature activation+0.000
rr
Tokenrr
Feature activation+0.000
hh
Tokenhh
Feature activation+0.000
or
Token or
Feature activation+0.000
floor
Token floor
Feature activation+0.315
steer
Token steer
Feature activation+0.000
clear
Token clear
Feature activation+0.000
of
Token of
Feature activation+0.000
phony
Token phony
Feature activation+0.000
or
Token or
Feature activation+0.000
counterfeit
Token counterfeit
Feature activation+1.100
products
Token products
Feature activation+0.000
being
Token being
Feature activation+0.000
sold
Token sold
Feature activation+0.000
online
Token online
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
kicker
Token kicker
Feature activation+0.000
or
Token or
Feature activation+0.019
pun
Token pun
Feature activation+0.898
ter
Tokenter
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
kick
Token kick
Feature activation+0.036
Ċ
TokenĊ
Feature activation+0.000
websites
Token websites
Feature activation+0.000
/
Token/
Feature activation+0.000
apps
Tokenapps
Feature activation+0.000
offering
Token offering
Feature activation+0.000
nominal
Token nominal
Feature activation+0.000
compensation
Token compensation
Feature activation+0.900
to
Token to
Feature activation+0.000
users
Token users
Feature activation+0.000
to
Token to
Feature activation+0.000
bypass
Token bypass
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.582 - 0.873
CONTAINS 0.009%

âĢĶ
Token âĢĶ
Feature activation+0.000
are
Token are
Feature activation+0.000
recommended
Token recommended
Feature activation+0.000
to
Token to
Feature activation+0.000
treat
Token treat
Feature activation+0.000
gon
Token gon
Feature activation+0.679
orr
Tokenorr
Feature activation+0.000
hea
Tokenhea
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.000
usually
Token usually
Feature activation+0.000
nurse
Token nurse
Feature activation+1.918
,
Token,
Feature activation+0.438
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
theatre
Token theatre
Feature activation+0.000
nurse
Token nurse
Feature activation+0.801
7
Token 7
Feature activation+0.000
£
Token £
Feature activation+0.000
31
Token31
Feature activation+0.000
,
Token,
Feature activation+0.000
07
Token07
Feature activation+0.000
cher
Tokencher
Feature activation+0.000
n
Tokenn
Feature activation+0.000
von
Token von
Feature activation+0.000
18
Token 18
Feature activation+0.000
28
Token28
Feature activation+0.000
bis
Token bis
Feature activation+0.868
2008
Token 2008
Feature activation+0.000
er
Token er
Feature activation+0.000
w
Tokenw
Feature activation+0.000
ä
Tokenä
Feature activation+0.000
h
Tokenh
Feature activation+0.000
We
Token We
Feature activation+0.000
have
Token have
Feature activation+0.000
determined
Token determined
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
service
Token service
Feature activation+0.650
(
Token(
Feature activation+0.000
s
Tokens
Feature activation+0.873
)
Token)
Feature activation+2.118
are
Token are
Feature activation+0.033
not
Token not
Feature activation+0.000
ways
Token ways
Feature activation+0.000
that
Token that
Feature activation+0.000
seem
Token seem
Feature activation+0.000
strange
Token strange
Feature activation+0.000
or
Token or
Feature activation+0.000
bizarre
Token bizarre
Feature activation+0.807
and
Token and
Feature activation+0.000
whether
Token whether
Feature activation+0.000
they
Token they
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 0.291 - 0.582
CONTAINS 0.016%

flies
Token flies
Feature activation+2.003
,
Token,
Feature activation+0.000
car
Token car
Feature activation+0.000
r
Tokenr
Feature activation+0.000
ion
Tokenion
Feature activation+0.000
flies
Token flies
Feature activation+0.319
and
Token and
Feature activation+0.000
beetles
Token beetles
Feature activation+0.000
.
Token.
Feature activation+0.000
Because
Token Because
Feature activation+0.000
of
Token of
Feature activation+0.000
swarm
Token swarm
Feature activation+0.000
strategies
Token strategies
Feature activation+0.000
.
Token.
Feature activation+0.000
Tor
Token Tor
Feature activation+0.000
por
Tokenpor
Feature activation+0.000
Orb
Token Orb
Feature activation+0.501
because
Token because
Feature activation+0.000
it
Token it
Feature activation+0.000
shuts
Token shuts
Feature activation+0.000
down
Token down
Feature activation+0.000
entire
Token entire
Feature activation+0.000
German
Token German
Feature activation+0.000
parliament
Token parliament
Feature activation+0.000
ahead
Token ahead
Feature activation+0.000
of
Token of
Feature activation+0.000
an
Token an
Feature activation+0.000
EU
Token EU
Feature activation+0.487
summit
Token summit
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.000
British
Token British
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
as
Token as
Feature activation+0.000
toxic
Token toxic
Feature activation+0.000
or
Token or
Feature activation+0.000
not
Token not
Feature activation+0.000
toxic
Token toxic
Feature activation+2.151
,
Token,
Feature activation+0.293
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
whether
Token whether
Feature activation+0.000
they
Token they
Feature activation+0.000
b
Token b
Feature activation+0.000
ien
Tokenien
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
illance
Tokenillance
Feature activation+0.000
"
Token"
Feature activation+0.000
or
Token or
Feature activation+0.427
in
Token in
Feature activation+0.000
English
Token English
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
Given
TokenGiven
Feature activation+0.000

INTERVAL 0.000 - 0.291
CONTAINS 99.953%

new
Token new
Feature activation+0.000
baby
Token baby
Feature activation+0.000
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
filming
Token filming
Feature activation+0.000
two
Token two
Feature activation+0.000
shows
Token shows
Feature activation+0.000
,
Token,
Feature activation+0.000
running
Token running
Feature activation+0.000
the
Token the
Feature activation+0.000
site
Token site
Feature activation+0.000
a
Token a
Feature activation+0.000
traditional
Token traditional
Feature activation+0.000
town
Token town
Feature activation+0.000
hall
Token hall
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
calendar
Token calendar
Feature activation+0.000
.
Token.
Feature activation+0.000
Anyone
Token Anyone
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
may
Token may
Feature activation+0.000
be
Token be
Feature activation+0.000
found
Token found
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
website
Token website
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
District
Token District
Feature activation+0.000
Court
Token Court
Feature activation+0.000
for
Token for
Feature activation+0.000
bas
Tokenbas
Feature activation+0.000
ically
Tokenically
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
config
Tokenconfig
Feature activation+0.000
ured
Tokenured
Feature activation+0.000
VM
Token VM
Feature activation+0.000
which
Token which
Feature activation+0.000
includes
Token includes
Feature activation+0.000
few
Token few
Feature activation+0.000
exceptions
Token exceptions
Feature activation+0.000
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
just
Token just
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
that
Token that
Feature activation+0.000
comes
Token comes
Feature activation+0.000
even
Token even
Feature activation+0.000
close
Token close
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 H5.5: (feature 28928)

TOP ACTIVATIONS
MAX = 1.974

found
Token found
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
men
Token men
Feature activation+0.000
ager
Tokenager
Feature activation+1.974
ie
Tokenie
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
35
Token 35
Feature activation+0.000
gage
Tokengage
Feature activation+0.000
servic
Token servic
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
."
Token."
Feature activation+0.000
Serv
Token Serv
Feature activation+1.480
ic
Tokenic
Feature activation+1.875
ers
Tokeners
Feature activation+0.000
have
Token have
Feature activation+0.000
committed
Token committed
Feature activation+0.000
widespread
Token widespread
Feature activation+0.000
fraud
Token fraud
Feature activation+0.000
to
Token to
Feature activation+0.000
check
Token check
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
wind
Token wind
Feature activation+0.000
sur
Tokensur
Feature activation+1.837
f
Tokenf
Feature activation+1.827
ers
Tokeners
Feature activation+0.540
were
Token were
Feature activation+0.170
fine
Token fine
Feature activation+0.000
,
Token,
Feature activation+0.000
check
Token check
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
wind
Token wind
Feature activation+0.000
sur
Tokensur
Feature activation+1.837
f
Tokenf
Feature activation+1.827
ers
Tokeners
Feature activation+0.540
were
Token were
Feature activation+0.170
fine
Token fine
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
chore
Token chore
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Well
TokenWell
Feature activation+0.000
,
Token,
Feature activation+0.000
shovel
Token shovel
Feature activation+1.804
ing
Tokening
Feature activation+0.000
dry
Token dry
Feature activation+0.000
compost
Token compost
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
:
Token:
Feature activation+0.000
Wikimedia
Token Wikimedia
Feature activation+0.000
Commons
Token Commons
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
O
TokenO
Feature activation+1.773
tto
Tokentto
Feature activation+0.935
ia
Tokenia
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Disc
TokenDisc
Feature activation+0.000
drops
Tokendrops
Feature activation+0.000
and
Token and
Feature activation+0.000
center
Token center
Feature activation+0.000
pieces
Tokenpieces
Feature activation+0.000
.
Token.
Feature activation+0.000
Summon
Token Summon
Feature activation+1.735
ing
Tokening
Feature activation+0.000
would
Token would
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
become
Token become
Feature activation+0.000
more
Token more
Feature activation+0.000
to
Token to
Feature activation+0.000
confirm
Token confirm
Feature activation+0.000
what
Token what
Feature activation+0.000
those
Token those
Feature activation+0.000
cat
Token cat
Feature activation+0.000
whisk
Token whisk
Feature activation+1.704
ers
Tokeners
Feature activation+0.000
are
Token are
Feature activation+0.000
telling
Token telling
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
yo
Tokenyo
Feature activation+0.000
Fine
Token Fine
Feature activation+0.000
Cannabis
Token Cannabis
Feature activation+0.000
Disp
Token Disp
Feature activation+0.112
ens
Tokenens
Feature activation+1.692
ary
Tokenary
Feature activation+0.000
in
Token in
Feature activation+0.000
Las
Token Las
Feature activation+0.000
Vegas
Token Vegas
Feature activation+0.000
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
fantastic
Token fantastic
Feature activation+0.000
concept
Token concept
Feature activation+0.000
F
Token F
Feature activation+0.000
1
Token1
Feature activation+0.000
liver
Token liver
Feature activation+1.679
ies
Tokenies
Feature activation+0.001
,
Token,
Feature activation+0.000
adding
Token adding
Feature activation+0.000
proof
Token proof
Feature activation+0.000
to
Token to
Feature activation+0.000
-
Token-
Feature activation+0.000
on
Tokenon
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
RC
Token RC
Feature activation+0.000
craw
Token craw
Feature activation+1.644
ler
Tokenler
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Con
TokenCon
Feature activation+0.003
+
Token +
Feature activation+0.000
2
Token2
Feature activation+0.000
Source
Token Source
Feature activation+0.000
Magic
Token Magic
Feature activation+0.000
,
Token,
Feature activation+0.000
Channel
Token Channel
Feature activation+1.615
ers
Tokeners
Feature activation+0.000
Authority
Token Authority
Feature activation+0.000
2
Token 2
Feature activation+0.000
1
Token 1
Feature activation+0.000
st
Tokenst
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Channel
TokenChannel
Feature activation+0.000
er
Tokener
Feature activation+0.000
The
Token The
Feature activation+0.000
Channel
Token Channel
Feature activation+1.595
er
Tokener
Feature activation+0.000
Level
Token Level
Feature activation+0.000
Prof
Token Prof
Feature activation+0.000
iciency
Tokeniciency
Feature activation+0.000
Bonus
Token Bonus
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
Man
TokenMan
Feature activation+0.013
ate
Tokenate
Feature activation+1.525
e
Tokene
Feature activation+0.000
popping
Token popping
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
1995
Token1995
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sum
TokenSum
Feature activation+0.170
mon
Tokenmon
Feature activation+1.481
ing
Tokening
Feature activation+0.000
is
Token is
Feature activation+0.000
important
Token important
Feature activation+0.000
to
Token to
Feature activation+0.000
dungeon
Token dungeon
Feature activation+0.000
mort
Tokenmort
Feature activation+0.000
gage
Tokengage
Feature activation+0.000
servic
Token servic
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
."
Token."
Feature activation+0.000
Serv
Token Serv
Feature activation+1.480
ic
Tokenic
Feature activation+1.875
ers
Tokeners
Feature activation+0.000
have
Token have
Feature activation+0.000
committed
Token committed
Feature activation+0.000
widespread
Token widespread
Feature activation+0.000
national
Token national
Feature activation+0.000
development
Token development
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Commission
TokenCommission
Feature activation+1.447
ing
Tokening
Feature activation+0.000
of
Token of
Feature activation+0.000
INS
Token INS
Feature activation+0.000
Vaj
Token Vaj
Feature activation+0.000
rak
Tokenrak
Feature activation+0.000
Mile
Token Mile
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Tat
Token Tat
Feature activation+1.447
ters
Tokenters
Feature activation+0.000
alls
Tokenalls
Feature activation+0.000
Horse
Token Horse
Feature activation+0.000
Sales
Token Sales
Feature activation+0.000
are
Token are
Feature activation+0.000
average
Tokenaverage
Feature activation+0.000
popularity
Token popularity
Feature activation+0.000
among
Token among
Feature activation+0.000
cord
Token cord
Feature activation+0.000
-
Token-
Feature activation+0.000
cut
Tokencut
Feature activation+1.437
ters
Tokenters
Feature activation+0.000
are
Token are
Feature activation+0.000
broadcast
Token broadcast
Feature activation+0.000
programs
Token programs
Feature activation+0.000
that
Token that
Feature activation+0.000
outline
Token outline
Feature activation+0.000
and
Token and
Feature activation+0.000
orientation
Token orientation
Feature activation+0.000
so
Token so
Feature activation+0.000
the
Token the
Feature activation+0.000
project
Token project
Feature activation+1.406
ors
Tokenors
Feature activation+0.000
can
Token can
Feature activation+0.000
overlay
Token overlay
Feature activation+0.000
a
Token a
Feature activation+0.000
virtual
Token virtual
Feature activation+0.000

Top DFA by src position
MAX = 2.499

original
Token original
Feature activation-0.000
Top resid features:
form
Token form
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
men
Token men
Feature activation+0.001
Top resid features:
ager
Tokenager
Feature activation+0.001
Top resid features:
ies
Tokenies
Feature activation+2.499
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.000
Top resid features:
have
Tokenhave
Feature activation+0.000
Top resid features:
been
Token been
Feature activation-0.000
Top resid features:
around
Token around
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
called
Token called
Feature activation-0.007
Top resid features:
"
Token "
Feature activation-0.002
Top resid features:
mort
Tokenmort
Feature activation+0.005
Top resid features:
gage
Tokengage
Feature activation-0.005
Top resid features:
servic
Token servic
Feature activation+0.000
Top resid features:
ers
Tokeners
Feature activation+2.271
Top resid features:
."
Token."
Feature activation+0.007
Top resid features:
Serv
Token Serv
Feature activation+0.144
Top resid features:
ic
Tokenic
Feature activation-0.000
Top resid features:
ers
Tokeners
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
five
Token five
Feature activation-0.001
Top resid features:
wind
Token wind
Feature activation+0.009
Top resid features:
sur
Tokensur
Feature activation+0.019
Top resid features:
f
Tokenf
Feature activation+0.051
Top resid features:
ers
Tokeners
Feature activation+2.215
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
sails
Token sails
Feature activation+0.014
Top resid features:
down
Token down
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
five
Token five
Feature activation+0.000
Top resid features:
wind
Token wind
Feature activation+0.005
Top resid features:
sur
Tokensur
Feature activation+0.060
Top resid features:
f
Tokenf
Feature activation+0.002
Top resid features:
ers
Tokeners
Feature activation+2.269
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
sails
Token sails
Feature activation+0.019
Top resid features:
down
Token down
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
move
Token move
Feature activation-0.003
Top resid features:
around
Token around
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Sho
Token Sho
Feature activation+0.003
Top resid features:
vel
Tokenvel
Feature activation+0.001
Top resid features:
ing
Tokening
Feature activation+2.291
Top resid features:
wet
Token wet
Feature activation-0.034
Top resid features:
compost
Token compost
Feature activation+0.009
Top resid features:
is
Token is
Feature activation-0.009
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
chore
Token chore
Feature activation-0.010
Top resid features:
body
Token body
Feature activation+0.001
Top resid features:
concealed
Token concealed
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
Otto
Token Otto
Feature activation-0.010
Top resid features:
ia
Tokenia
Feature activation+2.206
Top resid features:
worm
Token worm
Feature activation-0.006
Top resid features:
would
Token would
Feature activation-0.009
Top resid features:
lur
Token lur
Feature activation-0.001
Top resid features:
k
Tokenk
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.000
Top resid features:
)
Token)
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Sum
TokenSum
Feature activation+0.002
Top resid features:
mon
Tokenmon
Feature activation+0.006
Top resid features:
ing
Tokening
Feature activation+1.617
Top resid features:
is
Token is
Feature activation+0.016
Top resid features:
important
Token important
Feature activation-0.000
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
dungeon
Token dungeon
Feature activation+0.003
Top resid features:
synth
Token synth
Feature activation+0.021
Top resid features:
her
Token her
Feature activation-0.000
Top resid features:
âĢ
Token âĢ
Feature activation-0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
wh
Tokenwh
Feature activation+0.001
Top resid features:
isk
Tokenisk
Feature activation+0.002
Top resid features:
er
Tokener
Feature activation+2.191
Top resid features:
gram
Tokengram
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ŀ
TokenĿ
Feature activation-0.001
Top resid features:
against
Token against
Feature activation-0.006
Top resid features:
her
Token her
Feature activation-0.003
Top resid features:
ate
Tokenate
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.003
Top resid features:
Dis
TokenDis
Feature activation+0.001
Top resid features:
p
Tokenp
Feature activation+0.000
Top resid features:
ens
Tokenens
Feature activation-0.001
Top resid features:
aries
Tokenaries
Feature activation+2.316
Top resid features:
trading
Token trading
Feature activation-0.002
Top resid features:
free
Token free
Feature activation+0.000
Top resid features:
weed
Token weed
Feature activation+0.001
Top resid features:
for
Token for
Feature activation-0.001
Top resid features:
holiday
Token holiday
Feature activation-0.000
Top resid features:
it
Token it
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
modern
Token modern
Feature activation+0.001
Top resid features:
liver
Token liver
Feature activation+0.005
Top resid features:
ies
Tokenies
Feature activation+2.067
Top resid features:
are
Token are
Feature activation+0.009
Top resid features:
boring
Token boring
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
unimagin
Token unimagin
Feature activation-0.000
Top resid features:
ative
Tokenative
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Qu
TokenQu
Feature activation+0.003
Top resid features:
ad
Tokenad
Feature activation+0.000
Top resid features:
rock
Tokenrock
Feature activation+0.007
Top resid features:
er
Tokener
Feature activation+1.926
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
a
Token a
Feature activation-0.004
Top resid features:
contro
Token contro
Feature activation+0.003
Top resid features:
ll
Tokenll
Feature activation+0.006
Top resid features:
able
Tokenable
Feature activation+0.036
Top resid features:
obvious
Token obvious
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Channel
TokenChannel
Feature activation-0.000
Top resid features:
er
Tokener
Feature activation+1.323
Top resid features:
The
Token The
Feature activation-0.001
Top resid features:
Channel
Token Channel
Feature activation+0.000
Top resid features:
er
Tokener
Feature activation+0.699
Top resid features:
Level
Token Level
Feature activation-0.007
Top resid features:
Prof
Token Prof
Feature activation-0.002
Top resid features:
obvious
Token obvious
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Channel
TokenChannel
Feature activation+0.000
Top resid features:
er
Tokener
Feature activation+2.152
Top resid features:
The
Token The
Feature activation-0.046
Top resid features:
Channel
Token Channel
Feature activation-0.014
Top resid features:
er
Tokener
Feature activation+0.000
Top resid features:
Level
Token Level
Feature activation+0.000
Top resid features:
Prof
Token Prof
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
third
Token third
Feature activation+0.000
Top resid features:
man
Token man
Feature activation-0.003
Top resid features:
ate
Tokenate
Feature activation+0.002
Top resid features:
e
Tokene
Feature activation+1.407
Top resid features:
made
Token made
Feature activation-0.004
Top resid features:
its
Token its
Feature activation-0.001
Top resid features:
way
Token way
Feature activation-0.000
Top resid features:
over
Token over
Feature activation+0.001
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Sum
TokenSum
Feature activation+0.010
Top resid features:
mon
Tokenmon
Feature activation+0.022
Top resid features:
ing
Tokening
Feature activation+1.677
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.211
Top resid features:
Min
Token Min
Feature activation-0.005
Top resid features:
as
Tokenas
Feature activation+0.000
Top resid features:
Morg
Token Morg
Feature activation+0.003
Top resid features:
ul
Tokenul
Feature activation-0.001
Top resid features:
called
Token called
Feature activation-0.008
Top resid features:
"
Token "
Feature activation-0.003
Top resid features:
mort
Tokenmort
Feature activation+0.006
Top resid features:
gage
Tokengage
Feature activation-0.014
Top resid features:
servic
Token servic
Feature activation+0.002
Top resid features:
ers
Tokeners
Feature activation+1.980
Top resid features:
."
Token."
Feature activation+0.018
Top resid features:
Serv
Token Serv
Feature activation-0.001
Top resid features:
ic
Tokenic
Feature activation+0.000
Top resid features:
ers
Tokeners
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
read
Token read
Feature activation+0.004
Top resid features:
out
Token out
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
Commission
Token Commission
Feature activation+0.018
Top resid features:
ing
Tokening
Feature activation+1.820
Top resid features:
Warrant
Token Warrant
Feature activation+0.015
Top resid features:
and
Token and
Feature activation+0.012
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
Naval
Token Naval
Feature activation-0.001
Top resid features:
ens
Token ens
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:
Welcome
TokenWelcome
Feature activation+0.002
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
Tat
Token Tat
Feature activation+0.014
Top resid features:
ters
Tokenters
Feature activation+1.652
Top resid features:
alls
Tokenalls
Feature activation+0.112
Top resid features:
&
Token &
Feature activation+0.046
Top resid features:
The
Token The
Feature activation+0.002
Top resid features:
Red
Token Red
Feature activation+0.033
Top resid features:
Mile
Token Mile
Feature activation+0.028
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
called
Tokencalled
Feature activation-0.000
Top resid features:
cord
Token cord
Feature activation+0.020
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
cut
Tokencut
Feature activation-0.001
Top resid features:
ters
Tokenters
Feature activation+1.996
Top resid features:
are
Token are
Feature activation+0.008
Top resid features:
more
Token more
Feature activation+0.001
Top resid features:
likely
Token likely
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
mounted
Tokenmounted
Feature activation+0.001
Top resid features:
cameras
Token cameras
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
project
Token project
Feature activation+0.014
Top resid features:
ors
Tokenors
Feature activation+1.865
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
overlay
Token overlay
Feature activation+0.003
Top resid features:
cooking
Token cooking
Feature activation+0.002
Top resid features:
instructions
Token instructions
Feature activation+0.003
Top resid features:
on
Token on
Feature activation-0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.08

Head 2: 0.03

Head 3: 0.03

Head 4: 0.03

Head 5: 0.55

Head 6: 0.04

Head 7: 0.02

Head 8: 0.04

Head 9: 0.06

Head 10: 0.05

Head 11: 0.03

Positive logits

icons2.50

ers2.42

eria2.40

elines2.39

ings2.33

eters2.28

oons2.27

aters2.25

zon2.17

services2.17

rs2.15

ales2.15

inar2.13

2.13

iaries2.13

gers2.13

keys2.11

enda2.09

ees2.09

2.09

Negative logits

quickShipAvailable-1.95

intervening-1.70

wast-1.67

McF-1.63

afore-1.61

horr-1.60

FML-1.58

acebook-1.57

heightened-1.55

wi-1.55

dh-1.55

bewild-1.55

Wi-1.55

Gw-1.55

Sur-1.53

disbelief-1.53

Broad-1.53

Mub-1.53

EStream-1.52

assetsadobe-1.52

INTERVAL 1.777 - 1.974
CONTAINS 0.001%

found
Token found
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
men
Token men
Feature activation+0.000
ager
Tokenager
Feature activation+1.974
ie
Tokenie
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
35
Token 35
Feature activation+0.000
gage
Tokengage
Feature activation+0.000
servic
Token servic
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
."
Token."
Feature activation+0.000
Serv
Token Serv
Feature activation+1.480
ic
Tokenic
Feature activation+1.875
ers
Tokeners
Feature activation+0.000
have
Token have
Feature activation+0.000
committed
Token committed
Feature activation+0.000
widespread
Token widespread
Feature activation+0.000
fraud
Token fraud
Feature activation+0.000
chore
Token chore
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Well
TokenWell
Feature activation+0.000
,
Token,
Feature activation+0.000
shovel
Token shovel
Feature activation+1.804
ing
Tokening
Feature activation+0.000
dry
Token dry
Feature activation+0.000
compost
Token compost
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
to
Token to
Feature activation+0.000
check
Token check
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
wind
Token wind
Feature activation+0.000
sur
Tokensur
Feature activation+1.837
f
Tokenf
Feature activation+1.827
ers
Tokeners
Feature activation+0.540
were
Token were
Feature activation+0.170
fine
Token fine
Feature activation+0.000
,
Token,
Feature activation+0.000
check
Token check
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
wind
Token wind
Feature activation+0.000
sur
Tokensur
Feature activation+1.837
f
Tokenf
Feature activation+1.827
ers
Tokeners
Feature activation+0.540
were
Token were
Feature activation+0.170
fine
Token fine
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000

INTERVAL 1.579 - 1.777
CONTAINS 0.001%

-
Token-
Feature activation+0.000
on
Tokenon
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
RC
Token RC
Feature activation+0.000
craw
Token craw
Feature activation+1.644
ler
Tokenler
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Con
TokenCon
Feature activation+0.003
drops
Tokendrops
Feature activation+0.000
and
Token and
Feature activation+0.000
center
Token center
Feature activation+0.000
pieces
Tokenpieces
Feature activation+0.000
.
Token.
Feature activation+0.000
Summon
Token Summon
Feature activation+1.735
ing
Tokening
Feature activation+0.000
would
Token would
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
become
Token become
Feature activation+0.000
more
Token more
Feature activation+0.000
to
Token to
Feature activation+0.000
confirm
Token confirm
Feature activation+0.000
what
Token what
Feature activation+0.000
those
Token those
Feature activation+0.000
cat
Token cat
Feature activation+0.000
whisk
Token whisk
Feature activation+1.704
ers
Tokeners
Feature activation+0.000
are
Token are
Feature activation+0.000
telling
Token telling
Feature activation+0.000
you
Token you
Feature activation+0.000
.
Token.
Feature activation+0.000
some
Token some
Feature activation+0.000
fantastic
Token fantastic
Feature activation+0.000
concept
Token concept
Feature activation+0.000
F
Token F
Feature activation+0.000
1
Token1
Feature activation+0.000
liver
Token liver
Feature activation+1.679
ies
Tokenies
Feature activation+0.001
,
Token,
Feature activation+0.000
adding
Token adding
Feature activation+0.000
proof
Token proof
Feature activation+0.000
to
Token to
Feature activation+0.000
:
Token:
Feature activation+0.000
Wikimedia
Token Wikimedia
Feature activation+0.000
Commons
Token Commons
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
O
TokenO
Feature activation+1.773
tto
Tokentto
Feature activation+0.935
ia
Tokenia
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Disc
TokenDisc
Feature activation+0.000

INTERVAL 1.382 - 1.579
CONTAINS 0.001%

outline
Token outline
Feature activation+0.000
and
Token and
Feature activation+0.000
orientation
Token orientation
Feature activation+0.000
so
Token so
Feature activation+0.000
the
Token the
Feature activation+0.000
project
Token project
Feature activation+1.406
ors
Tokenors
Feature activation+0.000
can
Token can
Feature activation+0.000
overlay
Token overlay
Feature activation+0.000
a
Token a
Feature activation+0.000
virtual
Token virtual
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
Man
TokenMan
Feature activation+0.013
ate
Tokenate
Feature activation+1.525
e
Tokene
Feature activation+0.000
popping
Token popping
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
national
Token national
Feature activation+0.000
development
Token development
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Commission
TokenCommission
Feature activation+1.447
ing
Tokening
Feature activation+0.000
of
Token of
Feature activation+0.000
INS
Token INS
Feature activation+0.000
Vaj
Token Vaj
Feature activation+0.000
rak
Tokenrak
Feature activation+0.000
1995
Token1995
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sum
TokenSum
Feature activation+0.170
mon
Tokenmon
Feature activation+1.481
ing
Tokening
Feature activation+0.000
is
Token is
Feature activation+0.000
important
Token important
Feature activation+0.000
to
Token to
Feature activation+0.000
dungeon
Token dungeon
Feature activation+0.000
1
Token1
Feature activation+0.000
fans
Token fans
Feature activation+0.000
can
Token can
Feature activation+0.000
design
Token design
Feature activation+0.000
better
Token better
Feature activation+0.000
liver
Token liver
Feature activation+1.403
ies
Tokenies
Feature activation+0.000
than
Token than
Feature activation+0.000
these
Token these
Feature activation+0.000
supposed
Token supposed
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000

INTERVAL 1.184 - 1.382
CONTAINS 0.002%

Python
Token Python
Feature activation+0.000
(
Token (
Feature activation+0.000
list
Tokenlist
Feature activation+0.000
and
Token and
Feature activation+0.000
generator
Token generator
Feature activation+0.000
comprehens
Token comprehens
Feature activation+1.193
ions
Tokenions
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
C
Token C
Feature activation+0.000
#
Token#
Feature activation+0.000
quite
Token quite
Feature activation+0.000
heavy
Token heavy
Feature activation+0.000
.
Token.
Feature activation+0.000
[
Token [
Feature activation+0.000
St
TokenSt
Feature activation+0.796
unt
Tokenunt
Feature activation+1.244
men
Tokenmen
Feature activation+0.000
]
Token]
Feature activation+0.000
train
Token train
Feature activation+0.000
for
Token for
Feature activation+0.000
months
Token months
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
know
Token know
Feature activation+0.000
,
Token,
Feature activation+0.000
vehicles
Token vehicles
Feature activation+0.000
tail
Token tail
Feature activation+1.285
ing
Tokening
Feature activation+0.000
me
Token me
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
Joe
Token Joe
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
vegan
Token vegan
Feature activation+0.000
condition
Token condition
Feature activation+1.252
er
Tokener
Feature activation+0.000
:
Token:
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
a
Token a
Feature activation+0.000
two
Token two
Feature activation+0.000
-
Token-
Feature activation+0.000
hour
Tokenhour
Feature activation+0.000
j
Token j
Feature activation+0.020
oust
Tokenoust
Feature activation+1.309
ing
Tokening
Feature activation+0.096
show
Token show
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

INTERVAL 0.987 - 1.184
CONTAINS 0.004%

missing
Token missing
Feature activation+0.000
a
Token a
Feature activation+0.000
limb
Token limb
Feature activation+0.000
,
Token,
Feature activation+0.000
amp
Token amp
Feature activation+0.000
ute
Tokenute
Feature activation+0.997
es
Tokenes
Feature activation+0.000
are
Token are
Feature activation+0.000
more
Token more
Feature activation+0.000
prone
Token prone
Feature activation+0.000
to
Token to
Feature activation+0.000
verse
Tokenverse
Feature activation+0.000
Phase
Token Phase
Feature activation+0.000
(
Token (
Feature activation+0.000
http
Token http
Feature activation+0.000
://
Token://
Feature activation+0.000
in
Tokenin
Feature activation+1.037
verse
Tokenverse
Feature activation+0.000
phase
Tokenphase
Feature activation+0.000
.
Token.
Feature activation+0.000
band
Tokenband
Feature activation+0.000
camp
Tokencamp
Feature activation+0.000
.
Token.
Feature activation+0.000
Pro
Token Pro
Feature activation+0.000
Football
Token Football
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
of
Token of
Feature activation+0.000
Fam
Token Fam
Feature activation+1.116
ers
Tokeners
Feature activation+0.000
aren
Token aren
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
S
Token S
Feature activation+0.000
AGES
TokenAGES
Feature activation+0.000
IN
Token IN
Feature activation+0.000
A
Token A
Feature activation+0.000
RE
Token RE
Feature activation+0.000
VIEW
TokenVIEW
Feature activation+1.041
TO
Token TO
Feature activation+0.000
BE
Token BE
Feature activation+0.000
PR
Token PR
Feature activation+0.000
INT
TokenINT
Feature activation+0.000
ED
TokenED
Feature activation+0.000
For
Token For
Feature activation+0.000
example
Token example
Feature activation+0.000
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
island
Token island
Feature activation+1.010
of
Token of
Feature activation+0.000
New
Token New
Feature activation+0.000
Han
Token Han
Feature activation+0.000
over
Tokenover
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.790 - 0.987
CONTAINS 0.009%

s
Tokens
Feature activation+0.000
and
Token and
Feature activation+0.000
Stars
Token Stars
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
z
Token z
Feature activation+0.858
ipp
Tokenipp
Feature activation+0.000
ered
Tokenered
Feature activation+0.000
sheets
Token sheets
Feature activation+0.000
(
Token (
Feature activation+0.000
available
Tokenavailable
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
heart
Token heart
Feature activation+0.000
of
Token of
Feature activation+0.000
Gr
Token Gr
Feature activation+0.066
ims
Tokenims
Feature activation+0.791
by
Tokenby
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
back
Token back
Feature activation+0.236
IT
TokenIT
Feature activation+0.000
has
Token has
Feature activation+0.000
taken
Token taken
Feature activation+0.000
in
Token in
Feature activation+0.000
30
Token 30
Feature activation+0.000
second
Token second
Feature activation+0.944
ees
Tokenees
Feature activation+0.000
since
Token since
Feature activation+0.000
its
Token its
Feature activation+0.000
establishment
Token establishment
Feature activation+0.000
in
Token in
Feature activation+0.000
.
Token.
Feature activation+0.000
Both
Token Both
Feature activation+0.000
W
Token W
Feature activation+0.000
ahl
Tokenahl
Feature activation+0.000
and
Token and
Feature activation+0.000
May
Token May
Feature activation+0.949
ers
Tokeners
Feature activation+0.000
will
Token will
Feature activation+0.000
throw
Token throw
Feature activation+0.000
anywhere
Token anywhere
Feature activation+0.000
from
Token from
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Researchers
TokenResearchers
Feature activation+0.000
found
Token found
Feature activation+0.000
that
Token that
Feature activation+0.000
fathers
Token fathers
Feature activation+0.905
in
Token in
Feature activation+0.000
divorced
Token divorced
Feature activation+0.000
families
Token families
Feature activation+0.000
had
Token had
Feature activation+0.000
greater
Token greater
Feature activation+0.000

INTERVAL 0.592 - 0.790
CONTAINS 0.013%

either
Token either
Feature activation+0.000
participant
Token participant
Feature activation+0.000
will
Token will
Feature activation+0.000
cancel
Token cancel
Feature activation+0.000
the
Token the
Feature activation+0.000
brawl
Token brawl
Feature activation+0.710
and
Token and
Feature activation+0.000
may
Token may
Feature activation+0.000
cause
Token cause
Feature activation+0.000
the
Token the
Feature activation+0.000
opponent
Token opponent
Feature activation+0.000
:
Token:
Feature activation+0.000
l
Token l
Feature activation+0.000
angs
Tokenangs
Feature activation+0.000
at
Tokenat
Feature activation+0.000
,
Token,
Feature activation+0.000
lan
Token lan
Feature activation+0.780
z
Tokenz
Feature activation+0.000
ones
Tokenones
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
J
TokenJ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
V
TokenV
Feature activation+0.000
inic
Tokeninic
Feature activation+0.000
ius
Tokenius
Feature activation+0.000
Vac
Token Vac
Feature activation+0.639
anti
Tokenanti
Feature activation+0.000
is
Token is
Feature activation+0.000
co
Token co
Feature activation+0.000
-
Token-
Feature activation+0.000
founder
Tokenfounder
Feature activation+0.000
cpp
Tokencpp
Feature activation+0.000
_
Token_
Feature activation+0.000
re
Tokenre
Feature activation+0.000
gex
Tokengex
Feature activation+0.000
_
Token_
Feature activation+0.000
tra
Tokentra
Feature activation+0.687
its
Tokenits
Feature activation+0.000
<
Token<
Feature activation+0.000
char
Tokenchar
Feature activation+0.000
>
Token>
Feature activation+0.000
>
Token >
Feature activation+0.000
recommends
Token recommends
Feature activation+0.000
slicing
Token slicing
Feature activation+0.000
the
Token the
Feature activation+0.000
Su
Token Su
Feature activation+0.000
ika
Tokenika
Feature activation+0.000
Bag
Token Bag
Feature activation+0.779
el
Tokenel
Feature activation+0.000
and
Token and
Feature activation+0.000
adding
Token adding
Feature activation+0.000
either
Token either
Feature activation+0.000
coconut
Token coconut
Feature activation+0.000

INTERVAL 0.395 - 0.592
CONTAINS 0.022%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
3
Token3
Feature activation+0.000
.
Token.
Feature activation+0.000
Wh
Token Wh
Feature activation+0.576
isk
Tokenisk
Feature activation+0.466
ers
Tokeners
Feature activation+0.000
help
Token help
Feature activation+0.000
her
Token her
Feature activation+0.000
figure
Token figure
Feature activation+0.000
out
Token out
Feature activation+0.000
Chef
Token Chef
Feature activation+0.000
dude
Token dude
Feature activation+0.000
told
Token told
Feature activation+0.000
me
Token me
Feature activation+0.000
that
Token that
Feature activation+0.000
sharp
Token sharp
Feature activation+0.432
ening
Tokenening
Feature activation+0.000
ste
Token ste
Feature activation+0.000
els
Tokenels
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
used
Token used
Feature activation+0.000
the
Token the
Feature activation+0.000
S
Token S
Feature activation+0.000
igm
Tokenigm
Feature activation+0.487
oid
Tokenoid
Feature activation+0.000
curve
Token curve
Feature activation+0.000
to
Token to
Feature activation+0.000
calculate
Token calculate
Feature activation+0.000
the
Token the
Feature activation+0.000
17
Token 17
Feature activation+0.000
88
Token88
Feature activation+0.000
that
Token that
Feature activation+0.000
W
Token W
Feature activation+0.000
oll
Tokenoll
Feature activation+0.000
stone
Tokenstone
Feature activation+0.474
craft
Tokencraft
Feature activation+0.000
began
Token began
Feature activation+0.000
to
Token to
Feature activation+0.000
write
Token write
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
best
Token best
Feature activation+0.000
choice
Token choice
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
bre
Token bre
Feature activation+0.489
eder
Tokeneder
Feature activation+0.000
should
Token should
Feature activation+0.000
know
Token know
Feature activation+0.000
all
Token all
Feature activation+0.000
about
Token about
Feature activation+0.000

INTERVAL 0.197 - 0.395
CONTAINS 0.048%

add
Token add
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
value
Token value
Feature activation+0.000
of
Token of
Feature activation+0.000
Spons
Token Spons
Feature activation+0.216
orship
Tokenorship
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.000
two
Token two
Feature activation+0.000
terms
Token terms
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
'
Token '
Feature activation+0.000
An
TokenAn
Feature activation+0.217
arch
Tokenarch
Feature activation+0.022
o
Tokeno
Feature activation+0.000
-
Token-
Feature activation+0.000
capitalist
Tokencapitalist
Feature activation+0.000
'
Token'
Feature activation+0.000
top
Token top
Feature activation+0.000
32
Token 32
Feature activation+0.000
,"
Token,"
Feature activation+0.000
National
Token National
Feature activation+0.000
Archer
Token Archer
Feature activation+0.031
y
Tokeny
Feature activation+0.231
Association
Token Association
Feature activation+0.000
spokeswoman
Token spokeswoman
Feature activation+0.000
Kathleen
Token Kathleen
Feature activation+0.000
Frazier
Token Frazier
Feature activation+0.000
said
Token said
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ste
TokenSte
Feature activation+0.367
in
Tokenin
Feature activation+0.263
went
Token went
Feature activation+0.000
on
Token on
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
that
Token that
Feature activation+0.000
bro
Tokenbro
Feature activation+0.000
can
Token can
Feature activation+0.000
improve
Token improve
Feature activation+0.000
upon
Token upon
Feature activation+0.000
their
Token their
Feature activation+0.000
Legends
Token Legends
Feature activation+0.222
game
Token game
Feature activation+0.000
is
Token is
Feature activation+0.000
by
Token by
Feature activation+0.000
creating
Token creating
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.000 - 0.197
CONTAINS 99.900%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
article
Token article
Feature activation+0.000
on
Token on
Feature activation+0.000
lazy
Token lazy
Feature activation+0.000
symbol
Token symbol
Feature activation+0.000
resolution
Token resolution
Feature activation+0.000
,
Token,
Feature activation+0.000
Linux
Token Linux
Feature activation+0.000
Intern
Token Intern
Feature activation+0.000
als
Tokenals
Feature activation+0.000
copyright
Token copyright
Feature activation+0.000
Think
Token Think
Feature activation+0.000
stock
Tokenstock
Feature activation+0.000
Image
Token Image
Feature activation+0.000
caption
Token caption
Feature activation+0.000
Domestic
Token Domestic
Feature activation+0.000
violence
Token violence
Feature activation+0.000
often
Token often
Feature activation+0.000
goes
Token goes
Feature activation+0.000
unre
Token unre
Feature activation+0.000
ported
Tokenported
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
what
Token what
Feature activation+0.000
being
Token being
Feature activation+0.000
a
Token a
Feature activation+0.000
shareholder
Token shareholder
Feature activation+0.000
makes
Token makes
Feature activation+0.000
you
Token you
Feature activation+0.000
:
Token:
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
outdoor
Token outdoor
Feature activation+0.000
shopping
Token shopping
Feature activation+0.000
development
Token development
Feature activation+0.000
announced
Token announced
Feature activation+0.000
this
Token this
Feature activation+0.000
week
Token week
Feature activation+0.000
that
Token that
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
cor
Tokencor
Feature activation+0.000
porate
Tokenporate
Feature activation+0.000
school
Token school
Feature activation+0.000
reform
Token reform
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
(
Token (
Feature activation+0.000
led
Tokenled
Feature activation+0.000
by
Token by
Feature activation+0.000
fe
Token fe
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 H5.5: (feature 43711)

TOP ACTIVATIONS
MAX = 2.116

the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
big
Token big
Feature activation+0.000
hurdle
Token hurdle
Feature activation+0.000
that
Token that
Feature activation+0.000
stands
Token stands
Feature activation+2.116
between
Token between
Feature activation+0.000
people
Token people
Feature activation+0.000
,
Token,
Feature activation+0.000
especially
Token especially
Feature activation+0.000
Christians
Token Christians
Feature activation+0.000
.
Token.
Feature activation+0.000
Instead
Token Instead
Feature activation+0.000
,
Token,
Feature activation+0.000
Gl
Token Gl
Feature activation+0.000
end
Tokenend
Feature activation+0.000
ening
Tokenening
Feature activation+2.072
is
Token is
Feature activation+0.673
known
Token known
Feature activation+0.000
for
Token for
Feature activation+0.000
face
Token face
Feature activation+0.000
-
Token-
Feature activation+0.000
upon
Token upon
Feature activation+0.000
entirely
Token entirely
Feature activation+0.151
escaping
Token escaping
Feature activation+0.000
the
Token the
Feature activation+0.000
heavy
Token heavy
Feature activation+0.000
hand
Token hand
Feature activation+2.023
of
Token of
Feature activation+0.866
government
Token government
Feature activation+0.000
are
Token are
Feature activation+0.000
dreaming
Token dreaming
Feature activation+0.000
.
Token.
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
plane
Token plane
Feature activation+0.000
,
Token,
Feature activation+0.000
Mar
Token Mar
Feature activation+0.000
lon
Tokenlon
Feature activation+1.965
?
Token?
Feature activation+0.000
Am
Token Am
Feature activation+0.000
I
Token I
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
the
Token the
Feature activation+0.000
concept
Token concept
Feature activation+0.000
of
Token of
Feature activation+0.000
early
Token early
Feature activation+0.000
-
Token-
Feature activation+0.000
escape
Tokenescape
Feature activation+1.935
in
Token in
Feature activation+0.466
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
effective
Token effective
Feature activation+0.000
manner
Token manner
Feature activation+0.000
decades
Token decades
Feature activation+0.000
psychologists
Token psychologists
Feature activation+0.000
have
Token have
Feature activation+0.000
known
Token known
Feature activation+0.000
that
Token that
Feature activation+0.000
context
Token context
Feature activation+1.885
matters
Token matters
Feature activation+0.053
when
Token when
Feature activation+0.000
assessing
Token assessing
Feature activation+0.000
people
Token people
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
exchange
Token exchange
Feature activation+0.000
between
Token between
Feature activation+0.000
Div
Token Div
Feature activation+0.000
illy
Tokenilly
Feature activation+1.868
and
Token and
Feature activation+0.000
Green
Token Green
Feature activation+0.000
Party
Token Party
Feature activation+0.000
leader
Token leader
Feature activation+0.000
E
Token E
Feature activation+0.000
of
Token of
Feature activation+0.000
Central
Token Central
Feature activation+0.000
American
Token American
Feature activation+0.000
migrants
Token migrants
Feature activation+0.000
who
Token who
Feature activation+0.000
cross
Token cross
Feature activation+1.762
into
Token into
Feature activation+0.000
Mexico
Token Mexico
Feature activation+0.000
are
Token are
Feature activation+0.000
often
Token often
Feature activation+0.000
detained
Token detained
Feature activation+0.000
cod
Token cod
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
gradual
Token gradual
Feature activation+0.000
elimination
Token elimination
Feature activation+1.762
of
Token of
Feature activation+1.085
20
Token 20
Feature activation+0.000
%
Token%
Feature activation+0.000
tariff
Token tariff
Feature activation+0.000
barriers
Token barriers
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
1991
Token 1991
Feature activation+0.000
K
Token K
Feature activation+0.000
ated
Tokenated
Feature activation+1.516
ra
Tokenra
Feature activation+1.761
played
Token played
Feature activation+0.000
at
Token at
Feature activation+0.000
"
Token "
Feature activation+0.000
Balt
TokenBalt
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
_
Token_
Feature activation+0.000
ptr
Tokenptr
Feature activation+0.000
<
Token <
Feature activation+0.000
boost
Tokenboost
Feature activation+0.000
/
Token/
Feature activation+0.000
sc
Tokensc
Feature activation+1.691
oped
Tokenoped
Feature activation+0.597
_
Token_
Feature activation+0.000
ptr
Tokenptr
Feature activation+0.006
.
Token.
Feature activation+0.000
h
Tokenh
Feature activation+0.000
in
Token in
Feature activation+0.067
same
Token same
Feature activation+0.000
st
Token st
Feature activation+0.000
,
Token,
Feature activation+0.000
h
Token h
Feature activation+0.000
dc
Tokendc
Feature activation+1.671
around
Token around
Feature activation+0.000
.
Token.
Feature activation+0.000
Sl
Token Sl
Feature activation+0.000
st
Tokenst
Feature activation+0.000
in
Token in
Feature activation+0.332
ISH
TokenISH
Feature activation+0.000
ED
TokenED
Feature activation+0.000
BY
Token BY
Feature activation+0.000
L
Token L
Feature activation+0.000
ITT
TokenITT
Feature activation+0.314
LE
TokenLE
Feature activation+1.665
,
Token,
Feature activation+0.117
BR
Token BR
Feature activation+0.000
OWN
TokenOWN
Feature activation+0.746
AND
Token AND
Feature activation+0.062
COMP
Token COMP
Feature activation+0.000
police
Token police
Feature activation+0.000
investigators
Token investigators
Feature activation+0.000
,
Token,
Feature activation+0.000
Qu
Token Qu
Feature activation+0.000
is
Tokenis
Feature activation+0.000
pe
Tokenpe
Feature activation+1.663
is
Token is
Feature activation+0.814
the
Token the
Feature activation+0.000
de
Token de
Feature activation+0.000
facto
Token facto
Feature activation+0.000
leader
Token leader
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Death
TokenDeath
Feature activation+0.000
at
Token at
Feature activation+0.000
Chen
Token Chen
Feature activation+0.000
og
Tokenog
Feature activation+0.747
ne
Tokenne
Feature activation+1.653
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
).
Token).
Feature activation+0.000
As
Token As
Feature activation+0.000
even
Token even
Feature activation+0.000
students
Token students
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
of
Token of
Feature activation+1.628
the
Token the
Feature activation+0.000
86
Token 86
Feature activation+0.000
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000
him
Token him
Feature activation+0.000
the
Token the
Feature activation+0.000
highest
Token highest
Feature activation+0.000
-
Token-
Feature activation+0.000
paid
Tokenpaid
Feature activation+0.000
center
Token center
Feature activation+1.609
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
league
Token league
Feature activation+0.000
,
Token,
Feature activation+0.000
surpass
Token surpass
Feature activation+0.000
was
Token was
Feature activation+0.000
wounded
Token wounded
Feature activation+0.000
twice
Token twice
Feature activation+0.000
.
Token.
Feature activation+0.000
Cle
Token Cle
Feature activation+0.000
m
Tokenm
Feature activation+1.584
was
Token was
Feature activation+0.000
discharged
Token discharged
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
Army
Token Army
Feature activation+0.000
An
Token An
Feature activation+0.000
j
Tokenj
Feature activation+0.000
em
Tokenem
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
oud
Tokenoud
Feature activation+0.000
ary
Tokenary
Feature activation+1.569
,
Token,
Feature activation+0.023
pictured
Token pictured
Feature activation+0.000
during
Token during
Feature activation+0.000
a
Token a
Feature activation+0.000
demonstration
Token demonstration
Feature activation+0.000
ango
Tokenango
Feature activation+0.000
~
Token~
Feature activation+0.000
]
Token]
Feature activation+0.000
$
Token$
Feature activation+0.000
sudo
Token sudo
Feature activation+0.000
y
Token y
Feature activation+1.560
um
Tokenum
Feature activation+0.000
install
Token install
Feature activation+0.000
post
Token post
Feature activation+0.543
gres
Tokengres
Feature activation+0.000
ql
Tokenql
Feature activation+0.064

Top DFA by src position
MAX = 2.515

<|endoftext|>
Token<|endoftext|>
Feature activation-0.228
Top resid features:
standing
Tokenstanding
Feature activation-0.003
Top resid features:
is
Token is
Feature activation+1.274
Top resid features:
the
Token the
Feature activation+1.225
Top resid features:
next
Token next
Feature activation+0.022
Top resid features:
big
Token big
Feature activation-0.003
Top resid features:
hurdle
Token hurdle
Feature activation+0.007
Top resid features:
that
Token that
Feature activation+0.052
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.238
Top resid features:
ening
Tokenening
Feature activation-0.004
Top resid features:
is
Token is
Feature activation+2.371
Top resid features:
a
Token a
Feature activation+0.202
Top resid features:
player
Token player
Feature activation-0.000
Top resid features:
that
Token that
Feature activation-0.012
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
somewhat
Token somewhat
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.282
Top resid features:
handed
Tokenhanded
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+2.515
Top resid features:
still
Token still
Feature activation+0.005
Top resid features:
government
Token government
Feature activation-0.004
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
mand
Tokenmand
Feature activation-0.002
Top resid features:
ated
Tokenated
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.249
Top resid features:
arl
Tokenarl
Feature activation+0.002
Top resid features:
on
Tokenon
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+2.448
Top resid features:
in
Token in
Feature activation+0.044
Top resid features:
case
Token case
Feature activation-0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.006
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.217
Top resid features:
escape
Tokenescape
Feature activation-0.004
Top resid features:
in
Token in
Feature activation+2.362
Top resid features:
many
Token many
Feature activation+0.016
Top resid features:
popular
Token popular
Feature activation+0.001
Top resid features:
programming
Token programming
Feature activation+0.003
Top resid features:
languages
Token languages
Feature activation+0.007
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.265
Top resid features:
âĢ
Token âĢ
Feature activation-0.002
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
context
Tokencontext
Feature activation+0.008
Top resid features:
is
Token is
Feature activation+2.364
Top resid features:
everything
Token everything
Feature activation+0.040
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
âĢ
TokenâĢ
Feature activation-0.010
Top resid features:
Ŀ
TokenĿ
Feature activation-0.001
Top resid features:
And
Token And
Feature activation-0.009
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.288
Top resid features:
illy
Tokenilly
Feature activation+0.002
Top resid features:
told
Token told
Feature activation+2.402
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
O
Token O
Feature activation+0.004
Top resid features:
ire
Tokenire
Feature activation+0.001
Top resid features:
acht
Tokenacht
Feature activation+0.002
Top resid features:
as
Tokenas
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.280
Top resid features:
cross
Token cross
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+2.153
Top resid features:
African
Token African
Feature activation+0.235
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
Asian
Token Asian
Feature activation+0.000
Top resid features:
migrants
Token migrants
Feature activation-0.023
Top resid features:
are
Token are
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.216
Top resid features:
eliminated
Token eliminated
Feature activation+0.002
Top resid features:
has
Token has
Feature activation+2.087
Top resid features:
been
Token been
Feature activation+0.032
Top resid features:
hugely
Token hugely
Feature activation+0.008
Top resid features:
controversial
Token controversial
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.281
Top resid features:
ated
Tokenated
Feature activation-0.002
Top resid features:
ra
Tokenra
Feature activation+0.002
Top resid features:
are
Token are
Feature activation+2.192
Top resid features:
the
Token the
Feature activation+0.088
Top resid features:
only
Token only
Feature activation+0.002
Top resid features:
mat
Token mat
Feature activation-0.001
Top resid features:
ad
Tokenad
Feature activation-0.000
Top resid features:
ors
Tokenors
Feature activation-0.008
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.255
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
sc
Tokensc
Feature activation-0.001
Top resid features:
oped
Tokenoped
Feature activation+2.064
Top resid features:
_
Token_
Feature activation+0.004
Top resid features:
ptr
Tokenptr
Feature activation+0.028
Top resid features:
<
Token <
Feature activation+0.009
Top resid features:
boost
Tokenboost
Feature activation+0.100
Top resid features:
/
Token/
Feature activation-0.006
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.171
Top resid features:
dc
Tokendc
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+2.006
Top resid features:
same
Token same
Feature activation+0.052
Top resid features:
st
Token st
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
h
Token h
Feature activation-0.037
Top resid features:
dc
Tokendc
Feature activation+0.029
Top resid features:
IC
TokenIC
Feature activation+0.007
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
L
TokenL
Feature activation-0.005
Top resid features:
ITT
TokenITT
Feature activation-0.000
Top resid features:
LE
TokenLE
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+2.160
Top resid features:
BR
Token BR
Feature activation+0.004
Top resid features:
OWN
TokenOWN
Feature activation+0.006
Top resid features:
BOOK
Token BOOK
Feature activation-0.011
Top resid features:
S
TokenS
Feature activation-0.003
Top resid features:
ARE
Token ARE
Feature activation-0.006
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.252
Top resid features:
is
Tokenis
Feature activation-0.017
Top resid features:
pe
Tokenpe
Feature activation-0.001
Top resid features:
is
Token is
Feature activation+2.186
Top resid features:
a
Token a
Feature activation+0.134
Top resid features:
master
Token master
Feature activation+0.005
Top resid features:
counterfe
Token counterfe
Feature activation-0.027
Top resid features:
iter
Tokeniter
Feature activation-0.034
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.240
Top resid features:
og
Tokenog
Feature activation-0.007
Top resid features:
ne
Tokenne
Feature activation+0.006
Top resid features:
(
Token (
Feature activation+2.153
Top resid features:
see
Tokensee
Feature activation+0.010
Top resid features:
âĢ
Token âĢ
Feature activation+0.017
Top resid features:
ľ
Tokenľ
Feature activation+0.001
Top resid features:
Death
TokenDeath
Feature activation+0.004
Top resid features:
at
Token at
Feature activation-0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.188
Top resid features:
of
Token of
Feature activation-0.028
Top resid features:
the
Token the
Feature activation+2.043
Top resid features:
nation
Token nation
Feature activation+0.039
Top resid features:
's
Token's
Feature activation+0.001
Top resid features:
two
Token two
Feature activation+0.008
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
and
Token and
Feature activation-0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.199
Top resid features:
center
Token center
Feature activation-0.000
Top resid features:
they
Token they
Feature activation+1.892
Top resid features:
landed
Token landed
Feature activation+0.012
Top resid features:
their
Token their
Feature activation-0.001
Top resid features:
guy
Token guy
Feature activation-0.007
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.204
Top resid features:
lem
Tokenlem
Feature activation+0.001
Top resid features:
went
Token went
Feature activation+1.989
Top resid features:
on
Token on
Feature activation-0.002
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
fight
Token fight
Feature activation+0.000
Top resid features:
at
Token at
Feature activation-0.001
Top resid features:
Perry
Token Perry
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.253
Top resid features:
oud
Tokenoud
Feature activation+0.001
Top resid features:
ary
Tokenary
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+2.060
Top resid features:
was
Token was
Feature activation+0.006
Top resid features:
arrested
Token arrested
Feature activation+0.011
Top resid features:
outside
Token outside
Feature activation+0.000
Top resid features:
his
Token his
Feature activation-0.002
Top resid features:
home
Token home
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.258
Top resid features:
y
Tokeny
Feature activation-0.003
Top resid features:
um
Tokenum
Feature activation+2.063
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
post
Tokenpost
Feature activation+0.052
Top resid features:
gres
Tokengres
Feature activation+0.002
Top resid features:
ql
Tokenql
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.06

Head 2: 0.03

Head 3: 0.03

Head 4: 0.02

Head 5: 0.55

Head 6: 0.02

Head 7: 0.02

Head 8: 0.07

Head 9: 0.06

Head 10: 0.05

Head 11: 0.04

Positive logits

annotation1.62

lett1.57

Conscious1.50

refers1.48

contraction1.48

transcript1.47

organism1.42

resume1.40

Debt1.39

Jen1.39

quotes1.38

Suggest1.36

Hyde1.35

Voting1.35

izen1.34

edient1.34

ITNESS1.32

Activity1.31

denotes1.30

largeDownload1.30

Negative logits

Gors-1.78

fir-1.63

itech-1.61

agna-1.60

MGM-1.56

\\\\\\\\-1.56

FB-1.53

OTAL-1.52

wings-1.50

Islanders-1.48

expensive-1.45

forts-1.45

lot-1.43

planes-1.43

FK-1.42

ouses-1.42

CT-1.41

-1.39

ghai-1.39

bread-1.37

INTERVAL 1.904 - 2.116
CONTAINS 0.001%

.
Token.
Feature activation+0.000
Instead
Token Instead
Feature activation+0.000
,
Token,
Feature activation+0.000
Gl
Token Gl
Feature activation+0.000
end
Tokenend
Feature activation+0.000
ening
Tokenening
Feature activation+2.072
is
Token is
Feature activation+0.673
known
Token known
Feature activation+0.000
for
Token for
Feature activation+0.000
face
Token face
Feature activation+0.000
-
Token-
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
big
Token big
Feature activation+0.000
hurdle
Token hurdle
Feature activation+0.000
that
Token that
Feature activation+0.000
stands
Token stands
Feature activation+2.116
between
Token between
Feature activation+0.000
people
Token people
Feature activation+0.000
,
Token,
Feature activation+0.000
especially
Token especially
Feature activation+0.000
Christians
Token Christians
Feature activation+0.000
the
Token the
Feature activation+0.000
concept
Token concept
Feature activation+0.000
of
Token of
Feature activation+0.000
early
Token early
Feature activation+0.000
-
Token-
Feature activation+0.000
escape
Tokenescape
Feature activation+1.935
in
Token in
Feature activation+0.466
a
Token a
Feature activation+0.000
more
Token more
Feature activation+0.000
effective
Token effective
Feature activation+0.000
manner
Token manner
Feature activation+0.000
upon
Token upon
Feature activation+0.000
entirely
Token entirely
Feature activation+0.151
escaping
Token escaping
Feature activation+0.000
the
Token the
Feature activation+0.000
heavy
Token heavy
Feature activation+0.000
hand
Token hand
Feature activation+2.023
of
Token of
Feature activation+0.866
government
Token government
Feature activation+0.000
are
Token are
Feature activation+0.000
dreaming
Token dreaming
Feature activation+0.000
.
Token.
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
plane
Token plane
Feature activation+0.000
,
Token,
Feature activation+0.000
Mar
Token Mar
Feature activation+0.000
lon
Tokenlon
Feature activation+1.965
?
Token?
Feature activation+0.000
Am
Token Am
Feature activation+0.000
I
Token I
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 1.692 - 1.904
CONTAINS 0.001%

decades
Token decades
Feature activation+0.000
psychologists
Token psychologists
Feature activation+0.000
have
Token have
Feature activation+0.000
known
Token known
Feature activation+0.000
that
Token that
Feature activation+0.000
context
Token context
Feature activation+1.885
matters
Token matters
Feature activation+0.053
when
Token when
Feature activation+0.000
assessing
Token assessing
Feature activation+0.000
people
Token people
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
exchange
Token exchange
Feature activation+0.000
between
Token between
Feature activation+0.000
Div
Token Div
Feature activation+0.000
illy
Tokenilly
Feature activation+1.868
and
Token and
Feature activation+0.000
Green
Token Green
Feature activation+0.000
Party
Token Party
Feature activation+0.000
leader
Token leader
Feature activation+0.000
E
Token E
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
1991
Token 1991
Feature activation+0.000
K
Token K
Feature activation+0.000
ated
Tokenated
Feature activation+1.516
ra
Tokenra
Feature activation+1.761
played
Token played
Feature activation+0.000
at
Token at
Feature activation+0.000
"
Token "
Feature activation+0.000
Balt
TokenBalt
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
cod
Token cod
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
gradual
Token gradual
Feature activation+0.000
elimination
Token elimination
Feature activation+1.762
of
Token of
Feature activation+1.085
20
Token 20
Feature activation+0.000
%
Token%
Feature activation+0.000
tariff
Token tariff
Feature activation+0.000
barriers
Token barriers
Feature activation+0.000
of
Token of
Feature activation+0.000
Central
Token Central
Feature activation+0.000
American
Token American
Feature activation+0.000
migrants
Token migrants
Feature activation+0.000
who
Token who
Feature activation+0.000
cross
Token cross
Feature activation+1.762
into
Token into
Feature activation+0.000
Mexico
Token Mexico
Feature activation+0.000
are
Token are
Feature activation+0.000
often
Token often
Feature activation+0.000
detained
Token detained
Feature activation+0.000

INTERVAL 1.481 - 1.692
CONTAINS 0.002%

ango
Tokenango
Feature activation+0.000
~
Token~
Feature activation+0.000
]
Token]
Feature activation+0.000
$
Token$
Feature activation+0.000
sudo
Token sudo
Feature activation+0.000
y
Token y
Feature activation+1.560
um
Tokenum
Feature activation+0.000
install
Token install
Feature activation+0.000
post
Token post
Feature activation+0.543
gres
Tokengres
Feature activation+0.000
ql
Tokenql
Feature activation+0.064
i
Tokeni
Feature activation+0.077
es
Token es
Feature activation+0.000
eg
Tokeneg
Feature activation+0.000
uit
Tokenuit
Feature activation+0.000
i
Tokeni
Feature activation+0.000
o
Token o
Feature activation+1.539
lt
Tokenlt
Feature activation+0.000
re
Tokenre
Feature activation+0.000
4
Token 4
Feature activation+0.000
.
Token.
Feature activation+0.000
000
Token000
Feature activation+0.000
abroad
Token abroad
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
1991
Token 1991
Feature activation+0.000
K
Token K
Feature activation+0.000
ated
Tokenated
Feature activation+1.516
ra
Tokenra
Feature activation+1.761
played
Token played
Feature activation+0.000
at
Token at
Feature activation+0.000
"
Token "
Feature activation+0.000
Balt
TokenBalt
Feature activation+0.000
police
Token police
Feature activation+0.000
investigators
Token investigators
Feature activation+0.000
,
Token,
Feature activation+0.000
Qu
Token Qu
Feature activation+0.000
is
Tokenis
Feature activation+0.000
pe
Tokenpe
Feature activation+1.663
is
Token is
Feature activation+0.814
the
Token the
Feature activation+0.000
de
Token de
Feature activation+0.000
facto
Token facto
Feature activation+0.000
leader
Token leader
Feature activation+0.000
students
Token students
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
of
Token of
Feature activation+1.628
the
Token the
Feature activation+0.000
86
Token 86
Feature activation+0.000
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
those
Token those
Feature activation+0.000

INTERVAL 1.269 - 1.481
CONTAINS 0.003%

I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.129
Ļ
TokenĻ
Feature activation+0.411
re
Tokenre
Feature activation+1.465
cheating
Token cheating
Feature activation+0.000
the
Token the
Feature activation+0.000
players
Token players
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
is
Token is
Feature activation+0.000
needed
Token needed
Feature activation+0.000
to
Token to
Feature activation+0.000
provide
Token provide
Feature activation+0.000
Atom
Token Atom
Feature activation+0.270
icity
Tokenicity
Feature activation+1.272
(
Token (
Feature activation+0.000
rolling
Tokenrolling
Feature activation+0.000
back
Token back
Feature activation+0.000
capabilities
Token capabilities
Feature activation+0.000
),
Token),
Feature activation+0.000
other
Token other
Feature activation+0.000
than
Token than
Feature activation+0.000
advertised
Token advertised
Feature activation+1.192
.
Token.
Feature activation+0.000
Fish
Token Fish
Feature activation+0.000
labeled
Token labeled
Feature activation+1.332
sn
Token sn
Feature activation+0.000
apper
Tokenapper
Feature activation+0.000
turned
Token turned
Feature activation+0.000
out
Token out
Feature activation+0.000
to
Token to
Feature activation+0.000
all
Token all
Feature activation+0.000
about
Token about
Feature activation+0.000
having
Token having
Feature activation+0.000
the
Token the
Feature activation+0.000
power
Token power
Feature activation+0.000
potion
Token potion
Feature activation+1.287
early
Token early
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
HAVE
Token HAVE
Feature activation+0.000
to
Token to
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
A
Token A
Feature activation+0.000
2
Token 2
Feature activation+0.000
A
TokenA
Feature activation+0.000
R
Token R
Feature activation+1.408
agon
Token agon
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
C
Token C
Feature activation+0.000
GS
TokenGS
Feature activation+0.000
216
Token216
Feature activation+0.000

INTERVAL 1.058 - 1.269
CONTAINS 0.007%

boost
Token boost
Feature activation+0.000
::
Token::
Feature activation+0.000
re
Tokenre
Feature activation+0.000
gex
Tokengex
Feature activation+0.000
_
Token_
Feature activation+0.000
tra
Tokentra
Feature activation+1.102
its
Tokenits
Feature activation+0.679
<
Token<
Feature activation+0.000
char
Tokenchar
Feature activation+0.000
,
Token,
Feature activation+0.000
boost
Token boost
Feature activation+0.000
tested
Token tested
Feature activation+0.000
was
Token was
Feature activation+0.000
something
Token something
Feature activation+0.000
other
Token other
Feature activation+0.000
than
Token than
Feature activation+0.000
advertised
Token advertised
Feature activation+1.192
.
Token.
Feature activation+0.000
Fish
Token Fish
Feature activation+0.000
labeled
Token labeled
Feature activation+1.332
sn
Token sn
Feature activation+0.000
apper
Tokenapper
Feature activation+0.000
Ħ
TokenĦ
Feature activation+0.000
(
Token (
Feature activation+0.198
zen
Tokenzen
Feature activation+0.000
).
Token).
Feature activation+0.000
This
Token This
Feature activation+0.000
shin
Token shin
Feature activation+1.262
means
Token means
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
truth
Tokentruth
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
violation
Token violation
Feature activation+0.176
carries
Token carries
Feature activation+0.000
the
Token the
Feature activation+0.000
risk
Token risk
Feature activation+1.127
of
Token of
Feature activation+0.228
a
Token a
Feature activation+0.000
possible
Token possible
Feature activation+0.000
misdemeanor
Token misdemeanor
Feature activation+0.000
citation
Token citation
Feature activation+0.000
is
Tokenis
Feature activation+0.000
concerned
Token concerned
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
reporting
Token reporting
Feature activation+1.219
burden
Token burden
Feature activation+0.000
,
Token,
Feature activation+0.000
particularly
Token particularly
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 0.846 - 1.058
CONTAINS 0.014%

.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
also
Token also
Feature activation+0.000
owns
Token owns
Feature activation+0.000
the
Token the
Feature activation+0.000
Trek
Token Trek
Feature activation+0.859
-
Token-
Feature activation+0.000
Seg
TokenSeg
Feature activation+0.000
af
Tokenaf
Feature activation+0.000
redo
Tokenredo
Feature activation+0.000
team
Token team
Feature activation+0.000
ring
Token ring
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
circle
Token circle
Feature activation+0.000
is
Token is
Feature activation+0.000
at
Token at
Feature activation+1.036
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
smallest
Token smallest
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
below
Token below
Feature activation+0.000
,
Token,
Feature activation+0.000
spots
Token spots
Feature activation+0.920
A
Token A
Feature activation+0.000
and
Token and
Feature activation+0.000
B
Token B
Feature activation+0.000
cannot
Token cannot
Feature activation+0.248
be
Token be
Feature activation+0.000
Then
Token Then
Feature activation+0.000
we
Token we
Feature activation+0.000
learned
Token learned
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.291
ľ
Tokenľ
Feature activation+0.855
assault
Tokenassault
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
worked
Token worked
Feature activation+0.000
taken
Token taken
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
context
Token context
Feature activation+0.000
and
Token and
Feature activation+0.000
pointed
Token pointed
Feature activation+0.855
out
Token out
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000

INTERVAL 0.635 - 0.846
CONTAINS 0.031%

were
Token were
Feature activation+0.000
living
Token living
Feature activation+0.000
in
Token in
Feature activation+0.000
.
Token.
Feature activation+0.000
Justice
Token Justice
Feature activation+0.000
Cro
Token Cro
Feature activation+0.704
ft
Tokenft
Feature activation+0.719
said
Token said
Feature activation+0.000
possession
Token possession
Feature activation+0.000
was
Token was
Feature activation+0.000
something
Token something
Feature activation+0.000
eker
Tokeneker
Feature activation+0.000
.
Token.
Feature activation+0.000
F
Token F
Feature activation+0.000
itter
Tokenitter
Feature activation+0.000
.
Token.
Feature activation+0.000
More
Token More
Feature activation+0.665
coordinated
Token coordinated
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
dare
Token dare
Feature activation+0.000
I
Token I
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Comp
TokenComp
Feature activation+0.000
rehens
Tokenrehens
Feature activation+0.760
ions
Tokenions
Feature activation+0.795
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
found
Token found
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
Fires
Token Fires
Feature activation+0.000
in
Token in
Feature activation+0.000
K
Token K
Feature activation+0.000
oot
Tokenoot
Feature activation+0.000
en
Tokenen
Feature activation+0.568
ays
Tokenays
Feature activation+0.644
advance
Token advance
Feature activation+0.000
on
Token on
Feature activation+0.000
homes
Token homes
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
concessions
Token concessions
Feature activation+0.000
for
Token for
Feature activation+0.000
all
Token all
Feature activation+0.000
season
Token season
Feature activation+0.000
ticket
Token ticket
Feature activation+0.000
members
Token members
Feature activation+0.696
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
CL
TokenCL
Feature activation+0.000
ICK
TokenICK
Feature activation+0.000

INTERVAL 0.423 - 0.635
CONTAINS 0.065%

k
Tokenk
Feature activation+0.000
-
Token-
Feature activation+0.000
v
Tokenv
Feature activation+0.000
at
Tokenat
Feature activation+0.000
-
Token-
Feature activation+0.000
rate
Tokenrate
Feature activation+0.517
*
Token *
Feature activation+0.000
;
Token ;
Feature activation+0.000
!
Token !
Feature activation+0.841
!
Token !
Feature activation+0.360
UK
Token UK
Feature activation+0.000
E
TokenE
Feature activation+0.000
yes
Tokenyes
Feature activation+0.000
T
TokenT
Feature activation+0.000
ore
Tokenore
Feature activation+0.000
ca
Tokenca
Feature activation+0.000
ga
Token ga
Feature activation+0.435
I
Token I
Feature activation+0.000
pp
Tokenpp
Feature activation+0.000
ai
Tokenai
Feature activation+0.000
,
Token,
Feature activation+0.000
Local
Token Local
Feature activation+0.000
ä
Tokenä
Feature activation+0.000
n
Tokenn
Feature activation+0.000
k
Tokenk
Feature activation+0.000
ning
Tokenning
Feature activation+0.000
till
Token till
Feature activation+0.000
run
Token run
Feature activation+0.618
text
Tokentext
Feature activation+0.000
dat
Tokendat
Feature activation+0.000
ab
Tokenab
Feature activation+0.000
as
Tokenas
Feature activation+0.000
en
Tokenen
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
recharge
Token recharge
Feature activation+0.000
able
Tokenable
Feature activation+0.000
batteries
Token batteries
Feature activation+0.503
are
Token are
Feature activation+0.000
consum
Token consum
Feature activation+0.000
able
Tokenable
Feature activation+0.000
components
Token components
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Romney
Token Romney
Feature activation+0.000
camp
Token camp
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
out
Token out
Feature activation+0.551
its
Token its
Feature activation+0.000
statement
Token statement
Feature activation+0.000
claiming
Token claiming
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000

INTERVAL 0.212 - 0.423
CONTAINS 0.157%

BIG
Token BIG
Feature activation+0.000
thanks
Token thanks
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
authors
Token authors
Feature activation+0.000
!
Token!
Feature activation+0.238
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
I
TokenI
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
law
Token law
Feature activation+0.000
says
Token says
Feature activation+0.000
and
Token and
Feature activation+0.000
define
Token define
Feature activation+0.000
hed
Token hed
Feature activation+0.628
ging
Tokenging
Feature activation+0.323
properly
Token properly
Feature activation+0.000
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
activity
Token activity
Feature activation+0.000
would
Token would
Feature activation+0.000
ICE
Token ICE
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.019
current
Token current
Feature activation+0.000
deportation
Token deportation
Feature activation+0.225
standards
Token standards
Feature activation+0.000
originated
Token originated
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
%
Token%
Feature activation+0.072
from
Token from
Feature activation+0.000
their
Token their
Feature activation+0.000
first
Token first
Feature activation+0.000
-
Token-
Feature activation+0.035
day
Tokenday
Feature activation+0.252
closing
Token closing
Feature activation+0.000
price
Token price
Feature activation+0.000
and
Token and
Feature activation+0.000
off
Token off
Feature activation+0.000
83
Token 83
Feature activation+0.000
my
Token my
Feature activation+0.000
name
Token name
Feature activation+0.000
publicly
Token publicly
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.343
stoked
Token stoked
Feature activation+0.000
the
Token the
Feature activation+0.000
fire
Token fire
Feature activation+0.000
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000

INTERVAL 0.000 - 0.212
CONTAINS 99.720%

build
Token build
Feature activation+0.000
new
Token new
Feature activation+0.000
factories
Token factories
Feature activation+0.000
and
Token and
Feature activation+0.000
ramp
Token ramp
Feature activation+0.000
up
Token up
Feature activation+0.000
research
Token research
Feature activation+0.000
and
Token and
Feature activation+0.000
development
Token development
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
this
Token this
Feature activation+0.000
picture
Token picture
Feature activation+0.111
!
Token!
Feature activation+0.000
Courtesy
Token Courtesy
Feature activation+0.000
of
Token of
Feature activation+0.000
BIG
Token BIG
Feature activation+0.000
-
Token -
Feature activation+0.000
B
Token B
Feature activation+0.000
jar
Tokenjar
Feature activation+0.000
ke
Tokenke
Feature activation+0.000
Ing
Token Ing
Feature activation+0.000
,
Token,
Feature activation+0.000
Suzanne
Token Suzanne
Feature activation+0.000
Meredith
Token Meredith
Feature activation+0.000
,
Token,
Feature activation+0.000
of
Token of
Feature activation+0.000
Wal
Token Wal
Feature activation+0.000
pole
Tokenpole
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
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
skin
Token skin
Feature activation+0.000
ner
Tokenner
Feature activation+0.000
box
Token box
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
was
Token was
Feature activation+0.000
Mark
Token Mark
Feature activation+0.000
free
Tokenfree
Feature activation+0.000
and
Token and
Feature activation+0.000
often
Token often
Feature activation+0.030
scar
Token scar
Feature activation+0.000
red
Tokenred
Feature activation+0.000
,
Token,
Feature activation+0.000
physically
Token physically
Feature activation+0.000
and
Token and
Feature activation+0.000
psychologically
Token psychologically
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 8 in H5.5: (feature 3002)

TOP ACTIVATIONS
MAX = 3.194

inferior
Token inferior
Feature activation+0.000
to
Token to
Feature activation+0.000
dec
Token dec
Feature activation+0.000
ou
Tokenou
Feature activation+0.000
page
Tokenpage
Feature activation+0.000
medium
Token medium
Feature activation+3.194
and
Token and
Feature activation+0.000
made
Token made
Feature activation+0.000
it
Token it
Feature activation+0.000
even
Token even
Feature activation+0.000
thinner
Token thinner
Feature activation+0.000
mone
Tokenmone
Feature activation+0.000
lla
Tokenlla
Feature activation+0.000
which
Token which
Feature activation+0.000
matched
Token matched
Feature activation+0.000
the
Token the
Feature activation+0.000
strain
Token strain
Feature activation+3.054
being
Token being
Feature activation+0.000
worked
Token worked
Feature activation+0.000
on
Token on
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
of
Token of
Feature activation+0.000
earnings
Token earnings
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
multiple
Token multiple
Feature activation+2.962
differs
Token differs
Feature activation+0.058
depending
Token depending
Feature activation+0.000
on
Token on
Feature activation+0.000
sector
Token sector
Feature activation+0.000
).
Token).
Feature activation+0.000
renew
Token renew
Feature activation+0.000
s
Tokens
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+2.847
has
Token has
Feature activation+0.848
two
Token two
Feature activation+0.000
dimensions
Token dimensions
Feature activation+0.000
:
Token:
Feature activation+0.000
a
Token a
Feature activation+0.000
Torah
Token Torah
Feature activation+0.000
,
Token,
Feature activation+0.000
assuming
Token assuming
Feature activation+0.000
that
Token that
Feature activation+0.000
each
Token each
Feature activation+0.000
book
Token book
Feature activation+2.816
of
Token of
Feature activation+0.646
the
Token the
Feature activation+0.000
Torah
Token Torah
Feature activation+0.000
is
Token is
Feature activation+0.040
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
neuron
Token neuron
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
output
Token output
Feature activation+2.610
is
Token is
Feature activation+1.839
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
positive
Token positive
Feature activation+0.000
or
Token or
Feature activation+0.000
fun
Token fun
Feature activation+0.000
.
Token.
Feature activation+0.000
Fun
Token Fun
Feature activation+0.000
Features
Token Features
Feature activation+0.000
4
Token 4
Feature activation+0.000
books
Token books
Feature activation+2.608
of
Token of
Feature activation+0.000
magic
Token magic
Feature activation+0.000
to
Token to
Feature activation+0.000
unlock
Token unlock
Feature activation+0.000
and
Token and
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
To
Token To
Feature activation+0.000
progress
Token progress
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
island
Token island
Feature activation+2.600
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
?)
Token?)
Feature activation+0.000
concrete
Token concrete
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
,
Token,
Feature activation+0.000
these
Token these
Feature activation+0.000
trees
Token trees
Feature activation+2.559
are
Token are
Feature activation+1.009
merely
Token merely
Feature activation+0.000
abstract
Token abstract
Feature activation+0.000
representations
Token representations
Feature activation+0.000
of
Token of
Feature activation+0.000
design
Token design
Feature activation+0.000
-
Token-
Feature activation+0.000
build
Tokenbuild
Feature activation+0.000
studios
Token studios
Feature activation+0.000
at
Token at
Feature activation+0.000
I
Token I
Feature activation+2.550
IT
TokenIT
Feature activation+0.731
including
Token including
Feature activation+0.000
the
Token the
Feature activation+0.000
recent
Token recent
Feature activation+0.000
A
Token A
Feature activation+0.000
the
Token the
Feature activation+0.000
disputed
Token disputed
Feature activation+0.000
territory
Token territory
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
sw
Token sw
Feature activation+2.548
immers
Tokenimmers
Feature activation+1.933
,
Token,
Feature activation+0.000
led
Token led
Feature activation+0.000
by
Token by
Feature activation+0.000
pop
Token pop
Feature activation+0.000
York
Token York
Feature activation+0.000
City
Token City
Feature activation+0.000
automatically
Token automatically
Feature activation+0.000
put
Token put
Feature activation+0.000
your
Token your
Feature activation+0.000
can
Token can
Feature activation+2.482
of
Token of
Feature activation+0.000
soda
Token soda
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
packet
Token packet
Feature activation+0.000
communication
Token communication
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
interpret
Token interpret
Feature activation+0.000
ive
Tokenive
Feature activation+0.000
frameworks
Token frameworks
Feature activation+2.463
are
Token are
Feature activation+1.049
powerful
Token powerful
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
have
Token have
Feature activation+0.000
meta
Token meta
Feature activation+0.000
-
Token-
Feature activation+0.000
rational
Tokenrational
Feature activation+0.000
.
Token .
Feature activation+0.000
These
Token These
Feature activation+0.000
stages
Token stages
Feature activation+2.396
are
Token are
Feature activation+1.101
distinctive
Token distinctive
Feature activation+0.000
,
Token,
Feature activation+0.000
internally
Token internally
Feature activation+0.000
consistent
Token consistent
Feature activation+0.000
magnetic
Token magnetic
Feature activation+0.000
field
Token field
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
larger
Token larger
Feature activation+0.000
arm
Token arm
Feature activation+2.380
on
Token on
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
'
Token '
Feature activation+0.000
FOX
TokenFOX
Feature activation+0.000
st
Token st
Feature activation+0.000
ony
Tokenony
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
carrots
Token carrots
Feature activation+2.369
that
Token that
Feature activation+0.221
first
Token first
Feature activation+0.000
year
Token year
Feature activation+0.000
were
Token were
Feature activation+0.000
stub
Token stub
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
cease
Token cease
Feature activation+0.000
-
Token-
Feature activation+0.000
fire
Tokenfire
Feature activation+0.000
line
Token line
Feature activation+2.347
in
Token in
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
expect
Token expect
Feature activation+0.000
000
Token000
Feature activation+0.000
year
Token year
Feature activation+0.000
ago
Token ago
Feature activation+0.000
.
Token.
Feature activation+0.000
Another
Token Another
Feature activation+0.000
stream
Token stream
Feature activation+2.339
is
Token is
Feature activation+0.000
closely
Token closely
Feature activation+0.000
related
Token related
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Alien
Token Alien
Feature activation+0.000
3
Token 3
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
first
Token first
Feature activation+0.148
draft
Token draft
Feature activation+2.326
was
Token was
Feature activation+0.704
completed
Token completed
Feature activation+0.000
sometime
Token sometime
Feature activation+0.000
in
Token in
Feature activation+0.000
1987
Token 1987
Feature activation+0.000
?"
Token?"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Although
TokenAlthough
Feature activation+0.000
the
Token the
Feature activation+0.000
anthology
Token anthology
Feature activation+2.303
features
Token features
Feature activation+0.000
established
Token established
Feature activation+0.000
names
Token names
Feature activation+0.000
and
Token and
Feature activation+0.000
writers
Token writers
Feature activation+0.122

Top DFA by src position
MAX = 3.799

a
Token a
Feature activation+0.001
Top resid features:
dec
Token dec
Feature activation+0.004
Top resid features:
ou
Tokenou
Feature activation+0.003
Top resid features:
page
Tokenpage
Feature activation+0.010
Top resid features:
medium
Token medium
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+3.799
Top resid features:
any
Token any
Feature activation+0.006
Top resid features:
sort
Token sort
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.014
Top resid features:
You
Token You
Feature activation+0.011
Top resid features:
're
Token're
Feature activation+0.002
Top resid features:
was
Token was
Feature activation-0.008
Top resid features:
infected
Token infected
Feature activation-0.001
Top resid features:
with
Token with
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
strain
Token strain
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+3.605
Top resid features:
Sal
Token Sal
Feature activation+0.034
Top resid features:
mone
Tokenmone
Feature activation+0.013
Top resid features:
lla
Tokenlla
Feature activation-0.000
Top resid features:
which
Token which
Feature activation+0.038
Top resid features:
matched
Token matched
Feature activation+0.016
Top resid features:
be
Token be
Feature activation-0.000
Top resid features:
priced
Token priced
Feature activation-0.004
Top resid features:
as
Token as
Feature activation+0.002
Top resid features:
some
Token some
Feature activation-0.004
Top resid features:
multiple
Token multiple
Feature activation+0.014
Top resid features:
of
Token of
Feature activation+3.619
Top resid features:
earnings
Token earnings
Feature activation+0.014
Top resid features:
(
Token (
Feature activation+0.004
Top resid features:
the
Tokenthe
Feature activation+0.057
Top resid features:
multiple
Token multiple
Feature activation+0.006
Top resid features:
differs
Token differs
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.002
Top resid features:
conception
Token conception
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
waves
Token waves
Feature activation+0.017
Top resid features:
of
Token of
Feature activation+3.375
Top resid features:
"
Token "
Feature activation+0.047
Top resid features:
creat
Tokencreat
Feature activation+0.012
Top resid features:
ive
Tokenive
Feature activation+0.003
Top resid features:
destruction
Token destruction
Feature activation+0.018
Top resid features:
"
Token"
Feature activation+0.026
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
third
Token third
Feature activation+0.004
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
five
Token five
Feature activation+0.003
Top resid features:
books
Token books
Feature activation+0.040
Top resid features:
of
Token of
Feature activation+2.902
Top resid features:
the
Token the
Feature activation+0.226
Top resid features:
Torah
Token Torah
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
assuming
Token assuming
Feature activation+0.030
Top resid features:
that
Token that
Feature activation+0.010
Top resid features:
curve
Token curve
Feature activation-0.005
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
calculate
Token calculate
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
output
Token output
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+3.143
Top resid features:
the
Token the
Feature activation+0.160
Top resid features:
neuron
Token neuron
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.027
Top resid features:
If
Token If
Feature activation+0.020
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
unlock
Token unlock
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
4
Token 4
Feature activation-0.000
Top resid features:
ancient
Token ancient
Feature activation+0.004
Top resid features:
books
Token books
Feature activation+0.042
Top resid features:
of
Token of
Feature activation+3.024
Top resid features:
magic
Token magic
Feature activation+0.044
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
collect
Token collect
Feature activation+0.004
Top resid features:
16
Token 16
Feature activation+0.002
Top resid features:
mysterious
Token mysterious
Feature activation+0.010
Top resid features:
as
Token as
Feature activation+0.002
Top resid features:
âĢ
Token âĢ
Feature activation+0.002
Top resid features:
ľ
Tokenľ
Feature activation-0.000
Top resid features:
is
Tokenis
Feature activation-0.002
Top resid features:
lands
Tokenlands
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+3.117
Top resid features:
psychological
Token psychological
Feature activation+0.023
Top resid features:
stability
Token stability
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
âĢ
TokenâĢ
Feature activation+0.018
Top resid features:
Ŀ
TokenĿ
Feature activation+0.005
Top resid features:
Ev
Token Ev
Feature activation-0.003
Top resid features:
als
Tokenals
Feature activation-0.003
Top resid features:
eat
Token eat
Feature activation-0.016
Top resid features:
these
Token these
Feature activation-0.000
Top resid features:
trees
Token trees
Feature activation+0.046
Top resid features:
of
Token of
Feature activation+2.999
Top resid features:
the
Token the
Feature activation+0.268
Top resid features:
species
Token species
Feature activation-0.006
Top resid features:
Lisp
Token Lisp
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.029
Top resid features:
More
Token More
Feature activation+0.007
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
own
Token own
Feature activation+0.001
Top resid features:
Illinois
Token Illinois
Feature activation+0.003
Top resid features:
Institute
Token Institute
Feature activation+0.013
Top resid features:
of
Token of
Feature activation+3.170
Top resid features:
Technology
Token Technology
Feature activation+0.025
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Professor
Token Professor
Feature activation+0.005
Top resid features:
Frank
Token Frank
Feature activation+0.001
Top resid features:
Fl
Token Fl
Feature activation+0.000
Top resid features:
are
Token are
Feature activation-0.000
Top resid features:
holding
Token holding
Feature activation+0.001
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
relay
Token relay
Feature activation-0.023
Top resid features:
swim
Token swim
Feature activation-0.010
Top resid features:
of
Token of
Feature activation+3.195
Top resid features:
220
Token 220
Feature activation-0.010
Top resid features:
km
Token km
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
South
Token South
Feature activation-0.001
Top resid features:
when
Token when
Feature activation-0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
buy
Token buy
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
can
Token can
Feature activation+0.002
Top resid features:
of
Token of
Feature activation+3.273
Top resid features:
soda
Token soda
Feature activation-0.019
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
or
Token or
Feature activation+0.002
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
few
Token few
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
We
Token We
Feature activation-0.000
Top resid features:
all
Token all
Feature activation+0.001
Top resid features:
have
Token have
Feature activation+0.003
Top resid features:
frameworks
Token frameworks
Feature activation+0.019
Top resid features:
of
Token of
Feature activation+3.013
Top resid features:
inter
Token inter
Feature activation+0.021
Top resid features:
related
Tokenrelated
Feature activation+0.004
Top resid features:
ideas
Token ideas
Feature activation+0.010
Top resid features:
through
Token through
Feature activation-0.001
Top resid features:
which
Token which
Feature activation+0.011
Top resid features:
Ke
TokenKe
Feature activation-0.002
Top resid features:
gan
Tokengan
Feature activation-0.000
Top resid features:
describes
Token describes
Feature activation-0.000
Top resid features:
three
Token three
Feature activation-0.002
Top resid features:
stages
Token stages
Feature activation-0.013
Top resid features:
of
Token of
Feature activation+3.089
Top resid features:
adult
Token adult
Feature activation+0.032
Top resid features:
development
Token development
Feature activation+0.015
Top resid features:
(
Token (
Feature activation+0.007
Top resid features:
numbered
Tokennumbered
Feature activation+0.002
Top resid features:
3
Token 3
Feature activation+0.003
Top resid features:
temperature
Token temperature
Feature activation-0.012
Top resid features:
change
Token change
Feature activation-0.000
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
both
Token both
Feature activation-0.005
Top resid features:
arms
Token arms
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+2.823
Top resid features:
the
Token the
Feature activation+0.286
Top resid features:
tuning
Token tuning
Feature activation+0.005
Top resid features:
fork
Token fork
Feature activation+0.013
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
subt
Token subt
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
grow
Token grow
Feature activation-0.001
Top resid features:
some
Token some
Feature activation+0.006
Top resid features:
fresh
Token fresh
Feature activation+0.004
Top resid features:
carrots
Token carrots
Feature activation+0.012
Top resid features:
of
Token of
Feature activation+3.003
Top resid features:
my
Token my
Feature activation+0.028
Top resid features:
own
Token own
Feature activation+0.001
Top resid features:
on
Token on
Feature activation-0.005
Top resid features:
our
Token our
Feature activation-0.000
Top resid features:
little
Token little
Feature activation+0.006
Top resid features:
not
Token not
Feature activation+0.001
Top resid features:
yet
Token yet
Feature activation+0.001
Top resid features:
visited
Token visited
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
line
Token line
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+2.787
Top resid features:
contact
Token contact
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
the
Token the
Feature activation+0.023
Top resid features:
cease
Token cease
Feature activation+0.003
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.230
Top resid features:
streams
Token streams
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+2.848
Top resid features:
the
Token the
Feature activation+0.166
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
Africa
Token Africa
Feature activation-0.001
Top resid features:
populations
Token populations
Feature activation+0.001
Top resid features:
writing
Token writing
Feature activation+0.026
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
first
Token first
Feature activation+0.006
Top resid features:
two
Token two
Feature activation+0.001
Top resid features:
drafts
Token drafts
Feature activation+0.026
Top resid features:
of
Token of
Feature activation+2.812
Top resid features:
Alien
Token Alien
Feature activation+0.014
Top resid features:
3
Token 3
Feature activation+0.015
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
His
Token His
Feature activation+0.010
Top resid features:
first
Token first
Feature activation+0.032
Top resid features:
Move
Token Move
Feature activation+0.013
Top resid features:
ments
Tokenments
Feature activation+0.005
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
an
Token an
Feature activation+0.002
Top resid features:
anthology
Token anthology
Feature activation+0.011
Top resid features:
of
Token of
Feature activation+2.850
Top resid features:
short
Token short
Feature activation+0.016
Top resid features:
sci
Token sci
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
fi
Tokenfi
Feature activation+0.002
Top resid features:
stories
Token stories
Feature activation+0.008
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.03

Head 3: 0.03

Head 4: 0.03

Head 5: 0.55

Head 6: 0.02

Head 7: 0.02

Head 8: 0.09

Head 9: 0.06

Head 10: 0.06

Head 11: 0.04

Positive logits

of1.94

Of1.92

of1.92

Of1.91

OF1.85

OF1.77

thereof1.76

oft1.59

ONY1.34

Thought1.31

yours1.31

Versions1.30

Abu1.27

Marble1.26

MR1.26

Niet1.25

Palest1.24

Zer1.23

Um1.22

Parables1.21

Negative logits

kish-1.49

ploy-1.49

gren-1.49

bourg-1.43

fortable-1.37

untarily-1.36

uable-1.36

vez-1.36

gaard-1.35

bard-1.35

bags-1.34

chy-1.33

enta-1.33

istani-1.33

gew-1.33

vertis-1.31

amazon-1.31

cot-1.31

install-1.30

-1.30

INTERVAL 2.875 - 3.194
CONTAINS 0.000%

inferior
Token inferior
Feature activation+0.000
to
Token to
Feature activation+0.000
dec
Token dec
Feature activation+0.000
ou
Tokenou
Feature activation+0.000
page
Tokenpage
Feature activation+0.000
medium
Token medium
Feature activation+3.194
and
Token and
Feature activation+0.000
made
Token made
Feature activation+0.000
it
Token it
Feature activation+0.000
even
Token even
Feature activation+0.000
thinner
Token thinner
Feature activation+0.000
mone
Tokenmone
Feature activation+0.000
lla
Tokenlla
Feature activation+0.000
which
Token which
Feature activation+0.000
matched
Token matched
Feature activation+0.000
the
Token the
Feature activation+0.000
strain
Token strain
Feature activation+3.054
being
Token being
Feature activation+0.000
worked
Token worked
Feature activation+0.000
on
Token on
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
of
Token of
Feature activation+0.000
earnings
Token earnings
Feature activation+0.000
(
Token (
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
multiple
Token multiple
Feature activation+2.962
differs
Token differs
Feature activation+0.058
depending
Token depending
Feature activation+0.000
on
Token on
Feature activation+0.000
sector
Token sector
Feature activation+0.000
).
Token).
Feature activation+0.000

INTERVAL 2.556 - 2.875
CONTAINS 0.001%

the
Token the
Feature activation+0.000
neuron
Token neuron
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
output
Token output
Feature activation+2.610
is
Token is
Feature activation+1.839
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
positive
Token positive
Feature activation+0.000
or
Token or
Feature activation+0.000
renew
Token renew
Feature activation+0.000
s
Tokens
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+2.847
has
Token has
Feature activation+0.848
two
Token two
Feature activation+0.000
dimensions
Token dimensions
Feature activation+0.000
:
Token:
Feature activation+0.000
a
Token a
Feature activation+0.000
?)
Token?)
Feature activation+0.000
concrete
Token concrete
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
,
Token,
Feature activation+0.000
these
Token these
Feature activation+0.000
trees
Token trees
Feature activation+2.559
are
Token are
Feature activation+1.009
merely
Token merely
Feature activation+0.000
abstract
Token abstract
Feature activation+0.000
representations
Token representations
Feature activation+0.000
of
Token of
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
To
Token To
Feature activation+0.000
progress
Token progress
Feature activation+0.000
from
Token from
Feature activation+0.000
one
Token one
Feature activation+0.000
island
Token island
Feature activation+2.600
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
fun
Token fun
Feature activation+0.000
.
Token.
Feature activation+0.000
Fun
Token Fun
Feature activation+0.000
Features
Token Features
Feature activation+0.000
4
Token 4
Feature activation+0.000
books
Token books
Feature activation+2.608
of
Token of
Feature activation+0.000
magic
Token magic
Feature activation+0.000
to
Token to
Feature activation+0.000
unlock
Token unlock
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 2.236 - 2.556
CONTAINS 0.001%

000
Token000
Feature activation+0.000
year
Token year
Feature activation+0.000
ago
Token ago
Feature activation+0.000
.
Token.
Feature activation+0.000
Another
Token Another
Feature activation+0.000
stream
Token stream
Feature activation+2.339
is
Token is
Feature activation+0.000
closely
Token closely
Feature activation+0.000
related
Token related
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
?"
Token?"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Although
TokenAlthough
Feature activation+0.000
the
Token the
Feature activation+0.000
anthology
Token anthology
Feature activation+2.303
features
Token features
Feature activation+0.000
established
Token established
Feature activation+0.000
names
Token names
Feature activation+0.000
and
Token and
Feature activation+0.000
writers
Token writers
Feature activation+0.122
communication
Token communication
Feature activation+0.000
.
Token.
Feature activation+0.000
These
Token These
Feature activation+0.000
interpret
Token interpret
Feature activation+0.000
ive
Tokenive
Feature activation+0.000
frameworks
Token frameworks
Feature activation+2.463
are
Token are
Feature activation+1.049
powerful
Token powerful
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
disputed
Token disputed
Feature activation+0.000
territory
Token territory
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
sw
Token sw
Feature activation+2.548
immers
Tokenimmers
Feature activation+1.933
,
Token,
Feature activation+0.000
led
Token led
Feature activation+0.000
by
Token by
Feature activation+0.000
pop
Token pop
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
cease
Token cease
Feature activation+0.000
-
Token-
Feature activation+0.000
fire
Tokenfire
Feature activation+0.000
line
Token line
Feature activation+2.347
in
Token in
Feature activation+0.000
Ukraine
Token Ukraine
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
expect
Token expect
Feature activation+0.000

INTERVAL 1.917 - 2.236
CONTAINS 0.003%

it
Token it
Feature activation+0.000
-
Token -
Feature activation+0.000
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
time
Token time
Feature activation+2.136
of
Token of
Feature activation+0.000
celebration
Token celebration
Feature activation+0.000
and
Token and
Feature activation+0.000
happiness
Token happiness
Feature activation+0.000
,''
Token,''
Feature activation+0.000
be
Token be
Feature activation+0.000
asked
Token asked
Feature activation+0.000
as
Token as
Feature activation+0.000
to
Token to
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.301
ľ
Tokenľ
Feature activation+1.965
how
Tokenhow
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
possible
Token possible
Feature activation+0.000
that
Token that
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Once
TokenOnce
Feature activation+0.000
inside
Token inside
Feature activation+0.000
the
Token the
Feature activation+0.000
base
Token base
Feature activation+2.077
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
tower
Token tower
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
confusing
Token confusing
Feature activation+0.000
series
Token series
Feature activation+2.104
of
Token of
Feature activation+0.000
letters
Token letters
Feature activation+0.000
is
Token is
Feature activation+0.000
in
Token in
Feature activation+0.000
line
Token line
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
what
Token what
Feature activation+0.000
makes
Token makes
Feature activation+0.000
the
Token the
Feature activation+0.000
community
Token community
Feature activation+1.987
what
Token what
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
no
Tokenno
Feature activation+0.000

INTERVAL 1.597 - 1.917
CONTAINS 0.005%

neuron
Token neuron
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
output
Token output
Feature activation+2.610
is
Token is
Feature activation+1.839
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
positive
Token positive
Feature activation+0.000
or
Token or
Feature activation+0.000
negative
Token negative
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
become
Token become
Feature activation+0.000
the
Token the
Feature activation+0.000
party
Token party
Feature activation+1.866
of
Token of
Feature activation+0.000
Ed
Token Ed
Feature activation+0.000
Gillespie
Token Gillespie
Feature activation+0.000
-
Token-
Feature activation+0.000
type
Tokentype
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
just
Token just
Feature activation+0.000
R
Token R
Feature activation+0.023
IB
TokenIB
Feature activation+1.692
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
n
Tokenn
Feature activation+0.000
ya
Token ya
Feature activation+0.000
!
Token!
Feature activation+0.000
on
Token on
Feature activation+0.000
phil
Token phil
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
lic
Tokenlic
Feature activation+0.000
f
Token f
Feature activation+0.010
akes
Tokenakes
Feature activation+1.619
and
Token and
Feature activation+0.000
for
Token for
Feature activation+0.000
geries
Tokengeries
Feature activation+0.025
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
realm
Token realm
Feature activation+0.000
of
Token of
Feature activation+0.000
vocabulary
Token vocabulary
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
ease
Token ease
Feature activation+1.687
might
Token might
Feature activation+0.130
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
ease
Token ease
Feature activation+0.158
of
Token of
Feature activation+0.000

INTERVAL 1.278 - 1.597
CONTAINS 0.009%

caps
Token caps
Feature activation+0.000
,
Token,
Feature activation+0.000
amber
Token amber
Feature activation+0.000
lens
Token lens
Feature activation+0.000
ed
Tokened
Feature activation+0.000
shades
Token shades
Feature activation+1.414
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+0.000
ultra
Token ultra
Feature activation+0.000
-
Token-
Feature activation+0.000
t
Tokent
Feature activation+0.000
expansion
Token expansion
Feature activation+0.000
would
Token would
Feature activation+0.000
mean
Token mean
Feature activation+0.000
that
Token that
Feature activation+0.000
said
Token said
Feature activation+0.000
heroes
Token heroes
Feature activation+1.349
would
Token would
Feature activation+0.000
appear
Token appear
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
weekend
Token weekend
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
two
Token two
Feature activation+0.000
-
Token-
Feature activation+0.000
day
Tokenday
Feature activation+1.431
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Paul
TokenPaul
Feature activation+0.000
Fest
Token Fest
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
you
Token you
Feature activation+0.000
ready
Token ready
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
day
Token day
Feature activation+1.438
,
Token,
Feature activation+0.000
there
Token there
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
t
Tokent
Feature activation+0.000
as
Tokenas
Feature activation+0.000
near
Token near
Feature activation+0.000
the
Token the
Feature activation+0.000
epic
Token epic
Feature activation+0.000
enter
Tokenenter
Feature activation+1.445
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000
multiple
Token multiple
Feature activation+0.000
submarine
Token submarine
Feature activation+0.000

INTERVAL 0.958 - 1.278
CONTAINS 0.017%

used
Token used
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
Pant
Token Pant
Feature activation+0.000
one
Tokenone
Feature activation+0.000
color
Token color
Feature activation+1.152
when
Token when
Feature activation+0.000
rec
Token rec
Feature activation+0.000
reating
Tokenreating
Feature activation+0.000
that
Token that
Feature activation+0.000
logo
Token logo
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
a
Token a
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
communities
Token communities
Feature activation+1.229
have
Token have
Feature activation+0.000
devised
Token devised
Feature activation+0.000
strategies
Token strategies
Feature activation+0.000
like
Token like
Feature activation+0.000
turn
Token turn
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
then
Tokenthen
Feature activation+0.000
who
Token who
Feature activation+0.000
knows
Token knows
Feature activation+0.000
what
Token what
Feature activation+0.000
sort
Token sort
Feature activation+1.202
of
Token of
Feature activation+0.000
'
Token '
Feature activation+0.000
di
Tokendi
Feature activation+0.000
plom
Tokenplom
Feature activation+0.000
acy
Tokenacy
Feature activation+0.000
Street
Token Street
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Un
TokenUn
Feature activation+0.000
identified
Tokenidentified
Feature activation+0.000
block
Token block
Feature activation+1.150
of
Token of
Feature activation+0.000
Le
Token Le
Feature activation+0.000
C
TokenC
Feature activation+0.000
ren
Tokenren
Feature activation+0.000
Street
Token Street
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
future
Token future
Feature activation+0.000
of
Token of
Feature activation+0.000
these
Token these
Feature activation+0.000
districts
Token districts
Feature activation+1.249
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
above
Token above
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000

INTERVAL 0.639 - 0.958
CONTAINS 0.025%

those
Token those
Feature activation+0.000
who
Token who
Feature activation+0.000
qualify
Token qualify
Feature activation+0.000
for
Token for
Feature activation+0.000
health
Token health
Feature activation+0.000
coverage
Token coverage
Feature activation+0.952
sometimes
Token sometimes
Feature activation+0.000
get
Token get
Feature activation+0.000
turned
Token turned
Feature activation+0.000
away
Token away
Feature activation+0.000
.
Token.
Feature activation+0.000
ended
Token ended
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
campaign
Token campaign
Feature activation+0.750
.
Token.
Feature activation+0.000
Another
Token Another
Feature activation+0.330
was
Token was
Feature activation+0.000
Rash
Token Rash
Feature activation+0.000
id
Tokenid
Feature activation+0.000
\
Token \
Feature activation+0.000
al
Tokenal
Feature activation+0.000
eph
Tokeneph
Feature activation+0.000
_
Token _
Feature activation+0.000
{
Token{
Feature activation+0.000
0
Token0
Feature activation+0.678
}}
Token}}
Feature activation+0.000
and
Token and
Feature activation+0.000
c
Token c
Feature activation+0.000
{\
Token {\
Feature activation+0.000
display
Tokendisplay
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Is
TokenIs
Feature activation+0.000
there
Token there
Feature activation+0.000
a
Token a
Feature activation+0.000
guarantee
Token guarantee
Feature activation+0.869
for
Token for
Feature activation+0.000
security
Token security
Feature activation+0.000
/
Token /
Feature activation+0.000
hacker
Token hacker
Feature activation+0.000
-
Token-
Feature activation+0.000
types
Token types
Feature activation+0.000
of
Token of
Feature activation+0.000
mushrooms
Token mushrooms
Feature activation+0.000
and
Token and
Feature activation+0.000
an
Token an
Feature activation+0.000
array
Token array
Feature activation+0.936
of
Token of
Feature activation+0.000
Asian
Token Asian
Feature activation+0.000
vegetables
Token vegetables
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000

INTERVAL 0.319 - 0.639
CONTAINS 0.049%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
proportion
Token proportion
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
cost
Token cost
Feature activation+0.439
being
Token being
Feature activation+0.000
expected
Token expected
Feature activation+0.000
at
Token at
Feature activation+0.000
that
Token that
Feature activation+0.000
time
Token time
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
default
Tokendefault
Feature activation+0.000
_
Token_
Feature activation+0.000
f
Tokenf
Feature activation+0.562
ov
Tokenov
Feature activation+0.000
70
Token 70
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Changes
TokenChanges
Feature activation+0.000
matter
Token matter
Feature activation+0.000
?!
Token?!
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
match
Tokenmatch
Feature activation+0.345
the
Token the
Feature activation+0.000
cooker
Token cooker
Feature activation+0.000
to
Token to
Feature activation+0.000
your
Token your
Feature activation+0.000
cooking
Token cooking
Feature activation+0.000
100
Token 100
Feature activation+0.000
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
even
Token even
Feature activation+0.000
50
Token 50
Feature activation+0.000
%
Token%
Feature activation+0.407
match
Token match
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
hard
Token hard
Feature activation+0.000
to
Token to
Feature activation+0.000
is
Token is
Feature activation+0.000
fielding
Token fielding
Feature activation+0.000
calls
Token calls
Feature activation+0.000
and
Token and
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
stories
Token stories
Feature activation+0.326
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
every
Tokenevery
Feature activation+0.000
week
Token week
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.319
CONTAINS 99.890%

they
Token they
Feature activation+0.000
love
Token love
Feature activation+0.000
.
Token.
Feature activation+0.000
Bin
Token Bin
Feature activation+0.000
Laden
Token Laden
Feature activation+0.000
et
Token et
Feature activation+0.000
al
Token al
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
eternal
Token eternal
Feature activation+0.000
warriors
Token warriors
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
safe
Token safe
Feature activation+0.000
,
Token,
Feature activation+0.000
everyone
Token everyone
Feature activation+0.000
around
Token around
Feature activation+0.000
Kara
Token Kara
Feature activation+0.000
is
Token is
Feature activation+0.000
happy
Token happy
Feature activation+0.000
,
Token,
Feature activation+0.000
except
Token except
Feature activation+0.000
s
Tokens
Feature activation+0.000
not
Token not
Feature activation+0.000
good
Token good
Feature activation+0.000
enough
Token enough
Feature activation+0.000
.
Token.
Feature activation+0.000
What
Token What
Feature activation+0.000
we
Token we
Feature activation+0.000
need
Token need
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
woman
Token woman
Feature activation+0.000
it
Token it
Feature activation+0.000
should
Token should
Feature activation+0.000
not
Token not
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
Ralph
Token Ralph
Feature activation+0.000
N
Token N
Feature activation+0.000
ader
Tokenader
Feature activation+0.000
-
Token-
Feature activation+0.000
type
Tokentype
Feature activation+0.000
person
Token person
Feature activation+0.000
governments
Token governments
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
fore
Token fore
Feature activation+0.000
close
Tokenclose
Feature activation+0.000
all
Token all
Feature activation+0.000
possibility
Token possibility
Feature activation+0.000
of
Token of
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 H5.5: (feature 44256)

TOP ACTIVATIONS
MAX = 3.909

be
Token be
Feature activation+0.000
cool
Token cool
Feature activation+0.000
with
Token with
Feature activation+0.000
both
Token both
Feature activation+0.000
She
Token She
Feature activation+0.999
ree
Tokenree
Feature activation+3.909
and
Token and
Feature activation+1.969
Kim
Token Kim
Feature activation+0.000
so
Token so
Feature activation+0.000
I
Token I
Feature activation+0.000
believe
Token believe
Feature activation+0.000
a
Token a
Feature activation+0.000
pleasant
Token pleasant
Feature activation+0.000
selection
Token selection
Feature activation+0.000
headache
Token headache
Feature activation+0.000
.
Token.
Feature activation+0.000
Joseph
Token Joseph
Feature activation+3.881
wore
Token wore
Feature activation+0.000
No
Token No
Feature activation+0.000
13
Token13
Feature activation+0.000
with
Token with
Feature activation+0.000
some
Token some
Feature activation+0.000
in
Token in
Feature activation+0.000
A
Token A
Feature activation+0.979
5
Token5
Feature activation+2.110
and
Token and
Feature activation+1.356
A
Token A
Feature activation+0.864
6
Token6
Feature activation+3.687
in
Token in
Feature activation+0.876
the
Token the
Feature activation+0.000
4
Token 4
Feature activation+0.000
x
Token x
Feature activation+0.000
50
Token 50
Feature activation+0.482
moved
Token moved
Feature activation+0.000
south
Token south
Feature activation+0.000
in
Token in
Feature activation+0.000
2004
Token 2004
Feature activation+0.000
.
Token.
Feature activation+0.000
Mexico
Token Mexico
Feature activation+3.656
City
Token City
Feature activation+2.293
,
Token,
Feature activation+1.541
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
lands
Tokenlands
Feature activation+0.000
Development
Token Development
Feature activation+0.000
Authority
Token Authority
Feature activation+0.192
(
Token (
Feature activation+0.000
DD
TokenDD
Feature activation+0.692
DA
TokenDA
Feature activation+3.653
)
Token)
Feature activation+0.355
have
Token have
Feature activation+0.199
a
Token a
Feature activation+0.000
"
Token "
Feature activation+0.000
moral
Tokenmoral
Feature activation+0.000
Dale
Token Dale
Feature activation+0.000
We
Token We
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
and
Token and
Feature activation+0.150
Boyd
Token Boyd
Feature activation+1.641
Gordon
Token Gordon
Feature activation+3.579
,
Token,
Feature activation+1.050
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
general
Token general
Feature activation+0.000
manager
Token manager
Feature activation+0.000
all
Token all
Feature activation+0.000
-
Token-
Feature activation+0.000
region
Tokenregion
Feature activation+0.000
players
Token players
Feature activation+0.000
.
Token.
Feature activation+0.000
Engel
Token Engel
Feature activation+3.560
is
Token is
Feature activation+1.478
a
Token a
Feature activation+0.000
rock
Token rock
Feature activation+0.000
at
Token at
Feature activation+0.000
center
Token center
Feature activation+0.000
,
Token,
Feature activation+0.000
Colin
Token Colin
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
ish
Tokenish
Feature activation+0.146
ol
Tokenol
Feature activation+1.203
m
Tokenm
Feature activation+3.541
III
Token III
Feature activation+0.000
,
Token,
Feature activation+0.044
62
Token 62
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
discrete
Token discrete
Feature activation+0.000
NA
Token NA
Feature activation+0.081
c
Tokenc
Feature activation+0.000
core
Token core
Feature activation+0.000
and
Token and
Feature activation+0.000
shell
Token shell
Feature activation+3.431
lesions
Token lesions
Feature activation+0.000
produced
Token produced
Feature activation+0.000
26
Token 26
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Al
TokenAl
Feature activation+0.512
mond
Tokenmond
Feature activation+1.889
jelly
Token jelly
Feature activation+3.387
is
Token is
Feature activation+1.331
eaten
Token eaten
Feature activation+0.000
chilled
Token chilled
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
y
Tokeny
Feature activation+0.818
edits
Token edits
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
sometimes
Token sometimes
Feature activation+0.000
Shay
Token Shay
Feature activation+3.374
writes
Token writes
Feature activation+0.004
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
tweak
Token tweak
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
idea
Token idea
Feature activation+0.000
of
Token of
Feature activation+0.000
Car
Token Car
Feature activation+1.293
ano
Tokenano
Feature activation+3.367
returning
Token returning
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
five
Token five
Feature activation+0.000
-
Token-
Feature activation+0.000
the
Token the
Feature activation+0.000
anxiety
Token anxiety
Feature activation+0.000
we
Token we
Feature activation+0.000
felt
Token felt
Feature activation+0.000
over
Token over
Feature activation+0.000
Liu
Token Liu
Feature activation+3.276
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.122
funeral
Token funeral
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
lead
Token lead
Feature activation+0.000
the
Token the
Feature activation+0.000
attack
Token attack
Feature activation+0.000
.
Token.
Feature activation+0.000
Gideon
Token Gideon
Feature activation+3.259
went
Token went
Feature activation+0.000
2
Token 2
Feature activation+0.000
-
Token-
Feature activation+0.000
for
Tokenfor
Feature activation+0.000
-
Token-
Feature activation+0.000
O
Token O
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Donnell
TokenDonnell
Feature activation+0.000
called
Token called
Feature activation+0.000
Donald
Token Donald
Feature activation+3.248
a
Token a
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
sn
Tokensn
Feature activation+0.000
ake
Tokenake
Feature activation+0.000
us
Token us
Feature activation+0.000
reun
Token reun
Feature activation+0.000
iting
Tokeniting
Feature activation+0.000
Mary
Token Mary
Feature activation+0.000
,
Token,
Feature activation+0.000
Mel
Token Mel
Feature activation+3.209
and
Token and
Feature activation+1.529
Sue
Token Sue
Feature activation+0.753
are
Token are
Feature activation+0.000
very
Token very
Feature activation+0.000
high
Token high
Feature activation+0.000
in
Token in
Feature activation+0.000
both
Token both
Feature activation+0.455
the
Token the
Feature activation+0.000
iPad
Token iPad
Feature activation+0.000
Air
Token Air
Feature activation+1.535
2
Token 2
Feature activation+3.201
and
Token and
Feature activation+1.380
the
Token the
Feature activation+0.000
iPad
Token iPad
Feature activation+0.000
mini
Token mini
Feature activation+0.000
3
Token 3
Feature activation+0.000
mph
Tokenmph
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pl
TokenPl
Feature activation+3.066
ato
Tokenato
Feature activation+3.194
,
Token,
Feature activation+2.641
then
Token then
Feature activation+0.042
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
Chevrolet
Token Chevrolet
Feature activation+0.000
and
Token and
Feature activation+0.000
above
Token above
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
up
Token up
Feature activation+1.090
values
Tokenvalues
Feature activation+3.174
are
Token are
Feature activation+0.102
mut
Token mut
Feature activation+0.000
able
Tokenable
Feature activation+0.169
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
(
Token (
Feature activation+0.000
D
TokenD
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
Eric
Token Eric
Feature activation+1.101
kson
Tokenkson
Feature activation+3.173
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.393
characterization
Token characterization
Feature activation+0.000
of
Token of
Feature activation+0.000

Top DFA by src position
MAX = 4.321

for
Token for
Feature activation+0.000
Top resid features:
Kim
Token Kim
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+0.040
Top resid features:
She
Token She
Feature activation-0.012
Top resid features:
ree
Tokenree
Feature activation-0.009
Top resid features:
(
Token (
Feature activation+4.321
Top resid features:
if
Tokenif
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
gossip
Token gossip
Feature activation-0.001
Top resid features:
ends
Token ends
Feature activation-0.000
Top resid features:
up
Token up
Feature activation-0.000
Top resid features:
Sl
Token Sl
Feature activation-0.019
Top resid features:
ade
Tokenade
Feature activation-0.004
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
Jonathan
Token Jonathan
Feature activation-0.001
Top resid features:
Joseph
Token Joseph
Feature activation-0.000
Top resid features:
will
Token will
Feature activation+4.280
Top resid features:
travel
Token travel
Feature activation+0.015
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
this
Token this
Feature activation-0.003
Top resid features:
gives
Token gives
Feature activation-0.005
Top resid features:
Jones
Token Jones
Feature activation-0.003
Top resid features:
A
Token A
Feature activation+0.006
Top resid features:
5
Token5
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.096
Top resid features:
A
Token A
Feature activation+0.012
Top resid features:
6
Token6
Feature activation-0.000
Top resid features:
in
Token in
Feature activation+3.842
Top resid features:
the
Token the
Feature activation+0.040
Top resid features:
4
Token 4
Feature activation+0.003
Top resid features:
x
Token x
Feature activation+0.013
Top resid features:
50
Token 50
Feature activation+0.001
Top resid features:
meter
Token meter
Feature activation-0.001
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
both
Token both
Feature activation+0.004
Top resid features:
Montreal
Token Montreal
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
Mexico
Token Mexico
Feature activation-0.001
Top resid features:
City
Token City
Feature activation+3.787
Top resid features:
are
Token are
Feature activation+0.113
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
sights
Token sights
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
receiver
Token receiver
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
DD
Token DD
Feature activation+0.000
Top resid features:
DA
TokenDA
Feature activation-0.000
Top resid features:
also
Token also
Feature activation+4.069
Top resid features:
had
Token had
Feature activation+0.047
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
part
Token part
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
play
Token play
Feature activation-0.000
Top resid features:
We
Token We
Feature activation-0.004
Top resid features:
ise
Tokenise
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
Boyd
Token Boyd
Feature activation-0.005
Top resid features:
Gordon
Token Gordon
Feature activation+0.011
Top resid features:
by
Token by
Feature activation+3.994
Top resid features:
Staff
Token Staff
Feature activation+0.001
Top resid features:
Writer
Token Writer
Feature activation+0.001
Top resid features:
/
Token /
Feature activation+0.001
Top resid features:
Philadelphia
Token Philadelphia
Feature activation+0.000
Top resid features:
Flyers
Token Flyers
Feature activation+0.000
Top resid features:
Cook
Token Cook
Feature activation-0.002
Top resid features:
s
Tokens
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.007
Top resid features:
Austin
Token Austin
Feature activation+0.001
Top resid features:
Engel
Token Engel
Feature activation-0.008
Top resid features:
,
Token,
Feature activation+3.923
Top resid features:
with
Token with
Feature activation+0.003
Top resid features:
James
Token James
Feature activation+0.002
Top resid features:
High
Token High
Feature activation-0.003
Top resid features:
smith
Tokensmith
Feature activation-0.012
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
Andrea
Token Andrea
Feature activation+0.002
Top resid features:
Ch
Token Ch
Feature activation+0.016
Top resid features:
ish
Tokenish
Feature activation+0.000
Top resid features:
ol
Tokenol
Feature activation-0.004
Top resid features:
m
Tokenm
Feature activation-0.011
Top resid features:
are
Token are
Feature activation+3.967
Top resid features:
charged
Token charged
Feature activation-0.000
Top resid features:
with
Token with
Feature activation-0.019
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
one
Token one
Feature activation-0.000
Top resid features:
count
Token count
Feature activation+0.002
Top resid features:
NA
Token NA
Feature activation+0.005
Top resid features:
c
Tokenc
Feature activation-0.001
Top resid features:
core
Token core
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.014
Top resid features:
shell
Token shell
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+3.754
Top resid features:
respectively
Token respectively
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
examined
Token examined
Feature activation-0.001
Top resid features:
arousal
Token arousal
Feature activation-0.013
Top resid features:
coconut
Token coconut
Feature activation+0.001
Top resid features:
milk
Token milk
Feature activation-0.003
Top resid features:
or
Token or
Feature activation+0.012
Top resid features:
almond
Token almond
Feature activation+0.002
Top resid features:
jelly
Token jelly
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+3.685
Top resid features:
called
Token called
Feature activation+0.042
Top resid features:
ann
Token ann
Feature activation-0.001
Top resid features:
ind
Tokenind
Feature activation-0.000
Top resid features:
of
Tokenof
Feature activation-0.001
Top resid features:
u
Tokenu
Feature activation-0.002
Top resid features:
mean
Token mean
Feature activation+0.000
Top resid features:
Mind
Token Mind
Feature activation-0.008
Top resid features:
y
Tokeny
Feature activation-0.012
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
Shay
Token Shay
Feature activation+0.004
Top resid features:
lol
Token lol
Feature activation+3.756
Top resid features:
),
Token),
Feature activation+0.003
Top resid features:
we
Token we
Feature activation-0.003
Top resid features:
work
Token work
Feature activation-0.005
Top resid features:
collectively
Token collectively
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
m
Tokenm
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
Gina
Token Gina
Feature activation+0.000
Top resid features:
Car
Token Car
Feature activation+0.002
Top resid features:
ano
Tokenano
Feature activation-0.002
Top resid features:
are
Token are
Feature activation+3.728
Top resid features:
all
Token all
Feature activation+0.032
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
matter
Token matter
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
getting
Token getting
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.004
Top resid features:
Wen
Token Wen
Feature activation+0.004
Top resid features:
j
Tokenj
Feature activation-0.000
Top resid features:
ian
Tokenian
Feature activation-0.001
Top resid features:
Liu
Token Liu
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+3.611
Top resid features:
two
Token two
Feature activation+0.076
Top resid features:
police
Token police
Feature activation+0.000
Top resid features:
officers
Token officers
Feature activation-0.002
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.001
Top resid features:
one
Token one
Feature activation-0.000
Top resid features:
Logan
Token Logan
Feature activation+0.008
Top resid features:
Taylor
Token Taylor
Feature activation-0.050
Top resid features:
and
Token and
Feature activation-0.009
Top resid features:
Ronnie
Token Ronnie
Feature activation-0.002
Top resid features:
Gideon
Token Gideon
Feature activation-0.015
Top resid features:
each
Token each
Feature activation+3.655
Top resid features:
knocked
Token knocked
Feature activation-0.011
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
runs
Token runs
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ļ
TokenĻ
Feature activation-0.000
Top resid features:
Donnell
TokenDonnell
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
Donald
Token Donald
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+3.113
Top resid features:
both
Token both
Feature activation+0.442
Top resid features:
outspoken
Token outspoken
Feature activation+0.006
Top resid features:
celebrities
Token celebrities
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
have
Token have
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.083
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Sue
Token Sue
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.017
Top resid features:
Mel
Token Mel
Feature activation-0.000
Top resid features:
for
Token for
Feature activation+3.541
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
cook
Token cook
Feature activation-0.001
Top resid features:
ery
Tokenery
Feature activation+0.000
Top resid features:
show
Token show
Feature activation-0.000
Top resid features:
after
Token after
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
iPad
Token iPad
Feature activation+0.003
Top resid features:
Air
Token Air
Feature activation+0.005
Top resid features:
2
Token 2
Feature activation-0.006
Top resid features:
are
Token are
Feature activation+3.605
Top resid features:
not
Token not
Feature activation+0.010
Top resid features:
able
Token able
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
payments
Token payments
Feature activation-0.002
Top resid features:
ton
Tokenton
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
Neal
Token Neal
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+0.048
Top resid features:
Plato
Token Plato
Feature activation-0.038
Top resid features:
came
Token came
Feature activation+3.438
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
blows
Token blows
Feature activation+0.000
Top resid features:
within
Token within
Feature activation-0.001
Top resid features:
seconds
Token seconds
Feature activation-0.000
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
environment
Token environment
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+0.033
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
up
Token up
Feature activation+0.002
Top resid features:
values
Tokenvalues
Feature activation+0.002
Top resid features:
are
Token are
Feature activation+3.491
Top resid features:
mut
Token mut
Feature activation+0.003
Top resid features:
able
Tokenable
Feature activation-0.011
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Lua
TokenLua
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.018
Top resid features:
Er
Token Er
Feature activation+0.002
Top resid features:
ick
Tokenick
Feature activation-0.001
Top resid features:
Eric
Token Eric
Feature activation+0.000
Top resid features:
kson
Tokenkson
Feature activation-0.003
Top resid features:
have
Token have
Feature activation+3.473
Top resid features:
gone
Token gone
Feature activation+0.006
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
war
Token war
Feature activation-0.001
Top resid features:
over
Token over
Feature activation+0.002
Top resid features:
Texas
Token Texas
Feature activation-0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.04

Head 2: 0.02

Head 3: 0.03

Head 4: 0.02

Head 5: 0.54

Head 6: 0.02

Head 7: 0.02

Head 8: 0.07

Head 9: 0.08

Head 10: 0.07

Head 11: 0.03

Positive logits

Unloaded1.81

aida1.76

/*1.75

UCHIJ1.74

Annotations1.72

Flavoring1.66

perture1.65

emouth1.61

ora1.61

heid1.61

wick1.61

/**1.60

¨1.58

deen1.55

ijah1.55

steamapps1.55

.?1.55

Keys1.54

Swap1.54

"]=>1.53

Negative logits

antha-1.50

petition-1.49

semen-1.49

iable-1.46

ITE-1.46

estimating-1.45

lease-1.40

requesting-1.38

UU-1.38

ITS-1.37

cel-1.36

rapes-1.36

etta-1.35

biologists-1.34

veterin-1.32

Azerbai-1.32

onis-1.32

Insight-1.32

printers-1.31

Ec-1.31

INTERVAL 3.518 - 3.909
CONTAINS 0.001%

,
Token,
Feature activation+0.000
Colin
Token Colin
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
ish
Tokenish
Feature activation+0.146
ol
Tokenol
Feature activation+1.203
m
Tokenm
Feature activation+3.541
III
Token III
Feature activation+0.000
,
Token,
Feature activation+0.044
62
Token 62
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
A
Token A
Feature activation+0.979
5
Token5
Feature activation+2.110
and
Token and
Feature activation+1.356
A
Token A
Feature activation+0.864
6
Token6
Feature activation+3.687
in
Token in
Feature activation+0.876
the
Token the
Feature activation+0.000
4
Token 4
Feature activation+0.000
x
Token x
Feature activation+0.000
50
Token 50
Feature activation+0.482
a
Token a
Feature activation+0.000
pleasant
Token pleasant
Feature activation+0.000
selection
Token selection
Feature activation+0.000
headache
Token headache
Feature activation+0.000
.
Token.
Feature activation+0.000
Joseph
Token Joseph
Feature activation+3.881
wore
Token wore
Feature activation+0.000
No
Token No
Feature activation+0.000
13
Token13
Feature activation+0.000
with
Token with
Feature activation+0.000
some
Token some
Feature activation+0.000
moved
Token moved
Feature activation+0.000
south
Token south
Feature activation+0.000
in
Token in
Feature activation+0.000
2004
Token 2004
Feature activation+0.000
.
Token.
Feature activation+0.000
Mexico
Token Mexico
Feature activation+3.656
City
Token City
Feature activation+2.293
,
Token,
Feature activation+1.541
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
Dale
Token Dale
Feature activation+0.000
We
Token We
Feature activation+0.000
ise
Tokenise
Feature activation+0.000
and
Token and
Feature activation+0.150
Boyd
Token Boyd
Feature activation+1.641
Gordon
Token Gordon
Feature activation+3.579
,
Token,
Feature activation+1.050
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
general
Token general
Feature activation+0.000
manager
Token manager
Feature activation+0.000

INTERVAL 3.127 - 3.518
CONTAINS 0.001%

and
Token and
Feature activation+0.000
above
Token above
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
up
Token up
Feature activation+1.090
values
Tokenvalues
Feature activation+3.174
are
Token are
Feature activation+0.102
mut
Token mut
Feature activation+0.000
able
Tokenable
Feature activation+0.169
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
idea
Token idea
Feature activation+0.000
of
Token of
Feature activation+0.000
Car
Token Car
Feature activation+1.293
ano
Tokenano
Feature activation+3.367
returning
Token returning
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
five
Token five
Feature activation+0.000
-
Token-
Feature activation+0.000
(
Token (
Feature activation+0.000
D
TokenD
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
Eric
Token Eric
Feature activation+1.101
kson
Tokenkson
Feature activation+3.173
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.393
characterization
Token characterization
Feature activation+0.000
of
Token of
Feature activation+0.000
us
Token us
Feature activation+0.000
reun
Token reun
Feature activation+0.000
iting
Tokeniting
Feature activation+0.000
Mary
Token Mary
Feature activation+0.000
,
Token,
Feature activation+0.000
Mel
Token Mel
Feature activation+3.209
and
Token and
Feature activation+1.529
Sue
Token Sue
Feature activation+0.753
are
Token are
Feature activation+0.000
very
Token very
Feature activation+0.000
high
Token high
Feature activation+0.000
discrete
Token discrete
Feature activation+0.000
NA
Token NA
Feature activation+0.081
c
Tokenc
Feature activation+0.000
core
Token core
Feature activation+0.000
and
Token and
Feature activation+0.000
shell
Token shell
Feature activation+3.431
lesions
Token lesions
Feature activation+0.000
produced
Token produced
Feature activation+0.000
26
Token 26
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000

INTERVAL 2.736 - 3.127
CONTAINS 0.003%

NA
Token NA
Feature activation+0.078
c
Tokenc
Feature activation+0.000
core
Token core
Feature activation+0.000
but
Token but
Feature activation+0.105
not
Token not
Feature activation+0.000
shell
Token shell
Feature activation+2.758
lesions
Token lesions
Feature activation+0.946
eliminated
Token eliminated
Feature activation+0.000
arousal
Token arousal
Feature activation+0.000
effects
Token effects
Feature activation+0.000
of
Token of
Feature activation+0.000
{\
Token {\
Feature activation+0.000
math
Tokenmath
Feature activation+0.000
f
Tokenf
Feature activation+0.000
rak
Tokenrak
Feature activation+0.000
{
Token {
Feature activation+0.000
c
Tokenc
Feature activation+2.857
}}}
Token}}}
Feature activation+0.000
,
Token ,
Feature activation+0.000
implies
Token implies
Feature activation+0.000
that
Token that
Feature activation+0.000
c
Token c
Feature activation+2.592
went
Token went
Feature activation+0.000
to
Token to
Feature activation+0.000
high
Token high
Feature activation+0.000
school
Token school
Feature activation+0.000
in
Token in
Feature activation+0.000
Wood
Token Wood
Feature activation+3.088
stock
Tokenstock
Feature activation+0.000
,
Token,
Feature activation+0.000
Ga
Token Ga
Feature activation+0.000
.,
Token.,
Feature activation+0.000
about
Token about
Feature activation+0.000
.
Token.
Feature activation+0.000
06
Token06
Feature activation+0.000
miles
Token miles
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
South
Token South
Feature activation+3.082
Pond
Token Pond
Feature activation+0.000
is
Token is
Feature activation+0.449
4
Token 4
Feature activation+0.000
.
Token.
Feature activation+0.000
17
Token17
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Neill
TokenNeill
Feature activation+0.000
.
Token.
Feature activation+0.000
D
Token D
Feature activation+1.014
ack
Tokenack
Feature activation+2.806
lasted
Token lasted
Feature activation+0.000
less
Token less
Feature activation+0.000
than
Token than
Feature activation+0.000
half
Token half
Feature activation+0.000
an
Token an
Feature activation+0.000

INTERVAL 2.345 - 2.736
CONTAINS 0.005%

Hogwarts
Token Hogwarts
Feature activation+0.000
,
Token,
Feature activation+0.000
trapping
Token trapping
Feature activation+0.000
Harry
Token Harry
Feature activation+0.000
and
Token and
Feature activation+0.223
Ron
Token Ron
Feature activation+2.479
miles
Token miles
Feature activation+0.000
beneath
Token beneath
Feature activation+0.000
the
Token the
Feature activation+0.000
surface
Token surface
Feature activation+0.000
.
Token.
Feature activation+0.000
dinner
Token dinner
Feature activation+0.000
or
Token or
Feature activation+0.000
something
Token something
Feature activation+0.000
.
Token.
Feature activation+0.000
Sab
Token Sab
Feature activation+2.086
ine
Tokenine
Feature activation+2.418
presses
Token presses
Feature activation+0.000
Jac
Token Jac
Feature activation+0.483
inda
Tokeninda
Feature activation+0.096
about
Token about
Feature activation+0.000
her
Token her
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Mol
Token Mol
Feature activation+1.148
ni
Tokenni
Feature activation+1.158
ya
Tokenya
Feature activation+2.521
-
Token-
Feature activation+2.210
M
TokenM
Feature activation+1.381
was
Token was
Feature activation+0.145
retired
Token retired
Feature activation+0.000
from
Token from
Feature activation+0.000
and
Token and
Feature activation+0.000
said
Token said
Feature activation+0.000
she
Token she
Feature activation+0.000
had
Token had
Feature activation+0.000
known
Token known
Feature activation+0.000
Kelly
Token Kelly
Feature activation+2.714
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
time
Token time
Feature activation+0.000
and
Token and
Feature activation+0.000
young
Token young
Feature activation+0.000
adults
Token adults
Feature activation+0.000
consumed
Token consumed
Feature activation+0.000
drinks
Token drinks
Feature activation+0.380
containing
Token containing
Feature activation+0.000
fat
Token fat
Feature activation+2.353
,
Token,
Feature activation+0.480
glucose
Token glucose
Feature activation+0.000
,
Token,
Feature activation+0.000
protein
Token protein
Feature activation+0.382
and
Token and
Feature activation+0.922

INTERVAL 1.954 - 2.345
CONTAINS 0.008%

GHC
Token GHC
Feature activation+0.000
.
Token.
Feature activation+0.000
Stack
TokenStack
Feature activation+0.190
.
Token.
Feature activation+0.084
current
Tokencurrent
Feature activation+0.000
Call
TokenCall
Feature activation+2.143
Stack
TokenStack
Feature activation+0.530
returns
Token returns
Feature activation+0.000
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
cost
Token cost
Feature activation+0.000
67
Token 67
Feature activation+0.000
yards
Token yards
Feature activation+0.000
rushing
Token rushing
Feature activation+0.000
and
Token and
Feature activation+0.000
Thiel
Token Thiel
Feature activation+1.211
en
Tokenen
Feature activation+1.982
only
Token only
Feature activation+0.000
needed
Token needed
Feature activation+0.000
two
Token two
Feature activation+0.000
attempts
Token attempts
Feature activation+0.000
to
Token to
Feature activation+0.000
fruit
Token fruit
Feature activation+0.000
flies
Token flies
Feature activation+0.000
,
Token,
Feature activation+0.000
car
Token car
Feature activation+0.367
r
Tokenr
Feature activation+0.329
ion
Tokenion
Feature activation+2.224
flies
Token flies
Feature activation+0.000
and
Token and
Feature activation+0.000
beetles
Token beetles
Feature activation+0.274
.
Token.
Feature activation+0.000
Because
Token Because
Feature activation+0.000
t
Tokent
Feature activation+0.000
mean
Token mean
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
double
Token double
Feature activation+2.138
agent
Token agent
Feature activation+0.602
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
fact
Token fact
Feature activation+0.000
refused
Token refused
Feature activation+0.000
to
Token to
Feature activation+0.000
sign
Token sign
Feature activation+0.000
up
Token up
Feature activation+0.000
.
Token.
Feature activation+0.000
UK
Token UK
Feature activation+1.962
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+0.000
David
Token David
Feature activation+0.000
Cameron
Token Cameron
Feature activation+0.000
said
Token said
Feature activation+0.000

INTERVAL 1.563 - 1.954
CONTAINS 0.015%

ell
Tokenell
Feature activation+0.000
yan
Tokenyan
Feature activation+0.000
ne
Tokenne
Feature activation+0.000
Conway
Token Conway
Feature activation+0.000
,
Token,
Feature activation+0.000
Trump
Token Trump
Feature activation+1.915
's
Token's
Feature activation+1.152
campaign
Token campaign
Feature activation+0.000
manager
Token manager
Feature activation+0.000
,
Token,
Feature activation+0.000
referenced
Token referenced
Feature activation+0.000
provincial
Token provincial
Feature activation+0.000
council
Token council
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
security
Token security
Feature activation+1.662
committee
Token committee
Feature activation+0.000
in
Token in
Feature activation+0.000
Mosul
Token Mosul
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
p
Token p
Feature activation+0.000
ours
Tokenours
Feature activation+0.000
out
Token out
Feature activation+0.000
to
Token to
Feature activation+0.000
Ed
Token Ed
Feature activation+0.828
ith
Tokenith
Feature activation+1.910
and
Token and
Feature activation+1.348
the
Token the
Feature activation+0.000
family
Token family
Feature activation+0.000
and
Token and
Feature activation+0.000
our
Token our
Feature activation+0.000
18
Token18
Feature activation+0.134
%),
Token%),
Feature activation+0.000
and
Token and
Feature activation+0.000
white
Token white
Feature activation+0.210
and
Token and
Feature activation+0.285
Native
Token Native
Feature activation+1.590
Hawaiian
Token Hawaiian
Feature activation+0.573
/
Token/
Feature activation+1.003
Pacific
TokenPacific
Feature activation+1.796
Island
Token Island
Feature activation+0.852
er
Tokener
Feature activation+1.395
bonds
Token bonds
Feature activation+0.000
with
Token with
Feature activation+0.000
other
Token other
Feature activation+0.000
gluten
Token gluten
Feature activation+0.132
in
Tokenin
Feature activation+0.261
and
Token and
Feature activation+1.770
gl
Token gl
Feature activation+0.000
i
Tokeni
Feature activation+1.066
adin
Tokenadin
Feature activation+2.341
molecules
Token molecules
Feature activation+0.000
they
Token they
Feature activation+0.000

INTERVAL 1.173 - 1.563
CONTAINS 0.027%

Polish
Token Polish
Feature activation+0.000
notation
Token notation
Feature activation+0.000
as
Token as
Feature activation+0.000
+
Token +
Feature activation+0.000
1
Token 1
Feature activation+0.000
2
Token 2
Feature activation+1.459
(
Token (
Feature activation+0.000
pre
Tokenpre
Feature activation+0.000
-
Token-
Feature activation+0.000
fix
Tokenfix
Feature activation+0.000
),
Token),
Feature activation+0.000
private
Tokenprivate
Feature activation+0.000
firm
Token firm
Feature activation+0.000
).
Token).
Feature activation+0.000
The
Token The
Feature activation+0.000
Sn
Token Sn
Feature activation+0.317
ell
Tokenell
Feature activation+1.218
standard
Token standard
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
much
Token much
Feature activation+0.000
tougher
Token tougher
Feature activation+0.000
Open
Token Open
Feature activation+0.951
Form
Token Form
Feature activation+1.767
ats
Tokenats
Feature activation+0.291
and
Token and
Feature activation+0.294
Protocol
Token Protocol
Feature activation+2.106
s
Tokens
Feature activation+1.517
are
Token are
Feature activation+0.001
used
Token used
Feature activation+0.000
,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.000
all
Token all
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Red
TokenRed
Feature activation+0.977
and
Token and
Feature activation+1.079
White
Token White
Feature activation+3.017
are
Token are
Feature activation+1.187
thought
Token thought
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
unlikely
Token unlikely
Feature activation+0.000
to
Token to
Feature activation+0.000
recreation
Token recreation
Feature activation+0.000
space
Token space
Feature activation+0.341
and
Token and
Feature activation+0.000
retail
Token retail
Feature activation+0.711
and
Token and
Feature activation+0.000
restaurant
Token restaurant
Feature activation+1.491
spots
Token spots
Feature activation+0.000
.
Token.
Feature activation+0.000
Engel
Token Engel
Feature activation+0.000
Bur
Token Bur
Feature activation+0.000
man
Tokenman
Feature activation+0.000

INTERVAL 0.782 - 1.173
CONTAINS 0.058%

much
Token much
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.090
of
Token of
Feature activation+0.000
Mexico
Token Mexico
Feature activation+0.808
,
Token,
Feature activation+0.133
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+0.000
of
Token of
Feature activation+0.000
Canada
Token Canada
Feature activation+0.000
trans
Token trans
Feature activation+0.000
verse
Tokenverse
Feature activation+0.000
colon
Token colon
Feature activation+0.184
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
descending
Token descending
Feature activation+0.807
colon
Token colon
Feature activation+0.173
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
s
Token s
Feature activation+0.000
igm
Tokenigm
Feature activation+0.000
,
Token,
Feature activation+0.000
featuring
Token featuring
Feature activation+0.000
a
Token a
Feature activation+0.000
display
Token display
Feature activation+0.000
of
Token of
Feature activation+0.000
missiles
Token missiles
Feature activation+0.791
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
April
Token April
Feature activation+0.000
15
Token 15
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
we
Token we
Feature activation+0.000
will
Token will
Feature activation+0.000
support
Token support
Feature activation+0.000
Stewart
Token Stewart
Feature activation+1.042
and
Token and
Feature activation+0.547
put
Token put
Feature activation+0.000
a
Token a
Feature activation+0.000
comprehensive
Token comprehensive
Feature activation+0.000
rehabilitation
Token rehabilitation
Feature activation+0.000
and
Token and
Feature activation+0.000
responses
Token responses
Feature activation+0.000
of
Token of
Feature activation+0.000
Fair
Token Fair
Feature activation+0.206
and
Token and
Feature activation+0.369
Poor
Token Poor
Feature activation+1.045
into
Token into
Feature activation+0.000
1
Token 1
Feature activation+0.000
category
Token category
Feature activation+0.000
,
Token,
Feature activation+0.000
creating
Token creating
Feature activation+0.000

INTERVAL 0.391 - 0.782
CONTAINS 0.142%

term
Token term
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
so
Token so
Feature activation+0.676
-
Token-
Feature activation+0.000
called
Tokencalled
Feature activation+0.000
Tier
Token Tier
Feature activation+0.000
3
Token 3
Feature activation+0.000
standards
Token standards
Feature activation+0.000
Mod
Token Mod
Feature activation+0.000
ification
Tokenification
Feature activation+0.000
and
Token and
Feature activation+0.000
its
Token its
Feature activation+0.000
Exp
Token Exp
Feature activation+0.166
ans
Tokenans
Feature activation+0.616
ions
Tokenions
Feature activation+0.641
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
B
Token B
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Nelson
Token Nelson
Feature activation+0.000
A
Token A
Feature activation+0.000
.
Token.
Feature activation+0.000
Rockefeller
Token Rockefeller
Feature activation+0.397
Center
Token Center
Feature activation+0.000
for
Token for
Feature activation+0.000
Latin
Token Latin
Feature activation+0.000
American
Token American
Feature activation+0.000
Art
Token Art
Feature activation+0.000
wife
Token wife
Feature activation+0.000
Linda
Token Linda
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
avoiding
Token avoiding
Feature activation+0.091
Lewis
Token Lewis
Feature activation+0.537
at
Token at
Feature activation+0.000
all
Token all
Feature activation+0.000
costs
Token costs
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
PlayStation
Token PlayStation
Feature activation+0.124
3
Token 3
Feature activation+0.996
and
Token and
Feature activation+0.000
PS
Token PS
Feature activation+0.510
Vita
Token Vita
Feature activation+2.137
and
Token and
Feature activation+0.000
plans
Token plans
Feature activation+0.000
to
Token to
Feature activation+0.000
release
Token release
Feature activation+0.000

INTERVAL 0.000 - 0.391
CONTAINS 99.739%

police
Token police
Feature activation+0.000
force
Token force
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
community
Token community
Feature activation+0.000
and
Token and
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+0.000
og
Tokenog
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
gan
Tokengan
Feature activation+0.000
's
Token's
Feature activation+0.000
career
Token career
Feature activation+0.000
had
Token had
Feature activation+0.000
appeared
Token appeared
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
allow
Token allow
Feature activation+0.000
insurers
Token insurers
Feature activation+0.000
to
Token to
Feature activation+0.000
cease
Token cease
Feature activation+0.000
providing
Token providing
Feature activation+0.000
coverage
Token coverage
Feature activation+0.000
of
Token of
Feature activation+0.000
essential
Token essential
Feature activation+0.000
health
Token health
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
,
Token,
Feature activation+0.000
GOP
Token GOP
Feature activation+0.000
runoff
Token runoff
Feature activation+0.000
,
Token,
Feature activation+0.000
Bannon
Token Bannon
Feature activation+0.000
has
Token has
Feature activation+0.000
declared
Token declared
Feature activation+0.000
his
Token his
Feature activation+0.000
support
Token support
Feature activation+0.000
for
Token for
Feature activation+0.000
Roy
Token Roy
Feature activation+0.000
Moore
Token Moore
Feature activation+0.000
that
Token that
Feature activation+0.000
these
Token these
Feature activation+0.000
environmental
Token environmental
Feature activation+0.000
variables
Token variables
Feature activation+0.000
are
Token are
Feature activation+0.000
set
Token set
Feature activation+0.000
,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.000
going
Token going
Feature activation+0.000
into
Token into
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