H5.7 top features

Top feature 0 in H5.7: (feature 23486)

TOP ACTIVATIONS
MAX = 6.916

He
Token He
Feature activation+0.000
included
Token included
Feature activation+0.236
the
Token the
Feature activation+1.759
following
Token following
Feature activation+2.683
paragraph
Token paragraph
Feature activation+2.457
in
Token in
Feature activation+6.916
every
Token every
Feature activation+4.719
ministerial
Token ministerial
Feature activation+0.000
mandate
Token mandate
Feature activation+0.000
letter
Token letter
Feature activation+0.000
:
Token:
Feature activation+0.898
including
Token including
Feature activation+2.093
a
Token a
Feature activation+4.160
foreign
Token foreign
Feature activation+0.000
language
Token language
Feature activation+0.000
in
Token in
Feature activation+6.405
the
Token the
Feature activation+6.607
e
Token e
Feature activation+0.000
B
TokenB
Feature activation+0.000
acc
Tokenacc
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
by
Token by
Feature activation+0.000
including
Token including
Feature activation+2.093
a
Token a
Feature activation+4.160
foreign
Token foreign
Feature activation+0.000
language
Token language
Feature activation+0.000
in
Token in
Feature activation+6.405
the
Token the
Feature activation+6.607
e
Token e
Feature activation+0.000
B
TokenB
Feature activation+0.000
acc
Tokenacc
Feature activation+0.000
.
Token.
Feature activation+0.000
ras
Tokenras
Feature activation+0.000
n
Tokenn
Feature activation+0.000
port
Tokenport
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+2.181
with
Token with
Feature activation+5.895
this
Token this
Feature activation+4.907
graphic
Token graphic
Feature activation+3.306
.
Token.
Feature activation+0.118
strong
Tokenstrong
Feature activation+0.000
>
Token>
Feature activation+0.000
to
Token to
Feature activation+0.000
include
Token include
Feature activation+0.000
the
Token the
Feature activation+1.900
marijuana
Token marijuana
Feature activation+0.000
language
Token language
Feature activation+1.412
in
Token in
Feature activation+5.628
the
Token the
Feature activation+5.341
comprehensive
Token comprehensive
Feature activation+0.613
tax
Token tax
Feature activation+0.000
bill
Token bill
Feature activation+0.023
âĢ
Token âĢ
Feature activation+0.000
's
Token's
Feature activation+0.000
signature
Token signature
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
included
Token included
Feature activation+0.942
on
Token on
Feature activation+5.626
the
Token the
Feature activation+4.695
cover
Token cover
Feature activation+2.708
page
Token page
Feature activation+0.000
a
Token a
Feature activation+1.941
list
Token list
Feature activation+0.529
include
Token include
Feature activation+0.815
land
Token land
Feature activation+0.429
-
Token-
Feature activation+0.000
use
Tokenuse
Feature activation+0.000
regulations
Token regulations
Feature activation+0.929
in
Token in
Feature activation+5.594
the
Token the
Feature activation+5.513
transportation
Token transportation
Feature activation+0.234
plans
Token plans
Feature activation+0.956
that
Token that
Feature activation+0.000
federal
Token federal
Feature activation+0.000
my
Token my
Feature activation+0.000
opinion
Token opinion
Feature activation+0.000
and
Token and
Feature activation+0.000
include
Token include
Feature activation+0.000
it
Token it
Feature activation+3.449
in
Token in
Feature activation+5.569
whatever
Token whatever
Feature activation+3.572
she
Token she
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
land
Token land
Feature activation+0.429
-
Token-
Feature activation+0.000
use
Tokenuse
Feature activation+0.000
regulations
Token regulations
Feature activation+0.929
in
Token in
Feature activation+5.594
the
Token the
Feature activation+5.513
transportation
Token transportation
Feature activation+0.234
plans
Token plans
Feature activation+0.956
that
Token that
Feature activation+0.000
federal
Token federal
Feature activation+0.000
law
Token law
Feature activation+0.000
include
Token include
Feature activation+0.000
the
Token the
Feature activation+1.900
marijuana
Token marijuana
Feature activation+0.000
language
Token language
Feature activation+1.412
in
Token in
Feature activation+5.628
the
Token the
Feature activation+5.341
comprehensive
Token comprehensive
Feature activation+0.613
tax
Token tax
Feature activation+0.000
bill
Token bill
Feature activation+0.023
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
families
Token families
Feature activation+0.000
of
Token of
Feature activation+0.000
former
Token former
Feature activation+0.000
players
Token players
Feature activation+0.000
included
Token included
Feature activation+0.000
in
Token in
Feature activation+5.301
the
Token the
Feature activation+5.080
settlement
Token settlement
Feature activation+0.510
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
of
Token of
Feature activation+0.000
former
Token former
Feature activation+0.000
players
Token players
Feature activation+0.000
included
Token included
Feature activation+0.000
in
Token in
Feature activation+5.301
the
Token the
Feature activation+5.080
settlement
Token settlement
Feature activation+0.510
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
has
Token has
Feature activation+0.000
n
Tokenn
Feature activation+0.000
port
Tokenport
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+2.181
with
Token with
Feature activation+5.895
this
Token this
Feature activation+4.907
graphic
Token graphic
Feature activation+3.306
.
Token.
Feature activation+0.118
strong
Tokenstrong
Feature activation+0.000
>
Token>
Feature activation+0.000
p
Tokenp
Feature activation+0.000
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
Systems
Token Systems
Feature activation+0.000
includes
Token includes
Feature activation+0.000
in
Token in
Feature activation+4.263
its
Token its
Feature activation+4.830
filament
Token filament
Feature activation+0.000
today
Token today
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Any
Token Any
Feature activation+0.000
V
TokenV
Feature activation+0.000
ille
Tokenille
Feature activation+0.000
V
TokenV
Feature activation+0.000
ille
Tokenille
Feature activation+0.000
in
Token in
Feature activation+4.753
this
Token this
Feature activation+4.302
)
Token)
Feature activation+0.104
from
Token from
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
included
Token included
Feature activation+0.236
the
Token the
Feature activation+1.759
following
Token following
Feature activation+2.683
paragraph
Token paragraph
Feature activation+2.457
in
Token in
Feature activation+6.916
every
Token every
Feature activation+4.719
ministerial
Token ministerial
Feature activation+0.000
mandate
Token mandate
Feature activation+0.000
letter
Token letter
Feature activation+0.000
:
Token:
Feature activation+0.898
Ċ
TokenĊ
Feature activation+0.590
signature
Token signature
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
included
Token included
Feature activation+0.942
on
Token on
Feature activation+5.626
the
Token the
Feature activation+4.695
cover
Token cover
Feature activation+2.708
page
Token page
Feature activation+0.000
a
Token a
Feature activation+1.941
list
Token list
Feature activation+0.529
of
Token of
Feature activation+0.000
include
Token include
Feature activation+1.014
such
Token such
Feature activation+1.833
a
Token a
Feature activation+2.640
statement
Token statement
Feature activation+1.056
in
Token in
Feature activation+4.123
your
Token your
Feature activation+4.642
submission
Token submission
Feature activation+1.103
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
det
Token det
Feature activation+0.000
achable
Tokenachable
Feature activation+0.000
strip
Token strip
Feature activation+0.000
of
Token of
Feature activation+0.000
metal
Token metal
Feature activation+0.000
on
Token on
Feature activation+4.534
an
Token an
Feature activation+2.522
otherwise
Token otherwise
Feature activation+0.000
plastic
Token plastic
Feature activation+0.000
gun
Token gun
Feature activation+0.000
.
Token.
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
also
Token also
Feature activation+0.000
included
Token included
Feature activation+0.000
as
Token as
Feature activation+2.621
a
Token a
Feature activation+4.450
sub
Token sub
Feature activation+0.110
-
Token-
Feature activation+0.000
category
Tokencategory
Feature activation+0.000
which
Token which
Feature activation+0.000
of
Token of
Feature activation+0.000

Top DFA by src position
MAX = 8.161

office
Token office
Feature activation+0.013
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
October
Token October
Feature activation+0.024
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
He
Token He
Feature activation+0.005
Top resid features:
included
Token included
Feature activation+8.161
Top resid features:
the
Token the
Feature activation+0.111
Top resid features:
following
Token following
Feature activation+0.078
Top resid features:
paragraph
Token paragraph
Feature activation+0.258
Top resid features:
in
Token in
Feature activation+0.254
Top resid features:
every
Token every
Feature activation+0.000
Top resid features:
long
Token long
Feature activation-0.000
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
term
Tokenterm
Feature activation+0.016
Top resid features:
fall
Token fall
Feature activation+0.001
Top resid features:
by
Token by
Feature activation-0.015
Top resid features:
including
Token including
Feature activation+7.893
Top resid features:
a
Token a
Feature activation+0.092
Top resid features:
foreign
Token foreign
Feature activation-0.027
Top resid features:
language
Token language
Feature activation+0.085
Top resid features:
in
Token in
Feature activation+0.345
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
long
Token long
Feature activation-0.004
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
term
Tokenterm
Feature activation-0.002
Top resid features:
fall
Token fall
Feature activation-0.012
Top resid features:
by
Token by
Feature activation-0.014
Top resid features:
including
Token including
Feature activation+7.853
Top resid features:
a
Token a
Feature activation+0.122
Top resid features:
foreign
Token foreign
Feature activation-0.018
Top resid features:
language
Token language
Feature activation+0.128
Top resid features:
in
Token in
Feature activation+0.078
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
p
Tokenp
Feature activation+0.007
Top resid features:
><
Token><
Feature activation-0.004
Top resid features:
strong
Tokenstrong
Feature activation-0.001
Top resid features:
>
Token>
Feature activation+0.031
Top resid features:
Please
TokenPlease
Feature activation+0.041
Top resid features:
include
Token include
Feature activation+7.297
Top resid features:
attribution
Token attribution
Feature activation+0.053
Top resid features:
to
Token to
Feature activation+0.094
Top resid features:
Jan
Token Jan
Feature activation+0.092
Top resid features:
ST
TokenST
Feature activation-0.000
Top resid features:
ras
Tokenras
Feature activation+0.004
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
good
Token good
Feature activation+0.001
Top resid features:
shot
Token shot
Feature activation-0.008
Top resid features:
to
Token to
Feature activation-0.010
Top resid features:
include
Token include
Feature activation+6.954
Top resid features:
the
Token the
Feature activation+0.242
Top resid features:
marijuana
Token marijuana
Feature activation+0.025
Top resid features:
language
Token language
Feature activation+0.147
Top resid features:
in
Token in
Feature activation+0.115
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
wife
Token wife
Feature activation+0.005
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
signature
Token signature
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
He
Token He
Feature activation+0.031
Top resid features:
included
Token included
Feature activation+7.149
Top resid features:
on
Token on
Feature activation+0.263
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
cover
Token cover
Feature activation+0.000
Top resid features:
page
Token page
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.038
Top resid features:
told
Token told
Feature activation+0.044
Top resid features:
metropolitan
Token metropolitan
Feature activation-0.025
Top resid features:
areas
Token areas
Feature activation-0.014
Top resid features:
to
Token to
Feature activation-0.046
Top resid features:
include
Token include
Feature activation+6.889
Top resid features:
land
Token land
Feature activation+0.037
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
use
Tokenuse
Feature activation+0.003
Top resid features:
regulations
Token regulations
Feature activation+0.321
Top resid features:
in
Token in
Feature activation+0.228
Top resid features:
still
Token still
Feature activation+0.008
Top resid features:
take
Token take
Feature activation+0.003
Top resid features:
my
Token my
Feature activation+0.002
Top resid features:
opinion
Token opinion
Feature activation+0.004
Top resid features:
and
Token and
Feature activation+0.028
Top resid features:
include
Token include
Feature activation+7.243
Top resid features:
it
Token it
Feature activation+0.175
Top resid features:
in
Token in
Feature activation-0.055
Top resid features:
whatever
Token whatever
Feature activation+0.000
Top resid features:
she
Token she
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.028
Top resid features:
told
Token told
Feature activation+0.033
Top resid features:
metropolitan
Token metropolitan
Feature activation-0.010
Top resid features:
areas
Token areas
Feature activation-0.010
Top resid features:
to
Token to
Feature activation-0.014
Top resid features:
include
Token include
Feature activation+6.649
Top resid features:
land
Token land
Feature activation+0.039
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
use
Tokenuse
Feature activation+0.016
Top resid features:
regulations
Token regulations
Feature activation+0.259
Top resid features:
in
Token in
Feature activation+0.416
Top resid features:
s
Tokens
Feature activation-0.000
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
good
Token good
Feature activation+0.004
Top resid features:
shot
Token shot
Feature activation-0.016
Top resid features:
to
Token to
Feature activation-0.004
Top resid features:
include
Token include
Feature activation+6.721
Top resid features:
the
Token the
Feature activation+0.077
Top resid features:
marijuana
Token marijuana
Feature activation+0.047
Top resid features:
language
Token language
Feature activation+0.129
Top resid features:
in
Token in
Feature activation+0.254
Top resid features:
the
Token the
Feature activation+0.040
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
families
Token families
Feature activation-0.005
Top resid features:
of
Token of
Feature activation-0.037
Top resid features:
former
Token former
Feature activation-0.024
Top resid features:
players
Token players
Feature activation+0.006
Top resid features:
included
Token included
Feature activation+7.151
Top resid features:
in
Token in
Feature activation+0.050
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
settlement
Token settlement
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:
the
Token the
Feature activation-0.016
Top resid features:
families
Token families
Feature activation-0.030
Top resid features:
of
Token of
Feature activation-0.010
Top resid features:
former
Token former
Feature activation-0.016
Top resid features:
players
Token players
Feature activation-0.001
Top resid features:
included
Token included
Feature activation+6.890
Top resid features:
in
Token in
Feature activation+0.104
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
settlement
Token settlement
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:
p
Tokenp
Feature activation+0.004
Top resid features:
><
Token><
Feature activation-0.008
Top resid features:
strong
Tokenstrong
Feature activation-0.008
Top resid features:
>
Token>
Feature activation+0.034
Top resid features:
Please
TokenPlease
Feature activation+0.060
Top resid features:
include
Token include
Feature activation+6.077
Top resid features:
attribution
Token attribution
Feature activation-0.010
Top resid features:
to
Token to
Feature activation+0.100
Top resid features:
Jan
Token Jan
Feature activation+0.041
Top resid features:
ST
TokenST
Feature activation-0.005
Top resid features:
ras
Tokenras
Feature activation+0.004
Top resid features:
chip
Token chip
Feature activation+0.052
Top resid features:
that
Token that
Feature activation+0.021
Top resid features:
3
Token 3
Feature activation+0.012
Top resid features:
D
TokenD
Feature activation-0.006
Top resid features:
Systems
Token Systems
Feature activation-0.011
Top resid features:
includes
Token includes
Feature activation+6.201
Top resid features:
in
Token in
Feature activation+0.540
Top resid features:
its
Token its
Feature activation-0.049
Top resid features:
filament
Token filament
Feature activation+0.000
Top resid features:
today
Token today
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
we
Tokenwe
Feature activation+0.030
Top resid features:
âĢ
TokenâĢ
Feature activation+0.084
Top resid features:
Ļ
TokenĻ
Feature activation+0.017
Top resid features:
re
Tokenre
Feature activation+0.004
Top resid features:
not
Token not
Feature activation+0.014
Top resid features:
including
Token including
Feature activation+5.855
Top resid features:
Any
Token Any
Feature activation+0.213
Top resid features:
V
TokenV
Feature activation+0.057
Top resid features:
ille
Tokenille
Feature activation+0.018
Top resid features:
V
TokenV
Feature activation+0.041
Top resid features:
ille
Tokenille
Feature activation+0.027
Top resid features:
office
Token office
Feature activation+0.006
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
October
Token October
Feature activation+0.017
Top resid features:
.
Token.
Feature activation+0.037
Top resid features:
He
Token He
Feature activation+0.010
Top resid features:
included
Token included
Feature activation+5.652
Top resid features:
the
Token the
Feature activation+0.061
Top resid features:
following
Token following
Feature activation+0.041
Top resid features:
paragraph
Token paragraph
Feature activation+0.229
Top resid features:
in
Token in
Feature activation+0.353
Top resid features:
every
Token every
Feature activation+0.065
Top resid features:
wife
Token wife
Feature activation+0.004
Top resid features:
's
Token's
Feature activation-0.001
Top resid features:
signature
Token signature
Feature activation-0.016
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
He
Token He
Feature activation+0.010
Top resid features:
included
Token included
Feature activation+6.046
Top resid features:
on
Token on
Feature activation+0.540
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
cover
Token cover
Feature activation+0.000
Top resid features:
page
Token page
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
your
Token your
Feature activation-0.002
Top resid features:
name
Token name
Feature activation-0.010
Top resid features:
posted
Token posted
Feature activation+0.026
Top resid features:
then
Token then
Feature activation+0.003
Top resid features:
please
Token please
Feature activation+0.037
Top resid features:
include
Token include
Feature activation+6.036
Top resid features:
such
Token such
Feature activation+0.050
Top resid features:
a
Token a
Feature activation+0.071
Top resid features:
statement
Token statement
Feature activation+0.115
Top resid features:
in
Token in
Feature activation+0.312
Top resid features:
your
Token your
Feature activation-0.031
Top resid features:
get
Token get
Feature activation+0.001
Top resid features:
around
Token around
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
requirements
Token requirements
Feature activation+0.016
Top resid features:
by
Token by
Feature activation+0.013
Top resid features:
including
Token including
Feature activation+5.827
Top resid features:
a
Token a
Feature activation+0.073
Top resid features:
det
Token det
Feature activation-0.015
Top resid features:
achable
Tokenachable
Feature activation+0.070
Top resid features:
strip
Token strip
Feature activation+0.087
Top resid features:
of
Token of
Feature activation+0.104
Top resid features:
three
Token three
Feature activation+0.003
Top resid features:
years
Token years
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
and
Token and
Feature activation+0.020
Top resid features:
also
Token also
Feature activation-0.004
Top resid features:
included
Token included
Feature activation+5.369
Top resid features:
as
Token as
Feature activation+0.587
Top resid features:
a
Token a
Feature activation+0.040
Top resid features:
sub
Token sub
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
category
Tokencategory
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.01

Head 1: 0.02

Head 2: 0.06

Head 3: 0.05

Head 4: 0.07

Head 5: 0.03

Head 6: 0.02

Head 7: 0.58

Head 8: 0.02

Head 9: 0.03

Head 10: 0.06

Head 11: 0.06

Positive logits

supplemental1.59

redund1.55

footnote1.52

Appendix1.51

supplementary1.46

Schedule1.44

CoC1.41

lists1.40

parade1.40

Inher1.37

Preferred1.36

inclusion1.35

Include1.33

Rule1.31

List1.31

Lists1.31

mandatory1.28

arthed1.28

list1.27

Mandatory1.26

Negative logits

uez-1.73

rompt-1.65

trak-1.46

alf-1.44

cept-1.42

oward-1.36

pring-1.36

olly-1.35

Gary-1.34

zzy-1.34

obbies-1.34

76561-1.33

renheit-1.31

wagen-1.31

wob-1.30

CrossRef-1.30

ache-1.26

sworth-1.26

runaway-1.24

manuel-1.24

INTERVAL 6.224 - 6.916
CONTAINS 0.000%

He
Token He
Feature activation+0.000
included
Token included
Feature activation+0.236
the
Token the
Feature activation+1.759
following
Token following
Feature activation+2.683
paragraph
Token paragraph
Feature activation+2.457
in
Token in
Feature activation+6.916
every
Token every
Feature activation+4.719
ministerial
Token ministerial
Feature activation+0.000
mandate
Token mandate
Feature activation+0.000
letter
Token letter
Feature activation+0.000
:
Token:
Feature activation+0.898
by
Token by
Feature activation+0.000
including
Token including
Feature activation+2.093
a
Token a
Feature activation+4.160
foreign
Token foreign
Feature activation+0.000
language
Token language
Feature activation+0.000
in
Token in
Feature activation+6.405
the
Token the
Feature activation+6.607
e
Token e
Feature activation+0.000
B
TokenB
Feature activation+0.000
acc
Tokenacc
Feature activation+0.000
.
Token.
Feature activation+0.000
including
Token including
Feature activation+2.093
a
Token a
Feature activation+4.160
foreign
Token foreign
Feature activation+0.000
language
Token language
Feature activation+0.000
in
Token in
Feature activation+6.405
the
Token the
Feature activation+6.607
e
Token e
Feature activation+0.000
B
TokenB
Feature activation+0.000
acc
Tokenacc
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 5.533 - 6.224
CONTAINS 0.001%

my
Token my
Feature activation+0.000
opinion
Token opinion
Feature activation+0.000
and
Token and
Feature activation+0.000
include
Token include
Feature activation+0.000
it
Token it
Feature activation+3.449
in
Token in
Feature activation+5.569
whatever
Token whatever
Feature activation+3.572
she
Token she
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
's
Token's
Feature activation+0.000
signature
Token signature
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
included
Token included
Feature activation+0.942
on
Token on
Feature activation+5.626
the
Token the
Feature activation+4.695
cover
Token cover
Feature activation+2.708
page
Token page
Feature activation+0.000
a
Token a
Feature activation+1.941
list
Token list
Feature activation+0.529
ras
Tokenras
Feature activation+0.000
n
Tokenn
Feature activation+0.000
port
Tokenport
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+2.181
with
Token with
Feature activation+5.895
this
Token this
Feature activation+4.907
graphic
Token graphic
Feature activation+3.306
.
Token.
Feature activation+0.118
strong
Tokenstrong
Feature activation+0.000
>
Token>
Feature activation+0.000
to
Token to
Feature activation+0.000
include
Token include
Feature activation+0.000
the
Token the
Feature activation+1.900
marijuana
Token marijuana
Feature activation+0.000
language
Token language
Feature activation+1.412
in
Token in
Feature activation+5.628
the
Token the
Feature activation+5.341
comprehensive
Token comprehensive
Feature activation+0.613
tax
Token tax
Feature activation+0.000
bill
Token bill
Feature activation+0.023
âĢ
Token âĢ
Feature activation+0.000
include
Token include
Feature activation+0.815
land
Token land
Feature activation+0.429
-
Token-
Feature activation+0.000
use
Tokenuse
Feature activation+0.000
regulations
Token regulations
Feature activation+0.929
in
Token in
Feature activation+5.594
the
Token the
Feature activation+5.513
transportation
Token transportation
Feature activation+0.234
plans
Token plans
Feature activation+0.956
that
Token that
Feature activation+0.000
federal
Token federal
Feature activation+0.000

INTERVAL 4.841 - 5.533
CONTAINS 0.001%

families
Token families
Feature activation+0.000
of
Token of
Feature activation+0.000
former
Token former
Feature activation+0.000
players
Token players
Feature activation+0.000
included
Token included
Feature activation+0.000
in
Token in
Feature activation+5.301
the
Token the
Feature activation+5.080
settlement
Token settlement
Feature activation+0.510
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
of
Token of
Feature activation+0.000
former
Token former
Feature activation+0.000
players
Token players
Feature activation+0.000
included
Token included
Feature activation+0.000
in
Token in
Feature activation+5.301
the
Token the
Feature activation+5.080
settlement
Token settlement
Feature activation+0.510
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
NFL
Token NFL
Feature activation+0.000
has
Token has
Feature activation+0.000
n
Tokenn
Feature activation+0.000
port
Tokenport
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+2.181
with
Token with
Feature activation+5.895
this
Token this
Feature activation+4.907
graphic
Token graphic
Feature activation+3.306
.
Token.
Feature activation+0.118
strong
Tokenstrong
Feature activation+0.000
>
Token>
Feature activation+0.000
p
Tokenp
Feature activation+0.000
include
Token include
Feature activation+0.000
the
Token the
Feature activation+1.900
marijuana
Token marijuana
Feature activation+0.000
language
Token language
Feature activation+1.412
in
Token in
Feature activation+5.628
the
Token the
Feature activation+5.341
comprehensive
Token comprehensive
Feature activation+0.613
tax
Token tax
Feature activation+0.000
bill
Token bill
Feature activation+0.023
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
land
Token land
Feature activation+0.429
-
Token-
Feature activation+0.000
use
Tokenuse
Feature activation+0.000
regulations
Token regulations
Feature activation+0.929
in
Token in
Feature activation+5.594
the
Token the
Feature activation+5.513
transportation
Token transportation
Feature activation+0.234
plans
Token plans
Feature activation+0.956
that
Token that
Feature activation+0.000
federal
Token federal
Feature activation+0.000
law
Token law
Feature activation+0.000

INTERVAL 4.150 - 4.841
CONTAINS 0.001%

,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
also
Token also
Feature activation+0.000
included
Token included
Feature activation+0.000
as
Token as
Feature activation+2.621
a
Token a
Feature activation+4.450
sub
Token sub
Feature activation+0.110
-
Token-
Feature activation+0.000
category
Tokencategory
Feature activation+0.000
which
Token which
Feature activation+0.000
of
Token of
Feature activation+0.000
include
Token include
Feature activation+1.014
such
Token such
Feature activation+1.833
a
Token a
Feature activation+2.640
statement
Token statement
Feature activation+1.056
in
Token in
Feature activation+4.123
your
Token your
Feature activation+4.642
submission
Token submission
Feature activation+1.103
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
that
Token that
Feature activation+0.000
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
Systems
Token Systems
Feature activation+0.000
includes
Token includes
Feature activation+0.000
in
Token in
Feature activation+4.263
its
Token its
Feature activation+4.830
filament
Token filament
Feature activation+0.000
today
Token today
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
-
Token-
Feature activation+0.000
term
Tokenterm
Feature activation+0.000
fall
Token fall
Feature activation+0.000
by
Token by
Feature activation+0.000
including
Token including
Feature activation+2.093
a
Token a
Feature activation+4.160
foreign
Token foreign
Feature activation+0.000
language
Token language
Feature activation+0.000
in
Token in
Feature activation+6.405
the
Token the
Feature activation+6.607
e
Token e
Feature activation+0.000
and
Token and
Feature activation+0.000
include
Token include
Feature activation+0.000
them
Token them
Feature activation+3.016
more
Token more
Feature activation+2.182
in
Token in
Feature activation+4.442
the
Token the
Feature activation+4.168
decision
Token decision
Feature activation+0.253
-
Token-
Feature activation+0.000
making
Tokenmaking
Feature activation+0.000
process
Token process
Feature activation+0.327
is
Token is
Feature activation+0.000

INTERVAL 3.458 - 4.150
CONTAINS 0.002%

on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
guaranteed
Token guaranteed
Feature activation+0.000
money
Token money
Feature activation+0.000
included
Token included
Feature activation+0.000
in
Token in
Feature activation+3.976
the
Token the
Feature activation+3.923
deal
Token deal
Feature activation+0.700
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
)
Token)
Feature activation+0.000
included
Token included
Feature activation+0.000
in
Token in
Feature activation+3.764
the
Token the
Feature activation+4.136
dump
Token dump
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
its
Token its
Feature activation+0.000
regular
Token regular
Feature activation+0.000
report
Token report
Feature activation+0.000
also
Token also
Feature activation+0.000
included
Token included
Feature activation+0.084
in
Token in
Feature activation+3.894
August
Token August
Feature activation+0.020
complaints
Token complaints
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
smartphone
Token smartphone
Feature activation+0.000
in
Token in
Feature activation+0.000
1977
Token 1977
Feature activation+0.000
included
Token included
Feature activation+0.000
Taiwan
Token Taiwan
Feature activation+0.000
in
Token in
Feature activation+2.999
a
Token a
Feature activation+4.016
list
Token list
Feature activation+1.008
of
Token of
Feature activation+0.000
"
Token "
Feature activation+0.000
in
Tokenin
Feature activation+0.000
secure
Tokensecure
Feature activation+0.000
you
Token you
Feature activation+0.000
think
Token think
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
included
Token included
Feature activation+1.431
in
Token in
Feature activation+3.821
Morning
Token Morning
Feature activation+0.000
Read
Token Read
Feature activation+0.000
s
Tokens
Feature activation+0.000
?
Token?
Feature activation+0.000
Tell
Token Tell
Feature activation+0.000

INTERVAL 2.766 - 3.458
CONTAINS 0.003%

five
Token five
Feature activation+0.000
debate
Token debate
Feature activation+0.000
demands
Token demands
Feature activation+0.000
included
Token included
Feature activation+1.733
in
Token in
Feature activation+3.741
a
Token a
Feature activation+3.291
draft
Token draft
Feature activation+0.000
letter
Token letter
Feature activation+0.000
to
Token to
Feature activation+0.000
debate
Token debate
Feature activation+0.000
media
Token media
Feature activation+0.000
lands
Token lands
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
included
Token included
Feature activation+0.724
in
Token in
Feature activation+2.804
the
Token the
Feature activation+2.842
side
Token side
Feature activation+0.000
board
Tokenboard
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
villages
Token villages
Feature activation+0.000
included
Token included
Feature activation+0.511
in
Token in
Feature activation+3.289
the
Token the
Feature activation+3.081
ESA
Token ESA
Feature activation+0.000
,
Token,
Feature activation+0.000
from
Token from
Feature activation+0.000
2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.000
historic
Token historic
Feature activation+0.000
-
Token-
Feature activation+0.000
ting
Tokenting
Feature activation+0.000
ed
Tokened
Feature activation+0.000
gospel
Token gospel
Feature activation+0.000
as
Token as
Feature activation+3.332
he
Token he
Feature activation+0.577
has
Token has
Feature activation+0.000
evolved
Token evolved
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
that
Token that
Feature activation+0.000
included
Token included
Feature activation+0.000
the
Token the
Feature activation+0.436
engine
Token engine
Feature activation+0.096
as
Token as
Feature activation+2.099
a
Token a
Feature activation+3.372
stressed
Token stressed
Feature activation+0.000
component
Token component
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
race
Token race
Feature activation+0.002

INTERVAL 2.075 - 2.766
CONTAINS 0.003%

the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
included
Token included
Feature activation+1.060
within
Token within
Feature activation+2.404
the
Token the
Feature activation+2.394
design
Token design
Feature activation+0.587
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
situation
Token situation
Feature activation+0.000
It
TokenIt
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
't
Token't
Feature activation+0.000
even
Token even
Feature activation+0.000
include
Token include
Feature activation+0.560
any
Token any
Feature activation+2.327
hip
Token hip
Feature activation+0.000
-
Token-
Feature activation+0.000
hop
Tokenhop
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
are
Token are
Feature activation+0.000
five
Token five
Feature activation+0.000
debate
Token debate
Feature activation+0.000
demands
Token demands
Feature activation+0.000
included
Token included
Feature activation+0.353
in
Token in
Feature activation+2.747
a
Token a
Feature activation+2.386
draft
Token draft
Feature activation+0.000
letter
Token letter
Feature activation+0.000
to
Token to
Feature activation+0.000
debate
Token debate
Feature activation+0.000
as
Token as
Feature activation+0.000
his
Token his
Feature activation+0.000
willingness
Token willingness
Feature activation+0.000
to
Token to
Feature activation+0.000
include
Token include
Feature activation+0.020
a
Token a
Feature activation+2.455
dose
Token dose
Feature activation+0.000
of
Token of
Feature activation+0.000
authenticity
Token authenticity
Feature activation+0.000
through
Token through
Feature activation+2.910
historic
Token historic
Feature activation+0.000
.
Token.
Feature activation+0.000
Included
Token Included
Feature activation+0.798
for
Token for
Feature activation+0.673
the
Token the
Feature activation+0.409
occasion
Token occasion
Feature activation+0.000
were
Token were
Feature activation+2.135
Tur
Token Tur
Feature activation+0.000
bot
Tokenbot
Feature activation+0.000
P
Token P
Feature activation+0.000
och
Tokenoch
Feature activation+0.000
é
Tokené
Feature activation+0.000

INTERVAL 1.383 - 2.075
CONTAINS 0.004%

and
Token and
Feature activation+0.000
J
Token J
Feature activation+0.000
B
TokenB
Feature activation+0.000
OD
TokenOD
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+1.632
the
Token the
Feature activation+3.567
case
Token case
Feature activation+0.000
of
Token of
Feature activation+0.000
AS
Token AS
Feature activation+0.000
100
Token100
Feature activation+0.000
-
Token-
Feature activation+0.000
so
Tokenso
Feature activation+0.000
-
Token-
Feature activation+0.000
tiny
Tokentiny
Feature activation+0.000
section
Token section
Feature activation+0.000
on
Token on
Feature activation+1.418
a
Token a
Feature activation+0.081
sub
Token sub
Feature activation+0.000
jet
Tokenjet
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.192
out
Token out
Feature activation+0.000
what
Token what
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
included
Token included
Feature activation+1.970
:
Token:
Feature activation+0.180
Ċ
TokenĊ
Feature activation+0.872
Ċ
TokenĊ
Feature activation+1.052
P
TokenP
Feature activation+0.000
ric
Tokenric
Feature activation+0.000
The
Token The
Feature activation+0.000
K
Token K
Feature activation+0.000
8
Token8
Feature activation+0.000
72
Token72
Feature activation+0.000
includes
Token includes
Feature activation+0.833
a
Token a
Feature activation+1.611
low
Token low
Feature activation+0.000
-
Token-
Feature activation+0.000
profile
Tokenprofile
Feature activation+0.000
carrying
Token carrying
Feature activation+0.000
case
Token case
Feature activation+0.000
name
Token name
Feature activation+0.000
posted
Token posted
Feature activation+0.000
then
Token then
Feature activation+0.000
please
Token please
Feature activation+0.000
include
Token include
Feature activation+1.014
such
Token such
Feature activation+1.833
a
Token a
Feature activation+2.640
statement
Token statement
Feature activation+1.056
in
Token in
Feature activation+4.123
your
Token your
Feature activation+4.642
submission
Token submission
Feature activation+1.103

INTERVAL 0.692 - 1.383
CONTAINS 0.008%

Mark
Token Mark
Feature activation+0.000
Twain
Token Twain
Feature activation+0.000
passages
Token passages
Feature activation+0.000
that
Token that
Feature activation+0.000
include
Token include
Feature activation+0.000
the
Token the
Feature activation+0.713
phrase
Token phrase
Feature activation+0.000
,
Token,
Feature activation+0.000
river
Token river
Feature activation+0.000
,
Token ,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
including
Token including
Feature activation+0.000
the
Token the
Feature activation+0.730
Daily
Token Daily
Feature activation+0.000
Star
Token Star
Feature activation+0.000
,
Token,
Feature activation+0.815
the
Token the
Feature activation+0.000
Daily
Token Daily
Feature activation+0.000
Mirror
Token Mirror
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
490
Token490
Feature activation+0.000
yen
Token yen
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
include
Token include
Feature activation+0.168
a
Token a
Feature activation+1.191
fan
Token fan
Feature activation+0.000
book
Token book
Feature activation+0.000
,
Token,
Feature activation+0.000
drama
Token drama
Feature activation+0.000
CD
Token CD
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
K
Token K
Feature activation+0.000
8
Token8
Feature activation+0.000
72
Token72
Feature activation+0.000
includes
Token includes
Feature activation+0.833
a
Token a
Feature activation+1.611
low
Token low
Feature activation+0.000
-
Token-
Feature activation+0.000
profile
Tokenprofile
Feature activation+0.000
carrying
Token carrying
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
included
Token included
Feature activation+1.970
:
Token:
Feature activation+0.180
Ċ
TokenĊ
Feature activation+0.872
Ċ
TokenĊ
Feature activation+1.052
P
TokenP
Feature activation+0.000
ric
Tokenric
Feature activation+0.000
ed
Tokened
Feature activation+0.000
at
Token at
Feature activation+0.000
$
Token $
Feature activation+0.000

INTERVAL 0.000 - 0.692
CONTAINS 99.978%

leaks
Token leaks
Feature activation+0.000
:
Token:
Feature activation+0.000
Today
Token Today
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
Democrats
Token Democrats
Feature activation+0.000
.
Token.
Feature activation+0.000
Tomorrow
Token Tomorrow
Feature activation+0.000
it
Token it
Feature activation+0.000
could
Token could
Feature activation+0.000
off
Token off
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
other
Token other
Feature activation+0.000
people
Token people
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
its
Token its
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
capacity
Token capacity
Feature activation+0.000
is
Token is
Feature activation+0.000
only
Token only
Feature activation+0.000
for
Token for
Feature activation+0.000
retaliation
Token retaliation
Feature activation+0.000
or
Token or
Feature activation+0.000
deterrence
Token deterrence
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
your
Token your
Feature activation+0.000
brand
Token brand
Feature activation+0.000
-
Token-
Feature activation+0.000
new
Tokennew
Feature activation+0.000
satellite
Token satellite
Feature activation+0.000
TV
Token TV
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
surf
Token surf
Feature activation+0.000
over
Token over
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
incredibly
Token incredibly
Feature activation+0.000
short
Token short
Feature activation+0.000
-
Token-
Feature activation+0.000
sighted
Tokensighted
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
least
Token least
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 1 in H5.7: (feature 29168)

TOP ACTIVATIONS
MAX = 4.995

other
Token other
Feature activation+0.000
processors
Token processors
Feature activation+0.000
and
Token and
Feature activation+0.000
passing
Token passing
Feature activation+0.000
it
Token it
Feature activation+4.683
along
Token along
Feature activation+4.995
.
Token.
Feature activation+0.000
Organ
Token Organ
Feature activation+0.000
izing
Tokenizing
Feature activation+0.000
these
Token these
Feature activation+0.000
networks
Token networks
Feature activation+0.000
the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
processors
Token processors
Feature activation+0.000
and
Token and
Feature activation+0.000
passing
Token passing
Feature activation+0.000
it
Token it
Feature activation+4.683
along
Token along
Feature activation+4.995
.
Token.
Feature activation+0.000
Organ
Token Organ
Feature activation+0.000
izing
Tokenizing
Feature activation+0.000
these
Token these
Feature activation+0.000
I
Token I
Feature activation+0.000
've
Token've
Feature activation+0.000
been
Token been
Feature activation+0.000
passing
Token passing
Feature activation+0.000
that
Token that
Feature activation+2.526
on
Token on
Feature activation+4.355
but
Token but
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
get
Token get
Feature activation+0.000
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
innocent
Token innocent
Feature activation+0.000
and
Token and
Feature activation+0.000
passed
Token passed
Feature activation+0.000
a
Token a
Feature activation+4.260
polyg
Token polyg
Feature activation+0.000
raph
Tokenraph
Feature activation+0.000
test
Token test
Feature activation+0.000
to
Token to
Feature activation+0.000
prove
Token prove
Feature activation+0.000
identical
Token identical
Feature activation+0.000
increase
Token increase
Feature activation+0.000
in
Token in
Feature activation+0.000
risk
Token risk
Feature activation+0.000
passed
Token passed
Feature activation+0.273
from
Token from
Feature activation+4.255
both
Token both
Feature activation+0.034
male
Token male
Feature activation+0.000
and
Token and
Feature activation+0.000
female
Token female
Feature activation+0.000
parents
Token parents
Feature activation+0.000
He
TokenHe
Feature activation+0.000
passed
Token passed
Feature activation+0.000
his
Token his
Feature activation+3.298
noble
Token noble
Feature activation+0.000
spirit
Token spirit
Feature activation+0.716
along
Token along
Feature activation+4.243
to
Token to
Feature activation+1.605
Rage
Token Rage
Feature activation+0.000
!
Token!
Feature activation+0.000
It
Token It
Feature activation+0.000
has
Token has
Feature activation+0.000
whom
Token whom
Feature activation+0.000
we
Token we
Feature activation+0.000
will
Token will
Feature activation+0.000
pass
Token pass
Feature activation+0.000
them
Token them
Feature activation+2.903
on
Token on
Feature activation+3.834
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Keane
Token Keane
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
song
Token song
Feature activation+0.000
got
Token got
Feature activation+0.000
passed
Token passed
Feature activation+0.561
around
Token around
Feature activation+3.146
to
Token to
Feature activation+3.761
five
Token five
Feature activation+3.558
or
Token or
Feature activation+0.091
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Call
TokenCall
Feature activation+0.000
it
Token it
Feature activation+0.000
that
Token that
Feature activation+0.000
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
passed
Token passed
Feature activation+1.861
along
Token along
Feature activation+3.725
to
Token to
Feature activation+3.263
other
Token other
Feature activation+1.696
channels
Token channels
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
pass
Token pass
Feature activation+0.000
on
Token on
Feature activation+3.594
the
Token the
Feature activation+1.778
increased
Token increased
Feature activation+0.237
risk
Token risk
Feature activation+0.000
through
Token through
Feature activation+0.625
inherited
Token inherited
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.000
passed
Token passed
Feature activation+0.000
it
Token it
Feature activation+1.465
on
Token on
Feature activation+3.561
directly
Token directly
Feature activation+0.579
to
Token to
Feature activation+0.261
councils
Token councils
Feature activation+0.000
.
Token.
Feature activation+0.000
Council
Token Council
Feature activation+0.000
song
Token song
Feature activation+0.000
got
Token got
Feature activation+0.000
passed
Token passed
Feature activation+0.561
around
Token around
Feature activation+3.146
to
Token to
Feature activation+3.761
five
Token five
Feature activation+3.558
or
Token or
Feature activation+0.091
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Call
TokenCall
Feature activation+0.000
it
Token it
Feature activation+0.000
creativity
Token creativity
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
name
Token name
Feature activation+0.000
is
Token is
Feature activation+0.000
passed
Token passed
Feature activation+1.751
to
Token to
Feature activation+3.526
the
Token the
Feature activation+3.307
function
Token function
Feature activation+0.000
'
Token '
Feature activation+0.000
r
Tokenr
Feature activation+0.000
plot
Tokenplot
Feature activation+0.000
were
Token were
Feature activation+0.000
very
Token very
Feature activation+0.000
unlikely
Token unlikely
Feature activation+0.000
to
Token to
Feature activation+0.000
pass
Token pass
Feature activation+0.000
on
Token on
Feature activation+3.474
HIV
Token HIV
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
document
Token document
Feature activation+0.000
became
Token became
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
pass
Token pass
Feature activation+0.000
the
Token the
Feature activation+3.468
bill
Token bill
Feature activation+0.276
to
Token to
Feature activation+0.743
find
Token find
Feature activation+0.000
out
Token out
Feature activation+0.000
what
Token what
Feature activation+0.000
which
Token which
Feature activation+0.000
name
Token name
Feature activation+0.000
is
Token is
Feature activation+0.000
passed
Token passed
Feature activation+1.751
to
Token to
Feature activation+3.526
the
Token the
Feature activation+3.307
function
Token function
Feature activation+0.000
'
Token '
Feature activation+0.000
r
Tokenr
Feature activation+0.000
plot
Tokenplot
Feature activation+0.000
engine
Tokenengine
Feature activation+0.000
agn
Tokenagn
Feature activation+0.000
otti
Tokenotti
Feature activation+0.000
"
Token "
Feature activation+0.000
He
TokenHe
Feature activation+0.000
passed
Token passed
Feature activation+0.000
his
Token his
Feature activation+3.298
noble
Token noble
Feature activation+0.000
spirit
Token spirit
Feature activation+0.716
along
Token along
Feature activation+4.243
to
Token to
Feature activation+1.605
Rage
Token Rage
Feature activation+0.000
Even
TokenEven
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+0.000
do
Token do
Feature activation+0.000
pass
Token pass
Feature activation+0.000
this
Token this
Feature activation+3.273
initial
Token initial
Feature activation+1.838
group
Token group
Feature activation+0.000
will
Token will
Feature activation+0.000
not
Token not
Feature activation+0.000
get
Token get
Feature activation+0.000
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
passed
Token passed
Feature activation+1.861
along
Token along
Feature activation+3.725
to
Token to
Feature activation+3.263
other
Token other
Feature activation+1.696
channels
Token channels
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
lawyer
Token lawyer
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
never
Token never
Feature activation+0.000
passed
Token passed
Feature activation+0.000
the
Token the
Feature activation+3.184
state
Token state
Feature activation+2.336
bar
Token bar
Feature activation+0.000
exam
Token exam
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000

Top DFA by src position
MAX = 5.867

from
Token from
Feature activation+0.023
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
other
Token other
Feature activation+0.016
Top resid features:
processors
Token processors
Feature activation-0.000
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
passing
Token passing
Feature activation+5.558
Top resid features:
it
Token it
Feature activation+0.371
Top resid features:
along
Token along
Feature activation+0.108
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Organ
Token Organ
Feature activation+0.000
Top resid features:
izing
Tokenizing
Feature activation+0.000
Top resid features:
from
Token from
Feature activation-0.074
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
other
Token other
Feature activation-0.002
Top resid features:
processors
Token processors
Feature activation+0.005
Top resid features:
and
Token and
Feature activation-0.019
Top resid features:
passing
Token passing
Feature activation+5.867
Top resid features:
it
Token it
Feature activation+0.028
Top resid features:
along
Token along
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Organ
Token Organ
Feature activation+0.000
Top resid features:
izing
Tokenizing
Feature activation+0.000
Top resid features:
players
Token players
Feature activation+0.006
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
I
Token I
Feature activation+0.015
Top resid features:
've
Token've
Feature activation-0.038
Top resid features:
been
Token been
Feature activation-0.047
Top resid features:
passing
Token passing
Feature activation+4.956
Top resid features:
that
Token that
Feature activation+0.287
Top resid features:
on
Token on
Feature activation+0.246
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
we
Token we
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
claimed
Token claimed
Feature activation+0.011
Top resid features:
he
Token he
Feature activation-0.012
Top resid features:
is
Token is
Feature activation-0.030
Top resid features:
innocent
Token innocent
Feature activation-0.045
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
passed
Token passed
Feature activation+5.398
Top resid features:
a
Token a
Feature activation-0.019
Top resid features:
polyg
Token polyg
Feature activation+0.000
Top resid features:
raph
Tokenraph
Feature activation+0.000
Top resid features:
test
Token test
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
an
Token an
Feature activation-0.035
Top resid features:
identical
Token identical
Feature activation+0.025
Top resid features:
increase
Token increase
Feature activation-0.057
Top resid features:
in
Token in
Feature activation+0.024
Top resid features:
risk
Token risk
Feature activation+0.013
Top resid features:
passed
Token passed
Feature activation+5.145
Top resid features:
from
Token from
Feature activation+0.039
Top resid features:
both
Token both
Feature activation+0.000
Top resid features:
male
Token male
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
female
Token female
Feature activation+0.000
Top resid features:
P
Token P
Feature activation+0.005
Top resid features:
agn
Tokenagn
Feature activation+0.001
Top resid features:
otti
Tokenotti
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.054
Top resid features:
He
TokenHe
Feature activation+0.011
Top resid features:
passed
Token passed
Feature activation+5.323
Top resid features:
his
Token his
Feature activation+0.170
Top resid features:
noble
Token noble
Feature activation+0.013
Top resid features:
spirit
Token spirit
Feature activation-0.045
Top resid features:
along
Token along
Feature activation-0.056
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
generations
Token generations
Feature activation+0.018
Top resid features:
to
Token to
Feature activation-0.057
Top resid features:
whom
Token whom
Feature activation+0.061
Top resid features:
we
Token we
Feature activation+0.033
Top resid features:
will
Token will
Feature activation+0.059
Top resid features:
pass
Token pass
Feature activation+4.135
Top resid features:
them
Token them
Feature activation+0.267
Top resid features:
on
Token on
Feature activation+0.363
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:
TM
Token TM
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.047
Top resid features:
the
Token the
Feature activation-0.032
Top resid features:
song
Token song
Feature activation-0.023
Top resid features:
got
Token got
Feature activation+0.038
Top resid features:
passed
Token passed
Feature activation+4.074
Top resid features:
around
Token around
Feature activation+0.797
Top resid features:
to
Token to
Feature activation+0.066
Top resid features:
five
Token five
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
1
Token 1
Feature activation+0.031
Top resid features:
that
Token that
Feature activation+0.051
Top resid features:
needs
Token needs
Feature activation+0.046
Top resid features:
to
Token to
Feature activation-0.011
Top resid features:
be
Token be
Feature activation+0.037
Top resid features:
passed
Token passed
Feature activation+4.585
Top resid features:
along
Token along
Feature activation+0.109
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
channels
Token channels
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
mother
Token mother
Feature activation+0.009
Top resid features:
might
Token might
Feature activation-0.012
Top resid features:
be
Token be
Feature activation-0.020
Top resid features:
able
Token able
Feature activation-0.004
Top resid features:
to
Token to
Feature activation-0.014
Top resid features:
pass
Token pass
Feature activation+4.125
Top resid features:
on
Token on
Feature activation+0.218
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
increased
Token increased
Feature activation+0.000
Top resid features:
risk
Token risk
Feature activation+0.000
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.707
Top resid features:
and
Token and
Feature activation-0.019
Top resid features:
has
Token has
Feature activation+0.034
Top resid features:
passed
Token passed
Feature activation+4.040
Top resid features:
it
Token it
Feature activation+0.448
Top resid features:
on
Token on
Feature activation+0.122
Top resid features:
directly
Token directly
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
councils
Token councils
Feature activation+0.000
Top resid features:
TM
Token TM
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.043
Top resid features:
the
Token the
Feature activation-0.020
Top resid features:
song
Token song
Feature activation-0.025
Top resid features:
got
Token got
Feature activation+0.057
Top resid features:
passed
Token passed
Feature activation+4.218
Top resid features:
around
Token around
Feature activation+0.422
Top resid features:
to
Token to
Feature activation+0.186
Top resid features:
five
Token five
Feature activation+0.009
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
file
Token file
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.065
Top resid features:
which
Token which
Feature activation+0.039
Top resid features:
name
Token name
Feature activation-0.049
Top resid features:
is
Token is
Feature activation+0.011
Top resid features:
passed
Token passed
Feature activation+4.369
Top resid features:
to
Token to
Feature activation+0.076
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
function
Token function
Feature activation+0.000
Top resid features:
'
Token '
Feature activation+0.000
Top resid features:
r
Tokenr
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.001
Top resid features:
were
Token were
Feature activation+0.010
Top resid features:
very
Token very
Feature activation-0.011
Top resid features:
unlikely
Token unlikely
Feature activation-0.034
Top resid features:
to
Token to
Feature activation-0.040
Top resid features:
pass
Token pass
Feature activation+3.980
Top resid features:
on
Token on
Feature activation+0.309
Top resid features:
HIV
Token HIV
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
This
Token This
Feature activation+0.000
Top resid features:
document
Token document
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.009
Top resid features:
ľ
Tokenľ
Feature activation+0.032
Top resid features:
We
TokenWe
Feature activation-0.028
Top resid features:
had
Token had
Feature activation+0.008
Top resid features:
to
Token to
Feature activation-0.038
Top resid features:
pass
Token pass
Feature activation+4.439
Top resid features:
the
Token the
Feature activation+0.041
Top resid features:
bill
Token bill
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
find
Token find
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
file
Token file
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.042
Top resid features:
which
Token which
Feature activation+0.029
Top resid features:
name
Token name
Feature activation-0.043
Top resid features:
is
Token is
Feature activation+0.012
Top resid features:
passed
Token passed
Feature activation+4.057
Top resid features:
to
Token to
Feature activation+0.038
Top resid features:
the
Token the
Feature activation+0.121
Top resid features:
function
Token function
Feature activation+0.000
Top resid features:
'
Token '
Feature activation+0.000
Top resid features:
r
Tokenr
Feature activation+0.000
Top resid features:
P
Token P
Feature activation+0.003
Top resid features:
agn
Tokenagn
Feature activation+0.004
Top resid features:
otti
Tokenotti
Feature activation-0.002
Top resid features:
"
Token "
Feature activation+0.031
Top resid features:
He
TokenHe
Feature activation-0.001
Top resid features:
passed
Token passed
Feature activation+4.552
Top resid features:
his
Token his
Feature activation+0.011
Top resid features:
noble
Token noble
Feature activation+0.000
Top resid features:
spirit
Token spirit
Feature activation+0.000
Top resid features:
along
Token along
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Even
TokenEven
Feature activation-0.042
Top resid features:
if
Token if
Feature activation+0.007
Top resid features:
they
Token they
Feature activation-0.021
Top resid features:
do
Token do
Feature activation-0.022
Top resid features:
pass
Token pass
Feature activation+4.444
Top resid features:
this
Token this
Feature activation+0.003
Top resid features:
initial
Token initial
Feature activation+0.000
Top resid features:
group
Token group
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
1
Token 1
Feature activation+0.032
Top resid features:
that
Token that
Feature activation+0.017
Top resid features:
needs
Token needs
Feature activation-0.048
Top resid features:
to
Token to
Feature activation-0.005
Top resid features:
be
Token be
Feature activation+0.015
Top resid features:
passed
Token passed
Feature activation+4.137
Top resid features:
along
Token along
Feature activation+0.293
Top resid features:
to
Token to
Feature activation+0.072
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
channels
Token channels
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
lawyer
Token lawyer
Feature activation-0.025
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
He
Token He
Feature activation+0.023
Top resid features:
never
Token never
Feature activation+0.000
Top resid features:
passed
Token passed
Feature activation+4.157
Top resid features:
the
Token the
Feature activation+0.071
Top resid features:
state
Token state
Feature activation+0.000
Top resid features:
bar
Token bar
Feature activation+0.000
Top resid features:
exam
Token exam
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.01

Head 1: 0.01

Head 2: 0.05

Head 3: 0.05

Head 4: 0.08

Head 5: 0.02

Head 6: 0.07

Head 7: 0.56

Head 8: 0.02

Head 9: 0.03

Head 10: 0.05

Head 11: 0.04

Positive logits

laws1.83

Passed1.74

1.72

Lords1.70

Written1.57

phies1.57

olescent1.51

rollers1.49

Introduced1.45

lasses1.45

1.44

heses1.44

Pastebin1.44

NetMessage1.43

Became1.43

onyms1.42

github1.41

geons1.41

Bye1.41

acent1.40

Negative logits

sqor-1.54

standoff-1.48

crim-1.44

tension-1.42

Balt-1.41

thirst-1.38

gau-1.38

natureconservancy-1.37

antagon-1.37

charged-1.37

Extra-1.35

iating-1.34

coordinating-1.34

confronting-1.33

zzy-1.33

trak-1.32

00200000-1.28

gou-1.28

caster-1.28

clashed-1.27

INTERVAL 4.495 - 4.995
CONTAINS 0.000%

the
Token the
Feature activation+0.000
other
Token other
Feature activation+0.000
processors
Token processors
Feature activation+0.000
and
Token and
Feature activation+0.000
passing
Token passing
Feature activation+0.000
it
Token it
Feature activation+4.683
along
Token along
Feature activation+4.995
.
Token.
Feature activation+0.000
Organ
Token Organ
Feature activation+0.000
izing
Tokenizing
Feature activation+0.000
these
Token these
Feature activation+0.000
other
Token other
Feature activation+0.000
processors
Token processors
Feature activation+0.000
and
Token and
Feature activation+0.000
passing
Token passing
Feature activation+0.000
it
Token it
Feature activation+4.683
along
Token along
Feature activation+4.995
.
Token.
Feature activation+0.000
Organ
Token Organ
Feature activation+0.000
izing
Tokenizing
Feature activation+0.000
these
Token these
Feature activation+0.000
networks
Token networks
Feature activation+0.000

INTERVAL 3.996 - 4.495
CONTAINS 0.001%

identical
Token identical
Feature activation+0.000
increase
Token increase
Feature activation+0.000
in
Token in
Feature activation+0.000
risk
Token risk
Feature activation+0.000
passed
Token passed
Feature activation+0.273
from
Token from
Feature activation+4.255
both
Token both
Feature activation+0.034
male
Token male
Feature activation+0.000
and
Token and
Feature activation+0.000
female
Token female
Feature activation+0.000
parents
Token parents
Feature activation+0.000
I
Token I
Feature activation+0.000
've
Token've
Feature activation+0.000
been
Token been
Feature activation+0.000
passing
Token passing
Feature activation+0.000
that
Token that
Feature activation+2.526
on
Token on
Feature activation+4.355
but
Token but
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
get
Token get
Feature activation+0.000
He
TokenHe
Feature activation+0.000
passed
Token passed
Feature activation+0.000
his
Token his
Feature activation+3.298
noble
Token noble
Feature activation+0.000
spirit
Token spirit
Feature activation+0.716
along
Token along
Feature activation+4.243
to
Token to
Feature activation+1.605
Rage
Token Rage
Feature activation+0.000
!
Token!
Feature activation+0.000
It
Token It
Feature activation+0.000
has
Token has
Feature activation+0.000
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
innocent
Token innocent
Feature activation+0.000
and
Token and
Feature activation+0.000
passed
Token passed
Feature activation+0.000
a
Token a
Feature activation+4.260
polyg
Token polyg
Feature activation+0.000
raph
Tokenraph
Feature activation+0.000
test
Token test
Feature activation+0.000
to
Token to
Feature activation+0.000
prove
Token prove
Feature activation+0.000

INTERVAL 3.496 - 3.996
CONTAINS 0.001%

whom
Token whom
Feature activation+0.000
we
Token we
Feature activation+0.000
will
Token will
Feature activation+0.000
pass
Token pass
Feature activation+0.000
them
Token them
Feature activation+2.903
on
Token on
Feature activation+3.834
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Keane
Token Keane
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
song
Token song
Feature activation+0.000
got
Token got
Feature activation+0.000
passed
Token passed
Feature activation+0.561
around
Token around
Feature activation+3.146
to
Token to
Feature activation+3.761
five
Token five
Feature activation+3.558
or
Token or
Feature activation+0.091
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Call
TokenCall
Feature activation+0.000
it
Token it
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.000
passed
Token passed
Feature activation+0.000
it
Token it
Feature activation+1.465
on
Token on
Feature activation+3.561
directly
Token directly
Feature activation+0.579
to
Token to
Feature activation+0.261
councils
Token councils
Feature activation+0.000
.
Token.
Feature activation+0.000
Council
Token Council
Feature activation+0.000
that
Token that
Feature activation+0.000
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
passed
Token passed
Feature activation+1.861
along
Token along
Feature activation+3.725
to
Token to
Feature activation+3.263
other
Token other
Feature activation+1.696
channels
Token channels
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
song
Token song
Feature activation+0.000
got
Token got
Feature activation+0.000
passed
Token passed
Feature activation+0.561
around
Token around
Feature activation+3.146
to
Token to
Feature activation+3.761
five
Token five
Feature activation+3.558
or
Token or
Feature activation+0.091
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Call
TokenCall
Feature activation+0.000
it
Token it
Feature activation+0.000
creativity
Token creativity
Feature activation+0.000

INTERVAL 2.997 - 3.496
CONTAINS 0.002%

âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
support
Tokensupport
Feature activation+0.000
the
Token the
Feature activation+0.000
passing
Token passing
Feature activation+0.000
of
Token of
Feature activation+3.034
new
Token new
Feature activation+2.365
rules
Token rules
Feature activation+0.000
to
Token to
Feature activation+0.000
introduce
Token introduce
Feature activation+0.000
ride
Token ride
Feature activation+0.000
agn
Tokenagn
Feature activation+0.000
otti
Tokenotti
Feature activation+0.000
"
Token "
Feature activation+0.000
He
TokenHe
Feature activation+0.000
passed
Token passed
Feature activation+0.000
his
Token his
Feature activation+3.298
noble
Token noble
Feature activation+0.000
spirit
Token spirit
Feature activation+0.716
along
Token along
Feature activation+4.243
to
Token to
Feature activation+1.605
Rage
Token Rage
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
gu
Token gu
Feature activation+0.000
ff
Tokenff
Feature activation+0.000
which
Token which
Feature activation+0.000
passes
Token passes
Feature activation+0.000
for
Token for
Feature activation+3.138
analysis
Token analysis
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Irish
Token Irish
Feature activation+0.000
Left
Token Left
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
song
Token song
Feature activation+0.000
got
Token got
Feature activation+0.000
passed
Token passed
Feature activation+0.561
around
Token around
Feature activation+3.146
to
Token to
Feature activation+3.761
five
Token five
Feature activation+3.558
or
Token or
Feature activation+0.091
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Call
TokenCall
Feature activation+0.000
needs
Token needs
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
passed
Token passed
Feature activation+1.861
along
Token along
Feature activation+3.725
to
Token to
Feature activation+3.263
other
Token other
Feature activation+1.696
channels
Token channels
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000

INTERVAL 2.497 - 2.997
CONTAINS 0.001%

winning
Token winning
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
),
Token),
Feature activation+0.000
pass
Token pass
Feature activation+0.000
that
Token that
Feature activation+2.996
card
Token card
Feature activation+0.253
up
Token up
Feature activation+1.351
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
whom
Token whom
Feature activation+0.000
we
Token we
Feature activation+0.000
will
Token will
Feature activation+0.000
pass
Token pass
Feature activation+0.000
them
Token them
Feature activation+2.903
on
Token on
Feature activation+3.834
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Keane
Token Keane
Feature activation+0.000
flat
Token flat
Feature activation+0.000
foot
Token foot
Feature activation+0.000
ed
Tokened
Feature activation+0.000
and
Token and
Feature activation+0.000
pass
Token pass
Feature activation+0.000
to
Token to
Feature activation+2.814
create
Token create
Feature activation+0.000
a
Token a
Feature activation+0.000
great
Token great
Feature activation+0.000
scoring
Token scoring
Feature activation+0.000
chance
Token chance
Feature activation+0.000
a
Token a
Feature activation+0.000
procedure
Token procedure
Feature activation+0.000
similar
Token similar
Feature activation+0.000
to
Token to
Feature activation+0.000
passing
Token passing
Feature activation+0.000
a
Token a
Feature activation+2.676
bill
Token bill
Feature activation+0.296
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
losing
Token losing
Feature activation+0.000
candidate
Token candidate
Feature activation+0.000
along
Token along
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
videos
Token videos
Feature activation+0.000
were
Token were
Feature activation+0.000
passed
Token passed
Feature activation+2.097
around
Token around
Feature activation+2.738
through
Token through
Feature activation+1.071
download
Token download
Feature activation+0.000
links
Token links
Feature activation+0.016
on
Token on
Feature activation+0.664
their
Token their
Feature activation+1.522

INTERVAL 1.998 - 2.497
CONTAINS 0.002%

disabled
Token disabled
Feature activation+0.000
children
Token children
Feature activation+0.000
who
Token who
Feature activation+0.000
have
Token have
Feature activation+0.000
passed
Token passed
Feature activation+0.000
their
Token their
Feature activation+2.228
Grade
Token Grade
Feature activation+0.601
Six
Token Six
Feature activation+0.000
Achievement
Token Achievement
Feature activation+0.000
Test
Token Test
Feature activation+0.000
and
Token and
Feature activation+0.000
came
Token came
Feature activation+0.000
along
Token along
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
videos
Token videos
Feature activation+0.000
were
Token were
Feature activation+0.000
passed
Token passed
Feature activation+2.097
around
Token around
Feature activation+2.738
through
Token through
Feature activation+1.071
download
Token download
Feature activation+0.000
links
Token links
Feature activation+0.016
on
Token on
Feature activation+0.664
customer
Token customer
Feature activation+0.000
was
Token was
Feature activation+0.000
cited
Token cited
Feature activation+0.000
after
Token after
Feature activation+0.000
passing
Token passing
Feature activation+0.000
a
Token a
Feature activation+2.086
fake
Token fake
Feature activation+0.000
$
Token $
Feature activation+0.000
10
Token10
Feature activation+0.000
bill
Token bill
Feature activation+0.000
at
Token at
Feature activation+0.351
.
Token.
Feature activation+0.000
Our
Token Our
Feature activation+0.000
guys
Token guys
Feature activation+0.000
are
Token are
Feature activation+0.000
passing
Token passing
Feature activation+0.000
the
Token the
Feature activation+2.268
eyeb
Token eyeb
Feature activation+0.000
all
Tokenall
Feature activation+0.000
test
Token test
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
constitution
Token constitution
Feature activation+0.000
that
Token that
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
passed
Token passed
Feature activation+0.504
into
Token into
Feature activation+2.398
law
Token law
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
referendum
Token referendum
Feature activation+0.000
last
Token last
Feature activation+0.000

INTERVAL 1.498 - 1.998
CONTAINS 0.002%

is
Token is
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
pass
Token pass
Feature activation+0.000
smoothly
Token smoothly
Feature activation+0.036
into
Token into
Feature activation+1.585
circulation
Token circulation
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
final
Token final
Feature activation+0.000
steps
Token steps
Feature activation+0.000
around
Token around
Feature activation+2.738
through
Token through
Feature activation+1.071
download
Token download
Feature activation+0.000
links
Token links
Feature activation+0.016
on
Token on
Feature activation+0.664
their
Token their
Feature activation+1.522
website
Token website
Feature activation+0.000
and
Token and
Feature activation+0.000
fans
Token fans
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
file
Token file
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
name
Token name
Feature activation+0.000
is
Token is
Feature activation+0.000
passed
Token passed
Feature activation+1.751
to
Token to
Feature activation+3.526
the
Token the
Feature activation+3.307
function
Token function
Feature activation+0.000
'
Token '
Feature activation+0.000
r
Tokenr
Feature activation+0.000
makeup
Token makeup
Feature activation+0.000
,
Token,
Feature activation+0.000
any
Token any
Feature activation+0.000
risk
Token risk
Feature activation+0.000
passed
Token passed
Feature activation+0.000
from
Token from
Feature activation+1.966
a
Token a
Feature activation+1.468
father
Token father
Feature activation+0.000
raises
Token raises
Feature activation+0.000
the
Token the
Feature activation+0.000
possibility
Token possibility
Feature activation+0.000
,
Token,
Feature activation+0.000
stealth
Token stealth
Feature activation+0.000
ily
Tokenily
Feature activation+0.000
passed
Token passed
Feature activation+0.000
around
Token around
Feature activation+0.940
the
Token the
Feature activation+1.799
two
Token two
Feature activation+0.498
-
Token-
Feature activation+0.000
page
Tokenpage
Feature activation+0.000
,
Token,
Feature activation+0.000
st
Token st
Feature activation+0.000

INTERVAL 0.999 - 1.498
CONTAINS 0.003%

federal
Token federal
Feature activation+0.000
courts
Token courts
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
passed
Token passed
Feature activation+0.000
a
Token a
Feature activation+1.442
2012
Token 2012
Feature activation+0.437
law
Token law
Feature activation+0.000
that
Token that
Feature activation+0.000
specifically
Token specifically
Feature activation+0.000
directs
Token directs
Feature activation+0.000
after
Token after
Feature activation+0.000
his
Token his
Feature activation+0.000
years
Token years
Feature activation+0.000
catching
Token catching
Feature activation+0.000
passes
Token passes
Feature activation+0.000
from
Token from
Feature activation+1.217
Rodgers
Token Rodgers
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
P
TokenP
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
videos
Token videos
Feature activation+0.000
were
Token were
Feature activation+0.000
passed
Token passed
Feature activation+2.097
around
Token around
Feature activation+2.738
through
Token through
Feature activation+1.071
download
Token download
Feature activation+0.000
links
Token links
Feature activation+0.016
on
Token on
Feature activation+0.664
their
Token their
Feature activation+1.522
website
Token website
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
DNC
Token DNC
Feature activation+0.000
a
Token a
Feature activation+0.000
free
Token free
Feature activation+0.000
pass
Token pass
Feature activation+1.158
for
Token for
Feature activation+1.907
cheating
Token cheating
Feature activation+0.000
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
Clinton
Token Clinton
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
publishers
Token publishers
Feature activation+0.000
passed
Token passed
Feature activation+0.000
on
Token on
Feature activation+1.048
the
Token the
Feature activation+0.991
game
Token game
Feature activation+0.000
due
Token due
Feature activation+0.000
to
Token to
Feature activation+0.028
its
Token its
Feature activation+0.079

INTERVAL 0.499 - 0.999
CONTAINS 0.006%

preventive
Token preventive
Feature activation+0.000
coverage
Token coverage
Feature activation+0.000
when
Token when
Feature activation+0.000
it
Token it
Feature activation+0.000
passed
Token passed
Feature activation+0.000
the
Token the
Feature activation+0.950
Affordable
Token Affordable
Feature activation+0.000
Care
Token Care
Feature activation+0.000
Act
Token Act
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
No
Token No
Feature activation+0.000
excuses
Token excuses
Feature activation+0.000
to
Token to
Feature activation+0.000
pass
Token pass
Feature activation+0.000
those
Token those
Feature activation+2.051
up
Token up
Feature activation+0.896
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Bruins
Token Bruins
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
bill
Token bill
Feature activation+0.000
passed
Token passed
Feature activation+0.000
the
Token the
Feature activation+0.604
Senate
Token Senate
Feature activation+0.000
43
Token 43
Feature activation+1.457
votes
Token votes
Feature activation+0.000
to
Token to
Feature activation+0.000
12
Token 12
Feature activation+0.000
lost
Token lost
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
passage
Token passage
Feature activation+0.000
of
Token of
Feature activation+0.016
time
Token time
Feature activation+0.680
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
tw
Token tw
Feature activation+0.000
roughly
Token roughly
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.000
to
Token to
Feature activation+0.000
pass
Token pass
Feature activation+0.000
half
Token half
Feature activation+0.684
guard
Token guard
Feature activation+0.111
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.000 - 0.499
CONTAINS 99.983%

marking
Token marking
Feature activation+0.000
the
Token the
Feature activation+0.000
19
Token 19
Feature activation+0.000
th
Tokenth
Feature activation+0.000
anniversary
Token anniversary
Feature activation+0.000
of
Token of
Feature activation+0.000
Hong
Token Hong
Feature activation+0.000
Kong
Token Kong
Feature activation+0.000
's
Token's
Feature activation+0.000
hand
Token hand
Feature activation+0.000
over
Tokenover
Feature activation+0.000
...
Token...
Feature activation+0.000
And
Token And
Feature activation+0.000
,
Token,
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
way
Token way
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
all
Token all
Feature activation+0.000
this
Token this
Feature activation+0.000
am
Token am
Feature activation+0.000
Human
Token Human
Feature activation+0.000
Rights
Token Rights
Feature activation+0.000
Commission
Token Commission
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
guidelines
Token guidelines
Feature activation+0.000
say
Token say
Feature activation+0.000
creed
Token creed
Feature activation+0.000
can
Token can
Feature activation+0.000
include
Token include
Feature activation+0.000
not
Token not
Feature activation+0.000
just
Token just
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
heritage
Token heritage
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
H
Token H
Feature activation+0.000
ora
Tokenora
Feature activation+0.000
because
Token because
Feature activation+0.000
these
Token these
Feature activation+0.000
pol
Token pol
Feature activation+0.000
ishes
Tokenishes
Feature activation+0.000
are
Token are
Feature activation+0.000
both
Token both
Feature activation+0.000
so
Token so
Feature activation+0.000
intense
Token intense
Feature activation+0.000
and
Token and
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 H5.7: (feature 19351)

TOP ACTIVATIONS
MAX = 4.440

says
Token says
Feature activation+0.000
officers
Token officers
Feature activation+0.000
found
Token found
Feature activation+0.000
a
Token a
Feature activation+2.019
weapon
Token weapon
Feature activation+0.942
in
Token in
Feature activation+4.440
his
Token his
Feature activation+3.401
vehicle
Token vehicle
Feature activation+0.970
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
classified
Token classified
Feature activation+0.000
information
Token information
Feature activation+0.000
found
Token found
Feature activation+0.211
in
Token in
Feature activation+4.422
Mrs
Token Mrs
Feature activation+0.000
.
Token.
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
youngster
Token youngster
Feature activation+0.000
found
Token found
Feature activation+0.000
in
Token in
Feature activation+3.261
the
Token the
Feature activation+3.891
Mexican
Token Mexican
Feature activation+0.000
state
Token state
Feature activation+0.000
of
Token of
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
ihu
Tokenihu
Feature activation+0.000
say
Token say
Feature activation+0.000
they
Token they
Feature activation+0.000
found
Token found
Feature activation+0.000
a
Token a
Feature activation+1.314
knife
Token knife
Feature activation+0.000
at
Token at
Feature activation+3.858
the
Token the
Feature activation+1.323
scene
Token scene
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
shooting
Token shooting
Feature activation+0.000
gasoline
Token gasoline
Feature activation+0.000
-
Token-
Feature activation+0.000
operated
Tokenoperated
Feature activation+0.000
water
Token water
Feature activation+0.000
pump
Token pump
Feature activation+0.000
in
Token in
Feature activation+3.572
the
Token the
Feature activation+2.476
back
Token back
Feature activation+0.000
seat
Token seat
Feature activation+0.000
.
Token.
Feature activation+0.000
Prosecutors
Token Prosecutors
Feature activation+0.000
officers
Token officers
Feature activation+0.000
found
Token found
Feature activation+0.000
a
Token a
Feature activation+2.019
weapon
Token weapon
Feature activation+0.942
in
Token in
Feature activation+4.440
his
Token his
Feature activation+3.401
vehicle
Token vehicle
Feature activation+0.970
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hours
TokenHours
Feature activation+0.000
4
Token 4
Feature activation+0.000
year
Token year
Feature activation+0.000
old
Token old
Feature activation+0.000
boy
Token boy
Feature activation+0.000
found
Token found
Feature activation+0.159
in
Token in
Feature activation+3.383
Ju
Token Ju
Feature activation+0.000
arez
Tokenarez
Feature activation+0.000
was
Token was
Feature activation+0.087
returned
Token returned
Feature activation+0.000
to
Token to
Feature activation+0.000
announced
Token announced
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
youngster
Token youngster
Feature activation+0.000
found
Token found
Feature activation+0.000
in
Token in
Feature activation+3.261
the
Token the
Feature activation+3.891
Mexican
Token Mexican
Feature activation+0.000
state
Token state
Feature activation+0.000
of
Token of
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
Rome
Token Rome
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Found
TokenFound
Feature activation+0.000
in
Token in
Feature activation+1.989
the
Token the
Feature activation+3.133
bathroom
Token bathroom
Feature activation+1.085
by
Token by
Feature activation+0.643
his
Token his
Feature activation+0.000
teenage
Token teenage
Feature activation+0.000
son
Token son
Feature activation+0.000
conflict
Token conflict
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
found
Token found
Feature activation+0.638
in
Token in
Feature activation+2.196
a
Token a
Feature activation+3.028
house
Token house
Feature activation+1.073
in
Token in
Feature activation+0.000
Der
Token Der
Feature activation+0.000
bys
Tokenbys
Feature activation+0.000
hire
Tokenhire
Feature activation+0.000
discovery
Token discovery
Feature activation+0.000
of
Token of
Feature activation+0.601
space
Token space
Feature activation+0.000
debris
Token debris
Feature activation+0.000
found
Token found
Feature activation+0.113
in
Token in
Feature activation+2.904
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.176
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Secretary
Token Secretary
Feature activation+0.000
of
Token of
Feature activation+0.000
M
Token M
Feature activation+0.000
x
Tokenx
Feature activation+0.000
.
Token.
Feature activation+0.000
found
Token found
Feature activation+0.000
by
Token by
Feature activation+2.875
Ms
Token Ms
Feature activation+0.000
.
Token.
Feature activation+0.000
Martin
Token Martin
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
TR
Token TR
Feature activation+0.000
UTH
TokenUTH
Feature activation+0.000
:
Token:
Feature activation+0.000
Letter
Token Letter
Feature activation+0.000
found
Token found
Feature activation+0.697
on
Token on
Feature activation+2.790
some
Token some
Feature activation+2.275
seats
Token seats
Feature activation+0.560
left
Token left
Feature activation+0.875
by
Token by
Feature activation+0.905
Stock
Token Stock
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
find
Token find
Feature activation+0.000
a
Token a
Feature activation+1.621
book
Token book
Feature activation+0.681
in
Token in
Feature activation+2.779
his
Token his
Feature activation+2.738
vehicle
Token vehicle
Feature activation+1.072
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pro
TokenPro
Feature activation+0.000
not
Token not
Feature activation+0.000
find
Token find
Feature activation+0.000
a
Token a
Feature activation+1.621
book
Token book
Feature activation+0.681
in
Token in
Feature activation+2.779
his
Token his
Feature activation+2.738
vehicle
Token vehicle
Feature activation+1.072
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pro
TokenPro
Feature activation+0.000
testers
Tokentesters
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
H
TokenH
Feature activation+0.000
ernandez
Tokenernandez
Feature activation+0.000
was
Token was
Feature activation+0.000
found
Token found
Feature activation+0.723
by
Token by
Feature activation+2.656
corrections
Token corrections
Feature activation+0.000
officers
Token officers
Feature activation+0.000
in
Token in
Feature activation+2.530
his
Token his
Feature activation+2.444
single
Token single
Feature activation+0.000
pictured
Tokenpictured
Feature activation+0.000
left
Token left
Feature activation+0.000
)
Token)
Feature activation+0.000
was
Token was
Feature activation+0.000
found
Token found
Feature activation+1.233
dead
Token dead
Feature activation+2.564
in
Token in
Feature activation+1.949
the
Token the
Feature activation+2.550
bathroom
Token bathroom
Feature activation+0.994
at
Token at
Feature activation+0.000
home
Token home
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
aircraft
Token aircraft
Feature activation+0.000
debris
Token debris
Feature activation+0.000
found
Token found
Feature activation+0.000
on
Token on
Feature activation+2.551
Re
Token Re
Feature activation+0.000
union
Tokenunion
Feature activation+0.000
Island
Token Island
Feature activation+0.000
is
Token is
Feature activation+0.000
indeed
Token indeed
Feature activation+0.000
)
Token)
Feature activation+0.000
was
Token was
Feature activation+0.000
found
Token found
Feature activation+1.233
dead
Token dead
Feature activation+2.564
in
Token in
Feature activation+1.949
the
Token the
Feature activation+2.550
bathroom
Token bathroom
Feature activation+0.994
at
Token at
Feature activation+0.000
home
Token home
Feature activation+0.000
in
Token in
Feature activation+0.000
Water
Token Water
Feature activation+0.000
-
Token-
Feature activation+0.000
equipped
Tokenequipped
Feature activation+0.000
gy
Token gy
Feature activation+0.000
ms
Tokenms
Feature activation+0.000
found
Token found
Feature activation+0.000
on
Token on
Feature activation+2.548
most
Token most
Feature activation+0.624
platforms
Token platforms
Feature activation+0.079
were
Token were
Feature activation+0.000
thought
Token thought
Feature activation+0.000
to
Token to
Feature activation+0.000

Top DFA by src position
MAX = 4.918

Kerr
Token Kerr
Feature activation-0.002
Top resid features:
Put
Token Put
Feature activation-0.002
Top resid features:
ney
Tokenney
Feature activation-0.000
Top resid features:
says
Token says
Feature activation+0.000
Top resid features:
officers
Token officers
Feature activation+0.001
Top resid features:
found
Token found
Feature activation+4.810
Top resid features:
a
Token a
Feature activation+0.083
Top resid features:
weapon
Token weapon
Feature activation+0.275
Top resid features:
in
Token in
Feature activation+0.032
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
vehicle
Token vehicle
Feature activation+0.000
Top resid features:
Most
Token Most
Feature activation+0.002
Top resid features:
of
Token of
Feature activation-0.030
Top resid features:
the
Token the
Feature activation-0.015
Top resid features:
classified
Token classified
Feature activation+0.155
Top resid features:
information
Token information
Feature activation+0.036
Top resid features:
found
Token found
Feature activation+4.918
Top resid features:
in
Token in
Feature activation+0.026
Top resid features:
Mrs
Token Mrs
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Clinton
Token Clinton
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Department
Token Department
Feature activation-0.006
Top resid features:
announced
Token announced
Feature activation-0.010
Top resid features:
that
Token that
Feature activation+0.006
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
youngster
Token youngster
Feature activation-0.000
Top resid features:
found
Token found
Feature activation+4.445
Top resid features:
in
Token in
Feature activation+0.307
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
Mexican
Token Mexican
Feature activation+0.000
Top resid features:
state
Token state
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
leave
Token leave
Feature activation-0.020
Top resid features:
.
Token.
Feature activation-0.018
Top resid features:
Officials
Token Officials
Feature activation-0.013
Top resid features:
say
Token say
Feature activation+0.006
Top resid features:
they
Token they
Feature activation+0.001
Top resid features:
found
Token found
Feature activation+4.332
Top resid features:
a
Token a
Feature activation+0.076
Top resid features:
knife
Token knife
Feature activation+0.183
Top resid features:
at
Token at
Feature activation+0.096
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
scene
Token scene
Feature activation+0.000
Top resid features:
mon
Token mon
Feature activation-0.002
Top resid features:
oxide
Tokenoxide
Feature activation+0.003
Top resid features:
poisoning
Token poisoning
Feature activation+0.003
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
police
Token police
Feature activation-0.024
Top resid features:
found
Token found
Feature activation+3.845
Top resid features:
a
Token a
Feature activation+0.239
Top resid features:
gasoline
Token gasoline
Feature activation+0.033
Top resid features:
-
Token-
Feature activation-0.007
Top resid features:
operated
Tokenoperated
Feature activation-0.004
Top resid features:
water
Token water
Feature activation+0.051
Top resid features:
Kerr
Token Kerr
Feature activation-0.007
Top resid features:
Put
Token Put
Feature activation-0.002
Top resid features:
ney
Tokenney
Feature activation-0.003
Top resid features:
says
Token says
Feature activation+0.003
Top resid features:
officers
Token officers
Feature activation-0.026
Top resid features:
found
Token found
Feature activation+3.918
Top resid features:
a
Token a
Feature activation+0.078
Top resid features:
weapon
Token weapon
Feature activation+0.071
Top resid features:
in
Token in
Feature activation+0.319
Top resid features:
his
Token his
Feature activation-0.129
Top resid features:
vehicle
Token vehicle
Feature activation+0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.049
Top resid features:
4
Token 4
Feature activation+0.097
Top resid features:
year
Token year
Feature activation-0.024
Top resid features:
old
Token old
Feature activation+0.076
Top resid features:
boy
Token boy
Feature activation+0.085
Top resid features:
found
Token found
Feature activation+3.927
Top resid features:
in
Token in
Feature activation+0.076
Top resid features:
Ju
Token Ju
Feature activation+0.000
Top resid features:
arez
Tokenarez
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
returned
Token returned
Feature activation+0.000
Top resid features:
Department
Token Department
Feature activation-0.005
Top resid features:
announced
Token announced
Feature activation-0.037
Top resid features:
that
Token that
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
youngster
Token youngster
Feature activation+0.061
Top resid features:
found
Token found
Feature activation+4.016
Top resid features:
in
Token in
Feature activation+0.041
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Mexican
Token Mexican
Feature activation+0.000
Top resid features:
state
Token state
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
out
Token out
Feature activation-0.037
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
Rome
Token Rome
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.035
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
Found
TokenFound
Feature activation+3.730
Top resid features:
in
Token in
Feature activation+0.197
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
bathroom
Token bathroom
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.010
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
conflict
Token conflict
Feature activation-0.006
Top resid features:
have
Token have
Feature activation-0.059
Top resid features:
been
Token been
Feature activation+0.034
Top resid features:
found
Token found
Feature activation+3.515
Top resid features:
in
Token in
Feature activation+0.125
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
house
Token house
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
Der
Token Der
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
discovery
Token discovery
Feature activation+0.100
Top resid features:
of
Token of
Feature activation+0.039
Top resid features:
space
Token space
Feature activation-0.018
Top resid features:
debris
Token debris
Feature activation+0.053
Top resid features:
found
Token found
Feature activation+3.253
Top resid features:
in
Token in
Feature activation+0.056
Top resid features:
New
Token New
Feature activation+0.000
Top resid features:
Zealand
Token Zealand
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
citation
Token citation
Feature activation-0.077
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
M
Token M
Feature activation+0.027
Top resid features:
x
Tokenx
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
found
Token found
Feature activation+3.790
Top resid features:
by
Token by
Feature activation+0.065
Top resid features:
Ms
Token Ms
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Martin
Token Martin
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
ARD
TokenARD
Feature activation-0.001
Top resid features:
TR
Token TR
Feature activation+0.006
Top resid features:
UTH
TokenUTH
Feature activation+0.013
Top resid features:
:
Token:
Feature activation+0.078
Top resid features:
Letter
Token Letter
Feature activation+0.060
Top resid features:
found
Token found
Feature activation+3.191
Top resid features:
on
Token on
Feature activation+0.170
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
seats
Token seats
Feature activation+0.000
Top resid features:
left
Token left
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
have
Token have
Feature activation-0.025
Top resid features:
insisted
Token insisted
Feature activation-0.001
Top resid features:
they
Token they
Feature activation-0.002
Top resid features:
did
Token did
Feature activation+0.004
Top resid features:
not
Token not
Feature activation+0.010
Top resid features:
find
Token find
Feature activation+3.184
Top resid features:
a
Token a
Feature activation+0.098
Top resid features:
book
Token book
Feature activation+0.078
Top resid features:
in
Token in
Feature activation+0.059
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
vehicle
Token vehicle
Feature activation+0.000
Top resid features:
have
Token have
Feature activation-0.037
Top resid features:
insisted
Token insisted
Feature activation-0.022
Top resid features:
they
Token they
Feature activation-0.019
Top resid features:
did
Token did
Feature activation-0.005
Top resid features:
not
Token not
Feature activation+0.006
Top resid features:
find
Token find
Feature activation+3.136
Top resid features:
a
Token a
Feature activation+0.110
Top resid features:
book
Token book
Feature activation+0.042
Top resid features:
in
Token in
Feature activation+0.376
Top resid features:
his
Token his
Feature activation-0.074
Top resid features:
vehicle
Token vehicle
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
H
TokenH
Feature activation+0.000
Top resid features:
ernandez
Tokenernandez
Feature activation-0.004
Top resid features:
was
Token was
Feature activation-0.014
Top resid features:
found
Token found
Feature activation+3.449
Top resid features:
by
Token by
Feature activation-0.000
Top resid features:
corrections
Token corrections
Feature activation+0.000
Top resid features:
officers
Token officers
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
(
Token (
Feature activation-0.006
Top resid features:
pictured
Tokenpictured
Feature activation+0.003
Top resid features:
left
Token left
Feature activation-0.001
Top resid features:
)
Token)
Feature activation+0.007
Top resid features:
was
Token was
Feature activation-0.030
Top resid features:
found
Token found
Feature activation+3.178
Top resid features:
dead
Token dead
Feature activation-0.019
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
bathroom
Token bathroom
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
confirmed
Token confirmed
Feature activation+0.006
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
aircraft
Token aircraft
Feature activation+0.012
Top resid features:
debris
Token debris
Feature activation+0.038
Top resid features:
found
Token found
Feature activation+3.277
Top resid features:
on
Token on
Feature activation+0.020
Top resid features:
Re
Token Re
Feature activation+0.000
Top resid features:
union
Tokenunion
Feature activation+0.000
Top resid features:
Island
Token Island
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
(
Token (
Feature activation-0.006
Top resid features:
pictured
Tokenpictured
Feature activation-0.003
Top resid features:
left
Token left
Feature activation-0.008
Top resid features:
)
Token)
Feature activation+0.003
Top resid features:
was
Token was
Feature activation-0.010
Top resid features:
found
Token found
Feature activation+3.261
Top resid features:
dead
Token dead
Feature activation-0.011
Top resid features:
in
Token in
Feature activation+0.030
Top resid features:
the
Token the
Feature activation-0.021
Top resid features:
bathroom
Token bathroom
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
Well
TokenWell
Feature activation-0.003
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
equipped
Tokenequipped
Feature activation+0.032
Top resid features:
gy
Token gy
Feature activation+0.011
Top resid features:
ms
Tokenms
Feature activation-0.014
Top resid features:
found
Token found
Feature activation+3.215
Top resid features:
on
Token on
Feature activation+0.052
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
platforms
Token platforms
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
thought
Token thought
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.01

Head 1: 0.02

Head 2: 0.06

Head 3: 0.05

Head 4: 0.07

Head 5: 0.02

Head 6: 0.03

Head 7: 0.55

Head 8: 0.03

Head 9: 0.03

Head 10: 0.07

Head 11: 0.05

Positive logits

Missing1.77

discrepancies1.72

wreckage1.71

AppData1.69

ById1.69

inconsistencies1.67

faulty1.60

misplaced1.58

cracks1.54

defective1.53

flaws1.52

luggage1.51

stains1.51

similarities1.50

boxes1.50

anomalies1.50

evidence1.49

objectionable1.49

Seat1.48

items1.45

Negative logits

endeav-1.74

endeavour-1.66

operation-1.65

farewell-1.65

endeavor-1.58

uncond-1.48

ctions-1.47

WAR-1.46

inaug-1.45

encour-1.45

goodbye-1.45

assisted-1.44

engagements-1.42

vigil-1.42

icz-1.41

ific-1.41

helicop-1.41

pport-1.40

ependence-1.39

mediated-1.39

INTERVAL 3.996 - 4.440
CONTAINS 0.000%

says
Token says
Feature activation+0.000
officers
Token officers
Feature activation+0.000
found
Token found
Feature activation+0.000
a
Token a
Feature activation+2.019
weapon
Token weapon
Feature activation+0.942
in
Token in
Feature activation+4.440
his
Token his
Feature activation+3.401
vehicle
Token vehicle
Feature activation+0.970
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
classified
Token classified
Feature activation+0.000
information
Token information
Feature activation+0.000
found
Token found
Feature activation+0.211
in
Token in
Feature activation+4.422
Mrs
Token Mrs
Feature activation+0.000
.
Token.
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 3.552 - 3.996
CONTAINS 0.000%

gasoline
Token gasoline
Feature activation+0.000
-
Token-
Feature activation+0.000
operated
Tokenoperated
Feature activation+0.000
water
Token water
Feature activation+0.000
pump
Token pump
Feature activation+0.000
in
Token in
Feature activation+3.572
the
Token the
Feature activation+2.476
back
Token back
Feature activation+0.000
seat
Token seat
Feature activation+0.000
.
Token.
Feature activation+0.000
Prosecutors
Token Prosecutors
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
youngster
Token youngster
Feature activation+0.000
found
Token found
Feature activation+0.000
in
Token in
Feature activation+3.261
the
Token the
Feature activation+3.891
Mexican
Token Mexican
Feature activation+0.000
state
Token state
Feature activation+0.000
of
Token of
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
ihu
Tokenihu
Feature activation+0.000
say
Token say
Feature activation+0.000
they
Token they
Feature activation+0.000
found
Token found
Feature activation+0.000
a
Token a
Feature activation+1.314
knife
Token knife
Feature activation+0.000
at
Token at
Feature activation+3.858
the
Token the
Feature activation+1.323
scene
Token scene
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
shooting
Token shooting
Feature activation+0.000

INTERVAL 3.108 - 3.552
CONTAINS 0.000%

officers
Token officers
Feature activation+0.000
found
Token found
Feature activation+0.000
a
Token a
Feature activation+2.019
weapon
Token weapon
Feature activation+0.942
in
Token in
Feature activation+4.440
his
Token his
Feature activation+3.401
vehicle
Token vehicle
Feature activation+0.970
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Hours
TokenHours
Feature activation+0.000
Rome
Token Rome
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Found
TokenFound
Feature activation+0.000
in
Token in
Feature activation+1.989
the
Token the
Feature activation+3.133
bathroom
Token bathroom
Feature activation+1.085
by
Token by
Feature activation+0.643
his
Token his
Feature activation+0.000
teenage
Token teenage
Feature activation+0.000
son
Token son
Feature activation+0.000
announced
Token announced
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
youngster
Token youngster
Feature activation+0.000
found
Token found
Feature activation+0.000
in
Token in
Feature activation+3.261
the
Token the
Feature activation+3.891
Mexican
Token Mexican
Feature activation+0.000
state
Token state
Feature activation+0.000
of
Token of
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
4
Token 4
Feature activation+0.000
year
Token year
Feature activation+0.000
old
Token old
Feature activation+0.000
boy
Token boy
Feature activation+0.000
found
Token found
Feature activation+0.159
in
Token in
Feature activation+3.383
Ju
Token Ju
Feature activation+0.000
arez
Tokenarez
Feature activation+0.000
was
Token was
Feature activation+0.087
returned
Token returned
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 2.664 - 3.108
CONTAINS 0.001%

TR
Token TR
Feature activation+0.000
UTH
TokenUTH
Feature activation+0.000
:
Token:
Feature activation+0.000
Letter
Token Letter
Feature activation+0.000
found
Token found
Feature activation+0.697
on
Token on
Feature activation+2.790
some
Token some
Feature activation+2.275
seats
Token seats
Feature activation+0.560
left
Token left
Feature activation+0.875
by
Token by
Feature activation+0.905
Stock
Token Stock
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
find
Token find
Feature activation+0.000
a
Token a
Feature activation+1.621
book
Token book
Feature activation+0.681
in
Token in
Feature activation+2.779
his
Token his
Feature activation+2.738
vehicle
Token vehicle
Feature activation+1.072
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pro
TokenPro
Feature activation+0.000
conflict
Token conflict
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
found
Token found
Feature activation+0.638
in
Token in
Feature activation+2.196
a
Token a
Feature activation+3.028
house
Token house
Feature activation+1.073
in
Token in
Feature activation+0.000
Der
Token Der
Feature activation+0.000
bys
Tokenbys
Feature activation+0.000
hire
Tokenhire
Feature activation+0.000
of
Token of
Feature activation+0.000
M
Token M
Feature activation+0.000
x
Tokenx
Feature activation+0.000
.
Token.
Feature activation+0.000
found
Token found
Feature activation+0.000
by
Token by
Feature activation+2.875
Ms
Token Ms
Feature activation+0.000
.
Token.
Feature activation+0.000
Martin
Token Martin
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
discovery
Token discovery
Feature activation+0.000
of
Token of
Feature activation+0.601
space
Token space
Feature activation+0.000
debris
Token debris
Feature activation+0.000
found
Token found
Feature activation+0.113
in
Token in
Feature activation+2.904
New
Token New
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.176
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Secretary
Token Secretary
Feature activation+0.000

INTERVAL 2.220 - 2.664
CONTAINS 0.002%

She
Token She
Feature activation+0.000
was
Token was
Feature activation+0.000
later
Token later
Feature activation+0.000
found
Token found
Feature activation+0.122
dead
Token dead
Feature activation+2.261
in
Token in
Feature activation+2.447
her
Token her
Feature activation+1.918
apartment
Token apartment
Feature activation+0.282
.
Token.
Feature activation+0.041
My
Token My
Feature activation+0.000
agent
Token agent
Feature activation+0.000
found
Token found
Feature activation+0.723
by
Token by
Feature activation+2.656
corrections
Token corrections
Feature activation+0.000
officers
Token officers
Feature activation+0.000
in
Token in
Feature activation+2.530
his
Token his
Feature activation+2.444
single
Token single
Feature activation+0.000
cell
Token cell
Feature activation+0.000
in
Token in
Feature activation+0.000
general
Token general
Feature activation+0.000
population
Token population
Feature activation+0.000
likely
Token likely
Feature activation+0.000
the
Token the
Feature activation+0.000
initiative
Token initiative
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
found
Token found
Feature activation+2.279
unconstitutional
Token unconstitutional
Feature activation+0.000
because
Token because
Feature activation+0.000
it
Token it
Feature activation+0.000
singles
Token singles
Feature activation+0.000
out
Token out
Feature activation+0.000
.
Token.
Feature activation+0.000
She
Token She
Feature activation+0.000
was
Token was
Feature activation+0.000
later
Token later
Feature activation+0.000
found
Token found
Feature activation+0.122
dead
Token dead
Feature activation+2.261
in
Token in
Feature activation+2.447
her
Token her
Feature activation+1.918
apartment
Token apartment
Feature activation+0.282
.
Token.
Feature activation+0.041
My
Token My
Feature activation+0.000
-
Token-
Feature activation+0.000
operated
Tokenoperated
Feature activation+0.000
water
Token water
Feature activation+0.000
pump
Token pump
Feature activation+0.000
in
Token in
Feature activation+3.572
the
Token the
Feature activation+2.476
back
Token back
Feature activation+0.000
seat
Token seat
Feature activation+0.000
.
Token.
Feature activation+0.000
Prosecutors
Token Prosecutors
Feature activation+0.000
say
Token say
Feature activation+0.000

INTERVAL 1.776 - 2.220
CONTAINS 0.003%

Carpenter
Token Carpenter
Feature activation+0.000
-
Token-
Feature activation+0.000
G
TokenG
Feature activation+0.000
unn
Tokenunn
Feature activation+0.000
found
Token found
Feature activation+0.000
in
Token in
Feature activation+1.844
favour
Token favour
Feature activation+0.000
of
Token of
Feature activation+0.000
Randy
Token Randy
Feature activation+0.000
Fleming
Token Fleming
Feature activation+0.000
,
Token,
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
identified
Token identified
Feature activation+0.000
and
Token and
Feature activation+0.000
found
Token found
Feature activation+0.345
on
Token on
Feature activation+2.173
Friday
Token Friday
Feature activation+0.788
,
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
plane
Token plane
Feature activation+0.000
debris
Token debris
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
found
Token found
Feature activation+0.792
on
Token on
Feature activation+1.864
Re
Token Re
Feature activation+0.000
union
Tokenunion
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
window
Token window
Feature activation+0.000
also
Token also
Feature activation+0.000
list
Token list
Feature activation+0.000
items
Token items
Feature activation+0.000
police
Token police
Feature activation+0.000
found
Token found
Feature activation+0.453
when
Token when
Feature activation+2.077
they
Token they
Feature activation+0.712
searched
Token searched
Feature activation+0.072
the
Token the
Feature activation+0.351
apartment
Token apartment
Feature activation+0.000
the
Token the
Feature activation+0.016
in
Token in
Feature activation+0.000
Rome
Token Rome
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Found
TokenFound
Feature activation+0.000
in
Token in
Feature activation+1.989
the
Token the
Feature activation+3.133
bathroom
Token bathroom
Feature activation+1.085
by
Token by
Feature activation+0.643
his
Token his
Feature activation+0.000
teenage
Token teenage
Feature activation+0.000

INTERVAL 1.332 - 1.776
CONTAINS 0.004%

weird
Token weird
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
found
Token found
Feature activation+0.000
in
Token in
Feature activation+1.578
the
Token the
Feature activation+1.681
ar
Token ar
Feature activation+0.000
thouse
Tokenthouse
Feature activation+0.000
genre
Token genre
Feature activation+0.000
.
Token.
Feature activation+0.000
Those
Token Those
Feature activation+0.000
).
Token).
Feature activation+0.000
Authorities
Token Authorities
Feature activation+0.000
found
Token found
Feature activation+0.000
classified
Token classified
Feature activation+0.215
documents
Token documents
Feature activation+1.189
throughout
Token throughout
Feature activation+1.648
his
Token his
Feature activation+0.000
home
Token home
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
ceramic
Token ceramic
Feature activation+0.000
vessel
Token vessel
Feature activation+0.000
shards
Token shards
Feature activation+0.000
found
Token found
Feature activation+0.122
in
Token in
Feature activation+1.701
the
Token the
Feature activation+2.030
pit
Token pit
Feature activation+0.057
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
O
Token O
Feature activation+0.000
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+0.000
readers
Token readers
Feature activation+0.000
)
Token)
Feature activation+0.000
found
Token found
Feature activation+0.000
so
Token so
Feature activation+1.442
fresh
Token fresh
Feature activation+0.431
and
Token and
Feature activation+0.000
enticing
Token enticing
Feature activation+0.000
about
Token about
Feature activation+0.000
my
Token my
Feature activation+0.000
ump
Tokenump
Feature activation+0.000
lubric
Token lubric
Feature activation+0.000
ation
Tokenation
Feature activation+0.000
system
Token system
Feature activation+0.000
found
Token found
Feature activation+0.000
on
Token on
Feature activation+1.533
the
Token the
Feature activation+1.723
V
Token V
Feature activation+0.000
8
Token8
Feature activation+0.000
V
Token V
Feature activation+0.000
antage
Tokenantage
Feature activation+0.000

INTERVAL 0.888 - 1.332
CONTAINS 0.008%

found
Token found
Feature activation+0.000
on
Token on
Feature activation+1.306
St
Token St
Feature activation+0.000
ans
Tokenans
Feature activation+0.000
bury
Tokenbury
Feature activation+0.000
at
Token at
Feature activation+1.049
the
Token the
Feature activation+1.088
crime
Token crime
Feature activation+0.000
scene
Token scene
Feature activation+0.059
was
Token was
Feature activation+0.446
reported
Token reported
Feature activation+0.000
priest
Token priest
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
uncovered
Token uncovered
Feature activation+0.000
in
Token in
Feature activation+0.986
the
Token the
Feature activation+1.141
investigative
Token investigative
Feature activation+0.000
project
Token project
Feature activation+0.000
,
Token,
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
Madden
Token Madden
Feature activation+0.000
:
Token:
Feature activation+0.000
15
Token15
Feature activation+0.000
a
Token a
Feature activation+0.000
.
Token.
Feature activation+0.000
m
Tokenm
Feature activation+0.000
.
Token.
Feature activation+1.031
walking
Token walking
Feature activation+0.087
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.036
middle
Token middle
Feature activation+0.000
of
Token of
Feature activation+0.000
and
Token and
Feature activation+0.000
ref
Token ref
Feature activation+0.000
s
Tokens
Feature activation+0.000
will
Token will
Feature activation+0.000
find
Token find
Feature activation+0.000
him
Token him
Feature activation+0.941
often
Token often
Feature activation+1.744
.
Token.
Feature activation+0.000
Related
Token Related
Feature activation+0.000
Links
Token Links
Feature activation+0.000
-
Token -
Feature activation+0.000
weed
Token weed
Feature activation+0.000
killer
Tokenkiller
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
detected
Token detected
Feature activation+0.000
in
Token in
Feature activation+1.076
food
Token food
Feature activation+0.000
,
Token,
Feature activation+0.000
water
Token water
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.042

INTERVAL 0.444 - 0.888
CONTAINS 0.017%

Letter
Token Letter
Feature activation+0.000
found
Token found
Feature activation+0.697
on
Token on
Feature activation+2.790
some
Token some
Feature activation+2.275
seats
Token seats
Feature activation+0.560
left
Token left
Feature activation+0.875
by
Token by
Feature activation+0.905
Stock
Token Stock
Feature activation+0.000
port
Tokenport
Feature activation+0.000
fans
Token fans
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
was
Token was
Feature activation+0.000
found
Token found
Feature activation+0.000
in
Token in
Feature activation+2.483
his
Token his
Feature activation+2.397
pickup
Token pickup
Feature activation+0.298
in
Token in
Feature activation+0.839
Fair
Token Fair
Feature activation+0.000
haven
Tokenhaven
Feature activation+0.000
on
Token on
Feature activation+0.000
July
Token July
Feature activation+0.000
13
Token 13
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
White
TokenWhite
Feature activation+0.000
tigers
Token tigers
Feature activation+0.000
are
Token are
Feature activation+0.000
found
Token found
Feature activation+0.000
in
Token in
Feature activation+0.664
southern
Token southern
Feature activation+0.285
and
Token and
Feature activation+0.000
eastern
Token eastern
Feature activation+0.000
Asia
Token Asia
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
found
Token found
Feature activation+0.683
to
Token to
Feature activation+2.223
be
Token be
Feature activation+0.720
prof
Token prof
Feature activation+0.000
iting
Tokeniting
Feature activation+0.000
from
Token from
Feature activation+0.000
fetal
Token fetal
Feature activation+0.000
tissue
Token tissue
Feature activation+0.000
was
Token was
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
discovery
Token discovery
Feature activation+0.000
of
Token of
Feature activation+0.724
extremely
Token extremely
Feature activation+0.000
sensitive
Token sensitive
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
that
Token that
Feature activation+0.153
was
Token was
Feature activation+0.000

INTERVAL 0.000 - 0.444
CONTAINS 99.965%

now
Token now
Feature activation+0.000
pe
Token pe
Feature activation+0.000
aking
Tokenaking
Feature activation+0.000
parallel
Token parallel
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
beginning
Token beginning
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
anticipated
Token anticipated
Feature activation+0.000
atrocities
Token atrocities
Feature activation+0.000
to
Token to
Feature activation+0.000
participate
Token participate
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
qualification
Token qualification
Feature activation+0.000
process
Token process
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
RL
Token RL
Feature activation+0.000
IF
TokenIF
Feature activation+0.000
Rugby
Token Rugby
Feature activation+0.000
s
Tokens
Feature activation+0.000
vice
Token vice
Feature activation+0.000
premier
Token premier
Feature activation+0.000
Sil
Token Sil
Feature activation+0.000
van
Tokenvan
Feature activation+0.000
Shal
Token Shal
Feature activation+0.000
om
Tokenom
Feature activation+0.000
told
Token told
Feature activation+0.000
reporters
Token reporters
Feature activation+0.000
that
Token that
Feature activation+0.000
if
Token if
Feature activation+0.000
prevent
Token prevent
Feature activation+0.000
an
Token an
Feature activation+0.000
am
Token am
Feature activation+0.000
orous
Tokenorous
Feature activation+0.000
male
Token male
Feature activation+0.000
from
Token from
Feature activation+0.000
mating
Token mating
Feature activation+0.000
with
Token with
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
prosper
Token prosper
Feature activation+0.000
with
Token with
Feature activation+0.000
real
Token real
Feature activation+0.000
money
Token money
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
foundation
Token foundation
Feature activation+0.000
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
economic
Token economic
Feature activation+0.000
structure
Token structure
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 H5.7: (feature 23925)

TOP ACTIVATIONS
MAX = 3.426

provincial
Token provincial
Feature activation+0.000
government
Token government
Feature activation+0.000
calculated
Token calculated
Feature activation+0.000
the
Token the
Feature activation+0.000
opening
Token opening
Feature activation+0.000
of
Token of
Feature activation+3.426
European
Token European
Feature activation+0.479
markets
Token markets
Feature activation+0.000
to
Token to
Feature activation+1.736
Canadian
Token Canadian
Feature activation+0.111
shrimp
Token shrimp
Feature activation+0.000
wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.000
the
Token the
Feature activation+2.302
store
Token store
Feature activation+0.410
to
Token to
Feature activation+3.242
individual
Token individual
Feature activation+1.313
merchants
Token merchants
Feature activation+0.000
who
Token who
Feature activation+0.000
could
Token could
Feature activation+0.000
sell
Token sell
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
State
Token State
Feature activation+0.000
announced
Token announced
Feature activation+0.000
the
Token the
Feature activation+0.000
opening
Token opening
Feature activation+0.000
of
Token of
Feature activation+3.242
its
Token its
Feature activation+1.692
own
Token own
Feature activation+2.594
bank
Token bank
Feature activation+0.000
.
Token.
Feature activation+0.000
Called
Token Called
Feature activation+0.000
site
Token site
Feature activation+0.000
could
Token could
Feature activation+0.000
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
open
Tokenopen
Feature activation+0.321
as
Token as
Feature activation+3.238
early
Token early
Feature activation+0.164
as
Token as
Feature activation+0.000
January
Token January
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
.
Token.
Feature activation+0.000
this
Token this
Feature activation+0.000
topic
Token topic
Feature activation+0.000
with
Token with
Feature activation+0.000
an
Token an
Feature activation+0.000
open
Token open
Feature activation+0.000
mind
Token mind
Feature activation+3.094
will
Token will
Feature activation+0.000
convince
Token convince
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
with
Token with
Feature activation+0.000
half
Token half
Feature activation+0.000
this
Token this
Feature activation+0.000
document
Token document
Feature activation+0.000
have
Token have
Feature activation+0.000
an
Token an
Feature activation+0.000
open
Token open
Feature activation+0.000
mind
Token mind
Feature activation+3.055
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
idea
Token idea
Feature activation+0.000
that
Token that
Feature activation+0.000
std
Token std
Feature activation+0.000
a
Token a
Feature activation+0.000
one
Token one
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+3.028
the
Token the
Feature activation+2.230
Canadian
Token Canadian
Feature activation+0.378
auto
Token auto
Feature activation+0.000
market
Token market
Feature activation+0.015
,
Token,
Feature activation+0.000
opened
Token opened
Feature activation+0.000
the
Token the
Feature activation+1.983
sentence
Token sentence
Feature activation+0.000
that
Token that
Feature activation+0.000
way
Token way
Feature activation+0.344
to
Token to
Feature activation+2.977
sound
Token sound
Feature activation+0.000
good
Token good
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
they
Token they
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.000
an
Token an
Feature activation+0.000
open
Token open
Feature activation+0.000
mind
Token mind
Feature activation+2.862
,
Token,
Feature activation+0.000
have
Token have
Feature activation+0.000
fun
Token fun
Feature activation+0.000
and
Token and
Feature activation+0.000
be
Token be
Feature activation+0.000
account
Token account
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
should
Token should
Feature activation+0.000
open
Token open
Feature activation+0.000
a
Token a
Feature activation+2.801
new
Token new
Feature activation+2.780
window
Token window
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.067
your
Token your
Feature activation+0.016
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
should
Token should
Feature activation+0.000
open
Token open
Feature activation+0.000
a
Token a
Feature activation+2.801
new
Token new
Feature activation+2.780
window
Token window
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.067
your
Token your
Feature activation+0.016
environmental
Token environmental
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
her
Tokenher
Feature activation+0.000
also
Token also
Feature activation+0.000
opened
Token opened
Feature activation+0.089
a
Token a
Feature activation+2.773
couple
Token couple
Feature activation+1.456
of
Token of
Feature activation+2.017
Titan
Token Titan
Feature activation+0.000
Pad
TokenPad
Feature activation+0.000
pages
Token pages
Feature activation+0.283
ying
Tokenying
Feature activation+0.000
these
Token these
Feature activation+0.000
could
Token could
Feature activation+0.000
"
Token "
Feature activation+0.000
open
Tokenopen
Feature activation+0.000
new
Token new
Feature activation+2.771
doors
Token doors
Feature activation+0.000
"
Token"
Feature activation+0.000
to
Token to
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.000
is
Token is
Feature activation+0.000
slated
Token slated
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.000
in
Token in
Feature activation+2.719
Japanese
Token Japanese
Feature activation+0.000
theaters
Token theaters
Feature activation+0.000
in
Token in
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
.
Token.
Feature activation+0.000
finally
Token finally
Feature activation+0.000
opened
Token opened
Feature activation+0.171
Tr
Token Tr
Feature activation+0.022
on
Tokenon
Feature activation+0.000
Legacy
Token Legacy
Feature activation+0.076
in
Token in
Feature activation+2.705
theaters
Token theaters
Feature activation+0.000
on
Token on
Feature activation+0.000
December
Token December
Feature activation+0.000
17
Token 17
Feature activation+0.000
th
Tokenth
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
historic
Token historic
Feature activation+0.000
opening
Token opening
Feature activation+0.000
to
Token to
Feature activation+2.667
Cuba
Token Cuba
Feature activation+0.587
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Be
TokenBe
Feature activation+0.000
ijing
Tokenijing
Feature activation+0.000
will
Token will
Feature activation+0.000
open
Token open
Feature activation+0.181
its
Token its
Feature activation+2.277
economy
Token economy
Feature activation+2.653
at
Token at
Feature activation+0.521
the
Token the
Feature activation+0.246
pace
Token pace
Feature activation+0.000
it
Token it
Feature activation+0.000
deems
Token deems
Feature activation+0.000
announced
Token announced
Feature activation+0.000
the
Token the
Feature activation+0.000
opening
Token opening
Feature activation+0.000
of
Token of
Feature activation+3.242
its
Token its
Feature activation+1.692
own
Token own
Feature activation+2.594
bank
Token bank
Feature activation+0.000
.
Token.
Feature activation+0.000
Called
Token Called
Feature activation+0.000
the
Token the
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
of
Token of
Feature activation+0.000
thoughts
Token thoughts
Feature activation+0.000
with
Token with
Feature activation+0.000
an
Token an
Feature activation+0.000
open
Token open
Feature activation+0.000
mind
Token mind
Feature activation+2.355
.
Token.
Feature activation+0.000
No
Token No
Feature activation+0.000
one
Token one
Feature activation+0.000
has
Token has
Feature activation+0.000
carved
Token carved
Feature activation+0.000
since
Token since
Feature activation+0.000
this
Token this
Feature activation+0.000
could
Token could
Feature activation+0.000
open
Token open
Feature activation+0.000
a
Token a
Feature activation+1.726
dangerous
Token dangerous
Feature activation+2.350
power
Token power
Feature activation+0.319
vacuum
Token vacuum
Feature activation+0.000
that
Token that
Feature activation+0.000
ISIS
Token ISIS
Feature activation+0.000
might
Token might
Feature activation+0.000

Top DFA by src position
MAX = 4.341

The
TokenThe
Feature activation+0.009
Top resid features:
provincial
Token provincial
Feature activation-0.012
Top resid features:
government
Token government
Feature activation-0.014
Top resid features:
calculated
Token calculated
Feature activation-0.010
Top resid features:
the
Token the
Feature activation-0.010
Top resid features:
opening
Token opening
Feature activation+4.341
Top resid features:
of
Token of
Feature activation-0.076
Top resid features:
European
Token European
Feature activation+0.000
Top resid features:
markets
Token markets
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Canadian
Token Canadian
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.012
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
management
Token management
Feature activation-0.003
Top resid features:
wants
Token wants
Feature activation+0.022
Top resid features:
to
Token to
Feature activation+0.014
Top resid features:
open
Token open
Feature activation+3.943
Top resid features:
the
Token the
Feature activation+0.088
Top resid features:
store
Token store
Feature activation+0.069
Top resid features:
to
Token to
Feature activation-0.146
Top resid features:
individual
Token individual
Feature activation+0.000
Top resid features:
merchants
Token merchants
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.011
Top resid features:
Islamic
Token Islamic
Feature activation-0.008
Top resid features:
State
Token State
Feature activation+0.000
Top resid features:
announced
Token announced
Feature activation+0.036
Top resid features:
the
Token the
Feature activation+0.036
Top resid features:
opening
Token opening
Feature activation+4.100
Top resid features:
of
Token of
Feature activation-0.039
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
own
Token own
Feature activation+0.000
Top resid features:
bank
Token bank
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.013
Top resid features:
site
Token site
Feature activation-0.001
Top resid features:
could
Token could
Feature activation-0.000
Top resid features:
re
Token re
Feature activation+0.076
Top resid features:
-
Token-
Feature activation-0.003
Top resid features:
open
Tokenopen
Feature activation+4.145
Top resid features:
as
Token as
Feature activation-0.070
Top resid features:
early
Token early
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
January
Token January
Feature activation+0.000
Top resid features:
2012
Token 2012
Feature activation+0.000
Top resid features:
on
Token on
Feature activation-0.070
Top resid features:
this
Token this
Feature activation-0.027
Top resid features:
topic
Token topic
Feature activation-0.006
Top resid features:
with
Token with
Feature activation-0.009
Top resid features:
an
Token an
Feature activation+0.007
Top resid features:
open
Token open
Feature activation+4.159
Top resid features:
mind
Token mind
Feature activation-0.010
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
convince
Token convince
Feature activation+0.000
Top resid features:
anyone
Token anyone
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
reading
Token reading
Feature activation-0.013
Top resid features:
this
Token this
Feature activation-0.026
Top resid features:
document
Token document
Feature activation-0.011
Top resid features:
have
Token have
Feature activation-0.060
Top resid features:
an
Token an
Feature activation-0.037
Top resid features:
open
Token open
Feature activation+4.133
Top resid features:
mind
Token mind
Feature activation-0.090
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
idea
Token idea
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.011
Top resid features:
a
Token a
Feature activation-0.035
Top resid features:
one
Token one
Feature activation+0.012
Top resid features:
-
Token-
Feature activation-0.055
Top resid features:
way
Tokenway
Feature activation-0.106
Top resid features:
opening
Token opening
Feature activation+4.045
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Canadian
Token Canadian
Feature activation+0.000
Top resid features:
auto
Token auto
Feature activation+0.000
Top resid features:
market
Token market
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
better
Token better
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
I
Token I
Feature activation+0.013
Top resid features:
just
Token just
Feature activation-0.076
Top resid features:
opened
Token opened
Feature activation+4.191
Top resid features:
the
Token the
Feature activation+0.143
Top resid features:
sentence
Token sentence
Feature activation-0.058
Top resid features:
that
Token that
Feature activation+0.044
Top resid features:
way
Token way
Feature activation-0.241
Top resid features:
to
Token to
Feature activation-0.055
Top resid features:
,
Token,
Feature activation-0.022
Top resid features:
they
Token they
Feature activation+0.021
Top resid features:
could
Token could
Feature activation+0.038
Top resid features:
have
Token have
Feature activation+0.011
Top resid features:
an
Token an
Feature activation+0.004
Top resid features:
open
Token open
Feature activation+3.639
Top resid features:
mind
Token mind
Feature activation-0.046
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
fun
Token fun
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
your
Token your
Feature activation+0.002
Top resid features:
account
Token account
Feature activation+0.019
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
This
Token This
Feature activation-0.022
Top resid features:
should
Token should
Feature activation-0.037
Top resid features:
open
Token open
Feature activation+3.478
Top resid features:
a
Token a
Feature activation+0.031
Top resid features:
new
Token new
Feature activation+0.000
Top resid features:
window
Token window
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
where
Token where
Feature activation+0.000
Top resid features:
your
Token your
Feature activation+0.001
Top resid features:
account
Token account
Feature activation+0.017
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
This
Token This
Feature activation-0.030
Top resid features:
should
Token should
Feature activation-0.034
Top resid features:
open
Token open
Feature activation+3.334
Top resid features:
a
Token a
Feature activation+0.193
Top resid features:
new
Token new
Feature activation+0.074
Top resid features:
window
Token window
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
where
Token where
Feature activation+0.000
Top resid features:
ease
Token ease
Feature activation+0.001
Top resid features:
.
Token.
Feature activation-0.022
Top resid features:
As
Token As
Feature activation-0.014
Top resid features:
her
Tokenher
Feature activation+0.009
Top resid features:
also
Token also
Feature activation-0.044
Top resid features:
opened
Token opened
Feature activation+3.440
Top resid features:
a
Token a
Feature activation+0.030
Top resid features:
couple
Token couple
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Titan
Token Titan
Feature activation+0.000
Top resid features:
Pad
TokenPad
Feature activation+0.000
Top resid features:
Stud
TokenStud
Feature activation-0.005
Top resid features:
ying
Tokenying
Feature activation+0.020
Top resid features:
these
Token these
Feature activation-0.006
Top resid features:
could
Token could
Feature activation+0.042
Top resid features:
"
Token "
Feature activation+0.108
Top resid features:
open
Tokenopen
Feature activation+3.294
Top resid features:
new
Token new
Feature activation+0.087
Top resid features:
doors
Token doors
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
understanding
Token understanding
Feature activation+0.000
Top resid features:
The
Token The
Feature activation-0.004
Top resid features:
film
Token film
Feature activation+0.022
Top resid features:
is
Token is
Feature activation-0.006
Top resid features:
slated
Token slated
Feature activation-0.014
Top resid features:
to
Token to
Feature activation-0.009
Top resid features:
open
Token open
Feature activation+3.488
Top resid features:
in
Token in
Feature activation-0.081
Top resid features:
Japanese
Token Japanese
Feature activation+0.000
Top resid features:
theaters
Token theaters
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
2017
Token 2017
Feature activation+0.000
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
Con
TokenCon
Feature activation-0.028
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Disney
Token Disney
Feature activation+0.010
Top resid features:
finally
Token finally
Feature activation+0.097
Top resid features:
opened
Token opened
Feature activation+3.138
Top resid features:
Tr
Token Tr
Feature activation+0.132
Top resid features:
on
Tokenon
Feature activation-0.007
Top resid features:
Legacy
Token Legacy
Feature activation+0.011
Top resid features:
in
Token in
Feature activation-0.051
Top resid features:
theaters
Token theaters
Feature activation+0.000
Top resid features:
Obama
Token Obama
Feature activation+0.020
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ļ
TokenĻ
Feature activation-0.011
Top resid features:
s
Tokens
Feature activation-0.016
Top resid features:
historic
Token historic
Feature activation-0.029
Top resid features:
opening
Token opening
Feature activation+3.658
Top resid features:
to
Token to
Feature activation-0.030
Top resid features:
Cuba
Token Cuba
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
wasn
Token wasn
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Be
TokenBe
Feature activation-0.013
Top resid features:
ijing
Tokenijing
Feature activation+0.028
Top resid features:
will
Token will
Feature activation+0.005
Top resid features:
open
Token open
Feature activation+3.329
Top resid features:
its
Token its
Feature activation+0.023
Top resid features:
economy
Token economy
Feature activation-0.020
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
pace
Token pace
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.013
Top resid features:
Islamic
Token Islamic
Feature activation-0.006
Top resid features:
State
Token State
Feature activation+0.142
Top resid features:
announced
Token announced
Feature activation-0.007
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
opening
Token opening
Feature activation+2.835
Top resid features:
of
Token of
Feature activation+0.449
Top resid features:
its
Token its
Feature activation+0.035
Top resid features:
own
Token own
Feature activation+0.007
Top resid features:
bank
Token bank
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
collection
Token collection
Feature activation-0.033
Top resid features:
of
Token of
Feature activation-0.044
Top resid features:
thoughts
Token thoughts
Feature activation-0.008
Top resid features:
with
Token with
Feature activation-0.084
Top resid features:
an
Token an
Feature activation-0.050
Top resid features:
open
Token open
Feature activation+3.389
Top resid features:
mind
Token mind
Feature activation-0.016
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
No
Token No
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
outright
Token outright
Feature activation-0.009
Top resid features:
,
Token,
Feature activation-0.026
Top resid features:
since
Token since
Feature activation-0.024
Top resid features:
this
Token this
Feature activation-0.031
Top resid features:
could
Token could
Feature activation+0.039
Top resid features:
open
Token open
Feature activation+3.111
Top resid features:
a
Token a
Feature activation+0.242
Top resid features:
dangerous
Token dangerous
Feature activation-0.002
Top resid features:
power
Token power
Feature activation+0.000
Top resid features:
vacuum
Token vacuum
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.04

Head 3: 0.04

Head 4: 0.07

Head 5: 0.04

Head 6: 0.05

Head 7: 0.55

Head 8: 0.03

Head 9: 0.03

Head 10: 0.05

Head 11: 0.05

Positive logits

IPM1.58

Pandora1.57

Dialog1.54

tunnel1.46

reversible1.42

galleries1.41

rift1.40

municip1.40

Terminal1.36

fault1.35

doors1.35

blush1.34

Movie1.31

Parkway1.30

creen1.28

Options1.27

libel1.26

crater1.26

plex1.26

theaters1.26

Negative logits

drivers-1.79

Zup-1.65

gey-1.60

覚醒-1.56

bred-1.44

Decay-1.44

ularity-1.39

horse-1.39

anny-1.34

leaders-1.32

hetamine-1.32

leader-1.32

enny-1.31

sie-1.31

龍喚士-1.30

incre-1.29

addle-1.29

ocobo-1.28

average-1.27

erity-1.26

INTERVAL 3.084 - 3.426
CONTAINS 0.001%

wants
Token wants
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.000
the
Token the
Feature activation+2.302
store
Token store
Feature activation+0.410
to
Token to
Feature activation+3.242
individual
Token individual
Feature activation+1.313
merchants
Token merchants
Feature activation+0.000
who
Token who
Feature activation+0.000
could
Token could
Feature activation+0.000
sell
Token sell
Feature activation+0.000
provincial
Token provincial
Feature activation+0.000
government
Token government
Feature activation+0.000
calculated
Token calculated
Feature activation+0.000
the
Token the
Feature activation+0.000
opening
Token opening
Feature activation+0.000
of
Token of
Feature activation+3.426
European
Token European
Feature activation+0.479
markets
Token markets
Feature activation+0.000
to
Token to
Feature activation+1.736
Canadian
Token Canadian
Feature activation+0.111
shrimp
Token shrimp
Feature activation+0.000
site
Token site
Feature activation+0.000
could
Token could
Feature activation+0.000
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
open
Tokenopen
Feature activation+0.321
as
Token as
Feature activation+3.238
early
Token early
Feature activation+0.164
as
Token as
Feature activation+0.000
January
Token January
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
.
Token.
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
State
Token State
Feature activation+0.000
announced
Token announced
Feature activation+0.000
the
Token the
Feature activation+0.000
opening
Token opening
Feature activation+0.000
of
Token of
Feature activation+3.242
its
Token its
Feature activation+1.692
own
Token own
Feature activation+2.594
bank
Token bank
Feature activation+0.000
.
Token.
Feature activation+0.000
Called
Token Called
Feature activation+0.000
this
Token this
Feature activation+0.000
topic
Token topic
Feature activation+0.000
with
Token with
Feature activation+0.000
an
Token an
Feature activation+0.000
open
Token open
Feature activation+0.000
mind
Token mind
Feature activation+3.094
will
Token will
Feature activation+0.000
convince
Token convince
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
with
Token with
Feature activation+0.000
half
Token half
Feature activation+0.000

INTERVAL 2.741 - 3.084
CONTAINS 0.001%

opened
Token opened
Feature activation+0.000
the
Token the
Feature activation+1.983
sentence
Token sentence
Feature activation+0.000
that
Token that
Feature activation+0.000
way
Token way
Feature activation+0.344
to
Token to
Feature activation+2.977
sound
Token sound
Feature activation+0.000
good
Token good
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ying
Tokenying
Feature activation+0.000
these
Token these
Feature activation+0.000
could
Token could
Feature activation+0.000
"
Token "
Feature activation+0.000
open
Tokenopen
Feature activation+0.000
new
Token new
Feature activation+2.771
doors
Token doors
Feature activation+0.000
"
Token"
Feature activation+0.000
to
Token to
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
her
Tokenher
Feature activation+0.000
also
Token also
Feature activation+0.000
opened
Token opened
Feature activation+0.089
a
Token a
Feature activation+2.773
couple
Token couple
Feature activation+1.456
of
Token of
Feature activation+2.017
Titan
Token Titan
Feature activation+0.000
Pad
TokenPad
Feature activation+0.000
pages
Token pages
Feature activation+0.283
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
should
Token should
Feature activation+0.000
open
Token open
Feature activation+0.000
a
Token a
Feature activation+2.801
new
Token new
Feature activation+2.780
window
Token window
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.067
your
Token your
Feature activation+0.016
environmental
Token environmental
Feature activation+0.000
account
Token account
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
should
Token should
Feature activation+0.000
open
Token open
Feature activation+0.000
a
Token a
Feature activation+2.801
new
Token new
Feature activation+2.780
window
Token window
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.067
your
Token your
Feature activation+0.016

INTERVAL 2.399 - 2.741
CONTAINS 0.001%

finally
Token finally
Feature activation+0.000
opened
Token opened
Feature activation+0.171
Tr
Token Tr
Feature activation+0.022
on
Tokenon
Feature activation+0.000
Legacy
Token Legacy
Feature activation+0.076
in
Token in
Feature activation+2.705
theaters
Token theaters
Feature activation+0.000
on
Token on
Feature activation+0.000
December
Token December
Feature activation+0.000
17
Token 17
Feature activation+0.000
th
Tokenth
Feature activation+0.000
film
Token film
Feature activation+0.000
is
Token is
Feature activation+0.000
slated
Token slated
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.000
in
Token in
Feature activation+2.719
Japanese
Token Japanese
Feature activation+0.000
theaters
Token theaters
Feature activation+0.000
in
Token in
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
.
Token.
Feature activation+0.000
Be
TokenBe
Feature activation+0.000
ijing
Tokenijing
Feature activation+0.000
will
Token will
Feature activation+0.000
open
Token open
Feature activation+0.181
its
Token its
Feature activation+2.277
economy
Token economy
Feature activation+2.653
at
Token at
Feature activation+0.521
the
Token the
Feature activation+0.246
pace
Token pace
Feature activation+0.000
it
Token it
Feature activation+0.000
deems
Token deems
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
historic
Token historic
Feature activation+0.000
opening
Token opening
Feature activation+0.000
to
Token to
Feature activation+2.667
Cuba
Token Cuba
Feature activation+0.587
but
Token but
Feature activation+0.000
it
Token it
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
announced
Token announced
Feature activation+0.000
the
Token the
Feature activation+0.000
opening
Token opening
Feature activation+0.000
of
Token of
Feature activation+3.242
its
Token its
Feature activation+1.692
own
Token own
Feature activation+2.594
bank
Token bank
Feature activation+0.000
.
Token.
Feature activation+0.000
Called
Token Called
Feature activation+0.000
the
Token the
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000

INTERVAL 2.056 - 2.399
CONTAINS 0.002%

bought
Token bought
Feature activation+0.000
the
Token the
Feature activation+0.000
building
Token building
Feature activation+0.000
after
Token after
Feature activation+0.000
opening
Token opening
Feature activation+0.000
a
Token a
Feature activation+2.324
salon
Token salon
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
street
Token street
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Be
TokenBe
Feature activation+0.000
ijing
Tokenijing
Feature activation+0.000
will
Token will
Feature activation+0.000
open
Token open
Feature activation+0.181
its
Token its
Feature activation+2.277
economy
Token economy
Feature activation+2.653
at
Token at
Feature activation+0.521
the
Token the
Feature activation+0.246
pace
Token pace
Feature activation+0.000
it
Token it
Feature activation+0.000
went
Token went
Feature activation+0.000
off
Token off
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
opened
Token opened
Feature activation+0.000
my
Token my
Feature activation+2.285
eyes
Token eyes
Feature activation+0.221
the
Token the
Feature activation+0.000
lights
Token lights
Feature activation+0.000
are
Token are
Feature activation+0.000
out
Token out
Feature activation+0.000
to
Token to
Feature activation+0.000
appear
Token appear
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
opening
Token opening
Feature activation+0.000
of
Token of
Feature activation+2.165
his
Token his
Feature activation+1.614
new
Token new
Feature activation+1.080
hotel
Token hotel
Feature activation+0.000
in
Token in
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
-
Token-
Feature activation+0.000
way
Tokenway
Feature activation+0.000
race
Token race
Feature activation+0.000
,
Token,
Feature activation+0.000
opened
Token opened
Feature activation+0.000
New
Token New
Feature activation+2.139
York
Token York
Feature activation+0.275
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+1.327
contest
Token contest
Feature activation+0.000

INTERVAL 1.713 - 2.056
CONTAINS 0.002%

better
Token better
Feature activation+0.000
,
Token,
Feature activation+0.000
I
Token I
Feature activation+0.000
just
Token just
Feature activation+0.000
opened
Token opened
Feature activation+0.000
the
Token the
Feature activation+1.983
sentence
Token sentence
Feature activation+0.000
that
Token that
Feature activation+0.000
way
Token way
Feature activation+0.344
to
Token to
Feature activation+2.977
sound
Token sound
Feature activation+0.000
open
Token open
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.946
entire
Token entire
Feature activation+0.362
Act
Token Act
Feature activation+0.000
to
Token to
Feature activation+1.856
revision
Token revision
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
regulation
Token regulation
Feature activation+0.000
-
Token-
Feature activation+0.000
,
Token,
Feature activation+0.000
since
Token since
Feature activation+0.000
this
Token this
Feature activation+0.000
could
Token could
Feature activation+0.000
open
Token open
Feature activation+0.000
a
Token a
Feature activation+1.726
dangerous
Token dangerous
Feature activation+2.350
power
Token power
Feature activation+0.319
vacuum
Token vacuum
Feature activation+0.000
that
Token that
Feature activation+0.000
ISIS
Token ISIS
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.000
opened
Token opened
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.364
similar
Token similar
Feature activation+1.800
tone
Token tone
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
quickly
Token quickly
Feature activation+0.000
ve
Token ve
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.000
the
Token the
Feature activation+0.983
cup
Token cup
Feature activation+0.000
too
Token too
Feature activation+1.765
much
Token much
Feature activation+1.861
for
Token for
Feature activation+0.000
you
Token you
Feature activation+0.000
(
Token (
Feature activation+0.000
You
TokenYou
Feature activation+0.000
can
Token can
Feature activation+0.000

INTERVAL 1.371 - 1.713
CONTAINS 0.003%

Is
Token Is
Feature activation+0.000
a
Token a
Feature activation+0.000
hiring
Token hiring
Feature activation+0.000
manager
Token manager
Feature activation+0.000
open
Token open
Feature activation+0.000
to
Token to
Feature activation+1.662
small
Token small
Feature activation+0.000
talk
Token talk
Feature activation+0.000
and
Token and
Feature activation+0.000
if
Token if
Feature activation+0.000
that
Token that
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
,
Token,
Feature activation+0.000
opening
Token opening
Feature activation+0.000
it
Token it
Feature activation+0.822
in
Token in
Feature activation+3.126
the
Token the
Feature activation+1.599
concentration
Token concentration
Feature activation+0.000
camp
Token camp
Feature activation+0.000
,
Token,
Feature activation+0.000
having
Token having
Feature activation+0.000
Wolverine
Token Wolverine
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
things
Token things
Feature activation+0.000
really
Token really
Feature activation+0.000
open
Token open
Feature activation+0.000
up
Token up
Feature activation+1.694
and
Token and
Feature activation+0.303
just
Token just
Feature activation+0.212
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
blending
Token blending
Feature activation+0.000
societal
Token societal
Feature activation+0.000
order
Token order
Feature activation+0.000
opened
Token opened
Feature activation+0.000
up
Token up
Feature activation+0.114
narratives
Token narratives
Feature activation+0.000
to
Token to
Feature activation+1.590
include
Token include
Feature activation+0.000
other
Token other
Feature activation+0.000
perceived
Token perceived
Feature activation+0.000
less
Token less
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
about
Token about
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.000
Public
Token Public
Feature activation+0.724
Option
Token Option
Feature activation+0.000
,
Token,
Feature activation+1.576
a
Token a
Feature activation+0.780
no
Token no
Feature activation+0.000
-
Token-
Feature activation+0.000
t
Tokent
Feature activation+0.000
ipping
Tokenipping
Feature activation+0.000

INTERVAL 1.028 - 1.371
CONTAINS 0.003%

,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
their
Token their
Feature activation+0.000
openness
Token openness
Feature activation+0.000
to
Token to
Feature activation+0.839
the
Token the
Feature activation+1.218
great
Token great
Feature activation+0.066
ocean
Token ocean
Feature activation+0.000
and
Token and
Feature activation+0.000
wealth
Token wealth
Feature activation+0.000
of
Token of
Feature activation+0.000
you
Token you
Feature activation+0.000
buy
Token buy
Feature activation+0.000
it
Token it
Feature activation+0.000
and
Token and
Feature activation+0.000
open
Token open
Feature activation+0.000
it
Token it
Feature activation+1.353
.
Token.
Feature activation+0.000
Nintendo
Token Nintendo
Feature activation+0.000
is
Token is
Feature activation+0.000
getting
Token getting
Feature activation+0.000
a
Token a
Feature activation+0.000
coach
Token coach
Feature activation+0.000
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
open
Token open
Feature activation+0.000
about
Token about
Feature activation+1.059
his
Token his
Feature activation+0.000
interest
Token interest
Feature activation+0.000
in
Token in
Feature activation+0.000
moving
Token moving
Feature activation+0.000
to
Token to
Feature activation+0.000
so
Token so
Feature activation+0.000
would
Token would
Feature activation+0.000
open
Token open
Feature activation+0.000
its
Token its
Feature activation+1.587
borders
Token borders
Feature activation+0.111
to
Token to
Feature activation+1.273
terrorists
Token terrorists
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Israel
TokenIsrael
Feature activation+0.000
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
opened
Token opened
Feature activation+0.000
a
Token a
Feature activation+1.041
small
Token small
Feature activation+0.484
plastic
Token plastic
Feature activation+0.113
bag
Token bag
Feature activation+0.000
of
Token of
Feature activation+0.000
what
Token what
Feature activation+0.000

INTERVAL 0.685 - 1.028
CONTAINS 0.004%

27
Token 27
Feature activation+0.000
that
Token that
Feature activation+0.000
opened
Token opened
Feature activation+0.005
a
Token a
Feature activation+2.210
pass
Token pass
Feature activation+0.209
to
Token to
Feature activation+0.878
the
Token the
Feature activation+0.288
P
Token P
Feature activation+0.000
us
Tokenus
Feature activation+0.000
an
Tokenan
Feature activation+0.000
area
Token area
Feature activation+0.000
AL
Token AL
Feature activation+0.000
Central
Token Central
Feature activation+0.000
is
Token is
Feature activation+0.000
wide
Token wide
Feature activation+0.000
open
Token open
Feature activation+0.000
.
Token.
Feature activation+0.898
The
Token The
Feature activation+0.169
Indians
Token Indians
Feature activation+0.000
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
ran
Token ran
Feature activation+0.000
sweet
Token sweet
Feature activation+0.000
smell
Token smell
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
newly
Token newly
Feature activation+0.000
opened
Token opened
Feature activation+0.726
car
Token car
Feature activation+0.000
air
Token air
Feature activation+0.000
fres
Token fres
Feature activation+0.000
hen
Tokenhen
Feature activation+0.000
er
Tokener
Feature activation+0.000
Denver
Token Denver
Feature activation+0.000
even
Token even
Feature activation+0.000
left
Token left
Feature activation+0.000
an
Token an
Feature activation+0.000
opening
Token opening
Feature activation+0.000
on
Token on
Feature activation+0.780
its
Token its
Feature activation+0.577
53
Token 53
Feature activation+0.000
-
Token-
Feature activation+0.000
man
Tokenman
Feature activation+0.000
roster
Token roster
Feature activation+0.000
the
Token the
Feature activation+0.000
budget
Token budget
Feature activation+0.000
,
Token,
Feature activation+0.000
leaving
Token leaving
Feature activation+0.000
open
Token open
Feature activation+0.000
the
Token the
Feature activation+0.824
question
Token question
Feature activation+0.000
of
Token of
Feature activation+0.000
what
Token what
Feature activation+0.000
will
Token will
Feature activation+0.000
happen
Token happen
Feature activation+0.000

INTERVAL 0.343 - 0.685
CONTAINS 0.010%

.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
pub
Token pub
Feature activation+0.000
was
Token was
Feature activation+0.000
opened
Token opened
Feature activation+0.000
at
Token at
Feature activation+0.361
the
Token the
Feature activation+0.134
current
Token current
Feature activation+0.000
Bow
Token Bow
Feature activation+0.000
e
Tokene
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
company
Token company
Feature activation+0.000
opened
Token opened
Feature activation+0.409
officially
Token officially
Feature activation+0.263
this
Token this
Feature activation+0.632
week
Token week
Feature activation+0.288
,
Token,
Feature activation+0.000
with
Token with
Feature activation+0.000
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
now
Token now
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
shut
Token shut
Feature activation+0.000
the
Token the
Feature activation+0.209
game
Token game
Feature activation+0.471
off
Token off
Feature activation+0.048
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
fool
Token fool
Feature activation+0.000
hard
Tokenhard
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
opening
Token opening
Feature activation+0.000
up
Token up
Feature activation+0.000
the
Token the
Feature activation+0.607
door
Token door
Feature activation+0.000
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.000
castle
Token castle
Feature activation+0.000
grounds
Token grounds
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
open
Token open
Feature activation+0.000
the
Token the
Feature activation+0.408
door
Token door
Feature activation+0.000
for
Token for
Feature activation+0.000
someone
Token someone
Feature activation+0.000
who
Token who
Feature activation+0.000
would
Token would
Feature activation+0.000

INTERVAL 0.000 - 0.343
CONTAINS 99.974%

911
Token911
Feature activation+0.000
.
Token.
Feature activation+0.000
24
Token24
Feature activation+0.000
billion
Token billion
Feature activation+0.000
)
Token)
Feature activation+0.000
-
Token -
Feature activation+0.000
would
Token would
Feature activation+0.000
take
Token take
Feature activation+0.000
place
Token place
Feature activation+0.000
immediately
Token immediately
Feature activation+0.000
and
Token and
Feature activation+0.000
tweet
Token tweet
Feature activation+0.000
about
Token about
Feature activation+0.000
this
Token this
Feature activation+0.000
post
Token post
Feature activation+0.000
or
Token or
Feature activation+0.000
mention
Token mention
Feature activation+0.000
in
Token in
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
and
Token and
Feature activation+0.000
essentially
Token essentially
Feature activation+0.000
follow
Token follow
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
drive
Token drive
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
direction
Token direction
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
be
Token be
Feature activation+0.000
L
Token L
Feature activation+0.000
ESS
TokenESS
Feature activation+0.000
local
Token local
Feature activation+0.000
than
Token than
Feature activation+0.000
the
Token the
Feature activation+0.000
tastes
Token tastes
Feature activation+0.000
of
Token of
Feature activation+0.000
Ireland
Token Ireland
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
an
Tokenan
Feature activation+0.000
rebel
Token rebel
Feature activation+0.000
factions
Token factions
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
First
Token First
Feature activation+0.000
Jewish
Token Jewish
Feature activation+0.000
-
Token-
Feature activation+0.000
Roman
TokenRoman
Feature activation+0.000
War
Token War
Feature activation+0.000
in
Token in
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 4 in H5.7: (feature 8139)

TOP ACTIVATIONS
MAX = 5.620

DM
Token DM
Feature activation+0.000
's
Token's
Feature activation+0.000
permission
Token permission
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.355
Ċ
TokenĊ
Feature activation+5.620
Ability
TokenAbility
Feature activation+0.000
Score
Token Score
Feature activation+0.000
Increase
Token Increase
Feature activation+0.000
.
Token.
Feature activation+0.000
Your
Token Your
Feature activation+0.000
23
Token 23
Feature activation+0.000
,
Token,
Feature activation+0.000
1969
Token 1969
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.165
Ċ
TokenĊ
Feature activation+5.086
For
TokenFor
Feature activation+0.000
one
Token one
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
album
Token album
Feature activation+0.000
EU
Token EU
Feature activation+0.000
design
Token design
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.602
Ċ
TokenĊ
Feature activation+4.916
The
TokenThe
Feature activation+0.000
prefix
Token prefix
Feature activation+0.000
micro
Token micro
Feature activation+0.000
-
Token-
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token ,
Feature activation+0.000
b
Token b
Feature activation+0.000
h
Tokenh
Feature activation+0.000
ubi
Tokenubi
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.031
Ċ
TokenĊ
Feature activation+4.801
,
Token,
Feature activation+0.000
Bur
Token Bur
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ese
Tokenese
Feature activation+0.000
:
Token:
Feature activation+0.000
.
Token .
Feature activation+0.000
[
Token [
Feature activation+0.000
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.012
Ċ
TokenĊ
Feature activation+4.771
or
Tokenor
Feature activation+0.000
,
Token ,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
7
Token 7
Feature activation+0.000
whiskey
Token whiskey
Feature activation+0.000
,
Token ,
Feature activation+0.000
2
Token 2
Feature activation+0.000
beers
Token beers
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.737
Ċ
TokenĊ
Feature activation+4.676
11
Token11
Feature activation+0.000
:
Token:
Feature activation+0.000
22
Token22
Feature activation+0.000
AM
Token AM
Feature activation+0.000
-
Token -
Feature activation+0.056
,
Token,
Feature activation+0.000
among
Token among
Feature activation+0.000
others
Token others
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.438
Ċ
TokenĊ
Feature activation+4.598
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Climate
TokenClimate
Feature activation+0.000
change
Token change
Feature activation+0.000
poses
Token poses
Feature activation+0.000
over
Token over
Feature activation+0.000
5
Token 5
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.999
Ċ
TokenĊ
Feature activation+4.490
I
TokenI
Feature activation+0.000
spent
Token spent
Feature activation+0.000
27
Token 27
Feature activation+0.000
months
Token months
Feature activation+0.000
in
Token in
Feature activation+0.000
igan
Tokenigan
Feature activation+0.000
,
Token,
Feature activation+0.000
below
Token below
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.062
Ċ
TokenĊ
Feature activation+4.406
Even
TokenEven
Feature activation+0.000
without
Token without
Feature activation+0.000
step
Token step
Feature activation+0.000
-
Token-
Feature activation+0.000
by
Tokenby
Feature activation+0.000
views
Token views
Feature activation+0.000
.
Token.
Feature activation+0.000
py
Tokenpy
Feature activation+0.000
.
Token .
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.309
Ċ
TokenĊ
Feature activation+4.392
The
TokenThe
Feature activation+0.000
app
Token app
Feature activation+0.000
is
Token is
Feature activation+0.000
created
Token created
Feature activation+0.000
but
Token but
Feature activation+0.000
url
Tokenurl
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
py
Tokenpy
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.904
Ċ
TokenĊ
Feature activation+4.343
url
Tokenurl
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
py
Tokenpy
Feature activation+0.000
from
Token from
Feature activation+0.000
another
Tokenanother
Feature activation+0.000
app
Token app
Feature activation+0.000
location
Token location
Feature activation+0.000
"
Token"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.725
Ċ
TokenĊ
Feature activation+4.269
Notes
TokenNotes
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
com
Tokencom
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ian
TokenIan
Feature activation+0.000
Clarke
Token Clarke
Feature activation+0.000
,
Token ,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.013
Ċ
TokenĊ
Feature activation+4.260
July
TokenJuly
Feature activation+0.000
8
Token 8
Feature activation+0.000
,
Token,
Feature activation+0.866
2015
Token 2015
Feature activation+3.003
Email
Token Email
Feature activation+0.000
May
Token May
Feature activation+0.000
23
Token 23
Feature activation+0.000
,
Token,
Feature activation+0.000
1969
Token 1969
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.165
Ċ
TokenĊ
Feature activation+5.086
For
TokenFor
Feature activation+0.000
one
Token one
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
ak
Tokenak
Feature activation+0.000
,
Token ,
Feature activation+0.000
d
Token d
Feature activation+0.000
uku
Tokenuku
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.022
,
Token,
Feature activation+0.000
C
Token C
Feature activation+0.000
eb
Tokeneb
Feature activation+0.000
u
Tokenu
Feature activation+0.000
ano
Tokenano
Feature activation+0.000
an
Tokenan
Feature activation+0.000
.
Token .
Feature activation+0.000
[
Token [
Feature activation+0.000
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.012
Ċ
TokenĊ
Feature activation+4.771
or
Tokenor
Feature activation+0.000
,
Token ,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
of
Token of
Feature activation+0.000
cosmic
Token cosmic
Feature activation+0.000
rays
Token rays
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.087
Ċ
TokenĊ
Feature activation+3.998
Now
TokenNow
Feature activation+0.000
all
Token all
Feature activation+0.000
these
Token these
Feature activation+0.000
scenarios
Token scenarios
Feature activation+0.000
are
Token are
Feature activation+0.000
,
Token ,
Feature activation+0.000
l
Token l
Feature activation+0.000
ans
Tokenans
Feature activation+0.000
ones
Tokenones
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.627
,
Token,
Feature activation+0.000
English
Token English
Feature activation+0.000
:
Token:
Feature activation+0.000
l
Token l
Feature activation+0.000
angs
Tokenangs
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.603
Newsletter
TokenNewsletter
Feature activation+0.000
Sign
Token Sign
Feature activation+0.000
Up
Token Up
Feature activation+0.000
Continue
Token Continue
Feature activation+0.000
reading
Token reading
Feature activation+0.000
or
Token or
Feature activation+0.000
EU
Token EU
Feature activation+0.000
design
Token design
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.602
Ċ
TokenĊ
Feature activation+4.916
The
TokenThe
Feature activation+0.000
prefix
Token prefix
Feature activation+0.000
micro
Token micro
Feature activation+0.000
-
Token-
Feature activation+0.000

Top DFA by src position
MAX = 5.639

blood
Token blood
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
flooded
Token flooded
Feature activation+0.003
Top resid features:
with
Token with
Feature activation+0.005
Top resid features:
darkness
Token darkness
Feature activation+0.004
Top resid features:
,
Token ,
Feature activation+5.551
Top resid features:
you
Tokenyou
Feature activation+0.240
Top resid features:
may
Token may
Feature activation+0.045
Top resid features:
use
Token use
Feature activation+0.027
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
God
Token God
Feature activation+0.000
Top resid features:
autobiography
Token autobiography
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
Who
Token Who
Feature activation+0.010
Top resid features:
I
Token I
Feature activation-0.002
Top resid features:
Am
Token Am
Feature activation+0.001
Top resid features:
,
Token ,
Feature activation+2.843
Top resid features:
Pete
Token Pete
Feature activation+0.008
Top resid features:
discussed
Token discussed
Feature activation+0.045
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
perfect
Token perfect
Feature activation-0.004
Top resid features:
storm
Token storm
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
X
Token X
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
K
Token K
Feature activation+0.000
Top resid features:
u
Token u
Feature activation+0.002
Top resid features:
,
Token ,
Feature activation+5.019
Top resid features:
K
Token K
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
or
Token or
Feature activation+0.003
Top resid features:
K
Token K
Feature activation-0.000
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
eng
Tokeneng
Feature activation+0.008
Top resid features:
ali
Tokenali
Feature activation+0.011
Top resid features:
:
Token:
Feature activation+0.037
Top resid features:
lot
Token lot
Feature activation+0.007
Top resid features:
ka
Tokenka
Feature activation-0.000
Top resid features:
,
Token ,
Feature activation+5.639
Top resid features:
b
Token b
Feature activation+0.005
Top resid features:
h
Tokenh
Feature activation+0.001
Top resid features:
ubi
Tokenubi
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.148
Top resid features:
Ċ
TokenĊ
Feature activation-0.026
Top resid features:
Ten
Token Ten
Feature activation+0.002
Top resid features:
'
Token'
Feature activation-0.000
Top resid features:
y
Tokeny
Feature activation+0.000
Top resid features:
Åį
TokenÅį
Feature activation+0.000
Top resid features:
1
Token 1
Feature activation+0.010
Top resid features:
,
Token ,
Feature activation+4.683
Top resid features:
in
Token in
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
7
Token 7
Feature activation+0.001
Top resid features:
th
Tokenth
Feature activation+0.002
Top resid features:
month
Token month
Feature activation+0.006
Top resid features:
:
Token:
Feature activation-0.090
Top resid features:
3
Token 3
Feature activation+0.053
Top resid features:
shots
Token shots
Feature activation+0.044
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
whiskey
Token whiskey
Feature activation-0.015
Top resid features:
,
Token ,
Feature activation+5.155
Top resid features:
2
Token 2
Feature activation+0.012
Top resid features:
beers
Token beers
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.212
Top resid features:
Ċ
TokenĊ
Feature activation+0.148
Top resid features:
11
Token11
Feature activation+0.000
Top resid features:
+
Token +
Feature activation+0.023
Top resid features:
0
Token0
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
07
Token07
Feature activation+0.002
Top resid features:
%
Token%
Feature activation+0.001
Top resid features:
,
Token ,
Feature activation+3.077
Top resid features:
Black
Token Black
Feature activation+0.003
Top resid features:
Rock
TokenRock
Feature activation+0.001
Top resid features:
Inc
Token Inc
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
BL
Token BL
Feature activation+0.007
Top resid features:
economic
Token economic
Feature activation+0.006
Top resid features:
development
Token development
Feature activation+0.002
Top resid features:
advisor
Token advisor
Feature activation+0.018
Top resid features:
in
Token in
Feature activation+0.027
Top resid features:
Vietnam
Token Vietnam
Feature activation+0.008
Top resid features:
,
Token ,
Feature activation+4.860
Top resid features:
and
Token and
Feature activation+0.029
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
captured
Token captured
Feature activation+0.009
Top resid features:
by
Token by
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
print
Token print
Feature activation+0.002
Top resid features:
able
Tokenable
Feature activation+0.001
Top resid features:
PDF
Token PDF
Feature activation+0.010
Top resid features:
s
Tokens
Feature activation+0.003
Top resid features:
,
Token ,
Feature activation+4.612
Top resid features:
such
Token such
Feature activation+0.006
Top resid features:
as
Token as
Feature activation+0.004
Top resid features:
this
Token this
Feature activation+0.010
Top resid features:
handsome
Token handsome
Feature activation+0.015
Top resid features:
gent
Token gent
Feature activation+0.005
Top resid features:
can
Token can
Feature activation+0.033
Top resid features:
things
Token things
Feature activation+0.021
Top resid features:
like
Token like
Feature activation-0.012
Top resid features:
migr
Token migr
Feature activation-0.016
Top resid features:
ations
Tokenations
Feature activation-0.001
Top resid features:
,
Token ,
Feature activation+3.173
Top resid features:
admin
Token admin
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
py
Tokenpy
Feature activation+0.011
Top resid features:
,
Token ,
Feature activation+1.156
Top resid features:
models
Token models
Feature activation+0.008
Top resid features:
main
Token main
Feature activation-0.052
Top resid features:
ur
Token ur
Feature activation+0.006
Top resid features:
ls
Tokenls
Feature activation+0.004
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
py
Tokenpy
Feature activation+0.024
Top resid features:
,
Token ,
Feature activation+4.663
Top resid features:
in
Token in
Feature activation+0.009
Top resid features:
my
Token my
Feature activation-0.001
Top resid features:
case
Token case
Feature activation+0.002
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
oh
Token oh
Feature activation-0.003
Top resid features:
,-
Token,-
Feature activation+0.010
Top resid features:
"
Token "
Feature activation+0.016
Top resid features:
app
Tokenapp
Feature activation+0.003
Top resid features:
location
Token location
Feature activation+0.001
Top resid features:
"
Token"
Feature activation+0.009
Top resid features:
,
Token ,
Feature activation+4.664
Top resid features:
-
Token-
Feature activation+0.030
Top resid features:
"
Token "
Feature activation+0.014
Top resid features:
another
Tokenanother
Feature activation-0.002
Top resid features:
app
Token app
Feature activation+0.003
Top resid features:
location
Token location
Feature activation+0.001
Top resid features:
by
Token by
Feature activation-0.033
Top resid features:
Ċ
TokenĊ
Feature activation-0.060
Top resid features:
Ċ
TokenĊ
Feature activation-0.085
Top resid features:
Ian
TokenIan
Feature activation+0.121
Top resid features:
Clarke
Token Clarke
Feature activation+0.027
Top resid features:
,
Token ,
Feature activation+5.568
Top resid features:
Ċ
TokenĊ
Feature activation+0.153
Top resid features:
Ċ
TokenĊ
Feature activation+0.057
Top resid features:
July
TokenJuly
Feature activation+0.000
Top resid features:
8
Token 8
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
autobiography
Token autobiography
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
Who
Token Who
Feature activation+0.003
Top resid features:
I
Token I
Feature activation-0.002
Top resid features:
Am
Token Am
Feature activation+0.001
Top resid features:
,
Token ,
Feature activation+3.190
Top resid features:
Pete
Token Pete
Feature activation+0.008
Top resid features:
discussed
Token discussed
Feature activation-0.049
Top resid features:
the
Token the
Feature activation+0.018
Top resid features:
perfect
Token perfect
Feature activation-0.003
Top resid features:
storm
Token storm
Feature activation-0.001
Top resid features:
ese
Tokenese
Feature activation+0.006
Top resid features:
:
Token:
Feature activation+0.126
Top resid features:
l
Token l
Feature activation+0.024
Top resid features:
angs
Tokenangs
Feature activation+0.005
Top resid features:
ak
Tokenak
Feature activation+0.000
Top resid features:
,
Token ,
Feature activation+4.234
Top resid features:
d
Token d
Feature activation+0.020
Top resid features:
uku
Tokenuku
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.214
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ten
Token Ten
Feature activation+0.002
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
y
Tokeny
Feature activation+0.000
Top resid features:
Åį
TokenÅį
Feature activation+0.000
Top resid features:
1
Token 1
Feature activation+0.011
Top resid features:
,
Token ,
Feature activation+3.641
Top resid features:
in
Token in
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
7
Token 7
Feature activation+0.000
Top resid features:
th
Tokenth
Feature activation+0.001
Top resid features:
month
Token month
Feature activation+0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.916
Top resid features:
chain
Tokenchain
Feature activation+0.072
Top resid features:
,
Token ,
Feature activation+4.354
Top resid features:
and
Token and
Feature activation+0.018
Top resid features:
you
Token you
Feature activation+0.037
Top resid features:
deliver
Token deliver
Feature activation-0.005
Top resid features:
consistently
Token consistently
Feature activation+0.004
Top resid features:
buggy
Token buggy
Feature activation+0.002
Top resid features:
u
Tokenu
Feature activation+0.000
Top resid features:
ano
Tokenano
Feature activation+0.004
Top resid features:
:
Token:
Feature activation+0.088
Top resid features:
bu
Token bu
Feature activation+0.005
Top resid features:
ahan
Tokenahan
Feature activation+0.002
Top resid features:
,
Token ,
Feature activation+3.479
Top resid features:
l
Token l
Feature activation+0.013
Top resid features:
ans
Tokenans
Feature activation+0.005
Top resid features:
ones
Tokenones
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.195
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
âĢ
TokenâĢ
Feature activation+0.016
Top resid features:
Ŀ
TokenĿ
Feature activation+0.006
Top resid features:
Paul
Token Paul
Feature activation+0.045
Top resid features:
Vol
Token Vol
Feature activation+0.008
Top resid features:
cker
Tokencker
Feature activation-0.000
Top resid features:
,
Token ,
Feature activation+3.316
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
former
Token former
Feature activation+0.008
Top resid features:
chairman
Token chairman
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
X
Token X
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
K
Token K
Feature activation-0.000
Top resid features:
u
Token u
Feature activation+0.002
Top resid features:
,
Token ,
Feature activation+3.798
Top resid features:
K
Token K
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
or
Token or
Feature activation+0.004
Top resid features:
K
Token K
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.013
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.02

Head 2: 0.04

Head 3: 0.05

Head 4: 0.04

Head 5: 0.04

Head 6: 0.04

Head 7: 0.54

Head 8: 0.03

Head 9: 0.08

Head 10: 0.05

Head 11: 0.05

Positive logits

iture1.99

itures1.57

eatures1.55

features1.48

grate1.44

memorial1.44

iency1.41

nces1.41

FILE1.40

minster1.40

agus1.39

dot1.38

Features1.37

Rew1.36

arf1.33

folder1.33

wealth1.32

deceased1.32

verb1.32

alty1.31

Negative logits

EngineDebug-1.51

EStreamFrame-1.38

camel-1.38

-1.37

kas-1.37

-1.36

ioxide-1.36

anol-1.34

acus-1.33

asus-1.33

Reviewer-1.32

ibaba-1.31

eele-1.31

Xeon-1.31

brisk-1.28

vigorous-1.25

Tat-1.25

Camel-1.25

Flavoring-1.25

apes-1.24

INTERVAL 5.058 - 5.620
CONTAINS 0.000%

DM
Token DM
Feature activation+0.000
's
Token's
Feature activation+0.000
permission
Token permission
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.355
Ċ
TokenĊ
Feature activation+5.620
Ability
TokenAbility
Feature activation+0.000
Score
Token Score
Feature activation+0.000
Increase
Token Increase
Feature activation+0.000
.
Token.
Feature activation+0.000
Your
Token Your
Feature activation+0.000
23
Token 23
Feature activation+0.000
,
Token,
Feature activation+0.000
1969
Token 1969
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.165
Ċ
TokenĊ
Feature activation+5.086
For
TokenFor
Feature activation+0.000
one
Token one
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
album
Token album
Feature activation+0.000

INTERVAL 4.496 - 5.058
CONTAINS 0.001%

.
Token .
Feature activation+0.000
[
Token [
Feature activation+0.000
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.012
Ċ
TokenĊ
Feature activation+4.771
or
Tokenor
Feature activation+0.000
,
Token ,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
7
Token 7
Feature activation+0.000
,
Token ,
Feature activation+0.000
b
Token b
Feature activation+0.000
h
Tokenh
Feature activation+0.000
ubi
Tokenubi
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.031
Ċ
TokenĊ
Feature activation+4.801
,
Token,
Feature activation+0.000
Bur
Token Bur
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ese
Tokenese
Feature activation+0.000
:
Token:
Feature activation+0.000
,
Token,
Feature activation+0.000
among
Token among
Feature activation+0.000
others
Token others
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.438
Ċ
TokenĊ
Feature activation+4.598
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Climate
TokenClimate
Feature activation+0.000
change
Token change
Feature activation+0.000
poses
Token poses
Feature activation+0.000
EU
Token EU
Feature activation+0.000
design
Token design
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.602
Ċ
TokenĊ
Feature activation+4.916
The
TokenThe
Feature activation+0.000
prefix
Token prefix
Feature activation+0.000
micro
Token micro
Feature activation+0.000
-
Token-
Feature activation+0.000
in
Token in
Feature activation+0.000
whiskey
Token whiskey
Feature activation+0.000
,
Token ,
Feature activation+0.000
2
Token 2
Feature activation+0.000
beers
Token beers
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.737
Ċ
TokenĊ
Feature activation+4.676
11
Token11
Feature activation+0.000
:
Token:
Feature activation+0.000
22
Token22
Feature activation+0.000
AM
Token AM
Feature activation+0.000
-
Token -
Feature activation+0.056

INTERVAL 3.934 - 4.496
CONTAINS 0.001%

an
Tokenan
Feature activation+0.000
.
Token .
Feature activation+0.000
[
Token [
Feature activation+0.000
6
Token6
Feature activation+0.000
]
Token]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.012
Ċ
TokenĊ
Feature activation+4.771
or
Tokenor
Feature activation+0.000
,
Token ,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
url
Tokenurl
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
py
Tokenpy
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.904
Ċ
TokenĊ
Feature activation+4.343
url
Tokenurl
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
py
Tokenpy
Feature activation+0.000
from
Token from
Feature activation+0.000
another
Tokenanother
Feature activation+0.000
app
Token app
Feature activation+0.000
location
Token location
Feature activation+0.000
"
Token"
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.725
Ċ
TokenĊ
Feature activation+4.269
Notes
TokenNotes
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
com
Tokencom
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ian
TokenIan
Feature activation+0.000
Clarke
Token Clarke
Feature activation+0.000
,
Token ,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.013
Ċ
TokenĊ
Feature activation+4.260
July
TokenJuly
Feature activation+0.000
8
Token 8
Feature activation+0.000
,
Token,
Feature activation+0.866
2015
Token 2015
Feature activation+3.003
Email
Token Email
Feature activation+0.000
of
Token of
Feature activation+0.000
cosmic
Token cosmic
Feature activation+0.000
rays
Token rays
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.087
Ċ
TokenĊ
Feature activation+3.998
Now
TokenNow
Feature activation+0.000
all
Token all
Feature activation+0.000
these
Token these
Feature activation+0.000
scenarios
Token scenarios
Feature activation+0.000
are
Token are
Feature activation+0.000

INTERVAL 3.372 - 3.934
CONTAINS 0.001%

s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.603
Newsletter
TokenNewsletter
Feature activation+0.000
Sign
Token Sign
Feature activation+0.000
Up
Token Up
Feature activation+0.000
Continue
Token Continue
Feature activation+0.000
reading
Token reading
Feature activation+0.000
,
Token ,
Feature activation+0.000
l
Token l
Feature activation+0.000
ans
Tokenans
Feature activation+0.000
ones
Tokenones
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.627
,
Token,
Feature activation+0.000
English
Token English
Feature activation+0.000
:
Token:
Feature activation+0.000
l
Token l
Feature activation+0.000
angs
Tokenangs
Feature activation+0.000
rice
Tokenrice
Feature activation+0.000
.
Token.
Feature activation+0.000
edu
Tokenedu
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.436
HOU
TokenHOU
Feature activation+0.000
STON
TokenSTON
Feature activation+0.000
-
Token-
Feature activation+0.000
R
TokenR
Feature activation+0.000
ice
Tokenice
Feature activation+0.000
or
Token or
Feature activation+0.000
EU
Token EU
Feature activation+0.000
design
Token design
Feature activation+0.000
ations
Tokenations
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.602
Ċ
TokenĊ
Feature activation+4.916
The
TokenThe
Feature activation+0.000
prefix
Token prefix
Feature activation+0.000
micro
Token micro
Feature activation+0.000
-
Token-
Feature activation+0.000
little
Token little
Feature activation+0.000
bit
Token bit
Feature activation+0.000
different
Token different
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.845
Ċ
TokenĊ
Feature activation+3.476
UPDATE
TokenUPDATE
Feature activation+0.000
tw
Token tw
Feature activation+0.000
ain
Tokenain
Feature activation+0.000
SET
Token SET
Feature activation+0.000
t
Token t
Feature activation+0.000

INTERVAL 2.810 - 3.372
CONTAINS 0.001%

by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
project
Token project
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.210
Ċ
TokenĊ
Feature activation+3.260
an
Tokenan
Feature activation+0.000
engaged
Token engaged
Feature activation+0.000
community
Token community
Feature activation+0.000
of
Token of
Feature activation+0.000
supporters
Token supporters
Feature activation+0.000
Python
Token Python
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token .
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.943
Ċ
TokenĊ
Feature activation+2.911
And
TokenAnd
Feature activation+0.000
our
Token our
Feature activation+0.000
star
Token star
Feature activation+0.000
c
Token c
Feature activation+0.000
oder
Tokenoder
Feature activation+0.000
an
Token an
Feature activation+0.000
N
Token N
Feature activation+0.000
PE
TokenPE
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.627
Ċ
TokenĊ
Feature activation+3.089
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
easy
Token easy
Feature activation+0.000
to
Token to
Feature activation+0.000
reproduce
Token reproduce
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ian
TokenIan
Feature activation+0.000
Clarke
Token Clarke
Feature activation+0.000
,
Token ,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.013
Ċ
TokenĊ
Feature activation+4.260
July
TokenJuly
Feature activation+0.000
8
Token 8
Feature activation+0.000
,
Token,
Feature activation+0.866
2015
Token 2015
Feature activation+3.003
assaults
Token assaults
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.202
Ċ
TokenĊ
Feature activation+2.819
Indeed
TokenIndeed
Feature activation+0.000
,
Token,
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
review
Token review
Feature activation+0.000

INTERVAL 2.248 - 2.810
CONTAINS 0.001%

aring
Tokenaring
Feature activation+0.000
Cross
Token Cross
Feature activation+0.000
Hospital
Token Hospital
Feature activation+0.000
.
Token .
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.097
Ċ
TokenĊ
Feature activation+2.684
C
TokenC
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
r
Tokenr
Feature activation+0.000
Cow
Token Cow
Feature activation+0.000
an
Tokenan
Feature activation+0.000
level
Tokenlevel
Feature activation+0.000
server
Token server
Feature activation+0.000
project
Token project
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.332
Ċ
TokenĊ
Feature activation+2.374
3
Token3
Feature activation+0.000
)
Token)
Feature activation+0.000
Use
Token Use
Feature activation+0.000
custom
Token custom
Feature activation+0.000
tasks
Token tasks
Feature activation+0.000
the
Token the
Feature activation+0.000
correct
Token correct
Feature activation+0.000
version
Token version
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.344
Ċ
TokenĊ
Feature activation+2.347
The
TokenThe
Feature activation+0.000
remaining
Token remaining
Feature activation+0.000
lines
Token lines
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
to
Token to
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
errors
Token errors
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.354
Ċ
TokenĊ
Feature activation+2.461
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+0.000
security
Token security
Feature activation+0.000
experts
Token experts
Feature activation+0.000
,
Token,
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
Fold
Token Fold
Feature activation+0.000
.
Token .
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.415
Ċ
TokenĊ
Feature activation+2.508
The
TokenThe
Feature activation+0.000
other
Token other
Feature activation+0.000
type
Token type
Feature activation+0.000
class
Token class
Feature activation+0.000
morph
Token morph
Feature activation+0.000

INTERVAL 1.686 - 2.248
CONTAINS 0.002%

will
Token will
Feature activation+0.000
definitely
Token definitely
Feature activation+0.000
'
Token '
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.898
Ċ
TokenĊ
Feature activation+1.963
Chief
TokenChief
Feature activation+0.000
ag
Token ag
Feature activation+0.000
sect
Tokensect
Feature activation+0.000
o
Tokeno
Feature activation+0.000
officers
Token officers
Feature activation+0.000
the
Token the
Feature activation+0.000
three
Token three
Feature activation+0.000
seconds
Token seconds
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.559
Ċ
TokenĊ
Feature activation+2.214
It
TokenIt
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
the
Token the
Feature activation+0.000
work
Token work
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
ounds
Tokenounds
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.980
Cross
TokenCross
Feature activation+0.000
-
Token-
Feature activation+0.000
Browser
TokenBrowser
Feature activation+0.000
Animation
Token Animation
Feature activation+0.000
Support
Token Support
Feature activation+0.000
set
Token set
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
project
Token project
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.210
Ċ
TokenĊ
Feature activation+3.260
an
Tokenan
Feature activation+0.000
engaged
Token engaged
Feature activation+0.000
community
Token community
Feature activation+0.000
of
Token of
Feature activation+0.000
old
Token old
Feature activation+0.000
master
Token master
Feature activation+0.000
painting
Token painting
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.032
Ċ
TokenĊ
Feature activation+2.238
Advertisement
TokenAdvertisement
Feature activation+0.000
Continue
Token Continue
Feature activation+0.000
reading
Token reading
Feature activation+0.000
the
Token the
Feature activation+0.000
main
Token main
Feature activation+0.000

INTERVAL 1.124 - 1.686
CONTAINS 0.003%

the
Token the
Feature activation+0.000
World
Token World
Feature activation+0.000
Cup
Token Cup
Feature activation+0.000
.
Token .
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.236
"
Token"
Feature activation+0.000
In
TokenIn
Feature activation+0.000
particular
Token particular
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
78
Token78
Feature activation+0.000
A
TokenA
Feature activation+0.000
)
Token )
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.667
Solar
TokenSolar
Feature activation+0.000
charge
Token charge
Feature activation+0.000
controller
Token controller
Feature activation+0.000
(
Token (
Feature activation+0.000
Ste
TokenSte
Feature activation+0.000
Euph
Token Euph
Feature activation+0.000
or
Tokenor
Feature activation+0.000
bi
Tokenbi
Feature activation+0.000
aceae
Tokenaceae
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.405
E
TokenE
Feature activation+0.000
uph
Tokenuph
Feature activation+0.000
or
Tokenor
Feature activation+0.000
bia
Tokenbia
Feature activation+0.000
as
Token as
Feature activation+0.000
and
Token and
Feature activation+0.000
Taiwanese
Token Taiwanese
Feature activation+0.000
Sources
Token Sources
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.029
Ċ
TokenĊ
Feature activation+1.490
:
Token:
Feature activation+0.000
Total
Token Total
Feature activation+0.000
losses
Token losses
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
_
Token_
Feature activation+0.000
shared
Tokenshared
Feature activation+0.000
()
Token()
Feature activation+0.000
.
Token .
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.387
Ċ
TokenĊ
Feature activation+1.376
Finally
TokenFinally
Feature activation+0.000
,
Token,
Feature activation+0.000
make
Token make
Feature activation+0.000
_
Token_
Feature activation+0.000
shared
Tokenshared
Feature activation+0.000

INTERVAL 0.562 - 1.124
CONTAINS 0.005%

Chinese
Token Chinese
Feature activation+0.000
and
Token and
Feature activation+0.000
Taiwanese
Token Taiwanese
Feature activation+0.000
Sources
Token Sources
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.029
Ċ
TokenĊ
Feature activation+1.490
:
Token:
Feature activation+0.000
Total
Token Total
Feature activation+0.000
losses
Token losses
Feature activation+0.000
of
Token of
Feature activation+0.000
with
Token with
Feature activation+0.000
this
Token this
Feature activation+0.000
approach
Token approach
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.011
Firstly
TokenFirstly
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
integration
Token integration
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.000
Breaking
TokenBreaking
Feature activation+0.000
traditions
Token traditions
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mr
TokenMr
Feature activation+0.000
again
Token again
Feature activation+0.000
in
Token in
Feature activation+0.000
two
Token two
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.616
Ċ
TokenĊ
Feature activation+2.899
Asked
TokenAsked
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
if
Token if
Feature activation+0.000
:
Token:
Feature activation+0.000
long
Token long
Feature activation+0.000
k
Token k
Feature activation+0.000
ong
Tokenong
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.013
Ind
TokenInd
Feature activation+0.000
ones
Tokenones
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
:
Token:
Feature activation+0.000
d
Token d
Feature activation+0.000

INTERVAL 0.000 - 0.562
CONTAINS 99.986%

Dub
Token Dub
Feature activation+0.000
ke
Tokenke
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
are
Token are
Feature activation+0.000
helping
Token helping
Feature activation+0.000
coordinate
Token coordinate
Feature activation+0.000
the
Token the
Feature activation+0.000
effort
Token effort
Feature activation+0.000
.
Token.
Feature activation+0.000
Press
Token Press
Feature activation+0.000
secretary
Token secretary
Feature activation+0.000
on
Token on
Feature activation+0.000
banks
Token banks
Feature activation+0.000
suspected
Token suspected
Feature activation+0.000
of
Token of
Feature activation+0.000
rigging
Token rigging
Feature activation+0.000
global
Token global
Feature activation+0.000
interest
Token interest
Feature activation+0.000
rate
Token rate
Feature activation+0.000
benchmarks
Token benchmarks
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
98
Token 98
Feature activation+0.000
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
%
Token%
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
stage
Tokenstage
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
statement
Token statement
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
Min
TokenMin
Feature activation+0.000
ister
Tokenister
Feature activation+0.000
of
Token of
Feature activation+0.000
State
Token State
Feature activation+0.000
for
Token for
Feature activation+0.000
Information
Token Information
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 H5.7: (feature 36610)

TOP ACTIVATIONS
MAX = 4.758

build
Token build
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
gap
Token gap
Feature activation+0.000
to
Token to
Feature activation+3.708
the
Token the
Feature activation+4.758
slower
Token slower
Feature activation+0.000
traffic
Token traffic
Feature activation+0.000
and
Token and
Feature activation+0.087
then
Token then
Feature activation+0.000
pit
Token pit
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
the
Token the
Feature activation+0.000
gap
Token gap
Feature activation+0.000
in
Token in
Feature activation+4.619
special
Token special
Feature activation+0.443
skills
Token skills
Feature activation+0.015
that
Token that
Feature activation+0.744
the
Token the
Feature activation+0.000
Vietnam
Token Vietnam
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
helped
Token helped
Feature activation+0.000
close
Token close
Feature activation+0.000
the
Token the
Feature activation+0.000
gap
Token gap
Feature activation+0.000
among
Token among
Feature activation+4.599
military
Token military
Feature activation+0.000
voters
Token voters
Feature activation+1.135
,
Token,
Feature activation+0.000
winning
Token winning
Feature activation+0.000
44
Token 44
Feature activation+0.000
process
Token process
Feature activation+0.000
has
Token has
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000
a
Token a
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.507
the
Token the
Feature activation+2.722
growing
Token growing
Feature activation+0.944
shared
Token shared
Feature activation+0.000
economy
Token economy
Feature activation+0.000
and
Token and
Feature activation+2.472
biggest
Token biggest
Feature activation+0.000
annual
Token annual
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.280
spending
Token spending
Feature activation+0.384
and
Token and
Feature activation+4.417
taxes
Token taxes
Feature activation+0.476
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.304
rich
Token rich
Feature activation+0.748
and
Token and
Feature activation+1.398
poor
Token poor
Feature activation+1.178
is
Token is
Feature activation+0.299
growing
Token growing
Feature activation+0.000
has
Token has
Feature activation+0.000
the
Token the
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
annual
Token annual
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.280
spending
Token spending
Feature activation+0.384
and
Token and
Feature activation+4.417
taxes
Token taxes
Feature activation+0.476
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
dynamic
Token dynamic
Feature activation+0.000
dramatically
Token dramatically
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.158
Democratic
Token Democratic
Feature activation+0.225
Party
Token Party
Feature activation+0.084
rhetoric
Token rhetoric
Feature activation+0.590
and
Token and
Feature activation+2.774
policy
Token policy
Feature activation+0.330
channels
Token channels
Feature activation+0.000
and
Token and
Feature activation+0.000
closes
Token closes
Feature activation+0.000
the
Token the
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.119
banking
Token banking
Feature activation+0.910
users
Token users
Feature activation+0.351
and
Token and
Feature activation+3.285
their
Token their
Feature activation+2.357
social
Token social
Feature activation+0.000
the
Token the
Feature activation+2.722
growing
Token growing
Feature activation+0.944
shared
Token shared
Feature activation+0.000
economy
Token economy
Feature activation+0.000
and
Token and
Feature activation+2.472
what
Token what
Feature activation+3.986
he
Token he
Feature activation+0.000
described
Token described
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
to
Token to
Feature activation+0.000
build
Token build
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
gap
Token gap
Feature activation+0.000
to
Token to
Feature activation+3.708
the
Token the
Feature activation+4.758
slower
Token slower
Feature activation+0.000
traffic
Token traffic
Feature activation+0.000
and
Token and
Feature activation+0.087
then
Token then
Feature activation+0.000
heard
Token heard
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
gender
Token gender
Feature activation+0.000
gap
Token gap
Feature activation+0.045
in
Token in
Feature activation+3.628
tech
Token tech
Feature activation+0.335
.
Token.
Feature activation+0.000
Women
Token Women
Feature activation+0.073
simply
Token simply
Feature activation+0.000
aren
Token aren
Feature activation+0.000
,
Token,
Feature activation+0.000
wide
Token wide
Feature activation+0.000
,
Token,
Feature activation+0.000
ugly
Token ugly
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+3.505
downtown
Token downtown
Feature activation+0.511
and
Token and
Feature activation+2.510
River
Token River
Feature activation+0.000
Market
Token Market
Feature activation+0.000
.
Token.
Feature activation+0.000
attainment
Token attainment
Feature activation+0.000
gap
Token gap
Feature activation+0.000
in
Token in
Feature activation+3.291
verbal
Token verbal
Feature activation+0.917
skills
Token skills
Feature activation+0.459
between
Token between
Feature activation+3.473
five
Token five
Feature activation+0.668
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
olds
Tokenolds
Feature activation+0.184
a
Token a
Feature activation+0.000
12
Token 12
Feature activation+0.000
-
Token-
Feature activation+0.000
minute
Tokenminute
Feature activation+0.000
gap
Token gap
Feature activation+0.265
between
Token between
Feature activation+3.322
each
Token each
Feature activation+0.114
frame
Token frame
Feature activation+0.000
.
Token.
Feature activation+0.204
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
an
Token an
Feature activation+0.000
18
Token 18
Feature activation+0.000
month
Token month
Feature activation+0.000
attainment
Token attainment
Feature activation+0.000
gap
Token gap
Feature activation+0.000
in
Token in
Feature activation+3.291
verbal
Token verbal
Feature activation+0.917
skills
Token skills
Feature activation+0.459
between
Token between
Feature activation+3.473
five
Token five
Feature activation+0.668
-
Token-
Feature activation+0.000
the
Token the
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.119
banking
Token banking
Feature activation+0.910
users
Token users
Feature activation+0.351
and
Token and
Feature activation+3.285
their
Token their
Feature activation+2.357
social
Token social
Feature activation+0.000
interactions
Token interactions
Feature activation+0.000
(
Token (
Feature activation+0.000
social
Tokensocial
Feature activation+0.000
It
TokenIt
Feature activation+0.000
helps
Token helps
Feature activation+0.000
close
Token close
Feature activation+0.000
the
Token the
Feature activation+0.000
gaps
Token gaps
Feature activation+0.000
between
Token between
Feature activation+2.993
data
Token data
Feature activation+1.289
transmitted
Token transmitted
Feature activation+0.000
between
Token between
Feature activation+0.000
POS
Token POS
Feature activation+0.000
devices
Token devices
Feature activation+0.000
failed
Token failed
Feature activation+0.000
to
Token to
Feature activation+0.000
bridge
Token bridge
Feature activation+0.000
big
Token big
Feature activation+0.000
gaps
Token gaps
Feature activation+0.314
between
Token between
Feature activation+2.974
richer
Token richer
Feature activation+0.000
countries
Token countries
Feature activation+0.000
and
Token and
Feature activation+1.419
those
Token those
Feature activation+1.624
which
Token which
Feature activation+0.496
a
Token a
Feature activation+0.000
much
Token much
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000
gap
Token gap
Feature activation+0.000
in
Token in
Feature activation+2.499
the
Token the
Feature activation+2.873
two
Token two
Feature activation+1.939
groups
Token groups
Feature activation+0.000
'
Token'
Feature activation+1.891
perceived
Token perceived
Feature activation+0.298
deserving
Token deserving
Feature activation+0.000

Top DFA by src position
MAX = 6.052

go
Token go
Feature activation-0.009
Top resid features:
to
Token to
Feature activation-0.028
Top resid features:
build
Token build
Feature activation+0.032
Top resid features:
a
Token a
Feature activation-0.007
Top resid features:
good
Token good
Feature activation+0.054
Top resid features:
gap
Token gap
Feature activation+5.644
Top resid features:
to
Token to
Feature activation+0.487
Top resid features:
the
Token the
Feature activation+0.054
Top resid features:
slower
Token slower
Feature activation+0.000
Top resid features:
traffic
Token traffic
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
trying
Token trying
Feature activation+0.068
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
fill
Token fill
Feature activation+0.133
Top resid features:
the
Token the
Feature activation+0.058
Top resid features:
gap
Token gap
Feature activation+5.448
Top resid features:
in
Token in
Feature activation+0.240
Top resid features:
special
Token special
Feature activation+0.000
Top resid features:
skills
Token skills
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Barack
Token Barack
Feature activation-0.016
Top resid features:
Obama
Token Obama
Feature activation-0.016
Top resid features:
helped
Token helped
Feature activation-0.055
Top resid features:
close
Token close
Feature activation+0.004
Top resid features:
the
Token the
Feature activation+0.060
Top resid features:
gap
Token gap
Feature activation+6.052
Top resid features:
among
Token among
Feature activation+0.188
Top resid features:
military
Token military
Feature activation+0.000
Top resid features:
voters
Token voters
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
winning
Token winning
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
process
Token process
Feature activation-0.040
Top resid features:
has
Token has
Feature activation-0.015
Top resid features:
revealed
Token revealed
Feature activation+0.056
Top resid features:
a
Token a
Feature activation-0.053
Top resid features:
gap
Token gap
Feature activation+5.583
Top resid features:
between
Token between
Feature activation+0.243
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
growing
Token growing
Feature activation+0.000
Top resid features:
shared
Token shared
Feature activation+0.000
Top resid features:
economy
Token economy
Feature activation+0.000
Top resid features:
Jersey
Token Jersey
Feature activation-0.013
Top resid features:
has
Token has
Feature activation-0.020
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
biggest
Token biggest
Feature activation+0.014
Top resid features:
annual
Token annual
Feature activation+0.011
Top resid features:
gap
Token gap
Feature activation+4.837
Top resid features:
between
Token between
Feature activation+0.597
Top resid features:
spending
Token spending
Feature activation+0.580
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
taxes
Token taxes
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
U
Token U
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
S
TokenS
Feature activation+0.009
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
The
Token The
Feature activation-0.037
Top resid features:
gap
Token gap
Feature activation+5.210
Top resid features:
between
Token between
Feature activation+0.303
Top resid features:
rich
Token rich
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
poor
Token poor
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
Jersey
Token Jersey
Feature activation-0.047
Top resid features:
has
Token has
Feature activation-0.070
Top resid features:
the
Token the
Feature activation-0.050
Top resid features:
biggest
Token biggest
Feature activation-0.007
Top resid features:
annual
Token annual
Feature activation-0.021
Top resid features:
gap
Token gap
Feature activation+5.405
Top resid features:
between
Token between
Feature activation+0.276
Top resid features:
spending
Token spending
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
taxes
Token taxes
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.014
Top resid features:
dynamic
Token dynamic
Feature activation-0.028
Top resid features:
dramatically
Token dramatically
Feature activation+0.036
Top resid features:
.
Token.
Feature activation+0.104
Top resid features:
The
Token The
Feature activation+0.013
Top resid features:
gap
Token gap
Feature activation+4.966
Top resid features:
between
Token between
Feature activation+0.304
Top resid features:
Democratic
Token Democratic
Feature activation+0.000
Top resid features:
Party
Token Party
Feature activation+0.000
Top resid features:
rhetoric
Token rhetoric
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
emerging
Token emerging
Feature activation+0.094
Top resid features:
channels
Token channels
Feature activation-0.018
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
closes
Token closes
Feature activation+0.220
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
gap
Token gap
Feature activation+4.818
Top resid features:
between
Token between
Feature activation+0.410
Top resid features:
banking
Token banking
Feature activation+0.000
Top resid features:
users
Token users
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.011
Top resid features:
process
Token process
Feature activation-0.013
Top resid features:
has
Token has
Feature activation+0.005
Top resid features:
revealed
Token revealed
Feature activation+0.051
Top resid features:
a
Token a
Feature activation+0.013
Top resid features:
gap
Token gap
Feature activation+4.529
Top resid features:
between
Token between
Feature activation+0.587
Top resid features:
the
Token the
Feature activation+0.126
Top resid features:
growing
Token growing
Feature activation+0.120
Top resid features:
shared
Token shared
Feature activation+0.073
Top resid features:
economy
Token economy
Feature activation+0.017
Top resid features:
go
Token go
Feature activation-0.007
Top resid features:
to
Token to
Feature activation-0.025
Top resid features:
build
Token build
Feature activation+0.104
Top resid features:
a
Token a
Feature activation-0.137
Top resid features:
good
Token good
Feature activation+0.046
Top resid features:
gap
Token gap
Feature activation+5.010
Top resid features:
to
Token to
Feature activation+0.187
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
slower
Token slower
Feature activation+0.000
Top resid features:
traffic
Token traffic
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.006
Top resid features:
heard
Token heard
Feature activation-0.043
Top resid features:
about
Token about
Feature activation+0.022
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
gender
Token gender
Feature activation+0.151
Top resid features:
gap
Token gap
Feature activation+4.668
Top resid features:
in
Token in
Feature activation+0.263
Top resid features:
tech
Token tech
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Women
Token Women
Feature activation+0.000
Top resid features:
simply
Token simply
Feature activation+0.000
Top resid features:
big
Token big
Feature activation-0.006
Top resid features:
,
Token,
Feature activation+0.041
Top resid features:
wide
Token wide
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
ugly
Token ugly
Feature activation+0.020
Top resid features:
gap
Token gap
Feature activation+4.163
Top resid features:
between
Token between
Feature activation+0.569
Top resid features:
downtown
Token downtown
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
River
Token River
Feature activation+0.000
Top resid features:
Market
Token Market
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.022
Top resid features:
an
Token an
Feature activation-0.001
Top resid features:
18
Token 18
Feature activation+0.007
Top resid features:
month
Token month
Feature activation+0.002
Top resid features:
attainment
Token attainment
Feature activation+0.243
Top resid features:
gap
Token gap
Feature activation+3.427
Top resid features:
in
Token in
Feature activation+0.452
Top resid features:
verbal
Token verbal
Feature activation+0.223
Top resid features:
skills
Token skills
Feature activation+0.341
Top resid features:
between
Token between
Feature activation+0.136
Top resid features:
five
Token five
Feature activation+0.000
Top resid features:
about
Token about
Feature activation-0.015
Top resid features:
a
Token a
Feature activation-0.004
Top resid features:
12
Token 12
Feature activation+0.059
Top resid features:
-
Token-
Feature activation+0.018
Top resid features:
minute
Tokenminute
Feature activation+0.044
Top resid features:
gap
Token gap
Feature activation+4.314
Top resid features:
between
Token between
Feature activation+0.270
Top resid features:
each
Token each
Feature activation+0.000
Top resid features:
frame
Token frame
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.027
Top resid features:
an
Token an
Feature activation+0.005
Top resid features:
18
Token 18
Feature activation-0.010
Top resid features:
month
Token month
Feature activation-0.007
Top resid features:
attainment
Token attainment
Feature activation+0.447
Top resid features:
gap
Token gap
Feature activation+3.895
Top resid features:
in
Token in
Feature activation+0.227
Top resid features:
verbal
Token verbal
Feature activation+0.000
Top resid features:
skills
Token skills
Feature activation+0.000
Top resid features:
between
Token between
Feature activation+0.000
Top resid features:
five
Token five
Feature activation+0.000
Top resid features:
emerging
Token emerging
Feature activation+0.044
Top resid features:
channels
Token channels
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.009
Top resid features:
closes
Token closes
Feature activation+0.198
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
gap
Token gap
Feature activation+3.125
Top resid features:
between
Token between
Feature activation+1.117
Top resid features:
banking
Token banking
Feature activation+0.105
Top resid features:
users
Token users
Feature activation+0.172
Top resid features:
and
Token and
Feature activation+0.088
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.023
Top resid features:
It
TokenIt
Feature activation-0.007
Top resid features:
helps
Token helps
Feature activation+0.008
Top resid features:
close
Token close
Feature activation-0.023
Top resid features:
the
Token the
Feature activation+0.105
Top resid features:
gaps
Token gaps
Feature activation+3.701
Top resid features:
between
Token between
Feature activation+0.352
Top resid features:
data
Token data
Feature activation+0.000
Top resid features:
transmitted
Token transmitted
Feature activation+0.000
Top resid features:
between
Token between
Feature activation+0.000
Top resid features:
POS
Token POS
Feature activation+0.000
Top resid features:
talks
Token talks
Feature activation-0.041
Top resid features:
failed
Token failed
Feature activation+0.010
Top resid features:
to
Token to
Feature activation-0.053
Top resid features:
bridge
Token bridge
Feature activation+0.029
Top resid features:
big
Token big
Feature activation+0.238
Top resid features:
gaps
Token gaps
Feature activation+3.943
Top resid features:
between
Token between
Feature activation+0.116
Top resid features:
richer
Token richer
Feature activation+0.000
Top resid features:
countries
Token countries
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
those
Token those
Feature activation+0.000
Top resid features:
there
Token there
Feature activation+0.007
Top resid features:
was
Token was
Feature activation+0.053
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
much
Token much
Feature activation+0.018
Top resid features:
smaller
Token smaller
Feature activation-0.055
Top resid features:
gap
Token gap
Feature activation+4.200
Top resid features:
in
Token in
Feature activation+0.295
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
groups
Token groups
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.01

Head 1: 0.01

Head 2: 0.09

Head 3: 0.05

Head 4: 0.06

Head 5: 0.02

Head 6: 0.04

Head 7: 0.53

Head 8: 0.02

Head 9: 0.03

Head 10: 0.06

Head 11: 0.07

Positive logits

ittal1.95

gaps1.73

deadlines1.70

papers1.66

comprehension1.63

publications1.61

erences1.57

standings1.56

timelines1.53

eligibility1.53

rium1.53

ancial1.53

resumes1.52

gap1.51

claimants1.49

entrance1.48

arlane1.48

olars1.47

belie1.47

izons1.46

Negative logits

spir-1.87

-1.60

-1.60

havoc-1.58

trak-1.50

arse-1.47

-1.43

EFF-1.41

lov-1.41

efe-1.40

-1.40

-1.37

slave-1.35

bal-1.35

Synopsis-1.34

vomiting-1.34

-1.33

Cru-1.31

ELF-1.31

Syn-1.30

INTERVAL 4.282 - 4.758
CONTAINS 0.001%

.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.304
rich
Token rich
Feature activation+0.748
and
Token and
Feature activation+1.398
poor
Token poor
Feature activation+1.178
is
Token is
Feature activation+0.299
growing
Token growing
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
the
Token the
Feature activation+0.000
gap
Token gap
Feature activation+0.000
in
Token in
Feature activation+4.619
special
Token special
Feature activation+0.443
skills
Token skills
Feature activation+0.015
that
Token that
Feature activation+0.744
the
Token the
Feature activation+0.000
Vietnam
Token Vietnam
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
annual
Token annual
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.280
spending
Token spending
Feature activation+0.384
and
Token and
Feature activation+4.417
taxes
Token taxes
Feature activation+0.476
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
build
Token build
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
gap
Token gap
Feature activation+0.000
to
Token to
Feature activation+3.708
the
Token the
Feature activation+4.758
slower
Token slower
Feature activation+0.000
traffic
Token traffic
Feature activation+0.000
and
Token and
Feature activation+0.087
then
Token then
Feature activation+0.000
pit
Token pit
Feature activation+0.000
process
Token process
Feature activation+0.000
has
Token has
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000
a
Token a
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.507
the
Token the
Feature activation+2.722
growing
Token growing
Feature activation+0.944
shared
Token shared
Feature activation+0.000
economy
Token economy
Feature activation+0.000
and
Token and
Feature activation+2.472

INTERVAL 3.806 - 4.282
CONTAINS 0.001%

the
Token the
Feature activation+2.722
growing
Token growing
Feature activation+0.944
shared
Token shared
Feature activation+0.000
economy
Token economy
Feature activation+0.000
and
Token and
Feature activation+2.472
what
Token what
Feature activation+3.986
he
Token he
Feature activation+0.000
described
Token described
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
current
Token current
Feature activation+0.000
dynamic
Token dynamic
Feature activation+0.000
dramatically
Token dramatically
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.158
Democratic
Token Democratic
Feature activation+0.225
Party
Token Party
Feature activation+0.084
rhetoric
Token rhetoric
Feature activation+0.590
and
Token and
Feature activation+2.774
policy
Token policy
Feature activation+0.330
channels
Token channels
Feature activation+0.000
and
Token and
Feature activation+0.000
closes
Token closes
Feature activation+0.000
the
Token the
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.119
banking
Token banking
Feature activation+0.910
users
Token users
Feature activation+0.351
and
Token and
Feature activation+3.285
their
Token their
Feature activation+2.357
social
Token social
Feature activation+0.000
has
Token has
Feature activation+0.000
the
Token the
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
annual
Token annual
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.280
spending
Token spending
Feature activation+0.384
and
Token and
Feature activation+4.417
taxes
Token taxes
Feature activation+0.476
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000

INTERVAL 3.330 - 3.806
CONTAINS 0.000%

,
Token,
Feature activation+0.000
wide
Token wide
Feature activation+0.000
,
Token,
Feature activation+0.000
ugly
Token ugly
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+3.505
downtown
Token downtown
Feature activation+0.511
and
Token and
Feature activation+2.510
River
Token River
Feature activation+0.000
Market
Token Market
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
build
Token build
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
gap
Token gap
Feature activation+0.000
to
Token to
Feature activation+3.708
the
Token the
Feature activation+4.758
slower
Token slower
Feature activation+0.000
traffic
Token traffic
Feature activation+0.000
and
Token and
Feature activation+0.087
then
Token then
Feature activation+0.000
heard
Token heard
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
gender
Token gender
Feature activation+0.000
gap
Token gap
Feature activation+0.045
in
Token in
Feature activation+3.628
tech
Token tech
Feature activation+0.335
.
Token.
Feature activation+0.000
Women
Token Women
Feature activation+0.073
simply
Token simply
Feature activation+0.000
aren
Token aren
Feature activation+0.000
attainment
Token attainment
Feature activation+0.000
gap
Token gap
Feature activation+0.000
in
Token in
Feature activation+3.291
verbal
Token verbal
Feature activation+0.917
skills
Token skills
Feature activation+0.459
between
Token between
Feature activation+3.473
five
Token five
Feature activation+0.668
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
olds
Tokenolds
Feature activation+0.184

INTERVAL 2.855 - 3.330
CONTAINS 0.001%

It
TokenIt
Feature activation+0.000
helps
Token helps
Feature activation+0.000
close
Token close
Feature activation+0.000
the
Token the
Feature activation+0.000
gaps
Token gaps
Feature activation+0.000
between
Token between
Feature activation+2.993
data
Token data
Feature activation+1.289
transmitted
Token transmitted
Feature activation+0.000
between
Token between
Feature activation+0.000
POS
Token POS
Feature activation+0.000
devices
Token devices
Feature activation+0.000
the
Token the
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.119
banking
Token banking
Feature activation+0.910
users
Token users
Feature activation+0.351
and
Token and
Feature activation+3.285
their
Token their
Feature activation+2.357
social
Token social
Feature activation+0.000
interactions
Token interactions
Feature activation+0.000
(
Token (
Feature activation+0.000
social
Tokensocial
Feature activation+0.000
failed
Token failed
Feature activation+0.000
to
Token to
Feature activation+0.000
bridge
Token bridge
Feature activation+0.000
big
Token big
Feature activation+0.000
gaps
Token gaps
Feature activation+0.314
between
Token between
Feature activation+2.974
richer
Token richer
Feature activation+0.000
countries
Token countries
Feature activation+0.000
and
Token and
Feature activation+1.419
those
Token those
Feature activation+1.624
which
Token which
Feature activation+0.496
a
Token a
Feature activation+0.000
much
Token much
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000
gap
Token gap
Feature activation+0.000
in
Token in
Feature activation+2.499
the
Token the
Feature activation+2.873
two
Token two
Feature activation+1.939
groups
Token groups
Feature activation+0.000
'
Token'
Feature activation+1.891
perceived
Token perceived
Feature activation+0.298
deserving
Token deserving
Feature activation+0.000
a
Token a
Feature activation+0.000
12
Token 12
Feature activation+0.000
-
Token-
Feature activation+0.000
minute
Tokenminute
Feature activation+0.000
gap
Token gap
Feature activation+0.265
between
Token between
Feature activation+3.322
each
Token each
Feature activation+0.114
frame
Token frame
Feature activation+0.000
.
Token.
Feature activation+0.204
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.379 - 2.855
CONTAINS 0.001%

was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
much
Token much
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000
gap
Token gap
Feature activation+0.000
in
Token in
Feature activation+2.499
the
Token the
Feature activation+2.873
two
Token two
Feature activation+1.939
groups
Token groups
Feature activation+0.000
'
Token'
Feature activation+1.891
perceived
Token perceived
Feature activation+0.298
has
Token has
Feature activation+0.000
revealed
Token revealed
Feature activation+0.000
a
Token a
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.507
the
Token the
Feature activation+2.722
growing
Token growing
Feature activation+0.944
shared
Token shared
Feature activation+0.000
economy
Token economy
Feature activation+0.000
and
Token and
Feature activation+2.472
what
Token what
Feature activation+3.986
,
Token,
Feature activation+0.000
ugly
Token ugly
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+3.505
downtown
Token downtown
Feature activation+0.511
and
Token and
Feature activation+2.510
River
Token River
Feature activation+0.000
Market
Token Market
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
would
Token would
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.158
Democratic
Token Democratic
Feature activation+0.225
Party
Token Party
Feature activation+0.084
rhetoric
Token rhetoric
Feature activation+0.590
and
Token and
Feature activation+2.774
policy
Token policy
Feature activation+0.330
has
Token has
Feature activation+0.000
widened
Token widened
Feature activation+0.000
since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
between
Token between
Feature activation+4.507
the
Token the
Feature activation+2.722
growing
Token growing
Feature activation+0.944
shared
Token shared
Feature activation+0.000
economy
Token economy
Feature activation+0.000
and
Token and
Feature activation+2.472
what
Token what
Feature activation+3.986
he
Token he
Feature activation+0.000
described
Token described
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.903 - 2.379
CONTAINS 0.000%

play
Token play
Feature activation+0.000
and
Token and
Feature activation+0.000
hit
Token hit
Feature activation+0.000
his
Token his
Feature activation+0.000
gap
Token gap
Feature activation+0.000
in
Token in
Feature activation+2.134
a
Token a
Feature activation+0.000
flash
Token flash
Feature activation+0.000
before
Token before
Feature activation+0.000
the
Token the
Feature activation+0.000
peel
Token peel
Feature activation+0.000
fill
Token fill
Feature activation+0.000
in
Token in
Feature activation+0.000
"
Token "
Feature activation+0.000
population
Tokenpopulation
Feature activation+0.000
gaps
Token gaps
Feature activation+0.262
"
Token"
Feature activation+1.937
they
Token they
Feature activation+0.000
say
Token say
Feature activation+0.000
occur
Token occur
Feature activation+0.747
because
Token because
Feature activation+0.000
some
Token some
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.119
banking
Token banking
Feature activation+0.910
users
Token users
Feature activation+0.351
and
Token and
Feature activation+3.285
their
Token their
Feature activation+2.357
social
Token social
Feature activation+0.000
interactions
Token interactions
Feature activation+0.000
(
Token (
Feature activation+0.000
social
Tokensocial
Feature activation+0.000
media
Token media
Feature activation+0.000
much
Token much
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000
gap
Token gap
Feature activation+0.000
in
Token in
Feature activation+2.499
the
Token the
Feature activation+2.873
two
Token two
Feature activation+1.939
groups
Token groups
Feature activation+0.000
'
Token'
Feature activation+1.891
perceived
Token perceived
Feature activation+0.298
deserving
Token deserving
Feature activation+0.000
ness
Tokenness
Feature activation+0.000

INTERVAL 1.427 - 1.903
CONTAINS 0.001%

gap
Token gap
Feature activation+0.000
in
Token in
Feature activation+2.499
the
Token the
Feature activation+2.873
two
Token two
Feature activation+1.939
groups
Token groups
Feature activation+0.000
'
Token'
Feature activation+1.891
perceived
Token perceived
Feature activation+0.298
deserving
Token deserving
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
among
Token among
Feature activation+0.472
African
Token African
Feature activation+0.000
amid
Token amid
Feature activation+0.000
reports
Token reports
Feature activation+0.000
of
Token of
Feature activation+0.000
discrepancies
Token discrepancies
Feature activation+0.000
in
Token in
Feature activation+1.729
its
Token its
Feature activation+1.597
record
Token record
Feature activation+0.279
-
Token-
Feature activation+0.000
keeping
Tokenkeeping
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
too
Token too
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+2.806
the
Token the
Feature activation+1.459
parties
Token parties
Feature activation+0.000
is
Token is
Feature activation+0.000
wider
Token wider
Feature activation+0.000
than
Token than
Feature activation+0.000
at
Token at
Feature activation+0.000
issues
Token issues
Feature activation+0.000
such
Token such
Feature activation+0.000
the
Token the
Feature activation+0.000
disconnect
Token disconnect
Feature activation+0.000
ion
Tokenion
Feature activation+0.000
of
Token of
Feature activation+1.456
Tel
Token Tel
Feature activation+0.000
stra
Tokenstra
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
transmitted
Token transmitted
Feature activation+0.000
between
Token between
Feature activation+0.000
POS
Token POS
Feature activation+0.000
devices
Token devices
Feature activation+0.000
and
Token and
Feature activation+1.334
the
Token the
Feature activation+1.688
data
Token data
Feature activation+0.194
center
Token center
Feature activation+0.000
and
Tokenand
Feature activation+0.618
support
Token support
Feature activation+0.000
supports
Token supports
Feature activation+0.000

INTERVAL 0.952 - 1.427
CONTAINS 0.002%

on
Token on
Feature activation+0.759
that
Token that
Feature activation+0.000
question
Token question
Feature activation+0.000
went
Token went
Feature activation+0.000
from
Token from
Feature activation+0.000
13
Token 13
Feature activation+0.987
points
Token points
Feature activation+0.921
in
Token in
Feature activation+0.000
1994
Token 1994
Feature activation+0.000
to
Token to
Feature activation+0.000
19
Token 19
Feature activation+0.000
close
Token close
Feature activation+0.000
the
Token the
Feature activation+0.000
gap
Token gap
Feature activation+0.000
among
Token among
Feature activation+4.599
military
Token military
Feature activation+0.000
voters
Token voters
Feature activation+1.135
,
Token,
Feature activation+0.000
winning
Token winning
Feature activation+0.000
44
Token 44
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
free
Token free
Feature activation+0.000
,
Token,
Feature activation+0.000
closing
Token closing
Feature activation+0.000
loopholes
Token loopholes
Feature activation+0.000
in
Token in
Feature activation+1.192
the
Token the
Feature activation+0.984
state
Token state
Feature activation+0.219
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
smoke
Token smoke
Feature activation+0.000
The
Token The
Feature activation+0.000
gap
Token gap
Feature activation+0.000
between
Token between
Feature activation+4.304
rich
Token rich
Feature activation+0.748
and
Token and
Feature activation+1.398
poor
Token poor
Feature activation+1.178
is
Token is
Feature activation+0.299
growing
Token growing
Feature activation+0.000
nationwide
Token nationwide
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
1924
Token 1924
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
growing
Token growing
Feature activation+0.000
rift
Token rift
Feature activation+0.000
between
Token between
Feature activation+1.043
the
Token the
Feature activation+0.382
two
Token two
Feature activation+1.088
largest
Token largest
Feature activation+0.000
schools
Token schools
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.476 - 0.952
CONTAINS 0.004%

discrepancy
Token discrepancy
Feature activation+0.000
in
Token in
Feature activation+0.984
her
Token her
Feature activation+0.924
parent
Token parent
Feature activation+0.000
age
Tokenage
Feature activation+0.000
.
Token.
Feature activation+0.783
The
Token The
Feature activation+0.320
Oxford
Token Oxford
Feature activation+0.000
Dictionary
Token Dictionary
Feature activation+0.000
of
Token of
Feature activation+0.000
National
Token National
Feature activation+0.000
in
Token in
Feature activation+1.280
the
Token the
Feature activation+0.931
short
Token short
Feature activation+0.000
-
Token-
Feature activation+0.000
term
Tokenterm
Feature activation+0.000
with
Token with
Feature activation+0.891
further
Token further
Feature activation+0.330
funding
Token funding
Feature activation+0.000
for
Token for
Feature activation+0.000
science
Token science
Feature activation+0.000
."
Token."
Feature activation+0.000
that
Token that
Feature activation+0.000
question
Token question
Feature activation+0.000
went
Token went
Feature activation+0.000
from
Token from
Feature activation+0.000
13
Token 13
Feature activation+0.987
points
Token points
Feature activation+0.921
in
Token in
Feature activation+0.000
1994
Token 1994
Feature activation+0.000
to
Token to
Feature activation+0.000
19
Token 19
Feature activation+0.000
points
Token points
Feature activation+0.000
in
Token in
Feature activation+0.638
the
Token the
Feature activation+0.678
platform
Token platform
Feature activation+0.000
world
Token world
Feature activation+0.207
between
Token between
Feature activation+0.968
the
Token the
Feature activation+0.488
whole
Token whole
Feature activation+0.000
ex
Token ex
Feature activation+0.000
ome
Tokenome
Feature activation+0.000
/
Token /
Feature activation+0.000
genome
Token genome
Feature activation+0.000
DUI
Token DUI
Feature activation+0.000
and
Token and
Feature activation+0.000
failure
Token failure
Feature activation+0.000
to
Token to
Feature activation+0.000
yield
Token yield
Feature activation+0.000
to
Token to
Feature activation+0.493
an
Token an
Feature activation+0.143
emergency
Token emergency
Feature activation+0.000
vehicle
Token vehicle
Feature activation+0.000
.
Token.
Feature activation+0.000
Her
Token Her
Feature activation+0.000

INTERVAL 0.000 - 0.476
CONTAINS 99.990%

and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
decision
Token decision
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Some
TokenSome
Feature activation+0.000
December
Token December
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
shocking
Token shocking
Feature activation+0.000
video
Token video
Feature activation+0.000
emerged
Token emerged
Feature activation+0.000
of
Token of
Feature activation+0.000
Syrian
Token Syrian
Feature activation+0.000
rebels
Token rebels
Feature activation+0.000
testing
Token testing
Feature activation+0.000
what
Token what
Feature activation+0.000
Facebook
Token Facebook
Feature activation+0.000
post
Token post
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
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
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Supp
TokenSupp
Feature activation+0.000
ose
Tokenose
Feature activation+0.000
you
Token you
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
fil
Token fil
Feature activation+0.000
let
Tokenlet
Feature activation+0.000
a
Token a
Feature activation+0.000
fish
Token fish
Feature activation+0.000
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
cities
Token cities
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
vibrant
Token vibrant
Feature activation+0.000
places
Token places
Feature activation+0.000
to
Token to
Feature activation+0.000
live
Token live
Feature activation+0.000
-
Token -
Feature activation+0.000
Paris
Token Paris
Feature activation+0.000
,
Token,
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H5.7: (feature 12065)

TOP ACTIVATIONS
MAX = 3.385

have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
his
Token his
Feature activation+1.935
or
Token or
Feature activation+0.000
her
Token her
Feature activation+3.385
gasoline
Token gasoline
Feature activation+0.667
tank
Token tank
Feature activation+0.248
several
Token several
Feature activation+0.000
times
Token times
Feature activation+0.137
a
Token a
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
about
Token about
Feature activation+0.000
who
Token who
Feature activation+0.000
could
Token could
Feature activation+0.000
fill
Token fill
Feature activation+0.000
those
Token those
Feature activation+3.203
large
Token large
Feature activation+0.000
-
Token-
Feature activation+0.000
sized
Tokensized
Feature activation+0.000
luxury
Token luxury
Feature activation+0.000
loaf
Token loaf
Feature activation+0.000
bucket
Token bucket
Feature activation+0.000
.
Token.
Feature activation+0.000
Fill
Token Fill
Feature activation+0.000
the
Token the
Feature activation+1.277
bucket
Token bucket
Feature activation+0.052
with
Token with
Feature activation+2.968
water
Token water
Feature activation+0.107
then
Token then
Feature activation+0.000
place
Token place
Feature activation+0.000
the
Token the
Feature activation+0.000
air
Token air
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
up
Token up
Feature activation+0.943
his
Token his
Feature activation+2.137
parents
Token parents
Feature activation+0.994
'
Token'
Feature activation+2.850
car
Token car
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
waited
Token waited
Feature activation+0.000
for
Token for
Feature activation+0.000
dungeon
Token dungeon
Feature activation+0.000
craw
Token craw
Feature activation+0.000
ler
Tokenler
Feature activation+0.000
is
Token is
Feature activation+0.000
filled
Token filled
Feature activation+0.000
to
Token to
Feature activation+2.232
the
Token the
Feature activation+2.068
brim
Token brim
Feature activation+0.000
with
Token with
Feature activation+0.147
vast
Token vast
Feature activation+0.000
maps
Token maps
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
looking
Token looking
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
up
Token up
Feature activation+0.943
his
Token his
Feature activation+2.137
parents
Token parents
Feature activation+0.994
'
Token'
Feature activation+2.850
car
Token car
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
craw
Token craw
Feature activation+0.000
ler
Tokenler
Feature activation+0.000
is
Token is
Feature activation+0.000
filled
Token filled
Feature activation+0.000
to
Token to
Feature activation+2.232
the
Token the
Feature activation+2.068
brim
Token brim
Feature activation+0.000
with
Token with
Feature activation+0.147
vast
Token vast
Feature activation+0.000
maps
Token maps
Feature activation+0.000
to
Token to
Feature activation+0.000
worker
Token worker
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
his
Token his
Feature activation+1.935
or
Token or
Feature activation+0.000
her
Token her
Feature activation+3.385
gasoline
Token gasoline
Feature activation+0.667
tank
Token tank
Feature activation+0.248
several
Token several
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
filled
Token filled
Feature activation+0.133
with
Token with
Feature activation+0.121
a
Token a
Feature activation+1.832
mixture
Token mixture
Feature activation+0.000
of
Token of
Feature activation+0.000
dead
Token dead
Feature activation+0.000
weeds
Token weeds
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
voter
Token voter
Feature activation+0.000
had
Token had
Feature activation+0.000
filled
Token filled
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+1.802
bubbles
Token bubbles
Feature activation+0.000
next
Token next
Feature activation+0.000
to
Token to
Feature activation+0.000
both
Token both
Feature activation+0.000
candidates
Token candidates
Feature activation+0.000
sweetness
Token sweetness
Feature activation+0.000
and
Token and
Feature activation+0.000
fill
Token fill
Feature activation+0.000
-
Token-
Feature activation+0.000
you
Tokenyou
Feature activation+0.000
-
Token-
Feature activation+1.790
up
Tokenup
Feature activation+0.000
protein
Token protein
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
be
Token be
Feature activation+0.000
ready
Token ready
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
your
Token your
Feature activation+1.777
eyes
Token eyes
Feature activation+0.456
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
beauty
Token beauty
Feature activation+0.000
of
Token of
Feature activation+0.000
Rift
Token Rift
Feature activation+0.000
headsets
Token headsets
Feature activation+0.000
were
Token were
Feature activation+0.000
filled
Token filled
Feature activation+0.598
with
Token with
Feature activation+0.011
the
Token the
Feature activation+1.489
work
Token work
Feature activation+0.000
of
Token of
Feature activation+0.000
studios
Token studios
Feature activation+0.000
looking
Token looking
Feature activation+0.000
to
Token to
Feature activation+0.000
lump
Token lump
Feature activation+0.000
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
skin
Token skin
Feature activation+0.000
filled
Token filled
Feature activation+0.659
with
Token with
Feature activation+1.392
infected
Token infected
Feature activation+0.000
fluids
Token fluids
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
selected
Token selected
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
these
Token these
Feature activation+1.362
jobs
Token jobs
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
more
Token more
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
the
Token the
Feature activation+0.000
bucket
Token bucket
Feature activation+0.000
.
Token.
Feature activation+0.000
Fill
Token Fill
Feature activation+0.000
the
Token the
Feature activation+1.277
bucket
Token bucket
Feature activation+0.052
with
Token with
Feature activation+2.968
water
Token water
Feature activation+0.107
then
Token then
Feature activation+0.000
place
Token place
Feature activation+0.000
Over
TokenOver
Feature activation+0.000
decades
Token decades
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
filled
Token filled
Feature activation+0.000
many
Token many
Feature activation+1.250
wetlands
Token wetlands
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
natural
Token natural
Feature activation+0.000
be
Token be
Feature activation+0.000
enough
Token enough
Feature activation+0.000
fans
Token fans
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
a
Token a
Feature activation+1.187
40
Token 40
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
-
Token-
Feature activation+0.000
seat
Tokenseat
Feature activation+0.000
forces
Token forces
Feature activation+0.000
,
Token,
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
the
Token the
Feature activation+1.171
gap
Token gap
Feature activation+0.000
in
Token in
Feature activation+0.000
special
Token special
Feature activation+0.000
skills
Token skills
Feature activation+0.000
that
Token that
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000
and
Token and
Feature activation+0.000
filled
Token filled
Feature activation+0.000
with
Token with
Feature activation+0.024
even
Token even
Feature activation+0.000
more
Token more
Feature activation+1.116
wonder
Token wonder
Feature activation+0.000
than
Token than
Feature activation+0.000
you
Token you
Feature activation+0.000
could
Token could
Feature activation+0.000
imagine
Token imagine
Feature activation+0.000

Top DFA by src position
MAX = 4.922

a
Token a
Feature activation-0.027
Top resid features:
worker
Token worker
Feature activation+0.125
Top resid features:
to
Token to
Feature activation-0.039
Top resid features:
have
Token have
Feature activation-0.066
Top resid features:
to
Token to
Feature activation-0.033
Top resid features:
fill
Token fill
Feature activation+4.922
Top resid features:
his
Token his
Feature activation-0.009
Top resid features:
or
Token or
Feature activation-0.226
Top resid features:
her
Token her
Feature activation-0.014
Top resid features:
gasoline
Token gasoline
Feature activation+0.000
Top resid features:
tank
Token tank
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.034
Top resid features:
thinking
Token thinking
Feature activation+0.015
Top resid features:
about
Token about
Feature activation+0.006
Top resid features:
who
Token who
Feature activation-0.038
Top resid features:
could
Token could
Feature activation-0.048
Top resid features:
fill
Token fill
Feature activation+4.258
Top resid features:
those
Token those
Feature activation+0.068
Top resid features:
large
Token large
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
sized
Tokensized
Feature activation+0.000
Top resid features:
luxury
Token luxury
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.026
Top resid features:
the
Token the
Feature activation-0.049
Top resid features:
bucket
Token bucket
Feature activation+0.170
Top resid features:
.
Token.
Feature activation-0.066
Top resid features:
Fill
Token Fill
Feature activation+4.058
Top resid features:
the
Token the
Feature activation+0.015
Top resid features:
bucket
Token bucket
Feature activation+0.096
Top resid features:
with
Token with
Feature activation-0.136
Top resid features:
water
Token water
Feature activation+0.000
Top resid features:
then
Token then
Feature activation+0.000
Top resid features:
around
Token around
Feature activation+0.030
Top resid features:
on
Token on
Feature activation+0.008
Top resid features:
Wednesday
Token Wednesday
Feature activation-0.007
Top resid features:
looking
Token looking
Feature activation+0.026
Top resid features:
to
Token to
Feature activation-0.030
Top resid features:
fill
Token fill
Feature activation+3.376
Top resid features:
up
Token up
Feature activation+0.139
Top resid features:
his
Token his
Feature activation+0.002
Top resid features:
parents
Token parents
Feature activation+0.459
Top resid features:
'
Token'
Feature activation-0.040
Top resid features:
car
Token car
Feature activation+0.000
Top resid features:
ike
Tokenike
Feature activation+0.003
Top resid features:
dungeon
Token dungeon
Feature activation+0.018
Top resid features:
craw
Token craw
Feature activation+0.017
Top resid features:
ler
Tokenler
Feature activation-0.026
Top resid features:
is
Token is
Feature activation+0.025
Top resid features:
filled
Token filled
Feature activation+3.250
Top resid features:
to
Token to
Feature activation-0.072
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
brim
Token brim
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
vast
Token vast
Feature activation+0.000
Top resid features:
around
Token around
Feature activation+0.029
Top resid features:
on
Token on
Feature activation+0.012
Top resid features:
Wednesday
Token Wednesday
Feature activation-0.019
Top resid features:
looking
Token looking
Feature activation+0.023
Top resid features:
to
Token to
Feature activation-0.017
Top resid features:
fill
Token fill
Feature activation+2.872
Top resid features:
up
Token up
Feature activation+0.472
Top resid features:
his
Token his
Feature activation+0.067
Top resid features:
parents
Token parents
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
car
Token car
Feature activation+0.000
Top resid features:
ike
Tokenike
Feature activation+0.002
Top resid features:
dungeon
Token dungeon
Feature activation+0.006
Top resid features:
craw
Token craw
Feature activation+0.019
Top resid features:
ler
Tokenler
Feature activation-0.012
Top resid features:
is
Token is
Feature activation+0.011
Top resid features:
filled
Token filled
Feature activation+3.720
Top resid features:
to
Token to
Feature activation-0.398
Top resid features:
the
Token the
Feature activation-0.137
Top resid features:
brim
Token brim
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
vast
Token vast
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.018
Top resid features:
worker
Token worker
Feature activation+0.004
Top resid features:
to
Token to
Feature activation-0.006
Top resid features:
have
Token have
Feature activation-0.035
Top resid features:
to
Token to
Feature activation-0.009
Top resid features:
fill
Token fill
Feature activation+3.112
Top resid features:
his
Token his
Feature activation-0.014
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
gasoline
Token gasoline
Feature activation+0.000
Top resid features:
tank
Token tank
Feature activation+0.000
Top resid features:
three
Token three
Feature activation+0.001
Top resid features:
deep
Token deep
Feature activation+0.008
Top resid features:
.
Token.
Feature activation-0.020
Top resid features:
It
Token It
Feature activation-0.050
Top resid features:
was
Token was
Feature activation-0.003
Top resid features:
filled
Token filled
Feature activation+2.861
Top resid features:
with
Token with
Feature activation-0.111
Top resid features:
a
Token a
Feature activation+0.021
Top resid features:
mixture
Token mixture
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
dead
Token dead
Feature activation+0.000
Top resid features:
question
Token question
Feature activation+0.049
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
voter
Token voter
Feature activation+0.003
Top resid features:
had
Token had
Feature activation+0.058
Top resid features:
filled
Token filled
Feature activation+2.470
Top resid features:
in
Token in
Feature activation+0.256
Top resid features:
the
Token the
Feature activation+0.033
Top resid features:
bubbles
Token bubbles
Feature activation+0.000
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
crunch
Token crunch
Feature activation-0.018
Top resid features:
,
Token,
Feature activation-0.032
Top resid features:
sweetness
Token sweetness
Feature activation-0.017
Top resid features:
and
Token and
Feature activation-0.033
Top resid features:
fill
Token fill
Feature activation+3.203
Top resid features:
-
Token-
Feature activation+0.082
Top resid features:
you
Tokenyou
Feature activation-0.223
Top resid features:
-
Token-
Feature activation-0.118
Top resid features:
up
Tokenup
Feature activation+0.000
Top resid features:
protein
Token protein
Feature activation+0.000
Top resid features:
website
Token website
Feature activation-0.033
Top resid features:
,
Token,
Feature activation-0.021
Top resid features:
be
Token be
Feature activation-0.027
Top resid features:
ready
Token ready
Feature activation-0.125
Top resid features:
to
Token to
Feature activation+0.023
Top resid features:
fill
Token fill
Feature activation+2.796
Top resid features:
your
Token your
Feature activation+0.164
Top resid features:
eyes
Token eyes
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
beauty
Token beauty
Feature activation+0.000
Top resid features:
Angeles
Token Angeles
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.057
Top resid features:
Rift
Token Rift
Feature activation-0.015
Top resid features:
headsets
Token headsets
Feature activation+0.004
Top resid features:
were
Token were
Feature activation+0.063
Top resid features:
filled
Token filled
Feature activation+2.709
Top resid features:
with
Token with
Feature activation+0.142
Top resid features:
the
Token the
Feature activation-0.134
Top resid features:
work
Token work
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
studios
Token studios
Feature activation+0.000
Top resid features:
large
Token large
Feature activation+0.045
Top resid features:
lump
Token lump
Feature activation+0.068
Top resid features:
under
Token under
Feature activation-0.026
Top resid features:
the
Token the
Feature activation+0.044
Top resid features:
skin
Token skin
Feature activation+0.193
Top resid features:
filled
Token filled
Feature activation+1.755
Top resid features:
with
Token with
Feature activation-0.020
Top resid features:
infected
Token infected
Feature activation+0.000
Top resid features:
fluids
Token fluids
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
If
Token If
Feature activation+0.000
Top resid features:
see
Token see
Feature activation+0.015
Top resid features:
who
Token who
Feature activation-0.024
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
selected
Token selected
Feature activation-0.026
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
fill
Token fill
Feature activation+2.308
Top resid features:
these
Token these
Feature activation+0.121
Top resid features:
jobs
Token jobs
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.043
Top resid features:
the
Token the
Feature activation-0.086
Top resid features:
bucket
Token bucket
Feature activation+0.051
Top resid features:
.
Token.
Feature activation+0.046
Top resid features:
Fill
Token Fill
Feature activation+2.311
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
bucket
Token bucket
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
water
Token water
Feature activation+0.000
Top resid features:
then
Token then
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Over
TokenOver
Feature activation-0.036
Top resid features:
decades
Token decades
Feature activation+0.043
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
we
Token we
Feature activation+0.044
Top resid features:
filled
Token filled
Feature activation+2.236
Top resid features:
many
Token many
Feature activation+0.078
Top resid features:
wetlands
Token wetlands
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
not
Token not
Feature activation-0.023
Top resid features:
be
Token be
Feature activation-0.011
Top resid features:
enough
Token enough
Feature activation-0.016
Top resid features:
fans
Token fans
Feature activation-0.103
Top resid features:
to
Token to
Feature activation+0.063
Top resid features:
fill
Token fill
Feature activation+2.474
Top resid features:
a
Token a
Feature activation-0.075
Top resid features:
40
Token 40
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
000
Token000
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
armed
Token armed
Feature activation-0.032
Top resid features:
forces
Token forces
Feature activation-0.014
Top resid features:
,
Token,
Feature activation-0.028
Top resid features:
trying
Token trying
Feature activation-0.003
Top resid features:
to
Token to
Feature activation-0.014
Top resid features:
fill
Token fill
Feature activation+2.382
Top resid features:
the
Token the
Feature activation-0.014
Top resid features:
gap
Token gap
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
special
Token special
Feature activation+0.000
Top resid features:
skills
Token skills
Feature activation+0.000
Top resid features:
discover
Token discover
Feature activation+0.055
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
world
Token world
Feature activation-0.021
Top resid features:
smaller
Token smaller
Feature activation-0.006
Top resid features:
and
Token and
Feature activation-0.083
Top resid features:
filled
Token filled
Feature activation+2.177
Top resid features:
with
Token with
Feature activation+0.029
Top resid features:
even
Token even
Feature activation+0.056
Top resid features:
more
Token more
Feature activation-0.106
Top resid features:
wonder
Token wonder
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.04

Head 3: 0.05

Head 4: 0.09

Head 5: 0.03

Head 6: 0.04

Head 7: 0.53

Head 8: 0.03

Head 9: 0.03

Head 10: 0.06

Head 11: 0.06

Positive logits

brim2.10

coffers1.64

ysis1.53

cubic1.51

dough1.51

pie1.46

yss1.44

crimson1.42

��極1.41

inn1.38

rette1.38

×1.36

vacancy1.35

dale1.34

grapes1.32

eyeb1.32

Kinn1.31

bil1.31

cub1.30

holes1.29

Negative logits

ilater-1.81

legality-1.72

orks-1.68

saf-1.60

origin-1.60

practice-1.57

nown-1.55

ursions-1.54

urtles-1.52

href-1.52

gradation-1.51

propagation-1.49

behaviours-1.48

istani-1.45

arians-1.45

laws-1.41

causation-1.40

effects-1.39

regulation-1.39

eworld-1.38

INTERVAL 3.046 - 3.385
CONTAINS 0.000%

have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
his
Token his
Feature activation+1.935
or
Token or
Feature activation+0.000
her
Token her
Feature activation+3.385
gasoline
Token gasoline
Feature activation+0.667
tank
Token tank
Feature activation+0.248
several
Token several
Feature activation+0.000
times
Token times
Feature activation+0.137
a
Token a
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
about
Token about
Feature activation+0.000
who
Token who
Feature activation+0.000
could
Token could
Feature activation+0.000
fill
Token fill
Feature activation+0.000
those
Token those
Feature activation+3.203
large
Token large
Feature activation+0.000
-
Token-
Feature activation+0.000
sized
Tokensized
Feature activation+0.000
luxury
Token luxury
Feature activation+0.000
loaf
Token loaf
Feature activation+0.000

INTERVAL 2.708 - 3.046
CONTAINS 0.000%

bucket
Token bucket
Feature activation+0.000
.
Token.
Feature activation+0.000
Fill
Token Fill
Feature activation+0.000
the
Token the
Feature activation+1.277
bucket
Token bucket
Feature activation+0.052
with
Token with
Feature activation+2.968
water
Token water
Feature activation+0.107
then
Token then
Feature activation+0.000
place
Token place
Feature activation+0.000
the
Token the
Feature activation+0.000
air
Token air
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
up
Token up
Feature activation+0.943
his
Token his
Feature activation+2.137
parents
Token parents
Feature activation+0.994
'
Token'
Feature activation+2.850
car
Token car
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
waited
Token waited
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 2.369 - 2.708
CONTAINS 0.000%

INTERVAL 2.031 - 2.369
CONTAINS 0.000%

Wednesday
Token Wednesday
Feature activation+0.000
looking
Token looking
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
up
Token up
Feature activation+0.943
his
Token his
Feature activation+2.137
parents
Token parents
Feature activation+0.994
'
Token'
Feature activation+2.850
car
Token car
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
dungeon
Token dungeon
Feature activation+0.000
craw
Token craw
Feature activation+0.000
ler
Tokenler
Feature activation+0.000
is
Token is
Feature activation+0.000
filled
Token filled
Feature activation+0.000
to
Token to
Feature activation+2.232
the
Token the
Feature activation+2.068
brim
Token brim
Feature activation+0.000
with
Token with
Feature activation+0.147
vast
Token vast
Feature activation+0.000
maps
Token maps
Feature activation+0.000
craw
Token craw
Feature activation+0.000
ler
Tokenler
Feature activation+0.000
is
Token is
Feature activation+0.000
filled
Token filled
Feature activation+0.000
to
Token to
Feature activation+2.232
the
Token the
Feature activation+2.068
brim
Token brim
Feature activation+0.000
with
Token with
Feature activation+0.147
vast
Token vast
Feature activation+0.000
maps
Token maps
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 1.692 - 2.031
CONTAINS 0.001%

sweetness
Token sweetness
Feature activation+0.000
and
Token and
Feature activation+0.000
fill
Token fill
Feature activation+0.000
-
Token-
Feature activation+0.000
you
Tokenyou
Feature activation+0.000
-
Token-
Feature activation+1.790
up
Tokenup
Feature activation+0.000
protein
Token protein
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
worker
Token worker
Feature activation+0.000
to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
his
Token his
Feature activation+1.935
or
Token or
Feature activation+0.000
her
Token her
Feature activation+3.385
gasoline
Token gasoline
Feature activation+0.667
tank
Token tank
Feature activation+0.248
several
Token several
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
filled
Token filled
Feature activation+0.133
with
Token with
Feature activation+0.121
a
Token a
Feature activation+1.832
mixture
Token mixture
Feature activation+0.000
of
Token of
Feature activation+0.000
dead
Token dead
Feature activation+0.000
weeds
Token weeds
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
be
Token be
Feature activation+0.000
ready
Token ready
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
your
Token your
Feature activation+1.777
eyes
Token eyes
Feature activation+0.456
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
beauty
Token beauty
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
voter
Token voter
Feature activation+0.000
had
Token had
Feature activation+0.000
filled
Token filled
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+1.802
bubbles
Token bubbles
Feature activation+0.000
next
Token next
Feature activation+0.000
to
Token to
Feature activation+0.000
both
Token both
Feature activation+0.000
candidates
Token candidates
Feature activation+0.000

INTERVAL 1.354 - 1.692
CONTAINS 0.000%

lump
Token lump
Feature activation+0.000
under
Token under
Feature activation+0.000
the
Token the
Feature activation+0.000
skin
Token skin
Feature activation+0.000
filled
Token filled
Feature activation+0.659
with
Token with
Feature activation+1.392
infected
Token infected
Feature activation+0.000
fluids
Token fluids
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
Rift
Token Rift
Feature activation+0.000
headsets
Token headsets
Feature activation+0.000
were
Token were
Feature activation+0.000
filled
Token filled
Feature activation+0.598
with
Token with
Feature activation+0.011
the
Token the
Feature activation+1.489
work
Token work
Feature activation+0.000
of
Token of
Feature activation+0.000
studios
Token studios
Feature activation+0.000
looking
Token looking
Feature activation+0.000
to
Token to
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
selected
Token selected
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
these
Token these
Feature activation+1.362
jobs
Token jobs
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
more
Token more
Feature activation+0.000

INTERVAL 1.015 - 1.354
CONTAINS 0.001%

forces
Token forces
Feature activation+0.000
,
Token,
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
the
Token the
Feature activation+1.171
gap
Token gap
Feature activation+0.000
in
Token in
Feature activation+0.000
special
Token special
Feature activation+0.000
skills
Token skills
Feature activation+0.000
that
Token that
Feature activation+0.000
operation
Token operation
Feature activation+0.000
,
Token,
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
filling
Token filling
Feature activation+0.000
this
Token this
Feature activation+1.022
critical
Token critical
Feature activation+0.239
gap
Token gap
Feature activation+0.000
in
Token in
Feature activation+0.000
education
Token education
Feature activation+0.000
access
Token access
Feature activation+0.000
Over
TokenOver
Feature activation+0.000
decades
Token decades
Feature activation+0.000
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
filled
Token filled
Feature activation+0.000
many
Token many
Feature activation+1.250
wetlands
Token wetlands
Feature activation+0.000
that
Token that
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
natural
Token natural
Feature activation+0.000
be
Token be
Feature activation+0.000
enough
Token enough
Feature activation+0.000
fans
Token fans
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
a
Token a
Feature activation+1.187
40
Token 40
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
-
Token-
Feature activation+0.000
seat
Tokenseat
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
flash
Token flash
Feature activation+0.000
drive
Token drive
Feature activation+0.000
filled
Token filled
Feature activation+0.316
with
Token with
Feature activation+1.036
information
Token information
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000

INTERVAL 0.677 - 1.015
CONTAINS 0.001%

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
have
Token have
Feature activation+0.000
books
Token books
Feature activation+0.000
filled
Token filled
Feature activation+0.000
with
Token with
Feature activation+0.698
transc
Token transc
Feature activation+0.000
ribed
Tokenribed
Feature activation+0.000
sol
Token sol
Feature activation+0.000
os
Tokenos
Feature activation+0.000
of
Token of
Feature activation+0.000
white
Token white
Feature activation+0.000
has
Token has
Feature activation+0.000
completely
Token completely
Feature activation+0.000
filled
Token filled
Feature activation+0.000
in
Token in
Feature activation+0.000
our
Token our
Feature activation+0.836
tracks
Token tracks
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
SD
Token SD
Feature activation+0.000
Card
Token Card
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
fill
Token fill
Feature activation+0.000
up
Token up
Feature activation+0.751
too
Token too
Feature activation+0.740
quickly
Token quickly
Feature activation+0.040
and
Token and
Feature activation+0.000
captures
Token captures
Feature activation+0.000
lots
Token lots
Feature activation+0.000
on
Token on
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
looking
Token looking
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
up
Token up
Feature activation+0.943
his
Token his
Feature activation+2.137
parents
Token parents
Feature activation+0.994
'
Token'
Feature activation+2.850
car
Token car
Feature activation+0.000
.
Token.
Feature activation+0.000
looking
Token looking
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
up
Token up
Feature activation+0.943
his
Token his
Feature activation+2.137
parents
Token parents
Feature activation+0.994
'
Token'
Feature activation+2.850
car
Token car
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
waited
Token waited
Feature activation+0.000

INTERVAL 0.338 - 0.677
CONTAINS 0.003%

be
Token be
Feature activation+0.000
ready
Token ready
Feature activation+0.000
to
Token to
Feature activation+0.000
fill
Token fill
Feature activation+0.000
your
Token your
Feature activation+1.777
eyes
Token eyes
Feature activation+0.456
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
beauty
Token beauty
Feature activation+0.000
of
Token of
Feature activation+0.000
nature
Token nature
Feature activation+0.000
folder
Token folder
Feature activation+0.000
should
Token should
Feature activation+0.000
now
Token now
Feature activation+0.000
be
Token be
Feature activation+0.000
flooded
Token flooded
Feature activation+0.422
by
Token by
Feature activation+0.571
sprite
Token sprite
Feature activation+0.000
files
Token files
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
which
Token which
Feature activation+0.000
were
Token were
Feature activation+0.000
being
Token being
Feature activation+0.000
pel
Token pel
Feature activation+0.000
ted
Tokented
Feature activation+0.262
with
Token with
Feature activation+0.467
ash
Token ash
Feature activation+0.000
and
Token and
Feature activation+0.000
acid
Token acid
Feature activation+0.000
rain
Token rain
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
basin
Token basin
Feature activation+0.000
has
Token has
Feature activation+0.000
filled
Token filled
Feature activation+0.000
in
Token in
Feature activation+0.000
with
Token with
Feature activation+0.355
water
Token water
Feature activation+0.033
to
Token to
Feature activation+0.445
form
Token form
Feature activation+0.000
a
Token a
Feature activation+0.000
prog
Token prog
Feature activation+0.000
pop
Token pop
Feature activation+0.000
ulates
Tokenulates
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
module
Token module
Feature activation+0.000
with
Token with
Feature activation+0.663
a
Token a
Feature activation+0.204
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
definitions
Token definitions
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.000 - 0.338
CONTAINS 99.994%

the
Token the
Feature activation+0.000
short
Token short
Feature activation+0.000
on
Token on
Feature activation+0.000
a
Token a
Feature activation+0.000
sho
Token sho
Feature activation+0.000
est
Tokenest
Feature activation+0.000
ring
Tokenring
Feature activation+0.000
budget
Token budget
Feature activation+0.000
,
Token,
Feature activation+0.000
hoping
Token hoping
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
All
TokenAll
Feature activation+0.000
you
Token you
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+0.000
this
Token this
Feature activation+0.000
guilt
Token guilt
Feature activation+0.000
-
Token-
Feature activation+0.000
free
Tokenfree
Feature activation+0.000
b
Token b
Feature activation+0.000
violate
Token violate
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
regulations
Token regulations
Feature activation+0.000
,
Token,
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
those
Token those
Feature activation+0.000
regarding
Token regarding
Feature activation+0.000
abusive
Token abusive
Feature activation+0.000
comment
Token comment
Feature activation+0.000
,
Token,
Feature activation+0.000
Asia
Token Asia
Feature activation+0.000
and
Token and
Feature activation+0.000
Africa
Token Africa
Feature activation+0.000
)
Token)
Feature activation+0.000
the
Token the
Feature activation+0.000
suffering
Token suffering
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
great
Token great
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
solar
Token solar
Feature activation+0.000
system
Token system
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
,
Token,
Feature activation+0.000
how
Token how
Feature activation+0.000
do
Token do
Feature activation+0.000
we
Token we
Feature activation+0.000
take
Token take
Feature activation+0.000
that
Token that
Feature activation+0.000
next
Token next
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 H5.7: (feature 26962)

TOP ACTIVATIONS
MAX = 5.500

to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
choice
Token choice
Feature activation+0.000
other
Token other
Feature activation+1.703
than
Token than
Feature activation+5.500
resort
Token resort
Feature activation+1.411
ing
Tokening
Feature activation+0.000
to
Token to
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
choice
Token choice
Feature activation+0.000
has
Token has
Feature activation+0.169
been
Token been
Feature activation+1.054
made
Token made
Feature activation+4.611
for
Token for
Feature activation+2.825
reasons
Token reasons
Feature activation+0.000
of
Token of
Feature activation+0.000
cost
Token cost
Feature activation+0.000
.
Token.
Feature activation+0.000
ÂŃ
TokenÂŃ
Feature activation+0.000
t
Tokent
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
the
Token the
Feature activation+0.000
choice
Token choice
Feature activation+0.000
of
Token of
Feature activation+4.503
delegates
Token delegates
Feature activation+0.000
to
Token to
Feature activation+0.000
international
Token international
Feature activation+0.000
conferences
Token conferences
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
your
Tokenyour
Feature activation+0.000
choices
Token choices
Feature activation+0.000
in
Token in
Feature activation+4.448
game
Token game
Feature activation+0.445
-
Token -
Feature activation+0.565
for
Token for
Feature activation+1.172
example
Token example
Feature activation+0.435
,
Token,
Feature activation+1.332
of
Token of
Feature activation+0.000
dict
Token dict
Feature activation+0.000
ating
Tokenating
Feature activation+0.000
their
Token their
Feature activation+0.000
choice
Token choice
Feature activation+0.000
of
Token of
Feature activation+4.382
marriage
Token marriage
Feature activation+0.106
partners
Token partners
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
city
Token city
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
made
Token made
Feature activation+0.000
the
Token the
Feature activation+0.000
unfortunate
Token unfortunate
Feature activation+0.000
choice
Token choice
Feature activation+1.180
of
Token of
Feature activation+3.849
plaster
Token plaster
Feature activation+0.000
ing
Tokening
Feature activation+0.000
each
Token each
Feature activation+0.000
box
Token box
Feature activation+0.000
with
Token with
Feature activation+0.000
choice
Token choice
Feature activation+0.000
has
Token has
Feature activation+0.136
never
Token never
Feature activation+0.538
been
Token been
Feature activation+2.969
clearer
Token clearer
Feature activation+0.000
-
Token -
Feature activation+3.834
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
calls
Token calls
Feature activation+0.000
on
Token on
Feature activation+0.000
us
Token us
Feature activation+0.000
's
Token's
Feature activation+0.000
influence
Token influence
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
choice
Token choice
Feature activation+0.000
of
Token of
Feature activation+3.707
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+0.000
gradually
Token gradually
Feature activation+0.000
declined
Token declined
Feature activation+0.000
over
Token over
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
had
Token had
Feature activation+0.000
little
Token little
Feature activation+0.000
choice
Token choice
Feature activation+0.535
but
Token but
Feature activation+3.703
to
Token to
Feature activation+2.252
remain
Token remain
Feature activation+0.759
.[
Token.[
Feature activation+0.000
8
Token8
Feature activation+0.000
]
Token]
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
ever
Token ever
Feature activation+1.720
made
Token made
Feature activation+3.497
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
all
Token all
Feature activation+0.000
that
Token that
Feature activation+0.000
she
Token she
Feature activation+0.000
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.000
but
Token but
Feature activation+3.493
to
Token to
Feature activation+1.806
to
Token to
Feature activation+0.379
go
Token go
Feature activation+1.577
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
felt
Token felt
Feature activation+0.000
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.000
but
Token but
Feature activation+3.247
to
Token to
Feature activation+1.773
remove
Token remove
Feature activation+0.000
him
Token him
Feature activation+0.000
from
Token from
Feature activation+0.000
his
Token his
Feature activation+0.000
can
Token can
Feature activation+0.000
compensate
Token compensate
Feature activation+0.000
for
Token for
Feature activation+0.000
local
Token local
Feature activation+0.000
choices
Token choices
Feature activation+0.000
of
Token of
Feature activation+3.176
homeowners
Token homeowners
Feature activation+0.427
.
Token.
Feature activation+0.000
Our
Token Our
Feature activation+0.000
work
Token work
Feature activation+0.000
suggests
Token suggests
Feature activation+0.000
no
Tokenno
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
choice
Token choice
Feature activation+0.000
of
Token of
Feature activation+3.148
the
Token the
Feature activation+1.267
next
Token next
Feature activation+0.009
B
Token B
Feature activation+0.000
achel
Tokenachel
Feature activation+0.000
oret
Tokenoret
Feature activation+0.000
.
Token.
Feature activation+0.000
The
TokenThe
Feature activation+0.000
choice
Token choice
Feature activation+0.000
has
Token has
Feature activation+0.136
never
Token never
Feature activation+0.538
been
Token been
Feature activation+2.969
clearer
Token clearer
Feature activation+0.000
-
Token -
Feature activation+3.834
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
calls
Token calls
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
choice
Token choice
Feature activation+0.000
for
Token for
Feature activation+2.888
science
Token science
Feature activation+0.252
adviser
Token adviser
Feature activation+0.000
should
Token should
Feature activation+0.000
be
Token be
Feature activation+0.000
confirmed
Token confirmed
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.038
other
Token other
Feature activation+1.092
than
Token than
Feature activation+2.876
copy
Token copy
Feature activation+0.137
past
Token past
Feature activation+0.000
ing
Tokening
Feature activation+0.000
code
Token code
Feature activation+0.000
and
Token and
Feature activation+0.000
The
TokenThe
Feature activation+0.000
choice
Token choice
Feature activation+0.000
has
Token has
Feature activation+0.169
been
Token been
Feature activation+1.054
made
Token made
Feature activation+4.611
for
Token for
Feature activation+2.825
reasons
Token reasons
Feature activation+0.000
of
Token of
Feature activation+0.000
cost
Token cost
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
that
Token that
Feature activation+0.000
Sweden
Token Sweden
Feature activation+0.000
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.099
but
Token but
Feature activation+2.773
to
Token to
Feature activation+1.067
enact
Token enact
Feature activation+0.000
the
Token the
Feature activation+0.000
controversial
Token controversial
Feature activation+0.000
regulation
Token regulation
Feature activation+0.000
name
Token name
Feature activation+0.000
stamp
Token stamp
Feature activation+0.000
with
Token with
Feature activation+0.000
your
Token your
Feature activation+0.000
choice
Token choice
Feature activation+0.000
of
Token of
Feature activation+2.658
unusual
Token unusual
Feature activation+0.000
animal
Token animal
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 6.501

are
Token are
Feature activation+0.027
Top resid features:
going
Token going
Feature activation-0.016
Top resid features:
to
Token to
Feature activation+0.041
Top resid features:
have
Token have
Feature activation+0.025
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
choice
Token choice
Feature activation+6.501
Top resid features:
other
Token other
Feature activation+0.183
Top resid features:
than
Token than
Feature activation+0.036
Top resid features:
resort
Token resort
Feature activation+0.000
Top resid features:
ing
Tokening
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.540
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
The
TokenThe
Feature activation-0.043
Top resid features:
choice
Token choice
Feature activation+5.674
Top resid features:
has
Token has
Feature activation+0.143
Top resid features:
been
Token been
Feature activation+0.007
Top resid features:
made
Token made
Feature activation-0.068
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
reasons
Token reasons
Feature activation+0.000
Top resid features:
ili
Tokenili
Feature activation-0.025
Top resid features:
ÂŃ
TokenÂŃ
Feature activation-0.006
Top resid features:
t
Tokent
Feature activation+0.002
Top resid features:
ate
Tokenate
Feature activation-0.060
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
choice
Token choice
Feature activation+5.514
Top resid features:
of
Token of
Feature activation+0.254
Top resid features:
delegates
Token delegates
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
international
Token international
Feature activation+0.000
Top resid features:
conferences
Token conferences
Feature activation+0.000
Top resid features:
goal
Token goal
Feature activation+0.066
Top resid features:
.
Token.
Feature activation+0.070
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
your
Tokenyour
Feature activation+0.145
Top resid features:
choices
Token choices
Feature activation+5.219
Top resid features:
in
Token in
Feature activation+0.054
Top resid features:
game
Token game
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
example
Token example
Feature activation+0.000
Top resid features:
point
Token point
Feature activation+0.004
Top resid features:
of
Token of
Feature activation-0.004
Top resid features:
dict
Token dict
Feature activation+0.043
Top resid features:
ating
Tokenating
Feature activation-0.006
Top resid features:
their
Token their
Feature activation+0.050
Top resid features:
choice
Token choice
Feature activation+5.267
Top resid features:
of
Token of
Feature activation+0.202
Top resid features:
marriage
Token marriage
Feature activation+0.000
Top resid features:
partners
Token partners
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:
s
Tokens
Feature activation+0.013
Top resid features:
marketing
Token marketing
Feature activation-0.034
Top resid features:
made
Token made
Feature activation-0.118
Top resid features:
the
Token the
Feature activation-0.075
Top resid features:
unfortunate
Token unfortunate
Feature activation+0.026
Top resid features:
choice
Token choice
Feature activation+5.040
Top resid features:
of
Token of
Feature activation+0.134
Top resid features:
plaster
Token plaster
Feature activation+0.000
Top resid features:
ing
Tokening
Feature activation+0.000
Top resid features:
each
Token each
Feature activation+0.000
Top resid features:
box
Token box
Feature activation+0.000
Top resid features:
gets
Token gets
Feature activation-0.005
Top resid features:
left
Token left
Feature activation-0.003
Top resid features:
behind
Token behind
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.084
Top resid features:
The
TokenThe
Feature activation-0.244
Top resid features:
choice
Token choice
Feature activation+4.969
Top resid features:
has
Token has
Feature activation+0.068
Top resid features:
never
Token never
Feature activation+0.041
Top resid features:
been
Token been
Feature activation+0.006
Top resid features:
clearer
Token clearer
Feature activation+0.032
Top resid features:
-
Token -
Feature activation+0.107
Top resid features:
sovereign
Token sovereign
Feature activation-0.038
Top resid features:
's
Token's
Feature activation-0.025
Top resid features:
influence
Token influence
Feature activation-0.236
Top resid features:
on
Token on
Feature activation+0.043
Top resid features:
the
Token the
Feature activation+0.048
Top resid features:
choice
Token choice
Feature activation+5.138
Top resid features:
of
Token of
Feature activation+0.234
Top resid features:
prime
Token prime
Feature activation+0.000
Top resid features:
minister
Token minister
Feature activation+0.000
Top resid features:
gradually
Token gradually
Feature activation+0.000
Top resid features:
declined
Token declined
Feature activation+0.000
Top resid features:
housing
Token housing
Feature activation-0.042
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
they
Token they
Feature activation-0.015
Top resid features:
had
Token had
Feature activation-0.055
Top resid features:
little
Token little
Feature activation-0.026
Top resid features:
choice
Token choice
Feature activation+4.915
Top resid features:
but
Token but
Feature activation+0.023
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
remain
Token remain
Feature activation+0.000
Top resid features:
.[
Token.[
Feature activation+0.000
Top resid features:
8
Token8
Feature activation+0.000
Top resid features:
beginning
Token beginning
Feature activation-0.020
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
re
Token re
Feature activation-0.002
Top resid features:
thinking
Tokenthinking
Feature activation-0.027
Top resid features:
every
Token every
Feature activation-0.054
Top resid features:
choice
Token choice
Feature activation+4.550
Top resid features:
I
Token I
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.080
Top resid features:
Ļ
TokenĻ
Feature activation+0.032
Top resid features:
ve
Tokenve
Feature activation+0.040
Top resid features:
ever
Token ever
Feature activation+0.022
Top resid features:
traditions
Token traditions
Feature activation+0.005
Top resid features:
that
Token that
Feature activation+0.016
Top resid features:
she
Token she
Feature activation+0.002
Top resid features:
had
Token had
Feature activation-0.065
Top resid features:
no
Token no
Feature activation-0.003
Top resid features:
choice
Token choice
Feature activation+4.620
Top resid features:
but
Token but
Feature activation+0.043
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
go
Token go
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
I
Token I
Feature activation-0.028
Top resid features:
felt
Token felt
Feature activation-0.081
Top resid features:
I
Token I
Feature activation+0.035
Top resid features:
had
Token had
Feature activation-0.010
Top resid features:
no
Token no
Feature activation-0.005
Top resid features:
choice
Token choice
Feature activation+4.464
Top resid features:
but
Token but
Feature activation+0.064
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
remove
Token remove
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
dynamics
Token dynamics
Feature activation-0.014
Top resid features:
can
Token can
Feature activation+0.013
Top resid features:
compensate
Token compensate
Feature activation-0.012
Top resid features:
for
Token for
Feature activation-0.015
Top resid features:
local
Token local
Feature activation-0.014
Top resid features:
choices
Token choices
Feature activation+4.373
Top resid features:
of
Token of
Feature activation+0.031
Top resid features:
homeowners
Token homeowners
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Our
Token Our
Feature activation+0.000
Top resid features:
work
Token work
Feature activation+0.000
Top resid features:
ok
Tokenok
Feature activation+0.001
Top resid features:
no
Tokenno
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
The
TokenThe
Feature activation+0.005
Top resid features:
choice
Token choice
Feature activation+4.060
Top resid features:
of
Token of
Feature activation+0.275
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
B
Token B
Feature activation+0.000
Top resid features:
achel
Tokenachel
Feature activation+0.000
Top resid features:
gets
Token gets
Feature activation-0.013
Top resid features:
left
Token left
Feature activation-0.006
Top resid features:
behind
Token behind
Feature activation-0.008
Top resid features:
.
Token.
Feature activation+0.073
Top resid features:
The
TokenThe
Feature activation-0.074
Top resid features:
choice
Token choice
Feature activation+3.780
Top resid features:
has
Token has
Feature activation+0.089
Top resid features:
never
Token never
Feature activation+0.080
Top resid features:
been
Token been
Feature activation+0.057
Top resid features:
clearer
Token clearer
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
?
Token?
Feature activation+0.087
Top resid features:
Trump
Token Trump
Feature activation-0.078
Top resid features:
âĢ
TokenâĢ
Feature activation-0.056
Top resid features:
Ļ
TokenĻ
Feature activation+0.004
Top resid features:
s
Tokens
Feature activation+0.061
Top resid features:
choice
Token choice
Feature activation+4.109
Top resid features:
for
Token for
Feature activation+0.363
Top resid features:
science
Token science
Feature activation+0.000
Top resid features:
adviser
Token adviser
Feature activation+0.000
Top resid features:
should
Token should
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
now
Token now
Feature activation+0.053
Top resid features:
you
Token you
Feature activation+0.008
Top resid features:
have
Token have
Feature activation+0.092
Top resid features:
no
Token no
Feature activation+0.010
Top resid features:
choice
Token choice
Feature activation+4.081
Top resid features:
other
Token other
Feature activation-0.034
Top resid features:
than
Token than
Feature activation-0.109
Top resid features:
copy
Token copy
Feature activation+0.000
Top resid features:
past
Token past
Feature activation+0.000
Top resid features:
ing
Tokening
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.443
Top resid features:
.
Token.
Feature activation-0.033
Top resid features:
Ċ
TokenĊ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.014
Top resid features:
The
TokenThe
Feature activation-0.039
Top resid features:
choice
Token choice
Feature activation+3.713
Top resid features:
has
Token has
Feature activation+0.153
Top resid features:
been
Token been
Feature activation-0.005
Top resid features:
made
Token made
Feature activation-0.072
Top resid features:
for
Token for
Feature activation+0.134
Top resid features:
reasons
Token reasons
Feature activation+0.000
Top resid features:
stressed
Token stressed
Feature activation-0.029
Top resid features:
that
Token that
Feature activation-0.032
Top resid features:
Sweden
Token Sweden
Feature activation-0.009
Top resid features:
had
Token had
Feature activation-0.048
Top resid features:
no
Token no
Feature activation-0.008
Top resid features:
choice
Token choice
Feature activation+4.078
Top resid features:
but
Token but
Feature activation+0.065
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
enact
Token enact
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
controversial
Token controversial
Feature activation+0.000
Top resid features:
o
Tokeno
Feature activation-0.023
Top resid features:
name
Token name
Feature activation+0.023
Top resid features:
stamp
Token stamp
Feature activation-0.106
Top resid features:
with
Token with
Feature activation+0.037
Top resid features:
your
Token your
Feature activation+0.011
Top resid features:
choice
Token choice
Feature activation+3.870
Top resid features:
of
Token of
Feature activation+0.036
Top resid features:
unusual
Token unusual
Feature activation+0.000
Top resid features:
animal
Token animal
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.01

Head 2: 0.05

Head 3: 0.05

Head 4: 0.09

Head 5: 0.04

Head 6: 0.05

Head 7: 0.53

Head 8: 0.03

Head 9: 0.02

Head 10: 0.07

Head 11: 0.05

Positive logits

choices2.21

choose1.98

choosing1.92

options1.89

Option1.88

option1.86

chooses1.82

chose1.82

龍�1.73

choice1.70

menus1.65

selecting1.64

prioritize1.64

CHO1.63

abst1.61

otom1.60

discard1.56

default1.56

Choose1.53

deciding1.52

Negative logits

Improvements-1.71

amation-1.67

urance-1.62

Lat-1.59

Improved-1.57

borough-1.52

issance-1.51

Improve-1.47

IRT-1.45

warming-1.43

idation-1.43

Ho-1.40

iminary-1.38

Prague-1.37

olerance-1.37

Stat-1.36

growth-1.36

Fraud-1.35

Critical-1.35

icum-1.35

INTERVAL 4.950 - 5.500
CONTAINS 0.000%

to
Token to
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
choice
Token choice
Feature activation+0.000
other
Token other
Feature activation+1.703
than
Token than
Feature activation+5.500
resort
Token resort
Feature activation+1.411
ing
Tokening
Feature activation+0.000
to
Token to
Feature activation+0.000
going
Token going
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 4.400 - 4.950
CONTAINS 0.000%

ÂŃ
TokenÂŃ
Feature activation+0.000
t
Tokent
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
the
Token the
Feature activation+0.000
choice
Token choice
Feature activation+0.000
of
Token of
Feature activation+4.503
delegates
Token delegates
Feature activation+0.000
to
Token to
Feature activation+0.000
international
Token international
Feature activation+0.000
conferences
Token conferences
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
your
Tokenyour
Feature activation+0.000
choices
Token choices
Feature activation+0.000
in
Token in
Feature activation+4.448
game
Token game
Feature activation+0.445
-
Token -
Feature activation+0.565
for
Token for
Feature activation+1.172
example
Token example
Feature activation+0.435
,
Token,
Feature activation+1.332
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
choice
Token choice
Feature activation+0.000
has
Token has
Feature activation+0.169
been
Token been
Feature activation+1.054
made
Token made
Feature activation+4.611
for
Token for
Feature activation+2.825
reasons
Token reasons
Feature activation+0.000
of
Token of
Feature activation+0.000
cost
Token cost
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 3.850 - 4.400
CONTAINS 0.000%

of
Token of
Feature activation+0.000
dict
Token dict
Feature activation+0.000
ating
Tokenating
Feature activation+0.000
their
Token their
Feature activation+0.000
choice
Token choice
Feature activation+0.000
of
Token of
Feature activation+4.382
marriage
Token marriage
Feature activation+0.106
partners
Token partners
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
city
Token city
Feature activation+0.000

INTERVAL 3.300 - 3.850
CONTAINS 0.001%

's
Token's
Feature activation+0.000
influence
Token influence
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
choice
Token choice
Feature activation+0.000
of
Token of
Feature activation+3.707
prime
Token prime
Feature activation+0.000
minister
Token minister
Feature activation+0.000
gradually
Token gradually
Feature activation+0.000
declined
Token declined
Feature activation+0.000
over
Token over
Feature activation+0.000
that
Token that
Feature activation+0.000
she
Token she
Feature activation+0.000
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.000
but
Token but
Feature activation+3.493
to
Token to
Feature activation+1.806
to
Token to
Feature activation+0.379
go
Token go
Feature activation+1.577
to
Token to
Feature activation+0.000
work
Token work
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
ever
Token ever
Feature activation+1.720
made
Token made
Feature activation+3.497
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
all
Token all
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
had
Token had
Feature activation+0.000
little
Token little
Feature activation+0.000
choice
Token choice
Feature activation+0.535
but
Token but
Feature activation+3.703
to
Token to
Feature activation+2.252
remain
Token remain
Feature activation+0.759
.[
Token.[
Feature activation+0.000
8
Token8
Feature activation+0.000
]
Token]
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
made
Token made
Feature activation+0.000
the
Token the
Feature activation+0.000
unfortunate
Token unfortunate
Feature activation+0.000
choice
Token choice
Feature activation+1.180
of
Token of
Feature activation+3.849
plaster
Token plaster
Feature activation+0.000
ing
Tokening
Feature activation+0.000
each
Token each
Feature activation+0.000
box
Token box
Feature activation+0.000
with
Token with
Feature activation+0.000

INTERVAL 2.750 - 3.300
CONTAINS 0.001%

no
Tokenno
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
choice
Token choice
Feature activation+0.000
of
Token of
Feature activation+3.148
the
Token the
Feature activation+1.267
next
Token next
Feature activation+0.009
B
Token B
Feature activation+0.000
achel
Tokenachel
Feature activation+0.000
oret
Tokenoret
Feature activation+0.000
.
Token.
Feature activation+0.000
The
TokenThe
Feature activation+0.000
choice
Token choice
Feature activation+0.000
has
Token has
Feature activation+0.136
never
Token never
Feature activation+0.538
been
Token been
Feature activation+2.969
clearer
Token clearer
Feature activation+0.000
-
Token -
Feature activation+3.834
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
calls
Token calls
Feature activation+0.000
that
Token that
Feature activation+0.000
Sweden
Token Sweden
Feature activation+0.000
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.099
but
Token but
Feature activation+2.773
to
Token to
Feature activation+1.067
enact
Token enact
Feature activation+0.000
the
Token the
Feature activation+0.000
controversial
Token controversial
Feature activation+0.000
regulation
Token regulation
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.038
other
Token other
Feature activation+1.092
than
Token than
Feature activation+2.876
copy
Token copy
Feature activation+0.137
past
Token past
Feature activation+0.000
ing
Tokening
Feature activation+0.000
code
Token code
Feature activation+0.000
and
Token and
Feature activation+0.000
The
TokenThe
Feature activation+0.000
choice
Token choice
Feature activation+0.000
has
Token has
Feature activation+0.169
been
Token been
Feature activation+1.054
made
Token made
Feature activation+4.611
for
Token for
Feature activation+2.825
reasons
Token reasons
Feature activation+0.000
of
Token of
Feature activation+0.000
cost
Token cost
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000

INTERVAL 2.200 - 2.750
CONTAINS 0.001%

name
Token name
Feature activation+0.000
stamp
Token stamp
Feature activation+0.000
with
Token with
Feature activation+0.000
your
Token your
Feature activation+0.000
choice
Token choice
Feature activation+0.000
of
Token of
Feature activation+2.658
unusual
Token unusual
Feature activation+0.000
animal
Token animal
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
moment
Token moment
Feature activation+0.000
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
choice
Token choice
Feature activation+0.282
about
Token about
Feature activation+2.527
who
Token who
Feature activation+1.343
I
Token I
Feature activation+0.122
am
Token am
Feature activation+0.449
becoming
Token becoming
Feature activation+0.000
.
Token.
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000
historic
Tokenhistoric
Feature activation+0.000
choice
Token choice
Feature activation+0.000
"
Token"
Feature activation+2.534
facing
Token facing
Feature activation+0.381
them
Token them
Feature activation+0.434
on
Token on
Feature activation+0.296
Thursday
Token Thursday
Feature activation+0.000
,
Token,
Feature activation+0.000
my
Token my
Feature activation+0.000
choice
Token choice
Feature activation+0.000
a
Token a
Feature activation+0.172
while
Token while
Feature activation+0.000
ago
Token ago
Feature activation+0.017
.
Token.
Feature activation+2.519
Didn
Token Didn
Feature activation+1.812
't
Token't
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
influence
Token influence
Feature activation+0.000
ax
Tokenax
Feature activation+0.000
am
Tokenam
Feature activation+0.000
ites
Tokenites
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.000
but
Token but
Feature activation+2.596
to
Token to
Feature activation+0.715
leave
Token leave
Feature activation+0.000
or
Token or
Feature activation+0.000
die
Token die
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.650 - 2.200
CONTAINS 0.002%

going
Token going
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
choice
Token choice
Feature activation+0.000
other
Token other
Feature activation+1.703
than
Token than
Feature activation+5.500
resort
Token resort
Feature activation+1.411
ing
Tokening
Feature activation+0.000
to
Token to
Feature activation+0.000
going
Token going
Feature activation+0.000
been
Token been
Feature activation+0.000
the
Token the
Feature activation+0.000
better
Token better
Feature activation+0.000
choice
Token choice
Feature activation+0.000
here
Token here
Feature activation+0.045
to
Token to
Feature activation+1.730
replace
Token replace
Feature activation+0.000
MS
Token MS
Feature activation+0.000
Office
Token Office
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
and
Token and
Feature activation+0.000
empower
Token empower
Feature activation+0.000
individuals
Token individuals
Feature activation+0.000
to
Token to
Feature activation+0.000
choose
Token choose
Feature activation+0.000
their
Token their
Feature activation+1.893
own
Token own
Feature activation+0.448
security
Token security
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
choice
Token choice
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
ever
Token ever
Feature activation+1.720
made
Token made
Feature activation+3.497
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
choice
Token choice
Feature activation+0.000
a
Token a
Feature activation+0.172
while
Token while
Feature activation+0.000
ago
Token ago
Feature activation+0.017
.
Token.
Feature activation+2.519
Didn
Token Didn
Feature activation+1.812
't
Token't
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
influence
Token influence
Feature activation+0.000
your
Token your
Feature activation+0.000

INTERVAL 1.100 - 1.650
CONTAINS 0.003%

s
Tokens
Feature activation+0.000
marketing
Token marketing
Feature activation+0.000
made
Token made
Feature activation+0.000
the
Token the
Feature activation+0.000
unfortunate
Token unfortunate
Feature activation+0.000
choice
Token choice
Feature activation+1.180
of
Token of
Feature activation+3.849
plaster
Token plaster
Feature activation+0.000
ing
Tokening
Feature activation+0.000
each
Token each
Feature activation+0.000
box
Token box
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
the
Token the
Feature activation+0.000
top
Token top
Feature activation+0.000
choice
Token choice
Feature activation+0.000
for
Token for
Feature activation+1.164
Western
Token Western
Feature activation+0.000
couples
Token couples
Feature activation+0.000
looking
Token looking
Feature activation+0.000
for
Token for
Feature activation+0.000
value
Token value
Feature activation+0.000
or
Token or
Feature activation+0.000
one
Token one
Feature activation+0.000
-
Token-
Feature activation+0.000
off
Tokenoff
Feature activation+0.000
decisions
Token decisions
Feature activation+0.000
to
Token to
Feature activation+1.154
invest
Token invest
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
home
Token home
Feature activation+0.000
away
Token away
Feature activation+0.000
faced
Token faced
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
monumental
Token monumental
Feature activation+0.000
decision
Token decision
Feature activation+0.000
:
Token:
Feature activation+1.568
What
Token What
Feature activation+1.395
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
at
Token at
Feature activation+0.000
quarterback
Token quarterback
Feature activation+0.000
the
Token the
Feature activation+0.000
numerical
Token numerical
Feature activation+0.000
method
Token method
Feature activation+0.000
of
Token of
Feature activation+0.000
choice
Token choice
Feature activation+0.000
for
Token for
Feature activation+1.512
this
Token this
Feature activation+1.190
study
Token study
Feature activation+0.844
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.550 - 1.100
CONTAINS 0.006%

is
Token is
Feature activation+0.000
ultimately
Token ultimately
Feature activation+0.000
he
Token he
Feature activation+0.000
who
Token who
Feature activation+0.000
chooses
Token chooses
Feature activation+0.000
the
Token the
Feature activation+0.589
measure
Token measure
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
simultaneously
Token simultaneously
Feature activation+0.000
supernatural
Token supernatural
Feature activation+0.000
R
TokenR
Feature activation+0.000
is
Token is
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
for
Token for
Feature activation+0.916
you
Token you
Feature activation+0.744
,
Token,
Feature activation+0.000
here
Token here
Feature activation+0.000
are
Token are
Feature activation+0.000
top
Token top
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
The
TokenThe
Feature activation+0.000
party
Token party
Feature activation+0.000
chooses
Token chooses
Feature activation+0.000
its
Token its
Feature activation+0.586
representative
Token representative
Feature activation+0.000
and
Token and
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
instance
Token instance
Feature activation+0.000
now
Token now
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
no
Token no
Feature activation+0.000
choice
Token choice
Feature activation+0.038
other
Token other
Feature activation+1.092
than
Token than
Feature activation+2.876
copy
Token copy
Feature activation+0.137
past
Token past
Feature activation+0.000
ing
Tokening
Feature activation+0.000
code
Token code
Feature activation+0.000
from
Token from
Feature activation+0.000
?
Token?
Feature activation+0.000
If
Token If
Feature activation+0.000
your
Token your
Feature activation+0.000
options
Token options
Feature activation+0.000
were
Token were
Feature activation+0.810
a
Token a
Feature activation+0.585
Harvard
Token Harvard
Feature activation+0.000
graduate
Token graduate
Feature activation+0.000
who
Token who
Feature activation+0.030
has
Token has
Feature activation+0.000

INTERVAL 0.000 - 0.550
CONTAINS 99.986%

of
Token of
Feature activation+0.000
fame
Token fame
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
approach
Token approach
Feature activation+0.000
ability
Tokenability
Feature activation+0.000
.
Token.
Feature activation+0.000
When
Token When
Feature activation+0.000
we
Token we
Feature activation+0.000
did
Token did
Feature activation+0.000
get
Token get
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
Minister
Token Minister
Feature activation+0.000
for
Token for
Feature activation+0.000
Major
Token Major
Feature activation+0.000
Projects
Token Projects
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
Fletcher
Token Fletcher
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
's
Token's
Feature activation+0.000
show
Token show
Feature activation+0.000
garnered
Token garnered
Feature activation+0.000
just
Token just
Feature activation+0.000
3
Token 3
Feature activation+0.000
.
Token.
Feature activation+0.000
17
Token17
Feature activation+0.000
million
Token million
Feature activation+0.000
viewers
Token viewers
Feature activation+0.000
,
Token,
Feature activation+0.000
down
Token down
Feature activation+0.000
Despite
Token Despite
Feature activation+0.000
those
Token those
Feature activation+0.000
setbacks
Token setbacks
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
or
Token or
Feature activation+0.000
perhaps
Token perhaps
Feature activation+0.000
to
Token to
Feature activation+0.000
spite
Token spite
Feature activation+0.000
them
Token them
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
yesterday
Token yesterday
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Americans
TokenAmericans
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
and
Tokenand
Feature activation+0.000
Filip
Token Filip
Feature activation+0.000
inos
Tokeninos
Feature activation+0.000
by
Token by
Feature activation+0.000
extension
Token extension
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
sn
Tokensn
Feature activation+0.000
ip
Tokenip
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 H5.7: (feature 22929)

TOP ACTIVATIONS
MAX = 4.734

,
Token,
Feature activation+0.000
whether
Token whether
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
true
Token true
Feature activation+0.946
that
Token that
Feature activation+4.734
a
Token a
Feature activation+0.000
senior
Token senior
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
bishop
Token bishop
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
True
TokenTrue
Feature activation+0.000
to
Token to
Feature activation+3.281
his
Token his
Feature activation+3.658
style
Token style
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
uses
Token uses
Feature activation+0.000
charts
Token charts
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
true
Token true
Feature activation+0.000
for
Token for
Feature activation+0.000
years
Token years
Feature activation+0.000
that
Token that
Feature activation+3.616
things
Token things
Feature activation+0.000
worked
Token worked
Feature activation+0.000
fine
Token fine
Feature activation+0.000
under
Token under
Feature activation+0.000
that
Token that
Feature activation+0.000
last
Token last
Feature activation+0.000
night
Token night
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
true
Token true
Feature activation+0.000
that
Token that
Feature activation+3.296
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
motivated
Token motivated
Feature activation+0.000
by
Token by
Feature activation+0.000
religious
Token religious
Feature activation+0.000
country
Token country
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
True
TokenTrue
Feature activation+0.000
to
Token to
Feature activation+3.281
his
Token his
Feature activation+3.658
style
Token style
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
uses
Token uses
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
While
Token While
Feature activation+0.000
true
Token true
Feature activation+0.000
to
Token to
Feature activation+2.903
some
Token some
Feature activation+1.674
extent
Token extent
Feature activation+0.091
,
Token,
Feature activation+0.422
Mart
Token Mart
Feature activation+0.000
os
Tokenos
Feature activation+0.000
sh
Token sh
Feature activation+0.000
ambling
Tokenambling
Feature activation+0.000
quality
Token quality
Feature activation+0.000
is
Token is
Feature activation+0.000
true
Token true
Feature activation+0.000
to
Token to
Feature activation+2.200
Harry
Token Harry
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
urban
Token urban
Feature activation+0.000
religions
Token religions
Feature activation+0.000
are
Token are
Feature activation+0.000
sort
Token sort
Feature activation+0.000
of
Token of
Feature activation+0.000
true
Token true
Feature activation+0.000
in
Token in
Feature activation+1.800
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
way
Token way
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
While
Token While
Feature activation+0.000
true
Token true
Feature activation+0.000
to
Token to
Feature activation+2.903
some
Token some
Feature activation+1.674
extent
Token extent
Feature activation+0.091
,
Token,
Feature activation+0.422
Mart
Token Mart
Feature activation+0.000
os
Tokenos
Feature activation+0.000
ko
Tokenko
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
true
Token true
Feature activation+0.151
that
Token that
Feature activation+1.412
P
Token P
Feature activation+0.000
(
Token(
Feature activation+0.000
~
Token~
Feature activation+0.000
E
TokenE
Feature activation+0.000
|
Token|
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
never
Token never
Feature activation+0.000
lost
Token lost
Feature activation+0.000
sight
Token sight
Feature activation+0.000
of
Token of
Feature activation+1.272
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
the
Token the
Feature activation+0.000
Commissioner
Token Commissioner
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ren
TokenRen
Feature activation+0.000
ew
Tokenew
Feature activation+0.000
ed
Tokened
Feature activation+1.048
questions
Token questions
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
raised
Token raised
Feature activation+0.000
over
Token over
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ren
TokenRen
Feature activation+0.000
ew
Tokenew
Feature activation+0.000
ed
Tokened
Feature activation+1.036
calls
Token calls
Feature activation+0.000
for
Token for
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Says
Token Says
Feature activation+0.000
its
Token its
Feature activation+0.000
true
Token true
Feature activation+0.000
the
Token the
Feature activation+1.003
other
Token other
Feature activation+0.000
way
Token way
Feature activation+0.000
too
Token too
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
)
Token)
Feature activation+0.000
This
Token This
Feature activation+0.000
downtown
Token downtown
Feature activation+0.000
o
Token o
Feature activation+0.000
de
Tokende
Feature activation+0.354
to
Token to
Feature activation+0.988
pig
Token pig
Feature activation+0.000
parts
Token parts
Feature activation+0.000
offers
Token offers
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
es
Tokenes
Feature activation+0.000
,
Token,
Feature activation+0.000
whether
Token whether
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
true
Token true
Feature activation+0.946
that
Token that
Feature activation+4.734
a
Token a
Feature activation+0.000
senior
Token senior
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
bishop
Token bishop
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
truth
Token truth
Feature activation+0.000
to
Token to
Feature activation+0.746
the
Token the
Feature activation+0.823
charges
Token charges
Feature activation+0.000
I
Token I
Feature activation+0.000
benefited
Token benefited
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
ev
Tokenev
Feature activation+0.000
ich
Tokenich
Feature activation+0.000
makes
Token makes
Feature activation+0.000
no
Token no
Feature activation+0.000
bones
Token bones
Feature activation+0.000
about
Token about
Feature activation+0.813
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.411
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
care
Token care
Feature activation+0.000
.
Token.
Feature activation+0.000
Small
Token Small
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.800
,
Token,
Feature activation+0.000
Jackson
Token Jackson
Feature activation+0.000
really
Token really
Feature activation+0.000
is
Token is
Feature activation+0.000
big
Token big
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
truth
Token truth
Feature activation+0.000
to
Token to
Feature activation+0.746
the
Token the
Feature activation+0.823
charges
Token charges
Feature activation+0.000
I
Token I
Feature activation+0.000
benefited
Token benefited
Feature activation+0.000
from
Token from
Feature activation+0.000

Top DFA by src position
MAX = 6.409

es
Tokenes
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
whether
Token whether
Feature activation-0.045
Top resid features:
it
Token it
Feature activation+0.084
Top resid features:
was
Token was
Feature activation+0.135
Top resid features:
true
Token true
Feature activation+6.409
Top resid features:
that
Token that
Feature activation+0.304
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
senior
Token senior
Feature activation+0.000
Top resid features:
Russian
Token Russian
Feature activation+0.000
Top resid features:
bishop
Token bishop
Feature activation+0.000
Top resid features:
our
Token our
Feature activation-0.004
Top resid features:
country
Token country
Feature activation-0.005
Top resid features:
."
Token."
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.023
Top resid features:
Ċ
TokenĊ
Feature activation-0.022
Top resid features:
True
TokenTrue
Feature activation+5.022
Top resid features:
to
Token to
Feature activation+0.346
Top resid features:
his
Token his
Feature activation+0.139
Top resid features:
style
Token style
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
even
Token even
Feature activation+0.027
Top resid features:
though
Token though
Feature activation+0.194
Top resid features:
it
Token it
Feature activation+0.082
Top resid features:
was
Token was
Feature activation+0.132
Top resid features:
true
Token true
Feature activation+5.057
Top resid features:
for
Token for
Feature activation+0.417
Top resid features:
years
Token years
Feature activation-0.050
Top resid features:
that
Token that
Feature activation+0.070
Top resid features:
things
Token things
Feature activation+0.000
Top resid features:
worked
Token worked
Feature activation+0.000
Top resid features:
Cloud
Token Cloud
Feature activation+0.002
Top resid features:
last
Token last
Feature activation+0.020
Top resid features:
night
Token night
Feature activation+0.008
Top resid features:
.
Token.
Feature activation+0.111
Top resid features:
If
Token If
Feature activation+0.347
Top resid features:
true
Token true
Feature activation+4.790
Top resid features:
that
Token that
Feature activation+0.400
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
motivated
Token motivated
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
our
Token our
Feature activation+0.003
Top resid features:
country
Token country
Feature activation+0.001
Top resid features:
."
Token."
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.031
Top resid features:
Ċ
TokenĊ
Feature activation-0.030
Top resid features:
True
TokenTrue
Feature activation+4.820
Top resid features:
to
Token to
Feature activation+0.116
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
style
Token style
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
road
Token road
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.059
Top resid features:
âĢ
TokenâĢ
Feature activation+0.029
Top resid features:
Ŀ
TokenĿ
Feature activation+0.016
Top resid features:
While
Token While
Feature activation+0.111
Top resid features:
true
Token true
Feature activation+4.494
Top resid features:
to
Token to
Feature activation+0.137
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
extent
Token extent
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Mart
Token Mart
Feature activation+0.000
Top resid features:
Its
Token Its
Feature activation+0.076
Top resid features:
sh
Token sh
Feature activation-0.009
Top resid features:
ambling
Tokenambling
Feature activation-0.008
Top resid features:
quality
Token quality
Feature activation-0.049
Top resid features:
is
Token is
Feature activation+0.067
Top resid features:
true
Token true
Feature activation+3.659
Top resid features:
to
Token to
Feature activation+0.269
Top resid features:
Harry
Token Harry
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
all
Tokenall
Feature activation+0.025
Top resid features:
religions
Token religions
Feature activation-0.048
Top resid features:
are
Token are
Feature activation+0.081
Top resid features:
sort
Token sort
Feature activation-0.065
Top resid features:
of
Token of
Feature activation+0.069
Top resid features:
true
Token true
Feature activation+3.561
Top resid features:
in
Token in
Feature activation+0.324
Top resid features:
their
Token their
Feature activation+0.000
Top resid features:
own
Token own
Feature activation+0.000
Top resid features:
way
Token way
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
road
Token road
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.097
Top resid features:
âĢ
TokenâĢ
Feature activation+0.019
Top resid features:
Ŀ
TokenĿ
Feature activation+0.021
Top resid features:
While
Token While
Feature activation+0.134
Top resid features:
true
Token true
Feature activation+3.473
Top resid features:
to
Token to
Feature activation+0.315
Top resid features:
some
Token some
Feature activation+0.035
Top resid features:
extent
Token extent
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Mart
Token Mart
Feature activation+0.000
Top resid features:
case
Token case
Feature activation+0.062
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
it
Token it
Feature activation+0.095
Top resid features:
is
Token is
Feature activation+0.045
Top resid features:
also
Token also
Feature activation+0.215
Top resid features:
true
Token true
Feature activation+2.557
Top resid features:
that
Token that
Feature activation+0.303
Top resid features:
P
Token P
Feature activation+0.000
Top resid features:
(
Token(
Feature activation+0.000
Top resid features:
~
Token~
Feature activation+0.000
Top resid features:
E
TokenE
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.018
Top resid features:
Ļ
TokenĻ
Feature activation-0.008
Top resid features:
ve
Tokenve
Feature activation+0.043
Top resid features:
never
Token never
Feature activation+0.049
Top resid features:
lost
Token lost
Feature activation+0.007
Top resid features:
sight
Token sight
Feature activation+3.863
Top resid features:
of
Token of
Feature activation-0.495
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
think
Token think
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
view
Token view
Feature activation-0.015
Top resid features:
."
Token."
Feature activation+0.071
Top resid features:
Ċ
TokenĊ
Feature activation-0.053
Top resid features:
Ċ
TokenĊ
Feature activation-0.058
Top resid features:
Ren
TokenRen
Feature activation+0.119
Top resid features:
ew
Tokenew
Feature activation+3.249
Top resid features:
ed
Tokened
Feature activation-0.265
Top resid features:
questions
Token questions
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
raised
Token raised
Feature activation+0.000
Top resid features:
campaign
Token campaign
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.068
Top resid features:
Ċ
TokenĊ
Feature activation-0.038
Top resid features:
Ċ
TokenĊ
Feature activation-0.017
Top resid features:
Ren
TokenRen
Feature activation+0.074
Top resid features:
ew
Tokenew
Feature activation+3.446
Top resid features:
ed
Tokened
Feature activation-0.329
Top resid features:
calls
Token calls
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Clinton
Token Clinton
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Mexican
Token Mexican
Feature activation+0.069
Top resid features:
âĢ
TokenâĢ
Feature activation+0.013
Top resid features:
Ŀ
TokenĿ
Feature activation+0.012
Top resid features:
Says
Token Says
Feature activation+0.038
Top resid features:
its
Token its
Feature activation-0.003
Top resid features:
true
Token true
Feature activation+2.645
Top resid features:
the
Token the
Feature activation+0.147
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
way
Token way
Feature activation+0.000
Top resid features:
too
Token too
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
above
Token above
Feature activation-0.014
Top resid features:
)
Token)
Feature activation-0.007
Top resid features:
This
Token This
Feature activation+0.060
Top resid features:
downtown
Token downtown
Feature activation-0.224
Top resid features:
o
Token o
Feature activation-0.071
Top resid features:
de
Tokende
Feature activation+3.203
Top resid features:
to
Token to
Feature activation+0.021
Top resid features:
pig
Token pig
Feature activation+0.000
Top resid features:
parts
Token parts
Feature activation+0.000
Top resid features:
offers
Token offers
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
es
Tokenes
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.019
Top resid features:
whether
Token whether
Feature activation-0.083
Top resid features:
it
Token it
Feature activation+0.239
Top resid features:
was
Token was
Feature activation+0.405
Top resid features:
true
Token true
Feature activation+2.281
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
senior
Token senior
Feature activation+0.000
Top resid features:
Russian
Token Russian
Feature activation+0.000
Top resid features:
bishop
Token bishop
Feature activation+0.000
Top resid features:
innocent
Token innocent
Feature activation-0.013
Top resid features:
.
Token.
Feature activation+0.026
Top resid features:
There
Token There
Feature activation-0.006
Top resid features:
is
Token is
Feature activation-0.002
Top resid features:
no
Token no
Feature activation-0.031
Top resid features:
truth
Token truth
Feature activation+3.139
Top resid features:
to
Token to
Feature activation-0.293
Top resid features:
the
Token the
Feature activation+0.234
Top resid features:
charges
Token charges
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
benefited
Token benefited
Feature activation+0.000
Top resid features:
j
Tokenj
Feature activation+0.009
Top resid features:
ev
Tokenev
Feature activation+0.007
Top resid features:
ich
Tokenich
Feature activation+0.010
Top resid features:
makes
Token makes
Feature activation-0.181
Top resid features:
no
Token no
Feature activation+0.081
Top resid features:
bones
Token bones
Feature activation+3.126
Top resid features:
about
Token about
Feature activation-0.148
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
I
Token I
Feature activation-0.014
Top resid features:
sought
Token sought
Feature activation-0.012
Top resid features:
care
Token care
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.068
Top resid features:
Small
Token Small
Feature activation-0.029
Top resid features:
as
Token as
Feature activation+2.545
Top resid features:
it
Token it
Feature activation+0.043
Top resid features:
is
Token is
Feature activation+0.318
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Jackson
Token Jackson
Feature activation+0.000
Top resid features:
really
Token really
Feature activation+0.000
Top resid features:
innocent
Token innocent
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.031
Top resid features:
There
Token There
Feature activation-0.005
Top resid features:
is
Token is
Feature activation+0.005
Top resid features:
no
Token no
Feature activation-0.015
Top resid features:
truth
Token truth
Feature activation+2.574
Top resid features:
to
Token to
Feature activation+0.124
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
charges
Token charges
Feature activation+0.000
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
benefited
Token benefited
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.01

Head 1: 0.02

Head 2: 0.06

Head 3: 0.05

Head 4: 0.08

Head 5: 0.03

Head 6: 0.06

Head 7: 0.53

Head 8: 0.03

Head 9: 0.03

Head 10: 0.05

Head 11: 0.05

Positive logits

Identity1.59

Outs1.54

1.51

stereotype1.50

trope1.40

myth1.39

falsehood1.38

False1.37

respecting1.37

ADS1.36

Claim1.35

reality1.35

Claim1.35

believer1.34

guiName1.33

tropes1.32

stereotypes1.31

>(1.30

FALSE1.29

oath1.29

Negative logits

quished-1.79

uria-1.72

ascus-1.68

oster-1.63

anqu-1.60

houses-1.54

umbn-1.48

urst-1.47

etting-1.46

morning-1.44

whe-1.42

leck-1.42

combinations-1.41

levers-1.40

ertodd-1.38

moil-1.38

rade-1.37

omach-1.37

ourt-1.37

ontent-1.36

INTERVAL 4.260 - 4.734
CONTAINS 0.000%

,
Token,
Feature activation+0.000
whether
Token whether
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
true
Token true
Feature activation+0.946
that
Token that
Feature activation+4.734
a
Token a
Feature activation+0.000
senior
Token senior
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
bishop
Token bishop
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 3.787 - 4.260
CONTAINS 0.000%

INTERVAL 3.314 - 3.787
CONTAINS 0.000%

it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
true
Token true
Feature activation+0.000
for
Token for
Feature activation+0.000
years
Token years
Feature activation+0.000
that
Token that
Feature activation+3.616
things
Token things
Feature activation+0.000
worked
Token worked
Feature activation+0.000
fine
Token fine
Feature activation+0.000
under
Token under
Feature activation+0.000
that
Token that
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
True
TokenTrue
Feature activation+0.000
to
Token to
Feature activation+3.281
his
Token his
Feature activation+3.658
style
Token style
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
uses
Token uses
Feature activation+0.000
charts
Token charts
Feature activation+0.000

INTERVAL 2.840 - 3.314
CONTAINS 0.000%

.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
While
Token While
Feature activation+0.000
true
Token true
Feature activation+0.000
to
Token to
Feature activation+2.903
some
Token some
Feature activation+1.674
extent
Token extent
Feature activation+0.091
,
Token,
Feature activation+0.422
Mart
Token Mart
Feature activation+0.000
os
Tokenos
Feature activation+0.000
last
Token last
Feature activation+0.000
night
Token night
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
true
Token true
Feature activation+0.000
that
Token that
Feature activation+3.296
they
Token they
Feature activation+0.000
were
Token were
Feature activation+0.000
motivated
Token motivated
Feature activation+0.000
by
Token by
Feature activation+0.000
religious
Token religious
Feature activation+0.000
country
Token country
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
True
TokenTrue
Feature activation+0.000
to
Token to
Feature activation+3.281
his
Token his
Feature activation+3.658
style
Token style
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
uses
Token uses
Feature activation+0.000

INTERVAL 2.367 - 2.840
CONTAINS 0.000%

INTERVAL 1.894 - 2.367
CONTAINS 0.000%

sh
Token sh
Feature activation+0.000
ambling
Tokenambling
Feature activation+0.000
quality
Token quality
Feature activation+0.000
is
Token is
Feature activation+0.000
true
Token true
Feature activation+0.000
to
Token to
Feature activation+2.200
Harry
Token Harry
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
urban
Token urban
Feature activation+0.000

INTERVAL 1.420 - 1.894
CONTAINS 0.000%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
While
Token While
Feature activation+0.000
true
Token true
Feature activation+0.000
to
Token to
Feature activation+2.903
some
Token some
Feature activation+1.674
extent
Token extent
Feature activation+0.091
,
Token,
Feature activation+0.422
Mart
Token Mart
Feature activation+0.000
os
Tokenos
Feature activation+0.000
ko
Tokenko
Feature activation+0.000
religions
Token religions
Feature activation+0.000
are
Token are
Feature activation+0.000
sort
Token sort
Feature activation+0.000
of
Token of
Feature activation+0.000
true
Token true
Feature activation+0.000
in
Token in
Feature activation+1.800
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
way
Token way
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000

INTERVAL 0.947 - 1.420
CONTAINS 0.001%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ren
TokenRen
Feature activation+0.000
ew
Tokenew
Feature activation+0.000
ed
Tokened
Feature activation+1.036
calls
Token calls
Feature activation+0.000
for
Token for
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Says
Token Says
Feature activation+0.000
its
Token its
Feature activation+0.000
true
Token true
Feature activation+0.000
the
Token the
Feature activation+1.003
other
Token other
Feature activation+0.000
way
Token way
Feature activation+0.000
too
Token too
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ren
TokenRen
Feature activation+0.000
ew
Tokenew
Feature activation+0.000
ed
Tokened
Feature activation+1.048
questions
Token questions
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
raised
Token raised
Feature activation+0.000
over
Token over
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
never
Token never
Feature activation+0.000
lost
Token lost
Feature activation+0.000
sight
Token sight
Feature activation+0.000
of
Token of
Feature activation+1.272
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
think
Token think
Feature activation+0.000
the
Token the
Feature activation+0.000
Commissioner
Token Commissioner
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
also
Token also
Feature activation+0.000
true
Token true
Feature activation+0.151
that
Token that
Feature activation+1.412
P
Token P
Feature activation+0.000
(
Token(
Feature activation+0.000
~
Token~
Feature activation+0.000
E
TokenE
Feature activation+0.000
|
Token|
Feature activation+0.000

INTERVAL 0.473 - 0.947
CONTAINS 0.001%

es
Tokenes
Feature activation+0.000
,
Token,
Feature activation+0.000
whether
Token whether
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
true
Token true
Feature activation+0.946
that
Token that
Feature activation+4.734
a
Token a
Feature activation+0.000
senior
Token senior
Feature activation+0.000
Russian
Token Russian
Feature activation+0.000
bishop
Token bishop
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
not
Token not
Feature activation+0.000
true
Token true
Feature activation+0.512
,
Token,
Feature activation+0.588
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
ev
Tokenev
Feature activation+0.000
ich
Tokenich
Feature activation+0.000
makes
Token makes
Feature activation+0.000
no
Token no
Feature activation+0.000
bones
Token bones
Feature activation+0.000
about
Token about
Feature activation+0.813
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.411
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
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
truth
Token truth
Feature activation+0.000
to
Token to
Feature activation+0.746
the
Token the
Feature activation+0.823
charges
Token charges
Feature activation+0.000
I
Token I
Feature activation+0.000
benefited
Token benefited
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
deep
Token deep
Feature activation+0.000
-
Token-
Feature activation+0.000
pocket
Tokenpocket
Feature activation+0.000
ed
Tokened
Feature activation+0.504
clubs
Token clubs
Feature activation+0.000
developed
Token developed
Feature activation+0.000
analytics
Token analytics
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000

INTERVAL 0.000 - 0.473
CONTAINS 99.998%

-
Token-
Feature activation+0.000
interest
Tokeninterest
Feature activation+0.000
allegations
Token allegations
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
RELATED
TokenRELATED
Feature activation+0.000
:
Token:
Feature activation+0.000
Gl
Token Gl
Feature activation+0.000
endale
Tokenendale
Feature activation+0.000
's
Token's
Feature activation+0.000
phones
Token phones
Feature activation+0.000
and
Token and
Feature activation+0.000
smart
Token smart
Feature activation+0.000
watches
Token watches
Feature activation+0.000
can
Token can
Feature activation+0.000
send
Token send
Feature activation+0.000
a
Token a
Feature activation+0.000
generic
Token generic
Feature activation+0.000
alert
Token alert
Feature activation+0.000
by
Token by
Feature activation+0.000
vibr
Token vibr
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
see
Token see
Feature activation+0.000
any
Token any
Feature activation+0.000
noticeable
Token noticeable
Feature activation+0.000
changes
Token changes
Feature activation+0.000
,"
Token,"
Feature activation+0.000
she
Token she
Feature activation+0.000
says
Token says
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
really
Token really
Feature activation+0.000
??
Token??
Feature activation+0.000
)
Token)
Feature activation+0.000
might
Token might
Feature activation+0.000
be
Token be
Feature activation+0.000
:
Token:
Feature activation+0.000
Bringing
Token Bringing
Feature activation+0.000
it
Token it
Feature activation+0.000
along
Token along
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
finalized
Token finalized
Feature activation+0.000
rules
Token rules
Feature activation+0.000
for
Token for
Feature activation+0.000
its
Token its
Feature activation+0.000
first
Token first
Feature activation+0.000
season
Token season
Feature activation+0.000
.[
Token.[
Feature activation+0.000
12
Token12
Feature activation+0.000
]
Token]
Feature activation+0.000
There
Token There
Feature activation+0.000
would
Token would
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 H5.7: (feature 16224)

TOP ACTIVATIONS
MAX = 4.146

robbing
Token robbing
Feature activation+0.000
Peter
Token Peter
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
every
Token every
Feature activation+4.055
month
Token month
Feature activation+1.140
to
Token to
Feature activation+2.905
meet
Token meet
Feature activation+0.129
the
Token the
Feature activation+0.000
debt
Token debt
Feature activation+0.000
.
Token.
Feature activation+0.000
Our
Token Our
Feature activation+0.000
progressives
Token progressives
Feature activation+0.000
should
Token should
Feature activation+0.000
pay
Token pay
Feature activation+0.000
them
Token them
Feature activation+3.999
some
Token some
Feature activation+2.672
attention
Token attention
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
offered
Token offered
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
him
Token him
Feature activation+3.884
to
Token to
Feature activation+2.232
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
hamb
Token hamb
Feature activation+0.000
urger
Tokenurger
Feature activation+0.000
at
Token at
Feature activation+0.000
how
Token how
Feature activation+0.000
much
Token much
Feature activation+0.000
we
Token we
Feature activation+0.000
pay
Token pay
Feature activation+0.055
them
Token them
Feature activation+3.756
in
Token in
Feature activation+2.379
relation
Token relation
Feature activation+0.212
to
Token to
Feature activation+0.000
men
Token men
Feature activation+0.107
.
Token.
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
the
Token the
Feature activation+0.954
affected
Token affected
Feature activation+0.000
companies
Token companies
Feature activation+1.109
proper
Token proper
Feature activation+3.608
compensation
Token compensation
Feature activation+0.282
for
Token for
Feature activation+1.120
the
Token the
Feature activation+1.096
cancelled
Token cancelled
Feature activation+0.000
deal
Token deal
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
get
Token get
Feature activation+0.000
paid
Token paid
Feature activation+0.430
to
Token to
Feature activation+3.598
think
Token think
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
.
Token.
Feature activation+0.000
wealthy
Token wealthy
Feature activation+0.000
foreigners
Token foreigners
Feature activation+0.000
paying
Token paying
Feature activation+0.000
poor
Token poor
Feature activation+0.949
Indians
Token Indians
Feature activation+0.395
to
Token to
Feature activation+3.522
have
Token have
Feature activation+0.373
babies
Token babies
Feature activation+0.000
has
Token has
Feature activation+0.000
raised
Token raised
Feature activation+0.000
ethical
Token ethical
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
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+3.442
drugs
Token drugs
Feature activation+0.895
that
Token that
Feature activation+0.000
might
Token might
Feature activation+0.000
cause
Token cause
Feature activation+0.000
abortions
Token abortions
Feature activation+0.000
you
Token you
Feature activation+0.000
want
Token want
Feature activation+0.000
us
Token us
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
you
Token you
Feature activation+3.442
in
Token in
Feature activation+2.543
small
Token small
Feature activation+0.210
kids
Token kids
Feature activation+2.001
maybe
Token maybe
Feature activation+0.000
?"
Token?"
Feature activation+0.000
took
Token took
Feature activation+0.000
to
Token to
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
his
Token his
Feature activation+3.368
respects
Token respects
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
fallen
Token fallen
Feature activation+0.000
art
Token art
Feature activation+0.000
Pac
Token Pac
Feature activation+0.000
-
Token-
Feature activation+0.000
12
Token12
Feature activation+0.137
assistant
Token assistant
Feature activation+0.804
EVER
Token EVER
Feature activation+0.389
by
Token by
Feature activation+3.154
around
Token around
Feature activation+0.000
500
Token 500
Feature activation+0.837
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
being
Token being
Feature activation+0.000
ev
Token ev
Feature activation+0.000
icted
Tokenicted
Feature activation+0.000
or
Token or
Feature activation+0.000
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+3.126
Aunt
Token Aunt
Feature activation+0.274
May
Token May
Feature activation+1.208
's
Token's
Feature activation+4.146
medicine
Token medicine
Feature activation+0.113
.
Token.
Feature activation+0.000
multinational
Token multinational
Feature activation+0.000
s
Tokens
Feature activation+0.000
were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.000
paying
Token paying
Feature activation+0.082
their
Token their
Feature activation+3.109
fair
Token fair
Feature activation+0.118
share
Token share
Feature activation+0.516
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
CIA
Token CIA
Feature activation+0.000
was
Token was
Feature activation+0.000
paying
Token paying
Feature activation+0.000
him
Token him
Feature activation+3.104
,
Token,
Feature activation+0.293
and
Token and
Feature activation+0.000
reimb
Token reimb
Feature activation+0.000
urs
Tokenurs
Feature activation+0.000
ing
Tokening
Feature activation+0.580
wat
Token wat
Feature activation+0.000
cher
Tokencher
Feature activation+1.891
out
Token out
Feature activation+2.690
in
Token in
Feature activation+0.000
America
Token America
Feature activation+0.000
to
Token to
Feature activation+3.073
keep
Token keep
Feature activation+0.140
an
Token an
Feature activation+0.000
eye
Token eye
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
end
Token end
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
stopped
Token stopped
Feature activation+0.000
paying
Token paying
Feature activation+0.000
our
Token our
Feature activation+3.065
wages
Token wages
Feature activation+0.584
,"
Token,"
Feature activation+0.000
the
Token the
Feature activation+0.000
60
Token 60
Feature activation+0.000
-
Token-
Feature activation+0.000
Celest
Token Celest
Feature activation+0.000
in
Tokenin
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
his
Token his
Feature activation+3.017
customs
Token customs
Feature activation+0.183
duties
Token duties
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
North
Token North
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
paying
Token paying
Feature activation+0.000
them
Token them
Feature activation+2.948
extortion
Token extortion
Feature activation+1.263
money
Token money
Feature activation+0.019
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
25
Token 25
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
s
Tokens
Feature activation+0.000
make
Token make
Feature activation+0.000
them
Token them
Feature activation+0.000
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+2.937
a
Token a
Feature activation+1.087
visit
Token visit
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
GP
Token GP
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
every
Token every
Feature activation+4.055
month
Token month
Feature activation+1.140
to
Token to
Feature activation+2.905
meet
Token meet
Feature activation+0.129
the
Token the
Feature activation+0.000
debt
Token debt
Feature activation+0.000
commitments
Token commitments
Feature activation+0.000
they
Token they
Feature activation+0.000

Top DFA by src position
MAX = 5.468

edge
Token edge
Feature activation-0.004
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
robbing
Token robbing
Feature activation+0.010
Top resid features:
Peter
Token Peter
Feature activation+0.077
Top resid features:
to
Token to
Feature activation+0.043
Top resid features:
pay
Token pay
Feature activation+4.876
Top resid features:
Paul
Token Paul
Feature activation+0.219
Top resid features:
every
Token every
Feature activation+0.044
Top resid features:
month
Token month
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
meet
Token meet
Feature activation+0.000
Top resid features:
progress
Token progress
Feature activation+0.025
Top resid features:
.
Token.
Feature activation+0.035
Top resid features:
Our
Token Our
Feature activation-0.021
Top resid features:
progressives
Token progressives
Feature activation-0.026
Top resid features:
should
Token should
Feature activation-0.015
Top resid features:
pay
Token pay
Feature activation+5.468
Top resid features:
them
Token them
Feature activation-0.009
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
attention
Token attention
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
colleagues
Token colleagues
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
offered
Token offered
Feature activation-0.073
Top resid features:
to
Token to
Feature activation+0.033
Top resid features:
pay
Token pay
Feature activation+5.329
Top resid features:
him
Token him
Feature activation+0.003
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
hamb
Token hamb
Feature activation+0.000
Top resid features:
look
Token look
Feature activation-0.012
Top resid features:
at
Token at
Feature activation-0.011
Top resid features:
how
Token how
Feature activation+0.039
Top resid features:
much
Token much
Feature activation+0.108
Top resid features:
we
Token we
Feature activation+0.029
Top resid features:
pay
Token pay
Feature activation+4.646
Top resid features:
them
Token them
Feature activation+0.128
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
relation
Token relation
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
men
Token men
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.008
Top resid features:
called
Token called
Feature activation-0.035
Top resid features:
on
Token on
Feature activation+0.025
Top resid features:
Mexico
Token Mexico
Feature activation+0.033
Top resid features:
to
Token to
Feature activation+0.017
Top resid features:
pay
Token pay
Feature activation+4.552
Top resid features:
the
Token the
Feature activation+0.060
Top resid features:
affected
Token affected
Feature activation+0.078
Top resid features:
companies
Token companies
Feature activation+0.094
Top resid features:
proper
Token proper
Feature activation+0.018
Top resid features:
compensation
Token compensation
Feature activation+0.000
Top resid features:
opinions
Token opinions
Feature activation-0.008
Top resid features:
of
Token of
Feature activation+0.019
Top resid features:
people
Token people
Feature activation+0.025
Top resid features:
who
Token who
Feature activation+0.051
Top resid features:
get
Token get
Feature activation-0.027
Top resid features:
paid
Token paid
Feature activation+4.784
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
think
Token think
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
future
Token future
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
issue
Token issue
Feature activation+0.021
Top resid features:
of
Token of
Feature activation+0.187
Top resid features:
wealthy
Token wealthy
Feature activation+0.028
Top resid features:
foreigners
Token foreigners
Feature activation+0.046
Top resid features:
paying
Token paying
Feature activation+4.253
Top resid features:
poor
Token poor
Feature activation+0.147
Top resid features:
Indians
Token Indians
Feature activation+0.095
Top resid features:
to
Token to
Feature activation+0.082
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
babies
Token babies
Feature activation+0.000
Top resid features:
we
Token we
Feature activation-0.015
Top resid features:
don
Token don
Feature activation-0.017
Top resid features:
âĢ
TokenâĢ
Feature activation-0.003
Top resid features:
Ļ
TokenĻ
Feature activation-0.005
Top resid features:
t
Tokent
Feature activation+0.056
Top resid features:
pay
Token pay
Feature activation+4.669
Top resid features:
for
Token for
Feature activation-0.129
Top resid features:
drugs
Token drugs
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
might
Token might
Feature activation+0.000
Top resid features:
cause
Token cause
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.026
Top resid features:
you
Token you
Feature activation+0.094
Top resid features:
want
Token want
Feature activation+0.002
Top resid features:
us
Token us
Feature activation+0.031
Top resid features:
to
Token to
Feature activation+0.023
Top resid features:
pay
Token pay
Feature activation+4.247
Top resid features:
you
Token you
Feature activation+0.073
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
small
Token small
Feature activation+0.000
Top resid features:
kids
Token kids
Feature activation+0.000
Top resid features:
maybe
Token maybe
Feature activation+0.000
Top resid features:
who
Token who
Feature activation-0.011
Top resid features:
took
Token took
Feature activation-0.067
Top resid features:
to
Token to
Feature activation-0.041
Top resid features:
Twitter
Token Twitter
Feature activation-0.022
Top resid features:
to
Token to
Feature activation-0.020
Top resid features:
pay
Token pay
Feature activation+4.881
Top resid features:
his
Token his
Feature activation-0.091
Top resid features:
respects
Token respects
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
fallen
Token fallen
Feature activation+0.000
Top resid features:
osed
Tokenosed
Feature activation-0.007
Top resid features:
ly
Tokenly
Feature activation-0.004
Top resid features:
)
Token)
Feature activation+0.008
Top resid features:
the
Token the
Feature activation-0.003
Top resid features:
most
Token most
Feature activation+0.036
Top resid features:
paid
Token paid
Feature activation+3.842
Top resid features:
Pac
Token Pac
Feature activation+0.023
Top resid features:
-
Token-
Feature activation-0.007
Top resid features:
12
Token12
Feature activation+0.003
Top resid features:
assistant
Token assistant
Feature activation+0.032
Top resid features:
EVER
Token EVER
Feature activation+0.560
Top resid features:
from
Token from
Feature activation+0.032
Top resid features:
being
Token being
Feature activation+0.001
Top resid features:
ev
Token ev
Feature activation+0.036
Top resid features:
icted
Tokenicted
Feature activation-0.002
Top resid features:
or
Token or
Feature activation+0.084
Top resid features:
pay
Token pay
Feature activation+4.263
Top resid features:
for
Token for
Feature activation-0.154
Top resid features:
Aunt
Token Aunt
Feature activation+0.000
Top resid features:
May
Token May
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
medicine
Token medicine
Feature activation+0.000
Top resid features:
concerns
Token concerns
Feature activation+0.003
Top resid features:
multinational
Token multinational
Feature activation+0.009
Top resid features:
s
Tokens
Feature activation+0.028
Top resid features:
were
Token were
Feature activation+0.061
Top resid features:
not
Token not
Feature activation+0.024
Top resid features:
paying
Token paying
Feature activation+4.408
Top resid features:
their
Token their
Feature activation-0.046
Top resid features:
fair
Token fair
Feature activation+0.000
Top resid features:
share
Token share
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
not
Token not
Feature activation-0.005
Top resid features:
?
Token?
Feature activation+0.037
Top resid features:
The
Token The
Feature activation-0.028
Top resid features:
CIA
Token CIA
Feature activation+0.001
Top resid features:
was
Token was
Feature activation-0.050
Top resid features:
paying
Token paying
Feature activation+4.314
Top resid features:
him
Token him
Feature activation+0.040
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
reimb
Token reimb
Feature activation+0.000
Top resid features:
urs
Tokenurs
Feature activation+0.000
Top resid features:
ih
Tokenih
Feature activation-0.003
Top resid features:
anna
Tokenanna
Feature activation-0.002
Top resid features:
has
Token has
Feature activation-0.002
Top resid features:
reportedly
Token reportedly
Feature activation+0.017
Top resid features:
started
Token started
Feature activation-0.034
Top resid features:
paying
Token paying
Feature activation+4.190
Top resid features:
a
Token a
Feature activation+0.041
Top resid features:
UFO
Token UFO
Feature activation+0.049
Top resid features:
wat
Token wat
Feature activation+0.021
Top resid features:
cher
Tokencher
Feature activation-0.007
Top resid features:
out
Token out
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.011
Top resid features:
end
Token end
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
they
Token they
Feature activation-0.034
Top resid features:
stopped
Token stopped
Feature activation-0.036
Top resid features:
paying
Token paying
Feature activation+4.503
Top resid features:
our
Token our
Feature activation-0.002
Top resid features:
wages
Token wages
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:
60
Token 60
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
Celest
Token Celest
Feature activation-0.002
Top resid features:
in
Tokenin
Feature activation-0.009
Top resid features:
decided
Token decided
Feature activation-0.014
Top resid features:
to
Token to
Feature activation+0.019
Top resid features:
pay
Token pay
Feature activation+4.365
Top resid features:
his
Token his
Feature activation-0.058
Top resid features:
customs
Token customs
Feature activation+0.000
Top resid features:
duties
Token duties
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
North
Token North
Feature activation-0.015
Top resid features:
Korea
Token Korea
Feature activation-0.027
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.077
Top resid features:
paying
Token paying
Feature activation+4.141
Top resid features:
them
Token them
Feature activation+0.042
Top resid features:
extortion
Token extortion
Feature activation+0.000
Top resid features:
money
Token money
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.611
Top resid features:
s
Tokens
Feature activation-0.010
Top resid features:
make
Token make
Feature activation-0.084
Top resid features:
them
Token them
Feature activation+0.026
Top resid features:
pay
Token pay
Feature activation+4.388
Top resid features:
for
Token for
Feature activation-0.125
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
visit
Token visit
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
edge
Token edge
Feature activation-0.011
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
robbing
Token robbing
Feature activation+0.011
Top resid features:
Peter
Token Peter
Feature activation+0.047
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
pay
Token pay
Feature activation+3.466
Top resid features:
Paul
Token Paul
Feature activation+0.178
Top resid features:
every
Token every
Feature activation+0.256
Top resid features:
month
Token month
Feature activation+0.053
Top resid features:
to
Token to
Feature activation+0.242
Top resid features:
meet
Token meet
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.02

Head 1: 0.02

Head 2: 0.04

Head 3: 0.03

Head 4: 0.11

Head 5: 0.02

Head 6: 0.04

Head 7: 0.53

Head 8: 0.04

Head 9: 0.03

Head 10: 0.06

Head 11: 0.06

Positive logits

dues2.17

salaries1.96

royalties1.95

unpaid1.84

wages1.83

debts1.70

expenses1.69

salary1.64

1.64

dividends1.64

rent1.64

repay1.62

paycheck1.62

payers1.62

hourly1.60

reimburse1.60

premiums1.59

1.58

tuition1.57

$1.55

Negative logits

ヴァ-1.56

nesota-1.44

cre-1.39

evidence-1.35

isman-1.34

phant-1.32

aten-1.32

forth-1.31

stable-1.30

rules-1.28

crete-1.28

atus-1.27

decentral-1.27

torn-1.26

zsche-1.26

uther-1.25

jab-1.25

apons-1.25

veyard-1.24

iverpool-1.24

INTERVAL 3.731 - 4.146
CONTAINS 0.001%

.
Token.
Feature activation+0.000
Our
Token Our
Feature activation+0.000
progressives
Token progressives
Feature activation+0.000
should
Token should
Feature activation+0.000
pay
Token pay
Feature activation+0.000
them
Token them
Feature activation+3.999
some
Token some
Feature activation+2.672
attention
Token attention
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
at
Token at
Feature activation+0.000
how
Token how
Feature activation+0.000
much
Token much
Feature activation+0.000
we
Token we
Feature activation+0.000
pay
Token pay
Feature activation+0.055
them
Token them
Feature activation+3.756
in
Token in
Feature activation+2.379
relation
Token relation
Feature activation+0.212
to
Token to
Feature activation+0.000
men
Token men
Feature activation+0.107
.
Token.
Feature activation+0.000
robbing
Token robbing
Feature activation+0.000
Peter
Token Peter
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
every
Token every
Feature activation+4.055
month
Token month
Feature activation+1.140
to
Token to
Feature activation+2.905
meet
Token meet
Feature activation+0.129
the
Token the
Feature activation+0.000
debt
Token debt
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
offered
Token offered
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
him
Token him
Feature activation+3.884
to
Token to
Feature activation+2.232
make
Token make
Feature activation+0.000
a
Token a
Feature activation+0.000
hamb
Token hamb
Feature activation+0.000
urger
Tokenurger
Feature activation+0.000

INTERVAL 3.317 - 3.731
CONTAINS 0.001%

took
Token took
Feature activation+0.000
to
Token to
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
his
Token his
Feature activation+3.368
respects
Token respects
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
fallen
Token fallen
Feature activation+0.000
art
Token art
Feature activation+0.000
you
Token you
Feature activation+0.000
want
Token want
Feature activation+0.000
us
Token us
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
you
Token you
Feature activation+3.442
in
Token in
Feature activation+2.543
small
Token small
Feature activation+0.210
kids
Token kids
Feature activation+2.001
maybe
Token maybe
Feature activation+0.000
?"
Token?"
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
who
Token who
Feature activation+0.000
get
Token get
Feature activation+0.000
paid
Token paid
Feature activation+0.430
to
Token to
Feature activation+3.598
think
Token think
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
.
Token.
Feature activation+0.000
wealthy
Token wealthy
Feature activation+0.000
foreigners
Token foreigners
Feature activation+0.000
paying
Token paying
Feature activation+0.000
poor
Token poor
Feature activation+0.949
Indians
Token Indians
Feature activation+0.395
to
Token to
Feature activation+3.522
have
Token have
Feature activation+0.373
babies
Token babies
Feature activation+0.000
has
Token has
Feature activation+0.000
raised
Token raised
Feature activation+0.000
ethical
Token ethical
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
the
Token the
Feature activation+0.954
affected
Token affected
Feature activation+0.000
companies
Token companies
Feature activation+1.109
proper
Token proper
Feature activation+3.608
compensation
Token compensation
Feature activation+0.282
for
Token for
Feature activation+1.120
the
Token the
Feature activation+1.096
cancelled
Token cancelled
Feature activation+0.000
deal
Token deal
Feature activation+0.000

INTERVAL 2.902 - 3.317
CONTAINS 0.001%

North
Token North
Feature activation+0.000
Korea
Token Korea
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
paying
Token paying
Feature activation+0.000
them
Token them
Feature activation+2.948
extortion
Token extortion
Feature activation+1.263
money
Token money
Feature activation+0.019
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
25
Token 25
Feature activation+0.000
being
Token being
Feature activation+0.000
ev
Token ev
Feature activation+0.000
icted
Tokenicted
Feature activation+0.000
or
Token or
Feature activation+0.000
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+3.126
Aunt
Token Aunt
Feature activation+0.274
May
Token May
Feature activation+1.208
's
Token's
Feature activation+4.146
medicine
Token medicine
Feature activation+0.113
.
Token.
Feature activation+0.000
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
CIA
Token CIA
Feature activation+0.000
was
Token was
Feature activation+0.000
paying
Token paying
Feature activation+0.000
him
Token him
Feature activation+3.104
,
Token,
Feature activation+0.293
and
Token and
Feature activation+0.000
reimb
Token reimb
Feature activation+0.000
urs
Tokenurs
Feature activation+0.000
ing
Tokening
Feature activation+0.580
Pac
Token Pac
Feature activation+0.000
-
Token-
Feature activation+0.000
12
Token12
Feature activation+0.137
assistant
Token assistant
Feature activation+0.804
EVER
Token EVER
Feature activation+0.389
by
Token by
Feature activation+3.154
around
Token around
Feature activation+0.000
500
Token 500
Feature activation+0.837
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
Celest
Token Celest
Feature activation+0.000
in
Tokenin
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
his
Token his
Feature activation+3.017
customs
Token customs
Feature activation+0.183
duties
Token duties
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.487 - 2.902
CONTAINS 0.001%

want
Token want
Feature activation+0.000
us
Token us
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
you
Token you
Feature activation+3.442
in
Token in
Feature activation+2.543
small
Token small
Feature activation+0.210
kids
Token kids
Feature activation+2.001
maybe
Token maybe
Feature activation+0.000
?"
Token?"
Feature activation+0.000
was
Token was
Feature activation+0.000
companies
Token companies
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
their
Token their
Feature activation+2.207
workers
Token workers
Feature activation+2.262
lower
Token lower
Feature activation+2.664
wages
Token wages
Feature activation+0.087
than
Token than
Feature activation+0.077
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
possible
Token possible
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
pay
Token pay
Feature activation+0.000
federal
Token federal
Feature activation+2.729
employees
Token employees
Feature activation+2.719
fairly
Token fairly
Feature activation+1.301
for
Token for
Feature activation+2.455
their
Token their
Feature activation+2.147
work
Token work
Feature activation+0.000
.
Token.
Feature activation+0.000
of
Token of
Feature activation+0.123
people
Token people
Feature activation+0.547
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
medical
Token medical
Feature activation+2.881
care
Token care
Feature activation+0.338
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
is
Token is
Feature activation+0.000
saying
Token saying
Feature activation+0.000
paying
Token paying
Feature activation+0.000
a
Token a
Feature activation+0.462
UFO
Token UFO
Feature activation+1.013
wat
Token wat
Feature activation+0.000
cher
Tokencher
Feature activation+1.891
out
Token out
Feature activation+2.690
in
Token in
Feature activation+0.000
America
Token America
Feature activation+0.000
to
Token to
Feature activation+3.073
keep
Token keep
Feature activation+0.140
an
Token an
Feature activation+0.000

INTERVAL 2.073 - 2.487
CONTAINS 0.003%

infrastructure
Token infrastructure
Feature activation+0.000
spending
Token spending
Feature activation+0.000
,
Token,
Feature activation+0.000
equal
Token equal
Feature activation+0.000
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+2.413
women
Token women
Feature activation+2.110
,
Token,
Feature activation+0.000
universal
Token universal
Feature activation+0.000
pre
Token pre
Feature activation+0.000
-
Token-
Feature activation+0.000
you
Token you
Feature activation+0.000
want
Token want
Feature activation+0.000
something
Token something
Feature activation+0.000
,
Token,
Feature activation+0.000
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+2.337
it
Token it
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
X
TokenX
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
taxes
Token taxes
Feature activation+0.000
that
Token that
Feature activation+0.000
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+2.147
Obamacare
Token Obamacare
Feature activation+0.000
,
Token,
Feature activation+0.000
roll
Token roll
Feature activation+0.000
back
Token back
Feature activation+0.000
expanded
Token expanded
Feature activation+0.000
how
Token how
Feature activation+0.000
they
Token they
Feature activation+0.000
intend
Token intend
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+2.346
all
Token all
Feature activation+0.370
those
Token those
Feature activation+1.229
investments
Token investments
Feature activation+0.000
,
Token,
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
pick
Token pick
Feature activation+0.000
along
Token along
Feature activation+0.000
with
Token with
Feature activation+0.000
paying
Token paying
Feature activation+0.000
Cruz
Token Cruz
Feature activation+0.344
a
Token a
Feature activation+2.271
mountain
Token mountain
Feature activation+0.000
of
Token of
Feature activation+0.000
cash
Token cash
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000

INTERVAL 1.658 - 2.073
CONTAINS 0.003%

products
Token products
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
fully
Token fully
Feature activation+0.000
paid
Token paid
Feature activation+0.557
for
Token for
Feature activation+1.922
or
Token or
Feature activation+0.000
are
Token are
Feature activation+0.000
being
Token being
Feature activation+0.000
sold
Token sold
Feature activation+0.000
on
Token on
Feature activation+0.000
makes
Token makes
Feature activation+0.000
the
Token the
Feature activation+0.000
capitalists
Token capitalists
Feature activation+0.000
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+1.639
the
Token the
Feature activation+1.858
crisis
Token crisis
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Over
TokenOver
Feature activation+0.000
deal
Token deal
Feature activation+0.000
would
Token would
Feature activation+0.000
involve
Token involve
Feature activation+0.000
rep
Token rep
Feature activation+0.000
aying
Tokenaying
Feature activation+0.673
all
Token all
Feature activation+2.004
players
Token players
Feature activation+1.113
in
Token in
Feature activation+0.000
full
Token full
Feature activation+0.272
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
haven
Token haven
Feature activation+0.000
't
Token't
Feature activation+0.000
paid
Token paid
Feature activation+0.000
their
Token their
Feature activation+1.976
fair
Token fair
Feature activation+0.410
share
Token share
Feature activation+0.000
.
Token.
Feature activation+0.000
But
Token But
Feature activation+0.000
,
Token,
Feature activation+0.000
demanded
Token demanded
Feature activation+0.000
the
Token the
Feature activation+0.000
regional
Token regional
Feature activation+0.000
government
Token government
Feature activation+0.000
pay
Token pay
Feature activation+0.000
their
Token their
Feature activation+1.746
wages
Token wages
Feature activation+0.398
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.000
said
Token said
Feature activation+0.000
they
Token they
Feature activation+0.000

INTERVAL 1.244 - 1.658
CONTAINS 0.005%

make
Token make
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000
US
TokenUS
Feature activation+0.000
pay
Token pay
Feature activation+0.000
a
Token a
Feature activation+1.327
price
Token price
Feature activation+0.000
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
as
Token as
Feature activation+0.000
much
Token much
Feature activation+0.000
as
Token as
Feature activation+0.000
12
Token 12
Feature activation+0.000
percent
Token percent
Feature activation+0.000
for
Token for
Feature activation+1.355
state
Token state
Feature activation+0.674
commissioners
Token commissioners
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
top
Token top
Feature activation+0.000
resources
Token resources
Feature activation+0.000
,
Token,
Feature activation+0.000
controlling
Token controlling
Feature activation+0.000
payment
Token payment
Feature activation+0.000
of
Token of
Feature activation+2.146
foreign
Token foreign
Feature activation+1.607
currency
Token currency
Feature activation+0.000
-
Token-
Feature activation+0.000
den
Tokenden
Feature activation+0.000
ominated
Tokenominated
Feature activation+0.000
obligations
Token obligations
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
already
Token already
Feature activation+0.000
paid
Token paid
Feature activation+0.000
their
Token their
Feature activation+1.457
Medicare
Token Medicare
Feature activation+0.353
Levy
Token Levy
Feature activation+0.000
.
Token.
Feature activation+0.000
Let
Token Let
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
second
Token second
Feature activation+0.000
ees
Tokenees
Feature activation+0.000
are
Token are
Feature activation+0.000
paid
Token paid
Feature activation+0.725
by
Token by
Feature activation+1.674
their
Token their
Feature activation+1.384
companies
Token companies
Feature activation+1.039
during
Token during
Feature activation+0.266
their
Token their
Feature activation+0.000
time
Token time
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.829 - 1.244
CONTAINS 0.010%

military
Token military
Feature activation+0.000
bases
Token bases
Feature activation+0.000
and
Token and
Feature activation+0.000
limiting
Token limiting
Feature activation+0.000
compensation
Token compensation
Feature activation+0.000
for
Token for
Feature activation+1.228
troops
Token troops
Feature activation+0.107
and
Token and
Feature activation+0.000
veterans
Token veterans
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Talk
Token Talk
Feature activation+0.000
Talk
TokenTalk
Feature activation+0.000
became
Token became
Feature activation+0.000
able
Token able
Feature activation+0.000
pay
Token pay
Feature activation+0.000
BT
Token BT
Feature activation+1.089
to
Token to
Feature activation+1.203
use
Token use
Feature activation+0.000
its
Token its
Feature activation+0.000
existing
Token existing
Feature activation+0.000
cables
Token cables
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+0.564
in
Token in
Feature activation+0.942
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
ing
Tokening
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
afford
Token afford
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+0.843
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
get
Token get
Feature activation+0.000
sick
Token sick
Feature activation+0.000
across
Token across
Feature activation+0.000
the
Token the
Feature activation+0.000
province
Token province
Feature activation+0.000
are
Token are
Feature activation+0.000
paid
Token paid
Feature activation+0.755
more
Token more
Feature activation+1.101
,
Token,
Feature activation+0.000
sometimes
Token sometimes
Feature activation+0.000
much
Token much
Feature activation+0.000
more
Token more
Feature activation+0.000
,
Token,
Feature activation+0.299

INTERVAL 0.415 - 0.829
CONTAINS 0.013%

have
Token have
Feature activation+0.000
the
Token the
Feature activation+0.000
funds
Token funds
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
the
Token the
Feature activation+0.556
families
Token families
Feature activation+1.141
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
suicide
Token suicide
Feature activation+0.000
bombers
Token bombers
Feature activation+0.000
one
Token one
Feature activation+0.000
specification
Token specification
Feature activation+0.000
of
Token of
Feature activation+0.000
wrongful
Token wrongful
Feature activation+0.000
discharge
Token discharge
Feature activation+0.000
of
Token of
Feature activation+0.485
a
Token a
Feature activation+0.153
firearm
Token firearm
Feature activation+0.000
and
Token and
Feature activation+0.000
one
Token one
Feature activation+0.000
specification
Token specification
Feature activation+0.000
perform
Token perform
Feature activation+0.000
well
Token well
Feature activation+0.000
tend
Token tend
Feature activation+0.000
to
Token to
Feature activation+0.000
pay
Token pay
Feature activation+0.000
close
Token close
Feature activation+0.764
attention
Token attention
Feature activation+0.000
to
Token to
Feature activation+0.000
customers
Token customers
Feature activation+0.000
and
Token and
Feature activation+0.000
engage
Token engage
Feature activation+0.000
services
Token services
Feature activation+0.000
ultimately
Token ultimately
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
paid
Token paid
Feature activation+0.614
for
Token for
Feature activation+1.817
somehow
Token somehow
Feature activation+0.000
.
Token.
Feature activation+0.000
By
Token By
Feature activation+0.000
gaining
Token gaining
Feature activation+0.000
ava
Tokenava
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
pay
Token pay
Feature activation+0.000
the
Token the
Feature activation+0.000
necessary
Token necessary
Feature activation+0.439
social
Token social
Feature activation+0.000
security
Token security
Feature activation+0.000
contributions
Token contributions
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000

INTERVAL 0.000 - 0.415
CONTAINS 99.963%

comprehensive
Token comprehensive
Feature activation+0.000
preventive
Token preventive
Feature activation+0.000
care
Token care
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
idea
Token idea
Feature activation+0.000
that
Token that
Feature activation+0.000
such
Token such
Feature activation+0.000
care
Token care
Feature activation+0.000
should
Token should
Feature activation+0.000
include
Token include
Feature activation+0.000
crus
Token crus
Feature activation+0.000
her
Tokenher
Feature activation+0.000
except
Token except
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
not
Token not
Feature activation+0.000
lying
Token lying
Feature activation+0.000
on
Token on
Feature activation+0.000
your
Token your
Feature activation+0.000
back
Token back
Feature activation+0.000
.
Token.
Feature activation+0.000
Arch
Token Arch
Feature activation+0.000
on
Tokenon
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
distance
Token distance
Feature activation+0.000
driver
Token driver
Feature activation+0.000
that
Token that
Feature activation+0.000
blends
Token blends
Feature activation+0.000
the
Token the
Feature activation+0.000
graceful
Token graceful
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
be
Token be
Feature activation+0.000
doing
Token doing
Feature activation+0.000
a
Token a
Feature activation+0.000
better
Token better
Feature activation+0.000
job
Token job
Feature activation+0.000
of
Token of
Feature activation+0.000
it
Token it
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
collected
Token collected
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
passengers
Token passengers
Feature activation+0.000
,
Token,
Feature activation+0.000
after
Token after
Feature activation+0.000
producing
Token producing
Feature activation+0.000
proof
Token proof
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