H7.5 top features

Top feature 0 in H7.5: (feature 43162)

TOP ACTIVATIONS
MAX = 2.683

family
Token family
Feature activation+0.000
's
Token's
Feature activation+0.000
bread
Token bread
Feature activation+0.528
winner
Tokenwinner
Feature activation+0.923
,
Token,
Feature activation+1.437
since
Token since
Feature activation+2.683
her
Token her
Feature activation+1.379
father
Token father
Feature activation+0.643
founded
Token founded
Feature activation+0.000
the
Token the
Feature activation+0.000
Fore
Token Fore
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
We
TokenWe
Feature activation+0.000
lost
Token lost
Feature activation+0.000
Krist
Token Krist
Feature activation+2.580
of
Tokenof
Feature activation+1.996
God
Token God
Feature activation+0.000
da
Tokenda
Feature activation+0.381
ert
Tokenert
Feature activation+0.847
,
Token,
Feature activation+1.070
Mark
Token Mark
Feature activation+0.000
took
Token took
Feature activation+0.000
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+2.495
young
Token young
Feature activation+2.345
William
Token William
Feature activation+0.534
,
Token,
Feature activation+0.469
then
Token then
Feature activation+0.000
age
Token age
Feature activation+0.000
took
Token took
Feature activation+0.000
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+2.495
young
Token young
Feature activation+2.345
William
Token William
Feature activation+0.534
,
Token,
Feature activation+0.469
then
Token then
Feature activation+0.000
age
Token age
Feature activation+0.000
9
Token 9
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.607
The
TokenThe
Feature activation+0.000
Higgins
Token Higgins
Feature activation+2.286
family
Token family
Feature activation+0.599
,
Token,
Feature activation+1.007
five
Token five
Feature activation+2.306
kids
Token kids
Feature activation+0.867
between
Token between
Feature activation+0.977
the
Token the
Feature activation+0.646
ages
Token ages
Feature activation+0.206
of
Token of
Feature activation+0.992
lawsuit
Token lawsuit
Feature activation+0.000
.
Token.
Feature activation+0.659
Ċ
TokenĊ
Feature activation+0.009
Ċ
TokenĊ
Feature activation+1.607
The
TokenThe
Feature activation+0.000
Higgins
Token Higgins
Feature activation+2.286
family
Token family
Feature activation+0.599
,
Token,
Feature activation+1.007
five
Token five
Feature activation+2.306
kids
Token kids
Feature activation+0.867
between
Token between
Feature activation+0.977
the
Token the
Feature activation+0.175
daughter
Token daughter
Feature activation+0.000
of
Token of
Feature activation+0.011
real
Token real
Feature activation+0.082
estate
Token estate
Feature activation+1.235
developer
Token developer
Feature activation+2.201
and
Token and
Feature activation+1.268
President
Token President
Feature activation+0.689
-
Token-
Feature activation+0.391
elect
Tokenelect
Feature activation+0.479
of
Token of
Feature activation+0.000
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.000
find
Token find
Feature activation+0.000
him
Token him
Feature activation+0.000
.
Token.
Feature activation+0.000
David
Token David
Feature activation+2.055
's
Token's
Feature activation+0.012
sister
Token sister
Feature activation+0.070
Danielle
Token Danielle
Feature activation+0.040
wrote
Token wrote
Feature activation+0.000
on
Token on
Feature activation+0.000
quez
Tokenquez
Feature activation+0.000
's
Token's
Feature activation+0.000
mother
Token mother
Feature activation+0.000
,
Token,
Feature activation+1.226
Arm
Token Arm
Feature activation+1.832
ida
Tokenida
Feature activation+2.032
Ch
Token Ch
Feature activation+0.377
acon
Tokenacon
Feature activation+0.414
,
Token,
Feature activation+0.000
told
Token told
Feature activation+0.000
reporters
Token reporters
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
We
TokenWe
Feature activation+0.000
lost
Token lost
Feature activation+0.000
Krist
Token Krist
Feature activation+2.580
of
Tokenof
Feature activation+1.996
God
Token God
Feature activation+0.000
da
Tokenda
Feature activation+0.381
ert
Tokenert
Feature activation+0.847
,
Token,
Feature activation+1.070
an
Token an
Feature activation+0.426
Kenny
Token Kenny
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+1.974
sk
Token sk
Feature activation+0.000
it
Tokenit
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
,"
Token,"
Feature activation+0.000
father
Token father
Feature activation+1.076
and
Token and
Feature activation+0.000
agent
Token agent
Feature activation+0.983
Ir
Token Ir
Feature activation+0.830
fan
Tokenfan
Feature activation+1.973
told
Token told
Feature activation+0.000
Kick
Token Kick
Feature activation+0.000
er
Tokener
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
mag
Tokenmag
Feature activation+0.000
down
Token down
Feature activation+0.000
the
Token the
Feature activation+0.000
street
Token street
Feature activation+0.000
.
Token.
Feature activation+0.000
Sa
Token Sa
Feature activation+0.939
eed
Tokeneed
Feature activation+1.898
,
Token,
Feature activation+0.130
with
Token with
Feature activation+0.000
long
Token long
Feature activation+0.000
hair
Token hair
Feature activation+0.000
,
Token,
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.497
,
Token,
Feature activation+1.785
Cookie
Token Cookie
Feature activation+1.892
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
.
Token.
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
was
Token was
Feature activation+0.000
joined
Token joined
Feature activation+0.000
by
Token by
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.244
,
Token,
Feature activation+1.874
Teresa
Token Teresa
Feature activation+0.000
Gi
Token Gi
Feature activation+0.000
ud
Tokenud
Feature activation+0.000
ice
Tokenice
Feature activation+0.000
.
Token.
Feature activation+0.000
family
Token family
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.656
Ċ
TokenĊ
Feature activation+0.903
We
TokenWe
Feature activation+0.544
have
Token have
Feature activation+1.011
6
Token 6
Feature activation+1.850
children
Token children
Feature activation+0.535
.
Token.
Feature activation+1.427
5
Token 5
Feature activation+1.349
that
Token that
Feature activation+0.419
are
Token are
Feature activation+0.414
Mar
TokenMar
Feature activation+0.000
quez
Tokenquez
Feature activation+0.000
's
Token's
Feature activation+0.000
mother
Token mother
Feature activation+0.000
,
Token,
Feature activation+1.226
Arm
Token Arm
Feature activation+1.832
ida
Tokenida
Feature activation+2.032
Ch
Token Ch
Feature activation+0.377
acon
Tokenacon
Feature activation+0.414
,
Token,
Feature activation+0.000
told
Token told
Feature activation+0.000
Magic
Token Magic
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.497
,
Token,
Feature activation+1.785
Cookie
Token Cookie
Feature activation+1.892
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
.
Token.
Feature activation+0.000
ground
Token ground
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dr
TokenDr
Feature activation+1.744
.
Token.
Feature activation+1.746
Fry
Token Fry
Feature activation+0.534
,
Token,
Feature activation+1.008
having
Token having
Feature activation+0.000
gone
Token gone
Feature activation+0.000
through
Token through
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
from
Token from
Feature activation+0.000
family
Token family
Feature activation+0.000
patriarch
Token patriarch
Feature activation+1.601
Ren
Token Ren
Feature activation+1.351
é
Tokené
Feature activation+1.745
Lind
Token Lind
Feature activation+0.877
em
Tokenem
Feature activation+1.359
ans
Tokenans
Feature activation+0.698
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

Top DFA by src position
MAX = 2.849

notes
Token notes
Feature activation-0.007
Top resid features:
,
Token,
Feature activation-0.015
Top resid features:
Chao
Token Chao
Feature activation+0.021
Top resid features:
is
Token is
Feature activation-0.010
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
family
Token family
Feature activation+2.674
Top resid features:
's
Token's
Feature activation+0.130
Top resid features:
bread
Token bread
Feature activation-0.000
Top resid features:
winner
Tokenwinner
Feature activation+0.358
Top resid features:
,
Token,
Feature activation+0.117
Top resid features:
since
Token since
Feature activation-0.049
Top resid features:
We
TokenWe
Feature activation+0.011
Top resid features:
think
Token think
Feature activation-0.002
Top resid features:
first
Token first
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
his
Token his
Feature activation-0.050
Top resid features:
family
Token family
Feature activation+2.849
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
loved
Token loved
Feature activation+0.011
Top resid features:
ones
Token ones
Feature activation+0.155
Top resid features:
to
Token to
Feature activation+0.019
Top resid features:
whom
Token whom
Feature activation+0.014
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
so
Token so
Feature activation+0.001
Top resid features:
Mark
Token Mark
Feature activation-0.024
Top resid features:
took
Token took
Feature activation-0.086
Top resid features:
his
Token his
Feature activation-0.006
Top resid features:
family
Token family
Feature activation+2.083
Top resid features:
,
Token,
Feature activation+0.224
Top resid features:
including
Token including
Feature activation+0.179
Top resid features:
young
Token young
Feature activation+0.000
Top resid features:
William
Token William
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
so
Token so
Feature activation+0.001
Top resid features:
Mark
Token Mark
Feature activation-0.005
Top resid features:
took
Token took
Feature activation-0.027
Top resid features:
his
Token his
Feature activation-0.003
Top resid features:
family
Token family
Feature activation+1.586
Top resid features:
,
Token,
Feature activation+0.093
Top resid features:
including
Token including
Feature activation+0.519
Top resid features:
young
Token young
Feature activation+0.001
Top resid features:
William
Token William
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.045
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
The
TokenThe
Feature activation+0.016
Top resid features:
Higgins
Token Higgins
Feature activation+0.017
Top resid features:
family
Token family
Feature activation+1.243
Top resid features:
,
Token,
Feature activation+0.586
Top resid features:
five
Token five
Feature activation+0.079
Top resid features:
kids
Token kids
Feature activation+0.000
Top resid features:
between
Token between
Feature activation+0.000
Top resid features:
the
Token the
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:
most
Token most
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.001
Top resid features:
One
TokenOne
Feature activation+0.009
Top resid features:
family
Token family
Feature activation+2.458
Top resid features:
says
Token says
Feature activation+0.074
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
ratings
Token ratings
Feature activation-0.012
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
grab
Tokengrab
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
She
Token She
Feature activation+0.018
Top resid features:
is
Token is
Feature activation+0.007
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
daughter
Token daughter
Feature activation+0.085
Top resid features:
of
Token of
Feature activation+2.599
Top resid features:
real
Token real
Feature activation+0.058
Top resid features:
estate
Token estate
Feature activation+0.017
Top resid features:
developer
Token developer
Feature activation+0.003
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
President
Token President
Feature activation+0.000
Top resid features:
post
Token post
Feature activation-0.015
Top resid features:
by
Token by
Feature activation-0.018
Top resid features:
Dre
Token Dre
Feature activation+0.005
Top resid features:
ger
Tokenger
Feature activation-0.000
Top resid features:
's
Token's
Feature activation+0.010
Top resid features:
family
Token family
Feature activation+2.468
Top resid features:
on
Token on
Feature activation-0.004
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
Facebook
Token Facebook
Feature activation-0.005
Top resid features:
page
Token page
Feature activation-0.002
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.020
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Mar
TokenMar
Feature activation+0.002
Top resid features:
quez
Tokenquez
Feature activation+0.007
Top resid features:
's
Token's
Feature activation+0.005
Top resid features:
mother
Token mother
Feature activation+2.311
Top resid features:
,
Token,
Feature activation+0.168
Top resid features:
Arm
Token Arm
Feature activation+0.069
Top resid features:
ida
Tokenida
Feature activation+0.002
Top resid features:
Ch
Token Ch
Feature activation+0.000
Top resid features:
acon
Tokenacon
Feature activation+0.000
Top resid features:
We
TokenWe
Feature activation+0.012
Top resid features:
think
Token think
Feature activation-0.006
Top resid features:
first
Token first
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
his
Token his
Feature activation-0.027
Top resid features:
family
Token family
Feature activation+2.117
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
loved
Token loved
Feature activation+0.013
Top resid features:
ones
Token ones
Feature activation+0.212
Top resid features:
to
Token to
Feature activation+0.020
Top resid features:
whom
Token whom
Feature activation+0.018
Top resid features:
it
Tokenit
Feature activation-0.029
Top resid features:
caused
Token caused
Feature activation+0.010
Top resid features:
Kenny
Token Kenny
Feature activation+0.010
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
his
Token his
Feature activation+0.034
Top resid features:
family
Token family
Feature activation+2.475
Top resid features:
,
Token,
Feature activation+0.128
Top resid features:
a
Token a
Feature activation+0.091
Top resid features:
sk
Token sk
Feature activation+0.000
Top resid features:
it
Tokenit
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
with
Token with
Feature activation-0.001
Top resid features:
Bor
Token Bor
Feature activation+0.005
Top resid features:
ussia
Tokenussia
Feature activation+0.000
Top resid features:
Dortmund
Token Dortmund
Feature activation-0.001
Top resid features:
,"
Token,"
Feature activation+0.009
Top resid features:
father
Token father
Feature activation+2.542
Top resid features:
and
Token and
Feature activation-0.043
Top resid features:
agent
Token agent
Feature activation+0.087
Top resid features:
Ir
Token Ir
Feature activation+0.057
Top resid features:
fan
Tokenfan
Feature activation+0.000
Top resid features:
told
Token told
Feature activation+0.000
Top resid features:
runs
Token runs
Feature activation+0.015
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
place
Token place
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.007
Top resid features:
four
Token four
Feature activation+0.004
Top resid features:
brothers
Token brothers
Feature activation+1.893
Top resid features:
,
Token,
Feature activation+0.016
Top resid features:
who
Token who
Feature activation+0.027
Top resid features:
like
Token like
Feature activation+0.002
Top resid features:
him
Token him
Feature activation-0.000
Top resid features:
were
Token were
Feature activation+0.006
Top resid features:
legend
Token legend
Feature activation-0.014
Top resid features:
Magic
Token Magic
Feature activation-0.001
Top resid features:
Johnson
Token Johnson
Feature activation-0.001
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
his
Token his
Feature activation+0.022
Top resid features:
wife
Token wife
Feature activation+2.148
Top resid features:
,
Token,
Feature activation+0.135
Top resid features:
Cookie
Token Cookie
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Monday
Token Monday
Feature activation+0.000
Top resid features:
he
Token he
Feature activation-0.002
Top resid features:
was
Token was
Feature activation+0.008
Top resid features:
joined
Token joined
Feature activation-0.004
Top resid features:
by
Token by
Feature activation+0.023
Top resid features:
his
Token his
Feature activation+0.016
Top resid features:
wife
Token wife
Feature activation+2.412
Top resid features:
,
Token,
Feature activation+0.022
Top resid features:
Teresa
Token Teresa
Feature activation+0.000
Top resid features:
Gi
Token Gi
Feature activation+0.000
Top resid features:
ud
Tokenud
Feature activation+0.000
Top resid features:
ice
Tokenice
Feature activation+0.000
Top resid features:
)
Token)
Feature activation-0.021
Top resid features:
Tell
Token Tell
Feature activation-0.003
Top resid features:
me
Token me
Feature activation-0.022
Top resid features:
about
Token about
Feature activation+0.017
Top resid features:
your
Token your
Feature activation+0.016
Top resid features:
family
Token family
Feature activation+1.676
Top resid features:
Ċ
TokenĊ
Feature activation+0.099
Top resid features:
Ċ
TokenĊ
Feature activation+0.063
Top resid features:
We
TokenWe
Feature activation+0.113
Top resid features:
have
Token have
Feature activation+0.424
Top resid features:
6
Token 6
Feature activation+0.054
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Mar
TokenMar
Feature activation+0.003
Top resid features:
quez
Tokenquez
Feature activation+0.007
Top resid features:
's
Token's
Feature activation+0.007
Top resid features:
mother
Token mother
Feature activation+1.950
Top resid features:
,
Token,
Feature activation+0.218
Top resid features:
Arm
Token Arm
Feature activation+0.020
Top resid features:
ida
Tokenida
Feature activation+0.000
Top resid features:
Ch
Token Ch
Feature activation+0.000
Top resid features:
acon
Tokenacon
Feature activation+0.000
Top resid features:
legend
Token legend
Feature activation-0.012
Top resid features:
Magic
Token Magic
Feature activation+0.036
Top resid features:
Johnson
Token Johnson
Feature activation-0.028
Top resid features:
and
Token and
Feature activation-0.010
Top resid features:
his
Token his
Feature activation+0.030
Top resid features:
wife
Token wife
Feature activation+2.361
Top resid features:
,
Token,
Feature activation+0.068
Top resid features:
Cookie
Token Cookie
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Monday
Token Monday
Feature activation+0.000
Top resid features:
such
Token such
Feature activation-0.000
Top resid features:
as
Token as
Feature activation+0.002
Top resid features:
themselves
Token themselves
Feature activation+0.087
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
couple
Token couple
Feature activation+0.976
Top resid features:
thought
Token thought
Feature activation+0.014
Top resid features:
they
Token they
Feature activation+0.014
Top resid features:
were
Token were
Feature activation+0.004
Top resid features:
on
Token on
Feature activation+0.001
Top resid features:
safe
Token safe
Feature activation-0.001
Top resid features:
Brewery
Token Brewery
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.006
Top resid features:
Ŀ
TokenĿ
Feature activation+0.001
Top resid features:
from
Token from
Feature activation-0.097
Top resid features:
family
Token family
Feature activation+1.521
Top resid features:
patriarch
Token patriarch
Feature activation+1.069
Top resid features:
Ren
Token Ren
Feature activation+0.025
Top resid features:
é
Tokené
Feature activation+0.042
Top resid features:
Lind
Token Lind
Feature activation+0.000
Top resid features:
em
Tokenem
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.06

Head 2: 0.03

Head 3: 0.06

Head 4: 0.04

Head 5: 0.52

Head 6: 0.07

Head 7: 0.03

Head 8: 0.06

Head 9: 0.05

Head 10: 0.02

Head 11: 0.02

Positive logits

sisters3.13

wives2.96

Wife2.94

siblings2.88

daughters2.87

grandparents2.81

endants2.79

Seym2.74

married2.74

family2.69

wife2.67

wife2.64

brothers2.64

aceae2.63

daughter2.61

sons2.60

spouses2.59

wives2.58

heirs2.56

cousins2.54

Negative logits

captcha-2.28

situational-2.16

Transparency-2.13

Dangerous-2.08

Feedback-2.03

destruct-2.01

danger-1.98

takedown-1.97

acceleration-1.96

risome-1.96

menace-1.93

dynamically-1.88

grading-1.88

Platform-1.88

blaster-1.88

congestion-1.88

selector-1.86

[|-1.85

CVE-1.83

bottleneck-1.82

INTERVAL 2.415 - 2.683
CONTAINS 0.000%

family
Token family
Feature activation+0.000
's
Token's
Feature activation+0.000
bread
Token bread
Feature activation+0.528
winner
Tokenwinner
Feature activation+0.923
,
Token,
Feature activation+1.437
since
Token since
Feature activation+2.683
her
Token her
Feature activation+1.379
father
Token father
Feature activation+0.643
founded
Token founded
Feature activation+0.000
the
Token the
Feature activation+0.000
Fore
Token Fore
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
We
TokenWe
Feature activation+0.000
lost
Token lost
Feature activation+0.000
Krist
Token Krist
Feature activation+2.580
of
Tokenof
Feature activation+1.996
God
Token God
Feature activation+0.000
da
Tokenda
Feature activation+0.381
ert
Tokenert
Feature activation+0.847
,
Token,
Feature activation+1.070
Mark
Token Mark
Feature activation+0.000
took
Token took
Feature activation+0.000
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+2.495
young
Token young
Feature activation+2.345
William
Token William
Feature activation+0.534
,
Token,
Feature activation+0.469
then
Token then
Feature activation+0.000
age
Token age
Feature activation+0.000

INTERVAL 2.146 - 2.415
CONTAINS 0.001%

the
Token the
Feature activation+0.175
daughter
Token daughter
Feature activation+0.000
of
Token of
Feature activation+0.011
real
Token real
Feature activation+0.082
estate
Token estate
Feature activation+1.235
developer
Token developer
Feature activation+2.201
and
Token and
Feature activation+1.268
President
Token President
Feature activation+0.689
-
Token-
Feature activation+0.391
elect
Tokenelect
Feature activation+0.479
of
Token of
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
.
Token.
Feature activation+0.659
Ċ
TokenĊ
Feature activation+0.009
Ċ
TokenĊ
Feature activation+1.607
The
TokenThe
Feature activation+0.000
Higgins
Token Higgins
Feature activation+2.286
family
Token family
Feature activation+0.599
,
Token,
Feature activation+1.007
five
Token five
Feature activation+2.306
kids
Token kids
Feature activation+0.867
between
Token between
Feature activation+0.977
Ċ
TokenĊ
Feature activation+1.607
The
TokenThe
Feature activation+0.000
Higgins
Token Higgins
Feature activation+2.286
family
Token family
Feature activation+0.599
,
Token,
Feature activation+1.007
five
Token five
Feature activation+2.306
kids
Token kids
Feature activation+0.867
between
Token between
Feature activation+0.977
the
Token the
Feature activation+0.646
ages
Token ages
Feature activation+0.206
of
Token of
Feature activation+0.992
took
Token took
Feature activation+0.000
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+2.495
young
Token young
Feature activation+2.345
William
Token William
Feature activation+0.534
,
Token,
Feature activation+0.469
then
Token then
Feature activation+0.000
age
Token age
Feature activation+0.000
9
Token 9
Feature activation+0.000

INTERVAL 1.878 - 2.146
CONTAINS 0.001%

Kenny
Token Kenny
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
family
Token family
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+1.974
sk
Token sk
Feature activation+0.000
it
Tokenit
Feature activation+0.000
that
Token that
Feature activation+0.000
was
Token was
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
We
TokenWe
Feature activation+0.000
lost
Token lost
Feature activation+0.000
Krist
Token Krist
Feature activation+2.580
of
Tokenof
Feature activation+1.996
God
Token God
Feature activation+0.000
da
Tokenda
Feature activation+0.381
ert
Tokenert
Feature activation+0.847
,
Token,
Feature activation+1.070
an
Token an
Feature activation+0.426
quez
Tokenquez
Feature activation+0.000
's
Token's
Feature activation+0.000
mother
Token mother
Feature activation+0.000
,
Token,
Feature activation+1.226
Arm
Token Arm
Feature activation+1.832
ida
Tokenida
Feature activation+2.032
Ch
Token Ch
Feature activation+0.377
acon
Tokenacon
Feature activation+0.414
,
Token,
Feature activation+0.000
told
Token told
Feature activation+0.000
reporters
Token reporters
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.497
,
Token,
Feature activation+1.785
Cookie
Token Cookie
Feature activation+1.892
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
Monday
Token Monday
Feature activation+0.000
.
Token.
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
down
Token down
Feature activation+0.000
the
Token the
Feature activation+0.000
street
Token street
Feature activation+0.000
.
Token.
Feature activation+0.000
Sa
Token Sa
Feature activation+0.939
eed
Tokeneed
Feature activation+1.898
,
Token,
Feature activation+0.130
with
Token with
Feature activation+0.000
long
Token long
Feature activation+0.000
hair
Token hair
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.610 - 1.878
CONTAINS 0.001%

and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
wife
Token wife
Feature activation+0.000
,
Token,
Feature activation+0.468
Vid
Token Vid
Feature activation+0.684
ula
Tokenula
Feature activation+1.626
,
Token,
Feature activation+0.000
co
Token co
Feature activation+0.000
-
Token-
Feature activation+0.000
founded
Tokenfounded
Feature activation+0.000
the
Token the
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.000
daughter
Token daughter
Feature activation+0.000
of
Token of
Feature activation+0.000
Thomas
Token Thomas
Feature activation+1.638
Hart
Token Hart
Feature activation+0.000
sh
Tokensh
Feature activation+0.000
orn
Tokenorn
Feature activation+0.678
Lawrence
Token Lawrence
Feature activation+0.000
and
Token and
Feature activation+1.391
family
Token family
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.656
Ċ
TokenĊ
Feature activation+0.903
We
TokenWe
Feature activation+0.544
have
Token have
Feature activation+1.011
6
Token 6
Feature activation+1.850
children
Token children
Feature activation+0.535
.
Token.
Feature activation+1.427
5
Token 5
Feature activation+1.349
that
Token that
Feature activation+0.419
are
Token are
Feature activation+0.414
ground
Token ground
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dr
TokenDr
Feature activation+1.744
.
Token.
Feature activation+1.746
Fry
Token Fry
Feature activation+0.534
,
Token,
Feature activation+1.008
having
Token having
Feature activation+0.000
gone
Token gone
Feature activation+0.000
through
Token through
Feature activation+0.000
legal
Token legal
Feature activation+0.000
ground
Token ground
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dr
TokenDr
Feature activation+1.744
.
Token.
Feature activation+1.746
Fry
Token Fry
Feature activation+0.534
,
Token,
Feature activation+1.008
having
Token having
Feature activation+0.000
gone
Token gone
Feature activation+0.000

INTERVAL 1.342 - 1.610
CONTAINS 0.002%

for
Token for
Feature activation+0.000
over
Token over
Feature activation+0.000
40
Token 40
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
Joseph
Token Joseph
Feature activation+1.430
was
Token was
Feature activation+0.000
honored
Token honored
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
parents
Token parents
Feature activation+0.000
'
Token'
Feature activation+0.000
basement
Token basement
Feature activation+0.000
when
Token when
Feature activation+0.155
Hear
Token Hear
Feature activation+0.000
n
Tokenn
Feature activation+1.530
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
give
Token give
Feature activation+0.000
Russell
Token Russell
Feature activation+0.000
a
Token a
Feature activation+0.000
and
Token and
Feature activation+0.872
two
Token two
Feature activation+0.101
small
Token small
Feature activation+0.000
children
Token children
Feature activation+0.000
(
Token (
Feature activation+0.125
including
Tokenincluding
Feature activation+1.526
yours
Token yours
Feature activation+0.179
truly
Token truly
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
We
TokenWe
Feature activation+0.544
have
Token have
Feature activation+1.011
6
Token 6
Feature activation+1.850
children
Token children
Feature activation+0.535
.
Token.
Feature activation+1.427
5
Token 5
Feature activation+1.349
that
Token that
Feature activation+0.419
are
Token are
Feature activation+0.414
living
Token living
Feature activation+0.211
.
Token.
Feature activation+1.074
I
Token I
Feature activation+0.539
but
Token but
Feature activation+0.000
a
Token a
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
.
Token.
Feature activation+0.659
Ċ
TokenĊ
Feature activation+0.009
Ċ
TokenĊ
Feature activation+1.607
The
TokenThe
Feature activation+0.000
Higgins
Token Higgins
Feature activation+2.286
family
Token family
Feature activation+0.599
,
Token,
Feature activation+1.007
five
Token five
Feature activation+2.306

INTERVAL 1.073 - 1.342
CONTAINS 0.003%

Ċ
TokenĊ
Feature activation+0.000
S
TokenS
Feature activation+0.000
iblings
Tokeniblings
Feature activation+0.000
:
Token:
Feature activation+0.356
Jane
Token Jane
Feature activation+1.557
Seymour
Token Seymour
Feature activation+1.183
had
Token had
Feature activation+0.578
three
Token three
Feature activation+0.172
older
Token older
Feature activation+0.275
brothers
Token brothers
Feature activation+0.000
,
Token,
Feature activation+0.000
30
Token 30
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
married
Token married
Feature activation+0.000
with
Token with
Feature activation+1.296
a
Token a
Feature activation+0.626
3
Token 3
Feature activation+0.508
-
Token-
Feature activation+0.377
week
Tokenweek
Feature activation+0.005
-
Token-
Feature activation+0.000
with
Token with
Feature activation+0.000
Bor
Token Bor
Feature activation+0.000
ussia
Tokenussia
Feature activation+0.000
Dortmund
Token Dortmund
Feature activation+0.000
,"
Token,"
Feature activation+0.000
father
Token father
Feature activation+1.076
and
Token and
Feature activation+0.000
agent
Token agent
Feature activation+0.983
Ir
Token Ir
Feature activation+0.830
fan
Tokenfan
Feature activation+1.973
told
Token told
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
,
Token,
Feature activation+0.016
Donald
Token Donald
Feature activation+0.048
Trump
Token Trump
Feature activation+0.000
and
Token and
Feature activation+1.086
former
Token former
Feature activation+0.000
model
Token model
Feature activation+0.013
Iv
Token Iv
Feature activation+0.000
ana
Tokenana
Feature activation+0.258
Trump
Token Trump
Feature activation+0.000
wedding
Token wedding
Feature activation+0.000
anniversary
Token anniversary
Feature activation+0.000
.
Token.
Feature activation+0.000
Prince
Token Prince
Feature activation+0.810
William
Token William
Feature activation+0.267
and
Token and
Feature activation+1.215
Kate
Token Kate
Feature activation+0.110
famously
Token famously
Feature activation+0.000
broke
Token broke
Feature activation+0.000
up
Token up
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 0.805 - 1.073
CONTAINS 0.010%

have
Token have
Feature activation+0.682
4
Token 4
Feature activation+0.811
daughters
Token daughters
Feature activation+0.000
(
Token (
Feature activation+0.351
D
TokenD
Feature activation+0.955
ove
Tokenove
Feature activation+1.009
,
Token,
Feature activation+0.998
Eden
Token Eden
Feature activation+0.457
,
Token,
Feature activation+0.711
Memory
Token Memory
Feature activation+0.000
,
Token,
Feature activation+0.561
children
Token children
Feature activation+0.000
together
Token together
Feature activation+0.000
,
Token,
Feature activation+0.062
Kate
Token Kate
Feature activation+1.047
,
Token,
Feature activation+0.916
Natalie
Token Natalie
Feature activation+0.819
and
Token and
Feature activation+0.876
Harry
Token Harry
Feature activation+0.723
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.408
parted
Token parted
Feature activation+0.025
,
Token,
Feature activation+0.000
Md
Token Md
Feature activation+0.000
.,
Token.,
Feature activation+0.000
whose
Token whose
Feature activation+0.000
wife
Token wife
Feature activation+0.000
Susan
Token Susan
Feature activation+1.010
was
Token was
Feature activation+0.000
killed
Token killed
Feature activation+0.000
in
Token in
Feature activation+0.000
August
Token August
Feature activation+0.000
2010
Token 2010
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.281
two
Token two
Feature activation+0.093
-
Token-
Feature activation+0.433
and
Tokenand
Feature activation+0.429
-
Token-
Feature activation+0.821
a
Tokena
Feature activation+0.337
-
Token-
Feature activation+0.000
half
Tokenhalf
Feature activation+0.093
year
Token year
Feature activation+0.000
boy
Token boy
Feature activation+0.000
disbelief
Token disbelief
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
me
Token me
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Mike
Token Mike
Feature activation+0.973
G
Token G
Feature activation+0.000
atto
Tokenatto
Feature activation+0.046
told
Token told
Feature activation+0.000
reporters
Token reporters
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.537 - 0.805
CONTAINS 0.016%

to
Token to
Feature activation+0.181
K
Token K
Feature activation+0.876
ami
Tokenami
Feature activation+0.589
.
Token.
Feature activation+1.111
We
Token We
Feature activation+0.669
have
Token have
Feature activation+0.682
4
Token 4
Feature activation+0.811
daughters
Token daughters
Feature activation+0.000
(
Token (
Feature activation+0.351
D
TokenD
Feature activation+0.955
ove
Tokenove
Feature activation+1.009
)
Token)
Feature activation+0.000
reports
Token reports
Feature activation+0.000
that
Token that
Feature activation+0.000
Lawrence
Token Lawrence
Feature activation+0.489
was
Token was
Feature activation+0.879
born
Token born
Feature activation+0.727
on
Token on
Feature activation+0.000
4
Token 4
Feature activation+0.000
October
Token October
Feature activation+0.000
1896
Token 1896
Feature activation+0.000
in
Token in
Feature activation+0.000
son
Token son
Feature activation+0.000
(
Token (
Feature activation+0.000
named
Tokennamed
Feature activation+0.000
Seven
Token Seven
Feature activation+0.000
).
Token).
Feature activation+0.474
People
Token People
Feature activation+0.627
always
Token always
Feature activation+0.000
ask
Token ask
Feature activation+0.000
us
Token us
Feature activation+0.000
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
later
Token later
Feature activation+0.000
publicly
Token publicly
Feature activation+0.000
identified
Token identified
Feature activation+0.000
herself
Token herself
Feature activation+0.000
as
Token as
Feature activation+0.138
actor
Token actor
Feature activation+0.630
,
Token,
Feature activation+0.171
singer
Token singer
Feature activation+0.000
and
Token and
Feature activation+0.000
TV
Token TV
Feature activation+0.000
presenter
Token presenter
Feature activation+0.140
County
Token County
Feature activation+0.000
parents
Token parents
Feature activation+0.000
concerned
Token concerned
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.466
Ċ
TokenĊ
Feature activation+0.683
Matthew
TokenMatthew
Feature activation+1.029
Wh
Token Wh
Feature activation+0.000
ool
Tokenool
Feature activation+0.009
ery
Tokenery
Feature activation+0.329
and
Token and
Feature activation+0.270

INTERVAL 0.268 - 0.537
CONTAINS 0.049%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dr
TokenDr
Feature activation+1.744
.
Token.
Feature activation+1.746
Fry
Token Fry
Feature activation+0.534
,
Token,
Feature activation+1.008
having
Token having
Feature activation+0.000
gone
Token gone
Feature activation+0.000
through
Token through
Feature activation+0.000
a
Token a
Feature activation+0.000
His
TokenHis
Feature activation+0.000
78
Token 78
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.320
father
Token father
Feature activation+0.000
founded
Token founded
Feature activation+0.000
the
Token the
Feature activation+0.000
Visual
Token Visual
Feature activation+0.000
Arts
Token Arts
Feature activation+0.000
in
Token in
Feature activation+0.000
"
Token "
Feature activation+0.000
some
Tokensome
Feature activation+0.000
capacity
Token capacity
Feature activation+0.000
,"
Token,"
Feature activation+0.000
including
Token including
Feature activation+0.280
Gab
Token Gab
Feature activation+0.000
ou
Tokenou
Feature activation+0.000
rey
Tokenrey
Feature activation+0.000
Sid
Token Sid
Feature activation+0.000
ibe
Tokenibe
Feature activation+0.116
.
Token.
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
among
Token among
Feature activation+0.000
these
Token these
Feature activation+0.000
is
Token is
Feature activation+0.000
Et
Token Et
Feature activation+0.346
ch
Tokench
Feature activation+0.000
mi
Tokenmi
Feature activation+0.194
ad
Tokenad
Feature activation+0.000
zin
Tokenzin
Feature activation+0.096
Cathedral
Token Cathedral
Feature activation+0.000
.
Token.
Feature activation+1.074
I
Token I
Feature activation+0.539
got
Token got
Feature activation+0.530
married
Token married
Feature activation+0.549
at
Token at
Feature activation+0.397
the
Token the
Feature activation+0.355
age
Token age
Feature activation+0.067
of
Token of
Feature activation+0.069
20
Token 20
Feature activation+0.000
to
Token to
Feature activation+0.181
K
Token K
Feature activation+0.876

INTERVAL 0.000 - 0.268
CONTAINS 99.918%

2
Token 2
Feature activation+0.000
,
Token,
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
leading
Token leading
Feature activation+0.000
bitcoin
Token bitcoin
Feature activation+0.000
exchange
Token exchange
Feature activation+0.000
by
Token by
Feature activation+0.000
USD
Token USD
Feature activation+0.000
volume
Token volume
Feature activation+0.000
fully
Token fully
Feature activation+0.000
satisfied
Token satisfied
Feature activation+0.000
.
Token.
Feature activation+0.000
Yet
Token Yet
Feature activation+0.000
Germany
Token Germany
Feature activation+0.000
could
Token could
Feature activation+0.000
l
Token l
Feature activation+0.000
ope
Tokenope
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
match
Token match
Feature activation+0.000
a
Token a
Feature activation+0.000
highlight
Token highlight
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
life
Token life
Feature activation+0.000
,
Token,
Feature activation+0.000
while
Token while
Feature activation+0.000
his
Token his
Feature activation+0.000
uncle
Token uncle
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
"
Token "
Feature activation+0.000
She
TokenShe
Feature activation+0.000
was
Token was
Feature activation+0.000
babys
Token babys
Feature activation+0.000
itting
Tokenitting
Feature activation+0.000
her
Token her
Feature activation+0.000
niece
Token niece
Feature activation+0.000
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
in
Token in
Feature activation+0.000
from
Token from
Feature activation+0.000
them
Token them
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
long
Token long
Feature activation+0.000
term
Token term
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
our
Token our
Feature activation+0.000
free
Token free
Feature activation+0.000
report
Token report
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 H7.5: (feature 15509)

TOP ACTIVATIONS
MAX = 3.932

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
White
TokenWhite
Feature activation+0.000
House
Token House
Feature activation+0.000
press
Token press
Feature activation+0.000
secretary
Token secretary
Feature activation+0.542
Josh
Token Josh
Feature activation+3.932
Earn
Token Earn
Feature activation+1.097
est
Tokenest
Feature activation+0.000
said
Token said
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
State
Token State
Feature activation+0.000
Department
Token Department
Feature activation+0.000
spokeswoman
Token spokeswoman
Feature activation+1.230
Jen
Token Jen
Feature activation+1.759
Ps
Token Ps
Feature activation+0.000
aki
Tokenaki
Feature activation+0.000
called
Token called
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
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
Sean
Token Sean
Feature activation+1.642
Spicer
Token Spicer
Feature activation+0.000
was
Token was
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
RNC
Token RNC
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
State
Token State
Feature activation+0.000
Department
Token Department
Feature activation+0.000
spokeswoman
Token spokeswoman
Feature activation+1.230
Jen
Token Jen
Feature activation+1.759
Ps
Token Ps
Feature activation+0.000
aki
Tokenaki
Feature activation+0.000
called
Token called
Feature activation+0.000
on
Token on
Feature activation+0.000
White
TokenWhite
Feature activation+0.000
House
Token House
Feature activation+0.000
press
Token press
Feature activation+0.000
secretary
Token secretary
Feature activation+0.542
Josh
Token Josh
Feature activation+3.932
Earn
Token Earn
Feature activation+1.097
est
Tokenest
Feature activation+0.000
said
Token said
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
the
Token the
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
State
Token State
Feature activation+0.000
Department
Token Department
Feature activation+0.000
spokesman
Token spokesman
Feature activation+0.000
Mark
Token Mark
Feature activation+1.036
T
Token T
Feature activation+0.000
oner
Tokenoner
Feature activation+0.000
said
Token said
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
note
Token note
Feature activation+0.000
from
Token from
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
speech
Token speech
Feature activation+0.000
writer
Tokenwriter
Feature activation+0.693
Dan
Token Dan
Feature activation+0.335
Sch
Token Sch
Feature activation+0.000
wer
Tokenwer
Feature activation+0.000
in
Tokenin
Feature activation+0.000
.
Token.
Feature activation+0.000
open
Token open
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
head
Token head
Feature activation+0.000
of
Token of
Feature activation+0.000
blonde
Token blonde
Feature activation+0.604
hair
Token hair
Feature activation+0.000
came
Token came
Feature activation+0.000
storm
Token storm
Feature activation+0.000
ing
Tokening
Feature activation+0.000
out
Token out
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
White
TokenWhite
Feature activation+0.000
House
Token House
Feature activation+0.000
press
Token press
Feature activation+0.000
secretary
Token secretary
Feature activation+0.542
Josh
Token Josh
Feature activation+3.932
Earn
Token Earn
Feature activation+1.097
est
Tokenest
Feature activation+0.000
said
Token said
Feature activation+0.000
on
Token on
Feature activation+0.000
note
Token note
Feature activation+0.000
from
Token from
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
speech
Token speech
Feature activation+0.000
writer
Tokenwriter
Feature activation+0.693
Dan
Token Dan
Feature activation+0.335
Sch
Token Sch
Feature activation+0.000
wer
Tokenwer
Feature activation+0.000
in
Tokenin
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
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
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
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
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
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

Top DFA by src position
MAX = 10.065

<|endoftext|>
Token<|endoftext|>
Feature activation+9.769
Top resid features:
a
Token a
Feature activation-0.009
Top resid features:
DA
Token DA
Feature activation-0.006
Top resid features:
O
TokenO
Feature activation-0.003
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+9.946
Top resid features:
adi
Tokenadi
Feature activation-0.016
Top resid features:
was
Token was
Feature activation-0.006
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
compound
Token compound
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+9.520
Top resid features:
up
Token up
Feature activation-0.008
Top resid features:
for
Token for
Feature activation-0.002
Top resid features:
POLITICO
Token POLITICO
Feature activation-0.000
Top resid features:
Play
Token Play
Feature activation-0.002
Top resid features:
book
Tokenbook
Feature activation-0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+9.583
Top resid features:
adi
Tokenadi
Feature activation-0.088
Top resid features:
was
Token was
Feature activation-0.014
Top resid features:
in
Token in
Feature activation-0.008
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
compound
Token compound
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+9.520
Top resid features:
a
Token a
Feature activation-0.013
Top resid features:
DA
Token DA
Feature activation-0.007
Top resid features:
O
TokenO
Feature activation-0.003
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+9.784
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
killing
Token killing
Feature activation-0.003
Top resid features:
510
Token 510
Feature activation-0.007
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
wounding
Token wounding
Feature activation-0.008
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+7.951
Top resid features:
her
Token her
Feature activation-0.166
Top resid features:
daughter
Token daughter
Feature activation+0.010
Top resid features:
suggested
Token suggested
Feature activation-0.044
Top resid features:
that
Token that
Feature activation-0.037
Top resid features:
it
Token it
Feature activation-0.024
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+7.913
Top resid features:
I
Token I
Feature activation-0.004
Top resid features:
would
Token would
Feature activation-0.003
Top resid features:
explain
Token explain
Feature activation-0.005
Top resid features:
everything
Token everything
Feature activation-0.003
Top resid features:
after
Token after
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+9.239
Top resid features:
a
Token a
Feature activation-0.012
Top resid features:
DA
Token DA
Feature activation-0.019
Top resid features:
O
TokenO
Feature activation-0.003
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+9.354
Top resid features:
her
Token her
Feature activation-0.054
Top resid features:
daughter
Token daughter
Feature activation+0.030
Top resid features:
suggested
Token suggested
Feature activation-0.012
Top resid features:
that
Token that
Feature activation-0.024
Top resid features:
it
Token it
Feature activation-0.008
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+8.556
Top resid features:
rik
Tokenrik
Feature activation-0.191
Top resid features:
ar
Tokenar
Feature activation-0.122
Top resid features:
said
Token said
Feature activation-0.004
Top resid features:
Saturday
Token Saturday
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.041
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+7.583
Top resid features:
rik
Tokenrik
Feature activation-0.243
Top resid features:
ar
Tokenar
Feature activation-0.105
Top resid features:
said
Token said
Feature activation+0.050
Top resid features:
Saturday
Token Saturday
Feature activation+0.026
Top resid features:
.
Token.
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+9.411
Top resid features:
rik
Tokenrik
Feature activation-0.116
Top resid features:
ar
Tokenar
Feature activation-0.037
Top resid features:
said
Token said
Feature activation+0.035
Top resid features:
Saturday
Token Saturday
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.042
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+8.993
Top resid features:
rik
Tokenrik
Feature activation-0.109
Top resid features:
ar
Tokenar
Feature activation-0.020
Top resid features:
said
Token said
Feature activation+0.233
Top resid features:
Saturday
Token Saturday
Feature activation+0.031
Top resid features:
.
Token.
Feature activation-0.049
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+7.777
Top resid features:
rik
Tokenrik
Feature activation-0.100
Top resid features:
ar
Tokenar
Feature activation-0.020
Top resid features:
said
Token said
Feature activation+0.134
Top resid features:
Saturday
Token Saturday
Feature activation-0.053
Top resid features:
.
Token.
Feature activation-0.205
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+7.658
Top resid features:
rik
Tokenrik
Feature activation-0.087
Top resid features:
ar
Tokenar
Feature activation-0.019
Top resid features:
said
Token said
Feature activation+0.002
Top resid features:
Saturday
Token Saturday
Feature activation+0.017
Top resid features:
.
Token.
Feature activation-0.084
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+9.143
Top resid features:
rik
Tokenrik
Feature activation-0.236
Top resid features:
ar
Tokenar
Feature activation-0.062
Top resid features:
said
Token said
Feature activation-0.292
Top resid features:
Saturday
Token Saturday
Feature activation+0.037
Top resid features:
.
Token.
Feature activation-0.094
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+9.370
Top resid features:
rik
Tokenrik
Feature activation-0.587
Top resid features:
ar
Tokenar
Feature activation-0.151
Top resid features:
said
Token said
Feature activation-0.331
Top resid features:
Saturday
Token Saturday
Feature activation+0.046
Top resid features:
.
Token.
Feature activation-0.040
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+10.065
Top resid features:
rik
Tokenrik
Feature activation-0.127
Top resid features:
ar
Tokenar
Feature activation-0.060
Top resid features:
said
Token said
Feature activation-0.152
Top resid features:
Saturday
Token Saturday
Feature activation+0.024
Top resid features:
.
Token.
Feature activation-0.061
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+7.809
Top resid features:
rik
Tokenrik
Feature activation-0.415
Top resid features:
ar
Tokenar
Feature activation-0.244
Top resid features:
said
Token said
Feature activation-1.710
Top resid features:
Saturday
Token Saturday
Feature activation-1.538
Top resid features:
.
Token.
Feature activation-0.187
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.04

Head 2: 0.03

Head 3: 0.05

Head 4: 0.04

Head 5: 0.52

Head 6: 0.05

Head 7: 0.03

Head 8: 0.08

Head 9: 0.04

Head 10: 0.04

Head 11: 0.02

Positive logits

ortment2.44

Asked2.38

advertising2.28

scheduling2.25

atform2.16

Regarding2.12

SPA2.07

Animation2.06

VERTIS2.03

presenter2.03

briefed2.02

NEWS2.00

updates2.00

reiter2.00

announced1.95

Statement1.94

newsp1.93

Pages1.92

Request1.91

briefing1.90

Negative logits

igon-2.34

onite-2.30

monastery-2.25

Leviathan-2.23

Scholar-2.22

Arbor-2.20

Viking-2.16

boulder-2.14

Haunted-2.14

Chaos-2.13

aurus-2.12

Demons-2.08

extinct-2.06

Ort-2.05

Thieves-2.05

Exodus-2.04

Antioch-2.01

ossus-2.01

aeus-2.01

Geh-1.97

INTERVAL 3.539 - 3.932
CONTAINS 0.000%

<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
White
TokenWhite
Feature activation+0.000
House
Token House
Feature activation+0.000
press
Token press
Feature activation+0.000
secretary
Token secretary
Feature activation+0.542
Josh
Token Josh
Feature activation+3.932
Earn
Token Earn
Feature activation+1.097
est
Tokenest
Feature activation+0.000
said
Token said
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000

INTERVAL 3.146 - 3.539
CONTAINS 0.000%

INTERVAL 2.752 - 3.146
CONTAINS 0.000%

INTERVAL 2.359 - 2.752
CONTAINS 0.000%

INTERVAL 1.966 - 2.359
CONTAINS 0.000%

INTERVAL 1.573 - 1.966
CONTAINS 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
Sean
Token Sean
Feature activation+1.642
Spicer
Token Spicer
Feature activation+0.000
was
Token was
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
RNC
Token RNC
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
State
Token State
Feature activation+0.000
Department
Token Department
Feature activation+0.000
spokeswoman
Token spokeswoman
Feature activation+1.230
Jen
Token Jen
Feature activation+1.759
Ps
Token Ps
Feature activation+0.000
aki
Tokenaki
Feature activation+0.000
called
Token called
Feature activation+0.000
on
Token on
Feature activation+0.000
both
Token both
Feature activation+0.000

INTERVAL 1.180 - 1.573
CONTAINS 0.000%

.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
State
Token State
Feature activation+0.000
Department
Token Department
Feature activation+0.000
spokeswoman
Token spokeswoman
Feature activation+1.230
Jen
Token Jen
Feature activation+1.759
Ps
Token Ps
Feature activation+0.000
aki
Tokenaki
Feature activation+0.000
called
Token called
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 0.786 - 1.180
CONTAINS 0.000%

White
TokenWhite
Feature activation+0.000
House
Token House
Feature activation+0.000
press
Token press
Feature activation+0.000
secretary
Token secretary
Feature activation+0.542
Josh
Token Josh
Feature activation+3.932
Earn
Token Earn
Feature activation+1.097
est
Tokenest
Feature activation+0.000
said
Token said
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
the
Token the
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
State
Token State
Feature activation+0.000
Department
Token Department
Feature activation+0.000
spokesman
Token spokesman
Feature activation+0.000
Mark
Token Mark
Feature activation+1.036
T
Token T
Feature activation+0.000
oner
Tokenoner
Feature activation+0.000
said
Token said
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 0.393 - 0.786
CONTAINS 0.000%

âĢ
Token âĢ
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
White
TokenWhite
Feature activation+0.000
House
Token House
Feature activation+0.000
press
Token press
Feature activation+0.000
secretary
Token secretary
Feature activation+0.542
Josh
Token Josh
Feature activation+3.932
Earn
Token Earn
Feature activation+1.097
est
Tokenest
Feature activation+0.000
said
Token said
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
note
Token note
Feature activation+0.000
from
Token from
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
speech
Token speech
Feature activation+0.000
writer
Tokenwriter
Feature activation+0.693
Dan
Token Dan
Feature activation+0.335
Sch
Token Sch
Feature activation+0.000
wer
Tokenwer
Feature activation+0.000
in
Tokenin
Feature activation+0.000
.
Token.
Feature activation+0.000
open
Token open
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
head
Token head
Feature activation+0.000
of
Token of
Feature activation+0.000
blonde
Token blonde
Feature activation+0.604
hair
Token hair
Feature activation+0.000
came
Token came
Feature activation+0.000
storm
Token storm
Feature activation+0.000
ing
Tokening
Feature activation+0.000
out
Token out
Feature activation+0.000

INTERVAL 0.000 - 0.393
CONTAINS 99.999%

But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
tricky
Token tricky
Feature activation+0.000
thing
Token thing
Feature activation+0.000
here
Token here
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
US
Token US
Feature activation+0.000
policy
Token policy
Feature activation+0.000
is
Token is
Feature activation+0.000
still
Token still
Feature activation+0.000
early
Token early
Feature activation+0.000
models
Token models
Feature activation+0.000
had
Token had
Feature activation+0.000
the
Token the
Feature activation+0.000
optional
Token optional
Feature activation+0.000
Electro
Token Electro
Feature activation+0.000
Gy
Token Gy
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
-
Token-
Feature activation+0.000
C
TokenC
Feature activation+0.000
ator
Tokenator
Feature activation+0.000
viable
Token viable
Feature activation+0.000
option
Token option
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Neither
TokenNeither
Feature activation+0.000
the
Token the
Feature activation+0.000
Treasury
Token Treasury
Feature activation+0.000
Department
Token Department
Feature activation+0.000
rup
Tokenrup
Feature activation+0.000
ulously
Tokenulously
Feature activation+0.000
honest
Token honest
Feature activation+0.000
magazine
Token magazine
Feature activation+0.000
that
Token that
Feature activation+0.000
cast
Token cast
Feature activation+0.000
an
Token an
Feature activation+0.000
appra
Token appra
Feature activation+0.000
ising
Tokenising
Feature activation+0.000
eye
Token eye
Feature activation+0.000
on
Token on
Feature activation+0.000
Mary
Token Mary
Feature activation+0.000
,
Token,
Feature activation+0.000
an
Token an
Feature activation+0.000
enemy
Token enemy
Feature activation+0.000
of
Token of
Feature activation+0.000
Daredevil
Token Daredevil
Feature activation+0.000
who
Token who
Feature activation+0.000
suffers
Token suffers
Feature activation+0.000
from
Token from
Feature activation+0.000
diss
Token diss
Feature activation+0.000
oci
Tokenoci
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 H7.5: (feature 8717)

TOP ACTIVATIONS
MAX = 2.693

.
Token.
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
Information
Token Information
Feature activation+0.000
Officer
Token Officer
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Van
Token Van
Feature activation+2.693
R
TokenR
Feature activation+0.589
oe
Tokenoe
Feature activation+0.000
kel
Tokenkel
Feature activation+0.000
and
Token and
Feature activation+0.000
U
Token U
Feature activation+0.000
,
Token,
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Steve
TokenSteve
Feature activation+0.000
D
Token D
Feature activation+2.291
illard
Tokenillard
Feature activation+0.000
's
Token's
Feature activation+0.000
infectious
Token infectious
Feature activation+0.000
excitement
Token excitement
Feature activation+0.000
,
Token,
Feature activation+0.000
community
Token community
Feature activation+0.000
?"
Token?"
Feature activation+0.000
MSNBC
Token MSNBC
Feature activation+0.000
's
Token's
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
K
Token K
Feature activation+2.103
orn
Tokenorn
Feature activation+0.000
ack
Tokenack
Feature activation+0.000
i
Tokeni
Feature activation+0.000
asked
Token asked
Feature activation+0.000
Hugh
Token Hugh
Feature activation+0.000
said
Token said
Feature activation+0.000
Go
Token Go
Feature activation+0.000
Coin
TokenCoin
Feature activation+0.000
CEO
Token CEO
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Be
Token Be
Feature activation+1.621
a
Tokena
Feature activation+0.000
ure
Tokenure
Feature activation+0.000
gard
Tokengard
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
Token He
Feature activation+0.000
p
Token p
Feature activation+0.000
uked
Tokenuked
Feature activation+0.000
on
Token on
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Mc
Token Mc
Feature activation+1.573
Queen
TokenQueen
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
of
Token of
Feature activation+0.000
Hive
Token Hive
Feature activation+0.000
Wallet
Token Wallet
Feature activation+0.000
,
Token,
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Be
Token Be
Feature activation+1.495
a
Tokena
Feature activation+0.000
ure
Tokenure
Feature activation+0.000
gard
Tokengard
Feature activation+0.000
the
Token the
Feature activation+0.000
founder
Token founder
Feature activation+0.000
pic
Token pic
Feature activation+0.000
st
Tokenst
Feature activation+0.000
ever
Tokenever
Feature activation+0.000
/
Token /
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
The
Token The
Feature activation+1.387
Rolling
Token Rolling
Feature activation+0.000
Stone
Token Stone
Feature activation+0.000
article
Token article
Feature activation+0.000
continues
Token continues
Feature activation+0.000
:
Token:
Feature activation+0.000
hosted
Token hosted
Feature activation+0.000
by
Token by
Feature activation+0.000
Rep
Token Rep
Feature activation+0.000
.
Token.
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Ch
Token Ch
Feature activation+1.192
ab
Tokenab
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
>>>
Token>>>
Feature activation+0.000
Check
TokenCheck
Feature activation+0.000
out
Token out
Feature activation+0.000
Steven
Token Steven
Feature activation+0.000
F
Token F
Feature activation+1.078
.
Token.
Feature activation+0.000
Hayward
Token Hayward
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
fish
Token fish
Feature activation+0.000
bowl
Tokenbowl
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Steven
TokenSteven
Feature activation+0.000
Se
Token Se
Feature activation+1.056
ag
Tokenag
Feature activation+0.000
al
Tokenal
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
under
Token under
Feature activation+0.000
W
Token W
Feature activation+0.000
off
Tokenoff
Feature activation+0.000
ord
Tokenord
Feature activation+0.000
:
Token:
Feature activation+0.000
Stephen
Token Stephen
Feature activation+0.000
A
Token A
Feature activation+0.963
.
Token.
Feature activation+0.000
Smith
Token Smith
Feature activation+0.000
-
Token -
Feature activation+0.000
Looks
Token Looks
Feature activation+0.000
like
Token like
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Steve
TokenSteve
Feature activation+0.000
Hel
Token Hel
Feature activation+0.921
ber
Tokenber
Feature activation+0.000
/
Token/
Feature activation+0.000
AP
TokenAP
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
Individuals
Token Individuals
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
Stan
Token Stan
Feature activation+0.000
F
Token F
Feature activation+0.823
isch
Tokenisch
Feature activation+0.000
ler
Tokenler
Feature activation+0.000
,
Token,
Feature activation+0.000
But
Token But
Feature activation+0.000
ch
Tokench
Feature activation+0.000
ine
Tokenine
Feature activation+0.000
K
Token K
Feature activation+0.000
ael
Tokenael
Feature activation+0.000
and
Token and
Feature activation+0.000
Roger
Token Roger
Feature activation+0.000
E
Token E
Feature activation+0.796
bert
Tokenbert
Feature activation+0.000
.)
Token.)
Feature activation+0.000
Age
Token Age
Feature activation+0.000
e
Tokene
Feature activation+0.000
himself
Token himself
Feature activation+0.000
en
Tokenen
Feature activation+0.000
est
Tokenest
Feature activation+0.000
ration
Tokenration
Feature activation+0.000
of
Token of
Feature activation+0.000
Steven
Token Steven
Feature activation+0.000
Sin
Token Sin
Feature activation+0.731
of
Tokenof
Feature activation+0.000
sky
Tokensky
Feature activation+0.000
,
Token,
Feature activation+0.000
comes
Token comes
Feature activation+0.000
as
Token as
Feature activation+0.000
but
Token but
Feature activation+0.000
was
Token was
Feature activation+0.000
replaced
Token replaced
Feature activation+0.000
by
Token by
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Di
Token Di
Feature activation+0.680
G
TokenG
Feature activation+0.000
ior
Tokenior
Feature activation+0.000
gio
Tokengio
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
13
Token13
Feature activation+0.000
)
Token)
Feature activation+0.000
Harvard
Token Harvard
Feature activation+0.000
:
Token:
Feature activation+0.000
Tony
Token Tony
Feature activation+0.000
Dun
Token Dun
Feature activation+0.673
gy
Tokengy
Feature activation+0.000
-
Token -
Feature activation+0.000
Guy
Token Guy
Feature activation+0.000
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
Information
Token Information
Feature activation+0.000
Officer
Token Officer
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Van
Token Van
Feature activation+2.693
R
TokenR
Feature activation+0.589
oe
Tokenoe
Feature activation+0.000
kel
Tokenkel
Feature activation+0.000
and
Token and
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
or
Token or
Feature activation+0.000
c
Token c
Feature activation+0.000
ospons
Tokenospons
Feature activation+0.000
or
Tokenor
Feature activation+0.000
Pete
Token Pete
Feature activation+0.000
De
Token De
Feature activation+0.507
F
TokenF
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
io
Tokenio
Feature activation+0.000
's
Token's
Feature activation+0.000
bill
Token bill
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
2
Token2
Feature activation+0.000
.
Token.
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
G
Token G
Feature activation+0.465
[
Token [
Feature activation+0.000
E
TokenE
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 = 3.603

S
TokenS
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
Chief
Token Chief
Feature activation+0.034
Top resid features:
Information
Token Information
Feature activation-0.013
Top resid features:
Officer
Token Officer
Feature activation+0.132
Top resid features:
Steve
Token Steve
Feature activation+3.603
Top resid features:
Van
Token Van
Feature activation+0.017
Top resid features:
R
TokenR
Feature activation+0.000
Top resid features:
oe
Tokenoe
Feature activation+0.000
Top resid features:
kel
Tokenkel
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
9
Token 9
Feature activation-0.003
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
2017
Token 2017
Feature activation-0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.026
Top resid features:
Steve
TokenSteve
Feature activation+3.380
Top resid features:
D
Token D
Feature activation+0.010
Top resid features:
illard
Tokenillard
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
infectious
Token infectious
Feature activation+0.000
Top resid features:
excitement
Token excitement
Feature activation+0.000
Top resid features:
intelligence
Token intelligence
Feature activation-0.002
Top resid features:
community
Token community
Feature activation+0.001
Top resid features:
?"
Token?"
Feature activation-0.024
Top resid features:
MSNBC
Token MSNBC
Feature activation-0.040
Top resid features:
's
Token's
Feature activation-0.044
Top resid features:
Steve
Token Steve
Feature activation+3.117
Top resid features:
K
Token K
Feature activation-0.005
Top resid features:
orn
Tokenorn
Feature activation+0.000
Top resid features:
ack
Tokenack
Feature activation+0.000
Top resid features:
i
Tokeni
Feature activation+0.000
Top resid features:
asked
Token asked
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.015
Top resid features:
said
Token said
Feature activation+0.015
Top resid features:
Go
Token Go
Feature activation-0.008
Top resid features:
Coin
TokenCoin
Feature activation-0.020
Top resid features:
CEO
Token CEO
Feature activation+0.072
Top resid features:
Steve
Token Steve
Feature activation+2.582
Top resid features:
Be
Token Be
Feature activation+0.008
Top resid features:
a
Tokena
Feature activation+0.000
Top resid features:
ure
Tokenure
Feature activation+0.000
Top resid features:
gard
Tokengard
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢ¢
TokenâĢ¢
Feature activation-0.010
Top resid features:
He
Token He
Feature activation+0.001
Top resid features:
p
Token p
Feature activation-0.010
Top resid features:
uked
Tokenuked
Feature activation-0.085
Top resid features:
on
Token on
Feature activation+0.125
Top resid features:
Steve
Token Steve
Feature activation+2.589
Top resid features:
Mc
Token Mc
Feature activation+0.084
Top resid features:
Queen
TokenQueen
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:
founder
Token founder
Feature activation-0.004
Top resid features:
of
Token of
Feature activation-0.040
Top resid features:
Hive
Token Hive
Feature activation-0.007
Top resid features:
Wallet
Token Wallet
Feature activation-0.022
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
Steve
Token Steve
Feature activation+2.786
Top resid features:
Be
Token Be
Feature activation+0.007
Top resid features:
a
Tokena
Feature activation+0.000
Top resid features:
ure
Tokenure
Feature activation+0.000
Top resid features:
gard
Tokengard
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.017
Top resid features:
pic
Token pic
Feature activation-0.029
Top resid features:
st
Tokenst
Feature activation-0.022
Top resid features:
ever
Tokenever
Feature activation-0.021
Top resid features:
/
Token /
Feature activation-0.076
Top resid features:
Steve
Token Steve
Feature activation+2.910
Top resid features:
The
Token The
Feature activation+0.090
Top resid features:
Rolling
Token Rolling
Feature activation+0.000
Top resid features:
Stone
Token Stone
Feature activation+0.000
Top resid features:
article
Token article
Feature activation+0.000
Top resid features:
continues
Token continues
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.678
Top resid features:
in
Token in
Feature activation-0.005
Top resid features:
his
Token his
Feature activation+0.003
Top resid features:
district
Token district
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
after
Token after
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.389
Top resid features:
understanding
Token understanding
Feature activation-0.042
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
principles
Token principles
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.569
Top resid features:
g
Token g
Feature activation-0.004
Top resid features:
erry
Tokenerry
Feature activation-0.001
Top resid features:
mand
Tokenmand
Feature activation-0.005
Top resid features:
ering
Tokenering
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.290
Top resid features:
)
Token)
Feature activation+0.004
Top resid features:
Ohio
Token Ohio
Feature activation-0.009
Top resid features:
State
Token State
Feature activation-0.000
Top resid features:
:
Token:
Feature activation-0.002
Top resid features:
Ed
Token Ed
Feature activation+0.009
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.654
Top resid features:
Rights
Token Rights
Feature activation-0.002
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
NRA
Token NRA
Feature activation-0.001
Top resid features:
store
Tokenstore
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.499
Top resid features:
on
Token on
Feature activation-0.012
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
site
Token site
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.495
Top resid features:
at
Token at
Feature activation-0.007
Top resid features:
movie
Token movie
Feature activation-0.005
Top resid features:
studios
Token studios
Feature activation-0.003
Top resid features:
:
Token:
Feature activation-0.001
Top resid features:
it
Token it
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.618
Top resid features:
29
Token 29
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
2016
Token 2016
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:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.498
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ļ
TokenĻ
Feature activation-0.006
Top resid features:
d
Tokend
Feature activation-0.002
Top resid features:
joined
Token joined
Feature activation+0.005
Top resid features:
Sch
Token Sch
Feature activation-0.007
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.505
Top resid features:
over
Token over
Feature activation-0.002
Top resid features:
stuffing
Token stuffing
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
#
Token#
Feature activation-0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.446
Top resid features:
administration
Token administration
Feature activation-0.063
Top resid features:
had
Token had
Feature activation-0.003
Top resid features:
called
Token called
Feature activation-0.003
Top resid features:
in
Token in
Feature activation-0.001
Top resid features:
leading
Token leading
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.495
Top resid features:
and
Token and
Feature activation-0.011
Top resid features:
would
Token would
Feature activation-0.001
Top resid features:
allow
Token allow
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
administration
Token administration
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+2.327
Top resid features:
and
Token and
Feature activation-0.016
Top resid features:
fees
Token fees
Feature activation-0.012
Top resid features:
for
Token for
Feature activation-0.009
Top resid features:
1
Token 1
Feature activation-0.002
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:

Decoder Weights Distribution

Head 0: 0.16

Head 1: 0.02

Head 2: 0.01

Head 3: 0.04

Head 4: 0.04

Head 5: 0.52

Head 6: 0.06

Head 7: 0.03

Head 8: 0.07

Head 9: 0.04

Head 10: 0.01

Head 11: 0.02

Positive logits

Companies2.23

newsletters2.08

wagen2.07

warranties2.05

mercial2.02

tools1.97

Interactive1.94

constructive1.92

anium1.91

advising1.91

fml1.90

engines1.88

automated1.87

stocks1.87

computer1.87

Graphics1.87

engine1.86

technical1.85

optimization1.83

Intelligent1.82

Negative logits

Rih-2.39

Peb-2.39

-2.35

Sarah-2.29

Suff-2.25

Jamaica-2.22

Deborah-2.22

Sao-2.22

Nur-2.19

Florence-2.18

ão-2.14

Jama-2.12

Emmanuel-2.12

Barth-2.09

Kap-2.06

Emma-2.05

Charlotte-2.05

��-2.04

-2.03

Rash-2.03

INTERVAL 2.424 - 2.693
CONTAINS 0.000%

.
Token.
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
Information
Token Information
Feature activation+0.000
Officer
Token Officer
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Van
Token Van
Feature activation+2.693
R
TokenR
Feature activation+0.589
oe
Tokenoe
Feature activation+0.000
kel
Tokenkel
Feature activation+0.000
and
Token and
Feature activation+0.000
U
Token U
Feature activation+0.000

INTERVAL 2.155 - 2.424
CONTAINS 0.000%

,
Token,
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Steve
TokenSteve
Feature activation+0.000
D
Token D
Feature activation+2.291
illard
Tokenillard
Feature activation+0.000
's
Token's
Feature activation+0.000
infectious
Token infectious
Feature activation+0.000
excitement
Token excitement
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.885 - 2.155
CONTAINS 0.000%

community
Token community
Feature activation+0.000
?"
Token?"
Feature activation+0.000
MSNBC
Token MSNBC
Feature activation+0.000
's
Token's
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
K
Token K
Feature activation+2.103
orn
Tokenorn
Feature activation+0.000
ack
Tokenack
Feature activation+0.000
i
Tokeni
Feature activation+0.000
asked
Token asked
Feature activation+0.000
Hugh
Token Hugh
Feature activation+0.000

INTERVAL 1.616 - 1.885
CONTAINS 0.000%

said
Token said
Feature activation+0.000
Go
Token Go
Feature activation+0.000
Coin
TokenCoin
Feature activation+0.000
CEO
Token CEO
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Be
Token Be
Feature activation+1.621
a
Tokena
Feature activation+0.000
ure
Tokenure
Feature activation+0.000
gard
Tokengard
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.347 - 1.616
CONTAINS 0.000%

He
Token He
Feature activation+0.000
p
Token p
Feature activation+0.000
uked
Tokenuked
Feature activation+0.000
on
Token on
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Mc
Token Mc
Feature activation+1.573
Queen
TokenQueen
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
pic
Token pic
Feature activation+0.000
st
Tokenst
Feature activation+0.000
ever
Tokenever
Feature activation+0.000
/
Token /
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
The
Token The
Feature activation+1.387
Rolling
Token Rolling
Feature activation+0.000
Stone
Token Stone
Feature activation+0.000
article
Token article
Feature activation+0.000
continues
Token continues
Feature activation+0.000
:
Token:
Feature activation+0.000
of
Token of
Feature activation+0.000
Hive
Token Hive
Feature activation+0.000
Wallet
Token Wallet
Feature activation+0.000
,
Token,
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Be
Token Be
Feature activation+1.495
a
Tokena
Feature activation+0.000
ure
Tokenure
Feature activation+0.000
gard
Tokengard
Feature activation+0.000
the
Token the
Feature activation+0.000
founder
Token founder
Feature activation+0.000

INTERVAL 1.077 - 1.347
CONTAINS 0.000%

hosted
Token hosted
Feature activation+0.000
by
Token by
Feature activation+0.000
Rep
Token Rep
Feature activation+0.000
.
Token.
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Ch
Token Ch
Feature activation+1.192
ab
Tokenab
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
(
Token (
Feature activation+0.000
R
TokenR
Feature activation+0.000
-
Token-
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
>>>
Token>>>
Feature activation+0.000
Check
TokenCheck
Feature activation+0.000
out
Token out
Feature activation+0.000
Steven
Token Steven
Feature activation+0.000
F
Token F
Feature activation+1.078
.
Token.
Feature activation+0.000
Hayward
Token Hayward
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 0.808 - 1.077
CONTAINS 0.001%

W
Token W
Feature activation+0.000
off
Tokenoff
Feature activation+0.000
ord
Tokenord
Feature activation+0.000
:
Token:
Feature activation+0.000
Stephen
Token Stephen
Feature activation+0.000
A
Token A
Feature activation+0.963
.
Token.
Feature activation+0.000
Smith
Token Smith
Feature activation+0.000
-
Token -
Feature activation+0.000
Looks
Token Looks
Feature activation+0.000
like
Token like
Feature activation+0.000
.
Token.
Feature activation+0.000
Individuals
Token Individuals
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.000
Stan
Token Stan
Feature activation+0.000
F
Token F
Feature activation+0.823
isch
Tokenisch
Feature activation+0.000
ler
Tokenler
Feature activation+0.000
,
Token,
Feature activation+0.000
But
Token But
Feature activation+0.000
ch
Tokench
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Steve
TokenSteve
Feature activation+0.000
Hel
Token Hel
Feature activation+0.921
ber
Tokenber
Feature activation+0.000
/
Token/
Feature activation+0.000
AP
TokenAP
Feature activation+0.000
)
Token)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
fish
Token fish
Feature activation+0.000
bowl
Tokenbowl
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Steven
TokenSteven
Feature activation+0.000
Se
Token Se
Feature activation+1.056
ag
Tokenag
Feature activation+0.000
al
Tokenal
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
under
Token under
Feature activation+0.000

INTERVAL 0.539 - 0.808
CONTAINS 0.001%

Chief
Token Chief
Feature activation+0.000
Information
Token Information
Feature activation+0.000
Officer
Token Officer
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Van
Token Van
Feature activation+2.693
R
TokenR
Feature activation+0.589
oe
Tokenoe
Feature activation+0.000
kel
Tokenkel
Feature activation+0.000
and
Token and
Feature activation+0.000
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
but
Token but
Feature activation+0.000
was
Token was
Feature activation+0.000
replaced
Token replaced
Feature activation+0.000
by
Token by
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Di
Token Di
Feature activation+0.680
G
TokenG
Feature activation+0.000
ior
Tokenior
Feature activation+0.000
gio
Tokengio
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
en
Tokenen
Feature activation+0.000
est
Tokenest
Feature activation+0.000
ration
Tokenration
Feature activation+0.000
of
Token of
Feature activation+0.000
Steven
Token Steven
Feature activation+0.000
Sin
Token Sin
Feature activation+0.731
of
Tokenof
Feature activation+0.000
sky
Tokensky
Feature activation+0.000
,
Token,
Feature activation+0.000
comes
Token comes
Feature activation+0.000
as
Token as
Feature activation+0.000
ine
Tokenine
Feature activation+0.000
K
Token K
Feature activation+0.000
ael
Tokenael
Feature activation+0.000
and
Token and
Feature activation+0.000
Roger
Token Roger
Feature activation+0.000
E
Token E
Feature activation+0.796
bert
Tokenbert
Feature activation+0.000
.)
Token.)
Feature activation+0.000
Age
Token Age
Feature activation+0.000
e
Tokene
Feature activation+0.000
himself
Token himself
Feature activation+0.000
13
Token13
Feature activation+0.000
)
Token)
Feature activation+0.000
Harvard
Token Harvard
Feature activation+0.000
:
Token:
Feature activation+0.000
Tony
Token Tony
Feature activation+0.000
Dun
Token Dun
Feature activation+0.673
gy
Tokengy
Feature activation+0.000
-
Token -
Feature activation+0.000
Guy
Token Guy
Feature activation+0.000
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.000

INTERVAL 0.269 - 0.539
CONTAINS 0.001%

the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
Stephen
Token Stephen
Feature activation+0.000
A
Token A
Feature activation+0.302
.
Token.
Feature activation+0.000
Smith
Token Smith
Feature activation+0.000
and
Token and
Feature activation+0.000
Skip
Token Skip
Feature activation+0.000
Bay
Token Bay
Feature activation+0.000
Video
Token Video
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
If
TokenIf
Feature activation+0.000
Nick
Token Nick
Feature activation+0.000
F
Token F
Feature activation+0.324
oles
Tokenoles
Feature activation+0.000
was
Token was
Feature activation+0.000
there
Token there
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
y
Tokeny
Feature activation+0.000
skin
Token skin
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Howe
Token Howe
Feature activation+0.309
ian
Tokenian
Feature activation+0.000
scor
Token scor
Feature activation+0.000
cher
Tokencher
Feature activation+0.000
.
Token.
Feature activation+0.000
This
Token This
Feature activation+0.000
or
Token or
Feature activation+0.000
c
Token c
Feature activation+0.000
ospons
Tokenospons
Feature activation+0.000
or
Tokenor
Feature activation+0.000
Pete
Token Pete
Feature activation+0.000
De
Token De
Feature activation+0.507
F
TokenF
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
io
Tokenio
Feature activation+0.000
's
Token's
Feature activation+0.000
bill
Token bill
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
.
Token.
Feature activation+0.000
Tony
Token Tony
Feature activation+0.000
Cu
Token Cu
Feature activation+0.226
cc
Tokencc
Feature activation+0.304
ine
Tokenine
Feature activation+0.000
llo
Tokenllo
Feature activation+0.000
!
Token!
Feature activation+0.000
I
Token I
Feature activation+0.000
mean
Token mean
Feature activation+0.000

INTERVAL 0.000 - 0.269
CONTAINS 99.997%

on
Token on
Feature activation+0.000
navigating
Token navigating
Feature activation+0.000
Content
Token Content
Feature activation+0.000
ID
TokenID
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
T
TokenT
Feature activation+0.000
ub
Tokenub
Feature activation+0.000
ef
Tokenef
Feature activation+0.000
il
Tokenil
Feature activation+0.000
delivered
Token delivered
Feature activation+0.000
to
Token to
Feature activation+0.000
your
Token your
Feature activation+0.000
inbox
Token inbox
Feature activation+0.000
We
Token We
Feature activation+0.000
're
Token're
Feature activation+0.000
sorry
Token sorry
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
something
Token something
Feature activation+0.000
went
Token went
Feature activation+0.000
work
Token work
Feature activation+0.000
out
Token out
Feature activation+0.000
how
Token how
Feature activation+0.000
much
Token much
Feature activation+0.000
land
Token land
Feature activation+0.000
would
Token would
Feature activation+0.000
be
Token be
Feature activation+0.000
required
Token required
Feature activation+0.000
to
Token to
Feature activation+0.000
feed
Token feed
Feature activation+0.000
today
Token today
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
has
Token has
Feature activation+0.000
the
Token the
Feature activation+0.000
power
Token power
Feature activation+0.000
to
Token to
Feature activation+0.000
grant
Token grant
Feature activation+0.000
pard
Token pard
Feature activation+0.000
ons
Tokenons
Feature activation+0.000
in
Token in
Feature activation+0.000
calm
Token calm
Feature activation+0.000
,
Token,
Feature activation+0.000
recorded
Token recorded
Feature activation+0.000
voice
Token voice
Feature activation+0.000
suggesting
Token suggesting
Feature activation+0.000
she
Token she
Feature activation+0.000
relax
Token relax
Feature activation+0.000
and
Token and
Feature activation+0.000
rise
Token rise
Feature activation+0.000
slowly
Token slowly
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 3 in H7.5: (feature 23077)

TOP ACTIVATIONS
MAX = 4.527

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
brother
Token brother
Feature activation+0.492
C
Token C
Feature activation+1.815
iar
Tokeniar
Feature activation+1.731
án
Tokenán
Feature activation+4.527
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
involvement
Token involvement
Feature activation+0.000
in
Token in
Feature activation+0.000
politics
Token politics
Feature activation+0.000
hugely
Token hugely
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
proportion
Token proportion
Feature activation+0.000
,"
Token,"
Feature activation+0.529
Eric
Token Eric
Feature activation+4.219
Trump
Token Trump
Feature activation+1.683
told
Token told
Feature activation+0.000
"
Token "
Feature activation+0.000
CBS
TokenCBS
Feature activation+0.000
This
Token This
Feature activation+0.000
idi
Tokenidi
Feature activation+0.000
's
Token's
Feature activation+0.000
father
Token father
Feature activation+0.587
,
Token,
Feature activation+3.229
Far
Token Far
Feature activation+1.550
ia
Tokenia
Feature activation+4.167
,
Token,
Feature activation+0.066
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
nominee
Token nominee
Feature activation+0.000
's
Token's
Feature activation+0.000
son
Token son
Feature activation+0.390
Eric
Token Eric
Feature activation+4.033
Trump
Token Trump
Feature activation+1.602
said
Token said
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,"
Token,"
Feature activation+0.000
father
Token father
Feature activation+2.113
and
Token and
Feature activation+0.000
agent
Token agent
Feature activation+2.236
Ir
Token Ir
Feature activation+1.565
fan
Tokenfan
Feature activation+3.770
told
Token told
Feature activation+0.000
Kick
Token Kick
Feature activation+0.000
er
Tokener
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
mag
Tokenmag
Feature activation+0.000
which
Token which
Feature activation+0.000
includes
Token includes
Feature activation+0.000
his
Token his
Feature activation+0.000
twin
Token twin
Feature activation+0.000
brother
Token brother
Feature activation+0.642
,
Token,
Feature activation+3.542
Sha
Token Sha
Feature activation+2.660
qu
Tokenqu
Feature activation+1.732
ill
Tokenill
Feature activation+3.227
.
Token.
Feature activation+0.000
Griffin
Token Griffin
Feature activation+0.000
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
brother
Token brother
Feature activation+0.878
Phil
Token Phil
Feature activation+3.258
iber
Tokeniber
Feature activation+1.474
t
Tokent
Feature activation+3.439
was
Token was
Feature activation+0.000
four
Token four
Feature activation+0.000
.
Token.
Feature activation+0.000
Their
Token Their
Feature activation+0.000
father
Token father
Feature activation+0.133
Rob
Token Rob
Feature activation+0.000
Moore
Token Moore
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
son
Token son
Feature activation+0.764
Michael
Token Michael
Feature activation+3.384
and
Token and
Feature activation+0.169
Happy
Token Happy
Feature activation+0.309
Madison
Token Madison
Feature activation+0.666
partner
Token partner
Feature activation+0.280
Jack
Token Jack
Feature activation+0.306
down
Token down
Feature activation+0.000
the
Token the
Feature activation+0.000
street
Token street
Feature activation+0.000
.
Token.
Feature activation+0.000
Sa
Token Sa
Feature activation+1.222
eed
Tokeneed
Feature activation+3.382
,
Token,
Feature activation+0.284
with
Token with
Feature activation+0.082
long
Token long
Feature activation+0.000
hair
Token hair
Feature activation+0.000
,
Token,
Feature activation+0.000
point
Tokenpoint
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
son
Token son
Feature activation+0.000
Albert
Token Albert
Feature activation+3.270
grew
Token grew
Feature activation+0.000
up
Token up
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
shadow
Token shadow
Feature activation+0.000
was
Token was
Feature activation+0.000
seven
Token seven
Feature activation+0.000
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
brother
Token brother
Feature activation+0.878
Phil
Token Phil
Feature activation+3.258
iber
Tokeniber
Feature activation+1.474
t
Tokent
Feature activation+3.439
was
Token was
Feature activation+0.000
four
Token four
Feature activation+0.000
.
Token.
Feature activation+0.000
Her
TokenHer
Feature activation+0.000
husband
Token husband
Feature activation+1.044
of
Token of
Feature activation+0.000
53
Token 53
Feature activation+0.638
years
Token years
Feature activation+0.491
,
Token,
Feature activation+3.239
Des
Token Des
Feature activation+2.256
,
Token,
Feature activation+0.655
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
Mat
TokenMat
Feature activation+0.086
u
Tokenu
Feature activation+0.000
idi
Tokenidi
Feature activation+0.000
's
Token's
Feature activation+0.000
father
Token father
Feature activation+0.587
,
Token,
Feature activation+3.229
Far
Token Far
Feature activation+1.550
ia
Tokenia
Feature activation+4.167
,
Token,
Feature activation+0.066
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
twin
Token twin
Feature activation+0.000
brother
Token brother
Feature activation+0.642
,
Token,
Feature activation+3.542
Sha
Token Sha
Feature activation+2.660
qu
Tokenqu
Feature activation+1.732
ill
Tokenill
Feature activation+3.227
.
Token.
Feature activation+0.000
Griffin
Token Griffin
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
partly
Token partly
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.166
,
Token,
Feature activation+2.307
Bill
Token Bill
Feature activation+3.215
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
of
Token of
Feature activation+0.000
Fame
Token Fame
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
policy
Token policy
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
David
TokenDavid
Feature activation+3.084
regards
Token regards
Feature activation+0.000
the
Token the
Feature activation+0.000
substantive
Token substantive
Feature activation+0.000
-
Token -
Feature activation+0.000
rather
Token rather
Feature activation+0.000
all
Tokenall
Feature activation+0.000
costs
Token costs
Feature activation+0.000
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.089
Anthony
TokenAnthony
Feature activation+3.052
Hamilton
Token Hamilton
Feature activation+0.315
had
Token had
Feature activation+0.047
earlier
Token earlier
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
father
Token father
Feature activation+0.103
,
Token,
Feature activation+2.078
Barack
Token Barack
Feature activation+3.033
Obama
Token Obama
Feature activation+0.901
Sr
Token Sr
Feature activation+0.599
.,
Token.,
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
who
Token who
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.618
was
Token was
Feature activation+0.397
(
Token (
Feature activation+0.506
Pierre
TokenPierre
Feature activation+2.919
Trudeau
Token Trudeau
Feature activation+0.491
,
Token,
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+0.000
after
Token after
Feature activation+0.000
Shiite
Token Shiite
Feature activation+0.000
im
Token im
Feature activation+0.000
ams
Tokenams
Feature activation+0.000
.
Token.
Feature activation+0.217
Amir
Token Amir
Feature activation+2.873
,
Token,
Feature activation+1.413
a
Token a
Feature activation+0.742
former
Token former
Feature activation+0.033
major
Token major
Feature activation+0.000
in
Token in
Feature activation+0.000

Top DFA by src position
MAX = 4.873

Cos
Token Cos
Feature activation+0.012
Top resid features:
grave
Tokengrave
Feature activation+0.009
Top resid features:
âĢ
TokenâĢ
Feature activation+0.095
Top resid features:
Ļ
TokenĻ
Feature activation+0.019
Top resid features:
s
Tokens
Feature activation+0.032
Top resid features:
brother
Token brother
Feature activation+4.873
Top resid features:
C
Token C
Feature activation+0.058
Top resid features:
iar
Tokeniar
Feature activation+0.177
Top resid features:
án
Tokenán
Feature activation+0.028
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation-0.002
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
Republican
Token Republican
Feature activation+0.001
Top resid features:
nominee
Token nominee
Feature activation+0.004
Top resid features:
's
Token's
Feature activation+0.003
Top resid features:
son
Token son
Feature activation+4.773
Top resid features:
Eric
Token Eric
Feature activation+0.004
Top resid features:
Trump
Token Trump
Feature activation-0.011
Top resid features:
said
Token said
Feature activation+0.038
Top resid features:
Tuesday
Token Tuesday
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.062
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Mat
TokenMat
Feature activation+0.004
Top resid features:
u
Tokenu
Feature activation-0.002
Top resid features:
idi
Tokenidi
Feature activation+0.009
Top resid features:
's
Token's
Feature activation+0.021
Top resid features:
father
Token father
Feature activation+4.666
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
Far
Token Far
Feature activation+0.050
Top resid features:
ia
Tokenia
Feature activation+0.023
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
,"
Token,"
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.024
Top resid features:
Republican
Token Republican
Feature activation+0.009
Top resid features:
nominee
Token nominee
Feature activation+0.002
Top resid features:
's
Token's
Feature activation+0.151
Top resid features:
son
Token son
Feature activation+4.700
Top resid features:
Eric
Token Eric
Feature activation+0.048
Top resid features:
Trump
Token Trump
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
Tuesday
Token Tuesday
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.002
Top resid features:
Bor
Token Bor
Feature activation+0.006
Top resid features:
ussia
Tokenussia
Feature activation+0.001
Top resid features:
Dortmund
Token Dortmund
Feature activation-0.002
Top resid features:
,"
Token,"
Feature activation+0.029
Top resid features:
father
Token father
Feature activation+4.391
Top resid features:
and
Token and
Feature activation-0.015
Top resid features:
agent
Token agent
Feature activation+0.018
Top resid features:
Ir
Token Ir
Feature activation+0.084
Top resid features:
fan
Tokenfan
Feature activation-0.001
Top resid features:
told
Token told
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
which
Token which
Feature activation-0.002
Top resid features:
includes
Token includes
Feature activation-0.004
Top resid features:
his
Token his
Feature activation+0.098
Top resid features:
twin
Token twin
Feature activation+0.398
Top resid features:
brother
Token brother
Feature activation+3.721
Top resid features:
,
Token,
Feature activation+0.107
Top resid features:
Sha
Token Sha
Feature activation+0.000
Top resid features:
qu
Tokenqu
Feature activation+0.000
Top resid features:
ill
Tokenill
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Louise
Token Louise
Feature activation+0.041
Top resid features:
was
Token was
Feature activation+0.043
Top resid features:
seven
Token seven
Feature activation+0.027
Top resid features:
and
Token and
Feature activation+0.043
Top resid features:
her
Token her
Feature activation+0.001
Top resid features:
brother
Token brother
Feature activation+3.714
Top resid features:
Phil
Token Phil
Feature activation+0.152
Top resid features:
iber
Tokeniber
Feature activation+0.033
Top resid features:
t
Tokent
Feature activation+0.021
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
four
Token four
Feature activation+0.000
Top resid features:
President
Token President
Feature activation-0.045
Top resid features:
Rob
Token Rob
Feature activation+0.010
Top resid features:
Moore
Token Moore
Feature activation+0.014
Top resid features:
,
Token,
Feature activation+0.029
Top resid features:
his
Token his
Feature activation+0.075
Top resid features:
son
Token son
Feature activation+3.918
Top resid features:
Michael
Token Michael
Feature activation+0.103
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Happy
Token Happy
Feature activation+0.000
Top resid features:
Madison
Token Madison
Feature activation+0.000
Top resid features:
partner
Token partner
Feature activation+0.000
Top resid features:
runs
Token runs
Feature activation+0.047
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
place
Token place
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.007
Top resid features:
four
Token four
Feature activation+0.004
Top resid features:
brothers
Token brothers
Feature activation+3.674
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
who
Token who
Feature activation+0.008
Top resid features:
like
Token like
Feature activation+0.005
Top resid features:
him
Token him
Feature activation+0.004
Top resid features:
were
Token were
Feature activation+0.016
Top resid features:
Pierre
Token Pierre
Feature activation+0.009
Top resid features:
point
Tokenpoint
Feature activation+0.024
Top resid features:
âĢ
TokenâĢ
Feature activation+0.076
Top resid features:
Ļ
TokenĻ
Feature activation+0.021
Top resid features:
s
Tokens
Feature activation+0.044
Top resid features:
son
Token son
Feature activation+3.760
Top resid features:
Albert
Token Albert
Feature activation+0.050
Top resid features:
grew
Token grew
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Louise
Token Louise
Feature activation+0.012
Top resid features:
was
Token was
Feature activation+0.014
Top resid features:
seven
Token seven
Feature activation+0.011
Top resid features:
and
Token and
Feature activation+0.016
Top resid features:
her
Token her
Feature activation-0.002
Top resid features:
brother
Token brother
Feature activation+3.650
Top resid features:
Phil
Token Phil
Feature activation+0.048
Top resid features:
iber
Tokeniber
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
four
Token four
Feature activation+0.000
Top resid features:
ur
Tokenur
Feature activation-0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.272
Top resid features:
Ċ
TokenĊ
Feature activation+0.037
Top resid features:
Her
TokenHer
Feature activation+0.043
Top resid features:
husband
Token husband
Feature activation+3.000
Top resid features:
of
Token of
Feature activation+0.048
Top resid features:
53
Token 53
Feature activation-0.002
Top resid features:
years
Token years
Feature activation+0.039
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
Des
Token Des
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Mat
TokenMat
Feature activation+0.008
Top resid features:
u
Tokenu
Feature activation+0.008
Top resid features:
idi
Tokenidi
Feature activation+0.012
Top resid features:
's
Token's
Feature activation+0.042
Top resid features:
father
Token father
Feature activation+3.694
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
Far
Token Far
Feature activation+0.000
Top resid features:
ia
Tokenia
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
which
Token which
Feature activation-0.025
Top resid features:
includes
Token includes
Feature activation+0.021
Top resid features:
his
Token his
Feature activation+0.039
Top resid features:
twin
Token twin
Feature activation+0.450
Top resid features:
brother
Token brother
Feature activation+3.168
Top resid features:
,
Token,
Feature activation+0.193
Top resid features:
Sha
Token Sha
Feature activation+0.022
Top resid features:
qu
Tokenqu
Feature activation+0.032
Top resid features:
ill
Tokenill
Feature activation+0.019
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
State
Token State
Feature activation-0.003
Top resid features:
based
Token based
Feature activation-0.006
Top resid features:
partly
Token partly
Feature activation-0.003
Top resid features:
on
Token on
Feature activation+0.008
Top resid features:
his
Token his
Feature activation+0.011
Top resid features:
father
Token father
Feature activation+3.675
Top resid features:
,
Token,
Feature activation+0.116
Top resid features:
Bill
Token Bill
Feature activation+0.036
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
Hall
Token Hall
Feature activation+0.000
Top resid features:
Downing
Token Downing
Feature activation+0.007
Top resid features:
Street
Token Street
Feature activation-0.005
Top resid features:
-
Token -
Feature activation-0.003
Top resid features:
but
Token but
Feature activation-0.000
Top resid features:
two
Token two
Feature activation+0.009
Top resid features:
brothers
Token brothers
Feature activation+2.604
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Image
TokenImage
Feature activation-0.002
Top resid features:
caption
Token caption
Feature activation-0.006
Top resid features:
Hamilton
Token Hamilton
Feature activation+0.169
Top resid features:
was
Token was
Feature activation+0.121
Top resid features:
friendly
Token friendly
Feature activation-0.021
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.029
Top resid features:
son
Token son
Feature activation+3.015
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
sometimes
Token sometimes
Feature activation+0.004
Top resid features:
he
Token he
Feature activation+0.039
Top resid features:
would
Token would
Feature activation+0.036
Top resid features:
avoid
Token avoid
Feature activation-0.005
Top resid features:
The
TokenThe
Feature activation+0.003
Top resid features:
president
Token president
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+0.031
Top resid features:
Ļ
TokenĻ
Feature activation+0.005
Top resid features:
s
Tokens
Feature activation+0.016
Top resid features:
father
Token father
Feature activation+3.585
Top resid features:
,
Token,
Feature activation+0.106
Top resid features:
Barack
Token Barack
Feature activation-0.007
Top resid features:
Obama
Token Obama
Feature activation+0.000
Top resid features:
Sr
Token Sr
Feature activation+0.000
Top resid features:
.,
Token.,
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
because
Token because
Feature activation+0.000
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
who
Token who
Feature activation-0.010
Top resid features:
his
Token his
Feature activation+0.007
Top resid features:
father
Token father
Feature activation+3.489
Top resid features:
was
Token was
Feature activation+0.015
Top resid features:
(
Token (
Feature activation+0.018
Top resid features:
Pierre
TokenPierre
Feature activation+0.048
Top resid features:
Trudeau
Token Trudeau
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
runs
Token runs
Feature activation+0.121
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
place
Token place
Feature activation-0.008
Top resid features:
with
Token with
Feature activation+0.005
Top resid features:
four
Token four
Feature activation+0.007
Top resid features:
brothers
Token brothers
Feature activation+2.972
Top resid features:
,
Token,
Feature activation+0.018
Top resid features:
who
Token who
Feature activation+0.015
Top resid features:
like
Token like
Feature activation-0.005
Top resid features:
him
Token him
Feature activation+0.011
Top resid features:
were
Token were
Feature activation+0.027
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.04

Head 2: 0.02

Head 3: 0.05

Head 4: 0.05

Head 5: 0.50

Head 6: 0.05

Head 7: 0.03

Head 8: 0.07

Head 9: 0.06

Head 10: 0.02

Head 11: 0.03

Positive logits

Mehran2.35

Jr2.31

Sirius2.26

asio2.19

ilon2.11

Sr2.10

Dad2.09

asar2.08

Jr2.06

HAEL2.05

grandson2.02

Nanto2.02

Son2.01

Dad2.00

brothers1.98

��1.98

uay1.98

rahim1.98

wiser1.91

iph1.91

Negative logits

nudity-2.26

neutrality-2.01

booths-1.99

booth-1.94

banning-1.84

disinfect-1.80

inducing-1.78

boobs-1.78

cot-1.78

transparency-1.77

neutral-1.76

UNESCO-1.76

embargo-1.74

moratorium-1.73

dissent-1.73

ambient-1.73

platform-1.73

discrimination-1.72

randomized-1.71

waiver-1.70

INTERVAL 4.075 - 4.527
CONTAINS 0.000%

hugely
Token hugely
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
proportion
Token proportion
Feature activation+0.000
,"
Token,"
Feature activation+0.529
Eric
Token Eric
Feature activation+4.219
Trump
Token Trump
Feature activation+1.683
told
Token told
Feature activation+0.000
"
Token "
Feature activation+0.000
CBS
TokenCBS
Feature activation+0.000
This
Token This
Feature activation+0.000
idi
Tokenidi
Feature activation+0.000
's
Token's
Feature activation+0.000
father
Token father
Feature activation+0.587
,
Token,
Feature activation+3.229
Far
Token Far
Feature activation+1.550
ia
Tokenia
Feature activation+4.167
,
Token,
Feature activation+0.066
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
brother
Token brother
Feature activation+0.492
C
Token C
Feature activation+1.815
iar
Tokeniar
Feature activation+1.731
án
Tokenán
Feature activation+4.527
had
Token had
Feature activation+0.000
no
Token no
Feature activation+0.000
involvement
Token involvement
Feature activation+0.000
in
Token in
Feature activation+0.000
politics
Token politics
Feature activation+0.000

INTERVAL 3.622 - 4.075
CONTAINS 0.000%

the
Token the
Feature activation+0.000
Republican
Token Republican
Feature activation+0.000
nominee
Token nominee
Feature activation+0.000
's
Token's
Feature activation+0.000
son
Token son
Feature activation+0.390
Eric
Token Eric
Feature activation+4.033
Trump
Token Trump
Feature activation+1.602
said
Token said
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,"
Token,"
Feature activation+0.000
father
Token father
Feature activation+2.113
and
Token and
Feature activation+0.000
agent
Token agent
Feature activation+2.236
Ir
Token Ir
Feature activation+1.565
fan
Tokenfan
Feature activation+3.770
told
Token told
Feature activation+0.000
Kick
Token Kick
Feature activation+0.000
er
Tokener
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
mag
Tokenmag
Feature activation+0.000

INTERVAL 3.169 - 3.622
CONTAINS 0.001%

which
Token which
Feature activation+0.000
includes
Token includes
Feature activation+0.000
his
Token his
Feature activation+0.000
twin
Token twin
Feature activation+0.000
brother
Token brother
Feature activation+0.642
,
Token,
Feature activation+3.542
Sha
Token Sha
Feature activation+2.660
qu
Tokenqu
Feature activation+1.732
ill
Tokenill
Feature activation+3.227
.
Token.
Feature activation+0.000
Griffin
Token Griffin
Feature activation+0.000
partly
Token partly
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.166
,
Token,
Feature activation+2.307
Bill
Token Bill
Feature activation+3.215
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
of
Token of
Feature activation+0.000
Fame
Token Fame
Feature activation+0.000
was
Token was
Feature activation+0.000
seven
Token seven
Feature activation+0.000
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
brother
Token brother
Feature activation+0.878
Phil
Token Phil
Feature activation+3.258
iber
Tokeniber
Feature activation+1.474
t
Tokent
Feature activation+3.439
was
Token was
Feature activation+0.000
four
Token four
Feature activation+0.000
.
Token.
Feature activation+0.000
down
Token down
Feature activation+0.000
the
Token the
Feature activation+0.000
street
Token street
Feature activation+0.000
.
Token.
Feature activation+0.000
Sa
Token Sa
Feature activation+1.222
eed
Tokeneed
Feature activation+3.382
,
Token,
Feature activation+0.284
with
Token with
Feature activation+0.082
long
Token long
Feature activation+0.000
hair
Token hair
Feature activation+0.000
,
Token,
Feature activation+0.000
Mat
TokenMat
Feature activation+0.086
u
Tokenu
Feature activation+0.000
idi
Tokenidi
Feature activation+0.000
's
Token's
Feature activation+0.000
father
Token father
Feature activation+0.587
,
Token,
Feature activation+3.229
Far
Token Far
Feature activation+1.550
ia
Tokenia
Feature activation+4.167
,
Token,
Feature activation+0.066
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 2.716 - 3.169
CONTAINS 0.001%

who
Token who
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.618
was
Token was
Feature activation+0.397
(
Token (
Feature activation+0.506
Pierre
TokenPierre
Feature activation+2.919
Trudeau
Token Trudeau
Feature activation+0.491
,
Token,
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+0.000
for
Token for
Feature activation+0.000
over
Token over
Feature activation+0.000
40
Token 40
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
Joseph
Token Joseph
Feature activation+2.849
was
Token was
Feature activation+0.000
honored
Token honored
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
policy
Token policy
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
David
TokenDavid
Feature activation+3.084
regards
Token regards
Feature activation+0.000
the
Token the
Feature activation+0.000
substantive
Token substantive
Feature activation+0.000
-
Token -
Feature activation+0.000
rather
Token rather
Feature activation+0.000
after
Token after
Feature activation+0.000
Shiite
Token Shiite
Feature activation+0.000
im
Token im
Feature activation+0.000
ams
Tokenams
Feature activation+0.000
.
Token.
Feature activation+0.217
Amir
Token Amir
Feature activation+2.873
,
Token,
Feature activation+1.413
a
Token a
Feature activation+0.742
former
Token former
Feature activation+0.033
major
Token major
Feature activation+0.000
in
Token in
Feature activation+0.000
all
Tokenall
Feature activation+0.000
costs
Token costs
Feature activation+0.000
".
Token".
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.089
Anthony
TokenAnthony
Feature activation+3.052
Hamilton
Token Hamilton
Feature activation+0.315
had
Token had
Feature activation+0.047
earlier
Token earlier
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 2.264 - 2.716
CONTAINS 0.001%

career
Token career
Feature activation+0.000
intentions
Token intentions
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Brother
TokenBrother
Feature activation+2.475
ly
Tokenly
Feature activation+0.000
scrutiny
Token scrutiny
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
of
Token of
Feature activation+0.000
Massachusetts
Token Massachusetts
Feature activation+0.000
.
Token.
Feature activation+0.000
T
Token T
Feature activation+0.319
amer
Tokenamer
Feature activation+1.634
lan
Tokenlan
Feature activation+2.456
Tsarnaev
Token Tsarnaev
Feature activation+0.088
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.044
legal
Token legal
Feature activation+0.000
permanent
Token permanent
Feature activation+0.000
based
Token based
Feature activation+0.000
partly
Token partly
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.166
,
Token,
Feature activation+2.307
Bill
Token Bill
Feature activation+3.215
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
of
Token of
Feature activation+0.000
includes
Token includes
Feature activation+0.000
his
Token his
Feature activation+0.000
twin
Token twin
Feature activation+0.000
brother
Token brother
Feature activation+0.642
,
Token,
Feature activation+3.542
Sha
Token Sha
Feature activation+2.660
qu
Tokenqu
Feature activation+1.732
ill
Tokenill
Feature activation+3.227
.
Token.
Feature activation+0.000
Griffin
Token Griffin
Feature activation+0.000
,
Token,
Feature activation+0.000
,
Token,
Feature activation+1.713
retired
Token retired
Feature activation+0.711
Army
Token Army
Feature activation+0.000
Col
Token Col
Feature activation+1.586
.
Token.
Feature activation+1.741
Joseph
Token Joseph
Feature activation+2.457
L
Token L
Feature activation+0.575
.
Token.
Feature activation+1.771
G
Token G
Feature activation+0.047
ude
Tokenude
Feature activation+0.486
,
Token,
Feature activation+0.000

INTERVAL 1.811 - 2.264
CONTAINS 0.002%

face
Token face
Feature activation+0.000
of
Token of
Feature activation+0.000
her
Token her
Feature activation+0.000
only
Token only
Feature activation+0.000
son
Token son
Feature activation+0.000
,
Token,
Feature activation+2.109
partially
Token partially
Feature activation+0.000
paralyzed
Token paralyzed
Feature activation+0.000
after
Token after
Feature activation+0.000
an
Token an
Feature activation+0.000
insect
Token insect
Feature activation+0.000
asked
Token asked
Feature activation+0.000
about
Token about
Feature activation+0.000
his
Token his
Feature activation+0.000
differences
Token differences
Feature activation+0.000
with
Token with
Feature activation+0.000
Ed
Token Ed
Feature activation+2.105
-
Token -
Feature activation+0.057
who
Token who
Feature activation+0.000
has
Token has
Feature activation+0.000
criticised
Token criticised
Feature activation+0.000
the
Token the
Feature activation+0.000
resident
Token resident
Feature activation+0.000
and
Token and
Feature activation+0.000
D
Token D
Feature activation+0.000
zh
Tokenzh
Feature activation+0.000
ok
Tokenok
Feature activation+0.000
har
Tokenhar
Feature activation+1.974
Tsarnaev
Token Tsarnaev
Feature activation+0.061
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
natural
Token natural
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
the
Token the
Feature activation+0.000
murder
Token murder
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
uncle
Token uncle
Feature activation+0.294
,
Token,
Feature activation+2.149
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
killed
Token killed
Feature activation+0.000
six
Token six
Feature activation+0.000
years
Token years
Feature activation+0.000
the
Token the
Feature activation+0.000
sworn
Token sworn
Feature activation+0.000
brother
Token brother
Feature activation+0.000
of
Token of
Feature activation+0.000
Ta
Token Ta
Feature activation+0.354
iga
Tokeniga
Feature activation+1.963
S
Token S
Feature activation+0.246
ae
Tokenae
Feature activation+0.000
j
Tokenj
Feature activation+0.000
ima
Tokenima
Feature activation+0.902
,
Token,
Feature activation+0.503

INTERVAL 1.358 - 1.811
CONTAINS 0.004%

Seymour
Token Seymour
Feature activation+1.185
had
Token had
Feature activation+0.362
three
Token three
Feature activation+0.081
older
Token older
Feature activation+0.204
brothers
Token brothers
Feature activation+0.078
,
Token,
Feature activation+1.493
two
Token two
Feature activation+0.727
younger
Token younger
Feature activation+0.109
brothers
Token brothers
Feature activation+0.000
,
Token,
Feature activation+1.115
and
Token and
Feature activation+1.021
to
Token to
Feature activation+0.000
her
Token her
Feature activation+0.000
racing
Token racing
Feature activation+0.000
driver
Token driver
Feature activation+0.000
grandfather
Token grandfather
Feature activation+0.000
Francis
Token Francis
Feature activation+1.402
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
5
Token 5
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Earl
Token Earl
Feature activation+0.709
Army
Token Army
Feature activation+0.000
Col
Token Col
Feature activation+1.586
.
Token.
Feature activation+1.741
Joseph
Token Joseph
Feature activation+2.457
L
Token L
Feature activation+0.575
.
Token.
Feature activation+1.771
G
Token G
Feature activation+0.047
ude
Tokenude
Feature activation+0.486
,
Token,
Feature activation+0.000
87
Token 87
Feature activation+0.000
,
Token,
Feature activation+0.000
throne
Token throne
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
made
Token made
Feature activation+0.000
Mu
Token Mu
Feature activation+0.870
q
Tokenq
Feature activation+1.429
rin
Tokenrin
Feature activation+0.000
crown
Token crown
Feature activation+0.000
prince
Token prince
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
half
Token half
Feature activation+0.000
-
Token-
Feature activation+0.000
brother
Tokenbrother
Feature activation+0.000
.
Token.
Feature activation+0.000
Mu
Token Mu
Feature activation+1.564
q
Tokenq
Feature activation+0.794
rin
Tokenrin
Feature activation+2.479
was
Token was
Feature activation+0.234
very
Token very
Feature activation+0.044
close
Token close
Feature activation+0.000

INTERVAL 0.905 - 1.358
CONTAINS 0.005%

together
Token together
Feature activation+0.000
,
Token,
Feature activation+0.000
Kate
Token Kate
Feature activation+0.752
,
Token,
Feature activation+0.874
Natalie
Token Natalie
Feature activation+0.549
and
Token and
Feature activation+0.961
Harry
Token Harry
Feature activation+0.570
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
parted
Token parted
Feature activation+0.000
ways
Token ways
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
.
Token.
Feature activation+0.000
Eric
Token Eric
Feature activation+1.113
Trump
Token Trump
Feature activation+0.000
:
Token:
Feature activation+0.000
Father
Token Father
Feature activation+0.426
's
Token's
Feature activation+0.000
Khan
Token Khan
Feature activation+0.153
father
Token father
Feature activation+0.000
,
Token,
Feature activation+1.068
Za
Token Za
Feature activation+0.811
her
Tokenher
Feature activation+1.904
N
Token N
Feature activation+0.704
asser
Tokenasser
Feature activation+1.048
,
Token,
Feature activation+0.000
reacted
Token reacted
Feature activation+0.000
to
Token to
Feature activation+0.000
those
Token those
Feature activation+0.000
seeking
Token seeking
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
son
Token son
Feature activation+0.000
,
Token,
Feature activation+0.000
Andrew
Token Andrew
Feature activation+1.052
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
"
Token "
Feature activation+0.000
l
Tokenl
Feature activation+0.000
aid
Tokenaid
Feature activation+0.000
brothers
Token brothers
Feature activation+0.078
,
Token,
Feature activation+1.493
two
Token two
Feature activation+0.727
younger
Token younger
Feature activation+0.109
brothers
Token brothers
Feature activation+0.000
,
Token,
Feature activation+1.115
and
Token and
Feature activation+1.021
3
Token 3
Feature activation+0.000
younger
Token younger
Feature activation+0.000
sisters
Token sisters
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.453 - 0.905
CONTAINS 0.017%

Hamilton
Token Hamilton
Feature activation+0.000
was
Token was
Feature activation+0.000
friendly
Token friendly
Feature activation+0.000
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
son
Token son
Feature activation+0.647
and
Token and
Feature activation+0.321
sometimes
Token sometimes
Feature activation+0.000
he
Token he
Feature activation+0.000
would
Token would
Feature activation+0.000
avoid
Token avoid
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Her
TokenHer
Feature activation+0.000
husband
Token husband
Feature activation+1.044
of
Token of
Feature activation+0.000
53
Token 53
Feature activation+0.638
years
Token years
Feature activation+0.491
,
Token,
Feature activation+3.239
Des
Token Des
Feature activation+2.256
,
Token,
Feature activation+0.655
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
eldest
Token eldest
Feature activation+0.000
child
Token child
Feature activation+0.000
of
Token of
Feature activation+0.000
Prince
Token Prince
Feature activation+1.023
F
Token F
Feature activation+0.810
um
Tokenum
Feature activation+0.000
ih
Tokenih
Feature activation+0.000
ito
Tokenito
Feature activation+0.502
,
Token,
Feature activation+0.329
whose
Token whose
Feature activation+0.289
Louise
Token Louise
Feature activation+0.000
was
Token was
Feature activation+0.000
seven
Token seven
Feature activation+0.000
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
brother
Token brother
Feature activation+0.878
Phil
Token Phil
Feature activation+3.258
iber
Tokeniber
Feature activation+1.474
t
Tokent
Feature activation+3.439
was
Token was
Feature activation+0.000
four
Token four
Feature activation+0.000
the
Token the
Feature activation+0.000
son
Token son
Feature activation+0.000
of
Token of
Feature activation+0.000
1986
Token 1986
Feature activation+0.000
champion
Token champion
Feature activation+1.290
Bobby
Token Bobby
Feature activation+0.597
Rah
Token Rah
Feature activation+0.000
al
Tokenal
Feature activation+0.000
was
Token was
Feature activation+0.000
looking
Token looking
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 0.000 - 0.453
CONTAINS 99.968%

private
Token private
Feature activation+0.000
property
Token property
Feature activation+0.000
owners
Token owners
Feature activation+0.000
from
Token from
Feature activation+0.000
developing
Token developing
Feature activation+0.000
land
Token land
Feature activation+0.000
right
Token right
Feature activation+0.000
up
Token up
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
trail
Token trail
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000
of
Token of
Feature activation+0.000
careful
Token careful
Feature activation+0.000
planning
Token planning
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
T
TokenT
Feature activation+0.000
-
Token-
Feature activation+0.000
shirts
Tokenshirts
Feature activation+0.000
with
Token with
Feature activation+0.000
accident
Token accident
Feature activation+0.000
involving
Token involving
Feature activation+0.000
a
Token a
Feature activation+0.000
trooper
Token trooper
Feature activation+0.000
sat
Token sat
Feature activation+0.000
down
Token down
Feature activation+0.000
with
Token with
Feature activation+0.000
W
Token W
Feature activation+0.000
Y
TokenY
Feature activation+0.000
FF
TokenFF
Feature activation+0.000
News
Token News
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
asked
Token asked
Feature activation+0.000
Pad
Token Pad
Feature activation+0.000
ale
Tokenale
Feature activation+0.000
cki
Tokencki
Feature activation+0.000
about
Token about
Feature activation+0.000
this
Token this
Feature activation+0.000
contradiction
Token contradiction
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
general
Token general
Feature activation+0.000
population
Token population
Feature activation+0.000
at
Token at
Feature activation+0.000
about
Token about
Feature activation+0.000
3
Token 3
Feature activation+0.000
:
Token:
Feature activation+0.000
05
Token05
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+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 H7.5: (feature 17981)

TOP ACTIVATIONS
MAX = 4.848

protect
Token protect
Feature activation+0.000
their
Token their
Feature activation+0.000
misunderstood
Token misunderstood
Feature activation+0.000
py
Token py
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
,
Token,
Feature activation+4.848
P
Token P
Feature activation+0.139
ia
Tokenia
Feature activation+0.000
and
Token and
Feature activation+0.000
Kir
Token Kir
Feature activation+0.000
an
Tokenan
Feature activation+0.000
complaint
Token complaint
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
joint
Token joint
Feature activation+0.000
response
Token response
Feature activation+0.342
,
Token,
Feature activation+3.686
Dr
Token Dr
Feature activation+0.328
Tr
Token Tr
Feature activation+0.000
acey
Tokenacey
Feature activation+0.000
Batt
Token Batt
Feature activation+0.000
en
Tokenen
Feature activation+0.591
fifth
Token fifth
Feature activation+0.000
record
Token record
Feature activation+0.443
,
Token,
Feature activation+2.042
Big
Token Big
Feature activation+0.000
Balloon
Token Balloon
Feature activation+0.000
,
Token,
Feature activation+3.594
Manchester
Token Manchester
Feature activation+0.148
's
Token's
Feature activation+0.684
Dutch
Token Dutch
Feature activation+0.000
Un
Token Un
Feature activation+0.000
cles
Tokencles
Feature activation+0.000
their
Token their
Feature activation+0.000
knowledge
Token knowledge
Feature activation+0.000
responsibly
Token responsibly
Feature activation+0.000
or
Token or
Feature activation+0.000
otherwise
Token otherwise
Feature activation+0.103
,
Token,
Feature activation+3.514
the
Token the
Feature activation+0.951
Jes
Token Jes
Feature activation+0.000
uits
Tokenuits
Feature activation+0.001
are
Token are
Feature activation+0.000
certainly
Token certainly
Feature activation+0.000
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+0.000
I
Token I
Feature activation+0.000
say
Token say
Feature activation+0.000
not
Token not
Feature activation+0.000
),
Token),
Feature activation+3.402
these
Token these
Feature activation+0.196
cases
Token cases
Feature activation+0.000
represent
Token represent
Feature activation+0.000
mere
Token mere
Feature activation+0.000
foot
Token foot
Feature activation+0.000
ict
Tokenict
Feature activation+0.000
us
Tokenus
Feature activation+0.000
Gaming
Token Gaming
Feature activation+0.000
last
Token last
Feature activation+0.000
night
Token night
Feature activation+0.367
,
Token,
Feature activation+3.130
would
Tokenwould
Feature activation+0.137
drive
Token drive
Feature activation+0.000
that
Token that
Feature activation+0.000
energy
Token energy
Feature activation+0.000
into
Token into
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Despite
TokenDespite
Feature activation+0.000
their
Token their
Feature activation+0.000
small
Token small
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
,
Token,
Feature activation+3.061
the
Token the
Feature activation+0.926
Italians
Token Italians
Feature activation+0.000
were
Token were
Feature activation+0.000
fright
Token fright
Feature activation+0.000
fully
Tokenfully
Feature activation+0.000
ened
Tokenened
Feature activation+0.000
by
Token by
Feature activation+0.000
their
Token their
Feature activation+0.000
growing
Token growing
Feature activation+0.000
power
Token power
Feature activation+0.000
,
Token,
Feature activation+2.990
the
Token the
Feature activation+2.493
King
Token King
Feature activation+0.630
and
Token and
Feature activation+0.000
Queen
Token Queen
Feature activation+0.000
concoct
Token concoct
Feature activation+0.000
am
Token am
Feature activation+0.000
icably
Tokenicably
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Day
Token Day
Feature activation+0.000
said
Token said
Feature activation+0.000
of
Token of
Feature activation+2.914
the
Token the
Feature activation+0.366
Caribbean
Token Caribbean
Feature activation+0.000
countries
Token countries
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
original
Token original
Feature activation+0.000
description
Token description
Feature activation+0.129
of
Token of
Feature activation+0.022
the
Token the
Feature activation+0.000
product
Token product
Feature activation+0.000
,
Token,
Feature activation+2.721
K
Token K
Feature activation+0.417
A
TokenA
Feature activation+0.002
Design
Token Design
Feature activation+1.609
wrote
Token wrote
Feature activation+0.119
,
Token,
Feature activation+0.241
have
Token have
Feature activation+0.000
made
Token made
Feature activation+0.100
to
Token to
Feature activation+0.049
the
Token the
Feature activation+0.000
contrary
Token contrary
Feature activation+0.000
,
Token,
Feature activation+2.709
and
Token and
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
process
Token process
Feature activation+0.000
which
Token which
Feature activation+0.000
every
Token every
Feature activation+0.000
year
Token year
Feature activation+0.000
around
Token around
Feature activation+0.000
this
Token this
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+2.705
arguments
Token arguments
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
ideal
Token ideal
Feature activation+0.000
format
Token format
Feature activation+0.000
their
Token their
Feature activation+0.000
W
Token W
Feature activation+0.164
F
TokenF
Feature activation+0.000
DP
TokenDP
Feature activation+1.246
project
Token project
Feature activation+0.686
,
Token,
Feature activation+2.610
the
Token the
Feature activation+1.636
N
Token N
Feature activation+0.000
FS
TokenFS
Feature activation+0.000
Bi
TokenBi
Feature activation+0.000
H
TokenH
Feature activation+0.491
,
Token,
Feature activation+0.000
virtually
Token virtually
Feature activation+0.000
impossible
Token impossible
Feature activation+0.000
to
Token to
Feature activation+0.000
reach
Token reach
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+2.587
their
Tokentheir
Feature activation+0.726
bewild
Token bewild
Feature activation+0.041
er
Tokener
Feature activation+0.000
ment
Tokenment
Feature activation+0.000
deep
Token deep
Feature activation+0.000
by
Token by
Feature activation+0.000
their
Token their
Feature activation+0.000
growing
Token growing
Feature activation+0.000
power
Token power
Feature activation+0.000
,
Token,
Feature activation+2.990
the
Token the
Feature activation+2.493
King
Token King
Feature activation+0.630
and
Token and
Feature activation+0.000
Queen
Token Queen
Feature activation+0.000
concoct
Token concoct
Feature activation+0.000
ed
Tokened
Feature activation+0.000
for
Token for
Feature activation+0.000
all
Token all
Feature activation+0.000
their
Token their
Feature activation+0.000
attacking
Token attacking
Feature activation+0.000
intent
Token intent
Feature activation+0.292
,
Token,
Feature activation+2.467
P
Token P
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
uca
Tokenuca
Feature activation+0.016
and
Token and
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
Christ
Token Christ
Feature activation+0.207
and
Token and
Feature activation+0.258
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Church
Token Church
Feature activation+0.000
,
Token,
Feature activation+2.418
the
Token the
Feature activation+0.929
couple
Token couple
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
family
Token family
Feature activation+0.000
track
Token track
Feature activation+0.000
record
Token record
Feature activation+0.000
in
Token in
Feature activation+0.000
occupied
Token occupied
Feature activation+0.000
Palestine
Token Palestine
Feature activation+0.000
,
Token,
Feature activation+2.310
I
Token I
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
expect
Token expect
Feature activation+0.000
G
Token G
Feature activation+0.000
throughout
Token throughout
Feature activation+0.321
their
Token their
Feature activation+0.316
entire
Token entire
Feature activation+0.870
developmental
Token developmental
Feature activation+0.370
life
Token life
Feature activation+1.213
,
Token,
Feature activation+2.298
Mill
Token Mill
Feature activation+0.149
en
Tokenen
Feature activation+0.000
ials
Tokenials
Feature activation+0.220
find
Token find
Feature activation+0.000
it
Token it
Feature activation+0.000
good
Token good
Feature activation+0.000
a
Token a
Feature activation+0.000
coach
Token coach
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
,
Token,
Feature activation+2.269
they
Token they
Feature activation+1.132
would
Token would
Feature activation+0.910
have
Token have
Feature activation+0.623
taken
Token taken
Feature activation+0.018
him
Token him
Feature activation+0.044

Top DFA by src position
MAX = 5.233

Ċ
TokenĊ
Feature activation+0.036
Top resid features:
In
TokenIn
Feature activation+0.028
Top resid features:
order
Token order
Feature activation+0.011
Top resid features:
to
Token to
Feature activation+0.017
Top resid features:
protect
Token protect
Feature activation+0.033
Top resid features:
their
Token their
Feature activation+5.233
Top resid features:
misunderstood
Token misunderstood
Feature activation+0.013
Top resid features:
py
Token py
Feature activation-0.030
Top resid features:
ro
Tokenro
Feature activation+0.034
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
P
Token P
Feature activation+0.000
Top resid features:
Making
TokenMaking
Feature activation+0.027
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
formal
Token formal
Feature activation+0.002
Top resid features:
complaint
Token complaint
Feature activation+0.009
Top resid features:
in
Token in
Feature activation+0.008
Top resid features:
their
Token their
Feature activation+4.091
Top resid features:
joint
Token joint
Feature activation+0.063
Top resid features:
response
Token response
Feature activation+0.065
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
Dr
Token Dr
Feature activation+0.000
Top resid features:
Tr
Token Tr
Feature activation+0.000
Top resid features:
push
Token push
Feature activation-0.001
Top resid features:
itself
Token itself
Feature activation+0.003
Top resid features:
forward
Token forward
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
On
Token On
Feature activation+0.075
Top resid features:
their
Token their
Feature activation+3.727
Top resid features:
fifth
Token fifth
Feature activation+0.104
Top resid features:
record
Token record
Feature activation+0.131
Top resid features:
,
Token,
Feature activation+0.089
Top resid features:
Big
Token Big
Feature activation+0.001
Top resid features:
Balloon
Token Balloon
Feature activation+0.004
Top resid features:
schools
Token schools
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.038
Top resid features:
Ċ
TokenĊ
Feature activation+0.043
Top resid features:
Whether
TokenWhether
Feature activation-0.009
Top resid features:
they
Token they
Feature activation+3.785
Top resid features:
use
Token use
Feature activation-0.058
Top resid features:
their
Token their
Feature activation+0.193
Top resid features:
knowledge
Token knowledge
Feature activation+0.017
Top resid features:
responsibly
Token responsibly
Feature activation+0.007
Top resid features:
or
Token or
Feature activation+0.039
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
three
Token three
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.121
Top resid features:
Whether
TokenWhether
Feature activation-0.006
Top resid features:
they
Token they
Feature activation+3.888
Top resid features:
constitute
Token constitute
Feature activation+0.011
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
trend
Token trend
Feature activation-0.047
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.056
Top resid features:
Championships
Token Championships
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Fresh
TokenFresh
Feature activation+0.007
Top resid features:
from
Token from
Feature activation+0.020
Top resid features:
their
Token their
Feature activation+3.657
Top resid features:
victory
Token victory
Feature activation+0.030
Top resid features:
against
Token against
Feature activation-0.004
Top resid features:
Inv
Token Inv
Feature activation-0.002
Top resid features:
ict
Tokenict
Feature activation-0.017
Top resid features:
us
Tokenus
Feature activation-0.010
Top resid features:
delayed
Token delayed
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.047
Top resid features:
Ċ
TokenĊ
Feature activation+0.042
Top resid features:
Despite
TokenDespite
Feature activation+0.035
Top resid features:
their
Token their
Feature activation+3.201
Top resid features:
small
Token small
Feature activation+0.012
Top resid features:
ness
Tokenness
Feature activation+0.104
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Italians
Token Italians
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
Th
TokenTh
Feature activation+0.014
Top resid features:
reat
Tokenreat
Feature activation+0.007
Top resid features:
ened
Tokenened
Feature activation+0.052
Top resid features:
by
Token by
Feature activation+0.015
Top resid features:
their
Token their
Feature activation+3.276
Top resid features:
growing
Token growing
Feature activation+0.025
Top resid features:
power
Token power
Feature activation+0.139
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
King
Token King
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
"
Token"
Feature activation+0.001
Top resid features:
I
TokenI
Feature activation-0.016
Top resid features:
think
Token think
Feature activation-0.010
Top resid features:
they
Token they
Feature activation+3.079
Top resid features:
would
Token would
Feature activation+0.288
Top resid features:
undoubtedly
Token undoubtedly
Feature activation+0.027
Top resid features:
want
Token want
Feature activation+0.035
Top resid features:
to
Token to
Feature activation+0.012
Top resid features:
try
Token try
Feature activation+0.002
Top resid features:
community
Token community
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
In
TokenIn
Feature activation+0.029
Top resid features:
their
Token their
Feature activation+2.822
Top resid features:
original
Token original
Feature activation+0.145
Top resid features:
description
Token description
Feature activation+0.143
Top resid features:
of
Token of
Feature activation+0.043
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
product
Token product
Feature activation-0.014
Top resid features:
But
TokenBut
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.041
Top resid features:
in
Token in
Feature activation+0.021
Top resid features:
spite
Token spite
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
their
Token their
Feature activation+2.237
Top resid features:
admirable
Token admirable
Feature activation+0.031
Top resid features:
spirit
Token spirit
Feature activation+0.053
Top resid features:
and
Token and
Feature activation+0.011
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
every
Token every
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
Ore
Token Ore
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
--
Token --
Feature activation+0.026
Top resid features:
As
Token As
Feature activation+0.037
Top resid features:
they
Token they
Feature activation+2.678
Top resid features:
do
Token do
Feature activation+0.330
Top resid features:
every
Token every
Feature activation+0.011
Top resid features:
year
Token year
Feature activation+0.003
Top resid features:
around
Token around
Feature activation+0.021
Top resid features:
this
Token this
Feature activation+0.080
Top resid features:
officials
Token officials
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
In
TokenIn
Feature activation+0.064
Top resid features:
their
Token their
Feature activation+3.054
Top resid features:
W
Token W
Feature activation-0.004
Top resid features:
F
TokenF
Feature activation+0.005
Top resid features:
DP
TokenDP
Feature activation+0.003
Top resid features:
project
Token project
Feature activation+0.020
Top resid features:
,
Token,
Feature activation+0.036
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ŀ
TokenĿ
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.037
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
When
TokenWhen
Feature activation+0.005
Top resid features:
they
Token they
Feature activation+2.699
Top resid features:
also
Token also
Feature activation+0.084
Top resid features:
learned
Token learned
Feature activation+0.174
Top resid features:
just
Token just
Feature activation+0.002
Top resid features:
before
Token before
Feature activation+0.021
Top resid features:
departure
Token departure
Feature activation+0.030
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Th
TokenTh
Feature activation+0.005
Top resid features:
reat
Tokenreat
Feature activation-0.004
Top resid features:
ened
Tokenened
Feature activation+0.043
Top resid features:
by
Token by
Feature activation+0.007
Top resid features:
their
Token their
Feature activation+2.799
Top resid features:
growing
Token growing
Feature activation+0.015
Top resid features:
power
Token power
Feature activation+0.067
Top resid features:
,
Token,
Feature activation+0.056
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
King
Token King
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.033
Top resid features:
Ċ
TokenĊ
Feature activation+0.046
Top resid features:
But
TokenBut
Feature activation+0.008
Top resid features:
for
Token for
Feature activation+0.036
Top resid features:
all
Token all
Feature activation+0.054
Top resid features:
their
Token their
Feature activation+2.841
Top resid features:
attacking
Token attacking
Feature activation-0.035
Top resid features:
intent
Token intent
Feature activation+0.044
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
P
Token P
Feature activation+0.000
Top resid features:
ach
Tokenach
Feature activation+0.000
Top resid features:
ization
Tokenization
Feature activation-0.002
Top resid features:
:
Token:
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation-0.018
Top resid features:
Because
TokenBecause
Feature activation+0.090
Top resid features:
they
Token they
Feature activation+2.828
Top resid features:
belong
Token belong
Feature activation+0.058
Top resid features:
to
Token to
Feature activation+0.010
Top resid features:
Christ
Token Christ
Feature activation+0.038
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
itan
Tokenitan
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
âĢ
Token âĢ
Feature activation+0.007
Top resid features:
ľ
Tokenľ
Feature activation+0.002
Top resid features:
Given
TokenGiven
Feature activation+0.188
Top resid features:
their
Token their
Feature activation+2.852
Top resid features:
track
Token track
Feature activation+0.009
Top resid features:
record
Token record
Feature activation+0.024
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
occupied
Token occupied
Feature activation+0.003
Top resid features:
Palestine
Token Palestine
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Having
TokenHaving
Feature activation+0.020
Top resid features:
been
Token been
Feature activation+0.008
Top resid features:
told
Token told
Feature activation+0.073
Top resid features:
they
Token they
Feature activation+1.381
Top resid features:
are
Token are
Feature activation+0.016
Top resid features:
special
Token special
Feature activation-0.002
Top resid features:
throughout
Token throughout
Feature activation+0.018
Top resid features:
their
Token their
Feature activation+1.267
Top resid features:
entire
Token entire
Feature activation+0.028
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
field
Token field
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Maybe
Token Maybe
Feature activation+0.009
Top resid features:
if
Token if
Feature activation+0.032
Top resid features:
they
Token they
Feature activation+1.972
Top resid features:
had
Token had
Feature activation+0.433
Top resid features:
known
Token known
Feature activation+0.300
Top resid features:
how
Token how
Feature activation+0.030
Top resid features:
good
Token good
Feature activation+0.014
Top resid features:
a
Token a
Feature activation-0.016
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.04

Head 2: 0.01

Head 3: 0.07

Head 4: 0.07

Head 5: 0.50

Head 6: 0.03

Head 7: 0.03

Head 8: 0.10

Head 9: 0.06

Head 10: 0.03

Head 11: 0.02

Positive logits

arians2.58

programmers2.39

agers2.38

rators2.36

writers2.34

teams2.32

sburg2.26

Directors2.24

selves2.22

icans2.22

Females2.21

dogs2.21

Participants2.19

hawks2.17

erers2.15

participants2.15

zees2.14

ippers2.14

ilers2.13

wives2.10

Negative logits

airspace-2.09

extrad-1.99

ebin-1.87

goodness-1.86

enance-1.84

ammy-1.84

milo-1.81

borders-1.78

sclerosis-1.76

blasphemy-1.74

autobiography-1.72

Transparency-1.72

Cooldown-1.72

extradition-1.72

ailability-1.68

Growing-1.68

landfall-1.68

Detective-1.68

anchester-1.68

tuberculosis-1.66

INTERVAL 4.364 - 4.848
CONTAINS 0.000%

protect
Token protect
Feature activation+0.000
their
Token their
Feature activation+0.000
misunderstood
Token misunderstood
Feature activation+0.000
py
Token py
Feature activation+0.000
ro
Tokenro
Feature activation+0.000
,
Token,
Feature activation+4.848
P
Token P
Feature activation+0.139
ia
Tokenia
Feature activation+0.000
and
Token and
Feature activation+0.000
Kir
Token Kir
Feature activation+0.000
an
Tokenan
Feature activation+0.000

INTERVAL 3.879 - 4.364
CONTAINS 0.000%

INTERVAL 3.394 - 3.879
CONTAINS 0.000%

complaint
Token complaint
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
joint
Token joint
Feature activation+0.000
response
Token response
Feature activation+0.342
,
Token,
Feature activation+3.686
Dr
Token Dr
Feature activation+0.328
Tr
Token Tr
Feature activation+0.000
acey
Tokenacey
Feature activation+0.000
Batt
Token Batt
Feature activation+0.000
en
Tokenen
Feature activation+0.591
their
Token their
Feature activation+0.000
knowledge
Token knowledge
Feature activation+0.000
responsibly
Token responsibly
Feature activation+0.000
or
Token or
Feature activation+0.000
otherwise
Token otherwise
Feature activation+0.103
,
Token,
Feature activation+3.514
the
Token the
Feature activation+0.951
Jes
Token Jes
Feature activation+0.000
uits
Tokenuits
Feature activation+0.001
are
Token are
Feature activation+0.000
certainly
Token certainly
Feature activation+0.000
fifth
Token fifth
Feature activation+0.000
record
Token record
Feature activation+0.443
,
Token,
Feature activation+2.042
Big
Token Big
Feature activation+0.000
Balloon
Token Balloon
Feature activation+0.000
,
Token,
Feature activation+3.594
Manchester
Token Manchester
Feature activation+0.148
's
Token's
Feature activation+0.684
Dutch
Token Dutch
Feature activation+0.000
Un
Token Un
Feature activation+0.000
cles
Tokencles
Feature activation+0.000
(
Token (
Feature activation+0.000
and
Tokenand
Feature activation+0.000
I
Token I
Feature activation+0.000
say
Token say
Feature activation+0.000
not
Token not
Feature activation+0.000
),
Token),
Feature activation+3.402
these
Token these
Feature activation+0.196
cases
Token cases
Feature activation+0.000
represent
Token represent
Feature activation+0.000
mere
Token mere
Feature activation+0.000
foot
Token foot
Feature activation+0.000

INTERVAL 2.909 - 3.394
CONTAINS 0.000%

ict
Tokenict
Feature activation+0.000
us
Tokenus
Feature activation+0.000
Gaming
Token Gaming
Feature activation+0.000
last
Token last
Feature activation+0.000
night
Token night
Feature activation+0.367
,
Token,
Feature activation+3.130
would
Tokenwould
Feature activation+0.137
drive
Token drive
Feature activation+0.000
that
Token that
Feature activation+0.000
energy
Token energy
Feature activation+0.000
into
Token into
Feature activation+0.000
am
Token am
Feature activation+0.000
icably
Tokenicably
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Day
Token Day
Feature activation+0.000
said
Token said
Feature activation+0.000
of
Token of
Feature activation+2.914
the
Token the
Feature activation+0.366
Caribbean
Token Caribbean
Feature activation+0.000
countries
Token countries
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
ened
Tokenened
Feature activation+0.000
by
Token by
Feature activation+0.000
their
Token their
Feature activation+0.000
growing
Token growing
Feature activation+0.000
power
Token power
Feature activation+0.000
,
Token,
Feature activation+2.990
the
Token the
Feature activation+2.493
King
Token King
Feature activation+0.630
and
Token and
Feature activation+0.000
Queen
Token Queen
Feature activation+0.000
concoct
Token concoct
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Despite
TokenDespite
Feature activation+0.000
their
Token their
Feature activation+0.000
small
Token small
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
,
Token,
Feature activation+3.061
the
Token the
Feature activation+0.926
Italians
Token Italians
Feature activation+0.000
were
Token were
Feature activation+0.000
fright
Token fright
Feature activation+0.000
fully
Tokenfully
Feature activation+0.000

INTERVAL 2.424 - 2.909
CONTAINS 0.001%

original
Token original
Feature activation+0.000
description
Token description
Feature activation+0.129
of
Token of
Feature activation+0.022
the
Token the
Feature activation+0.000
product
Token product
Feature activation+0.000
,
Token,
Feature activation+2.721
K
Token K
Feature activation+0.417
A
TokenA
Feature activation+0.002
Design
Token Design
Feature activation+1.609
wrote
Token wrote
Feature activation+0.119
,
Token,
Feature activation+0.241
every
Token every
Feature activation+0.000
year
Token year
Feature activation+0.000
around
Token around
Feature activation+0.000
this
Token this
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+2.705
arguments
Token arguments
Feature activation+0.000
about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
ideal
Token ideal
Feature activation+0.000
format
Token format
Feature activation+0.000
,
Token,
Feature activation+0.000
virtually
Token virtually
Feature activation+0.000
impossible
Token impossible
Feature activation+0.000
to
Token to
Feature activation+0.000
reach
Token reach
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+2.587
their
Tokentheir
Feature activation+0.726
bewild
Token bewild
Feature activation+0.041
er
Tokener
Feature activation+0.000
ment
Tokenment
Feature activation+0.000
deep
Token deep
Feature activation+0.000
for
Token for
Feature activation+0.000
all
Token all
Feature activation+0.000
their
Token their
Feature activation+0.000
attacking
Token attacking
Feature activation+0.000
intent
Token intent
Feature activation+0.292
,
Token,
Feature activation+2.467
P
Token P
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
uca
Tokenuca
Feature activation+0.016
and
Token and
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
their
Token their
Feature activation+0.000
W
Token W
Feature activation+0.164
F
TokenF
Feature activation+0.000
DP
TokenDP
Feature activation+1.246
project
Token project
Feature activation+0.686
,
Token,
Feature activation+2.610
the
Token the
Feature activation+1.636
N
Token N
Feature activation+0.000
FS
TokenFS
Feature activation+0.000
Bi
TokenBi
Feature activation+0.000
H
TokenH
Feature activation+0.491

INTERVAL 1.939 - 2.424
CONTAINS 0.001%

"
Token"
Feature activation+0.000
In
TokenIn
Feature activation+0.000
general
Token general
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
[
Token [
Feature activation+2.170
Prince
TokenPrince
Feature activation+0.000
Philip
Token Philip
Feature activation+0.000
and
Token and
Feature activation+0.000
Lord
Token Lord
Feature activation+0.000
Mont
Token Mont
Feature activation+0.000
Against
TokenAgainst
Feature activation+0.000
a
Token a
Feature activation+0.000
tenth
Token tenth
Feature activation+0.000
their
Token their
Feature activation+0.000
number
Token number
Feature activation+0.897
,
Token,
Feature activation+2.166
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.175
I
Token I
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
human
Token human
Feature activation+0.000
rights
Token rights
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
victim
Token victim
Feature activation+0.000
,
Token,
Feature activation+2.075
violating
Token violating
Feature activation+0.000
them
Token them
Feature activation+0.000
in
Token in
Feature activation+0.048
order
Token order
Feature activation+0.016
to
Token to
Feature activation+0.078
Christ
Token Christ
Feature activation+0.207
and
Token and
Feature activation+0.258
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Church
Token Church
Feature activation+0.000
,
Token,
Feature activation+2.418
the
Token the
Feature activation+0.929
couple
Token couple
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
family
Token family
Feature activation+0.000
practiced
Token practiced
Feature activation+0.000
their
Token their
Feature activation+0.000
line
Token line
Feature activation+0.000
out
Tokenout
Feature activation+0.000
moves
Token moves
Feature activation+1.022
,
Token,
Feature activation+2.199
pink
Token pink
Feature activation+0.000
flaming
Token flaming
Feature activation+0.000
os
Tokenos
Feature activation+0.000
strut
Token strut
Feature activation+0.000
ted
Tokented
Feature activation+0.000

INTERVAL 1.455 - 1.939
CONTAINS 0.002%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
For
TokenFor
Feature activation+0.000
their
Token their
Feature activation+0.000
study
Token study
Feature activation+0.232
,
Token,
Feature activation+1.855
the
Token the
Feature activation+0.881
scientists
Token scientists
Feature activation+0.000
collected
Token collected
Feature activation+0.000
fl
Token fl
Feature activation+0.000
otation
Tokenotation
Feature activation+0.000
legs
Token legs
Feature activation+0.000
are
Token are
Feature activation+0.000
their
Token their
Feature activation+0.000
greatest
Token greatest
Feature activation+0.000
strength
Token strength
Feature activation+0.000
,
Token,
Feature activation+1.569
they
Token they
Feature activation+0.031
modify
Token modify
Feature activation+0.386
their
Token their
Feature activation+0.000
entry
Token entry
Feature activation+0.000
into
Token into
Feature activation+0.000
murky
Token murky
Feature activation+0.000
history
Token history
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
art
Token art
Feature activation+0.000
,
Token,
Feature activation+1.478
some
Token some
Feature activation+0.000
organizations
Token organizations
Feature activation+0.000
and
Token and
Feature activation+0.000
individuals
Token individuals
Feature activation+0.000
have
Token have
Feature activation+0.000
W
Token W
Feature activation+0.164
F
TokenF
Feature activation+0.000
DP
TokenDP
Feature activation+1.246
project
Token project
Feature activation+0.686
,
Token,
Feature activation+2.610
the
Token the
Feature activation+1.636
N
Token N
Feature activation+0.000
FS
TokenFS
Feature activation+0.000
Bi
TokenBi
Feature activation+0.000
H
TokenH
Feature activation+0.491
aimed
Token aimed
Feature activation+0.000
Their
Token Their
Feature activation+0.000
14
Token 14
Feature activation+0.514
-
Token-
Feature activation+0.552
year
Tokenyear
Feature activation+0.596
-
Token-
Feature activation+0.762
old
Tokenold
Feature activation+1.871
boy
Token boy
Feature activation+0.828
had
Token had
Feature activation+0.000
cancer
Token cancer
Feature activation+0.000
.
Token.
Feature activation+0.312
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.970 - 1.455
CONTAINS 0.002%

purchasing
Token purchasing
Feature activation+0.000
behavior
Token behavior
Feature activation+0.000
on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
website
Token website
Feature activation+0.091
,
Token,
Feature activation+1.001
it
Token it
Feature activation+0.000
also
Token also
Feature activation+0.000
collects
Token collects
Feature activation+0.000
other
Token other
Feature activation+0.000
data
Token data
Feature activation+0.000
street
Token street
Feature activation+0.000
harassment
Token harassment
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
lif
Token lif
Feature activation+0.214
etimes
Tokenetimes
Feature activation+1.010
.
Token.
Feature activation+0.114
Even
Token Even
Feature activation+0.000
worse
Token worse
Feature activation+0.000
,
Token,
Feature activation+0.000
41
Token 41
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
their
Token their
Feature activation+0.000
W
Token W
Feature activation+0.164
F
TokenF
Feature activation+0.000
DP
TokenDP
Feature activation+1.246
project
Token project
Feature activation+0.686
,
Token,
Feature activation+2.610
the
Token the
Feature activation+1.636
N
Token N
Feature activation+0.000
FS
TokenFS
Feature activation+0.000
think
Token think
Feature activation+0.000
is
Token is
Feature activation+0.000
their
Token their
Feature activation+0.000
home
Token home
Feature activation+0.152
,
Token,
Feature activation+1.525
the
Token the
Feature activation+1.309
front
Token front
Feature activation+0.000
door
Token door
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
mentioned
Token mentioned
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.009
K
TokenK
Feature activation+0.440
urt
Tokenurt
Feature activation+1.318
Cob
Token Cob
Feature activation+0.000
ain
Tokenain
Feature activation+0.071
's
Token's
Feature activation+0.000
destructive
Token destructive
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.485 - 0.970
CONTAINS 0.013%

the
Token the
Feature activation+0.015
legendary
Token legendary
Feature activation+0.000
photographer
Token photographer
Feature activation+0.000
Kevin
Token Kevin
Feature activation+0.000
Cumm
Token Cumm
Feature activation+0.000
ins
Tokenins
Feature activation+0.518
who
Token who
Feature activation+0.000
captured
Token captured
Feature activation+0.000
James
Token James
Feature activation+0.000
,
Token,
Feature activation+0.000
Sean
Token Sean
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
tendency
Token tendency
Feature activation+0.000
to
Token to
Feature activation+0.000
color
Token color
Feature activation+0.000
.
Token.
Feature activation+0.748
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
F
TokenF
Feature activation+0.000
ruits
Tokenruits
Feature activation+0.000
are
Token are
Feature activation+0.000
the
Token the
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
explosion
Token explosion
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
on
Token on
Feature activation+0.564
their
Token their
Feature activation+0.000
labels
Token labels
Feature activation+0.268
.
Token.
Feature activation+0.000
So
Token So
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
longer
Token longer
Feature activation+0.000
.
Token.
Feature activation+0.000
Wood
Token Wood
Feature activation+0.128
ruff
Tokenruff
Feature activation+0.839
says
Token says
Feature activation+0.000
first
Token first
Feature activation+0.000
they
Token they
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
differences
Token differences
Feature activation+0.000
is
Token is
Feature activation+0.241
that
Token that
Feature activation+0.492
the
Token the
Feature activation+0.107
dogs
Token dogs
Feature activation+0.000
care
Token care
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.485
CONTAINS 99.980%

an
Token an
Feature activation+0.000
enthusiastic
Token enthusiastic
Feature activation+0.000
member
Token member
Feature activation+0.000
of
Token of
Feature activation+0.000
Rid
Token Rid
Feature activation+0.000
gew
Tokengew
Feature activation+0.000
ell
Tokenell
Feature activation+0.000
Gl
Token Gl
Feature activation+0.000
iding
Tokeniding
Feature activation+0.000
Club
Token Club
Feature activation+0.000
and
Token and
Feature activation+0.000
immense
Token immense
Feature activation+0.000
flexibility
Token flexibility
Feature activation+0.000
.
Token.
Feature activation+0.000
He
Token He
Feature activation+0.000
averaged
Token averaged
Feature activation+0.000
268
Token 268
Feature activation+0.000
.
Token.
Feature activation+0.000
7
Token7
Feature activation+0.000
yards
Token yards
Feature activation+0.000
in
Token in
Feature activation+0.000
driving
Token driving
Feature activation+0.000
to
Token to
Feature activation+0.000
dig
Token dig
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
graves
Token graves
Feature activation+0.000
in
Token in
Feature activation+0.000
front
Token front
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
family
Token family
Feature activation+0.000
and
Token and
Feature activation+0.000
-
Token-
Feature activation+0.000
power
Tokenpower
Feature activation+0.000
BP
Token BP
Feature activation+0.000
12
Token 12
Feature activation+0.000
-
Token-
Feature activation+0.000
7
Token7
Feature activation+0.000
.
Token.
Feature activation+0.000
0
Token0
Feature activation+0.000
,
Token,
Feature activation+0.000
7
Token 7
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
interview
Token interview
Feature activation+0.000
he
Token he
Feature activation+0.000
shared
Token shared
Feature activation+0.000
it
Token it
Feature activation+0.000
with
Token with
Feature activation+0.000
his
Token his
Feature activation+0.000
co
Token co
Feature activation+0.000
-
Token-
Feature activation+0.000
workers
Tokenworkers
Feature activation+0.000
because
Token because
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 H7.5: (feature 29111)

TOP ACTIVATIONS
MAX = 3.255

number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
flights
Token flights
Feature activation+0.000
,
Token,
Feature activation+0.146
believed
Token believed
Feature activation+1.016
to
Token to
Feature activation+3.255
include
Token include
Feature activation+1.319
routes
Token routes
Feature activation+0.000
from
Token from
Feature activation+0.000
Heath
Token Heath
Feature activation+0.000
row
Tokenrow
Feature activation+0.000
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
went
Token went
Feature activation+0.000
as
Token as
Feature activation+0.000
low
Token low
Feature activation+0.000
as
Token as
Feature activation+2.882
11
Token 11
Feature activation+1.569
and
Token and
Feature activation+0.000
10
Token 10
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.467
of
Token of
Feature activation+0.000
land
Token land
Feature activation+0.000
available
Token available
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.287
only
Token only
Feature activation+1.901
seven
Token seven
Feature activation+2.613
of
Token of
Feature activation+0.180
the
Token the
Feature activation+0.000
900
Token 900
Feature activation+0.495
tracts
Token tracts
Feature activation+0.000
offered
Token offered
Feature activation+0.000
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
typically
Token typically
Feature activation+0.000
mild
Token mild
Feature activation+0.000
,
Token,
Feature activation+1.191
including
Token including
Feature activation+2.495
fever
Token fever
Feature activation+0.106
and
Token and
Feature activation+1.455
joint
Token joint
Feature activation+0.000
pain
Token pain
Feature activation+0.000
.
Token.
Feature activation+0.000
were
Token were
Feature activation+0.000
small
Token small
Feature activation+0.000
,
Token,
Feature activation+0.802
fewer
Token fewer
Feature activation+1.055
than
Token than
Feature activation+1.397
100
Token 100
Feature activation+2.384
people
Token people
Feature activation+0.958
,
Token,
Feature activation+0.604
recalls
Token recalls
Feature activation+0.000
Charlie
Token Charlie
Feature activation+0.000
Hughes
Token Hughes
Feature activation+0.000
are
Token are
Feature activation+0.000
"
Token "
Feature activation+0.000
small
Tokensmall
Feature activation+0.000
"
Token"
Feature activation+0.000
(
Token (
Feature activation+0.367
having
Tokenhaving
Feature activation+2.089
shorter
Token shorter
Feature activation+0.952
wavelengths
Token wavelengths
Feature activation+0.302
),
Token),
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.000
kid
Token kid
Feature activation+0.000
who
Token who
Feature activation+0.587
didn
Token didn
Feature activation+0.959
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+2.077
talk
Token talk
Feature activation+0.843
much
Token much
Feature activation+0.453
in
Token in
Feature activation+0.189
class
Token class
Feature activation+0.000
or
Token or
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.696
A
Token A
Feature activation+1.333
mere
Token mere
Feature activation+1.789
fifteen
Token fifteen
Feature activation+2.043
players
Token players
Feature activation+0.725
make
Token make
Feature activation+0.471
up
Token up
Feature activation+0.352
a
Token a
Feature activation+0.151
very
Token very
Feature activation+0.254
women
Token women
Feature activation+0.000
initially
Token initially
Feature activation+0.000
charged
Token charged
Feature activation+0.000
very
Token very
Feature activation+0.000
little
Token little
Feature activation+0.000
,
Token,
Feature activation+2.010
but
Token but
Feature activation+0.449
then
Token then
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
their
Token their
Feature activation+0.000
a
Token a
Feature activation+0.000
relatively
Token relatively
Feature activation+0.000
small
Token small
Feature activation+0.067
distance
Token distance
Feature activation+0.000
of
Token of
Feature activation+0.815
260
Token 260
Feature activation+2.010
kilometres
Token kilometres
Feature activation+0.226
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
surface
Token surface
Feature activation+0.000
of
Token of
Feature activation+0.006
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.255
You
TokenYou
Feature activation+0.794
're
Token're
Feature activation+0.673
talking
Token talking
Feature activation+1.462
about
Token about
Feature activation+2.001
a
Token a
Feature activation+1.291
combined
Token combined
Feature activation+0.545
total
Token total
Feature activation+0.630
of
Token of
Feature activation+1.098
about
Token about
Feature activation+0.886
in
Token in
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000
areas
Token areas
Feature activation+0.000
(
Token (
Feature activation+0.429
such
Tokensuch
Feature activation+1.092
as
Token as
Feature activation+1.908
Burke
Token Burke
Feature activation+0.000
Virginia
Token Virginia
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
),
Token),
Feature activation+0.009
fraction
Token fraction
Feature activation+0.000
of
Token of
Feature activation+0.000
land
Token land
Feature activation+0.000
available
Token available
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.287
only
Token only
Feature activation+1.901
seven
Token seven
Feature activation+2.613
of
Token of
Feature activation+0.180
the
Token the
Feature activation+0.000
900
Token 900
Feature activation+0.495
tracts
Token tracts
Feature activation+0.000
restaurant
Token restaurant
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
tiny
Token tiny
Feature activation+0.000
space
Token space
Feature activation+0.445
with
Token with
Feature activation+1.879
blue
Token blue
Feature activation+0.029
marble
Token marble
Feature activation+0.000
counters
Token counters
Feature activation+0.166
where
Token where
Feature activation+0.188
customers
Token customers
Feature activation+0.024
allow
Token allow
Feature activation+0.000
small
Token small
Feature activation+0.000
elite
Token elite
Feature activation+0.000
units
Token units
Feature activation+0.000
,
Token,
Feature activation+0.042
like
Token like
Feature activation+1.875
Green
Token Green
Feature activation+0.060
Bere
Token Bere
Feature activation+0.000
ts
Tokents
Feature activation+0.142
or
Token or
Feature activation+0.375
Navy
Token Navy
Feature activation+0.027
to
Token to
Feature activation+0.077
make
Token make
Feature activation+0.061
it
Token it
Feature activation+0.000
small
Token small
Feature activation+0.057
enough
Token enough
Feature activation+0.159
to
Token to
Feature activation+1.794
form
Token form
Feature activation+0.400
the
Token the
Feature activation+0.000
basis
Token basis
Feature activation+0.000
of
Token of
Feature activation+0.020
the
Token the
Feature activation+0.000
require
Token require
Feature activation+0.000
minimal
Token minimal
Feature activation+0.000
formation
Token formation
Feature activation+0.075
of
Token of
Feature activation+0.095
gluten
Token gluten
Feature activation+0.000
,
Token,
Feature activation+1.794
like
Token like
Feature activation+0.890
cake
Token cake
Feature activation+0.000
and
Token and
Feature activation+0.017
muff
Token muff
Feature activation+0.000
ins
Tokenins
Feature activation+0.076
small
Token small
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.696
A
Token A
Feature activation+1.333
mere
Token mere
Feature activation+1.789
fifteen
Token fifteen
Feature activation+2.043
players
Token players
Feature activation+0.725
make
Token make
Feature activation+0.471
up
Token up
Feature activation+0.352
a
Token a
Feature activation+0.151
small
Token small
Feature activation+0.000
portion
Token portion
Feature activation+0.000
is
Token is
Feature activation+0.000
sent
Token sent
Feature activation+0.000
(
Token (
Feature activation+0.632
a
Tokena
Feature activation+1.735
key
Token key
Feature activation+0.254
)
Token)
Feature activation+0.000
to
Token to
Feature activation+0.000
indicate
Token indicate
Feature activation+0.000
the
Token the
Feature activation+0.000
low
Token low
Feature activation+0.000
Mach
Token Mach
Feature activation+0.000
number
Token number
Feature activation+0.000
(
Token (
Feature activation+0.340
less
Tokenless
Feature activation+1.627
than
Token than
Feature activation+1.719
two
Token two
Feature activation+0.659
).
Token).
Feature activation+0.000
Sound
Token Sound
Feature activation+0.000
moves
Token moves
Feature activation+0.000
pretty
Token pretty
Feature activation+0.000

Top DFA by src position
MAX = 3.549

said
Token said
Feature activation+0.003
Top resid features:
it
Token it
Feature activation+0.002
Top resid features:
had
Token had
Feature activation+0.003
Top resid features:
diverted
Token diverted
Feature activation+0.006
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
small
Token small
Feature activation+3.549
Top resid features:
number
Token number
Feature activation+0.141
Top resid features:
of
Token of
Feature activation+0.013
Top resid features:
flights
Token flights
Feature activation-0.037
Top resid features:
,
Token,
Feature activation+0.049
Top resid features:
believed
Token believed
Feature activation-0.027
Top resid features:
percent
Token percent
Feature activation+0.024
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
some
Token some
Feature activation+0.008
Top resid features:
went
Token went
Feature activation-0.017
Top resid features:
as
Token as
Feature activation-0.002
Top resid features:
low
Token low
Feature activation+3.315
Top resid features:
as
Token as
Feature activation+0.006
Top resid features:
11
Token 11
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
10
Token 10
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
But
Token But
Feature activation-0.011
Top resid features:
companies
Token companies
Feature activation-0.031
Top resid features:
bid
Token bid
Feature activation-0.003
Top resid features:
on
Token on
Feature activation-0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
tiny
Token tiny
Feature activation+1.759
Top resid features:
fraction
Token fraction
Feature activation+1.020
Top resid features:
of
Token of
Feature activation+0.119
Top resid features:
land
Token land
Feature activation-0.009
Top resid features:
available
Token available
Feature activation+0.005
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.112
Top resid features:
appear
Token appear
Feature activation+0.014
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
they
Token they
Feature activation+0.001
Top resid features:
are
Token are
Feature activation+0.011
Top resid features:
typically
Token typically
Feature activation+0.010
Top resid features:
mild
Token mild
Feature activation+2.859
Top resid features:
,
Token,
Feature activation+0.047
Top resid features:
including
Token including
Feature activation+0.016
Top resid features:
fever
Token fever
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
joint
Token joint
Feature activation+0.000
Top resid features:
mid
Token mid
Feature activation+0.002
Top resid features:
-
Token-
Feature activation+0.004
Top resid features:
1980
Token1980
Feature activation+0.020
Top resid features:
s
Tokens
Feature activation-0.004
Top resid features:
were
Token were
Feature activation+0.036
Top resid features:
small
Token small
Feature activation+2.277
Top resid features:
,
Token,
Feature activation+0.206
Top resid features:
fewer
Token fewer
Feature activation+0.280
Top resid features:
than
Token than
Feature activation+0.002
Top resid features:
100
Token 100
Feature activation+0.014
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
microw
Token microw
Feature activation+0.000
Top resid features:
aves
Tokenaves
Feature activation-0.001
Top resid features:
are
Token are
Feature activation-0.002
Top resid features:
"
Token "
Feature activation+0.005
Top resid features:
small
Tokensmall
Feature activation+0.999
Top resid features:
"
Token"
Feature activation+1.134
Top resid features:
(
Token (
Feature activation+0.305
Top resid features:
having
Tokenhaving
Feature activation+0.018
Top resid features:
shorter
Token shorter
Feature activation+0.000
Top resid features:
wavelengths
Token wavelengths
Feature activation+0.000
Top resid features:
),
Token),
Feature activation+0.000
Top resid features:
principal
Token principal
Feature activation-0.003
Top resid features:
said
Token said
Feature activation-0.007
Top resid features:
he
Token he
Feature activation+0.008
Top resid features:
was
Token was
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
quiet
Token quiet
Feature activation+1.667
Top resid features:
,
Token,
Feature activation+0.188
Top resid features:
shy
Token shy
Feature activation+0.554
Top resid features:
kid
Token kid
Feature activation+0.094
Top resid features:
who
Token who
Feature activation+0.041
Top resid features:
didn
Token didn
Feature activation+0.037
Top resid features:
about
Token about
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
team
Token team
Feature activation+0.001
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
how
Token how
Feature activation+0.000
Top resid features:
small
Token small
Feature activation+1.561
Top resid features:
it
Token it
Feature activation+0.267
Top resid features:
is
Token is
Feature activation+0.573
Top resid features:
.
Token.
Feature activation+0.025
Top resid features:
A
Token A
Feature activation+0.005
Top resid features:
mere
Token mere
Feature activation+0.028
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
women
Token women
Feature activation+0.008
Top resid features:
initially
Token initially
Feature activation-0.036
Top resid features:
charged
Token charged
Feature activation-0.031
Top resid features:
very
Token very
Feature activation+0.043
Top resid features:
little
Token little
Feature activation+2.372
Top resid features:
,
Token,
Feature activation+0.159
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
then
Token then
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.001
Top resid features:
orbit
Token orbit
Feature activation+0.024
Top resid features:
at
Token at
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
relatively
Token relatively
Feature activation+0.013
Top resid features:
small
Token small
Feature activation+1.419
Top resid features:
distance
Token distance
Feature activation+0.839
Top resid features:
of
Token of
Feature activation+0.049
Top resid features:
260
Token 260
Feature activation+0.014
Top resid features:
kilometres
Token kilometres
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
These
TokenThese
Feature activation+0.004
Top resid features:
two
Token two
Feature activation+0.001
Top resid features:
things
Token things
Feature activation-0.016
Top resid features:
are
Token are
Feature activation-0.005
Top resid features:
very
Token very
Feature activation-0.000
Top resid features:
modest
Token modest
Feature activation+2.220
Top resid features:
impacts
Token impacts
Feature activation+0.085
Top resid features:
on
Token on
Feature activation+0.025
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
budget
Token budget
Feature activation+0.029
Top resid features:
,"
Token,"
Feature activation+0.002
Top resid features:
operation
Token operation
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
when
Token when
Feature activation+0.006
Top resid features:
concentrated
Token concentrated
Feature activation+0.076
Top resid features:
in
Token in
Feature activation+0.008
Top resid features:
smaller
Token smaller
Feature activation+2.094
Top resid features:
areas
Token areas
Feature activation+0.105
Top resid features:
(
Token (
Feature activation+0.060
Top resid features:
such
Tokensuch
Feature activation+0.015
Top resid features:
as
Token as
Feature activation+0.010
Top resid features:
Burke
Token Burke
Feature activation+0.000
Top resid features:
But
Token But
Feature activation-0.016
Top resid features:
companies
Token companies
Feature activation-0.024
Top resid features:
bid
Token bid
Feature activation-0.001
Top resid features:
on
Token on
Feature activation-0.002
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
tiny
Token tiny
Feature activation+1.078
Top resid features:
fraction
Token fraction
Feature activation+0.970
Top resid features:
of
Token of
Feature activation+0.187
Top resid features:
land
Token land
Feature activation+0.011
Top resid features:
available
Token available
Feature activation+0.042
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.121
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
The
TokenThe
Feature activation-0.003
Top resid features:
restaurant
Token restaurant
Feature activation-0.006
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
a
Token a
Feature activation+0.055
Top resid features:
tiny
Token tiny
Feature activation+2.008
Top resid features:
space
Token space
Feature activation+0.254
Top resid features:
with
Token with
Feature activation+0.006
Top resid features:
blue
Token blue
Feature activation+0.000
Top resid features:
marble
Token marble
Feature activation+0.000
Top resid features:
counters
Token counters
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.011
Top resid features:
Mexican
Token Mexican
Feature activation-0.001
Top resid features:
government
Token government
Feature activation-0.004
Top resid features:
would
Token would
Feature activation-0.004
Top resid features:
allow
Token allow
Feature activation-0.006
Top resid features:
small
Token small
Feature activation+2.041
Top resid features:
elite
Token elite
Feature activation+0.071
Top resid features:
units
Token units
Feature activation+0.233
Top resid features:
,
Token,
Feature activation+0.066
Top resid features:
like
Token like
Feature activation+0.014
Top resid features:
Green
Token Green
Feature activation+0.000
Top resid features:
stretched
Token stretched
Feature activation+0.060
Top resid features:
out
Token out
Feature activation+0.092
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
make
Token make
Feature activation+0.018
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
small
Token small
Feature activation+1.777
Top resid features:
enough
Token enough
Feature activation+0.181
Top resid features:
to
Token to
Feature activation+0.058
Top resid features:
form
Token form
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
basis
Token basis
Feature activation+0.000
Top resid features:
pizza
Token pizza
Feature activation-0.009
Top resid features:
dough
Token dough
Feature activation-0.002
Top resid features:
;
Token;
Feature activation-0.037
Top resid features:
others
Token others
Feature activation-0.003
Top resid features:
require
Token require
Feature activation-0.056
Top resid features:
minimal
Token minimal
Feature activation+2.303
Top resid features:
formation
Token formation
Feature activation+0.017
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
gluten
Token gluten
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
like
Token like
Feature activation+0.000
Top resid features:
about
Token about
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
team
Token team
Feature activation-0.004
Top resid features:
is
Token is
Feature activation-0.000
Top resid features:
how
Token how
Feature activation+0.010
Top resid features:
small
Token small
Feature activation+1.682
Top resid features:
it
Token it
Feature activation+0.146
Top resid features:
is
Token is
Feature activation+0.369
Top resid features:
.
Token.
Feature activation+0.027
Top resid features:
A
Token A
Feature activation+0.023
Top resid features:
mere
Token mere
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Instead
Token Instead
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
only
Token only
Feature activation+0.026
Top resid features:
a
Token a
Feature activation+0.027
Top resid features:
small
Token small
Feature activation+1.412
Top resid features:
portion
Token portion
Feature activation+0.491
Top resid features:
is
Token is
Feature activation+0.062
Top resid features:
sent
Token sent
Feature activation+0.026
Top resid features:
(
Token (
Feature activation+0.112
Top resid features:
a
Tokena
Feature activation+0.024
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
gas
Token gas
Feature activation+0.010
Top resid features:
flows
Token flows
Feature activation-0.005
Top resid features:
at
Token at
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
low
Token low
Feature activation+1.549
Top resid features:
Mach
Token Mach
Feature activation+0.121
Top resid features:
number
Token number
Feature activation+0.278
Top resid features:
(
Token (
Feature activation+0.224
Top resid features:
less
Tokenless
Feature activation+0.108
Top resid features:
than
Token than
Feature activation+0.014
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.06

Head 2: 0.02

Head 3: 0.08

Head 4: 0.03

Head 5: 0.49

Head 6: 0.04

Head 7: 0.03

Head 8: 0.12

Head 9: 0.06

Head 10: 0.02

Head 11: 0.02

Positive logits

minimal2.75

negligible2.74

nowhere2.56

smallest2.44

meager2.41

nominal2.38

(<2.33

modest2.32

spare2.30

bare2.28

fewer2.28

barely2.26

avoids2.20

insignificant2.19

anonymity2.18

curs2.13

devoid2.13

ocre2.11

sparse2.09

cob2.08

Negative logits

piracy-2.35

ierce-2.10

acca-2.01

assi-1.98

raged-1.96

asus-1.93

culminating-1.90

iseum-1.89

ogenesis-1.89

onslaught-1.88

reper-1.86

Steele-1.85

enraged-1.83

��-1.82

invading-1.81

Unleashed-1.81

Competition-1.75

ratulations-1.75

leased-1.74

Destruction-1.74

INTERVAL 2.930 - 3.255
CONTAINS 0.000%

number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
flights
Token flights
Feature activation+0.000
,
Token,
Feature activation+0.146
believed
Token believed
Feature activation+1.016
to
Token to
Feature activation+3.255
include
Token include
Feature activation+1.319
routes
Token routes
Feature activation+0.000
from
Token from
Feature activation+0.000
Heath
Token Heath
Feature activation+0.000
row
Tokenrow
Feature activation+0.000

INTERVAL 2.604 - 2.930
CONTAINS 0.000%

,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
went
Token went
Feature activation+0.000
as
Token as
Feature activation+0.000
low
Token low
Feature activation+0.000
as
Token as
Feature activation+2.882
11
Token 11
Feature activation+1.569
and
Token and
Feature activation+0.000
10
Token 10
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.467
of
Token of
Feature activation+0.000
land
Token land
Feature activation+0.000
available
Token available
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.287
only
Token only
Feature activation+1.901
seven
Token seven
Feature activation+2.613
of
Token of
Feature activation+0.180
the
Token the
Feature activation+0.000
900
Token 900
Feature activation+0.495
tracts
Token tracts
Feature activation+0.000
offered
Token offered
Feature activation+0.000

INTERVAL 2.279 - 2.604
CONTAINS 0.000%

they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
typically
Token typically
Feature activation+0.000
mild
Token mild
Feature activation+0.000
,
Token,
Feature activation+1.191
including
Token including
Feature activation+2.495
fever
Token fever
Feature activation+0.106
and
Token and
Feature activation+1.455
joint
Token joint
Feature activation+0.000
pain
Token pain
Feature activation+0.000
.
Token.
Feature activation+0.000
were
Token were
Feature activation+0.000
small
Token small
Feature activation+0.000
,
Token,
Feature activation+0.802
fewer
Token fewer
Feature activation+1.055
than
Token than
Feature activation+1.397
100
Token 100
Feature activation+2.384
people
Token people
Feature activation+0.958
,
Token,
Feature activation+0.604
recalls
Token recalls
Feature activation+0.000
Charlie
Token Charlie
Feature activation+0.000
Hughes
Token Hughes
Feature activation+0.000

INTERVAL 1.953 - 2.279
CONTAINS 0.001%

.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.255
You
TokenYou
Feature activation+0.794
're
Token're
Feature activation+0.673
talking
Token talking
Feature activation+1.462
about
Token about
Feature activation+2.001
a
Token a
Feature activation+1.291
combined
Token combined
Feature activation+0.545
total
Token total
Feature activation+0.630
of
Token of
Feature activation+1.098
about
Token about
Feature activation+0.886
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.696
A
Token A
Feature activation+1.333
mere
Token mere
Feature activation+1.789
fifteen
Token fifteen
Feature activation+2.043
players
Token players
Feature activation+0.725
make
Token make
Feature activation+0.471
up
Token up
Feature activation+0.352
a
Token a
Feature activation+0.151
very
Token very
Feature activation+0.254
a
Token a
Feature activation+0.000
relatively
Token relatively
Feature activation+0.000
small
Token small
Feature activation+0.067
distance
Token distance
Feature activation+0.000
of
Token of
Feature activation+0.815
260
Token 260
Feature activation+2.010
kilometres
Token kilometres
Feature activation+0.226
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
surface
Token surface
Feature activation+0.000
of
Token of
Feature activation+0.006
kid
Token kid
Feature activation+0.000
who
Token who
Feature activation+0.587
didn
Token didn
Feature activation+0.959
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+2.077
talk
Token talk
Feature activation+0.843
much
Token much
Feature activation+0.453
in
Token in
Feature activation+0.189
class
Token class
Feature activation+0.000
or
Token or
Feature activation+0.000
are
Token are
Feature activation+0.000
"
Token "
Feature activation+0.000
small
Tokensmall
Feature activation+0.000
"
Token"
Feature activation+0.000
(
Token (
Feature activation+0.367
having
Tokenhaving
Feature activation+2.089
shorter
Token shorter
Feature activation+0.952
wavelengths
Token wavelengths
Feature activation+0.302
),
Token),
Feature activation+0.000
compared
Token compared
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 1.628 - 1.953
CONTAINS 0.001%

in
Token in
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000
areas
Token areas
Feature activation+0.000
(
Token (
Feature activation+0.429
such
Tokensuch
Feature activation+1.092
as
Token as
Feature activation+1.908
Burke
Token Burke
Feature activation+0.000
Virginia
Token Virginia
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
),
Token),
Feature activation+0.009
small
Token small
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.696
A
Token A
Feature activation+1.333
mere
Token mere
Feature activation+1.789
fifteen
Token fifteen
Feature activation+2.043
players
Token players
Feature activation+0.725
make
Token make
Feature activation+0.471
up
Token up
Feature activation+0.352
a
Token a
Feature activation+0.151
city
Token city
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
with
Token with
Feature activation+1.644
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.102
stop
Tokenstop
Feature activation+0.371
service
Token service
Feature activation+0.320
to
Token to
Feature activation+0.000
restaurant
Token restaurant
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
tiny
Token tiny
Feature activation+0.000
space
Token space
Feature activation+0.445
with
Token with
Feature activation+1.879
blue
Token blue
Feature activation+0.029
marble
Token marble
Feature activation+0.000
counters
Token counters
Feature activation+0.166
where
Token where
Feature activation+0.188
customers
Token customers
Feature activation+0.024
fraction
Token fraction
Feature activation+0.000
of
Token of
Feature activation+0.000
land
Token land
Feature activation+0.000
available
Token available
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.287
only
Token only
Feature activation+1.901
seven
Token seven
Feature activation+2.613
of
Token of
Feature activation+0.180
the
Token the
Feature activation+0.000
900
Token 900
Feature activation+0.495
tracts
Token tracts
Feature activation+0.000

INTERVAL 1.302 - 1.628
CONTAINS 0.003%

moth
Token moth
Feature activation+0.000
is
Token is
Feature activation+0.000
much
Token much
Feature activation+0.000
smaller
Token smaller
Feature activation+0.000
.
Token.
Feature activation+0.517
It
Token It
Feature activation+1.360
is
Token is
Feature activation+0.958
also
Token also
Feature activation+0.000
more
Token more
Feature activation+0.206
yellow
Token yellow
Feature activation+0.000
in
Token in
Feature activation+0.000
traders
Token traders
Feature activation+0.000
with
Token with
Feature activation+1.018
turnover
Token turnover
Feature activation+0.000
below
Token below
Feature activation+0.410
Rs
Token Rs
Feature activation+0.324
20
Token 20
Feature activation+1.406
lakh
Token lakh
Feature activation+0.110
are
Token are
Feature activation+0.000
registered
Token registered
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
cheap
Token cheap
Feature activation+0.000
.
Token .
Feature activation+0.561
Literally
Token Literally
Feature activation+0.737
,
Token,
Feature activation+0.601
penn
Token penn
Feature activation+0.021
ies
Tokenies
Feature activation+1.362
per
Token per
Feature activation+1.171
batch
Token batch
Feature activation+0.487
.
Token.
Feature activation+0.459
There
Token There
Feature activation+0.463
are
Token are
Feature activation+1.331
typically
Token typically
Feature activation+0.000
mild
Token mild
Feature activation+0.000
,
Token,
Feature activation+1.191
including
Token including
Feature activation+2.495
fever
Token fever
Feature activation+0.106
and
Token and
Feature activation+1.455
joint
Token joint
Feature activation+0.000
pain
Token pain
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
t
Tokent
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.255
You
TokenYou
Feature activation+0.794
're
Token're
Feature activation+0.673
talking
Token talking
Feature activation+1.462
about
Token about
Feature activation+2.001
a
Token a
Feature activation+1.291
combined
Token combined
Feature activation+0.545
total
Token total
Feature activation+0.630
of
Token of
Feature activation+1.098

INTERVAL 0.977 - 1.302
CONTAINS 0.006%

million
Token million
Feature activation+0.000
,
Token,
Feature activation+0.327
a
Token a
Feature activation+0.000
tiny
Token tiny
Feature activation+0.000
fraction
Token fraction
Feature activation+0.016
of
Token of
Feature activation+1.056
the
Token the
Feature activation+0.322
UC
Token UC
Feature activation+0.000
system
Token system
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
simple
Token simple
Feature activation+0.000
tur
Token tur
Feature activation+0.000
ban
Tokenban
Feature activation+0.000
with
Token with
Feature activation+0.993
the
Token the
Feature activation+0.190
shape
Token shape
Feature activation+0.000
and
Token and
Feature activation+0.000
size
Token size
Feature activation+0.000
of
Token of
Feature activation+0.061
on
Token on
Feature activation+0.492
the
Token the
Feature activation+0.109
Amazon
Token Amazon
Feature activation+0.000
App
Token App
Feature activation+0.000
store
Tokenstore
Feature activation+0.000
and
Token and
Feature activation+1.066
on
Token on
Feature activation+0.264
Google
Token Google
Feature activation+0.000
Play
Token Play
Feature activation+0.000
.
Token.
Feature activation+0.854
However
Token However
Feature activation+0.000
fix
Token fix
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
on
Token on
Feature activation+0.000
small
Token small
Feature activation+0.000
details
Token details
Feature activation+0.000
such
Token such
Feature activation+1.237
as
Token as
Feature activation+1.037
shots
Token shots
Feature activation+0.915
of
Token of
Feature activation+0.821
uns
Token uns
Feature activation+0.193
ight
Tokenight
Feature activation+0.000
relatively
Token relatively
Feature activation+0.000
few
Token few
Feature activation+0.000
people
Token people
Feature activation+0.181
and
Token and
Feature activation+0.800
is
Token is
Feature activation+0.754
not
Token not
Feature activation+1.025
profitable
Token profitable
Feature activation+0.073
for
Token for
Feature activation+0.067
pharmaceutical
Token pharmaceutical
Feature activation+0.000
companies
Token companies
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.651 - 0.977
CONTAINS 0.018%

to
Token to
Feature activation+0.000
publish
Token publish
Feature activation+0.000
them
Token them
Feature activation+0.000
quietly
Token quietly
Feature activation+0.000
online
Token online
Feature activation+0.000
without
Token without
Feature activation+0.964
a
Token a
Feature activation+0.291
news
Token news
Feature activation+0.078
release
Token release
Feature activation+0.000
just
Token just
Feature activation+0.000
days
Token days
Feature activation+0.000
threat
Token threat
Feature activation+0.000
level
Token level
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
example
Token example
Feature activation+0.840
,
Token,
Feature activation+0.855
it
Token it
Feature activation+0.892
is
Token is
Feature activation+0.631
estimated
Token estimated
Feature activation+0.000
that
Token that
Feature activation+0.000
42
Token 42
Feature activation+0.000
down
Token down
Feature activation+0.000
the
Token the
Feature activation+0.000
socioeconomic
Token socioeconomic
Feature activation+0.000
scale
Token scale
Feature activation+0.000
,
Token,
Feature activation+0.192
among
Token among
Feature activation+0.689
the
Token the
Feature activation+0.261
least
Token least
Feature activation+0.083
privileged
Token privileged
Feature activation+0.020
,
Token,
Feature activation+0.307
men
Token men
Feature activation+0.356
to
Token to
Feature activation+0.000
stabilize
Token stabilize
Feature activation+0.000
prices
Token prices
Feature activation+0.000
.
Token.
Feature activation+0.272
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.899
January
TokenJanuary
Feature activation+0.000
West
Token West
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
Intermediate
Token Intermediate
Feature activation+0.000
crude
Token crude
Feature activation+0.000
problematic
Token problematic
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
small
Token small
Feature activation+0.000
farmers
Token farmers
Feature activation+0.341
in
Token in
Feature activation+0.668
the
Token the
Feature activation+0.116
developing
Token developing
Feature activation+0.000
world
Token world
Feature activation+0.000
prefer
Token prefer
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.326 - 0.651
CONTAINS 0.066%

protection
Token protection
Feature activation+0.000
now
Token now
Feature activation+0.000
possibly
Token possibly
Feature activation+0.000
limited
Token limited
Feature activation+0.000
to
Token to
Feature activation+0.000
only
Token only
Feature activation+0.500
the
Token the
Feature activation+0.000
(
Token (
Feature activation+0.000
shr
Tokenshr
Feature activation+0.000
inking
Tokeninking
Feature activation+0.000
)
Token)
Feature activation+0.000
idea
Token idea
Feature activation+0.000
.
Token.
Feature activation+0.086
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.097
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.483
I
TokenI
Feature activation+0.284
told
Token told
Feature activation+0.000
him
Token him
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
rawling
Tokenrawling
Feature activation+0.000
uses
Token uses
Feature activation+0.000
fewer
Token fewer
Feature activation+0.000
channels
Token channels
Feature activation+0.000
and
Token and
Feature activation+0.121
requires
Token requires
Feature activation+0.402
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.145
think
Token think
Feature activation+0.000
about
Token about
Feature activation+0.000
less
Token less
Feature activation+0.000
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
with
Token with
Feature activation+1.644
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.102
stop
Tokenstop
Feature activation+0.371
service
Token service
Feature activation+0.320
to
Token to
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.179
ness
Tokenness
Feature activation+0.000
;
Token;
Feature activation+0.000
normal
Token normal
Feature activation+0.079
doses
Token doses
Feature activation+0.122
(
Token (
Feature activation+0.546
200
Token200
Feature activation+0.490
mg
Token mg
Feature activation+0.358
or
Token or
Feature activation+0.618
more
Token more
Feature activation+0.252
)
Token)
Feature activation+0.164
of
Token of
Feature activation+0.060

INTERVAL 0.000 - 0.326
CONTAINS 99.904%

his
Token his
Feature activation+0.000
discourse
Token discourse
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
press
Token press
Feature activation+0.000
conference
Token conference
Feature activation+0.000
shows
Token shows
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.000
either
Token either
Feature activation+0.000
,
Token,
Feature activation+0.000
always
Token always
Feature activation+0.000
a
Token a
Feature activation+0.000
bigger
Token bigger
Feature activation+0.000
challenge
Token challenge
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Midwest
Token Midwest
Feature activation+0.000
than
Token than
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
an
Token an
Feature activation+0.000
anthropology
Token anthropology
Feature activation+0.000
student
Token student
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
traveled
Token traveled
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
South
Token South
Feature activation+0.000
Pacific
Token Pacific
Feature activation+0.000
island
Token island
Feature activation+0.000
terms
Token terms
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
evidence
Token evidence
Feature activation+0.000
against
Token against
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
designing
Token designing
Feature activation+0.000
the
Token the
Feature activation+0.000
characters
Token characters
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
series
Token series
Feature activation+0.000
will
Token will
Feature activation+0.000
premiere
Token premiere
Feature activation+0.000
on
Token on
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 H7.5: (feature 24343)

TOP ACTIVATIONS
MAX = 3.364

,
Token,
Feature activation+0.000
anytime
Token anytime
Feature activation+0.000
.
Token.
Feature activation+0.000
Using
Token Using
Feature activation+0.000
apps
Token apps
Feature activation+0.000
like
Token like
Feature activation+3.364
I
Token I
Feature activation+2.381
FT
TokenFT
Feature activation+0.117
TT
TokenTT
Feature activation+0.820
and
Token and
Feature activation+0.885
more
Token more
Feature activation+0.000
etc
Token etc
Feature activation+0.000
.).
Token.).
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
tools
Token tools
Feature activation+0.126
like
Token like
Feature activation+2.856
Sync
Token Sync
Feature activation+2.146
apse
Tokenapse
Feature activation+1.913
that
Token that
Feature activation+0.628
are
Token are
Feature activation+0.407
building
Token building
Feature activation+0.000
With
Token With
Feature activation+0.000
an
Token an
Feature activation+0.000
app
Token app
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+1.599
Pokémon
Token Pokémon
Feature activation+2.808
Go
Token Go
Feature activation+0.231
,
Token,
Feature activation+0.176
we
Token we
Feature activation+0.485
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
cleaning
Token cleaning
Feature activation+1.646
your
Token your
Feature activation+0.196
address
Token address
Feature activation+0.000
book
Token book
Feature activation+0.000
named
Token named
Feature activation+2.066
Touch
Token Touch
Feature activation+2.411
Up
TokenUp
Feature activation+1.422
)
Token)
Feature activation+0.065
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.134
developer
Token developer
Feature activation+0.000
anytime
Token anytime
Feature activation+0.000
.
Token.
Feature activation+0.000
Using
Token Using
Feature activation+0.000
apps
Token apps
Feature activation+0.000
like
Token like
Feature activation+3.364
I
Token I
Feature activation+2.381
FT
TokenFT
Feature activation+0.117
TT
TokenTT
Feature activation+0.820
and
Token and
Feature activation+0.885
more
Token more
Feature activation+0.000
,
Token,
Feature activation+0.011
!?
Token!?
Feature activation+0.554
Ċ
TokenĊ
Feature activation+0.181
Ċ
TokenĊ
Feature activation+0.123
Swe
TokenSwe
Feature activation+1.620
at
Tokenat
Feature activation+1.871
coin
Tokencoin
Feature activation+2.348
is
Token is
Feature activation+0.406
a
Token a
Feature activation+0.818
digital
Token digital
Feature activation+0.615
currency
Token currency
Feature activation+0.000
(
Token (
Feature activation+0.000
.).
Token.).
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
tools
Token tools
Feature activation+0.126
like
Token like
Feature activation+2.856
Sync
Token Sync
Feature activation+2.146
apse
Tokenapse
Feature activation+1.913
that
Token that
Feature activation+0.628
are
Token are
Feature activation+0.407
building
Token building
Feature activation+0.000
this
Token this
Feature activation+0.000
for
Token for
Feature activation+0.444
cleaning
Token cleaning
Feature activation+1.646
your
Token your
Feature activation+0.196
address
Token address
Feature activation+0.000
book
Token book
Feature activation+0.000
named
Token named
Feature activation+2.066
Touch
Token Touch
Feature activation+2.411
Up
TokenUp
Feature activation+1.422
)
Token)
Feature activation+0.065
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.134
Android
Token Android
Feature activation+0.000
app
Token app
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.539
users
Token users
Feature activation+1.095
can
Token can
Feature activation+2.019
hold
Token hold
Feature activation+0.835
a
Token a
Feature activation+0.468
balance
Token balance
Feature activation+0.159
of
Token of
Feature activation+0.000
Rs
Token Rs
Feature activation+0.000
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
true
Token true
Feature activation+0.000
.
Token.
Feature activation+0.000
Apps
Token Apps
Feature activation+0.000
like
Token like
Feature activation+1.948
Task
Token Task
Feature activation+0.872
er
Tokener
Feature activation+0.289
can
Token can
Feature activation+0.014
do
Token do
Feature activation+0.000
similar
Token similar
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
tools
Token tools
Feature activation+0.126
like
Token like
Feature activation+2.856
Sync
Token Sync
Feature activation+2.146
apse
Tokenapse
Feature activation+1.913
that
Token that
Feature activation+0.628
are
Token are
Feature activation+0.407
building
Token building
Feature activation+0.000
this
Token this
Feature activation+0.000
capability
Token capability
Feature activation+0.000
about
Token about
Feature activation+0.000
!?
Token!?
Feature activation+0.554
Ċ
TokenĊ
Feature activation+0.181
Ċ
TokenĊ
Feature activation+0.123
Swe
TokenSwe
Feature activation+1.620
at
Tokenat
Feature activation+1.871
coin
Tokencoin
Feature activation+2.348
is
Token is
Feature activation+0.406
a
Token a
Feature activation+0.818
digital
Token digital
Feature activation+0.615
currency
Token currency
Feature activation+0.000
,"
Token,"
Feature activation+0.000
or
Token or
Feature activation+0.000
traditional
Token traditional
Feature activation+0.000
Windows
Token Windows
Feature activation+0.000
programs
Token programs
Feature activation+0.000
like
Token like
Feature activation+1.847
Adobe
Token Adobe
Feature activation+0.485
Photoshop
Token Photoshop
Feature activation+0.020
and
Token and
Feature activation+0.459
Excel
Token Excel
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.054
4
Token4
Feature activation+0.074
.
Token.
Feature activation+0.134
Clement
Token Clement
Feature activation+0.443
ine
Tokenine
Feature activation+1.844
Ċ
TokenĊ
Feature activation+0.220
Ċ
TokenĊ
Feature activation+0.000
C
TokenC
Feature activation+0.191
lement
Tokenlement
Feature activation+0.710
ine
Tokenine
Feature activation+1.194
'
Token '
Feature activation+0.899
S
TokenS
Feature activation+1.055
ere
Tokenere
Feature activation+0.805
nd
Tokennd
Feature activation+0.000
ip
Tokenip
Feature activation+0.147
ity
Tokenity
Feature activation+1.771
Inf
Token Inf
Feature activation+1.158
ol
Tokenol
Feature activation+0.000
abs
Tokenabs
Feature activation+0.838
Pv
Token Pv
Feature activation+0.000
t
Tokent
Feature activation+0.000
huge
Token huge
Feature activation+0.000
app
Token app
Feature activation+0.000
that
Token that
Feature activation+0.000
allows
Token allows
Feature activation+1.604
users
Token users
Feature activation+0.789
to
Token to
Feature activation+1.671
check
Token check
Feature activation+0.855
on
Token on
Feature activation+0.310
the
Token the
Feature activation+0.112
results
Token results
Feature activation+0.000
of
Token of
Feature activation+0.000
growing
Token growing
Feature activation+0.000
success
Token success
Feature activation+0.000
of
Token of
Feature activation+0.000
services
Token services
Feature activation+0.000
such
Token such
Feature activation+0.084
as
Token as
Feature activation+1.654
Hulu
Token Hulu
Feature activation+1.322
demonstrates
Token demonstrates
Feature activation+0.000
that
Token that
Feature activation+0.000
people
Token people
Feature activation+0.000
will
Token will
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
stock
Token stock
Feature activation+0.000
trading
Token trading
Feature activation+0.000
game
Token game
Feature activation+0.011
platform
Token platform
Feature activation+0.137
Stock
Token Stock
Feature activation+1.653
f
Tokenf
Feature activation+0.457
use
Tokenuse
Feature activation+1.369
is
Token is
Feature activation+0.109
in
Token in
Feature activation+0.000
advanced
Token advanced
Feature activation+0.000
(
Token (
Feature activation+0.000
an
Tokenan
Feature activation+0.000
iOS
Token iOS
Feature activation+0.000
app
Token app
Feature activation+0.037
for
Token for
Feature activation+0.444
cleaning
Token cleaning
Feature activation+1.646
your
Token your
Feature activation+0.196
address
Token address
Feature activation+0.000
book
Token book
Feature activation+0.000
named
Token named
Feature activation+2.066
Touch
Token Touch
Feature activation+2.411
all
Token all
Feature activation+0.000
about
Token about
Feature activation+0.000
!?
Token!?
Feature activation+0.554
Ċ
TokenĊ
Feature activation+0.181
Ċ
TokenĊ
Feature activation+0.123
Swe
TokenSwe
Feature activation+1.620
at
Tokenat
Feature activation+1.871
coin
Tokencoin
Feature activation+2.348
is
Token is
Feature activation+0.406
a
Token a
Feature activation+0.818
digital
Token digital
Feature activation+0.615

Top DFA by src position
MAX = 3.907

anywhere
Token anywhere
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
anytime
Token anytime
Feature activation-0.001
Top resid features:
.
Token.
Feature activation-0.007
Top resid features:
Using
Token Using
Feature activation+0.014
Top resid features:
apps
Token apps
Feature activation+3.907
Top resid features:
like
Token like
Feature activation+0.049
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
FT
TokenFT
Feature activation+0.000
Top resid features:
TT
TokenTT
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
etc
Token etc
Feature activation-0.004
Top resid features:
.).
Token.).
Feature activation+0.014
Top resid features:
There
Token There
Feature activation+0.003
Top resid features:
are
Token are
Feature activation+0.005
Top resid features:
tools
Token tools
Feature activation+3.416
Top resid features:
like
Token like
Feature activation+0.009
Top resid features:
Sync
Token Sync
Feature activation+0.000
Top resid features:
apse
Tokenapse
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:
me
Token me
Feature activation+0.002
Top resid features:
pause
Token pause
Feature activation-0.002
Top resid features:
:
Token:
Feature activation+0.002
Top resid features:
With
Token With
Feature activation+0.022
Top resid features:
an
Token an
Feature activation+0.010
Top resid features:
app
Token app
Feature activation+2.905
Top resid features:
such
Token such
Feature activation+0.057
Top resid features:
as
Token as
Feature activation+0.243
Top resid features:
Pokémon
Token Pokémon
Feature activation+0.011
Top resid features:
Go
Token Go
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.467
Top resid features:
(
Token (
Feature activation-0.004
Top resid features:
an
Tokenan
Feature activation+0.006
Top resid features:
iOS
Token iOS
Feature activation+0.043
Top resid features:
app
Token app
Feature activation+2.467
Top resid features:
for
Token for
Feature activation+0.149
Top resid features:
cleaning
Token cleaning
Feature activation+0.014
Top resid features:
your
Token your
Feature activation+0.005
Top resid features:
address
Token address
Feature activation+0.002
Top resid features:
book
Token book
Feature activation+0.035
Top resid features:
anywhere
Token anywhere
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
anytime
Token anytime
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Using
Token Using
Feature activation+0.012
Top resid features:
apps
Token apps
Feature activation+2.603
Top resid features:
like
Token like
Feature activation+0.161
Top resid features:
I
Token I
Feature activation+0.003
Top resid features:
FT
TokenFT
Feature activation+0.000
Top resid features:
TT
TokenTT
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
What
Token What
Feature activation-0.002
Top resid features:
âĢ
TokenâĢ
Feature activation-0.002
Top resid features:
Ļ
TokenĻ
Feature activation-0.000
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
app
Token app
Feature activation+2.698
Top resid features:
all
Token all
Feature activation-0.006
Top resid features:
about
Token about
Feature activation+0.010
Top resid features:
!?
Token!?
Feature activation+0.037
Top resid features:
Ċ
TokenĊ
Feature activation+0.061
Top resid features:
Ċ
TokenĊ
Feature activation+0.058
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
etc
Token etc
Feature activation-0.004
Top resid features:
.).
Token.).
Feature activation+0.006
Top resid features:
There
Token There
Feature activation+0.005
Top resid features:
are
Token are
Feature activation+0.013
Top resid features:
tools
Token tools
Feature activation+2.407
Top resid features:
like
Token like
Feature activation+0.297
Top resid features:
Sync
Token Sync
Feature activation-0.015
Top resid features:
apse
Tokenapse
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:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.378
Top resid features:
(
Token (
Feature activation-0.011
Top resid features:
an
Tokenan
Feature activation+0.000
Top resid features:
iOS
Token iOS
Feature activation+0.070
Top resid features:
app
Token app
Feature activation+2.382
Top resid features:
for
Token for
Feature activation+0.098
Top resid features:
cleaning
Token cleaning
Feature activation-0.005
Top resid features:
your
Token your
Feature activation+0.002
Top resid features:
address
Token address
Feature activation-0.014
Top resid features:
book
Token book
Feature activation+0.012
Top resid features:
company
Token company
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.006
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation-0.000
Top resid features:
Android
Token Android
Feature activation+0.097
Top resid features:
app
Token app
Feature activation+2.334
Top resid features:
,
Token,
Feature activation+0.153
Top resid features:
where
Token where
Feature activation+0.124
Top resid features:
users
Token users
Feature activation-0.156
Top resid features:
can
Token can
Feature activation-0.085
Top resid features:
hold
Token hold
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.002
Top resid features:
that
Token that
Feature activation+0.008
Top resid features:
's
Token's
Feature activation-0.003
Top resid features:
true
Token true
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.024
Top resid features:
Apps
Token Apps
Feature activation+2.294
Top resid features:
like
Token like
Feature activation+0.023
Top resid features:
Task
Token Task
Feature activation+0.000
Top resid features:
er
Tokener
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
etc
Token etc
Feature activation-0.010
Top resid features:
.).
Token.).
Feature activation+0.010
Top resid features:
There
Token There
Feature activation+0.008
Top resid features:
are
Token are
Feature activation+0.029
Top resid features:
tools
Token tools
Feature activation+2.135
Top resid features:
like
Token like
Feature activation+0.385
Top resid features:
Sync
Token Sync
Feature activation-0.011
Top resid features:
apse
Tokenapse
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:
What
Token What
Feature activation-0.004
Top resid features:
âĢ
TokenâĢ
Feature activation-0.006
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
s
Tokens
Feature activation+0.004
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
app
Token app
Feature activation+2.254
Top resid features:
all
Token all
Feature activation-0.010
Top resid features:
about
Token about
Feature activation+0.027
Top resid features:
!?
Token!?
Feature activation+0.040
Top resid features:
Ċ
TokenĊ
Feature activation+0.069
Top resid features:
Ċ
TokenĊ
Feature activation+0.104
Top resid features:
acy
Tokenacy
Feature activation-0.007
Top resid features:
,"
Token,"
Feature activation-0.004
Top resid features:
or
Token or
Feature activation-0.010
Top resid features:
traditional
Token traditional
Feature activation+0.011
Top resid features:
Windows
Token Windows
Feature activation+0.002
Top resid features:
programs
Token programs
Feature activation+2.285
Top resid features:
like
Token like
Feature activation+0.013
Top resid features:
Adobe
Token Adobe
Feature activation+0.000
Top resid features:
Photoshop
Token Photoshop
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Excel
Token Excel
Feature activation+0.000
Top resid features:
handles
Token handles
Feature activation-0.001
Top resid features:
system
Token system
Feature activation+0.005
Top resid features:
resources
Token resources
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
This
Token This
Feature activation+0.001
Top resid features:
app
Token app
Feature activation+2.005
Top resid features:
is
Token is
Feature activation+0.012
Top resid features:
extremely
Token extremely
Feature activation-0.000
Top resid features:
system
Token system
Feature activation+0.003
Top resid features:
friendly
Token friendly
Feature activation-0.001
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
another
Token another
Feature activation+0.002
Top resid features:
app
Token app
Feature activation+0.055
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
based
Tokenbased
Feature activation+0.031
Top resid features:
cab
Token cab
Feature activation+0.050
Top resid features:
service
Token service
Feature activation+1.182
Top resid features:
provider
Token provider
Feature activation+1.120
Top resid features:
'
Token '
Feature activation+0.044
Top resid features:
S
TokenS
Feature activation-0.015
Top resid features:
ere
Tokenere
Feature activation+0.038
Top resid features:
nd
Tokennd
Feature activation-0.021
Top resid features:
Google
Token Google
Feature activation+0.005
Top resid features:
blocked
Token blocked
Feature activation-0.045
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
huge
Token huge
Feature activation-0.009
Top resid features:
app
Token app
Feature activation+0.876
Top resid features:
that
Token that
Feature activation+1.330
Top resid features:
allows
Token allows
Feature activation+0.281
Top resid features:
users
Token users
Feature activation-0.069
Top resid features:
to
Token to
Feature activation-0.037
Top resid features:
check
Token check
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
growing
Token growing
Feature activation+0.023
Top resid features:
success
Token success
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.070
Top resid features:
services
Token services
Feature activation+1.988
Top resid features:
such
Token such
Feature activation+0.079
Top resid features:
as
Token as
Feature activation+0.044
Top resid features:
Hulu
Token Hulu
Feature activation+0.000
Top resid features:
demonstrates
Token demonstrates
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.445
Top resid features:
stock
Token stock
Feature activation-0.001
Top resid features:
trading
Token trading
Feature activation-0.039
Top resid features:
game
Token game
Feature activation+0.567
Top resid features:
platform
Token platform
Feature activation+1.667
Top resid features:
Stock
Token Stock
Feature activation+0.005
Top resid features:
f
Tokenf
Feature activation+0.000
Top resid features:
use
Tokenuse
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.462
Top resid features:
(
Token (
Feature activation-0.010
Top resid features:
an
Tokenan
Feature activation+0.020
Top resid features:
iOS
Token iOS
Feature activation+0.053
Top resid features:
app
Token app
Feature activation+1.155
Top resid features:
for
Token for
Feature activation+0.932
Top resid features:
cleaning
Token cleaning
Feature activation+0.025
Top resid features:
your
Token your
Feature activation+0.000
Top resid features:
address
Token address
Feature activation+0.000
Top resid features:
book
Token book
Feature activation+0.000
Top resid features:
What
Token What
Feature activation-0.002
Top resid features:
âĢ
TokenâĢ
Feature activation-0.004
Top resid features:
Ļ
TokenĻ
Feature activation-0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
this
Token this
Feature activation+0.001
Top resid features:
app
Token app
Feature activation+1.908
Top resid features:
all
Token all
Feature activation-0.003
Top resid features:
about
Token about
Feature activation+0.010
Top resid features:
!?
Token!?
Feature activation+0.047
Top resid features:
Ċ
TokenĊ
Feature activation+0.069
Top resid features:
Ċ
TokenĊ
Feature activation+0.090
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.08

Head 2: 0.02

Head 3: 0.05

Head 4: 0.04

Head 5: 0.49

Head 6: 0.08

Head 7: 0.03

Head 8: 0.06

Head 9: 0.04

Head 10: 0.02

Head 11: 0.02

Positive logits

Chat3.22

apps2.67

Apps2.66

Tracker2.63

Sync2.54

Explorer2.47

Tracker2.47

plugin2.47

Reader2.45

websites2.43

Plugin2.43

Clicker2.39

Compass2.39

online2.35

widgets2.34

widget2.33

Online2.32

Sync2.27

Voice2.27

Online2.27

Negative logits

ittal-2.23

Marketable-2.20

nants-2.18

recess-2.07

surviving-2.05

unanimous-2.04

-2.02

*/(-1.96

retiring-1.94

"]=>-1.93

injuring-1.90

defeating-1.90

victorious-1.89

residues-1.89

exhausted-1.88

rupt-1.87

fortunate-1.86

Ital-1.86

vacated-1.86

advancing-1.86

INTERVAL 3.028 - 3.364
CONTAINS 0.000%

,
Token,
Feature activation+0.000
anytime
Token anytime
Feature activation+0.000
.
Token.
Feature activation+0.000
Using
Token Using
Feature activation+0.000
apps
Token apps
Feature activation+0.000
like
Token like
Feature activation+3.364
I
Token I
Feature activation+2.381
FT
TokenFT
Feature activation+0.117
TT
TokenTT
Feature activation+0.820
and
Token and
Feature activation+0.885
more
Token more
Feature activation+0.000

INTERVAL 2.691 - 3.028
CONTAINS 0.000%

etc
Token etc
Feature activation+0.000
.).
Token.).
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
tools
Token tools
Feature activation+0.126
like
Token like
Feature activation+2.856
Sync
Token Sync
Feature activation+2.146
apse
Tokenapse
Feature activation+1.913
that
Token that
Feature activation+0.628
are
Token are
Feature activation+0.407
building
Token building
Feature activation+0.000
With
Token With
Feature activation+0.000
an
Token an
Feature activation+0.000
app
Token app
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+1.599
Pokémon
Token Pokémon
Feature activation+2.808
Go
Token Go
Feature activation+0.231
,
Token,
Feature activation+0.176
we
Token we
Feature activation+0.485
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 2.355 - 2.691
CONTAINS 0.000%

anytime
Token anytime
Feature activation+0.000
.
Token.
Feature activation+0.000
Using
Token Using
Feature activation+0.000
apps
Token apps
Feature activation+0.000
like
Token like
Feature activation+3.364
I
Token I
Feature activation+2.381
FT
TokenFT
Feature activation+0.117
TT
TokenTT
Feature activation+0.820
and
Token and
Feature activation+0.885
more
Token more
Feature activation+0.000
,
Token,
Feature activation+0.011
cleaning
Token cleaning
Feature activation+1.646
your
Token your
Feature activation+0.196
address
Token address
Feature activation+0.000
book
Token book
Feature activation+0.000
named
Token named
Feature activation+2.066
Touch
Token Touch
Feature activation+2.411
Up
TokenUp
Feature activation+1.422
)
Token)
Feature activation+0.065
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.134
developer
Token developer
Feature activation+0.000

INTERVAL 2.018 - 2.355
CONTAINS 0.001%

Android
Token Android
Feature activation+0.000
app
Token app
Feature activation+0.000
,
Token,
Feature activation+0.000
where
Token where
Feature activation+0.539
users
Token users
Feature activation+1.095
can
Token can
Feature activation+2.019
hold
Token hold
Feature activation+0.835
a
Token a
Feature activation+0.468
balance
Token balance
Feature activation+0.159
of
Token of
Feature activation+0.000
Rs
Token Rs
Feature activation+0.000
for
Token for
Feature activation+0.444
cleaning
Token cleaning
Feature activation+1.646
your
Token your
Feature activation+0.196
address
Token address
Feature activation+0.000
book
Token book
Feature activation+0.000
named
Token named
Feature activation+2.066
Touch
Token Touch
Feature activation+2.411
Up
TokenUp
Feature activation+1.422
)
Token)
Feature activation+0.065
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.134
.).
Token.).
Feature activation+0.000
There
Token There
Feature activation+0.000
are
Token are
Feature activation+0.000
tools
Token tools
Feature activation+0.126
like
Token like
Feature activation+2.856
Sync
Token Sync
Feature activation+2.146
apse
Tokenapse
Feature activation+1.913
that
Token that
Feature activation+0.628
are
Token are
Feature activation+0.407
building
Token building
Feature activation+0.000
this
Token this
Feature activation+0.000
!?
Token!?
Feature activation+0.554
Ċ
TokenĊ
Feature activation+0.181
Ċ
TokenĊ
Feature activation+0.123
Swe
TokenSwe
Feature activation+1.620
at
Tokenat
Feature activation+1.871
coin
Tokencoin
Feature activation+2.348
is
Token is
Feature activation+0.406
a
Token a
Feature activation+0.818
digital
Token digital
Feature activation+0.615
currency
Token currency
Feature activation+0.000
(
Token (
Feature activation+0.000

INTERVAL 1.682 - 2.018
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.054
4
Token4
Feature activation+0.074
.
Token.
Feature activation+0.134
Clement
Token Clement
Feature activation+0.443
ine
Tokenine
Feature activation+1.844
Ċ
TokenĊ
Feature activation+0.220
Ċ
TokenĊ
Feature activation+0.000
C
TokenC
Feature activation+0.191
lement
Tokenlement
Feature activation+0.710
ine
Tokenine
Feature activation+1.194
'
Token '
Feature activation+0.899
S
TokenS
Feature activation+1.055
ere
Tokenere
Feature activation+0.805
nd
Tokennd
Feature activation+0.000
ip
Tokenip
Feature activation+0.147
ity
Tokenity
Feature activation+1.771
Inf
Token Inf
Feature activation+1.158
ol
Tokenol
Feature activation+0.000
abs
Tokenabs
Feature activation+0.838
Pv
Token Pv
Feature activation+0.000
t
Tokent
Feature activation+0.000
that
Token that
Feature activation+0.000
's
Token's
Feature activation+0.000
true
Token true
Feature activation+0.000
.
Token.
Feature activation+0.000
Apps
Token Apps
Feature activation+0.000
like
Token like
Feature activation+1.948
Task
Token Task
Feature activation+0.872
er
Tokener
Feature activation+0.289
can
Token can
Feature activation+0.014
do
Token do
Feature activation+0.000
similar
Token similar
Feature activation+0.000
about
Token about
Feature activation+0.000
!?
Token!?
Feature activation+0.554
Ċ
TokenĊ
Feature activation+0.181
Ċ
TokenĊ
Feature activation+0.123
Swe
TokenSwe
Feature activation+1.620
at
Tokenat
Feature activation+1.871
coin
Tokencoin
Feature activation+2.348
is
Token is
Feature activation+0.406
a
Token a
Feature activation+0.818
digital
Token digital
Feature activation+0.615
currency
Token currency
Feature activation+0.000
,"
Token,"
Feature activation+0.000
or
Token or
Feature activation+0.000
traditional
Token traditional
Feature activation+0.000
Windows
Token Windows
Feature activation+0.000
programs
Token programs
Feature activation+0.000
like
Token like
Feature activation+1.847
Adobe
Token Adobe
Feature activation+0.485
Photoshop
Token Photoshop
Feature activation+0.020
and
Token and
Feature activation+0.459
Excel
Token Excel
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.346 - 1.682
CONTAINS 0.003%

affiliated
Tokenaffiliated
Feature activation+0.000
hacking
Token hacking
Feature activation+0.000
tool
Token tool
Feature activation+0.000
kit
Tokenkit
Feature activation+0.000
known
Token known
Feature activation+0.000
as
Token as
Feature activation+1.350
the
Token the
Feature activation+0.935
Equ
Token Equ
Feature activation+0.136
ation
Tokenation
Feature activation+0.040
Group
Token Group
Feature activation+0.333
,
Token,
Feature activation+0.000
privacy
Token privacy
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.089
aut
Tokenaut
Feature activation+0.673
of
Tokenof
Feature activation+0.066
ill
Tokenill
Feature activation+1.140
,
Token,
Feature activation+1.567
address
Token address
Feature activation+0.220
saving
Token saving
Feature activation+0.434
,
Token,
Feature activation+1.136
password
Token password
Feature activation+0.152
saving
Token saving
Feature activation+0.000
them
Token them
Feature activation+0.000
!
Token!
Feature activation+0.206
Ċ
TokenĊ
Feature activation+0.473
Ċ
TokenĊ
Feature activation+0.685
GN
TokenGN
Feature activation+1.452
OME
TokenOME
Feature activation+1.513
Software
Token Software
Feature activation+0.837
will
Token will
Feature activation+0.139
be
Token be
Feature activation+0.000
available
Token available
Feature activation+0.000
on
Token on
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
stock
Token stock
Feature activation+0.000
trading
Token trading
Feature activation+0.000
game
Token game
Feature activation+0.011
platform
Token platform
Feature activation+0.137
Stock
Token Stock
Feature activation+1.653
f
Tokenf
Feature activation+0.457
use
Tokenuse
Feature activation+1.369
is
Token is
Feature activation+0.109
in
Token in
Feature activation+0.000
advanced
Token advanced
Feature activation+0.000
and
Token and
Feature activation+0.000
CSS
Token CSS
Feature activation+0.000
)
Token)
Feature activation+0.000
writing
Token writing
Feature activation+0.000
platform
Token platform
Feature activation+0.553
Book
Token Book
Feature activation+1.381
type
Tokentype
Feature activation+1.058
was
Token was
Feature activation+0.000
chosen
Token chosen
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.009 - 1.346
CONTAINS 0.005%

Internet
Token Internet
Feature activation+0.000
browser
Token browser
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.068
World
TokenWorld
Feature activation+1.134
Wide
TokenWide
Feature activation+0.861
Web
TokenWeb
Feature activation+0.755
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
problem
Token problem
Feature activation+0.000
.
Token.
Feature activation+0.000
With
Token With
Feature activation+0.000
an
Token an
Feature activation+0.000
application
Token application
Feature activation+0.000
called
Token called
Feature activation+1.022
Work
Token Work
Feature activation+1.268
day
Tokenday
Feature activation+1.341
Talent
Token Talent
Feature activation+0.815
Ins
Token Ins
Feature activation+0.218
ights
Tokenights
Feature activation+0.427
be
Token be
Feature activation+0.000
building
Token building
Feature activation+0.000
a
Token a
Feature activation+0.000
demo
Token demo
Feature activation+0.000
app
Token app
Feature activation+0.017
called
Token called
Feature activation+1.140
Attend
Token Attend
Feature activation+1.050
ance
Tokenance
Feature activation+1.052
App
Token App
Feature activation+0.358
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Zealand
Token Zealand
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.000
website
Token website
Feature activation+0.000
,
Token,
Feature activation+0.042
called
Token called
Feature activation+1.095
We
Token We
Feature activation+0.677
G
TokenG
Feature activation+0.312
row
Tokenrow
Feature activation+0.206
Bit
TokenBit
Feature activation+0.387
coins
Tokencoins
Feature activation+0.801
of
Tokenof
Feature activation+0.066
ill
Tokenill
Feature activation+1.140
,
Token,
Feature activation+1.567
address
Token address
Feature activation+0.220
saving
Token saving
Feature activation+0.434
,
Token,
Feature activation+1.136
password
Token password
Feature activation+0.152
saving
Token saving
Feature activation+0.000
,
Token,
Feature activation+0.773
history
Token history
Feature activation+0.000
,
Token,
Feature activation+0.256

INTERVAL 0.673 - 1.009
CONTAINS 0.014%

product
Token product
Feature activation+0.000
roadmap
Token roadmap
Feature activation+0.000
.
Token.
Feature activation+0.071
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.103
Z
TokenZ
Feature activation+0.898
uber
Tokenuber
Feature activation+0.362
ance
Tokenance
Feature activation+1.602
is
Token is
Feature activation+0.220
a
Token a
Feature activation+0.388
great
Token great
Feature activation+0.032
rd
Tokenrd
Feature activation+0.000
party
Token party
Feature activation+0.000
apps
Token apps
Feature activation+0.000
,
Token,
Feature activation+0.000
especially
Token especially
Feature activation+0.477
consumer
Token consumer
Feature activation+0.776
apps
Token apps
Feature activation+0.297
,
Token,
Feature activation+0.000
do
Token do
Feature activation+0.000
not
Token not
Feature activation+0.000
matter
Token matter
Feature activation+0.000
creating
Token creating
Feature activation+0.000
a
Token a
Feature activation+0.000
web
Token web
Feature activation+0.000
application
Token application
Feature activation+0.000
that
Token that
Feature activation+0.000
displays
Token displays
Feature activation+0.872
a
Token a
Feature activation+0.196
bar
Token bar
Feature activation+0.204
chart
Token chart
Feature activation+0.093
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
Google
Token Google
Feature activation+0.508
Chrome
Token Chrome
Feature activation+0.000
,
Token,
Feature activation+0.790
Libre
Token Libre
Feature activation+0.640
Office
TokenOffice
Feature activation+0.089
,
Token,
Feature activation+0.840
P
Token P
Feature activation+0.497
id
Tokenid
Feature activation+0.383
gin
Tokengin
Feature activation+0.226
Instant
Token Instant
Feature activation+0.511
Messenger
Token Messenger
Feature activation+0.257
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
Chat
TokenChat
Feature activation+0.696
-
Token-
Feature activation+0.311
Template
TokenTemplate
Feature activation+0.000
in
Token in
Feature activation+0.000
action
Token action
Feature activation+0.000
on
Token on
Feature activation+0.000

INTERVAL 0.336 - 0.673
CONTAINS 0.041%

to
Token to
Feature activation+0.000
watch
Token watch
Feature activation+0.000
ABC
Token ABC
Feature activation+0.454
programs
Token programs
Feature activation+0.014
like
Token like
Feature activation+0.563
"
Token "
Feature activation+0.414
Jimmy
TokenJimmy
Feature activation+0.034
Kimmel
Token Kimmel
Feature activation+0.094
Live
Token Live
Feature activation+0.014
"
Token"
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.529
some
Token some
Feature activation+0.039
instructions
Token instructions
Feature activation+0.000
,
Token,
Feature activation+0.412
and
Token and
Feature activation+0.489
then
Token then
Feature activation+0.613
you
Token you
Feature activation+0.058
go
Token go
Feature activation+0.000
nuts
Token nuts
Feature activation+0.000
from
Token from
Feature activation+0.000
there
Token there
Feature activation+0.000
portfolio
Token portfolio
Feature activation+0.000
such
Token such
Feature activation+0.000
as
Token as
Feature activation+1.023
content
Token content
Feature activation+0.497
recommendation
Token recommendation
Feature activation+0.467
engine
Token engine
Feature activation+0.461
Tab
Token Tab
Feature activation+1.175
oola
Tokenoola
Feature activation+0.640
,
Token,
Feature activation+0.053
which
Token which
Feature activation+0.083
they
Token they
Feature activation+0.000
service
Token service
Feature activation+0.000
for
Token for
Feature activation+0.321
everyone
Token everyone
Feature activation+0.043
who
Token who
Feature activation+0.000
want
Token want
Feature activation+0.661
to
Token to
Feature activation+0.455
rent
Token rent
Feature activation+0.014
a
Token a
Feature activation+0.000
holiday
Token holiday
Feature activation+0.000
accommodation
Token accommodation
Feature activation+0.000
.
Token.
Feature activation+0.000
let
Tokenlet
Feature activation+0.179
called
Token called
Feature activation+0.819
j
Token j
Feature activation+0.171
n
Tokenn
Feature activation+0.099
ana
Tokenana
Feature activation+0.593
.
Token.
Feature activation+0.576
ts
Tokents
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+0.000

INTERVAL 0.000 - 0.336
CONTAINS 99.936%

they
Token they
Feature activation+0.000
would
Token would
Feature activation+0.000
deny
Token deny
Feature activation+0.000
us
Token us
Feature activation+0.000
the
Token the
Feature activation+0.000
basic
Token basic
Feature activation+0.000
human
Token human
Feature activation+0.000
right
Token right
Feature activation+0.000
to
Token to
Feature activation+0.000
self
Token self
Feature activation+0.000
defense
Token defense
Feature activation+0.000
?
Token?
Feature activation+0.000
Or
Token Or
Feature activation+0.000
was
Token was
Feature activation+0.000
it
Token it
Feature activation+0.000
the
Token the
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
abuse
Token abuse
Feature activation+0.000
I
Token I
Feature activation+0.000
suffered
Token suffered
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
phone
Token phone
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
buy
Token buy
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
phone
Token phone
Feature activation+0.000
and
Token and
Feature activation+0.000
pay
Token pay
Feature activation+0.000
for
Token for
Feature activation+0.000
it
Token it
Feature activation+0.000
we
Token we
Feature activation+0.000
sound
Token sound
Feature activation+0.000
like
Token like
Feature activation+0.000
we
Token we
Feature activation+0.000
do
Token do
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
outs
Tokenouts
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
somehow
Token somehow
Feature activation+0.000
familiar
Token familiar
Feature activation+0.000
âĢ¦
TokenâĢ¦
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Of
TokenOf
Feature activation+0.000
course
Token course
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 H7.5: (feature 43469)

TOP ACTIVATIONS
MAX = 2.519

man
Token man
Feature activation+0.000
identified
Token identified
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
document
Token document
Feature activation+0.000
as
Token as
Feature activation+2.519
Mark
Token Mark
Feature activation+1.640
O
Token O
Feature activation+0.000
th
Tokenth
Feature activation+0.000
on
Tokenon
Feature activation+0.150
came
Token came
Feature activation+0.000
project
Token project
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
single
Token single
Feature activation+0.000
man
Token man
Feature activation+0.000
:
Token:
Feature activation+1.923
President
Token President
Feature activation+0.000
Recep
Token Recep
Feature activation+0.000
Tayyip
Token Tayyip
Feature activation+0.000
Erdogan
Token Erdogan
Feature activation+0.000
,
Token,
Feature activation+0.000
identified
Token identified
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
document
Token document
Feature activation+0.000
as
Token as
Feature activation+2.519
Mark
Token Mark
Feature activation+1.640
O
Token O
Feature activation+0.000
th
Tokenth
Feature activation+0.000
on
Tokenon
Feature activation+0.150
came
Token came
Feature activation+0.000
forward
Token forward
Feature activation+0.000
sent
Token sent
Feature activation+0.000
to
Token to
Feature activation+0.000
meet
Token meet
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
named
Token named
Feature activation+1.599
Robert
Token Robert
Feature activation+0.575
Warren
Token Warren
Feature activation+0.193
to
Token to
Feature activation+0.000
evaluate
Token evaluate
Feature activation+0.000
his
Token his
Feature activation+0.000
location
Token location
Feature activation+0.000
of
Token of
Feature activation+0.000
Hitler
Token Hitler
Feature activation+0.000
's
Token's
Feature activation+0.000
remains
Token remains
Feature activation+0.000
,
Token,
Feature activation+1.500
and
Token and
Feature activation+0.368
he
Token he
Feature activation+0.160
vowed
Token vowed
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
polymer
Token polymer
Feature activation+0.000
guns
Token guns
Feature activation+0.000
,
Token,
Feature activation+1.275
I
Token I
Feature activation+0.000
honestly
Token honestly
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
Police
Token Police
Feature activation+0.000
identified
Token identified
Feature activation+0.000
the
Token the
Feature activation+0.000
man
Token man
Feature activation+0.000
as
Token as
Feature activation+1.274
42
Token 42
Feature activation+0.758
-
Token-
Feature activation+0.377
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+1.560
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
catastrophe
Token catastrophe
Feature activation+0.000
.
Token.
Feature activation+0.648
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.234
Republican
TokenRepublican
Feature activation+0.674
pund
Token pund
Feature activation+0.000
it
Tokenit
Feature activation+0.575
,
Token,
Feature activation+0.202
former
Token former
Feature activation+0.000
sent
Token sent
Feature activation+0.000
to
Token to
Feature activation+0.000
meet
Token meet
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
named
Token named
Feature activation+1.226
Robert
Token Robert
Feature activation+0.564
Warren
Token Warren
Feature activation+0.090
to
Token to
Feature activation+0.000
evaluate
Token evaluate
Feature activation+0.000
his
Token his
Feature activation+0.000
and
Token and
Feature activation+0.000
being
Token being
Feature activation+0.000
a
Token a
Feature activation+0.000
fun
Token fun
Feature activation+0.000
guy
Token guy
Feature activation+0.000
,
Token,
Feature activation+0.962
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
sit
Token sit
Feature activation+0.000
described
Token described
Feature activation+0.000
the
Token the
Feature activation+0.000
British
Token British
Feature activation+0.000
man
Token man
Feature activation+0.000
known
Token known
Feature activation+0.000
as
Token as
Feature activation+0.954
J
Token J
Feature activation+0.536
ihadi
Tokenihadi
Feature activation+0.000
John
Token John
Feature activation+0.000
as
Token as
Feature activation+0.000
his
Token his
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.701
Le
TokenLe
Feature activation+0.057
o
Tokeno
Feature activation+0.940
Hunter
Token Hunter
Feature activation+0.000
was
Token was
Feature activation+0.000
awarded
Token awarded
Feature activation+0.000
a
Token a
Feature activation+0.000
23
Token 23
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
talks
Token talks
Feature activation+0.000
about
Token about
Feature activation+0.000
that
Token that
Feature activation+0.000
guy
Token guy
Feature activation+0.000
,
Token,
Feature activation+0.918
who
Token who
Feature activation+0.402
always
Token always
Feature activation+0.000
seems
Token seems
Feature activation+0.000
to
Token to
Feature activation+0.000
notice
Token notice
Feature activation+0.000
o
Tokeno
Feature activation+0.000
Rio
Token Rio
Feature activation+0.000
two
Token two
Feature activation+0.000
men
Token men
Feature activation+0.000
,
Token,
Feature activation+0.824
Travis
Token Travis
Feature activation+0.885
and
Token and
Feature activation+0.134
Ch
Token Ch
Feature activation+0.000
ato
Tokenato
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
he
Token he
Feature activation+0.000
believed
Token believed
Feature activation+0.000
to
Token to
Feature activation+0.468
be
Token be
Feature activation+0.856
a
Token a
Feature activation+0.258
crime
Token crime
Feature activation+0.000
boss
Token boss
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
Sant
Token Sant
Feature activation+0.000
o
Tokeno
Feature activation+0.000
Rio
Token Rio
Feature activation+0.000
two
Token two
Feature activation+0.000
men
Token men
Feature activation+0.000
,
Token,
Feature activation+0.824
Travis
Token Travis
Feature activation+0.885
and
Token and
Feature activation+0.134
Ch
Token Ch
Feature activation+0.000
ato
Tokenato
Feature activation+0.000
,
Token,
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
man
Token man
Feature activation+0.000
from
Token from
Feature activation+0.821
Glou
Token Glou
Feature activation+0.000
cester
Tokencester
Feature activation+0.000
was
Token was
Feature activation+0.000
arrested
Token arrested
Feature activation+0.000
at
Token at
Feature activation+0.000
fighter
Token fighter
Feature activation+0.000
,
Token,
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.182
man
Token man
Feature activation+0.219
Robert
Token Robert
Feature activation+0.765
Rose
Token Rose
Feature activation+0.164
,
Token,
Feature activation+0.205
said
Token said
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
Police
Token Police
Feature activation+0.000
identified
Token identified
Feature activation+0.000
the
Token the
Feature activation+0.000
man
Token man
Feature activation+0.000
as
Token as
Feature activation+1.274
42
Token 42
Feature activation+0.758
-
Token-
Feature activation+0.377
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+1.560
H
Token H
Feature activation+0.208
's
Token's
Feature activation+0.000
obsession
Token obsession
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
actor
Token actor
Feature activation+0.000
.
Token.
Feature activation+0.731
Back
Token Back
Feature activation+0.156
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
summer
Token summer
Feature activation+0.000
of
Token of
Feature activation+0.000

Top DFA by src position
MAX = 3.889

after
Token after
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
fire
Token fire
Feature activation-0.020
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.026
Top resid features:
man
Token man
Feature activation+3.889
Top resid features:
identified
Token identified
Feature activation-0.023
Top resid features:
in
Token in
Feature activation-0.042
Top resid features:
the
Token the
Feature activation-0.016
Top resid features:
document
Token document
Feature activation-0.038
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
passion
Token passion
Feature activation-0.012
Top resid features:
project
Token project
Feature activation+0.030
Top resid features:
of
Token of
Feature activation+0.035
Top resid features:
a
Token a
Feature activation+0.026
Top resid features:
single
Token single
Feature activation+0.065
Top resid features:
man
Token man
Feature activation+3.025
Top resid features:
:
Token:
Feature activation+0.060
Top resid features:
President
Token President
Feature activation+0.000
Top resid features:
Recep
Token Recep
Feature activation+0.000
Top resid features:
Tayyip
Token Tayyip
Feature activation+0.000
Top resid features:
Erdogan
Token Erdogan
Feature activation+0.000
Top resid features:
after
Token after
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
fire
Token fire
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
man
Token man
Feature activation+2.193
Top resid features:
identified
Token identified
Feature activation-0.085
Top resid features:
in
Token in
Feature activation-0.019
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
document
Token document
Feature activation-0.008
Top resid features:
as
Token as
Feature activation+0.615
Top resid features:
,
Token,
Feature activation+0.019
Top resid features:
sent
Token sent
Feature activation+0.032
Top resid features:
to
Token to
Feature activation-0.018
Top resid features:
meet
Token meet
Feature activation+0.017
Top resid features:
a
Token a
Feature activation+0.027
Top resid features:
man
Token man
Feature activation+2.420
Top resid features:
named
Token named
Feature activation+0.135
Top resid features:
Robert
Token Robert
Feature activation+0.000
Top resid features:
Warren
Token Warren
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
evaluate
Token evaluate
Feature activation+0.000
Top resid features:
There
Token There
Feature activation+0.002
Top resid features:
is
Token is
Feature activation+0.041
Top resid features:
only
Token only
Feature activation+0.009
Top resid features:
one
Token one
Feature activation+0.268
Top resid features:
living
Token living
Feature activation+0.057
Top resid features:
man
Token man
Feature activation+1.664
Top resid features:
who
Token who
Feature activation+0.546
Top resid features:
knows
Token knows
Feature activation+0.127
Top resid features:
the
Token the
Feature activation+0.059
Top resid features:
final
Token final
Feature activation+0.010
Top resid features:
location
Token location
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
As
TokenAs
Feature activation+0.017
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
man
Token man
Feature activation+2.021
Top resid features:
who
Token who
Feature activation+0.268
Top resid features:
enjoys
Token enjoys
Feature activation+0.028
Top resid features:
âĢ
Token âĢ
Feature activation+0.014
Top resid features:
ľ
Tokenľ
Feature activation+0.013
Top resid features:
ug
Tokenug
Feature activation+0.027
Top resid features:
Dav
Token Dav
Feature activation-0.036
Top resid features:
ie
Tokenie
Feature activation-0.002
Top resid features:
Police
Token Police
Feature activation-0.007
Top resid features:
identified
Token identified
Feature activation-0.028
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
man
Token man
Feature activation+1.566
Top resid features:
as
Token as
Feature activation-0.029
Top resid features:
42
Token 42
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
year
Tokenyear
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
league
Tokenleague
Feature activation-0.000
Top resid features:
red
Tokenred
Feature activation-0.005
Top resid features:
cities
Token cities
Feature activation+0.101
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
one
Token one
Feature activation+0.013
Top resid features:
man
Token man
Feature activation+1.764
Top resid features:
has
Token has
Feature activation+0.260
Top resid features:
emerged
Token emerged
Feature activation+0.090
Top resid features:
as
Token as
Feature activation+0.028
Top resid features:
a
Token a
Feature activation+0.013
Top resid features:
leading
Token leading
Feature activation+0.046
Top resid features:
,
Token,
Feature activation+0.025
Top resid features:
sent
Token sent
Feature activation+0.024
Top resid features:
to
Token to
Feature activation-0.012
Top resid features:
meet
Token meet
Feature activation+0.014
Top resid features:
a
Token a
Feature activation+0.037
Top resid features:
man
Token man
Feature activation+2.022
Top resid features:
named
Token named
Feature activation+0.169
Top resid features:
Robert
Token Robert
Feature activation+0.000
Top resid features:
Warren
Token Warren
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
evaluate
Token evaluate
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.033
Top resid features:
and
Token and
Feature activation-0.179
Top resid features:
being
Token being
Feature activation-0.050
Top resid features:
a
Token a
Feature activation-0.006
Top resid features:
fun
Token fun
Feature activation+0.022
Top resid features:
guy
Token guy
Feature activation+2.670
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
time
Token time
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
State
Token State
Feature activation-0.064
Top resid features:
and
Token and
Feature activation-0.036
Top resid features:
described
Token described
Feature activation-0.038
Top resid features:
the
Token the
Feature activation-0.090
Top resid features:
British
Token British
Feature activation+0.007
Top resid features:
man
Token man
Feature activation+2.239
Top resid features:
known
Token known
Feature activation+0.032
Top resid features:
as
Token as
Feature activation+0.081
Top resid features:
J
Token J
Feature activation+0.000
Top resid features:
ihadi
Tokenihadi
Feature activation+0.000
Top resid features:
John
Token John
Feature activation+0.000
Top resid features:
Invalid
Token Invalid
Feature activation-0.003
Top resid features:
Email
Token Email
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
A
TokenA
Feature activation+0.004
Top resid features:
boy
Token boy
Feature activation+1.675
Top resid features:
of
Token of
Feature activation+0.052
Top resid features:
six
Token six
Feature activation+0.011
Top resid features:
has
Token has
Feature activation+0.072
Top resid features:
won
Token won
Feature activation-0.000
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
v
Tokenv
Feature activation+0.002
Top resid features:
ie
Tokenie
Feature activation+0.018
Top resid features:
talks
Token talks
Feature activation+0.084
Top resid features:
about
Token about
Feature activation+0.159
Top resid features:
that
Token that
Feature activation+0.062
Top resid features:
guy
Token guy
Feature activation+1.884
Top resid features:
,
Token,
Feature activation+0.021
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
always
Token always
Feature activation+0.000
Top resid features:
seems
Token seems
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
At
Token At
Feature activation+0.001
Top resid features:
Sant
Token Sant
Feature activation+0.005
Top resid features:
o
Tokeno
Feature activation+0.001
Top resid features:
Rio
Token Rio
Feature activation-0.019
Top resid features:
two
Token two
Feature activation+0.015
Top resid features:
men
Token men
Feature activation+1.996
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
Travis
Token Travis
Feature activation-0.004
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Ch
Token Ch
Feature activation+0.000
Top resid features:
ato
Tokenato
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.011
Top resid features:
sofa
Token sofa
Feature activation-0.019
Top resid features:
across
Token across
Feature activation-0.041
Top resid features:
from
Token from
Feature activation-0.042
Top resid features:
a
Token a
Feature activation+0.047
Top resid features:
man
Token man
Feature activation+1.978
Top resid features:
he
Token he
Feature activation+0.079
Top resid features:
believed
Token believed
Feature activation+0.129
Top resid features:
to
Token to
Feature activation+0.042
Top resid features:
be
Token be
Feature activation+0.125
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
At
Token At
Feature activation-0.008
Top resid features:
Sant
Token Sant
Feature activation-0.002
Top resid features:
o
Tokeno
Feature activation+0.012
Top resid features:
Rio
Token Rio
Feature activation+0.003
Top resid features:
two
Token two
Feature activation+0.041
Top resid features:
men
Token men
Feature activation+1.895
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
Travis
Token Travis
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Ch
Token Ch
Feature activation+0.000
Top resid features:
ato
Tokenato
Feature activation+0.000
Top resid features:
42
Token 42
Feature activation+0.018
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
year
Tokenyear
Feature activation+0.023
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
old
Tokenold
Feature activation+0.746
Top resid features:
man
Token man
Feature activation+0.871
Top resid features:
from
Token from
Feature activation+0.031
Top resid features:
Glou
Token Glou
Feature activation+0.000
Top resid features:
cester
Tokencester
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
arrested
Token arrested
Feature activation+0.000
Top resid features:
YPG
Token YPG
Feature activation-0.026
Top resid features:
fighter
Token fighter
Feature activation+0.223
Top resid features:
,
Token,
Feature activation+0.095
Top resid features:
New
Token New
Feature activation-0.005
Top resid features:
York
Token York
Feature activation+0.024
Top resid features:
man
Token man
Feature activation+1.233
Top resid features:
Robert
Token Robert
Feature activation+0.078
Top resid features:
Rose
Token Rose
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
Dav
Token Dav
Feature activation-0.007
Top resid features:
ie
Tokenie
Feature activation-0.003
Top resid features:
Police
Token Police
Feature activation-0.006
Top resid features:
identified
Token identified
Feature activation-0.017
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
man
Token man
Feature activation+0.904
Top resid features:
as
Token as
Feature activation+0.167
Top resid features:
42
Token 42
Feature activation+0.009
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
year
Tokenyear
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
ollywood
Tokenollywood
Feature activation+0.027
Top resid features:
films
Token films
Feature activation+0.024
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
But
Token But
Feature activation+0.019
Top resid features:
one
Token one
Feature activation+0.052
Top resid features:
man
Token man
Feature activation+1.171
Top resid features:
's
Token's
Feature activation+0.118
Top resid features:
se
Token se
Feature activation-0.003
Top resid features:
rend
Tokenrend
Feature activation-0.001
Top resid features:
ip
Tokenip
Feature activation-0.002
Top resid features:
itous
Tokenitous
Feature activation+0.032
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.07

Head 2: 0.02

Head 3: 0.06

Head 4: 0.05

Head 5: 0.49

Head 6: 0.06

Head 7: 0.02

Head 8: 0.09

Head 9: 0.05

Head 10: 0.02

Head 11: 0.02

Positive logits

dilig2.29

Commodore2.29

Extensions2.19

yip2.18

Gutenberg2.18

Afee2.16

chev2.14

exch2.05

intendent2.04

acca2.03

$$$$2.02

Rasm2.02

rov2.00

ertodd2.00

Aviation1.95

helm1.95

Rodrigo1.94

ctor1.92

Yamaha1.92

looph1.90

Negative logits

actresses-3.06

heroine-2.63

women-2.61

females-2.50

sisters-2.50

mothers-2.45

womb-2.42

girls-2.41

female-2.40

women-2.34

breast-2.28

maid-2.26

breasts-2.25

daughters-2.24

femin-2.22

vaginal-2.21

feminists-2.20

femin-2.19

feminine-2.18

vagina-2.16

INTERVAL 2.267 - 2.519
CONTAINS 0.000%

man
Token man
Feature activation+0.000
identified
Token identified
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
document
Token document
Feature activation+0.000
as
Token as
Feature activation+2.519
Mark
Token Mark
Feature activation+1.640
O
Token O
Feature activation+0.000
th
Tokenth
Feature activation+0.000
on
Tokenon
Feature activation+0.150
came
Token came
Feature activation+0.000

INTERVAL 2.015 - 2.267
CONTAINS 0.000%

INTERVAL 1.763 - 2.015
CONTAINS 0.000%

project
Token project
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
single
Token single
Feature activation+0.000
man
Token man
Feature activation+0.000
:
Token:
Feature activation+1.923
President
Token President
Feature activation+0.000
Recep
Token Recep
Feature activation+0.000
Tayyip
Token Tayyip
Feature activation+0.000
Erdogan
Token Erdogan
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 1.511 - 1.763
CONTAINS 0.000%

identified
Token identified
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
document
Token document
Feature activation+0.000
as
Token as
Feature activation+2.519
Mark
Token Mark
Feature activation+1.640
O
Token O
Feature activation+0.000
th
Tokenth
Feature activation+0.000
on
Tokenon
Feature activation+0.150
came
Token came
Feature activation+0.000
forward
Token forward
Feature activation+0.000
sent
Token sent
Feature activation+0.000
to
Token to
Feature activation+0.000
meet
Token meet
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
named
Token named
Feature activation+1.599
Robert
Token Robert
Feature activation+0.575
Warren
Token Warren
Feature activation+0.193
to
Token to
Feature activation+0.000
evaluate
Token evaluate
Feature activation+0.000
his
Token his
Feature activation+0.000

INTERVAL 1.259 - 1.511
CONTAINS 0.000%

ly
Tokenly
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
polymer
Token polymer
Feature activation+0.000
guns
Token guns
Feature activation+0.000
,
Token,
Feature activation+1.275
I
Token I
Feature activation+0.000
honestly
Token honestly
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
Police
Token Police
Feature activation+0.000
identified
Token identified
Feature activation+0.000
the
Token the
Feature activation+0.000
man
Token man
Feature activation+0.000
as
Token as
Feature activation+1.274
42
Token 42
Feature activation+0.758
-
Token-
Feature activation+0.377
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+1.560
location
Token location
Feature activation+0.000
of
Token of
Feature activation+0.000
Hitler
Token Hitler
Feature activation+0.000
's
Token's
Feature activation+0.000
remains
Token remains
Feature activation+0.000
,
Token,
Feature activation+1.500
and
Token and
Feature activation+0.368
he
Token he
Feature activation+0.160
vowed
Token vowed
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000

INTERVAL 1.008 - 1.259
CONTAINS 0.000%

sent
Token sent
Feature activation+0.000
to
Token to
Feature activation+0.000
meet
Token meet
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
named
Token named
Feature activation+1.226
Robert
Token Robert
Feature activation+0.564
Warren
Token Warren
Feature activation+0.090
to
Token to
Feature activation+0.000
evaluate
Token evaluate
Feature activation+0.000
his
Token his
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
catastrophe
Token catastrophe
Feature activation+0.000
.
Token.
Feature activation+0.648
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.234
Republican
TokenRepublican
Feature activation+0.674
pund
Token pund
Feature activation+0.000
it
Tokenit
Feature activation+0.575
,
Token,
Feature activation+0.202
former
Token former
Feature activation+0.000

INTERVAL 0.756 - 1.008
CONTAINS 0.001%

thousands
Token thousands
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.701
Le
TokenLe
Feature activation+0.057
o
Tokeno
Feature activation+0.940
Hunter
Token Hunter
Feature activation+0.000
was
Token was
Feature activation+0.000
awarded
Token awarded
Feature activation+0.000
a
Token a
Feature activation+0.000
23
Token 23
Feature activation+0.000
described
Token described
Feature activation+0.000
the
Token the
Feature activation+0.000
British
Token British
Feature activation+0.000
man
Token man
Feature activation+0.000
known
Token known
Feature activation+0.000
as
Token as
Feature activation+0.954
J
Token J
Feature activation+0.536
ihadi
Tokenihadi
Feature activation+0.000
John
Token John
Feature activation+0.000
as
Token as
Feature activation+0.000
his
Token his
Feature activation+0.000
and
Token and
Feature activation+0.000
being
Token being
Feature activation+0.000
a
Token a
Feature activation+0.000
fun
Token fun
Feature activation+0.000
guy
Token guy
Feature activation+0.000
,
Token,
Feature activation+0.962
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
time
Token time
Feature activation+0.000
to
Token to
Feature activation+0.000
sit
Token sit
Feature activation+0.000
Sant
Token Sant
Feature activation+0.000
o
Tokeno
Feature activation+0.000
Rio
Token Rio
Feature activation+0.000
two
Token two
Feature activation+0.000
men
Token men
Feature activation+0.000
,
Token,
Feature activation+0.824
Travis
Token Travis
Feature activation+0.885
and
Token and
Feature activation+0.134
Ch
Token Ch
Feature activation+0.000
ato
Tokenato
Feature activation+0.000
,
Token,
Feature activation+0.000
-
Token-
Feature activation+0.000
year
Tokenyear
Feature activation+0.000
-
Token-
Feature activation+0.000
old
Tokenold
Feature activation+0.000
man
Token man
Feature activation+0.000
from
Token from
Feature activation+0.821
Glou
Token Glou
Feature activation+0.000
cester
Tokencester
Feature activation+0.000
was
Token was
Feature activation+0.000
arrested
Token arrested
Feature activation+0.000
at
Token at
Feature activation+0.000

INTERVAL 0.504 - 0.756
CONTAINS 0.002%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
quick
Token quick
Feature activation+0.000
anecdote
Token anecdote
Feature activation+0.000
:
Token:
Feature activation+0.635
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
10
Token 10
Feature activation+0.000
th
Tokenth
Feature activation+0.000
from
Token from
Feature activation+0.000
court
Token court
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.506
Gary
TokenGary
Feature activation+0.707
Stewart
Token Stewart
Feature activation+0.202
,
Token,
Feature activation+0.159
37
Token 37
Feature activation+0.000
,
Token,
Feature activation+0.000
had
Token had
Feature activation+0.000
skept
Token skept
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
catastrophe
Token catastrophe
Feature activation+0.000
.
Token.
Feature activation+0.648
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.234
Republican
TokenRepublican
Feature activation+0.674
pund
Token pund
Feature activation+0.000
it
Tokenit
Feature activation+0.575
deal
Token deal
Feature activation+0.000
worth
Token worth
Feature activation+0.000
thousands
Token thousands
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.701
Le
TokenLe
Feature activation+0.057
o
Tokeno
Feature activation+0.940
Hunter
Token Hunter
Feature activation+0.000
was
Token was
Feature activation+0.000
awarded
Token awarded
Feature activation+0.000
the
Token the
Feature activation+0.000
catastrophe
Token catastrophe
Feature activation+0.000
.
Token.
Feature activation+0.648
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.234
Republican
TokenRepublican
Feature activation+0.674
pund
Token pund
Feature activation+0.000
it
Tokenit
Feature activation+0.575
,
Token,
Feature activation+0.202
former
Token former
Feature activation+0.000
state
Token state
Feature activation+0.000

INTERVAL 0.252 - 0.504
CONTAINS 0.005%

shared
Token shared
Feature activation+0.000
as
Token as
Feature activation+0.000
he
Token he
Feature activation+0.000
accepted
Token accepted
Feature activation+0.000
him
Token him
Feature activation+0.000
as
Token as
Feature activation+0.302
someone
Token someone
Feature activation+0.000
Kara
Token Kara
Feature activation+0.000
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
love
Token love
Feature activation+0.000
levy
Token levy
Feature activation+0.000
on
Token on
Feature activation+0.000
just
Token just
Feature activation+0.000
one
Token one
Feature activation+0.000
man
Token man
Feature activation+0.000
:
Token:
Feature activation+0.303
James
Token James
Feature activation+0.000
D
Token D
Feature activation+0.000
olan
Tokenolan
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
her
Token her
Feature activation+0.000
boyfriend
Token boyfriend
Feature activation+0.000
,
Token,
Feature activation+0.321
Sam
Token Sam
Feature activation+0.307
,
Token,
Feature activation+0.000
visiting
Token visiting
Feature activation+0.000
from
Token from
Feature activation+0.000
Indiana
Token Indiana
Feature activation+0.000
.
Token.
Feature activation+0.000
involving
Token involving
Feature activation+0.000
a
Token a
Feature activation+0.000
man
Token man
Feature activation+0.000
who
Token who
Feature activation+0.000
calls
Token calls
Feature activation+0.000
himself
Token himself
Feature activation+0.461
Saint
Token Saint
Feature activation+0.000
Dr
Token Dr
Feature activation+0.000
.
Token.
Feature activation+0.000
Gur
Token Gur
Feature activation+0.000
meet
Tokenmeet
Feature activation+0.000
tickets
Token tickets
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
her
Token her
Feature activation+0.000
boyfriend
Token boyfriend
Feature activation+0.000
,
Token,
Feature activation+0.321
Sam
Token Sam
Feature activation+0.307
,
Token,
Feature activation+0.000
visiting
Token visiting
Feature activation+0.000
from
Token from
Feature activation+0.000
Indiana
Token Indiana
Feature activation+0.000

INTERVAL 0.000 - 0.252
CONTAINS 99.991%

to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
done
Token done
Feature activation+0.000
about
Token about
Feature activation+0.000
ton
Token ton
Feature activation+0.000
ing
Tokening
Feature activation+0.000
down
Token down
Feature activation+0.000
the
Token the
Feature activation+0.000
rhetoric
Token rhetoric
Feature activation+0.000
from
Token from
Feature activation+0.000
certain
Token certain
Feature activation+0.000
unaware
Token unaware
Feature activation+0.000
of
Token of
Feature activation+0.000
anyone
Token anyone
Feature activation+0.000
being
Token being
Feature activation+0.000
prosecuted
Token prosecuted
Feature activation+0.000
for
Token for
Feature activation+0.000
pot
Token pot
Feature activation+0.000
cookies
Token cookies
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
councillor
Token councillor
Feature activation+0.000
who
Token who
Feature activation+0.000
called
Token called
Feature activation+0.000
People
Token People
Feature activation+0.000
Before
Token Before
Feature activation+0.000
Profit
Token Profit
Feature activation+0.000
's
Token's
Feature activation+0.000
Gerry
Token Gerry
Feature activation+0.000
Carroll
Token Carroll
Feature activation+0.000
a
Token a
Feature activation+0.000
"
Token "
Feature activation+0.000
social
Token social
Feature activation+0.000
being
Token being
Feature activation+0.000
held
Token held
Feature activation+0.000
again
Token again
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
main
Token main
Feature activation+0.000
conference
Token conference
Feature activation+0.000
room
Token room
Feature activation+0.000
with
Token with
Feature activation+0.000
more
Token more
Feature activation+0.000
see
Token see
Feature activation+0.000
that
Token that
Feature activation+0.000
trend
Token trend
Feature activation+0.000
continue
Token continue
Feature activation+0.000
,
Token,
Feature activation+0.000
on
Token on
Feature activation+0.000
and
Token and
Feature activation+0.000
off
Token off
Feature activation+0.000
,
Token,
Feature activation+0.000
until
Token until
Feature activation+0.000
it
Token it
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 H7.5: (feature 14937)

TOP ACTIVATIONS
MAX = 2.637

well
Token well
Feature activation+0.000
.
Token.
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
among
Token among
Feature activation+0.000
them
Token them
Feature activation+0.781
are
Token are
Feature activation+2.637
new
Token new
Feature activation+2.158
gameplay
Token gameplay
Feature activation+0.170
scenarios
Token scenarios
Feature activation+0.280
that
Token that
Feature activation+0.438
embrace
Token embrace
Feature activation+0.356
the
Token the
Feature activation+0.000
FCC
Token FCC
Feature activation+0.000
.
Token.
Feature activation+0.000
Wi
TokenWi
Feature activation+0.739
-
Token-
Feature activation+0.000
Fi
TokenFi
Feature activation+2.374
calling
Token calling
Feature activation+0.725
will
Token will
Feature activation+0.409
allow
Token allow
Feature activation+0.656
Verizon
Token Verizon
Feature activation+0.000
customers
Token customers
Feature activation+0.000
t
Tokent
Feature activation+0.000
include
Token include
Feature activation+0.000
some
Token some
Feature activation+0.000
Sony
Token Sony
Feature activation+0.000
features
Token features
Feature activation+0.000
such
Token such
Feature activation+2.251
as
Token as
Feature activation+1.231
Stamina
Token Stamina
Feature activation+0.674
mode
Token mode
Feature activation+0.132
,
Token,
Feature activation+1.420
Screen
Token Screen
Feature activation+0.628
.
Token.
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
among
Token among
Feature activation+0.000
them
Token them
Feature activation+0.781
are
Token are
Feature activation+2.637
new
Token new
Feature activation+2.158
gameplay
Token gameplay
Feature activation+0.170
scenarios
Token scenarios
Feature activation+0.280
that
Token that
Feature activation+0.438
embrace
Token embrace
Feature activation+0.356
elements
Token elements
Feature activation+0.000
First
Token First
Feature activation+0.573
,
Token,
Feature activation+1.402
we
Token we
Feature activation+1.528
added
Token added
Feature activation+1.081
the
Token the
Feature activation+1.641
ability
Token ability
Feature activation+2.124
to
Token to
Feature activation+1.156
download
Token download
Feature activation+0.343
files
Token files
Feature activation+0.000
from
Token from
Feature activation+0.000
Box
Token Box
Feature activation+0.000
two
Token two
Feature activation+0.000
new
Token new
Feature activation+0.000
,
Token,
Feature activation+0.000
important
Token important
Feature activation+0.000
features
Token features
Feature activation+0.000
:
Token:
Feature activation+2.123
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Donald
TokenDonald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
calls
Token calls
Feature activation+0.000
for
Token for
Feature activation+0.000
tested
Token tested
Feature activation+0.000
features
Token features
Feature activation+0.000
,
Token,
Feature activation+0.252
with
Token with
Feature activation+0.485
the
Token the
Feature activation+0.279
cam
Token cam
Feature activation+1.966
c
Tokenc
Feature activation+0.000
order
Tokenorder
Feature activation+1.853
and
Token and
Feature activation+1.109
LEDs
Token LEDs
Feature activation+0.728
during
Token during
Feature activation+0.054
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pro
TokenPro
Feature activation+0.000
Features
Token Features
Feature activation+0.205
Ċ
TokenĊ
Feature activation+1.309
Ċ
TokenĊ
Feature activation+1.934
Send
TokenSend
Feature activation+0.722
St
Token St
Feature activation+0.000
ickers
Tokenickers
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.845
Ċ
TokenĊ
Feature activation+1.327
,
Token,
Feature activation+0.252
with
Token with
Feature activation+0.485
the
Token the
Feature activation+0.279
cam
Token cam
Feature activation+1.966
c
Tokenc
Feature activation+0.000
order
Tokenorder
Feature activation+1.853
and
Token and
Feature activation+1.109
LEDs
Token LEDs
Feature activation+0.728
during
Token during
Feature activation+0.054
boot
Token boot
Feature activation+0.000
being
Token being
Feature activation+0.858
features
Token features
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+1.562
the
Token the
Feature activation+1.171
ability
Token ability
Feature activation+1.171
to
Token to
Feature activation+1.838
schedule
Token schedule
Feature activation+0.164
rides
Token rides
Feature activation+0.000
in
Token in
Feature activation+0.242
advance
Token advance
Feature activation+0.000
,
Token,
Feature activation+1.237
in
Token in
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
latest
Token latest
Feature activation+0.000
features
Token features
Feature activation+0.000
like
Token like
Feature activation+1.836
2
Token 2
Feature activation+0.588
.
Token.
Feature activation+0.000
4
Token4
Feature activation+0.000
GHz
TokenGHz
Feature activation+0.318
control
Token control
Feature activation+0.482
with
Token with
Feature activation+0.000
suggest
Token suggest
Feature activation+0.000
and
Token and
Feature activation+0.000
auto
Token auto
Feature activation+0.000
complete
Token complete
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.809
Ċ
TokenĊ
Feature activation+0.761
Have
TokenHave
Feature activation+0.021
click
Token click
Feature activation+0.202
able
Tokenable
Feature activation+0.080
icons
Token icons
Feature activation+0.000
let
Tokenlet
Feature activation+0.865
of
Token of
Feature activation+0.000
user
Token user
Feature activation+0.000
sche
Token sche
Feature activation+0.000
mas
Tokenmas
Feature activation+0.362
Ċ
TokenĊ
Feature activation+1.808
Ċ
TokenĊ
Feature activation+1.282
Tree
TokenTree
Feature activation+0.718
View
Token View
Feature activation+0.427
of
Token of
Feature activation+0.000
schema
Token schema
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.380
See
TokenSee
Feature activation+0.662
your
Token your
Feature activation+0.498
current
Token current
Feature activation+0.043
location
Token location
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.739
Ċ
TokenĊ
Feature activation+1.252
Search
TokenSearch
Feature activation+0.315
for
Token for
Feature activation+0.000
what
Token what
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
.
Token.
Feature activation+0.109
First
Token First
Feature activation+0.573
,
Token,
Feature activation+1.402
we
Token we
Feature activation+1.528
added
Token added
Feature activation+1.081
the
Token the
Feature activation+1.641
ability
Token ability
Feature activation+2.124
to
Token to
Feature activation+1.156
download
Token download
Feature activation+0.343
files
Token files
Feature activation+0.000
from
Token from
Feature activation+0.000
instead
Token instead
Feature activation+0.000
of
Token of
Feature activation+0.000
other
Token other
Feature activation+0.000
key
Token key
Feature activation+0.000
features
Token features
Feature activation+0.000
like
Token like
Feature activation+1.579
e
Token e
Feature activation+0.098
-
Token-
Feature activation+0.000
commerce
Tokencommerce
Feature activation+0.000
or
Token or
Feature activation+0.008
connected
Token connected
Feature activation+0.000
Repl
Token Repl
Feature activation+0.000
ies
Tokenies
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
Comment
Token Comment
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.569
Ċ
TokenĊ
Feature activation+1.413
Reply
TokenReply
Feature activation+0.516
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
Comment
Token Comment
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+0.000
new
Token new
Feature activation+0.000
features
Token features
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+1.562
the
Token the
Feature activation+1.171
ability
Token ability
Feature activation+1.171
to
Token to
Feature activation+1.838
schedule
Token schedule
Feature activation+0.164
rides
Token rides
Feature activation+0.000
requested
Token requested
Feature activation+0.000
features
Token features
Feature activation+0.000
.
Token.
Feature activation+0.109
First
Token First
Feature activation+0.573
,
Token,
Feature activation+1.402
we
Token we
Feature activation+1.528
added
Token added
Feature activation+1.081
the
Token the
Feature activation+1.641
ability
Token ability
Feature activation+2.124
to
Token to
Feature activation+1.156
download
Token download
Feature activation+0.343
As
Token As
Feature activation+0.081
a
Token a
Feature activation+0.613
shuttle
Token shuttle
Feature activation+0.000
,
Token,
Feature activation+0.464
he
Token he
Feature activation+1.152
can
Token can
Feature activation+1.520
easily
Token easily
Feature activation+0.000
travel
Token travel
Feature activation+0.000
between
Token between
Feature activation+0.000
star
Token star
Feature activation+0.000
systems
Token systems
Feature activation+0.000

Top DFA by src position
MAX = 3.604

2
Token 2
Feature activation+0.006
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
0
Token0
Feature activation-0.008
Top resid features:
's
Token's
Feature activation+0.033
Top resid features:
new
Token new
Feature activation+0.041
Top resid features:
features
Token features
Feature activation+3.604
Top resid features:
as
Token as
Feature activation-0.008
Top resid features:
well
Token well
Feature activation+0.004
Top resid features:
.
Token.
Feature activation-0.001
Top resid features:
Chief
Token Chief
Feature activation-0.005
Top resid features:
among
Token among
Feature activation-0.005
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
Fi
TokenFi
Feature activation+0.004
Top resid features:
calling
Token calling
Feature activation+0.152
Top resid features:
,
Token,
Feature activation+0.101
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
feature
Token feature
Feature activation+2.910
Top resid features:
was
Token was
Feature activation+0.046
Top resid features:
turned
Token turned
Feature activation+0.001
Top resid features:
on
Token on
Feature activation+0.048
Top resid features:
within
Token within
Feature activation-0.000
Top resid features:
days
Token days
Feature activation-0.001
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
t
Tokent
Feature activation-0.029
Top resid features:
include
Token include
Feature activation+0.039
Top resid features:
some
Token some
Feature activation+0.022
Top resid features:
Sony
Token Sony
Feature activation+0.033
Top resid features:
features
Token features
Feature activation+2.755
Top resid features:
such
Token such
Feature activation+0.055
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Stamina
Token Stamina
Feature activation+0.000
Top resid features:
mode
Token mode
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
2
Token 2
Feature activation+0.051
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
0
Token0
Feature activation+0.095
Top resid features:
's
Token's
Feature activation+0.082
Top resid features:
new
Token new
Feature activation+0.035
Top resid features:
features
Token features
Feature activation+2.664
Top resid features:
as
Token as
Feature activation-0.001
Top resid features:
well
Token well
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Chief
Token Chief
Feature activation-0.002
Top resid features:
among
Token among
Feature activation+0.002
Top resid features:
that
Token that
Feature activation+0.032
Top resid features:
includes
Token includes
Feature activation+0.074
Top resid features:
several
Token several
Feature activation+0.023
Top resid features:
highly
Token highly
Feature activation+0.009
Top resid features:
requested
Token requested
Feature activation+0.117
Top resid features:
features
Token features
Feature activation+2.227
Top resid features:
.
Token.
Feature activation+0.046
Top resid features:
First
Token First
Feature activation+0.012
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
we
Token we
Feature activation+0.009
Top resid features:
added
Token added
Feature activation+0.095
Top resid features:
also
Token also
Feature activation-0.000
Top resid features:
two
Token two
Feature activation+0.027
Top resid features:
new
Token new
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
important
Token important
Feature activation+0.019
Top resid features:
features
Token features
Feature activation+2.737
Top resid features:
:
Token:
Feature activation+0.018
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
Donald
TokenDonald
Feature activation+0.000
Top resid features:
Trump
Token Trump
Feature activation+0.000
Top resid features:
calls
Token calls
Feature activation+0.000
Top resid features:
M
Token M
Feature activation+0.002
Top resid features:
comes
Token comes
Feature activation+0.020
Top resid features:
with
Token with
Feature activation+0.259
Top resid features:
many
Token many
Feature activation+0.077
Top resid features:
tested
Token tested
Feature activation-0.008
Top resid features:
features
Token features
Feature activation+2.125
Top resid features:
,
Token,
Feature activation+0.074
Top resid features:
with
Token with
Feature activation+0.040
Top resid features:
the
Token the
Feature activation+0.047
Top resid features:
cam
Token cam
Feature activation-0.018
Top resid features:
c
Tokenc
Feature activation+0.000
Top resid features:
an
Token an
Feature activation-0.006
Top resid features:
Album
Token Album
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Pro
TokenPro
Feature activation-0.002
Top resid features:
Features
Token Features
Feature activation+1.836
Top resid features:
Ċ
TokenĊ
Feature activation+0.567
Top resid features:
Ċ
TokenĊ
Feature activation+0.183
Top resid features:
Send
TokenSend
Feature activation+0.000
Top resid features:
St
Token St
Feature activation+0.000
Top resid features:
ickers
Tokenickers
Feature activation+0.000
Top resid features:
M
Token M
Feature activation+0.004
Top resid features:
comes
Token comes
Feature activation+0.057
Top resid features:
with
Token with
Feature activation+0.656
Top resid features:
many
Token many
Feature activation+0.141
Top resid features:
tested
Token tested
Feature activation-0.010
Top resid features:
features
Token features
Feature activation+1.446
Top resid features:
,
Token,
Feature activation+0.103
Top resid features:
with
Token with
Feature activation+0.158
Top resid features:
the
Token the
Feature activation+0.099
Top resid features:
cam
Token cam
Feature activation+0.015
Top resid features:
c
Tokenc
Feature activation+0.024
Top resid features:
added
Token added
Feature activation+0.029
Top resid features:
a
Token a
Feature activation+0.038
Top resid features:
number
Token number
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.024
Top resid features:
new
Token new
Feature activation+0.085
Top resid features:
features
Token features
Feature activation+1.611
Top resid features:
,
Token,
Feature activation+0.236
Top resid features:
including
Token including
Feature activation+0.082
Top resid features:
the
Token the
Feature activation+0.076
Top resid features:
ability
Token ability
Feature activation+0.028
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
packed
Token packed
Feature activation+0.017
Top resid features:
in
Token in
Feature activation+0.025
Top resid features:
all
Token all
Feature activation+0.027
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
latest
Token latest
Feature activation+0.912
Top resid features:
features
Token features
Feature activation+1.665
Top resid features:
like
Token like
Feature activation+0.023
Top resid features:
2
Token 2
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
4
Token4
Feature activation+0.000
Top resid features:
GHz
TokenGHz
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.041
Top resid features:
same
Token same
Feature activation+0.002
Top resid features:
Google
Token Google
Feature activation+0.003
Top resid features:
Maps
Token Maps
Feature activation+0.012
Top resid features:
features
Token features
Feature activation+2.435
Top resid features:
you
Token you
Feature activation+0.004
Top resid features:
âĢ
TokenâĢ
Feature activation-0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.001
Top resid features:
re
Tokenre
Feature activation-0.001
Top resid features:
used
Token used
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
Overview
TokenOverview
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Features
TokenFeatures
Feature activation+2.107
Top resid features:
Ċ
TokenĊ
Feature activation+0.342
Top resid features:
Ċ
TokenĊ
Feature activation+0.398
Top resid features:
Pal
TokenPal
Feature activation-0.001
Top resid features:
let
Tokenlet
Feature activation+0.003
Top resid features:
of
Token of
Feature activation+0.009
Top resid features:
of
Token of
Feature activation+0.011
Top resid features:
the
Token the
Feature activation+0.016
Top resid features:
same
Token same
Feature activation+0.002
Top resid features:
Google
Token Google
Feature activation+0.007
Top resid features:
Maps
Token Maps
Feature activation+0.018
Top resid features:
features
Token features
Feature activation+2.282
Top resid features:
you
Token you
Feature activation+0.012
Top resid features:
âĢ
TokenâĢ
Feature activation-0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.002
Top resid features:
re
Tokenre
Feature activation-0.001
Top resid features:
used
Token used
Feature activation+0.002
Top resid features:
that
Token that
Feature activation+0.053
Top resid features:
includes
Token includes
Feature activation+0.046
Top resid features:
several
Token several
Feature activation+0.029
Top resid features:
highly
Token highly
Feature activation+0.008
Top resid features:
requested
Token requested
Feature activation+0.115
Top resid features:
features
Token features
Feature activation+1.711
Top resid features:
.
Token.
Feature activation+0.081
Top resid features:
First
Token First
Feature activation+0.047
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
we
Token we
Feature activation+0.024
Top resid features:
added
Token added
Feature activation+0.055
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
instead
Token instead
Feature activation-0.038
Top resid features:
of
Token of
Feature activation-0.039
Top resid features:
other
Token other
Feature activation+0.039
Top resid features:
key
Token key
Feature activation+0.006
Top resid features:
features
Token features
Feature activation+2.396
Top resid features:
like
Token like
Feature activation+0.058
Top resid features:
e
Token e
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
commerce
Tokencommerce
Feature activation+0.000
Top resid features:
or
Token or
Feature activation+0.000
Top resid features:
an
Token an
Feature activation-0.001
Top resid features:
Album
Token Album
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.078
Top resid features:
Pro
TokenPro
Feature activation-0.013
Top resid features:
Features
Token Features
Feature activation+1.361
Top resid features:
Ċ
TokenĊ
Feature activation+0.387
Top resid features:
Ċ
TokenĊ
Feature activation+0.447
Top resid features:
Send
TokenSend
Feature activation+0.001
Top resid features:
St
Token St
Feature activation-0.014
Top resid features:
ickers
Tokenickers
Feature activation-0.008
Top resid features:
added
Token added
Feature activation+0.063
Top resid features:
a
Token a
Feature activation-0.008
Top resid features:
number
Token number
Feature activation+0.007
Top resid features:
of
Token of
Feature activation+0.041
Top resid features:
new
Token new
Feature activation+0.218
Top resid features:
features
Token features
Feature activation+1.562
Top resid features:
,
Token,
Feature activation+0.218
Top resid features:
including
Token including
Feature activation+0.056
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
ability
Token ability
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.066
Top resid features:
includes
Token includes
Feature activation+0.233
Top resid features:
several
Token several
Feature activation+0.051
Top resid features:
highly
Token highly
Feature activation+0.008
Top resid features:
requested
Token requested
Feature activation+0.084
Top resid features:
features
Token features
Feature activation+1.550
Top resid features:
.
Token.
Feature activation+0.077
Top resid features:
First
Token First
Feature activation+0.032
Top resid features:
,
Token,
Feature activation+0.083
Top resid features:
we
Token we
Feature activation+0.012
Top resid features:
added
Token added
Feature activation+0.000
Top resid features:
unusual
Token unusual
Feature activation+0.017
Top resid features:
form
Token form
Feature activation-0.024
Top resid features:
grants
Token grants
Feature activation+0.033
Top resid features:
him
Token him
Feature activation-0.002
Top resid features:
several
Token several
Feature activation+0.025
Top resid features:
abilities
Token abilities
Feature activation+2.074
Top resid features:
.
Token.
Feature activation+0.148
Top resid features:
As
Token As
Feature activation-0.003
Top resid features:
a
Token a
Feature activation-0.002
Top resid features:
shuttle
Token shuttle
Feature activation-0.010
Top resid features:
,
Token,
Feature activation+0.142
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.07

Head 2: 0.02

Head 3: 0.07

Head 4: 0.03

Head 5: 0.49

Head 6: 0.08

Head 7: 0.04

Head 8: 0.06

Head 9: 0.05

Head 10: 0.02

Head 11: 0.02

Positive logits

customization3.01

connectivity2.79

functionality2.71

customizable2.63

ability2.54

interface2.53

integration2.53

features2.50

sync2.43

flexibility2.42

capabilities2.41

modes2.40

Remote2.40

streamlined2.38

dynamically2.37

widget2.36

enhancements2.33

encryption2.33

unlock2.33

navigation2.32

Negative logits

ateurs-2.11

unworthy-2.05

irgin-2.04

prevailed-2.02

lington-1.96

boys-1.95

iddles-1.93

-1.92

Herz-1.92

Americans-1.90

-1.90

ּ-1.89

discarded-1.86

ansas-1.86

doomed-1.86

Mond-1.86

disappointed-1.85

mere-1.82

ohm-1.82

unsuccessful-1.81

INTERVAL 2.373 - 2.637
CONTAINS 0.000%

well
Token well
Feature activation+0.000
.
Token.
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
among
Token among
Feature activation+0.000
them
Token them
Feature activation+0.781
are
Token are
Feature activation+2.637
new
Token new
Feature activation+2.158
gameplay
Token gameplay
Feature activation+0.170
scenarios
Token scenarios
Feature activation+0.280
that
Token that
Feature activation+0.438
embrace
Token embrace
Feature activation+0.356
the
Token the
Feature activation+0.000
FCC
Token FCC
Feature activation+0.000
.
Token.
Feature activation+0.000
Wi
TokenWi
Feature activation+0.739
-
Token-
Feature activation+0.000
Fi
TokenFi
Feature activation+2.374
calling
Token calling
Feature activation+0.725
will
Token will
Feature activation+0.409
allow
Token allow
Feature activation+0.656
Verizon
Token Verizon
Feature activation+0.000
customers
Token customers
Feature activation+0.000

INTERVAL 2.110 - 2.373
CONTAINS 0.000%

.
Token.
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
among
Token among
Feature activation+0.000
them
Token them
Feature activation+0.781
are
Token are
Feature activation+2.637
new
Token new
Feature activation+2.158
gameplay
Token gameplay
Feature activation+0.170
scenarios
Token scenarios
Feature activation+0.280
that
Token that
Feature activation+0.438
embrace
Token embrace
Feature activation+0.356
elements
Token elements
Feature activation+0.000
t
Tokent
Feature activation+0.000
include
Token include
Feature activation+0.000
some
Token some
Feature activation+0.000
Sony
Token Sony
Feature activation+0.000
features
Token features
Feature activation+0.000
such
Token such
Feature activation+2.251
as
Token as
Feature activation+1.231
Stamina
Token Stamina
Feature activation+0.674
mode
Token mode
Feature activation+0.132
,
Token,
Feature activation+1.420
Screen
Token Screen
Feature activation+0.628
two
Token two
Feature activation+0.000
new
Token new
Feature activation+0.000
,
Token,
Feature activation+0.000
important
Token important
Feature activation+0.000
features
Token features
Feature activation+0.000
:
Token:
Feature activation+2.123
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Donald
TokenDonald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
calls
Token calls
Feature activation+0.000
for
Token for
Feature activation+0.000
First
Token First
Feature activation+0.573
,
Token,
Feature activation+1.402
we
Token we
Feature activation+1.528
added
Token added
Feature activation+1.081
the
Token the
Feature activation+1.641
ability
Token ability
Feature activation+2.124
to
Token to
Feature activation+1.156
download
Token download
Feature activation+0.343
files
Token files
Feature activation+0.000
from
Token from
Feature activation+0.000
Box
Token Box
Feature activation+0.000

INTERVAL 1.846 - 2.110
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pro
TokenPro
Feature activation+0.000
Features
Token Features
Feature activation+0.205
Ċ
TokenĊ
Feature activation+1.309
Ċ
TokenĊ
Feature activation+1.934
Send
TokenSend
Feature activation+0.722
St
Token St
Feature activation+0.000
ickers
Tokenickers
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.845
Ċ
TokenĊ
Feature activation+1.327
tested
Token tested
Feature activation+0.000
features
Token features
Feature activation+0.000
,
Token,
Feature activation+0.252
with
Token with
Feature activation+0.485
the
Token the
Feature activation+0.279
cam
Token cam
Feature activation+1.966
c
Tokenc
Feature activation+0.000
order
Tokenorder
Feature activation+1.853
and
Token and
Feature activation+1.109
LEDs
Token LEDs
Feature activation+0.728
during
Token during
Feature activation+0.054
,
Token,
Feature activation+0.252
with
Token with
Feature activation+0.485
the
Token the
Feature activation+0.279
cam
Token cam
Feature activation+1.966
c
Tokenc
Feature activation+0.000
order
Tokenorder
Feature activation+1.853
and
Token and
Feature activation+1.109
LEDs
Token LEDs
Feature activation+0.728
during
Token during
Feature activation+0.054
boot
Token boot
Feature activation+0.000
being
Token being
Feature activation+0.858

INTERVAL 1.582 - 1.846
CONTAINS 0.001%

.
Token.
Feature activation+0.109
First
Token First
Feature activation+0.573
,
Token,
Feature activation+1.402
we
Token we
Feature activation+1.528
added
Token added
Feature activation+1.081
the
Token the
Feature activation+1.641
ability
Token ability
Feature activation+2.124
to
Token to
Feature activation+1.156
download
Token download
Feature activation+0.343
files
Token files
Feature activation+0.000
from
Token from
Feature activation+0.000
with
Token with
Feature activation+0.000
suggest
Token suggest
Feature activation+0.000
and
Token and
Feature activation+0.000
auto
Token auto
Feature activation+0.000
complete
Token complete
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.809
Ċ
TokenĊ
Feature activation+0.761
Have
TokenHave
Feature activation+0.021
click
Token click
Feature activation+0.202
able
Tokenable
Feature activation+0.080
icons
Token icons
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.380
See
TokenSee
Feature activation+0.662
your
Token your
Feature activation+0.498
current
Token current
Feature activation+0.043
location
Token location
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.739
Ċ
TokenĊ
Feature activation+1.252
Search
TokenSearch
Feature activation+0.315
for
Token for
Feature activation+0.000
what
Token what
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
let
Tokenlet
Feature activation+0.865
of
Token of
Feature activation+0.000
user
Token user
Feature activation+0.000
sche
Token sche
Feature activation+0.000
mas
Tokenmas
Feature activation+0.362
Ċ
TokenĊ
Feature activation+1.808
Ċ
TokenĊ
Feature activation+1.282
Tree
TokenTree
Feature activation+0.718
View
Token View
Feature activation+0.427
of
Token of
Feature activation+0.000
schema
Token schema
Feature activation+0.000
features
Token features
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+1.562
the
Token the
Feature activation+1.171
ability
Token ability
Feature activation+1.171
to
Token to
Feature activation+1.838
schedule
Token schedule
Feature activation+0.164
rides
Token rides
Feature activation+0.000
in
Token in
Feature activation+0.242
advance
Token advance
Feature activation+0.000
,
Token,
Feature activation+1.237

INTERVAL 1.319 - 1.582
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+1.413
Reply
TokenReply
Feature activation+0.516
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
Comment
Token Comment
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.500
Ċ
TokenĊ
Feature activation+1.039
Download
TokenDownload
Feature activation+0.662
Videos
Token Videos
Feature activation+0.000
and
Token and
Feature activation+0.000
Photos
Token Photos
Feature activation+0.000
As
Token As
Feature activation+0.081
a
Token a
Feature activation+0.613
shuttle
Token shuttle
Feature activation+0.000
,
Token,
Feature activation+0.464
he
Token he
Feature activation+1.152
can
Token can
Feature activation+1.520
easily
Token easily
Feature activation+0.000
travel
Token travel
Feature activation+0.000
between
Token between
Feature activation+0.000
star
Token star
Feature activation+0.000
systems
Token systems
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.934
Send
TokenSend
Feature activation+0.722
St
Token St
Feature activation+0.000
ickers
Tokenickers
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.845
Ċ
TokenĊ
Feature activation+1.327
View
TokenView
Feature activation+0.418
Repl
Token Repl
Feature activation+0.000
ies
Tokenies
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
ies
Tokenies
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
Comment
Token Comment
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.569
Ċ
TokenĊ
Feature activation+1.413
Reply
TokenReply
Feature activation+0.516
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
Comment
Token Comment
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.500
highly
Token highly
Feature activation+0.248
requested
Token requested
Feature activation+0.000
features
Token features
Feature activation+0.000
.
Token.
Feature activation+0.109
First
Token First
Feature activation+0.573
,
Token,
Feature activation+1.402
we
Token we
Feature activation+1.528
added
Token added
Feature activation+1.081
the
Token the
Feature activation+1.641
ability
Token ability
Feature activation+2.124
to
Token to
Feature activation+1.156

INTERVAL 1.055 - 1.319
CONTAINS 0.003%

in
Token in
Feature activation+0.242
advance
Token advance
Feature activation+0.000
,
Token,
Feature activation+1.237
as
Token as
Feature activation+0.267
well
Token well
Feature activation+0.611
as
Token as
Feature activation+1.267
providing
Token providing
Feature activation+0.908
up
Token up
Feature activation+0.016
-
Token-
Feature activation+0.169
front
Tokenfront
Feature activation+0.024
fare
Token fare
Feature activation+0.057
c
Tokenc
Feature activation+0.000
's
Token's
Feature activation+0.000
other
Token other
Feature activation+0.000
distinctive
Token distinctive
Feature activation+0.000
feature
Token feature
Feature activation+0.000
is
Token is
Feature activation+1.188
its
Token its
Feature activation+1.059
similarity
Token similarity
Feature activation+0.169
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
G
Token G
Feature activation+0.000
Cowboys
Token Cowboys
Feature activation+0.000
Stadium
Token Stadium
Feature activation+0.000
and
Token and
Feature activation+0.000
amenities
Token amenities
Feature activation+0.000
such
Token such
Feature activation+0.410
as
Token as
Feature activation+1.290
the
Token the
Feature activation+0.922
1
Token 1
Feature activation+0.159
.
Token.
Feature activation+0.165
3
Token3
Feature activation+0.000
-
Token-
Feature activation+0.000
new
Token new
Feature activation+0.000
aspects
Token aspects
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
:
Token:
Feature activation+1.072
Cooperative
Token Cooperative
Feature activation+0.120
building
Token building
Feature activation+0.170
,
Token,
Feature activation+0.587
selling
Token selling
Feature activation+0.000
of
Token of
Feature activation+0.000
price
Token price
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
make
Tokenmake
Feature activation+1.120
-
Token-
Feature activation+0.284
or
Tokenor
Feature activation+0.000
-
Token-
Feature activation+0.000
break
Tokenbreak
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 0.791 - 1.055
CONTAINS 0.005%

res
Tokenres
Feature activation+0.000
,
Token,
Feature activation+0.507
S
Token S
Feature activation+0.000
CC
TokenCC
Feature activation+0.000
annotations
Token annotations
Feature activation+0.321
,
Token,
Feature activation+0.997
reporting
Token reporting
Feature activation+0.322
allocations
Token allocations
Feature activation+0.000
/
Token/
Feature activation+0.000
t
Tokent
Feature activation+0.000
icks
Tokenicks
Feature activation+0.000
interviews
Token interviews
Feature activation+0.000
,
Token,
Feature activation+0.626
interviews
Token interviews
Feature activation+0.000
with
Token with
Feature activation+0.000
prospects
Token prospects
Feature activation+0.000
,
Token,
Feature activation+0.875
and
Token and
Feature activation+0.692
updates
Token updates
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Isles
Token Isles
Feature activation+0.000
the
Token the
Feature activation+0.000
things
Token things
Feature activation+0.000
I
Token I
Feature activation+0.000
like
Token like
Feature activation+0.000
:
Token:
Feature activation+0.726
Numbers
Token Numbers
Feature activation+0.884
(
Token (
Feature activation+0.418
I
TokenI
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
Reply
TokenReply
Feature activation+0.516
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
Comment
Token Comment
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.500
Ċ
TokenĊ
Feature activation+1.039
Download
TokenDownload
Feature activation+0.662
Videos
Token Videos
Feature activation+0.000
and
Token and
Feature activation+0.000
Photos
Token Photos
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.167
further
Token further
Feature activation+0.000
extended
Token extended
Feature activation+0.000
with
Token with
Feature activation+0.738
plugins
Token plugins
Feature activation+0.317
.
Token.
Feature activation+0.942
It
Token It
Feature activation+1.000
also
Token also
Feature activation+0.000
has
Token has
Feature activation+0.199
customizable
Token customizable
Feature activation+0.712
looks
Token looks
Feature activation+0.026
,
Token,
Feature activation+0.196

INTERVAL 0.527 - 0.791
CONTAINS 0.009%

View
Token View
Feature activation+0.427
of
Token of
Feature activation+0.000
schema
Token schema
Feature activation+0.000
elements
Token elements
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.338
Ċ
TokenĊ
Feature activation+0.755
Context
TokenContext
Feature activation+0.231
Menu
Token Menu
Feature activation+0.195
Ċ
TokenĊ
Feature activation+0.950
Ċ
TokenĊ
Feature activation+0.283
Property
TokenProperty
Feature activation+0.120
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
N
TokenN
Feature activation+0.000
ile
Tokenile
Feature activation+0.000
cruise
Token cruise
Feature activation+0.000
,
Token,
Feature activation+0.546
anyone
Token anyone
Feature activation+0.000
?)
Token?)
Feature activation+0.000
Ever
Token Ever
Feature activation+0.000
since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
ups
Tokenups
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
arena
Token arena
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+0.567
mega
Token mega
Feature activation+0.407
health
Tokenhealth
Feature activation+0.390
,
Token,
Feature activation+0.000
haste
Token haste
Feature activation+0.040
,
Token,
Feature activation+0.150
to
Token to
Feature activation+1.163
have
Token have
Feature activation+0.050
a
Token a
Feature activation+0.187
fancy
Token fancy
Feature activation+0.000
access
Token access
Feature activation+0.000
to
Token to
Feature activation+0.706
Google
Token Google
Feature activation+0.000
's
Token's
Feature activation+0.043
Gmail
Token Gmail
Feature activation+0.046
with
Token with
Feature activation+0.061
a
Token a
Feature activation+0.195
some
Token some
Feature activation+0.000
Sony
Token Sony
Feature activation+0.000
features
Token features
Feature activation+0.000
such
Token such
Feature activation+2.251
as
Token as
Feature activation+1.231
Stamina
Token Stamina
Feature activation+0.674
mode
Token mode
Feature activation+0.132
,
Token,
Feature activation+1.420
Screen
Token Screen
Feature activation+0.628
Recording
Token Recording
Feature activation+0.855
and
Token and
Feature activation+0.685

INTERVAL 0.264 - 0.527
CONTAINS 0.022%

of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
iPhone
Token iPhone
Feature activation+0.000
's
Token's
Feature activation+0.000
battery
Token battery
Feature activation+0.000
,
Token,
Feature activation+0.368
so
Token so
Feature activation+0.000
they
Token they
Feature activation+0.000
can
Token can
Feature activation+0.000
see
Token see
Feature activation+0.000
for
Token for
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.478
Text
TokenText
Feature activation+0.000
View
Token View
Feature activation+0.000
of
Token of
Feature activation+0.000
schema
Token schema
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.437
Ċ
TokenĊ
Feature activation+0.315
Drag
TokenDrag
Feature activation+0.000
and
Token and
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token .
Feature activation+0.000
Lyn
Token Lyn
Feature activation+0.000
c
Tokenc
Feature activation+0.093
2013
Token 2013
Feature activation+0.000
users
Token users
Feature activation+0.000
will
Token will
Feature activation+0.305
be
Token be
Feature activation+0.338
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.017
see
Token see
Feature activation+0.000
presence
Token presence
Feature activation+0.000
The
TokenThe
Feature activation+0.000
facility
Token facility
Feature activation+0.000
will
Token will
Feature activation+0.000
include
Token include
Feature activation+0.000
activities
Token activities
Feature activation+0.000
such
Token such
Feature activation+0.425
as
Token as
Feature activation+0.329
indoor
Token indoor
Feature activation+0.000
surfing
Token surfing
Feature activation+0.040
,
Token,
Feature activation+0.000
tr
Token tr
Feature activation+0.000
and
Token and
Feature activation+0.000
carry
Token carry
Feature activation+0.000
passengers
Token passengers
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
.
Token.
Feature activation+0.265
When
Token When
Feature activation+0.000
transformed
Token transformed
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
can
Token can
Feature activation+0.075

INTERVAL 0.000 - 0.264
CONTAINS 99.959%

.
Token.
Feature activation+0.000
Mike
Token Mike
Feature activation+0.000
Pence
Token Pence
Feature activation+0.000
drew
Token drew
Feature activation+0.000
headlines
Token headlines
Feature activation+0.000
earlier
Token earlier
Feature activation+0.000
this
Token this
Feature activation+0.000
month
Token month
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.000
defended
Token defended
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
Ċ
TokenĊ
Feature activation+0.000
G
TokenG
Feature activation+0.000
ross
Tokenross
Feature activation+0.000
debt
Token debt
Feature activation+0.000
sums
Token sums
Feature activation+0.000
up
Token up
Feature activation+0.000
voters
Token voters
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.000
has
Token has
Feature activation+0.000
already
Token already
Feature activation+0.000
sunk
Token sunk
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Type
TokenType
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
After
TokenAfter
Feature activation+0.000
four
Token four
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000
of
Token of
Feature activation+0.000
play
Token play
Feature activation+0.000
in
Token in
Feature activation+0.000
Atlanta
Token Atlanta
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
more
Token more
Feature activation+0.000
than
Token than
Feature activation+0.000
200
Token 200
Feature activation+0.000
languages
Token languages
Feature activation+0.000
,
Token,
Feature activation+0.000
accompanied
Token accompanied
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
dozen
Token dozen
Feature activation+0.000
additional
Token additional
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 H7.5: (feature 419)

TOP ACTIVATIONS
MAX = 3.290

partly
Token partly
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.218
,
Token,
Feature activation+2.787
Bill
Token Bill
Feature activation+3.290
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
of
Token of
Feature activation+0.000
Fame
Token Fame
Feature activation+0.000
who
Token who
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.552
was
Token was
Feature activation+0.571
(
Token (
Feature activation+0.925
Pierre
TokenPierre
Feature activation+3.189
Trudeau
Token Trudeau
Feature activation+0.890
,
Token,
Feature activation+0.194
Canadian
Token Canadian
Feature activation+0.122
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+1.280
,
Token,
Feature activation+0.000
Germany
Token Germany
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+3.045
Samuel
Token Samuel
Feature activation+2.667
Levi
Token Levi
Feature activation+2.779
Jos
Token Jos
Feature activation+0.000
ap
Tokenap
Feature activation+0.604
hat
Tokenhat
Feature activation+2.109
idi
Tokenidi
Feature activation+0.000
's
Token's
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+2.532
Far
Token Far
Feature activation+1.002
ia
Tokenia
Feature activation+2.922
,
Token,
Feature activation+0.077
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
president
Token president
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
father
Token father
Feature activation+0.648
,
Token,
Feature activation+2.911
Barack
Token Barack
Feature activation+2.564
Obama
Token Obama
Feature activation+1.269
Sr
Token Sr
Feature activation+0.967
.,
Token.,
Feature activation+0.577
and
Token and
Feature activation+0.188
based
Token based
Feature activation+0.000
partly
Token partly
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.218
,
Token,
Feature activation+2.787
Bill
Token Bill
Feature activation+3.290
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+3.045
Samuel
Token Samuel
Feature activation+2.667
Levi
Token Levi
Feature activation+2.779
Jos
Token Jos
Feature activation+0.000
ap
Tokenap
Feature activation+0.604
hat
Tokenhat
Feature activation+2.109
,
Token,
Feature activation+0.062
was
Token was
Feature activation+0.077
Germany
Token Germany
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+3.045
Samuel
Token Samuel
Feature activation+2.667
Levi
Token Levi
Feature activation+2.779
Jos
Token Jos
Feature activation+0.000
ap
Tokenap
Feature activation+0.604
hat
Tokenhat
Feature activation+2.109
,
Token,
Feature activation+0.062
.
Token.
Feature activation+0.195
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
His
TokenHis
Feature activation+0.000
father
Token father
Feature activation+0.194
,
Token,
Feature activation+2.575
who
Token who
Feature activation+0.304
shares
Token shares
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.063
name
Token name
Feature activation+0.269
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
father
Token father
Feature activation+0.648
,
Token,
Feature activation+2.911
Barack
Token Barack
Feature activation+2.564
Obama
Token Obama
Feature activation+1.269
Sr
Token Sr
Feature activation+0.967
.,
Token.,
Feature activation+0.577
and
Token and
Feature activation+0.188
his
Token his
Feature activation+0.078
Mat
TokenMat
Feature activation+0.000
u
Tokenu
Feature activation+0.000
idi
Tokenidi
Feature activation+0.000
's
Token's
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+2.532
Far
Token Far
Feature activation+1.002
ia
Tokenia
Feature activation+2.922
,
Token,
Feature activation+0.077
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+2.047
retired
Token retired
Feature activation+1.119
Army
Token Army
Feature activation+0.000
Col
Token Col
Feature activation+1.745
.
Token.
Feature activation+1.861
Joseph
Token Joseph
Feature activation+2.349
L
Token L
Feature activation+0.455
.
Token.
Feature activation+1.774
G
Token G
Feature activation+0.000
ude
Tokenude
Feature activation+0.568
,
Token,
Feature activation+0.000
for
Token for
Feature activation+0.000
over
Token over
Feature activation+0.000
40
Token 40
Feature activation+0.000
years
Token years
Feature activation+0.000
.
Token.
Feature activation+0.000
Joseph
Token Joseph
Feature activation+2.330
was
Token was
Feature activation+0.000
honored
Token honored
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
White
Token White
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
dad
Token dad
Feature activation+0.000
,
Token,
Feature activation+1.840
Ag
Token Ag
Feature activation+0.623
ato
Tokenato
Feature activation+2.316
-
Token -
Feature activation+0.150
a
Token a
Feature activation+0.865
big
Token big
Feature activation+0.315
rugby
Token rugby
Feature activation+0.000
fan
Token fan
Feature activation+0.000
,"
Token,"
Feature activation+0.000
father
Token father
Feature activation+0.744
and
Token and
Feature activation+0.000
agent
Token agent
Feature activation+1.312
Ir
Token Ir
Feature activation+0.672
fan
Tokenfan
Feature activation+2.227
told
Token told
Feature activation+0.000
Kick
Token Kick
Feature activation+0.000
er
Tokener
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
mag
Tokenmag
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Her
TokenHer
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+1.914
Ar
Token Ar
Feature activation+1.637
un
Tokenun
Feature activation+2.118
Sebastian
Token Sebastian
Feature activation+0.723
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.150
radi
Token radi
Feature activation+0.000
ologist
Tokenologist
Feature activation+0.464
,
Token,
Feature activation+3.045
Samuel
Token Samuel
Feature activation+2.667
Levi
Token Levi
Feature activation+2.779
Jos
Token Jos
Feature activation+0.000
ap
Tokenap
Feature activation+0.604
hat
Tokenhat
Feature activation+2.109
,
Token,
Feature activation+0.062
was
Token was
Feature activation+0.077
a
Token a
Feature activation+0.602
rabbi
Token rabbi
Feature activation+0.409
.
Token.
Feature activation+0.000
-
Token-
Feature activation+0.000
G
TokenG
Feature activation+0.000
ude
Tokenude
Feature activation+0.000
's
Token's
Feature activation+0.000
grandfather
Token grandfather
Feature activation+0.020
,
Token,
Feature activation+2.047
retired
Token retired
Feature activation+1.119
Army
Token Army
Feature activation+0.000
Col
Token Col
Feature activation+1.745
.
Token.
Feature activation+1.861
Joseph
Token Joseph
Feature activation+2.349
grandfather
Token grandfather
Feature activation+0.020
,
Token,
Feature activation+2.047
retired
Token retired
Feature activation+1.119
Army
Token Army
Feature activation+0.000
Col
Token Col
Feature activation+1.745
.
Token.
Feature activation+1.861
Joseph
Token Joseph
Feature activation+2.349
L
Token L
Feature activation+0.455
.
Token.
Feature activation+1.774
G
Token G
Feature activation+0.000
ude
Tokenude
Feature activation+0.568
in
Token in
Feature activation+0.000
Samoa
Token Samoa
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
dad
Token dad
Feature activation+0.000
,
Token,
Feature activation+1.840
Ag
Token Ag
Feature activation+0.623
ato
Tokenato
Feature activation+2.316
-
Token -
Feature activation+0.150
a
Token a
Feature activation+0.865
big
Token big
Feature activation+0.315

Top DFA by src position
MAX = 4.153

State
Token State
Feature activation-0.013
Top resid features:
based
Token based
Feature activation-0.002
Top resid features:
partly
Token partly
Feature activation-0.001
Top resid features:
on
Token on
Feature activation+0.018
Top resid features:
his
Token his
Feature activation+0.041
Top resid features:
father
Token father
Feature activation+3.852
Top resid features:
,
Token,
Feature activation+0.326
Top resid features:
Bill
Token Bill
Feature activation+0.043
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
Hall
Token Hall
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
because
Token because
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
who
Token who
Feature activation-0.001
Top resid features:
his
Token his
Feature activation+0.006
Top resid features:
father
Token father
Feature activation+3.738
Top resid features:
was
Token was
Feature activation+0.057
Top resid features:
(
Token (
Feature activation+0.245
Top resid features:
Pierre
TokenPierre
Feature activation+0.040
Top resid features:
Trudeau
Token Trudeau
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
sel
Tokensel
Feature activation-0.030
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
Germany
Token Germany
Feature activation-0.091
Top resid features:
.
Token.
Feature activation-0.041
Top resid features:
His
Token His
Feature activation+0.034
Top resid features:
father
Token father
Feature activation+4.153
Top resid features:
,
Token,
Feature activation+0.124
Top resid features:
Samuel
Token Samuel
Feature activation+0.000
Top resid features:
Levi
Token Levi
Feature activation+0.000
Top resid features:
Jos
Token Jos
Feature activation+0.000
Top resid features:
ap
Tokenap
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Mat
TokenMat
Feature activation+0.002
Top resid features:
u
Tokenu
Feature activation+0.004
Top resid features:
idi
Tokenidi
Feature activation+0.011
Top resid features:
's
Token's
Feature activation+0.040
Top resid features:
father
Token father
Feature activation+3.377
Top resid features:
,
Token,
Feature activation+0.219
Top resid features:
Far
Token Far
Feature activation+0.242
Top resid features:
ia
Tokenia
Feature activation+0.030
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.028
Top resid features:
president
Token president
Feature activation+0.014
Top resid features:
âĢ
TokenâĢ
Feature activation+0.079
Top resid features:
Ļ
TokenĻ
Feature activation+0.010
Top resid features:
s
Tokens
Feature activation+0.047
Top resid features:
father
Token father
Feature activation+3.728
Top resid features:
,
Token,
Feature activation+0.106
Top resid features:
Barack
Token Barack
Feature activation+0.000
Top resid features:
Obama
Token Obama
Feature activation+0.000
Top resid features:
Sr
Token Sr
Feature activation+0.000
Top resid features:
.,
Token.,
Feature activation+0.000
Top resid features:
State
Token State
Feature activation-0.019
Top resid features:
based
Token based
Feature activation+0.002
Top resid features:
partly
Token partly
Feature activation-0.009
Top resid features:
on
Token on
Feature activation+0.009
Top resid features:
his
Token his
Feature activation+0.034
Top resid features:
father
Token father
Feature activation+3.658
Top resid features:
,
Token,
Feature activation+0.131
Top resid features:
Bill
Token Bill
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
Hall
Token Hall
Feature activation+0.000
Top resid features:
sel
Tokensel
Feature activation-0.006
Top resid features:
,
Token,
Feature activation-0.010
Top resid features:
Germany
Token Germany
Feature activation-0.049
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
His
Token His
Feature activation+0.035
Top resid features:
father
Token father
Feature activation+2.743
Top resid features:
,
Token,
Feature activation+0.511
Top resid features:
Samuel
Token Samuel
Feature activation+0.301
Top resid features:
Levi
Token Levi
Feature activation+0.111
Top resid features:
Jos
Token Jos
Feature activation+0.000
Top resid features:
ap
Tokenap
Feature activation+0.000
Top resid features:
sel
Tokensel
Feature activation-0.008
Top resid features:
,
Token,
Feature activation-0.009
Top resid features:
Germany
Token Germany
Feature activation-0.055
Top resid features:
.
Token.
Feature activation+0.053
Top resid features:
His
Token His
Feature activation+0.041
Top resid features:
father
Token father
Feature activation+2.862
Top resid features:
,
Token,
Feature activation+0.528
Top resid features:
Samuel
Token Samuel
Feature activation+0.088
Top resid features:
Levi
Token Levi
Feature activation+0.000
Top resid features:
Jos
Token Jos
Feature activation+0.000
Top resid features:
ap
Tokenap
Feature activation+0.000
Top resid features:
problem
Token problem
Feature activation+0.006
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.099
Top resid features:
Ċ
TokenĊ
Feature activation+0.035
Top resid features:
His
TokenHis
Feature activation+0.127
Top resid features:
father
Token father
Feature activation+2.259
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
shares
Token shares
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
same
Token same
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.005
Top resid features:
president
Token president
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.048
Top resid features:
Ļ
TokenĻ
Feature activation+0.026
Top resid features:
s
Tokens
Feature activation+0.020
Top resid features:
father
Token father
Feature activation+3.111
Top resid features:
,
Token,
Feature activation+0.284
Top resid features:
Barack
Token Barack
Feature activation+0.021
Top resid features:
Obama
Token Obama
Feature activation+0.000
Top resid features:
Sr
Token Sr
Feature activation+0.000
Top resid features:
.,
Token.,
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Mat
TokenMat
Feature activation+0.021
Top resid features:
u
Tokenu
Feature activation+0.038
Top resid features:
idi
Tokenidi
Feature activation+0.027
Top resid features:
's
Token's
Feature activation+0.068
Top resid features:
father
Token father
Feature activation+3.383
Top resid features:
,
Token,
Feature activation+0.047
Top resid features:
Far
Token Far
Feature activation+0.000
Top resid features:
ia
Tokenia
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.000
Top resid features:
enzie
Tokenenzie
Feature activation-0.011
Top resid features:
-
Token-
Feature activation-0.034
Top resid features:
G
TokenG
Feature activation-0.023
Top resid features:
ude
Tokenude
Feature activation+0.007
Top resid features:
's
Token's
Feature activation+0.044
Top resid features:
grandfather
Token grandfather
Feature activation+2.818
Top resid features:
,
Token,
Feature activation+0.223
Top resid features:
retired
Token retired
Feature activation+0.071
Top resid features:
Army
Token Army
Feature activation-0.004
Top resid features:
Col
Token Col
Feature activation+0.021
Top resid features:
.
Token.
Feature activation+0.109
Top resid features:
78
Token 78
Feature activation+0.002
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
year
Tokenyear
Feature activation+0.005
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
old
Tokenold
Feature activation+0.008
Top resid features:
father
Token father
Feature activation+2.695
Top resid features:
founded
Token founded
Feature activation+0.009
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
Visual
Token Visual
Feature activation+0.011
Top resid features:
Arts
Token Arts
Feature activation-0.003
Top resid features:
Department
Token Department
Feature activation-0.001
Top resid features:
world
Token world
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.002
Top resid features:
Samoa
Token Samoa
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.006
Top resid features:
his
Token his
Feature activation+0.025
Top resid features:
dad
Token dad
Feature activation+2.499
Top resid features:
,
Token,
Feature activation+0.427
Top resid features:
Ag
Token Ag
Feature activation+0.274
Top resid features:
ato
Tokenato
Feature activation+0.093
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.003
Top resid features:
Bor
Token Bor
Feature activation+0.000
Top resid features:
ussia
Tokenussia
Feature activation-0.000
Top resid features:
Dortmund
Token Dortmund
Feature activation-0.004
Top resid features:
,"
Token,"
Feature activation-0.018
Top resid features:
father
Token father
Feature activation+2.943
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
agent
Token agent
Feature activation+0.087
Top resid features:
Ir
Token Ir
Feature activation+0.196
Top resid features:
fan
Tokenfan
Feature activation+0.027
Top resid features:
told
Token told
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.907
Top resid features:
Her
TokenHer
Feature activation+0.023
Top resid features:
father
Token father
Feature activation+2.553
Top resid features:
,
Token,
Feature activation+0.193
Top resid features:
Ar
Token Ar
Feature activation+0.267
Top resid features:
un
Tokenun
Feature activation-0.026
Top resid features:
Sebastian
Token Sebastian
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
sel
Tokensel
Feature activation-0.009
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
Germany
Token Germany
Feature activation-0.056
Top resid features:
.
Token.
Feature activation-0.027
Top resid features:
His
Token His
Feature activation+0.016
Top resid features:
father
Token father
Feature activation+1.439
Top resid features:
,
Token,
Feature activation+0.673
Top resid features:
Samuel
Token Samuel
Feature activation+0.482
Top resid features:
Levi
Token Levi
Feature activation+0.171
Top resid features:
Jos
Token Jos
Feature activation+0.459
Top resid features:
ap
Tokenap
Feature activation+0.034
Top resid features:
enzie
Tokenenzie
Feature activation-0.019
Top resid features:
-
Token-
Feature activation-0.039
Top resid features:
G
TokenG
Feature activation-0.050
Top resid features:
ude
Tokenude
Feature activation+0.039
Top resid features:
's
Token's
Feature activation+0.061
Top resid features:
grandfather
Token grandfather
Feature activation+2.895
Top resid features:
,
Token,
Feature activation+0.106
Top resid features:
retired
Token retired
Feature activation+0.000
Top resid features:
Army
Token Army
Feature activation+0.000
Top resid features:
Col
Token Col
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
enzie
Tokenenzie
Feature activation-0.007
Top resid features:
-
Token-
Feature activation-0.028
Top resid features:
G
TokenG
Feature activation-0.013
Top resid features:
ude
Tokenude
Feature activation-0.001
Top resid features:
's
Token's
Feature activation+0.038
Top resid features:
grandfather
Token grandfather
Feature activation+2.429
Top resid features:
,
Token,
Feature activation+0.212
Top resid features:
retired
Token retired
Feature activation+0.148
Top resid features:
Army
Token Army
Feature activation+0.007
Top resid features:
Col
Token Col
Feature activation+0.053
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
world
Token world
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:
Samoa
Token Samoa
Feature activation-0.011
Top resid features:
,
Token,
Feature activation-0.030
Top resid features:
his
Token his
Feature activation+0.059
Top resid features:
dad
Token dad
Feature activation+2.772
Top resid features:
,
Token,
Feature activation+0.111
Top resid features:
Ag
Token Ag
Feature activation+0.000
Top resid features:
ato
Tokenato
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.13

Head 1: 0.03

Head 2: 0.01

Head 3: 0.04

Head 4: 0.05

Head 5: 0.48

Head 6: 0.03

Head 7: 0.02

Head 8: 0.11

Head 9: 0.05

Head 10: 0.02

Head 11: 0.02

Positive logits

grandfather2.88

father2.32

Sr2.30

grandparents2.28

18962.23

Dad2.22

Papa2.15

mah2.14

conqu2.13

patriarch2.12

Ottoman2.12

Hale2.11

uncle2.10

prin2.08

Aristotle2.04

Dad2.03

maj2.02

Saban2.01

Mandal2.00

ancestor2.00

Negative logits

actions-2.14

bystand-2.14

selfie-2.13

clusions-2.08

selfies-2.07

monitor-2.05

ressive-2.03

target-2.03

trending-2.01

randomized-2.01

susp-1.97

uptake-1.96

ividual-1.95

targeted-1.95

messaging-1.93

healthy-1.93

tracking-1.89

alert-1.88

target-1.87

hashtag-1.87

INTERVAL 2.961 - 3.290
CONTAINS 0.000%

,
Token,
Feature activation+0.000
Germany
Token Germany
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+3.045
Samuel
Token Samuel
Feature activation+2.667
Levi
Token Levi
Feature activation+2.779
Jos
Token Jos
Feature activation+0.000
ap
Tokenap
Feature activation+0.604
hat
Tokenhat
Feature activation+2.109
who
Token who
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.552
was
Token was
Feature activation+0.571
(
Token (
Feature activation+0.925
Pierre
TokenPierre
Feature activation+3.189
Trudeau
Token Trudeau
Feature activation+0.890
,
Token,
Feature activation+0.194
Canadian
Token Canadian
Feature activation+0.122
Prime
Token Prime
Feature activation+0.000
Minister
Token Minister
Feature activation+1.280
partly
Token partly
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.218
,
Token,
Feature activation+2.787
Bill
Token Bill
Feature activation+3.290
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
of
Token of
Feature activation+0.000
Fame
Token Fame
Feature activation+0.000

INTERVAL 2.632 - 2.961
CONTAINS 0.001%

president
Token president
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
father
Token father
Feature activation+0.648
,
Token,
Feature activation+2.911
Barack
Token Barack
Feature activation+2.564
Obama
Token Obama
Feature activation+1.269
Sr
Token Sr
Feature activation+0.967
.,
Token.,
Feature activation+0.577
and
Token and
Feature activation+0.188
Germany
Token Germany
Feature activation+0.000
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+3.045
Samuel
Token Samuel
Feature activation+2.667
Levi
Token Levi
Feature activation+2.779
Jos
Token Jos
Feature activation+0.000
ap
Tokenap
Feature activation+0.604
hat
Tokenhat
Feature activation+2.109
,
Token,
Feature activation+0.062
.
Token.
Feature activation+0.000
His
Token His
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+3.045
Samuel
Token Samuel
Feature activation+2.667
Levi
Token Levi
Feature activation+2.779
Jos
Token Jos
Feature activation+0.000
ap
Tokenap
Feature activation+0.604
hat
Tokenhat
Feature activation+2.109
,
Token,
Feature activation+0.062
was
Token was
Feature activation+0.077
idi
Tokenidi
Feature activation+0.000
's
Token's
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+2.532
Far
Token Far
Feature activation+1.002
ia
Tokenia
Feature activation+2.922
,
Token,
Feature activation+0.077
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
based
Token based
Feature activation+0.000
partly
Token partly
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.218
,
Token,
Feature activation+2.787
Bill
Token Bill
Feature activation+3.290
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
Hall
Token Hall
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 2.303 - 2.632
CONTAINS 0.001%

.
Token.
Feature activation+0.195
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
His
TokenHis
Feature activation+0.000
father
Token father
Feature activation+0.194
,
Token,
Feature activation+2.575
who
Token who
Feature activation+0.304
shares
Token shares
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.063
name
Token name
Feature activation+0.269
,
Token,
Feature activation+2.047
retired
Token retired
Feature activation+1.119
Army
Token Army
Feature activation+0.000
Col
Token Col
Feature activation+1.745
.
Token.
Feature activation+1.861
Joseph
Token Joseph
Feature activation+2.349
L
Token L
Feature activation+0.455
.
Token.
Feature activation+1.774
G
Token G
Feature activation+0.000
ude
Tokenude
Feature activation+0.568
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
dad
Token dad
Feature activation+0.000
,
Token,
Feature activation+1.840
Ag
Token Ag
Feature activation+0.623
ato
Tokenato
Feature activation+2.316
-
Token -
Feature activation+0.150
a
Token a
Feature activation+0.865
big
Token big
Feature activation+0.315
rugby
Token rugby
Feature activation+0.000
fan
Token fan
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
father
Token father
Feature activation+0.648
,
Token,
Feature activation+2.911
Barack
Token Barack
Feature activation+2.564
Obama
Token Obama
Feature activation+1.269
Sr
Token Sr
Feature activation+0.967
.,
Token.,
Feature activation+0.577
and
Token and
Feature activation+0.188
his
Token his
Feature activation+0.078
Mat
TokenMat
Feature activation+0.000
u
Tokenu
Feature activation+0.000
idi
Tokenidi
Feature activation+0.000
's
Token's
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+2.532
Far
Token Far
Feature activation+1.002
ia
Tokenia
Feature activation+2.922
,
Token,
Feature activation+0.077
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 1.974 - 2.303
CONTAINS 0.000%

-
Token-
Feature activation+0.000
G
TokenG
Feature activation+0.000
ude
Tokenude
Feature activation+0.000
's
Token's
Feature activation+0.000
grandfather
Token grandfather
Feature activation+0.020
,
Token,
Feature activation+2.047
retired
Token retired
Feature activation+1.119
Army
Token Army
Feature activation+0.000
Col
Token Col
Feature activation+1.745
.
Token.
Feature activation+1.861
Joseph
Token Joseph
Feature activation+2.349
,
Token,
Feature activation+3.045
Samuel
Token Samuel
Feature activation+2.667
Levi
Token Levi
Feature activation+2.779
Jos
Token Jos
Feature activation+0.000
ap
Tokenap
Feature activation+0.604
hat
Tokenhat
Feature activation+2.109
,
Token,
Feature activation+0.062
was
Token was
Feature activation+0.077
a
Token a
Feature activation+0.602
rabbi
Token rabbi
Feature activation+0.409
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Her
TokenHer
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+1.914
Ar
Token Ar
Feature activation+1.637
un
Tokenun
Feature activation+2.118
Sebastian
Token Sebastian
Feature activation+0.723
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.150
radi
Token radi
Feature activation+0.000
ologist
Tokenologist
Feature activation+0.464
,"
Token,"
Feature activation+0.000
father
Token father
Feature activation+0.744
and
Token and
Feature activation+0.000
agent
Token agent
Feature activation+1.312
Ir
Token Ir
Feature activation+0.672
fan
Tokenfan
Feature activation+2.227
told
Token told
Feature activation+0.000
Kick
Token Kick
Feature activation+0.000
er
Tokener
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
mag
Tokenmag
Feature activation+0.000

INTERVAL 1.645 - 1.974
CONTAINS 0.001%

in
Token in
Feature activation+0.000
Samoa
Token Samoa
Feature activation+0.000
,
Token,
Feature activation+0.000
his
Token his
Feature activation+0.000
dad
Token dad
Feature activation+0.000
,
Token,
Feature activation+1.840
Ag
Token Ag
Feature activation+0.623
ato
Tokenato
Feature activation+2.316
-
Token -
Feature activation+0.150
a
Token a
Feature activation+0.865
big
Token big
Feature activation+0.315
's
Token's
Feature activation+0.000
grandfather
Token grandfather
Feature activation+0.020
,
Token,
Feature activation+2.047
retired
Token retired
Feature activation+1.119
Army
Token Army
Feature activation+0.000
Col
Token Col
Feature activation+1.745
.
Token.
Feature activation+1.861
Joseph
Token Joseph
Feature activation+2.349
L
Token L
Feature activation+0.455
.
Token.
Feature activation+1.774
G
Token G
Feature activation+0.000
grandfather
Token grandfather
Feature activation+0.020
,
Token,
Feature activation+2.047
retired
Token retired
Feature activation+1.119
Army
Token Army
Feature activation+0.000
Col
Token Col
Feature activation+1.745
.
Token.
Feature activation+1.861
Joseph
Token Joseph
Feature activation+2.349
L
Token L
Feature activation+0.455
.
Token.
Feature activation+1.774
G
Token G
Feature activation+0.000
ude
Tokenude
Feature activation+0.568
Army
Token Army
Feature activation+0.000
Col
Token Col
Feature activation+1.745
.
Token.
Feature activation+1.861
Joseph
Token Joseph
Feature activation+2.349
L
Token L
Feature activation+0.455
.
Token.
Feature activation+1.774
G
Token G
Feature activation+0.000
ude
Tokenude
Feature activation+0.568
,
Token,
Feature activation+0.000
87
Token 87
Feature activation+0.000
,
Token,
Feature activation+0.117
to
Token to
Feature activation+0.000
her
Token her
Feature activation+0.000
racing
Token racing
Feature activation+0.000
driver
Token driver
Feature activation+0.000
grandfather
Token grandfather
Feature activation+0.294
Francis
Token Francis
Feature activation+1.734
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.617
5
Token 5
Feature activation+0.564
th
Tokenth
Feature activation+0.721
Earl
Token Earl
Feature activation+1.006

INTERVAL 1.316 - 1.645
CONTAINS 0.001%

funeral
Token funeral
Feature activation+0.000
procession
Token procession
Feature activation+0.000
,
Token,
Feature activation+0.000
her
Token her
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+1.373
Za
Token Za
Feature activation+0.638
her
Tokenher
Feature activation+1.506
N
Token N
Feature activation+0.277
asser
Tokenasser
Feature activation+0.973
,
Token,
Feature activation+0.000
,
Token,
Feature activation+0.000
her
Token her
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+1.373
Za
Token Za
Feature activation+0.638
her
Tokenher
Feature activation+1.506
N
Token N
Feature activation+0.277
asser
Tokenasser
Feature activation+0.973
,
Token,
Feature activation+0.000
reacted
Token reacted
Feature activation+0.000
to
Token to
Feature activation+0.000
stated
Token stated
Feature activation+0.000
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
My
TokenMy
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+1.517
you
Token you
Feature activation+0.090
can
Token can
Feature activation+0.000
just
Token just
Feature activation+0.000
say
Token say
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.987 - 1.316
CONTAINS 0.001%

G
TokenG
Feature activation+0.000
ude
Tokenude
Feature activation+0.000
's
Token's
Feature activation+0.000
grandfather
Token grandfather
Feature activation+0.020
,
Token,
Feature activation+2.047
retired
Token retired
Feature activation+1.119
Army
Token Army
Feature activation+0.000
Col
Token Col
Feature activation+1.745
.
Token.
Feature activation+1.861
Joseph
Token Joseph
Feature activation+2.349
L
Token L
Feature activation+0.455
from
Token from
Feature activation+0.000
rural
Token rural
Feature activation+0.000
Delaware
Token Delaware
Feature activation+0.000
whose
Token whose
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+1.227
a
Token a
Feature activation+0.665
minister
Token minister
Feature activation+0.164
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Church
Token Church
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
father
Token father
Feature activation+0.000
and
Token and
Feature activation+1.014
son
Token son
Feature activation+0.000
cap
Token cap
Feature activation+0.000
ed
Tokened
Feature activation+0.000
-
Token-
Feature activation+0.000
cr
Tokencr
Feature activation+0.000
u
Tokenu
Feature activation+0.000
idi
Tokenidi
Feature activation+0.000
's
Token's
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+2.532
Far
Token Far
Feature activation+1.002
ia
Tokenia
Feature activation+2.922
,
Token,
Feature activation+0.077
said
Token said
Feature activation+0.000
that
Token that
Feature activation+0.000
with
Token with
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
T
TokenT
Feature activation+0.000
ravis
Tokenravis
Feature activation+0.000
's
Token's
Feature activation+0.000
uncle
Token uncle
Feature activation+0.000
Alexander
Token Alexander
Feature activation+1.139
migrated
Token migrated
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
territory
Token territory
Feature activation+0.000

INTERVAL 0.658 - 0.987
CONTAINS 0.003%

ics
Tokenics
Feature activation+0.000
.
Token.
Feature activation+0.000
Although
Token Although
Feature activation+0.000
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.000
's
Token's
Feature activation+0.722
approach
Token approach
Feature activation+0.000
to
Token to
Feature activation+0.000
education
Token education
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
Albert
Token Albert
Feature activation+0.000
idol
Token idol
Feature activation+0.000
ised
Tokenised
Feature activation+0.000
his
Token his
Feature activation+0.000
uncle
Token uncle
Feature activation+0.000
,
Token,
Feature activation+0.710
and
Token and
Feature activation+0.000
when
Token when
Feature activation+0.000
he
Token he
Feature activation+0.000
stayed
Token stayed
Feature activation+0.000
with
Token with
Feature activation+0.000
.
Token.
Feature activation+0.000
We
Token We
Feature activation+0.000
need
Token need
Feature activation+0.000
more
Token more
Feature activation+0.000
fathers
Token fathers
Feature activation+0.000
like
Token like
Feature activation+0.679
the
Token the
Feature activation+0.418
one
Token one
Feature activation+0.000
in
Token in
Feature activation+0.000
J
Token J
Feature activation+0.000
h
Tokenh
Feature activation+0.000
Dortmund
Token Dortmund
Feature activation+0.000
,"
Token,"
Feature activation+0.000
father
Token father
Feature activation+0.744
and
Token and
Feature activation+0.000
agent
Token agent
Feature activation+1.312
Ir
Token Ir
Feature activation+0.672
fan
Tokenfan
Feature activation+2.227
told
Token told
Feature activation+0.000
Kick
Token Kick
Feature activation+0.000
er
Tokener
Feature activation+0.000
Sport
Token Sport
Feature activation+0.000
her
Token her
Feature activation+0.000
late
Token late
Feature activation+0.000
husband
Token husband
Feature activation+0.661
,
Token,
Feature activation+0.841
former
Token former
Feature activation+0.251
president
Token president
Feature activation+0.956
Nest
Token Nest
Feature activation+0.000
or
Tokenor
Feature activation+0.717
Kir
Token Kir
Feature activation+0.000
ch
Tokench
Feature activation+0.000
ner
Tokenner
Feature activation+0.000

INTERVAL 0.329 - 0.658
CONTAINS 0.005%

,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
from
Token from
Feature activation+0.000
family
Token family
Feature activation+0.000
patriarch
Token patriarch
Feature activation+0.430
Ren
Token Ren
Feature activation+0.000
é
Tokené
Feature activation+1.069
Lind
Token Lind
Feature activation+0.175
em
Tokenem
Feature activation+0.000
ans
Tokenans
Feature activation+0.259
"
Token"
Feature activation+0.000
Gregory
Token Gregory
Feature activation+0.000
Mayer
Token Mayer
Feature activation+0.000
's
Token's
Feature activation+0.000
father
Token father
Feature activation+0.000
Greg
Token Greg
Feature activation+0.565
Mayer
Token Mayer
Feature activation+0.000
said
Token said
Feature activation+0.000
by
Token by
Feature activation+0.000
telephone
Token telephone
Feature activation+0.000
from
Token from
Feature activation+0.000
racing
Token racing
Feature activation+0.000
driver
Token driver
Feature activation+0.000
grandfather
Token grandfather
Feature activation+0.294
Francis
Token Francis
Feature activation+1.734
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.617
5
Token 5
Feature activation+0.564
th
Tokenth
Feature activation+0.721
Earl
Token Earl
Feature activation+1.006
Howe
Token Howe
Feature activation+0.856
.
Token.
Feature activation+0.000
raised
Token raised
Feature activation+0.000
him
Token him
Feature activation+0.000
ever
Token ever
Feature activation+0.000
since
Token since
Feature activation+0.000
his
Token his
Feature activation+0.000
parents
Token parents
Feature activation+0.332
had
Token had
Feature activation+0.264
died
Token died
Feature activation+0.000
.
Token.
Feature activation+0.000
For
Token For
Feature activation+0.000
years
Token years
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+3.045
Samuel
Token Samuel
Feature activation+2.667
Levi
Token Levi
Feature activation+2.779
Jos
Token Jos
Feature activation+0.000
ap
Tokenap
Feature activation+0.604
hat
Tokenhat
Feature activation+2.109
,
Token,
Feature activation+0.062
was
Token was
Feature activation+0.077
a
Token a
Feature activation+0.602
rabbi
Token rabbi
Feature activation+0.409

INTERVAL 0.000 - 0.329
CONTAINS 99.988%

another
Token another
Feature activation+0.000
independence
Token independence
Feature activation+0.000
referendum
Token referendum
Feature activation+0.000
is
Token is
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Scottish
Token Scottish
Feature activation+0.000
Government
Token Government
Feature activation+0.000
death
Token death
Feature activation+0.000
sentence
Token sentence
Feature activation+0.000
on
Token on
Feature activation+0.000
those
Token those
Feature activation+0.000
convicted
Token convicted
Feature activation+0.000
of
Token of
Feature activation+0.000
certain
Token certain
Feature activation+0.000
homosexual
Token homosexual
Feature activation+0.000
acts
Token acts
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Ay
TokenAy
Feature activation+0.000
,
Token,
Feature activation+0.000
check
Token check
Feature activation+0.000
out
Token out
Feature activation+0.000
my
Token my
Feature activation+0.000
monkey
Token monkey
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
locks
Tokenlocks
Feature activation+0.000
and
Token and
Feature activation+0.000
twisted
Token twisted
Feature activation+0.000
hair
Token hair
Feature activation+0.000
were
Token were
Feature activation+0.000
not
Token not
Feature activation+0.000
new
Token new
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
carried
Token carried
Feature activation+0.000
over
Token over
Feature activation+0.000
of
Token of
Feature activation+0.000
go
Token go
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
process
Token process
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Advertisement
TokenAdvertisement
Feature activation+0.000
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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