H10.10 top features

Top feature 0 in H10.10: (feature 6954)

TOP ACTIVATIONS
MAX = 9.037

wrestler
Token wrestler
Feature activation+0.000
and
Token and
Feature activation+0.000
mixed
Token mixed
Feature activation+0.000
martial
Token martial
Feature activation+0.000
artist
Token artist
Feature activation+0.000
.
Token.
Feature activation+9.037
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.908
B
TokenB
Feature activation+0.000
aut
Tokenaut
Feature activation+0.000
ista
Tokenista
Feature activation+0.000
this
Token this
Feature activation+1.005
,
Token,
Feature activation+5.200
the
Token the
Feature activation+5.709
report
Token report
Feature activation+0.000
criticized
Token criticized
Feature activation+7.446
the
Token the
Feature activation+8.660
foundation
Token foundation
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
promotion
Token promotion
Feature activation+0.000
bond
Token bond
Feature activation+0.000
'
Token'
Feature activation+3.083
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.229
She
TokenShe
Feature activation+0.000
said
Token said
Feature activation+8.654
they
Token they
Feature activation+0.000
decided
Token decided
Feature activation+3.828
to
Token to
Feature activation+0.000
adopt
Token adopt
Feature activation+3.574
him
Token him
Feature activation+0.000
County
Token County
Feature activation+0.000
Sheriff
Token Sheriff
Feature activation+0.000
's
Token's
Feature activation+0.010
Office
Token Office
Feature activation+0.000
Photo
Token Photo
Feature activation+0.000
:
Token:
Feature activation+8.518
B
Token B
Feature activation+0.609
ex
Tokenex
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
County
Token County
Feature activation+0.000
Sheriff
Token Sheriff
Feature activation+0.000
"
Token "
Feature activation+1.167
Senator
TokenSenator
Feature activation+1.270
Johnson
Token Johnson
Feature activation+0.000
and
Token and
Feature activation+0.399
Mr
Token Mr
Feature activation+7.057
.
Token.
Feature activation+8.417
B
Token B
Feature activation+0.000
lando
Tokenlando
Feature activation+0.000
conveyed
Token conveyed
Feature activation+0.000
their
Token their
Feature activation+0.000
commitment
Token commitment
Feature activation+0.000
eye
Token eye
Feature activation+0.000
on
Token on
Feature activation+7.250
.
Token.
Feature activation+4.682
As
TokenAs
Feature activation+4.492
far
Token far
Feature activation+1.955
as
Token as
Feature activation+8.152
control
Token control
Feature activation+0.000
,
Token,
Feature activation+6.407
B
Token B
Feature activation+0.000
urd
Tokenurd
Feature activation+0.000
i
Tokeni
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.302
It
TokenIt
Feature activation+0.000
also
Token also
Feature activation+0.000
accused
Token accused
Feature activation+7.383
the
Token the
Feature activation+8.009
foundation
Token foundation
Feature activation+0.000
of
Token of
Feature activation+0.000
undermining
Token undermining
Feature activation+0.297
sustainable
Token sustainable
Feature activation+0.000
,
Token,
Feature activation+0.000
polarization
Token polarization
Feature activation+0.000
)
Token)
Feature activation+0.000
or
Token or
Feature activation+0.000
inflation
Token inflation
Feature activation+0.000
,
Token,
Feature activation+3.979
the
Token the
Feature activation+7.891
B
Token B
Feature activation+0.000
ICE
TokenICE
Feature activation+0.000
P
TokenP
Feature activation+0.000
2
Token2
Feature activation+1.266
results
Token results
Feature activation+0.000
and
Token and
Feature activation+0.000
Recon
Token Recon
Feature activation+0.000
c
Tokenc
Feature activation+0.000
iliation
Tokeniliation
Feature activation+0.000
Commission
Token Commission
Feature activation+0.666
,
Token,
Feature activation+7.727
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+6.433
The
TokenThe
Feature activation+1.624
doctors
Token doctors
Feature activation+0.000
who
Token who
Feature activation+0.000
other
Token other
Feature activation+0.107
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.102
it
Token it
Feature activation+0.000
:
Token:
Feature activation+7.495
the
Token the
Feature activation+1.201
Jaguars
Token Jaguars
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
quarterback
Token quarterback
Feature activation+0.444
police
Token police
Feature activation+0.000
.
Token.
Feature activation+6.254
On
Token On
Feature activation+0.000
7
Token 7
Feature activation+0.000
September
Token September
Feature activation+0.360
1977
Token 1977
Feature activation+7.482
he
Token he
Feature activation+0.000
sustained
Token sustained
Feature activation+0.000
a
Token a
Feature activation+0.000
head
Token head
Feature activation+0.000
injury
Token injury
Feature activation+0.000
the
Token the
Feature activation+0.000
Israelis
Token Israelis
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Palestinians
Token Palestinians
Feature activation+0.000
,"
Token,"
Feature activation+7.467
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+1.970
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.860
to
Token to
Feature activation+1.537
this
Token this
Feature activation+1.005
,
Token,
Feature activation+5.200
the
Token the
Feature activation+5.709
report
Token report
Feature activation+0.000
criticized
Token criticized
Feature activation+7.446
the
Token the
Feature activation+8.660
foundation
Token foundation
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+2.434
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.302
It
TokenIt
Feature activation+0.000
also
Token also
Feature activation+0.000
accused
Token accused
Feature activation+7.383
the
Token the
Feature activation+8.009
foundation
Token foundation
Feature activation+0.000
of
Token of
Feature activation+0.000
undermining
Token undermining
Feature activation+0.297
sustainable
Token sustainable
Feature activation+0.000
to
Token to
Feature activation+0.000
you
Token you
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dan
TokenDan
Feature activation+7.319
B
Token B
Feature activation+0.000
oul
Tokenoul
Feature activation+0.000
ton
Tokenton
Feature activation+0.000
:
Token:
Feature activation+0.000
Absolutely
Token Absolutely
Feature activation+0.000
food
Token food
Feature activation+0.000
,"
Token,"
Feature activation+5.625
the
Token the
Feature activation+0.000
finance
Token finance
Feature activation+0.000
community
Token community
Feature activation+0.000
told
Token told
Feature activation+7.292
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+4.538
the
Token the
Feature activation+0.000
group
Token group
Feature activation+0.000
be
Token be
Feature activation+0.985
worth
Token worth
Feature activation+0.000
keeping
Token keeping
Feature activation+3.577
an
Token an
Feature activation+0.000
eye
Token eye
Feature activation+0.000
on
Token on
Feature activation+7.250
.
Token.
Feature activation+4.682
As
TokenAs
Feature activation+4.492
far
Token far
Feature activation+1.955
as
Token as
Feature activation+8.152
control
Token control
Feature activation+0.000
from
Token from
Feature activation+0.009
over
Token over
Feature activation+0.000
use
Tokenuse
Feature activation+0.000
.
Token.
Feature activation+5.684
Nevertheless
Token Nevertheless
Feature activation+0.590
,
Token,
Feature activation+7.196
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.985
worth
Token worth
Feature activation+0.000
keeping
Token keeping
Feature activation+3.577
the
Token the
Feature activation+2.615
story
Token story
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000
.
Token.
Feature activation+3.643
The
Token The
Feature activation+7.067
measurement
Token measurement
Feature activation+0.000
of
Token of
Feature activation+2.391
polarization
Token polarization
Feature activation+0.000
is
Token is
Feature activation+0.000
significantly
Token significantly
Feature activation+0.000
.
Token.
Feature activation+4.416
"
Token "
Feature activation+1.167
Senator
TokenSenator
Feature activation+1.270
Johnson
Token Johnson
Feature activation+0.000
and
Token and
Feature activation+0.399
Mr
Token Mr
Feature activation+7.057
.
Token.
Feature activation+8.417
B
Token B
Feature activation+0.000
lando
Tokenlando
Feature activation+0.000
conveyed
Token conveyed
Feature activation+0.000
their
Token their
Feature activation+0.000

Top DFA by src position
MAX = 9.634

)
Token)
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.011
Top resid features:
David
TokenDavid
Feature activation-0.079
Top resid features:
Michael
Token Michael
Feature activation-0.032
Top resid features:
B
Token B
Feature activation+9.634
Top resid features:
aut
Tokenaut
Feature activation+0.031
Top resid features:
ista
Tokenista
Feature activation+0.014
Top resid features:
Jr
Token Jr
Feature activation-0.061
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
(
Token (
Feature activation-0.001
Top resid features:
global
Token global
Feature activation-0.002
Top resid features:
poverty
Token poverty
Feature activation+0.011
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
accused
Token accused
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
B
Token B
Feature activation+9.277
Top resid features:
MG
TokenMG
Feature activation+0.261
Top resid features:
F
TokenF
Feature activation-0.018
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
prof
Token prof
Feature activation-0.001
Top resid features:
iting
Tokeniting
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Mrs
TokenMrs
Feature activation-0.002
Top resid features:
Hunt
Token Hunt
Feature activation+0.001
Top resid features:
described
Token described
Feature activation-0.002
Top resid features:
B
Token B
Feature activation+9.248
Top resid features:
isc
Tokenisc
Feature activation+0.079
Top resid features:
uit
Tokenuit
Feature activation+0.066
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
who
Token who
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
warrant
Token warrant
Feature activation-0.000
Top resid features:
affidavit
Token affidavit
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Photo
Token Photo
Feature activation+0.004
Top resid features:
:
Token:
Feature activation-0.017
Top resid features:
B
Token B
Feature activation+8.729
Top resid features:
ex
Tokenex
Feature activation+0.486
Top resid features:
ar
Tokenar
Feature activation+0.019
Top resid features:
County
Token County
Feature activation-0.008
Top resid features:
Sheriff
Token Sheriff
Feature activation-0.003
Top resid features:
's
Token's
Feature activation-0.003
Top resid features:
chief
Token chief
Feature activation-0.024
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
staff
Token staff
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
Tony
Token Tony
Feature activation-0.065
Top resid features:
B
Token B
Feature activation+8.780
Top resid features:
lando
Tokenlando
Feature activation+0.174
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
she
Token she
Feature activation-0.000
Top resid features:
already
Token already
Feature activation-0.001
Top resid features:
had
Token had
Feature activation-0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
become
Token become
Feature activation-0.001
Top resid features:
an
Token an
Feature activation-0.000
Top resid features:
issue
Token issue
Feature activation+0.001
Top resid features:
for
Token for
Feature activation+0.003
Top resid features:
B
Token B
Feature activation+8.736
Top resid features:
urd
Tokenurd
Feature activation+0.114
Top resid features:
i
Tokeni
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.005
Top resid features:
since
Token since
Feature activation+0.002
Top resid features:
global
Token global
Feature activation-0.000
Top resid features:
poverty
Token poverty
Feature activation+0.007
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
accused
Token accused
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
B
Token B
Feature activation+8.664
Top resid features:
MG
TokenMG
Feature activation+0.243
Top resid features:
F
TokenF
Feature activation-0.018
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
prof
Token prof
Feature activation+0.001
Top resid features:
iting
Tokeniting
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
which
Token which
Feature activation+0.002
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
why
Token why
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.010
Top resid features:
B
Token B
Feature activation+8.361
Top resid features:
ICE
TokenICE
Feature activation+0.178
Top resid features:
P
TokenP
Feature activation+0.011
Top resid features:
2
Token2
Feature activation-0.027
Top resid features:
results
Token results
Feature activation-0.032
Top resid features:
are
Token are
Feature activation+0.002
Top resid features:
they
Token they
Feature activation-0.000
Top resid features:
could
Token could
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
B
TokenB
Feature activation+5.144
Top resid features:
iko
Tokeniko
Feature activation+0.136
Top resid features:
was
Token was
Feature activation+0.004
Top resid features:
detained
Token detained
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.006
Top resid features:
interrogated
Token interrogated
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
3
Token3
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Blake
Token Blake
Feature activation-0.089
Top resid features:
B
Token B
Feature activation+7.875
Top resid features:
ort
Tokenort
Feature activation+0.118
Top resid features:
les
Tokenles
Feature activation-0.021
Top resid features:
struggled
Token struggled
Feature activation-0.015
Top resid features:
Sunday
Token Sunday
Feature activation+0.022
Top resid features:
âĢ¦
Token âĢ¦
Feature activation+0.026
Top resid features:
they
Token they
Feature activation-0.000
Top resid features:
could
Token could
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.041
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.043
Top resid features:
B
TokenB
Feature activation+5.161
Top resid features:
iko
Tokeniko
Feature activation+0.053
Top resid features:
was
Token was
Feature activation+0.012
Top resid features:
detained
Token detained
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.021
Top resid features:
interrogated
Token interrogated
Feature activation+0.008
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Mar
TokenMar
Feature activation-0.295
Top resid features:
wan
Tokenwan
Feature activation-0.015
Top resid features:
B
Token B
Feature activation+7.965
Top resid features:
ish
Tokenish
Feature activation+0.209
Top resid features:
ara
Tokenara
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
Al
Token Al
Feature activation-0.019
Top resid features:
Jazeera
Token Jazeera
Feature activation-0.002
Top resid features:
global
Token global
Feature activation-0.002
Top resid features:
poverty
Token poverty
Feature activation+0.009
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
accused
Token accused
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.014
Top resid features:
B
Token B
Feature activation+7.671
Top resid features:
MG
TokenMG
Feature activation+0.360
Top resid features:
F
TokenF
Feature activation-0.025
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
prof
Token prof
Feature activation-0.001
Top resid features:
iting
Tokeniting
Feature activation-0.000
Top resid features:
global
Token global
Feature activation+0.001
Top resid features:
poverty
Token poverty
Feature activation+0.005
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
accused
Token accused
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.019
Top resid features:
B
Token B
Feature activation+7.577
Top resid features:
MG
TokenMG
Feature activation+0.346
Top resid features:
F
TokenF
Feature activation-0.024
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
prof
Token prof
Feature activation-0.002
Top resid features:
iting
Tokeniting
Feature activation-0.000
Top resid features:
wrong
Token wrong
Feature activation+0.012
Top resid features:
âĢ
TokenâĢ
Feature activation+0.011
Top resid features:
Ŀ
TokenĿ
Feature activation+0.001
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.013
Top resid features:
Dan
Token Dan
Feature activation-0.044
Top resid features:
B
Token B
Feature activation+7.628
Top resid features:
oul
Tokenoul
Feature activation+0.197
Top resid features:
ton
Tokenton
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
Ċ
TokenĊ
Feature activation+0.039
Top resid features:
People
TokenPeople
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
According
Token According
Feature activation+0.012
Top resid features:
to
Token to
Feature activation-0.003
Top resid features:
Ari
Token Ari
Feature activation-0.006
Top resid features:
ane
Tokenane
Feature activation+0.024
Top resid features:
B
Token B
Feature activation+7.682
Top resid features:
atter
Tokenatter
Feature activation+0.051
Top resid features:
berry
Tokenberry
Feature activation-0.037
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
who
Token who
Feature activation+0.005
Top resid features:
spoke
Token spoke
Feature activation-0.004
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
become
Token become
Feature activation-0.000
Top resid features:
an
Token an
Feature activation-0.000
Top resid features:
issue
Token issue
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
B
Token B
Feature activation+7.676
Top resid features:
urd
Tokenurd
Feature activation+0.215
Top resid features:
i
Tokeni
Feature activation+0.070
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
and
Token and
Feature activation+0.013
Top resid features:
since
Token since
Feature activation+0.008
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
become
Token become
Feature activation+0.001
Top resid features:
an
Token an
Feature activation-0.000
Top resid features:
issue
Token issue
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.003
Top resid features:
B
Token B
Feature activation+7.560
Top resid features:
urd
Tokenurd
Feature activation+0.286
Top resid features:
i
Tokeni
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
and
Token and
Feature activation+0.015
Top resid features:
since
Token since
Feature activation+0.016
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.001
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
why
Token why
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
B
Token B
Feature activation+4.587
Top resid features:
ICE
TokenICE
Feature activation+0.081
Top resid features:
P
TokenP
Feature activation+0.007
Top resid features:
2
Token2
Feature activation+0.001
Top resid features:
results
Token results
Feature activation-0.014
Top resid features:
are
Token are
Feature activation+0.001
Top resid features:
chief
Token chief
Feature activation-0.018
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
staff
Token staff
Feature activation+0.013
Top resid features:
,
Token,
Feature activation-0.002
Top resid features:
Tony
Token Tony
Feature activation-0.048
Top resid features:
B
Token B
Feature activation+7.537
Top resid features:
lando
Tokenlando
Feature activation+0.058
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
she
Token she
Feature activation-0.000
Top resid features:
already
Token already
Feature activation-0.000
Top resid features:
had
Token had
Feature activation-0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.04

Head 2: 0.08

Head 3: 0.03

Head 4: 0.02

Head 5: 0.02

Head 6: 0.04

Head 7: 0.11

Head 8: 0.02

Head 9: 0.04

Head 10: 0.54

Head 11: 0.02

Positive logits

B10.61

B8.43

b7.12

b6.01

Bs5.70

BS5.10

BA4.98

BC4.64

BIP4.63

BN4.61

BI4.49

BS4.46

Bib4.38

BG4.32

BA4.27

BI4.20

Ba4.10

Bis4.06

Bor4.02

Boll4.00

Negative logits

haw-3.15

tle-3.06

princ-2.95

Sov-2.84

XD-2.84

zone-2.83

nces-2.78

glers-2.77

lake-2.74

ascript-2.65

qualified-2.61

ht-2.60

arty-2.58

hran-2.58

hua-2.52

arag-2.52

warr-2.52

newsp-2.51

lan-2.50

hawk-2.50

INTERVAL 8.134 - 9.037
CONTAINS 0.001%

bond
Token bond
Feature activation+0.000
'
Token'
Feature activation+3.083
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.229
She
TokenShe
Feature activation+0.000
said
Token said
Feature activation+8.654
they
Token they
Feature activation+0.000
decided
Token decided
Feature activation+3.828
to
Token to
Feature activation+0.000
adopt
Token adopt
Feature activation+3.574
him
Token him
Feature activation+0.000
this
Token this
Feature activation+1.005
,
Token,
Feature activation+5.200
the
Token the
Feature activation+5.709
report
Token report
Feature activation+0.000
criticized
Token criticized
Feature activation+7.446
the
Token the
Feature activation+8.660
foundation
Token foundation
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
promotion
Token promotion
Feature activation+0.000
"
Token "
Feature activation+1.167
Senator
TokenSenator
Feature activation+1.270
Johnson
Token Johnson
Feature activation+0.000
and
Token and
Feature activation+0.399
Mr
Token Mr
Feature activation+7.057
.
Token.
Feature activation+8.417
B
Token B
Feature activation+0.000
lando
Tokenlando
Feature activation+0.000
conveyed
Token conveyed
Feature activation+0.000
their
Token their
Feature activation+0.000
commitment
Token commitment
Feature activation+0.000
wrestler
Token wrestler
Feature activation+0.000
and
Token and
Feature activation+0.000
mixed
Token mixed
Feature activation+0.000
martial
Token martial
Feature activation+0.000
artist
Token artist
Feature activation+0.000
.
Token.
Feature activation+9.037
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.908
B
TokenB
Feature activation+0.000
aut
Tokenaut
Feature activation+0.000
ista
Tokenista
Feature activation+0.000
County
Token County
Feature activation+0.000
Sheriff
Token Sheriff
Feature activation+0.000
's
Token's
Feature activation+0.010
Office
Token Office
Feature activation+0.000
Photo
Token Photo
Feature activation+0.000
:
Token:
Feature activation+8.518
B
Token B
Feature activation+0.609
ex
Tokenex
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
County
Token County
Feature activation+0.000
Sheriff
Token Sheriff
Feature activation+0.000

INTERVAL 7.230 - 8.134
CONTAINS 0.001%

polarization
Token polarization
Feature activation+0.000
)
Token)
Feature activation+0.000
or
Token or
Feature activation+0.000
inflation
Token inflation
Feature activation+0.000
,
Token,
Feature activation+3.979
the
Token the
Feature activation+7.891
B
Token B
Feature activation+0.000
ICE
TokenICE
Feature activation+0.000
P
TokenP
Feature activation+0.000
2
Token2
Feature activation+1.266
results
Token results
Feature activation+0.000
other
Token other
Feature activation+0.107
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.102
it
Token it
Feature activation+0.000
:
Token:
Feature activation+7.495
the
Token the
Feature activation+1.201
Jaguars
Token Jaguars
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
quarterback
Token quarterback
Feature activation+0.444
the
Token the
Feature activation+0.000
Israelis
Token Israelis
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Palestinians
Token Palestinians
Feature activation+0.000
,"
Token,"
Feature activation+7.467
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+1.970
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.860
.
Token.
Feature activation+2.434
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.302
It
TokenIt
Feature activation+0.000
also
Token also
Feature activation+0.000
accused
Token accused
Feature activation+7.383
the
Token the
Feature activation+8.009
foundation
Token foundation
Feature activation+0.000
of
Token of
Feature activation+0.000
undermining
Token undermining
Feature activation+0.297
sustainable
Token sustainable
Feature activation+0.000
to
Token to
Feature activation+0.000
you
Token you
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dan
TokenDan
Feature activation+7.319
B
Token B
Feature activation+0.000
oul
Tokenoul
Feature activation+0.000
ton
Tokenton
Feature activation+0.000
:
Token:
Feature activation+0.000
Absolutely
Token Absolutely
Feature activation+0.000

INTERVAL 6.326 - 7.230
CONTAINS 0.002%

.
Token.
Feature activation+4.682
As
TokenAs
Feature activation+4.492
far
Token far
Feature activation+1.955
as
Token as
Feature activation+8.152
control
Token control
Feature activation+0.000
,
Token,
Feature activation+6.407
B
Token B
Feature activation+0.000
urd
Tokenurd
Feature activation+0.000
i
Tokeni
Feature activation+0.000
obviously
Token obviously
Feature activation+0.000
had
Token had
Feature activation+0.000
TOR
TokenTOR
Feature activation+0.000
BA
TokenBA
Feature activation+0.323
(
Token (
Feature activation+0.000
Toronto
TokenToronto
Feature activation+0.593
Off
Token Off
Feature activation+0.000
road
Tokenroad
Feature activation+6.845
B
Token B
Feature activation+0.396
icy
Tokenicy
Feature activation+0.000
cling
Tokencling
Feature activation+1.002
Association
Token Association
Feature activation+0.000
)
Token)
Feature activation+0.070
in
Token in
Feature activation+1.005
B
Token B
Feature activation+0.397
izz
Tokenizz
Feature activation+0.228
,
Token,
Feature activation+5.175
B
Token B
Feature activation+0.549
umble
Tokenumble
Feature activation+6.813
expects
Token expects
Feature activation+0.863
to
Token to
Feature activation+0.000
see
Token see
Feature activation+1.361
the
Token the
Feature activation+1.312
same
Token same
Feature activation+0.000
c
Tokenc
Feature activation+0.000
iliation
Tokeniliation
Feature activation+0.000
Commission
Token Commission
Feature activation+0.666
,
Token,
Feature activation+7.727
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+6.433
The
TokenThe
Feature activation+1.624
doctors
Token doctors
Feature activation+0.000
who
Token who
Feature activation+0.000
examined
Token examined
Feature activation+6.728
him
Token him
Feature activation+0.000
the
Token the
Feature activation+2.615
story
Token story
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000
.
Token.
Feature activation+3.643
The
Token The
Feature activation+7.067
measurement
Token measurement
Feature activation+0.000
of
Token of
Feature activation+2.391
polarization
Token polarization
Feature activation+0.000
is
Token is
Feature activation+0.000
significantly
Token significantly
Feature activation+0.000

INTERVAL 5.422 - 6.326
CONTAINS 0.004%

)
Token)
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
alloy
Token alloy
Feature activation+0.000
(
Token (
Feature activation+6.130
80
Token80
Feature activation+0.000
%
Token%
Feature activation+0.000
copper
Token copper
Feature activation+0.000
/
Token /
Feature activation+0.000
20
Token 20
Feature activation+0.000
year
Tokenyear
Feature activation+0.097
transportation
Token transportation
Feature activation+0.000
plan
Token plan
Feature activation+0.000
that
Token that
Feature activation+1.409
will
Token will
Feature activation+0.000
cost
Token cost
Feature activation+5.853
$
Token $
Feature activation+0.000
2
Token2
Feature activation+0.000
.
Token.
Feature activation+0.000
5
Token5
Feature activation+0.000
billion
Token billion
Feature activation+0.000
picture
Token picture
Feature activation+0.000
!
Token!
Feature activation+0.340
Courtesy
Token Courtesy
Feature activation+0.157
of
Token of
Feature activation+0.935
BIG
Token BIG
Feature activation+0.071
-
Token -
Feature activation+5.549
B
Token B
Feature activation+0.000
jar
Tokenjar
Feature activation+0.000
ke
Tokenke
Feature activation+0.000
Ing
Token Ing
Feature activation+0.000
els
Tokenels
Feature activation+0.000
easier
Token easier
Feature activation+0.000
for
Token for
Feature activation+3.855
designers
Token designers
Feature activation+0.000
.
Token.
Feature activation+2.832
Now
Token Now
Feature activation+4.824
,
Token,
Feature activation+5.574
with
Token with
Feature activation+2.650
Creative
Token Creative
Feature activation+0.000
Sync
TokenSync
Feature activation+0.000
,
Token,
Feature activation+4.864
they
Token they
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
car
Token car
Feature activation+0.000
with
Token with
Feature activation+0.000
me
Token me
Feature activation+0.000
,"
Token,"
Feature activation+6.246
offered
Token offered
Feature activation+5.165
B
Token B
Feature activation+0.063
ann
Tokenann
Feature activation+0.000
an
Tokenan
Feature activation+0.000
.
Token.
Feature activation+2.395

INTERVAL 4.519 - 5.422
CONTAINS 0.007%

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
what
Token what
Feature activation+1.944
sets
Token sets
Feature activation+5.362
each
Token each
Feature activation+1.428
belt
Token belt
Feature activation+0.000
level
Token level
Feature activation+0.000
apart
Token apart
Feature activation+0.000
from
Token from
Feature activation+0.278
B
Token B
Feature activation+0.000
aid
Tokenaid
Feature activation+0.000
u
Tokenu
Feature activation+0.171
said
Token said
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.365
Elect
TokenElect
Feature activation+0.000
ronic
Tokenronic
Feature activation+0.000
chop
Token chop
Feature activation+0.000
sticks
Tokensticks
Feature activation+0.000
that
Token that
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
Feature activation+0.000
.
Token.
Feature activation+0.000
government
Token government
Feature activation+0.000
to
Token to
Feature activation+0.000
charge
Token charge
Feature activation+5.350
a
Token a
Feature activation+1.331
"
Token "
Feature activation+0.504
fair
Tokenfair
Feature activation+0.000
price
Token price
Feature activation+0.000
for
Token for
Feature activation+4.139
B
Token B
Feature activation+0.215
umble
Tokenumble
Feature activation+4.065
statement
Token statement
Feature activation+0.000
.
Token.
Feature activation+1.653
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.590
Image
TokenImage
Feature activation+0.000
:
Token:
Feature activation+5.778
b
Token b
Feature activation+0.000
umble
Tokenumble
Feature activation+2.766
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+1.717
groom
Token groom
Feature activation+2.097
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
father
Token father
Feature activation+4.840
went
Token went
Feature activation+0.000
to
Token to
Feature activation+0.667
Bans
Token Bans
Feature activation+0.000
d
Tokend
Feature activation+0.000
ih
Tokenih
Feature activation+0.000

INTERVAL 3.615 - 4.519
CONTAINS 0.011%

keeping
Token keeping
Feature activation+3.577
an
Token an
Feature activation+0.000
eye
Token eye
Feature activation+0.000
on
Token on
Feature activation+7.250
.
Token.
Feature activation+4.682
As
TokenAs
Feature activation+4.492
far
Token far
Feature activation+1.955
as
Token as
Feature activation+8.152
control
Token control
Feature activation+0.000
,
Token,
Feature activation+6.407
B
Token B
Feature activation+0.000
B
Token B
Feature activation+0.160
anc
Tokenanc
Feature activation+0.000
or
Tokenor
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
supporting
Token supporting
Feature activation+4.068
us
Token us
Feature activation+0.000
with
Token with
Feature activation+1.278
product
Token product
Feature activation+0.000
development
Token development
Feature activation+0.000
guidance
Token guidance
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+2.780
the
Token the
Feature activation+0.287
company
Token company
Feature activation+0.000
tweeted
Token tweeted
Feature activation+0.000
.
Token.
Feature activation+4.433
However
Token However
Feature activation+3.673
,
Token,
Feature activation+5.806
the
Token the
Feature activation+0.909
only
Token only
Feature activation+0.849
businesses
Token businesses
Feature activation+0.306
foreign
Token foreign
Feature activation+0.000
policy
Token policy
Feature activation+0.000
at
Token at
Feature activation+0.355
that
Token that
Feature activation+0.000
point
Token point
Feature activation+0.000
."
Token."
Feature activation+4.038
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.793
V
TokenV
Feature activation+0.000
nes
Tokennes
Feature activation+0.000
he
Tokenhe
Feature activation+0.000
,"
Token,"
Feature activation+5.696
reads
Token reads
Feature activation+6.672
an
Token an
Feature activation+3.171
official
Token official
Feature activation+5.206
B
Token B
Feature activation+0.215
umble
Tokenumble
Feature activation+4.065
statement
Token statement
Feature activation+0.000
.
Token.
Feature activation+1.653
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.590
Image
TokenImage
Feature activation+0.000

INTERVAL 2.711 - 3.615
CONTAINS 0.019%

to
Token to
Feature activation+0.100
the
Token the
Feature activation+0.000
lawsuit
Token lawsuit
Feature activation+0.000
.
Token.
Feature activation+1.899
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.133
B
TokenB
Feature activation+0.000
TH
TokenTH
Feature activation+0.000
HM
TokenHM
Feature activation+0.414
Berkeley
Token Berkeley
Feature activation+0.000
LLC
Token LLC
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+1.936
a
Token a
Feature activation+2.129
Cabinet
Token Cabinet
Feature activation+0.000
paper
Token paper
Feature activation+0.000
said
Token said
Feature activation+2.952
there
Token there
Feature activation+0.000
were
Token were
Feature activation+0.000
concerns
Token concerns
Feature activation+0.274
multinational
Token multinational
Feature activation+0.000
s
Tokens
Feature activation+0.000
sv
Tokensv
Feature activation+0.000
FROM
Token FROM
Feature activation+0.000
(
Token (
Feature activation+0.000
SELECT
Token SELECT
Feature activation+0.000
cart
Token cart
Feature activation+0.000
od
Tokenod
Feature activation+3.206
b
Tokenb
Feature activation+0.117
_
Token_
Feature activation+0.000
id
Tokenid
Feature activation+0.000
,
Token ,
Feature activation+0.000
name
Token name
Feature activation+0.000
the
Token the
Feature activation+1.079
video
Token video
Feature activation+0.000
.
Token.
Feature activation+0.520
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.307
The
TokenThe
Feature activation+2.760
B
Token B
Feature activation+0.000
TS
TokenTS
Feature activation+0.330
video
Token video
Feature activation+0.000
colours
Token colours
Feature activation+0.000
look
Token look
Feature activation+0.000
a
Token a
Feature activation+0.000
regular
Token regular
Feature activation+0.077
rings
Token rings
Feature activation+0.000
ide
Tokenide
Feature activation+0.000
fixture
Token fixture
Feature activation+0.000
at
Token at
Feature activation+2.929
the
Token the
Feature activation+3.706
fights
Token fights
Feature activation+0.000
,'
Token,'
Feature activation+0.000
Mc
Token Mc
Feature activation+0.000
P
TokenP
Feature activation+0.000

INTERVAL 1.807 - 2.711
CONTAINS 0.034%

It
Token It
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
time
Token time
Feature activation+0.760
the
Token the
Feature activation+1.825
group
Token group
Feature activation+0.000
had
Token had
Feature activation+0.000
experienced
Token experienced
Feature activation+0.000
such
Token such
Feature activation+0.000
flag
Token flag
Feature activation+0.000
looking
Token looking
Feature activation+0.000
for
Token for
Feature activation+0.026
a
Token a
Feature activation+0.106
new
Token new
Feature activation+0.138
home
Token home
Feature activation+0.000
at
Token at
Feature activation+2.344
B
Token B
Feature activation+0.000
atter
Tokenatter
Feature activation+0.000
sea
Tokensea
Feature activation+0.482
,
Token,
Feature activation+2.090
but
Token but
Feature activation+2.958
her
Token her
Feature activation+0.000
decision
Token decision
Feature activation+0.000
.
Token.
Feature activation+1.613
Later
TokenLater
Feature activation+0.684
,
Token,
Feature activation+1.717
groom
Token groom
Feature activation+2.097
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
father
Token father
Feature activation+4.840
went
Token went
Feature activation+0.000
50
Token 50
Feature activation+0.000
and
Token and
Feature activation+0.000
150
Token 150
Feature activation+0.000
pages
Token pages
Feature activation+0.000
,
Token,
Feature activation+0.000
making
Token making
Feature activation+2.007
for
Token for
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
4
Token 4
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
approximately
Token approximately
Feature activation+0.000
25
Token 25
Feature activation+0.000
minutes
Token minutes
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
until
Token until
Feature activation+2.467
the
Token the
Feature activation+3.164
b
Token b
Feature activation+0.000
uns
Tokenuns
Feature activation+0.106
are
Token are
Feature activation+0.000
golden
Token golden
Feature activation+0.000

INTERVAL 0.904 - 1.807
CONTAINS 0.088%

status
Tokenstatus
Feature activation+0.000
=
Token=
Feature activation+0.000
*
Token*
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
ad
Tokenad
Feature activation+1.631
b
Tokenb
Feature activation+0.000
shell
Token shell
Feature activation+0.000
settings
Token settings
Feature activation+0.000
put
Token put
Feature activation+0.000
global
Token global
Feature activation+0.000
palace
Token palace
Feature activation+0.000
.[
Token.[
Feature activation+0.000
3
Token3
Feature activation+0.000
][
Token][
Feature activation+0.000
4
Token4
Feature activation+0.000
]
Token]
Feature activation+1.248
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.522
Design
TokenDesign
Feature activation+0.000
and
Token and
Feature activation+0.000
layout
Token layout
Feature activation+0.000
'
Token '
Feature activation+0.000
not
Tokennot
Feature activation+0.000
qualified
Token qualified
Feature activation+0.000
'
Token'
Feature activation+0.000
to
Token to
Feature activation+0.000
make
Token make
Feature activation+1.428
call
Token call
Feature activation+0.000
on
Token on
Feature activation+3.935
trust
Token trust
Feature activation+0.000
in
Token in
Feature activation+0.830
tax
Token tax
Feature activation+0.000
as
Token as
Feature activation+0.094
it
Token it
Feature activation+0.000
could
Token could
Feature activation+0.000
not
Token not
Feature activation+0.000
accept
Token accept
Feature activation+1.236
that
Token that
Feature activation+1.593
stip
Token stip
Feature activation+0.000
ulation
Tokenulation
Feature activation+0.000
.
Token.
Feature activation+0.953
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.052
-
Token-
Feature activation+0.000
f
Tokenf
Feature activation+0.000
ifty
Tokenifty
Feature activation+0.000
.
Token.
Feature activation+0.084
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.184
A
TokenA
Feature activation+0.000
kar
Tokenkar
Feature activation+0.000
and
Token and
Feature activation+0.000
colleagues
Token colleagues
Feature activation+0.000
surveyed
Token surveyed
Feature activation+0.000

INTERVAL 0.000 - 0.904
CONTAINS 99.834%

gent
Tokengent
Feature activation+0.000
technology
Token technology
Feature activation+0.000
.
Token.
Feature activation+0.000
Using
Token Using
Feature activation+0.000
technology
Token technology
Feature activation+0.000
,
Token,
Feature activation+0.000
businesses
Token businesses
Feature activation+0.000
can
Token can
Feature activation+0.000
reach
Token reach
Feature activation+0.000
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
extra
Token extra
Feature activation+0.000
charges
Token charges
Feature activation+0.000
on
Token on
Feature activation+0.000
firms
Token firms
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
result
Token result
Feature activation+0.000
of
Token of
Feature activation+0.000
new
Token new
Feature activation+0.000
rules
Token rules
Feature activation+0.000
or
Token or
Feature activation+0.000
It
Token It
Feature activation+0.000
's
Token's
Feature activation+0.000
possible
Token possible
Feature activation+0.000
that
Token that
Feature activation+0.000
he
Token he
Feature activation+0.000
then
Token then
Feature activation+0.000
contributed
Token contributed
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
implementation
Token implementation
Feature activation+0.000
of
Token of
Feature activation+0.000
commissioner
Token commissioner
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
Nuclear
Token Nuclear
Feature activation+0.000
Regulatory
Token Regulatory
Feature activation+0.000
Commission
Token Commission
Feature activation+0.000
during
Token during
Feature activation+0.000
the
Token the
Feature activation+0.000
Three
Token Three
Feature activation+0.000
Mile
Token Mile
Feature activation+0.000
Island
Token Island
Feature activation+0.000
of
Token of
Feature activation+0.000
hacking
Token hacking
Feature activation+0.000
or
Token or
Feature activation+0.000
voter
Token voter
Feature activation+0.000
fraud
Token fraud
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
former
Token former
Feature activation+0.000
of
Token of
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
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 H10.10: (feature 4910)

TOP ACTIVATIONS
MAX = 8.593

Cup
Token Cup
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
mountain
Token mountain
Feature activation+0.000
climbing
Token climbing
Feature activation+0.000
,
Token,
Feature activation+8.593
canoe
Token canoe
Feature activation+0.000
ing
Tokening
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
even
Token even
Feature activation+0.000
a
Token a
Feature activation+0.000
Sea
Token Sea
Feature activation+0.000
-
Token-
Feature activation+0.000
D
TokenD
Feature activation+0.000
oo
Tokenoo
Feature activation+0.000
,
Token,
Feature activation+8.478
Kimmel
Token Kimmel
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.110
what
Token what
Feature activation+2.081
which
Token which
Feature activation+0.649
was
Token was
Feature activation+0.000
24
Token 24
Feature activation+0.000
th
Tokenth
Feature activation+0.103
on
Token on
Feature activation+3.758
the
Token the
Feature activation+8.115
P
Token P
Feature activation+0.138
GA
TokenGA
Feature activation+0.000
Tour
Token Tour
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
revert
Token revert
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
mean
Token mean
Feature activation+0.000
and
Token and
Feature activation+7.508
for
Token for
Feature activation+7.966
P
Token P
Feature activation+0.000
omin
Tokenomin
Feature activation+0.000
ville
Tokenville
Feature activation+0.000
to
Token to
Feature activation+0.000
eclipse
Token eclipse
Feature activation+3.046
their
Token their
Feature activation+0.000
course
Token course
Feature activation+0.000
work
Token work
Feature activation+0.000
.
Token.
Feature activation+3.245
Clearly
Token Clearly
Feature activation+5.846
,
Token,
Feature activation+7.950
a
Token a
Feature activation+1.186
$
Token $
Feature activation+0.032
50
Token50
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.337
.
Token.
Feature activation+2.882
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.143
But
TokenBut
Feature activation+7.171
backers
Token backers
Feature activation+0.339
of
Token of
Feature activation+7.560
the
Token the
Feature activation+3.746
project
Token project
Feature activation+0.000
argue
Token argue
Feature activation+3.787
such
Token such
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
to
Token to
Feature activation+0.000
revert
Token revert
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
mean
Token mean
Feature activation+0.000
and
Token and
Feature activation+7.508
for
Token for
Feature activation+7.966
P
Token P
Feature activation+0.000
omin
Tokenomin
Feature activation+0.000
ville
Tokenville
Feature activation+0.000
to
Token to
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
with
Token with
Feature activation+7.280
P
Token P
Feature activation+0.000
ire
Tokenire
Feature activation+0.000
lli
Tokenlli
Feature activation+0.000
.
Token.
Feature activation+2.086
The
Token The
Feature activation+1.347
,
Token,
Feature activation+0.000
was
Token was
Feature activation+0.000
flown
Token flown
Feature activation+0.000
by
Token by
Feature activation+0.000
helicopter
Token helicopter
Feature activation+0.000
to
Token to
Feature activation+7.242
a
Token a
Feature activation+0.721
jail
Token jail
Feature activation+0.000
in
Token in
Feature activation+6.216
the
Token the
Feature activation+2.659
nearby
Token nearby
Feature activation+0.590
million
Token million
Feature activation+0.000
articles
Token articles
Feature activation+0.000
.
Token.
Feature activation+2.882
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.143
But
TokenBut
Feature activation+7.171
backers
Token backers
Feature activation+0.339
of
Token of
Feature activation+7.560
the
Token the
Feature activation+3.746
project
Token project
Feature activation+0.000
argue
Token argue
Feature activation+3.787
in
Token in
Feature activation+0.000
Copper
Token Copper
Feature activation+0.000
Mountain
Token Mountain
Feature activation+0.000
,
Token,
Feature activation+0.000
Colorado
Token Colorado
Feature activation+0.000
.
Token.
Feature activation+7.048
P
Token P
Feature activation+0.000
urdy
Tokenurdy
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
a
Token a
Feature activation+0.000
ways
Tokenways
Feature activation+0.000
are
Token are
Feature activation+0.000
back
Token back
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Wade
Token Wade
Feature activation+0.135
-
Token-
Feature activation+7.023
P
TokenP
Feature activation+0.000
ent
Tokenent
Feature activation+0.000
el
Tokenel
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
night
Token night
Feature activation+0.000
.
Token.
Feature activation+0.614
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.809
From
TokenFrom
Feature activation+6.978
P
Token P
Feature activation+0.154
aks
Tokenaks
Feature activation+0.000
ong
Tokenong
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+1.728
a
Token a
Feature activation+0.000
bank
Token bank
Feature activation+0.000
holiday
Token holiday
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
St
Token St
Feature activation+6.971
Patrick
Token Patrick
Feature activation+0.000
is
Token is
Feature activation+0.000
considered
Token considered
Feature activation+0.000
the
Token the
Feature activation+0.000
patron
Token patron
Feature activation+0.000
t
Tokent
Feature activation+0.000
not
Token not
Feature activation+0.000
to
Token to
Feature activation+0.000
say
Token say
Feature activation+0.000
that
Token that
Feature activation+0.000
St
Token St
Feature activation+6.955
P
Token P
Feature activation+0.137
addy
Tokenaddy
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.531
s
Tokens
Feature activation+0.959
the
Token the
Feature activation+5.842
beauty
Token beauty
Feature activation+0.000
of
Token of
Feature activation+6.937
P
Token P
Feature activation+0.000
ono
Tokenono
Feature activation+0.000
.
Token.
Feature activation+2.172
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.134
H
TokenH
Feature activation+0.000
|
Token|
Feature activation+0.056
~
Token~
Feature activation+0.000
E
TokenE
Feature activation+0.000
)
Token)
Feature activation+0.196
<
Token <
Feature activation+6.765
P
TokenP
Feature activation+1.250
(
Token(
Feature activation+0.955
H
TokenH
Feature activation+0.000
),
Token),
Feature activation+0.126
or
Token or
Feature activation+0.908
being
Token being
Feature activation+0.000
held
Token held
Feature activation+0.000
next
Token next
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
here
Token here
Feature activation+0.000
in
Token in
Feature activation+6.604
Chicago
Token Chicago
Feature activation+0.000
called
Token called
Feature activation+0.000
Latino
Token Latino
Feature activation+0.000
Nation
Token Nation
Feature activation+0.000
.
Token.
Feature activation+0.000
recovery
Token recovery
Feature activation+0.000
programs
Token programs
Feature activation+0.000
.
Token.
Feature activation+4.225
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.168
Through
TokenThrough
Feature activation+6.575
Amer
Token Amer
Feature activation+0.000
i
Tokeni
Feature activation+0.000
Cor
TokenCor
Feature activation+0.000
ps
Tokenps
Feature activation+0.000
,
Token,
Feature activation+3.487
seeing
Token seeing
Feature activation+0.000
mold
Token mold
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
trailer
Token trailer
Feature activation+0.000
,
Token,
Feature activation+6.572
which
Token which
Feature activation+3.714
is
Token is
Feature activation+0.000
air
Token air
Feature activation+0.000
-
Token-
Feature activation+0.000
condition
Tokencondition
Feature activation+0.000

Top DFA by src position
MAX = 9.114

Hall
Token Hall
Feature activation-0.005
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Fame
Token Fame
Feature activation-0.002
Top resid features:
curator
Token curator
Feature activation-0.026
Top resid features:
Phil
Token Phil
Feature activation+0.042
Top resid features:
P
Token P
Feature activation+9.114
Top resid features:
rit
Tokenrit
Feature activation+0.034
Top resid features:
chard
Tokenchard
Feature activation-0.078
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.002
Top resid features:
showed
Token showed
Feature activation+0.001
Top resid features:
up
Token up
Feature activation-0.001
Top resid features:
Hall
Token Hall
Feature activation-0.004
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Fame
Token Fame
Feature activation-0.002
Top resid features:
curator
Token curator
Feature activation-0.015
Top resid features:
Phil
Token Phil
Feature activation+0.039
Top resid features:
P
Token P
Feature activation+8.973
Top resid features:
rit
Tokenrit
Feature activation+0.030
Top resid features:
chard
Tokenchard
Feature activation-0.057
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.005
Top resid features:
showed
Token showed
Feature activation-0.000
Top resid features:
up
Token up
Feature activation-0.001
Top resid features:
which
Token which
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
eighth
Token eighth
Feature activation-0.004
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.008
Top resid features:
P
Token P
Feature activation+8.568
Top resid features:
GA
TokenGA
Feature activation+0.033
Top resid features:
Tour
Token Tour
Feature activation+0.047
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
full
Token full
Feature activation-0.001
Top resid features:
season
Token season
Feature activation-0.003
Top resid features:
with
Token with
Feature activation-0.001
Top resid features:
Minnesota
Token Minnesota
Feature activation-0.038
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
P
Token P
Feature activation+5.757
Top resid features:
omin
Tokenomin
Feature activation+0.133
Top resid features:
ville
Tokenville
Feature activation-0.037
Top resid features:
posted
Token posted
Feature activation-0.003
Top resid features:
18
Token 18
Feature activation-0.006
Top resid features:
goals
Token goals
Feature activation+0.040
Top resid features:
To
TokenTo
Feature activation+0.004
Top resid features:
complete
Token complete
Feature activation-0.009
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
project
Token project
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
P
Token P
Feature activation+8.191
Top resid features:
edia
Tokenedia
Feature activation+0.106
Top resid features:
Press
TokenPress
Feature activation-0.018
Top resid features:
is
Token is
Feature activation+0.001
Top resid features:
trying
Token trying
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
To
TokenTo
Feature activation+0.005
Top resid features:
complete
Token complete
Feature activation-0.024
Top resid features:
the
Token the
Feature activation-0.026
Top resid features:
project
Token project
Feature activation-0.005
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
P
Token P
Feature activation+7.771
Top resid features:
edia
Tokenedia
Feature activation+0.238
Top resid features:
Press
TokenPress
Feature activation-0.017
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
trying
Token trying
Feature activation-0.001
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
do
Token do
Feature activation+0.001
Top resid features:
with
Token with
Feature activation-0.003
Top resid features:
bad
Token bad
Feature activation+0.013
Top resid features:
luck
Token luck
Feature activation-0.009
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
P
Token P
Feature activation+4.689
Top resid features:
omin
Tokenomin
Feature activation+0.116
Top resid features:
ville
Tokenville
Feature activation+0.024
Top resid features:
registered
Token registered
Feature activation-0.003
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
career
Token career
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.042
Top resid features:
agreement
Token agreement
Feature activation+0.008
Top resid features:
with
Token with
Feature activation-0.012
Top resid features:
P
Token P
Feature activation+7.750
Top resid features:
ire
Tokenire
Feature activation+0.183
Top resid features:
lli
Tokenlli
Feature activation-0.030
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Can
Token Can
Feature activation-0.013
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.047
Top resid features:
an
Token an
Feature activation-0.000
Top resid features:
Indian
Token Indian
Feature activation-0.078
Top resid features:
court
Token court
Feature activation+0.010
Top resid features:
in
Token in
Feature activation-0.014
Top resid features:
P
Token P
Feature activation+7.545
Top resid features:
anch
Tokenanch
Feature activation+0.209
Top resid features:
k
Tokenk
Feature activation-0.002
Top resid features:
ula
Tokenula
Feature activation-0.008
Top resid features:
on
Token on
Feature activation-0.000
Top resid features:
Friday
Token Friday
Feature activation+0.000
Top resid features:
To
TokenTo
Feature activation+0.007
Top resid features:
complete
Token complete
Feature activation-0.013
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
project
Token project
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
P
Token P
Feature activation+7.536
Top resid features:
edia
Tokenedia
Feature activation+0.126
Top resid features:
Press
TokenPress
Feature activation-0.011
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
trying
Token trying
Feature activation-0.002
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:
Sport
TokenSport
Feature activation+0.001
Top resid features:
)
Token)
Feature activation+0.014
Top resid features:
Ċ
TokenĊ
Feature activation+0.029
Top resid features:
Ċ
TokenĊ
Feature activation+0.025
Top resid features:
Amy
TokenAmy
Feature activation-0.103
Top resid features:
P
Token P
Feature activation+7.615
Top resid features:
urdy
Tokenurdy
Feature activation-0.005
Top resid features:
swaps
Token swaps
Feature activation+0.003
Top resid features:
her
Token her
Feature activation-0.005
Top resid features:
prost
Token prost
Feature activation-0.015
Top resid features:
hetic
Tokenhetic
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.042
Top resid features:
resident
Token resident
Feature activation+0.004
Top resid features:
Will
Token Will
Feature activation-0.001
Top resid features:
Wade
Token Wade
Feature activation-0.140
Top resid features:
-
Token-
Feature activation-0.011
Top resid features:
P
TokenP
Feature activation+8.195
Top resid features:
ent
Tokenent
Feature activation-0.408
Top resid features:
el
Tokenel
Feature activation-0.024
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
25
Token 25
Feature activation-0.002
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
close
Token close
Feature activation-0.007
Top resid features:
to
Token to
Feature activation-0.008
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
town
Token town
Feature activation+0.006
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
P
Token P
Feature activation+7.346
Top resid features:
aks
Tokenaks
Feature activation+0.067
Top resid features:
ong
Tokenong
Feature activation+0.011
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
stopped
Token stopped
Feature activation-0.001
Top resid features:
here
Token here
Feature activation+0.119
Top resid features:
Irish
Token Irish
Feature activation+0.006
Top resid features:
exp
Token exp
Feature activation+0.001
Top resid features:
ats
Tokenats
Feature activation+0.012
Top resid features:
celebrated
Token celebrated
Feature activation-0.001
Top resid features:
St
Token St
Feature activation-0.004
Top resid features:
P
Token P
Feature activation+2.637
Top resid features:
addy
Tokenaddy
Feature activation-0.018
Top resid features:
âĢ
TokenâĢ
Feature activation+0.028
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
s
Tokens
Feature activation+0.010
Top resid features:
Day
Token Day
Feature activation+0.002
Top resid features:
Irish
Token Irish
Feature activation+0.007
Top resid features:
exp
Token exp
Feature activation+0.002
Top resid features:
ats
Tokenats
Feature activation+0.022
Top resid features:
celebrated
Token celebrated
Feature activation-0.002
Top resid features:
St
Token St
Feature activation-0.012
Top resid features:
P
Token P
Feature activation+4.896
Top resid features:
addy
Tokenaddy
Feature activation+0.013
Top resid features:
âĢ
TokenâĢ
Feature activation+0.041
Top resid features:
Ļ
TokenĻ
Feature activation+0.013
Top resid features:
s
Tokens
Feature activation+0.020
Top resid features:
Day
Token Day
Feature activation+0.010
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
now
Token now
Feature activation+0.003
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
with
Token with
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
P
Token P
Feature activation+6.747
Top resid features:
ono
Tokenono
Feature activation+0.640
Top resid features:
Player
TokenPlayer
Feature activation+0.027
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
can
Token can
Feature activation-0.001
Top resid features:
E
TokenE
Feature activation-0.008
Top resid features:
|
Token|
Feature activation-0.006
Top resid features:
H
TokenH
Feature activation-0.014
Top resid features:
)
Token)
Feature activation-0.002
Top resid features:
<
Token <
Feature activation-0.001
Top resid features:
P
TokenP
Feature activation+4.455
Top resid features:
(
Token(
Feature activation-0.002
Top resid features:
~
Token~
Feature activation+0.021
Top resid features:
E
TokenE
Feature activation-0.004
Top resid features:
),
Token),
Feature activation-0.005
Top resid features:
so
Token so
Feature activation-0.010
Top resid features:
outside
Token outside
Feature activation-0.002
Top resid features:
Metro
Token Metro
Feature activation-0.019
Top resid features:
Bank
Token Bank
Feature activation-0.024
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
east
Token east
Feature activation+0.073
Top resid features:
P
Token P
Feature activation+6.757
Top resid features:
ils
Tokenils
Feature activation+0.463
Top resid features:
en
Tokenen
Feature activation+0.028
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
We
Token We
Feature activation+0.002
Top resid features:
will
Token will
Feature activation-0.000
Top resid features:
are
Token are
Feature activation-0.001
Top resid features:
pleased
Token pleased
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
announce
Token announce
Feature activation-0.000
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
P
Token P
Feature activation+7.000
Top resid features:
.
Token.
Feature activation+0.117
Top resid features:
A
TokenA
Feature activation+0.016
Top resid features:
.
Token.
Feature activation+0.041
Top resid features:
A
TokenA
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.030
Top resid features:
Ŀ
TokenĿ
Feature activation-0.006
Top resid features:
said
Token said
Feature activation-0.002
Top resid features:
Gus
Token Gus
Feature activation-0.024
Top resid features:
P
Token P
Feature activation+5.449
Top resid features:
rent
Tokenrent
Feature activation+0.042
Top resid features:
z
Tokenz
Feature activation+0.029
Top resid features:
as
Tokenas
Feature activation+0.043
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
president
Token president
Feature activation-0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.07

Head 3: 0.03

Head 4: 0.03

Head 5: 0.03

Head 6: 0.04

Head 7: 0.11

Head 8: 0.02

Head 9: 0.04

Head 10: 0.52

Head 11: 0.03

Positive logits

P10.42

P8.42

p5.97

p5.91

PW5.17

Pere4.98

PJ4.97

PN4.78

Pom4.77

PP4.75

Pu4.70

Ps4.58

PP4.56

Pip4.45

Pel4.34

PB4.33

PI4.25

Panda4.18

Pis4.17

PK4.16

Negative logits

aeda-3.56

igen-2.95

gh-2.75

hitch-2.70

riad-2.69

tram-2.54

oldown-2.51

-2.50

nox-2.48

roma-2.48

unden-2.47

thur-2.46

Bleach-2.46

mic-2.44

ab-2.40

acy-2.40

fri-2.39

necks-2.39

ゼウス-2.36

DX-2.31

INTERVAL 7.734 - 8.593
CONTAINS 0.001%

Cup
Token Cup
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
mountain
Token mountain
Feature activation+0.000
climbing
Token climbing
Feature activation+0.000
,
Token,
Feature activation+8.593
canoe
Token canoe
Feature activation+0.000
ing
Tokening
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
even
Token even
Feature activation+0.000
a
Token a
Feature activation+0.000
Sea
Token Sea
Feature activation+0.000
-
Token-
Feature activation+0.000
D
TokenD
Feature activation+0.000
oo
Tokenoo
Feature activation+0.000
,
Token,
Feature activation+8.478
Kimmel
Token Kimmel
Feature activation+0.000
decided
Token decided
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.110
what
Token what
Feature activation+2.081
revert
Token revert
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
mean
Token mean
Feature activation+0.000
and
Token and
Feature activation+7.508
for
Token for
Feature activation+7.966
P
Token P
Feature activation+0.000
omin
Tokenomin
Feature activation+0.000
ville
Tokenville
Feature activation+0.000
to
Token to
Feature activation+0.000
eclipse
Token eclipse
Feature activation+3.046
which
Token which
Feature activation+0.649
was
Token was
Feature activation+0.000
24
Token 24
Feature activation+0.000
th
Tokenth
Feature activation+0.103
on
Token on
Feature activation+3.758
the
Token the
Feature activation+8.115
P
Token P
Feature activation+0.138
GA
TokenGA
Feature activation+0.000
Tour
Token Tour
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
their
Token their
Feature activation+0.000
course
Token course
Feature activation+0.000
work
Token work
Feature activation+0.000
.
Token.
Feature activation+3.245
Clearly
Token Clearly
Feature activation+5.846
,
Token,
Feature activation+7.950
a
Token a
Feature activation+1.186
$
Token $
Feature activation+0.032
50
Token50
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.337

INTERVAL 6.874 - 7.734
CONTAINS 0.001%

million
Token million
Feature activation+0.000
articles
Token articles
Feature activation+0.000
.
Token.
Feature activation+2.882
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.143
But
TokenBut
Feature activation+7.171
backers
Token backers
Feature activation+0.339
of
Token of
Feature activation+7.560
the
Token the
Feature activation+3.746
project
Token project
Feature activation+0.000
argue
Token argue
Feature activation+3.787
to
Token to
Feature activation+0.000
revert
Token revert
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
mean
Token mean
Feature activation+0.000
and
Token and
Feature activation+7.508
for
Token for
Feature activation+7.966
P
Token P
Feature activation+0.000
omin
Tokenomin
Feature activation+0.000
ville
Tokenville
Feature activation+0.000
to
Token to
Feature activation+0.000
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
a
Token a
Feature activation+0.000
long
Token long
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
with
Token with
Feature activation+7.280
P
Token P
Feature activation+0.000
ire
Tokenire
Feature activation+0.000
lli
Tokenlli
Feature activation+0.000
.
Token.
Feature activation+2.086
The
Token The
Feature activation+1.347
the
Token the
Feature activation+0.000
night
Token night
Feature activation+0.000
.
Token.
Feature activation+0.614
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.809
From
TokenFrom
Feature activation+6.978
P
Token P
Feature activation+0.154
aks
Tokenaks
Feature activation+0.000
ong
Tokenong
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+1.728
in
Token in
Feature activation+0.000
Copper
Token Copper
Feature activation+0.000
Mountain
Token Mountain
Feature activation+0.000
,
Token,
Feature activation+0.000
Colorado
Token Colorado
Feature activation+0.000
.
Token.
Feature activation+7.048
P
Token P
Feature activation+0.000
urdy
Tokenurdy
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 6.015 - 6.874
CONTAINS 0.002%

on
Token on
Feature activation+0.000
transgender
Token transgender
Feature activation+0.000
issues
Token issues
Feature activation+0.000
I
Token I
Feature activation+0.000
applauded
Token applauded
Feature activation+0.000
.
Token.
Feature activation+6.141
She
Token She
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
that
Token that
Feature activation+0.261
she
Token she
Feature activation+0.000
understood
Token understood
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
with
Token with
Feature activation+5.153
bad
Token bad
Feature activation+0.000
luck
Token luck
Feature activation+0.000
.
Token.
Feature activation+6.520
P
Token P
Feature activation+0.000
omin
Tokenomin
Feature activation+0.000
ville
Tokenville
Feature activation+0.000
registered
Token registered
Feature activation+0.000
a
Token a
Feature activation+0.000
82
Token 82
Feature activation+0.000
-
Token-
Feature activation+0.000
game
Tokengame
Feature activation+0.000
season
Token season
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+6.107
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+1.823
that
Token that
Feature activation+0.000
had
Token had
Feature activation+0.000
Marshal
Token Marshal
Feature activation+0.000
Philippe
Token Philippe
Feature activation+0.000
P
Token P
Feature activation+0.000
é
Tokené
Feature activation+0.000
tain
Tokentain
Feature activation+0.156
.
Token.
Feature activation+6.322
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.826
French
TokenFrench
Feature activation+0.069
General
Token General
Feature activation+4.045
Charles
Token Charles
Feature activation+0.000
a
Token a
Feature activation+0.000
soul
Token soul
Feature activation+0.000
and
Token and
Feature activation+0.000
a
Token a
Feature activation+0.000
brain
Token brain
Feature activation+0.000
,
Token,
Feature activation+6.098
it
Token it
Feature activation+0.000
was
Token was
Feature activation+1.093
.
Token.
Feature activation+3.399
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.612

INTERVAL 5.156 - 6.015
CONTAINS 0.003%

quickly
Token quickly
Feature activation+0.030
apparent
Token apparent
Feature activation+2.157
among
Token among
Feature activation+5.542
these
Token these
Feature activation+3.796
is
Token is
Feature activation+0.841
that
Token that
Feature activation+5.453
rather
Token rather
Feature activation+0.000
of
Token of
Feature activation+0.375
the
Token the
Feature activation+2.272
lab
Token lab
Feature activation+0.000
orer
Tokenorer
Feature activation+0.000
Before
Token Before
Feature activation+0.068
making
Token making
Feature activation+0.000
our
Token our
Feature activation+0.000
way
Token way
Feature activation+0.000
back
Token back
Feature activation+0.000
to
Token to
Feature activation+5.380
our
Token our
Feature activation+0.000
starting
Token starting
Feature activation+0.000
point
Token point
Feature activation+1.352
of
Token of
Feature activation+4.053
Pak
Token Pak
Feature activation+0.000
activity
Token activity
Feature activation+0.000
of
Token of
Feature activation+1.139
a
Token a
Feature activation+0.296
third
Token third
Feature activation+1.056
pass
Token pass
Feature activation+0.000
through
Token through
Feature activation+5.413
the
Token the
Feature activation+1.288
area
Token area
Feature activation+0.000
.
Token.
Feature activation+0.167
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.256
Alfred
Token Alfred
Feature activation+0.123
,
Token,
Feature activation+1.375
the
Token the
Feature activation+3.821
entry
Token entry
Feature activation+0.850
-
Token-
Feature activation+0.000
level
Tokenlevel
Feature activation+5.772
U
Token U
Feature activation+0.000
JS
TokenJS
Feature activation+0.296
wrist
Token wrist
Feature activation+0.000
watch
Tokenwatch
Feature activation+0.000
featured
Token featured
Feature activation+2.899
benefits
Token benefits
Feature activation+0.000
to
Token to
Feature activation+2.401
be
Token be
Feature activation+0.000
had
Token had
Feature activation+0.000
.
Token.
Feature activation+4.591
The
Token The
Feature activation+5.821
first
Token first
Feature activation+1.593
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
majority
Token majority
Feature activation+0.000
of
Token of
Feature activation+5.277

INTERVAL 4.296 - 5.156
CONTAINS 0.005%

about
Token about
Feature activation+0.000
$
Token $
Feature activation+0.000
12
Token12
Feature activation+0.000
,
Token,
Feature activation+0.000
500
Token500
Feature activation+0.000
.
Token.
Feature activation+4.527
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.305
Wikipedia
TokenWikipedia
Feature activation+0.131
is
Token is
Feature activation+0.272
at
Token at
Feature activation+0.542
taking
Token taking
Feature activation+2.418
education
Token education
Feature activation+0.000
very
Token very
Feature activation+0.000
seriously
Token seriously
Feature activation+0.000
.
Token.
Feature activation+0.492
The
Token The
Feature activation+4.545
work
Token work
Feature activation+0.178
ethic
Token ethic
Feature activation+0.000
is
Token is
Feature activation+0.000
amazingly
Token amazingly
Feature activation+0.000
strong
Token strong
Feature activation+0.000
,
Token ,
Feature activation+0.862
President
Token President
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
recalled
Token recalled
Feature activation+2.345
how
Token how
Feature activation+1.000
the
Token the
Feature activation+4.800
Soviet
Token Soviet
Feature activation+0.000
Union
Token Union
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.717
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
mind
Token mind
Feature activation+1.490
hearing
Token hearing
Feature activation+3.396
,
Token,
Feature activation+1.769
from
Token from
Feature activation+4.399
teammates
Token teammates
Feature activation+0.000
at
Token at
Feature activation+0.385
least
Token least
Feature activation+0.000
,
Token,
Feature activation+1.016
about
Token about
Feature activation+4.374
4
Token 4
Feature activation+0.000
million
Token million
Feature activation+0.000
articles
Token articles
Feature activation+0.000
.
Token.
Feature activation+2.882
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.143
But
TokenBut
Feature activation+7.171
backers
Token backers
Feature activation+0.339
of
Token of
Feature activation+7.560
the
Token the
Feature activation+3.746
project
Token project
Feature activation+0.000

INTERVAL 3.437 - 4.296
CONTAINS 0.009%

tain
Tokentain
Feature activation+0.156
.
Token.
Feature activation+6.322
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.826
French
TokenFrench
Feature activation+0.069
General
Token General
Feature activation+4.045
Charles
Token Charles
Feature activation+0.000
de
Token de
Feature activation+0.000
Gaul
Token Gaul
Feature activation+0.000
le
Tokenle
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
higher
Token higher
Feature activation+0.000
,
Token,
Feature activation+0.352
the
Token the
Feature activation+4.032
way
Token way
Feature activation+1.920
the
Token the
Feature activation+3.798
artist
Token artist
Feature activation+0.000
made
Token made
Feature activation+1.031
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
But
TokenBut
Feature activation+7.171
backers
Token backers
Feature activation+0.339
of
Token of
Feature activation+7.560
the
Token the
Feature activation+3.746
project
Token project
Feature activation+0.000
argue
Token argue
Feature activation+3.787
such
Token such
Feature activation+0.000
concerns
Token concerns
Feature activation+0.000
miss
Token miss
Feature activation+0.000
the
Token the
Feature activation+0.000
point
Token point
Feature activation+0.000
Trust
Token Trust
Feature activation+0.000
for
Token for
Feature activation+0.370
Public
Token Public
Feature activation+0.000
Land
Token Land
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+3.743
US
Token US
Feature activation+0.198
FS
TokenFS
Feature activation+0.000
purchased
Token purchased
Feature activation+0.564
808
Token 808
Feature activation+0.023
acres
Token acres
Feature activation+0.000
.
Token.
Feature activation+0.455
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.265
Design
TokenDesign
Feature activation+0.000
characteristics
Token characteristics
Feature activation+0.000
of
Token of
Feature activation+4.008
SM
Token SM
Feature activation+0.000
ART
TokenART
Feature activation+0.665
contributing
Token contributing
Feature activation+0.000
to
Token to
Feature activation+0.349
the
Token the
Feature activation+0.583

INTERVAL 2.578 - 3.437
CONTAINS 0.017%

doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
mind
Token mind
Feature activation+1.490
hearing
Token hearing
Feature activation+3.396
,
Token,
Feature activation+1.769
from
Token from
Feature activation+4.399
teammates
Token teammates
Feature activation+0.000
at
Token at
Feature activation+0.385
least
Token least
Feature activation+0.000
it
Token it
Feature activation+0.000
plans
Token plans
Feature activation+0.000
to
Token to
Feature activation+0.000
launch
Token launch
Feature activation+2.455
a
Token a
Feature activation+3.133
flagship
Token flagship
Feature activation+3.170
smartphone
Token smartphone
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.601
US
Token US
Feature activation+0.000
this
Token this
Feature activation+0.000
their
Token their
Feature activation+0.695
first
Token first
Feature activation+0.095
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+2.773
much
Token much
Feature activation+0.000
of
Token of
Feature activation+0.000
their
Token their
Feature activation+0.000
spending
Token spending
Feature activation+0.000
promises
Token promises
Feature activation+0.000
carefully
Token carefully
Feature activation+0.000
pr
Token pr
Feature activation+0.000
uned
Tokenuned
Feature activation+0.000
features
Token features
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+2.700
Open
Token Open
Feature activation+0.000
W
TokenW
Feature activation+0.000
RT
TokenRT
Feature activation+0.000
to
Token to
Feature activation+0.000
minimize
Token minimize
Feature activation+0.000
ession
Tokenession
Feature activation+0.000
:
Token:
Feature activation+0.000
Fashion
Token Fashion
Feature activation+0.000
photographer
Token photographer
Feature activation+0.000
Special
TokenSpecial
Feature activation+0.000
Some
Token Some
Feature activation+3.126
p
Tokenp
Feature activation+0.000
ony
Tokenony
Feature activation+0.000
:
Token:
Feature activation+0.000
Food
Token Food
Feature activation+0.000
critic
Token critic
Feature activation+0.000

INTERVAL 1.719 - 2.578
CONTAINS 0.028%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
mind
Token mind
Feature activation+1.490
hearing
Token hearing
Feature activation+3.396
,
Token,
Feature activation+1.769
from
Token from
Feature activation+4.399
teammates
Token teammates
Feature activation+0.000
at
Token at
Feature activation+0.385
least
Token least
Feature activation+0.000
,
Token,
Feature activation+1.016
the
Token the
Feature activation+0.000
record
Token record
Feature activation+0.000
as
Token as
Feature activation+0.000
having
Token having
Feature activation+0.000
said
Token said
Feature activation+0.000
that
Token that
Feature activation+1.756
it
Token it
Feature activation+0.000
plans
Token plans
Feature activation+0.000
to
Token to
Feature activation+0.000
launch
Token launch
Feature activation+2.455
a
Token a
Feature activation+3.133
Ċ
TokenĊ
Feature activation+2.370
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.339
I
TokenI
Feature activation+0.000
think
Token think
Feature activation+0.993
(
Token (
Feature activation+2.146
the
Tokenthe
Feature activation+0.546
deal
Token deal
Feature activation+0.000
)
Token)
Feature activation+0.000
shows
Token shows
Feature activation+0.669
that
Token that
Feature activation+0.731
North
Token North
Feature activation+0.000
Carolina
Token Carolina
Feature activation+0.000
,
Token ,
Feature activation+0.862
President
Token President
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
recalled
Token recalled
Feature activation+2.345
how
Token how
Feature activation+1.000
the
Token the
Feature activation+4.800
Soviet
Token Soviet
Feature activation+0.000
Union
Token Union
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
down
Token down
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
ceiling
Token ceiling
Feature activation+0.000
and
Token and
Feature activation+0.000
punched
Token punched
Feature activation+1.873
off
Token off
Feature activation+3.068
half
Token half
Feature activation+0.000
of
Token of
Feature activation+4.035
the
Token the
Feature activation+0.000
security
Token security
Feature activation+0.000

INTERVAL 0.859 - 1.719
CONTAINS 0.063%

for
Token for
Feature activation+3.938
Ch
Token Ch
Feature activation+0.000
ivas
Tokenivas
Feature activation+0.000
would
Token would
Feature activation+0.000
continue
Token continue
Feature activation+2.204
the
Token the
Feature activation+0.940
momentum
Token momentum
Feature activation+3.511
generated
Token generated
Feature activation+0.000
from
Token from
Feature activation+2.202
four
Token four
Feature activation+0.320
consecutive
Token consecutive
Feature activation+0.324
will
Token will
Feature activation+0.000
become
Token become
Feature activation+0.000
the
Token the
Feature activation+0.050
longest
Token longest
Feature activation+0.000
sponsorship
Token sponsorship
Feature activation+0.000
deal
Token deal
Feature activation+1.006
in
Token in
Feature activation+1.798
Italian
Token Italian
Feature activation+0.000
football
Token football
Feature activation+0.000
and
Token and
Feature activation+3.294
one
Token one
Feature activation+0.000
thought
Token thought
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
free
Token free
Feature activation+0.000
speech
Token speech
Feature activation+0.000
,
Token,
Feature activation+1.034
now
Token now
Feature activation+0.000
universities
Token universities
Feature activation+0.000
are
Token are
Feature activation+0.000
training
Token training
Feature activation+0.000
centers
Token centers
Feature activation+0.000
.
Token.
Feature activation+0.000
group
Tokengroup
Feature activation+0.000
(
Token(
Feature activation+0.000
CS
TokenCS
Feature activation+0.000
_
Token_
Feature activation+0.000
GR
TokenGR
Feature activation+1.138
P
TokenP
Feature activation+0.000
_
Token_
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
An
TokenAn
Feature activation+0.000
American
Token American
Feature activation+0.000
&
Token&
Feature activation+0.000
L
TokenL
Feature activation+0.000
of
Token of
Feature activation+1.006
a
Token a
Feature activation+1.655
supplier
Token supplier
Feature activation+0.000
.
Token.
Feature activation+1.034
Lawyers
Token Lawyers
Feature activation+0.000
will
Token will
Feature activation+0.000
probably
Token probably
Feature activation+0.000
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.000 - 0.859
CONTAINS 99.872%

business
Token business
Feature activation+0.000
why
Token why
Feature activation+0.000
I
Token I
Feature activation+0.000
did
Token did
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
think
Token think
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ILS
TokenILS
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
cost
Token cost
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
evening
Token evening
Feature activation+0.000
reception
Token reception
Feature activation+0.000
is
Token is
Feature activation+0.000
free
Token free
Feature activation+0.000
signing
Token signing
Feature activation+0.000
up
Token up
Feature activation+0.000
you
Token you
Feature activation+0.000
agree
Token agree
Feature activation+0.000
to
Token to
Feature activation+0.000
receive
Token receive
Feature activation+0.000
email
Token email
Feature activation+0.000
newsletters
Token newsletters
Feature activation+0.000
or
Token or
Feature activation+0.000
alerts
Token alerts
Feature activation+0.000
from
Token from
Feature activation+0.000
Pacific
Token Pacific
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Why
TokenWhy
Feature activation+0.000
Prince
Token Prince
Feature activation+0.000
Philip
Token Philip
Feature activation+0.000
?
Token?
Feature activation+0.000
Bay
Token Bay
Feature activation+0.000
lis
Tokenlis
Feature activation+0.000
said
Token said
Feature activation+0.000
um
Tokenum
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
11
Token11
Feature activation+0.000
pm
Tokenpm
Feature activation+0.000
Legends
Token Legends
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
June
TokenJune
Feature activation+0.000
29
Token 29
Feature activation+0.000
9
Token 9
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 H10.10: (feature 12045)

TOP ACTIVATIONS
MAX = 9.616

high
Token high
Feature activation+0.000
,
Token,
Feature activation+0.000
loop
Token loop
Feature activation+0.000
ing
Tokening
Feature activation+0.000
shot
Token shot
Feature activation+0.000
over
Token over
Feature activation+9.616
goalkeeper
Token goalkeeper
Feature activation+0.000
Michael
Token Michael
Feature activation+0.000
Maurice
Token Maurice
Feature activation+0.000
for
Token for
Feature activation+0.378
his
Token his
Feature activation+0.000
election
Token election
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
,
Token,
Feature activation+2.672
a
Token a
Feature activation+2.074
spokesperson
Token spokesperson
Feature activation+0.000
for
Token for
Feature activation+9.364
H
Token H
Feature activation+0.000
icken
Tokenicken
Feature activation+0.000
lo
Tokenlo
Feature activation+0.000
oper
Tokenoper
Feature activation+0.000
's
Token's
Feature activation+0.000
test
Token test
Feature activation+0.000
.
Token.
Feature activation+5.737
A
TokenA
Feature activation+0.000
magistrate
Token magistrate
Feature activation+0.000
judge
Token judge
Feature activation+0.000
set
Token set
Feature activation+9.126
H
Token H
Feature activation+0.000
aney
Tokenaney
Feature activation+0.000
's
Token's
Feature activation+0.000
bond
Token bond
Feature activation+0.000
at
Token at
Feature activation+0.000
reviewed
Token reviewed
Feature activation+0.000
by
Token by
Feature activation+0.000
International
Token International
Feature activation+0.000
Business
Token Business
Feature activation+0.000
Times
Token Times
Feature activation+0.000
,
Token,
Feature activation+9.019
the
Token the
Feature activation+5.349
Colorado
Token Colorado
Feature activation+0.089
governor
Token governor
Feature activation+0.000
's
Token's
Feature activation+0.000
office
Token office
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Matt
Token Matt
Feature activation+0.000
H
Token H
Feature activation+0.000
inton
Tokeninton
Feature activation+0.000
(@
Token (@
Feature activation+1.893
Matt
TokenMatt
Feature activation+8.900
RH
TokenRH
Feature activation+0.000
inton
Tokeninton
Feature activation+0.000
)
Token)
Feature activation+0.000
November
Token November
Feature activation+0.000
22
Token 22
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.610
Perhaps
TokenPerhaps
Feature activation+4.731
Walker
Token Walker
Feature activation+0.000
felt
Token felt
Feature activation+5.619
that
Token that
Feature activation+8.874
H
Token H
Feature activation+0.000
aged
Tokenaged
Feature activation+0.000
orn
Tokenorn
Feature activation+0.000
was
Token was
Feature activation+0.000
qualified
Token qualified
Feature activation+0.000
,
Token,
Feature activation+6.943
in
Token in
Feature activation+2.396
Walker
Token Walker
Feature activation+0.000
's
Token's
Feature activation+0.000
eyes
Token eyes
Feature activation+7.567
,
Token,
Feature activation+8.794
H
Token H
Feature activation+0.000
aged
Tokenaged
Feature activation+0.000
orn
Tokenorn
Feature activation+0.000
's
Token's
Feature activation+0.000
greatest
Token greatest
Feature activation+0.000
As
Token As
Feature activation+3.085
part
Token part
Feature activation+0.000
of
Token of
Feature activation+3.415
the
Token the
Feature activation+0.000
conditions
Token conditions
Feature activation+0.823
,
Token,
Feature activation+8.578
H
Token H
Feature activation+0.000
aney
Tokenaney
Feature activation+0.000
will
Token will
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
confirmed
Token confirmed
Feature activation+8.288
to
Token to
Feature activation+0.000
Ey
Token Ey
Feature activation+0.000
ewitness
Tokenewitness
Feature activation+0.000
News
Token News
Feature activation+2.778
that
Token that
Feature activation+8.397
H
Token H
Feature activation+0.000
aney
Tokenaney
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
sitting
Token sitting
Feature activation+0.000
in
Token in
Feature activation+2.000
her
Token her
Feature activation+0.000
vehicle
Token vehicle
Feature activation+0.000
.
Token.
Feature activation+4.603
Additionally
Token Additionally
Feature activation+4.683
,
Token,
Feature activation+8.343
she
Token she
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
allowed
Token allowed
Feature activation+0.000
into
Token into
Feature activation+1.957
Texas
TokenTexas
Feature activation+0.000
City
Token City
Feature activation+0.000
Mayor
Token Mayor
Feature activation+0.000
Matthew
Token Matthew
Feature activation+0.000
Doyle
Token Doyle
Feature activation+0.000
confirmed
Token confirmed
Feature activation+8.288
to
Token to
Feature activation+0.000
Ey
Token Ey
Feature activation+0.000
ewitness
Tokenewitness
Feature activation+0.000
News
Token News
Feature activation+2.778
that
Token that
Feature activation+8.397
Tro
Token Tro
Feature activation+0.000
opers
Tokenopers
Feature activation+0.000
determined
Token determined
Feature activation+4.910
marijuana
Token marijuana
Feature activation+0.441
intoxication
Token intoxication
Feature activation+0.000
after
Token after
Feature activation+8.287
a
Token a
Feature activation+0.000
field
Token field
Feature activation+0.000
sob
Token sob
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
ety
Tokenety
Feature activation+0.000
side
Token side
Feature activation+0.000
presents
Token presents
Feature activation+6.442
a
Token a
Feature activation+0.000
special
Token special
Feature activation+0.000
treat
Token treat
Feature activation+0.000
:
Token:
Feature activation+8.281
H
Token H
Feature activation+0.000
ain
Tokenain
Feature activation+0.000
o
Tokeno
Feature activation+0.000
's
Token's
Feature activation+0.000
first
Token first
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
moment
Token moment
Feature activation+0.000
of
Token of
Feature activation+0.000
silence
Token silence
Feature activation+0.000
for
Token for
Feature activation+8.259
H
Token H
Feature activation+0.000
ogg
Tokenogg
Feature activation+0.000
.
Token.
Feature activation+2.019
Activ
Token Activ
Feature activation+0.000
ists
Tokenists
Feature activation+0.000
lan
Tokenlan
Feature activation+0.678
,
Token,
Feature activation+1.391
who
Token who
Feature activation+0.000
took
Token took
Feature activation+2.596
over
Token over
Feature activation+4.969
as
Token as
Feature activation+8.115
the
Token the
Feature activation+6.670
clinic
Token clinic
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
were
Token were
Feature activation+0.000
killed
Token killed
Feature activation+0.000
when
Token when
Feature activation+0.232
forces
Token forces
Feature activation+0.000
loyal
Token loyal
Feature activation+0.000
to
Token to
Feature activation+7.971
President
Token President
Feature activation+3.212
Abd
Token Abd
Feature activation+0.000
-
Token-
Feature activation+0.000
R
TokenR
Feature activation+0.000
abb
Tokenabb
Feature activation+0.000
the
Token the
Feature activation+0.000
prize
Token prize
Feature activation+0.000
,
Token,
Feature activation+0.000
Ark
Token Ark
Feature activation+0.000
ani
Tokenani
Feature activation+1.454
-
Token-
Feature activation+7.796
H
TokenH
Feature activation+0.000
amed
Tokenamed
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
again
Token again
Feature activation+2.728
,
Token,
Feature activation+6.943
in
Token in
Feature activation+2.396
Walker
Token Walker
Feature activation+0.000
's
Token's
Feature activation+0.000
eyes
Token eyes
Feature activation+7.567
,
Token,
Feature activation+8.794
H
Token H
Feature activation+0.000
aged
Tokenaged
Feature activation+0.000
orn
Tokenorn
Feature activation+0.000
's
Token's
Feature activation+0.000
at
Token at
Feature activation+0.000
H
Token H
Feature activation+0.000
udd
Tokenudd
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
field
Tokenfield
Feature activation+0.000
.
Token.
Feature activation+7.437
However
Token However
Feature activation+5.701
,
Token,
Feature activation+5.793
Red
Token Red
Feature activation+0.000
kn
Tokenkn
Feature activation+0.000
app
Tokenapp
Feature activation+0.000
its
Token its
Feature activation+0.000
name
Token name
Feature activation+0.000
from
Token from
Feature activation+5.295
a
Token a
Feature activation+0.000
quote
Token quote
Feature activation+5.026
in
Token in
Feature activation+7.398
Blake
Token Blake
Feature activation+0.000
's
Token's
Feature activation+0.000
poem
Token poem
Feature activation+0.000
"
Token "
Feature activation+0.000
The
TokenThe
Feature activation+0.000

Top DFA by src position
MAX = 10.129

Brian
Token Brian
Feature activation+0.007
Top resid features:
Williams
Token Williams
Feature activation+0.005
Top resid features:
up
Token up
Feature activation-0.001
Top resid features:
ended
Tokenended
Feature activation-0.007
Top resid features:
John
Token John
Feature activation-0.036
Top resid features:
H
Token H
Feature activation+10.129
Top resid features:
ark
Tokenark
Feature activation+0.080
Top resid features:
es
Tokenes
Feature activation-0.046
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
midfield
Token midfield
Feature activation-0.010
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
The
Token The
Feature activation+0.016
Top resid features:
firm
Token firm
Feature activation-0.003
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
hired
Token hired
Feature activation-0.004
Top resid features:
by
Token by
Feature activation+0.001
Top resid features:
H
Token H
Feature activation+9.269
Top resid features:
icken
Tokenicken
Feature activation+0.583
Top resid features:
lo
Tokenlo
Feature activation+0.007
Top resid features:
oper
Tokenoper
Feature activation-0.001
Top resid features:
's
Token's
Feature activation-0.008
Top resid features:
government
Token government
Feature activation-0.037
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
trooper
Token trooper
Feature activation-0.057
Top resid features:
told
Token told
Feature activation+0.000
Top resid features:
investigators
Token investigators
Feature activation-0.002
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
H
Token H
Feature activation+9.622
Top resid features:
aney
Tokenaney
Feature activation+0.057
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
under
Token under
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
influence
Token influence
Feature activation-0.003
Top resid features:
The
Token The
Feature activation+0.015
Top resid features:
firm
Token firm
Feature activation-0.006
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
hired
Token hired
Feature activation-0.015
Top resid features:
by
Token by
Feature activation+0.002
Top resid features:
H
Token H
Feature activation+6.733
Top resid features:
icken
Tokenicken
Feature activation+0.370
Top resid features:
lo
Tokenlo
Feature activation+0.003
Top resid features:
oper
Tokenoper
Feature activation-0.002
Top resid features:
's
Token's
Feature activation-0.000
Top resid features:
government
Token government
Feature activation-0.044
Top resid features:
Ju
TokenJu
Feature activation+0.000
Top resid features:
HA
TokenHA
Feature activation-0.000
Top resid features:
zy
Tokenzy
Feature activation-0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.019
Top resid features:
Matt
Token Matt
Feature activation+0.010
Top resid features:
H
Token H
Feature activation+9.306
Top resid features:
inton
Tokeninton
Feature activation+0.085
Top resid features:
(@
Token (@
Feature activation+0.012
Top resid features:
Matt
TokenMatt
Feature activation-0.002
Top resid features:
RH
TokenRH
Feature activation+0.000
Top resid features:
inton
Tokeninton
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
In
TokenIn
Feature activation+0.002
Top resid features:
fact
Token fact
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
H
Token H
Feature activation+9.161
Top resid features:
aged
Tokenaged
Feature activation+0.251
Top resid features:
orn
Tokenorn
Feature activation+0.035
Top resid features:
has
Token has
Feature activation+0.006
Top resid features:
precious
Token precious
Feature activation+0.004
Top resid features:
little
Token little
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Perhaps
TokenPerhaps
Feature activation+0.001
Top resid features:
Walker
Token Walker
Feature activation-0.037
Top resid features:
felt
Token felt
Feature activation+0.001
Top resid features:
that
Token that
Feature activation+0.006
Top resid features:
H
Token H
Feature activation+4.966
Top resid features:
aged
Tokenaged
Feature activation+0.017
Top resid features:
orn
Tokenorn
Feature activation+0.013
Top resid features:
was
Token was
Feature activation+0.004
Top resid features:
qualified
Token qualified
Feature activation-0.014
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.013
Top resid features:
trooper
Token trooper
Feature activation-0.058
Top resid features:
told
Token told
Feature activation-0.000
Top resid features:
investigators
Token investigators
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
H
Token H
Feature activation+5.124
Top resid features:
aney
Tokenaney
Feature activation+0.019
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
under
Token under
Feature activation-0.002
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
influence
Token influence
Feature activation-0.004
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
trooper
Token trooper
Feature activation-0.028
Top resid features:
told
Token told
Feature activation-0.000
Top resid features:
investigators
Token investigators
Feature activation-0.001
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
H
Token H
Feature activation+5.537
Top resid features:
aney
Tokenaney
Feature activation+0.042
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
under
Token under
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
influence
Token influence
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.012
Top resid features:
trooper
Token trooper
Feature activation-0.096
Top resid features:
told
Token told
Feature activation-0.000
Top resid features:
investigators
Token investigators
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.001
Top resid features:
H
Token H
Feature activation+3.863
Top resid features:
aney
Tokenaney
Feature activation+0.029
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
under
Token under
Feature activation-0.004
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
influence
Token influence
Feature activation-0.002
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
trooper
Token trooper
Feature activation-0.011
Top resid features:
told
Token told
Feature activation-0.000
Top resid features:
investigators
Token investigators
Feature activation-0.005
Top resid features:
that
Token that
Feature activation-0.000
Top resid features:
H
Token H
Feature activation+4.211
Top resid features:
aney
Tokenaney
Feature activation+0.036
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
under
Token under
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
influence
Token influence
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.006
Top resid features:
trooper
Token trooper
Feature activation-0.052
Top resid features:
told
Token told
Feature activation+0.001
Top resid features:
investigators
Token investigators
Feature activation-0.013
Top resid features:
that
Token that
Feature activation+0.002
Top resid features:
H
Token H
Feature activation+8.860
Top resid features:
aney
Tokenaney
Feature activation+0.098
Top resid features:
was
Token was
Feature activation+0.004
Top resid features:
under
Token under
Feature activation-0.012
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
influence
Token influence
Feature activation-0.012
Top resid features:
first
Token first
Feature activation+0.001
Top resid features:
side
Token side
Feature activation+0.013
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
dominated
Token dominated
Feature activation-0.005
Top resid features:
by
Token by
Feature activation-0.004
Top resid features:
H
Token H
Feature activation+8.078
Top resid features:
ain
Tokenain
Feature activation+0.173
Top resid features:
o
Tokeno
Feature activation+0.044
Top resid features:
's
Token's
Feature activation+0.003
Top resid features:
imp
Token imp
Feature activation+0.007
Top resid features:
assion
Tokenassion
Feature activation+0.000
Top resid features:
makeshift
Token makeshift
Feature activation+0.001
Top resid features:
replica
Token replica
Feature activation-0.001
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
vehicle
Token vehicle
Feature activation-0.010
Top resid features:
H
Token H
Feature activation+8.182
Top resid features:
ogg
Tokenogg
Feature activation+0.652
Top resid features:
was
Token was
Feature activation+0.005
Top resid features:
found
Token found
Feature activation-0.001
Top resid features:
sleeping
Token sleeping
Feature activation-0.007
Top resid features:
in
Token in
Feature activation+0.001
Top resid features:
resigned
Token resigned
Feature activation+0.000
Top resid features:
yesterday
Token yesterday
Feature activation-0.009
Top resid features:
has
Token has
Feature activation+0.006
Top resid features:
repaid
Token repaid
Feature activation-0.008
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
H
Token H
Feature activation+8.538
Top resid features:
SE
TokenSE
Feature activation+0.163
Top resid features:
extra
Token extra
Feature activation+0.006
Top resid features:
funding
Token funding
Feature activation+0.006
Top resid features:
he
Token he
Feature activation-0.000
Top resid features:
received
Token received
Feature activation+0.001
Top resid features:
R
TokenR
Feature activation-0.003
Top resid features:
abb
Tokenabb
Feature activation+0.012
Top resid features:
u
Tokenu
Feature activation-0.020
Top resid features:
Mans
Token Mans
Feature activation-0.182
Top resid features:
our
Tokenour
Feature activation+0.001
Top resid features:
H
Token H
Feature activation+8.808
Top resid features:
adi
Tokenadi
Feature activation-0.004
Top resid features:
take
Token take
Feature activation-0.000
Top resid features:
photos
Token photos
Feature activation+0.000
Top resid features:
near
Token near
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.001
Top resid features:
N
Token N
Feature activation+0.001
Top resid features:
ima
Tokenima
Feature activation-0.000
Top resid features:
Ark
Token Ark
Feature activation-0.039
Top resid features:
ani
Tokenani
Feature activation-0.065
Top resid features:
-
Token-
Feature activation+0.007
Top resid features:
H
TokenH
Feature activation+8.072
Top resid features:
amed
Tokenamed
Feature activation+0.249
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
was
Token was
Feature activation-0.001
Top resid features:
recognised
Token recognised
Feature activation-0.001
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.032
Top resid features:
Perhaps
TokenPerhaps
Feature activation+0.001
Top resid features:
Walker
Token Walker
Feature activation-0.056
Top resid features:
felt
Token felt
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.007
Top resid features:
H
Token H
Feature activation+4.020
Top resid features:
aged
Tokenaged
Feature activation+0.023
Top resid features:
orn
Tokenorn
Feature activation+0.025
Top resid features:
was
Token was
Feature activation+0.003
Top resid features:
qualified
Token qualified
Feature activation-0.007
Top resid features:
for
Token for
Feature activation-0.000
Top resid features:
question
Token question
Feature activation+0.002
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
Yorkshire
Token Yorkshire
Feature activation+0.054
Top resid features:
man
Tokenman
Feature activation-0.000
Top resid features:
Dean
Token Dean
Feature activation-0.138
Top resid features:
H
Token H
Feature activation+7.017
Top resid features:
oyle
Tokenoyle
Feature activation+0.037
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
founder
Token founder
Feature activation+0.004
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
Card
Token Card
Feature activation+0.086
Top resid features:
work
Token work
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
writer
Token writer
Feature activation-0.005
Top resid features:
Ald
Token Ald
Feature activation+0.028
Top resid features:
ous
Tokenous
Feature activation+0.002
Top resid features:
H
Token H
Feature activation+5.567
Top resid features:
ux
Tokenux
Feature activation+0.020
Top resid features:
ley
Tokenley
Feature activation+0.018
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
though
Token though
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.07

Head 3: 0.03

Head 4: 0.03

Head 5: 0.02

Head 6: 0.04

Head 7: 0.10

Head 8: 0.03

Head 9: 0.04

Head 10: 0.52

Head 11: 0.03

Positive logits

H10.80

H8.69

h6.88

HO5.91

h5.72

HG5.66

HW5.37

HH5.26

Ho5.00

HC4.97

HH4.93

ha4.90

HA4.89

HCR4.83

HC4.79

Ha4.77

HS4.73

Hab4.70

HIP4.59

HO4.56

Negative logits

qt-3.60

coni-3.07

Pam-2.94

ieved-2.86

-2.85

Angelo-2.81

ao-2.81

xa-2.69

xb-2.68

Reviewer-2.67

Qt-2.62

arse-2.62

azeera-2.60

fter-2.56

Louie-2.54

ucl-2.54

ply-2.54

gnu-2.53

Thom-2.53

mite-2.52

INTERVAL 8.655 - 9.616
CONTAINS 0.001%

election
Token election
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
,
Token,
Feature activation+2.672
a
Token a
Feature activation+2.074
spokesperson
Token spokesperson
Feature activation+0.000
for
Token for
Feature activation+9.364
H
Token H
Feature activation+0.000
icken
Tokenicken
Feature activation+0.000
lo
Tokenlo
Feature activation+0.000
oper
Tokenoper
Feature activation+0.000
's
Token's
Feature activation+0.000
high
Token high
Feature activation+0.000
,
Token,
Feature activation+0.000
loop
Token loop
Feature activation+0.000
ing
Tokening
Feature activation+0.000
shot
Token shot
Feature activation+0.000
over
Token over
Feature activation+9.616
goalkeeper
Token goalkeeper
Feature activation+0.000
Michael
Token Michael
Feature activation+0.000
Maurice
Token Maurice
Feature activation+0.000
for
Token for
Feature activation+0.378
his
Token his
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Matt
Token Matt
Feature activation+0.000
H
Token H
Feature activation+0.000
inton
Tokeninton
Feature activation+0.000
(@
Token (@
Feature activation+1.893
Matt
TokenMatt
Feature activation+8.900
RH
TokenRH
Feature activation+0.000
inton
Tokeninton
Feature activation+0.000
)
Token)
Feature activation+0.000
November
Token November
Feature activation+0.000
22
Token 22
Feature activation+0.000
test
Token test
Feature activation+0.000
.
Token.
Feature activation+5.737
A
TokenA
Feature activation+0.000
magistrate
Token magistrate
Feature activation+0.000
judge
Token judge
Feature activation+0.000
set
Token set
Feature activation+9.126
H
Token H
Feature activation+0.000
aney
Tokenaney
Feature activation+0.000
's
Token's
Feature activation+0.000
bond
Token bond
Feature activation+0.000
at
Token at
Feature activation+0.000
,
Token,
Feature activation+6.943
in
Token in
Feature activation+2.396
Walker
Token Walker
Feature activation+0.000
's
Token's
Feature activation+0.000
eyes
Token eyes
Feature activation+7.567
,
Token,
Feature activation+8.794
H
Token H
Feature activation+0.000
aged
Tokenaged
Feature activation+0.000
orn
Tokenorn
Feature activation+0.000
's
Token's
Feature activation+0.000
greatest
Token greatest
Feature activation+0.000

INTERVAL 7.693 - 8.655
CONTAINS 0.001%

had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
moment
Token moment
Feature activation+0.000
of
Token of
Feature activation+0.000
silence
Token silence
Feature activation+0.000
for
Token for
Feature activation+8.259
H
Token H
Feature activation+0.000
ogg
Tokenogg
Feature activation+0.000
.
Token.
Feature activation+2.019
Activ
Token Activ
Feature activation+0.000
ists
Tokenists
Feature activation+0.000
Tro
Token Tro
Feature activation+0.000
opers
Tokenopers
Feature activation+0.000
determined
Token determined
Feature activation+4.910
marijuana
Token marijuana
Feature activation+0.441
intoxication
Token intoxication
Feature activation+0.000
after
Token after
Feature activation+8.287
a
Token a
Feature activation+0.000
field
Token field
Feature activation+0.000
sob
Token sob
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
ety
Tokenety
Feature activation+0.000
the
Token the
Feature activation+0.000
prize
Token prize
Feature activation+0.000
,
Token,
Feature activation+0.000
Ark
Token Ark
Feature activation+0.000
ani
Tokenani
Feature activation+1.454
-
Token-
Feature activation+7.796
H
TokenH
Feature activation+0.000
amed
Tokenamed
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
"
Token "
Feature activation+0.000
As
Token As
Feature activation+3.085
part
Token part
Feature activation+0.000
of
Token of
Feature activation+3.415
the
Token the
Feature activation+0.000
conditions
Token conditions
Feature activation+0.823
,
Token,
Feature activation+8.578
H
Token H
Feature activation+0.000
aney
Tokenaney
Feature activation+0.000
will
Token will
Feature activation+0.000
have
Token have
Feature activation+0.000
to
Token to
Feature activation+0.000
confirmed
Token confirmed
Feature activation+8.288
to
Token to
Feature activation+0.000
Ey
Token Ey
Feature activation+0.000
ewitness
Tokenewitness
Feature activation+0.000
News
Token News
Feature activation+2.778
that
Token that
Feature activation+8.397
H
Token H
Feature activation+0.000
aney
Tokenaney
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
sitting
Token sitting
Feature activation+0.000

INTERVAL 6.731 - 7.693
CONTAINS 0.002%

at
Token at
Feature activation+0.000
H
Token H
Feature activation+0.000
udd
Tokenudd
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
field
Tokenfield
Feature activation+0.000
.
Token.
Feature activation+7.437
However
Token However
Feature activation+5.701
,
Token,
Feature activation+5.793
Red
Token Red
Feature activation+0.000
kn
Tokenkn
Feature activation+0.000
app
Tokenapp
Feature activation+0.000
etic
Tokenetic
Feature activation+0.000
studies
Token studies
Feature activation+0.000
consistently
Token consistently
Feature activation+0.000
threw
Token threw
Feature activation+2.171
doubt
Token doubt
Feature activation+0.000
on
Token on
Feature activation+7.136
the
Token the
Feature activation+2.025
mon
Token mon
Feature activation+0.000
ophy
Tokenophy
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
of
Token of
Feature activation+1.657
style
Token style
Feature activation+0.000
Mr
Token Mr
Feature activation+2.905
Snow
Token Snow
Feature activation+0.000
,
Token,
Feature activation+0.000
sorry
Token sorry
Feature activation+0.000
Kit
Token Kit
Feature activation+6.772
,
Token,
Feature activation+0.000
we
Token we
Feature activation+0.000
mean
Token mean
Feature activation+0.000
Kit
Token Kit
Feature activation+4.850
!
Token!
Feature activation+0.787
year
Token year
Feature activation+0.000
.
Token.
Feature activation+1.990
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.348
9
Token9
Feature activation+0.000
Tom
Token Tom
Feature activation+6.839
H
Token H
Feature activation+0.000
anks
Tokenanks
Feature activation+0.000
posed
Token posed
Feature activation+0.000
with
Token with
Feature activation+0.000
this
Token this
Feature activation+0.000
.
Token.
Feature activation+3.365
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.524
Three
TokenThree
Feature activation+0.000
times
Token times
Feature activation+4.601
,
Token,
Feature activation+7.060
it
Token it
Feature activation+0.000
almost
Token almost
Feature activation+0.000
happened
Token happened
Feature activation+0.000
.
Token.
Feature activation+6.282
As
Token As
Feature activation+5.858

INTERVAL 5.770 - 6.731
CONTAINS 0.003%

.
Token.
Feature activation+2.268
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.081
A
TokenA
Feature activation+5.766
spokesman
Token spokesman
Feature activation+0.000
for
Token for
Feature activation+6.383
Mr
Token Mr
Feature activation+0.643
Con
Token Con
Feature activation+0.000
lan
Tokenlan
Feature activation+0.000
confirmed
Token confirmed
Feature activation+1.259
today
Token today
Feature activation+0.790
D
Token D
Feature activation+0.000
iller
Tokeniller
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
had
Token had
Feature activation+0.000
led
Token led
Feature activation+6.448
the
Token the
Feature activation+2.985
creation
Token creation
Feature activation+0.168
of
Token of
Feature activation+6.348
the
Token the
Feature activation+3.894
Fox
Token Fox
Feature activation+0.000
Urban
Token Urban
Feature activation+0.000
o
Tokeno
Feature activation+0.000
,
Token,
Feature activation+0.000
Patrick
Token Patrick
Feature activation+0.611
M
Token M
Feature activation+3.957
.
Token.
Feature activation+6.388
H
Token H
Feature activation+0.000
oe
Tokenoe
Feature activation+0.000
y
Tokeny
Feature activation+0.000
,
Token,
Feature activation+0.000
Roy
Token Roy
Feature activation+1.456
udd
Tokenudd
Feature activation+0.000
ers
Tokeners
Feature activation+0.000
field
Tokenfield
Feature activation+0.000
.
Token.
Feature activation+7.437
However
Token However
Feature activation+5.701
,
Token,
Feature activation+5.793
Red
Token Red
Feature activation+0.000
kn
Tokenkn
Feature activation+0.000
app
Tokenapp
Feature activation+0.000
did
Token did
Feature activation+0.000
suggest
Token suggest
Feature activation+1.494
have
Token have
Feature activation+2.960
a
Token a
Feature activation+1.760
specific
Token specific
Feature activation+1.344
written
Token written
Feature activation+0.000
policy
Token policy
Feature activation+0.000
on
Token on
Feature activation+6.605
the
Token the
Feature activation+2.024
topic
Token topic
Feature activation+0.000
.
Token.
Feature activation+1.417
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.770

INTERVAL 4.808 - 5.770
CONTAINS 0.007%

by
Token by
Feature activation+0.000
International
Token International
Feature activation+0.000
Business
Token Business
Feature activation+0.000
Times
Token Times
Feature activation+0.000
,
Token,
Feature activation+9.019
the
Token the
Feature activation+5.349
Colorado
Token Colorado
Feature activation+0.089
governor
Token governor
Feature activation+0.000
's
Token's
Feature activation+0.000
office
Token office
Feature activation+0.000
in
Token in
Feature activation+0.276
the
Token the
Feature activation+0.000
crash
Token crash
Feature activation+0.000
.
Token.
Feature activation+4.042
Tro
Token Tro
Feature activation+0.000
opers
Tokenopers
Feature activation+0.000
determined
Token determined
Feature activation+4.910
marijuana
Token marijuana
Feature activation+0.441
intoxication
Token intoxication
Feature activation+0.000
after
Token after
Feature activation+8.287
a
Token a
Feature activation+0.000
field
Token field
Feature activation+0.000
field
Token field
Feature activation+0.000
sob
Token sob
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
ety
Tokenety
Feature activation+0.000
test
Token test
Feature activation+0.000
.
Token.
Feature activation+5.737
A
TokenA
Feature activation+0.000
magistrate
Token magistrate
Feature activation+0.000
judge
Token judge
Feature activation+0.000
set
Token set
Feature activation+9.126
H
Token H
Feature activation+0.000
the
Token the
Feature activation+0.178
league
Token league
Feature activation+0.000
's
Token's
Feature activation+0.000
minimum
Token minimum
Feature activation+0.000
salary
Token salary
Feature activation+0.000
.
Token.
Feature activation+4.920
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.078
The
TokenThe
Feature activation+0.568
minimum
Token minimum
Feature activation+0.342
salary
Token salary
Feature activation+1.394
orn
Tokenorn
Feature activation+0.000
was
Token was
Feature activation+0.000
qualified
Token qualified
Feature activation+0.000
for
Token for
Feature activation+1.713
the
Token the
Feature activation+0.000
things
Token things
Feature activation+5.241
he
Token he
Feature activation+0.000
did
Token did
Feature activation+0.000
while
Token while
Feature activation+0.327
Walker
Token Walker
Feature activation+0.000
's
Token's
Feature activation+0.000

INTERVAL 3.847 - 4.808
CONTAINS 0.010%

with
Token with
Feature activation+1.523
the
Token the
Feature activation+1.103
following
Token following
Feature activation+0.000
paragraph
Token paragraph
Feature activation+0.000
:
Token:
Feature activation+4.700
Are
TokenAre
Feature activation+4.154
there
Token there
Feature activation+0.418
legitimate
Token legitimate
Feature activation+0.781
concerns
Token concerns
Feature activation+0.000
that
Token that
Feature activation+6.830
some
Token some
Feature activation+4.248
Federal
Token Federal
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
Society
Token Society
Feature activation+0.000
.
Token.
Feature activation+4.910
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.610
Perhaps
TokenPerhaps
Feature activation+4.731
Walker
Token Walker
Feature activation+0.000
felt
Token felt
Feature activation+5.619
that
Token that
Feature activation+8.874
H
Token H
Feature activation+0.000
establish
Token establish
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
rule
Token rule
Feature activation+0.000
.
Token.
Feature activation+0.273
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.454
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
We
TokenWe
Feature activation+0.000
love
Token love
Feature activation+0.000
death
Token death
Feature activation+0.000
but
Token but
Feature activation+4.050
if
Token if
Feature activation+3.532
you
Token you
Feature activation+0.000
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
buy
Token buy
Feature activation+4.040
that
Token that
Feature activation+0.809
one
Token one
Feature activation+0.000
,
Token,
Feature activation+1.517
I
Token I
Feature activation+0.000
guess
Token guess
Feature activation+0.000
7
Token7
Feature activation+0.000
]
Token]
Feature activation+2.667
In
Token In
Feature activation+0.000
August
Token August
Feature activation+0.000
1995
Token 1995
Feature activation+3.281
,
Token,
Feature activation+4.181
Barry
Token Barry
Feature activation+0.000
D
Token D
Feature activation+0.000
iller
Tokeniller
Feature activation+0.000
acquired
Token acquired
Feature activation+5.562
control
Token control
Feature activation+0.000

INTERVAL 2.885 - 3.847
CONTAINS 0.020%

had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
mean
Token mean
Feature activation+0.000
looking
Token looking
Feature activation+0.000
cancer
Token cancer
Feature activation+0.000
,"
Token,"
Feature activation+3.658
H
Token H
Feature activation+0.584
rus
Tokenrus
Feature activation+0.000
hes
Tokenhes
Feature activation+0.000
ky
Tokenky
Feature activation+0.000
remembers
Token remembers
Feature activation+2.158
keep
Token keep
Feature activation+3.378
their
Token their
Feature activation+0.000
custody
Token custody
Feature activation+0.000
battle
Token battle
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+3.139
the
Token the
Feature activation+0.000
press
Token press
Feature activation+0.000
for
Token for
Feature activation+0.098
starters
Token starters
Feature activation+0.000
.
Token.
Feature activation+1.791
the
Token the
Feature activation+0.000
1980
Token 1980
Feature activation+0.000
s
Tokens
Feature activation+4.878
,
Token,
Feature activation+5.040
Raven
Token Raven
Feature activation+0.000
elevated
Token elevated
Feature activation+3.242
part
Token part
Feature activation+0.000
of
Token of
Feature activation+2.133
Simon
Token Simon
Feature activation+0.250
's
Token's
Feature activation+0.000
Di
Token Di
Feature activation+0.000
this
Token this
Feature activation+0.000
.
Token.
Feature activation+0.289
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.500
Watch
TokenWatch
Feature activation+0.141
above
Token above
Feature activation+0.000
,
Token,
Feature activation+0.000
via
Token via
Feature activation+0.000
ABC
Token ABC
Feature activation+0.000
and
Token and
Feature activation+2.372
some
Token some
Feature activation+0.000
people
Token people
Feature activation+0.000
are
Token are
Feature activation+0.000
now
Token now
Feature activation+0.000
paying
Token paying
Feature activation+2.960
well
Token well
Feature activation+0.000
over
Token over
Feature activation+0.607
50
Token 50
Feature activation+0.000
per
Token per
Feature activation+0.000
cent
Token cent
Feature activation+2.289

INTERVAL 1.923 - 2.885
CONTAINS 0.032%

There
Token There
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
raid
Token raid
Feature activation+0.000
,
Token,
Feature activation+0.878
but
Token but
Feature activation+2.786
there
Token there
Feature activation+0.000
were
Token were
Feature activation+0.000
no
Token no
Feature activation+0.000
casualties
Token casualties
Feature activation+0.000
.
Token.
Feature activation+2.702
where
Token where
Feature activation+0.000
he
Token he
Feature activation+0.000
can
Token can
Feature activation+0.000
still
Token still
Feature activation+0.000
help
Token help
Feature activation+0.092
the
Token the
Feature activation+1.988
team
Token team
Feature activation+0.000
but
Token but
Feature activation+0.000
not
Token not
Feature activation+0.000
get
Token get
Feature activation+0.000
caught
Token caught
Feature activation+0.000
on
Token on
Feature activation+0.407
August
Token August
Feature activation+0.000
25
Token 25
Feature activation+0.000
.
Token.
Feature activation+2.544
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.177
The
TokenThe
Feature activation+1.347
original
Token original
Feature activation+4.558
game
Token game
Feature activation+0.000
inspired
Token inspired
Feature activation+1.415
a
Token a
Feature activation+0.000
.
Token.
Feature activation+4.885
For
Token For
Feature activation+1.611
example
Token example
Feature activation+3.183
,
Token,
Feature activation+4.382
when
Token when
Feature activation+3.377
the
Token the
Feature activation+2.139
D
Token D
Feature activation+0.000
BL
TokenBL
Feature activation+0.000
P
TokenP
Feature activation+0.000
file
Token file
Feature activation+0.000
is
Token is
Feature activation+0.344
enn
Tokenenn
Feature activation+0.000
ep
Tokenep
Feature activation+0.000
in
Tokenin
Feature activation+0.000
County
Token County
Feature activation+0.000
terminated
Token terminated
Feature activation+1.754
all
Token all
Feature activation+2.045
welfare
Token welfare
Feature activation+0.000
benefits
Token benefits
Feature activation+0.000
to
Token to
Feature activation+0.580
the
Token the
Feature activation+0.918
Ch
Token Ch
Feature activation+0.000

INTERVAL 0.962 - 1.923
CONTAINS 0.078%

,
Token,
Feature activation+0.218
and
Token and
Feature activation+3.251
even
Token even
Feature activation+0.268
more
Token more
Feature activation+0.000
fascinating
Token fascinating
Feature activation+0.000
when
Token when
Feature activation+1.600
you
Token you
Feature activation+0.000
know
Token know
Feature activation+1.895
the
Token the
Feature activation+0.000
story
Token story
Feature activation+0.037
behind
Token behind
Feature activation+1.638
ins
Tokenins
Feature activation+0.000
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
release
Token release
Feature activation+0.000
.
Token.
Feature activation+1.015
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.047
We
TokenWe
Feature activation+0.000
wish
Token wish
Feature activation+0.000
him
Token him
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
decided
Token decided
Feature activation+0.787
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+1.471
it
Token it
Feature activation+0.000
into
Token into
Feature activation+0.673
a
Token a
Feature activation+0.882
*
Token *
Feature activation+0.000
H
TokenH
Feature activation+0.000
l
Tokenl
Feature activation+0.000
mann
Tokenmann
Feature activation+0.000
himself
Token himself
Feature activation+0.000
once
Token once
Feature activation+0.000
lived
Token lived
Feature activation+0.000
.
Token.
Feature activation+1.278
She
Token She
Feature activation+0.000
bought
Token bought
Feature activation+1.329
the
Token the
Feature activation+1.339
place
Token place
Feature activation+0.000
for
Token for
Feature activation+0.000
Background
TokenBackground
Feature activation+0.000
[
Token [
Feature activation+0.000
edit
Token edit
Feature activation+0.000
]
Token ]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.289
According
TokenAccording
Feature activation+0.000
to
Token to
Feature activation+0.369
Tyr
Token Tyr
Feature activation+0.000
one
Tokenone
Feature activation+0.000
Taylor
Token Taylor
Feature activation+0.000

INTERVAL 0.000 - 0.962
CONTAINS 99.847%

economy
Token economy
Feature activation+0.000
remains
Token remains
Feature activation+0.000
sluggish
Token sluggish
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
a
Token a
Feature activation+0.000
fact
Token fact
Feature activation+0.000
Ambrose
Token Ambrose
Feature activation+0.000
was
Token was
Feature activation+0.000
happy
Token happy
Feature activation+0.000
to
Token to
Feature activation+0.000
remind
Token remind
Feature activation+0.000
-
Token-
Feature activation+0.000
page
Tokenpage
Feature activation+0.000
bill
Token bill
Feature activation+0.000
--
Token --
Feature activation+0.000
a
Token a
Feature activation+0.000
combination
Token combination
Feature activation+0.000
of
Token of
Feature activation+0.000
three
Token three
Feature activation+0.000
versions
Token versions
Feature activation+0.000
passed
Token passed
Feature activation+0.000
by
Token by
Feature activation+0.000
grip
Token grip
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
oil
Token oil
Feature activation+0.000
industry
Token industry
Feature activation+0.000
as
Token as
Feature activation+0.000
low
Token low
Feature activation+0.000
crude
Token crude
Feature activation+0.000
prices
Token prices
Feature activation+0.000
pinch
Token pinch
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
bombardment
Token bombardment
Feature activation+0.000
came
Token came
Feature activation+0.000
as
Token as
Feature activation+0.000
government
Token government
Feature activation+0.000
troops
Token troops
Feature activation+0.000
pressed
Token pressed
Feature activation+0.000
an
Token an
Feature activation+0.000
assault
Token assault
Feature activation+0.000
on
Token on
Feature activation+0.000
2009
Token 2009
Feature activation+0.000
--
Token --
Feature activation+0.000
the
Token the
Feature activation+0.000
old
Token old
Feature activation+0.000
App
Token App
Feature activation+0.000
Gallery
Token Gallery
Feature activation+0.000
is
Token is
Feature activation+0.000
gone
Token gone
Feature activation+0.000
and
Token and
Feature activation+0.000
now
Token now
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 H10.10: (feature 2723)

TOP ACTIVATIONS
MAX = 11.598

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+10.180
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
,
Token,
Feature activation+5.316
as
Token as
Feature activation+11.598
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
confronts
Token confronts
Feature activation+0.000
global
Token global
Feature activation+0.000
warming
Token warming
Feature activation+0.000
breeze
Token breeze
Feature activation+1.386
of
Token of
Feature activation+2.045
Air
Token Air
Feature activation+0.598
,
Token,
Feature activation+0.000
fresh
Token fresh
Feature activation+0.000
from
Token from
Feature activation+10.856
S
Token S
Feature activation+0.000
iesta
Tokeniesta
Feature activation+0.000
Key
Token Key
Feature activation+0.000
Beach
Token Beach
Feature activation+0.000
!
Token!
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
carbon
Tokencarbon
Feature activation+0.000
bubble
Token bubble
Feature activation+0.000
,
Token,
Feature activation+4.886
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+10.180
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
,
Token,
Feature activation+5.316
as
Token as
Feature activation+11.598
the
Token the
Feature activation+0.000
a
Token a
Feature activation+0.000
e
Token e
Feature activation+0.000
ug
Tokenug
Feature activation+0.000
enic
Tokenenic
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
,
Token,
Feature activation+9.655
S
Token S
Feature activation+0.000
anger
Tokenanger
Feature activation+0.000
encouraged
Token encouraged
Feature activation+0.000
the
Token the
Feature activation+0.000
steril
Token steril
Feature activation+0.000
been
Token been
Feature activation+0.000
growing
Token growing
Feature activation+0.000
for
Token for
Feature activation+0.708
some
Token some
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+9.108
but
Token but
Feature activation+5.953
the
Token the
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
turned
Token turned
Feature activation+0.000
cost
Token cost
Feature activation+0.000
-
Token-
Feature activation+0.000
cent
Tokencent
Feature activation+0.000
re
Tokenre
Feature activation+0.610
stacks
Token stacks
Feature activation+0.000
and
Token and
Feature activation+8.667
call
Token call
Feature activation+0.000
stacks
Token stacks
Feature activation+0.000
are
Token are
Feature activation+0.000
same
Token same
Feature activation+0.000
thing
Token thing
Feature activation+0.000
ça
Tokença
Feature activation+0.000
.
Token.
Feature activation+4.114
Ċ
TokenĊ
Feature activation+0.147
Ċ
TokenĊ
Feature activation+2.550
Not
TokenNot
Feature activation+0.045
that
Token that
Feature activation+8.575
his
Token his
Feature activation+0.126
best
Token best
Feature activation+0.000
qualities
Token qualities
Feature activation+0.000
are
Token are
Feature activation+0.000
in
Token in
Feature activation+0.300
is
Token is
Feature activation+0.602
plain
Token plain
Feature activation+0.402
that
Token that
Feature activation+7.487
the
Token the
Feature activation+0.366
core
Token core
Feature activation+0.000
of
Token of
Feature activation+8.338
his
Token his
Feature activation+0.000
identity
Token identity
Feature activation+0.000
,
Token,
Feature activation+0.280
his
Token his
Feature activation+0.000
heart
Token heart
Feature activation+0.000
Companies
Token Companies
Feature activation+0.000
stand
Token stand
Feature activation+0.000
to
Token to
Feature activation+0.000
lose
Token lose
Feature activation+0.000
billions
Token billions
Feature activation+0.000
,
Token,
Feature activation+8.298
the
Token the
Feature activation+0.000
think
Token think
Feature activation+0.000
tank
Token tank
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+2.928
current
Token current
Feature activation+0.000
situation
Token situation
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
region
Token region
Feature activation+0.000
,
Token,
Feature activation+7.773
the
Token the
Feature activation+0.000
President
Token President
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.124
Thu
TokenThu
Feature activation+0.000
Aug
Token Aug
Feature activation+0.000
13
Token 13
Feature activation+0.000
:
Token:
Feature activation+7.677
S
Token S
Feature activation+0.000
agin
Tokenagin
Feature activation+0.000
aw
Tokenaw
Feature activation+0.000
Valley
Token Valley
Feature activation+0.000
State
Token State
Feature activation+0.000
16
Token 16
Feature activation+0.000
House
Token House
Feature activation+0.000
Judiciary
Token Judiciary
Feature activation+0.000
Committee
Token Committee
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
on
Token on
Feature activation+7.575
H
Token H
Feature activation+0.000
.
Token.
Feature activation+0.000
R
TokenR
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token3
Feature activation+0.000
President
Token President
Feature activation+0.253
-
Token-
Feature activation+0.000
elect
Tokenelect
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
,"
Token,"
Feature activation+7.512
S
Token S
Feature activation+1.150
án
Tokenán
Feature activation+0.000
che
Tokenche
Feature activation+0.000
z
Tokenz
Feature activation+0.000
said
Token said
Feature activation+0.000
been
Token been
Feature activation+0.000
diagnosed
Token diagnosed
Feature activation+0.000
with
Token with
Feature activation+0.000
acute
Token acute
Feature activation+0.000
leukemia
Token leukemia
Feature activation+0.000
.
Token.
Feature activation+7.498
Because
Token Because
Feature activation+7.156
S
Token S
Feature activation+0.364
udd
Tokenudd
Feature activation+0.000
uth
Tokenuth
Feature activation+0.000
is
Token is
Feature activation+0.000
something
Token something
Feature activation+0.000
a
Token a
Feature activation+0.000
little
Token little
Feature activation+0.000
too
Token too
Feature activation+0.000
comfortable
Token comfortable
Feature activation+0.000
,
Token,
Feature activation+7.490
S
Token S
Feature activation+0.799
án
Tokenán
Feature activation+0.092
che
Tokenche
Feature activation+0.000
z
Tokenz
Feature activation+0.000
has
Token has
Feature activation+0.000
conservatives
Token conservatives
Feature activation+0.000
.
Token.
Feature activation+5.646
It
Token It
Feature activation+0.000
is
Token is
Feature activation+0.602
plain
Token plain
Feature activation+0.402
that
Token that
Feature activation+7.487
the
Token the
Feature activation+0.366
core
Token core
Feature activation+0.000
of
Token of
Feature activation+8.338
his
Token his
Feature activation+0.000
identity
Token identity
Feature activation+0.000
will
Token will
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
approve
Token approve
Feature activation+0.000
the
Token the
Feature activation+0.000
transaction
Token transaction
Feature activation+0.000
,
Token,
Feature activation+7.333
but
Token but
Feature activation+6.499
opponents
Token opponents
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
buoy
Token buoy
Feature activation+0.000
S
Token S
Feature activation+0.000
essler
Tokenessler
Feature activation+0.000
on
Token on
Feature activation+0.000
Twitter
Token Twitter
Feature activation+0.000
@
Token @
Feature activation+0.452
Marc
TokenMarc
Feature activation+7.270
S
TokenS
Feature activation+0.135
essler
Tokenessler
Feature activation+0.000
NFL
TokenNFL
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
attack
Token attack
Feature activation+0.000
was
Token was
Feature activation+0.000
detected
Token detected
Feature activation+0.000
and
Token and
Feature activation+0.242
countered
Token countered
Feature activation+0.000
,
Token,
Feature activation+7.235
Bethesda
Token Bethesda
Feature activation+0.000
,
Token,
Feature activation+0.000
Maryland
Token Maryland
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+1.543
most
Token most
Feature activation+0.000
,
Token,
Feature activation+5.154
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.849
Mr
Token Mr
Feature activation+3.057
.
Token.
Feature activation+7.161
S
Token S
Feature activation+0.000
ato
Tokenato
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000

Top DFA by src position
MAX = 12.143

,
Token,
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.016
Top resid features:
Ŀ
TokenĿ
Feature activation+0.010
Top resid features:
said
Token said
Feature activation+0.009
Top resid features:
Luke
Token Luke
Feature activation-0.117
Top resid features:
S
Token S
Feature activation+12.143
Top resid features:
uss
Tokenuss
Feature activation+0.019
Top resid features:
ams
Tokenams
Feature activation+0.089
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
co
Token co
Feature activation-0.018
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
Air
Token Air
Feature activation+0.012
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
fresh
Token fresh
Feature activation+0.017
Top resid features:
from
Token from
Feature activation-0.003
Top resid features:
S
Token S
Feature activation+11.249
Top resid features:
iesta
Tokeniesta
Feature activation+0.147
Top resid features:
Key
Token Key
Feature activation+0.090
Top resid features:
Beach
Token Beach
Feature activation+0.030
Top resid features:
!
Token!
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.032
Top resid features:
Ŀ
TokenĿ
Feature activation+0.033
Top resid features:
said
Token said
Feature activation-0.003
Top resid features:
Luke
Token Luke
Feature activation-0.058
Top resid features:
S
Token S
Feature activation+10.421
Top resid features:
uss
Tokenuss
Feature activation+0.132
Top resid features:
ams
Tokenams
Feature activation+0.084
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
co
Token co
Feature activation-0.034
Top resid features:
-
Token-
Feature activation-0.000
Top resid features:
largest
Token largest
Feature activation+0.002
Top resid features:
abortion
Token abortion
Feature activation+0.027
Top resid features:
chain
Token chain
Feature activation-0.010
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Margaret
Token Margaret
Feature activation-0.093
Top resid features:
S
Token S
Feature activation+10.500
Top resid features:
anger
Tokenanger
Feature activation+0.145
Top resid features:
âĢ
TokenâĢ
Feature activation+0.034
Top resid features:
Ļ
TokenĻ
Feature activation+0.007
Top resid features:
s
Tokens
Feature activation-0.016
Top resid features:
ideology
Token ideology
Feature activation+0.002
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.031
Top resid features:
Ŀ
TokenĿ
Feature activation+0.042
Top resid features:
Dustin
Token Dustin
Feature activation+0.047
Top resid features:
S
Token S
Feature activation+9.605
Top resid features:
iggins
Tokeniggins
Feature activation+0.057
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
a
Token a
Feature activation-0.014
Top resid features:
conservative
Token conservative
Feature activation-0.002
Top resid features:
journalist
Token journalist
Feature activation+0.009
Top resid features:
cost
Tokencost
Feature activation+0.030
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
cent
Tokencent
Feature activation+0.032
Top resid features:
res
Tokenres
Feature activation+0.039
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
S
Token S
Feature activation+8.910
Top resid features:
CC
TokenCC
Feature activation+0.362
Top resid features:
annotations
Token annotations
Feature activation-0.059
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
reporting
Token reporting
Feature activation+0.113
Top resid features:
allocations
Token allocations
Feature activation+0.075
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
c
Token c
Feature activation-0.074
Top resid features:
ach
Tokenach
Feature activation+0.026
Top resid features:
ai
Tokenai
Feature activation+0.053
Top resid features:
about
Token about
Feature activation+0.000
Top resid features:
S
Token S
Feature activation+8.614
Top resid features:
án
Tokenán
Feature activation+0.187
Top resid features:
che
Tokenche
Feature activation+0.008
Top resid features:
z
Tokenz
Feature activation+0.008
Top resid features:
now
Token now
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
be
Token be
Feature activation-0.000
Top resid features:
m
Token m
Feature activation-0.009
Top resid features:
add
Tokenadd
Feature activation+0.002
Top resid features:
ening
Tokenening
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
S
Token S
Feature activation+9.082
Top resid features:
owell
Tokenowell
Feature activation+0.080
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
more
Token more
Feature activation-0.001
Top resid features:
so
Token so
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
âĢ
TokenâĢ
Feature activation+0.007
Top resid features:
Ŀ
TokenĿ
Feature activation+0.076
Top resid features:
said
Token said
Feature activation+0.003
Top resid features:
Luke
Token Luke
Feature activation-0.150
Top resid features:
S
Token S
Feature activation+8.807
Top resid features:
uss
Tokenuss
Feature activation+0.084
Top resid features:
ams
Tokenams
Feature activation+0.086
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
co
Token co
Feature activation-0.064
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
President
Token President
Feature activation+0.030
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
Armenia
Token Armenia
Feature activation-0.002
Top resid features:
Ser
Token Ser
Feature activation-0.570
Top resid features:
zh
Tokenzh
Feature activation+0.005
Top resid features:
S
Token S
Feature activation+8.541
Top resid features:
arg
Tokenarg
Feature activation+0.269
Top resid features:
sy
Tokensy
Feature activation+0.052
Top resid features:
an
Tokenan
Feature activation+0.037
Top resid features:
said
Token said
Feature activation+0.009
Top resid features:
there
Token there
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Mon
TokenMon
Feature activation-0.018
Top resid features:
Aug
Token Aug
Feature activation-0.003
Top resid features:
10
Token 10
Feature activation+0.000
Top resid features:
:
Token:
Feature activation-0.001
Top resid features:
S
Token S
Feature activation+4.920
Top resid features:
agin
Tokenagin
Feature activation+0.007
Top resid features:
aw
Tokenaw
Feature activation+0.005
Top resid features:
Valley
Token Valley
Feature activation+0.014
Top resid features:
State
Token State
Feature activation+0.017
Top resid features:
at
Token at
Feature activation-0.001
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
staunch
Token staunch
Feature activation-0.001
Top resid features:
critic
Token critic
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.001
Top resid features:
both
Token both
Feature activation-0.015
Top resid features:
S
Token S
Feature activation+8.349
Top resid features:
OPA
TokenOPA
Feature activation+0.072
Top resid features:
and
Token and
Feature activation-0.006
Top resid features:
the
Token the
Feature activation-0.009
Top resid features:
Protect
Token Protect
Feature activation+0.008
Top resid features:
IP
Token IP
Feature activation-0.050
Top resid features:
according
Token according
Feature activation+0.014
Top resid features:
to
Token to
Feature activation-0.006
Top resid features:
Mexican
Token Mexican
Feature activation-0.002
Top resid features:
officials
Token officials
Feature activation+0.011
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
S
Token S
Feature activation+7.583
Top resid features:
án
Tokenán
Feature activation+0.609
Top resid features:
che
Tokenche
Feature activation+0.031
Top resid features:
z
Tokenz
Feature activation+0.050
Top resid features:
said
Token said
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
bone
Token bone
Feature activation-0.006
Top resid features:
marrow
Token marrow
Feature activation-0.006
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
Erik
Token Erik
Feature activation-0.111
Top resid features:
S
Token S
Feature activation+8.053
Top resid features:
udd
Tokenudd
Feature activation+0.232
Top resid features:
uth
Tokenuth
Feature activation+0.021
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
school
Token school
Feature activation-0.009
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
c
Token c
Feature activation-0.034
Top resid features:
ach
Tokenach
Feature activation+0.010
Top resid features:
ai
Tokenai
Feature activation+0.028
Top resid features:
about
Token about
Feature activation+0.001
Top resid features:
S
Token S
Feature activation+7.949
Top resid features:
án
Tokenán
Feature activation+0.230
Top resid features:
che
Tokenche
Feature activation+0.019
Top resid features:
z
Tokenz
Feature activation+0.047
Top resid features:
now
Token now
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
be
Token be
Feature activation+0.001
Top resid features:
m
Token m
Feature activation-0.019
Top resid features:
add
Tokenadd
Feature activation+0.003
Top resid features:
ening
Tokenening
Feature activation+0.000
Top resid features:
to
Token to
Feature activation-0.002
Top resid features:
S
Token S
Feature activation+8.231
Top resid features:
owell
Tokenowell
Feature activation+0.058
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
even
Token even
Feature activation+0.000
Top resid features:
more
Token more
Feature activation-0.002
Top resid features:
so
Token so
Feature activation-0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.073
Top resid features:
Ŀ
TokenĿ
Feature activation+0.043
Top resid features:
said
Token said
Feature activation-0.010
Top resid features:
Gig
Token Gig
Feature activation-0.093
Top resid features:
i
Tokeni
Feature activation-0.000
Top resid features:
S
Token S
Feature activation+7.778
Top resid features:
ohn
Tokenohn
Feature activation+0.314
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
president
Token president
Feature activation+0.002
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
Public
Token Public
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Follow
TokenFollow
Feature activation-0.011
Top resid features:
Marc
Token Marc
Feature activation-0.059
Top resid features:
S
Token S
Feature activation+7.742
Top resid features:
essler
Tokenessler
Feature activation+0.202
Top resid features:
on
Token on
Feature activation+0.004
Top resid features:
Twitter
Token Twitter
Feature activation-0.058
Top resid features:
@
Token @
Feature activation-0.005
Top resid features:
Marc
TokenMarc
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
world
Token world
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.021
Top resid features:
Ŀ
TokenĿ
Feature activation+0.015
Top resid features:
S
Token S
Feature activation+7.570
Top resid features:
ond
Tokenond
Feature activation+0.151
Top resid features:
ra
Tokenra
Feature activation+0.017
Top resid features:
Bar
Token Bar
Feature activation+0.142
Top resid features:
bour
Tokenbour
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
February
TokenFebruary
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
said
Token said
Feature activation-0.001
Top resid features:
Greg
Token Greg
Feature activation+0.016
Top resid features:
S
Token S
Feature activation+7.708
Top resid features:
ato
Tokenato
Feature activation+0.309
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
store
Token store
Feature activation-0.004
Top resid features:
manager
Token manager
Feature activation-0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.04

Head 2: 0.07

Head 3: 0.04

Head 4: 0.02

Head 5: 0.01

Head 6: 0.04

Head 7: 0.11

Head 8: 0.03

Head 9: 0.04

Head 10: 0.52

Head 11: 0.04

Positive logits

S10.24

S7.80

s6.50

SV4.51

SA4.00

SQ3.97

Sor3.94

s3.87

SAR3.86

SAS3.80

Sack3.78

Sar3.75

SI3.73

SAP3.71

SS3.64

Si3.63

Sabb3.62

SJ3.56

ss3.55

Sau3.52

Negative logits

kered-3.10

yip-2.89

umen-2.77

dn-2.75

GW-2.73

dan-2.68

lehem-2.64

ceed-2.64

glers-2.55

iries-2.49

gp-2.48

buquerque-2.46

Buyable-2.44

ERAL-2.44

-2.43

arget-2.38

ItemThumbnailImage-2.37

minster-2.34

="#-2.32

eal-2.31

INTERVAL 10.439 - 11.598
CONTAINS 0.000%

âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+10.180
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
,
Token,
Feature activation+5.316
as
Token as
Feature activation+11.598
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
confronts
Token confronts
Feature activation+0.000
global
Token global
Feature activation+0.000
warming
Token warming
Feature activation+0.000
breeze
Token breeze
Feature activation+1.386
of
Token of
Feature activation+2.045
Air
Token Air
Feature activation+0.598
,
Token,
Feature activation+0.000
fresh
Token fresh
Feature activation+0.000
from
Token from
Feature activation+10.856
S
Token S
Feature activation+0.000
iesta
Tokeniesta
Feature activation+0.000
Key
Token Key
Feature activation+0.000
Beach
Token Beach
Feature activation+0.000
!
Token!
Feature activation+0.000

INTERVAL 9.279 - 10.439
CONTAINS 0.000%

a
Token a
Feature activation+0.000
e
Token e
Feature activation+0.000
ug
Tokenug
Feature activation+0.000
enic
Tokenenic
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
,
Token,
Feature activation+9.655
S
Token S
Feature activation+0.000
anger
Tokenanger
Feature activation+0.000
encouraged
Token encouraged
Feature activation+0.000
the
Token the
Feature activation+0.000
steril
Token steril
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
carbon
Tokencarbon
Feature activation+0.000
bubble
Token bubble
Feature activation+0.000
,
Token,
Feature activation+4.886
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+10.180
in
Token in
Feature activation+0.000
which
Token which
Feature activation+0.000
,
Token,
Feature activation+5.316
as
Token as
Feature activation+11.598
the
Token the
Feature activation+0.000

INTERVAL 8.119 - 9.279
CONTAINS 0.001%

ça
Tokença
Feature activation+0.000
.
Token.
Feature activation+4.114
Ċ
TokenĊ
Feature activation+0.147
Ċ
TokenĊ
Feature activation+2.550
Not
TokenNot
Feature activation+0.045
that
Token that
Feature activation+8.575
his
Token his
Feature activation+0.126
best
Token best
Feature activation+0.000
qualities
Token qualities
Feature activation+0.000
are
Token are
Feature activation+0.000
in
Token in
Feature activation+0.300
is
Token is
Feature activation+0.602
plain
Token plain
Feature activation+0.402
that
Token that
Feature activation+7.487
the
Token the
Feature activation+0.366
core
Token core
Feature activation+0.000
of
Token of
Feature activation+8.338
his
Token his
Feature activation+0.000
identity
Token identity
Feature activation+0.000
,
Token,
Feature activation+0.280
his
Token his
Feature activation+0.000
heart
Token heart
Feature activation+0.000
cost
Token cost
Feature activation+0.000
-
Token-
Feature activation+0.000
cent
Tokencent
Feature activation+0.000
re
Tokenre
Feature activation+0.610
stacks
Token stacks
Feature activation+0.000
and
Token and
Feature activation+8.667
call
Token call
Feature activation+0.000
stacks
Token stacks
Feature activation+0.000
are
Token are
Feature activation+0.000
same
Token same
Feature activation+0.000
thing
Token thing
Feature activation+0.000
been
Token been
Feature activation+0.000
growing
Token growing
Feature activation+0.000
for
Token for
Feature activation+0.708
some
Token some
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+9.108
but
Token but
Feature activation+5.953
the
Token the
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
turned
Token turned
Feature activation+0.000
Companies
Token Companies
Feature activation+0.000
stand
Token stand
Feature activation+0.000
to
Token to
Feature activation+0.000
lose
Token lose
Feature activation+0.000
billions
Token billions
Feature activation+0.000
,
Token,
Feature activation+8.298
the
Token the
Feature activation+0.000
think
Token think
Feature activation+0.000
tank
Token tank
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+2.928

INTERVAL 6.959 - 8.119
CONTAINS 0.002%

most
Token most
Feature activation+0.000
,
Token,
Feature activation+5.154
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.849
Mr
Token Mr
Feature activation+3.057
.
Token.
Feature activation+7.161
S
Token S
Feature activation+0.000
ato
Tokenato
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
current
Token current
Feature activation+0.000
situation
Token situation
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
region
Token region
Feature activation+0.000
,
Token,
Feature activation+7.773
the
Token the
Feature activation+0.000
President
Token President
Feature activation+0.000
said
Token said
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
President
Token President
Feature activation+0.253
-
Token-
Feature activation+0.000
elect
Tokenelect
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
,"
Token,"
Feature activation+7.512
S
Token S
Feature activation+1.150
án
Tokenán
Feature activation+0.000
che
Tokenche
Feature activation+0.000
z
Tokenz
Feature activation+0.000
said
Token said
Feature activation+0.000
16
Token 16
Feature activation+0.000
House
Token House
Feature activation+0.000
Judiciary
Token Judiciary
Feature activation+0.000
Committee
Token Committee
Feature activation+0.000
hearing
Token hearing
Feature activation+0.000
on
Token on
Feature activation+7.575
H
Token H
Feature activation+0.000
.
Token.
Feature activation+0.000
R
TokenR
Feature activation+0.000
.
Token.
Feature activation+0.000
3
Token3
Feature activation+0.000
-
Token-
Feature activation+0.000
Up
TokenUp
Feature activation+0.000
to
Token to
Feature activation+0.000
raise
Token raise
Feature activation+0.000
money
Token money
Feature activation+0.000
for
Token for
Feature activation+7.086
charity
Token charity
Feature activation+0.228
.
Token.
Feature activation+5.052
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.726
They
TokenThey
Feature activation+0.000

INTERVAL 5.799 - 6.959
CONTAINS 0.003%

said
Token said
Feature activation+0.000
.
Token.
Feature activation+5.311
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.813
Some
TokenSome
Feature activation+0.000
of
Token of
Feature activation+6.430
the
Token the
Feature activation+0.000
crowd
Token crowd
Feature activation+0.000
wore
Token wore
Feature activation+0.097
shirts
Token shirts
Feature activation+0.000
that
Token that
Feature activation+0.000
growing
Token growing
Feature activation+0.000
for
Token for
Feature activation+0.708
some
Token some
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+9.108
but
Token but
Feature activation+5.953
the
Token the
Feature activation+0.000
presidential
Token presidential
Feature activation+0.000
campaign
Token campaign
Feature activation+0.000
turned
Token turned
Feature activation+0.000
a
Token a
Feature activation+0.000
eventually
Token eventually
Feature activation+0.000
approve
Token approve
Feature activation+0.000
the
Token the
Feature activation+0.000
transaction
Token transaction
Feature activation+0.000
,
Token,
Feature activation+7.333
but
Token but
Feature activation+6.499
opponents
Token opponents
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
buoy
Token buoy
Feature activation+0.000
ed
Tokened
Feature activation+0.000
j
Tokenj
Feature activation+0.000
ö
Tokenö
Feature activation+0.000
gren
Tokengren
Feature activation+0.420
's
Token's
Feature activation+0.731
syndrome
Token syndrome
Feature activation+0.000
?
Token?
Feature activation+5.930
Ċ
TokenĊ
Feature activation+0.339
Ċ
TokenĊ
Feature activation+4.551
S
TokenS
Feature activation+0.000
j
Tokenj
Feature activation+0.000
ö
Tokenö
Feature activation+0.000
the
Token the
Feature activation+0.000
weakest
Token weakest
Feature activation+0.000
and
Token and
Feature activation+0.000
most
Token most
Feature activation+0.000
vulnerable
Token vulnerable
Feature activation+0.000
.
Token.
Feature activation+5.957
From
Token From
Feature activation+4.816
its
Token its
Feature activation+0.000
conception
Token conception
Feature activation+0.124
,
Token,
Feature activation+3.793
Planned
Token Planned
Feature activation+0.000

INTERVAL 4.639 - 5.799
CONTAINS 0.007%

botched
Token botched
Feature activation+0.000
big
Token big
Feature activation+0.000
-
Token-
Feature activation+0.000
money
Tokenmoney
Feature activation+0.000
moves
Token moves
Feature activation+0.000
.
Token.
Feature activation+5.360
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.189
City
TokenCity
Feature activation+0.000
were
Token were
Feature activation+0.000
genuinely
Token genuinely
Feature activation+0.000
",
Token",
Feature activation+0.160
AFP
Token AFP
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+5.311
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.813
Some
TokenSome
Feature activation+0.000
of
Token of
Feature activation+6.430
the
Token the
Feature activation+0.000
crowd
Token crowd
Feature activation+0.000
wore
Token wore
Feature activation+0.097
0
Token0
Feature activation+0.000
just
Token just
Feature activation+0.000
after
Token after
Feature activation+0.889
the
Token the
Feature activation+0.000
break
Token break
Feature activation+0.000
.
Token.
Feature activation+4.761
While
Token While
Feature activation+5.024
S
Token S
Feature activation+0.166
esse
Tokenesse
Feature activation+0.000
gn
Tokengn
Feature activation+0.000
on
Tokenon
Feature activation+0.000
that
Token that
Feature activation+4.987
even
Token even
Feature activation+2.177
when
Token when
Feature activation+4.923
the
Token the
Feature activation+3.639
most
Token most
Feature activation+0.353
advanced
Token advanced
Feature activation+5.256
technology
Token technology
Feature activation+0.000
is
Token is
Feature activation+0.000
at
Token at
Feature activation+0.000
your
Token your
Feature activation+0.000
fingertips
Token fingertips
Feature activation+0.000
on
Token on
Feature activation+0.000
October
Token October
Feature activation+0.000
22
Token 22
Feature activation+0.000
.
Token.
Feature activation+3.717
According
Token According
Feature activation+0.287
to
Token to
Feature activation+5.084
this
Token this
Feature activation+1.912
report
Token report
Feature activation+3.486
,
Token,
Feature activation+3.913
ISIS
Token ISIS
Feature activation+0.000
was
Token was
Feature activation+0.000

INTERVAL 3.480 - 4.639
CONTAINS 0.012%

It
Token It
Feature activation+0.000
can
Token can
Feature activation+0.000
also
Token also
Feature activation+0.000
be
Token be
Feature activation+0.000
confirmed
Token confirmed
Feature activation+0.111
that
Token that
Feature activation+3.975
the
Token the
Feature activation+3.544
Carlton
Token Carlton
Feature activation+0.000
Hotel
Token Hotel
Feature activation+0.000
was
Token was
Feature activation+0.000
recently
Token recently
Feature activation+0.000
killed
Token killed
Feature activation+0.000
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
to
Token to
Feature activation+0.000
28
Token 28
Feature activation+0.000
.
Token.
Feature activation+3.655
H
Token H
Feature activation+0.000
é
Tokené
Feature activation+0.000
ctor
Tokenctor
Feature activation+0.000
Belt
Token Belt
Feature activation+0.000
r
Tokenr
Feature activation+0.000
.
Token.
Feature activation+1.032
The
Token The
Feature activation+0.000
Egyptian
Token Egyptian
Feature activation+0.000
government
Token government
Feature activation+0.000
has
Token has
Feature activation+0.000
defended
Token defended
Feature activation+4.055
the
Token the
Feature activation+0.000
incarceration
Token incarceration
Feature activation+0.000
of
Token of
Feature activation+1.471
the
Token the
Feature activation+0.000
journalists
Token journalists
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.176
taken
Token taken
Feature activation+0.000
care
Token care
Feature activation+0.000
of
Token of
Feature activation+0.000
with
Token with
Feature activation+3.961
a
Token a
Feature activation+2.121
trip
Token trip
Feature activation+0.000
to
Token to
Feature activation+0.461
the
Token the
Feature activation+1.065
principal
Token principal
Feature activation+0.000
characteristics
Token characteristics
Feature activation+0.000
of
Token of
Feature activation+1.964
S
Token S
Feature activation+0.000
DF
TokenDF
Feature activation+0.000
troops
Token troops
Feature activation+0.000
.
Token.
Feature activation+3.552
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.023
On
TokenOn
Feature activation+0.000
October
Token October
Feature activation+0.000
25
Token 25
Feature activation+3.085

INTERVAL 2.320 - 3.480
CONTAINS 0.026%

into
Token into
Feature activation+0.000
remission
Token remission
Feature activation+0.000
."
Token."
Feature activation+1.823
Patients
Token Patients
Feature activation+0.000
usually
Token usually
Feature activation+0.000
manage
Token manage
Feature activation+2.812
the
Token the
Feature activation+3.453
symptoms
Token symptoms
Feature activation+0.000
with
Token with
Feature activation+0.000
drops
Token drops
Feature activation+0.000
for
Token for
Feature activation+0.489
in
Token in
Feature activation+0.000
Finland
Token Finland
Feature activation+0.000
.
Token.
Feature activation+1.696
Jones
Token Jones
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
to
Token to
Feature activation+2.348
me
Token me
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
email
Token email
Feature activation+0.000
this
Token this
Feature activation+0.000
me
Token me
Feature activation+2.765
to
Token to
Feature activation+1.580
des
Token des
Feature activation+0.982
st
Tokenst
Feature activation+0.425
roy
Tokenroy
Feature activation+3.390
world
Token world
Feature activation+2.910
,
Token,
Feature activation+3.020
y
Token y
Feature activation+0.000
ess
Tokeness
Feature activation+0.216
,
Token,
Feature activation+1.603
but
Token but
Feature activation+2.309
to
Token to
Feature activation+2.113
everyone
Token everyone
Feature activation+0.000
who
Token who
Feature activation+0.000
took
Token took
Feature activation+0.000
offense
Token offense
Feature activation+0.000
with
Token with
Feature activation+3.400
his
Token his
Feature activation+0.000
"
Token "
Feature activation+0.000
j
Tokenj
Feature activation+0.000
oke
Tokenoke
Feature activation+0.000
",
Token",
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
L
Token L
Feature activation+0.000
acey
Tokenacey
Feature activation+0.000
Act
Token Act
Feature activation+0.000
.
Token.
Feature activation+2.924
French
Token French
Feature activation+0.000
said
Token said
Feature activation+0.000
America
Token America
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000

INTERVAL 1.160 - 2.320
CONTAINS 0.061%

iss
Token iss
Feature activation+1.332
inevitably
Token inevitably
Feature activation+0.993
doomed
Token doomed
Feature activation+2.013
-
Token -
Feature activation+1.013
alternative
Token alternative
Feature activation+1.699
iss
Token iss
Feature activation+1.672
end
Token end
Feature activation+1.226
of
Token of
Feature activation+1.063
all
Token all
Feature activation+1.201
life
Token life
Feature activation+1.394
.
Token.
Feature activation+1.214
ich
Tokenich
Feature activation+0.000
Sch
Token Sch
Feature activation+0.000
al
Tokenal
Feature activation+0.000
ke
Tokenke
Feature activation+0.000
und
Token und
Feature activation+0.622
der
Token der
Feature activation+1.239
Ab
Token Ab
Feature activation+0.000
we
Tokenwe
Feature activation+0.000
hr
Tokenhr
Feature activation+0.000
mann
Tokenmann
Feature activation+0.000
des
Token des
Feature activation+0.000
ir
Tokenir
Feature activation+0.000
E
Token E
Feature activation+0.000
zz
Tokenzz
Feature activation+0.000
or
Tokenor
Feature activation+0.000
.
Token.
Feature activation+2.855
Now
Token Now
Feature activation+1.399
,
Token,
Feature activation+3.352
government
Token government
Feature activation+0.000
forces
Token forces
Feature activation+0.000
are
Token are
Feature activation+0.000
aiming
Token aiming
Feature activation+0.000
to
Token to
Feature activation+2.853
the
Token the
Feature activation+2.979
media
Token media
Feature activation+0.000
centre
Token centre
Feature activation+0.000
of
Token of
Feature activation+1.306
the
Token the
Feature activation+1.170
State
Token State
Feature activation+0.000
Administration
Token Administration
Feature activation+0.000
of
Token of
Feature activation+0.000
Science
Token Science
Feature activation+0.001
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
clearly
Token clearly
Feature activation+0.000
still
Token still
Feature activation+0.000
bothered
Token bothered
Feature activation+0.000
by
Token by
Feature activation+1.173
his
Token his
Feature activation+0.000
incon
Token incon
Feature activation+0.000
clusive
Tokenclusive
Feature activation+0.000
spell
Token spell
Feature activation+0.000
at
Token at
Feature activation+0.092

INTERVAL 0.000 - 1.160
CONTAINS 99.888%

Plant
Token Plant
Feature activation+0.000
constituent
Token constituent
Feature activation+0.000
,
Token,
Feature activation+0.000
az
Token az
Feature activation+0.000
ul
Tokenul
Feature activation+0.000
ene
Tokenene
Feature activation+0.000
,
Token,
Feature activation+0.000
reduces
Token reduces
Feature activation+0.000
red
Token red
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
and
Token and
Feature activation+0.000
so
Token so
Feature activation+0.000
,
Token,
Feature activation+0.000
finance
Token finance
Feature activation+0.000
has
Token has
Feature activation+0.000
bo
Token bo
Feature activation+0.000
omed
Tokenomed
Feature activation+0.000
,
Token,
Feature activation+0.000
becoming
Token becoming
Feature activation+0.000
ever
Token ever
Feature activation+0.000
more
Token more
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
Life
Token Life
Feature activation+0.000
Points
Token Points
Feature activation+0.000
to
Token to
Feature activation+0.000
pull
Token pull
Feature activation+0.000
off
Token off
Feature activation+0.000
a
Token a
Feature activation+0.000
Black
Token Black
Feature activation+0.000
Rose
Token Rose
Feature activation+0.000
Dragon
Token Dragon
Feature activation+0.000
or
Token or
Feature activation+0.000
Be
Token Be
Feature activation+0.000
industry
Token industry
Feature activation+0.000
,
Token,
Feature activation+0.000
actively
Token actively
Feature activation+0.000
pursuing
Token pursuing
Feature activation+0.000
opportunities
Token opportunities
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
which
Token which
Feature activation+0.000
reduces
Token reduces
Feature activation+0.000
conflicts
Token conflicts
Feature activation+0.000
between
Token between
Feature activation+0.000
left
Token left
Feature activation+0.000
-
Token-
Feature activation+0.000
turn
Tokenturn
Feature activation+0.000
ing
Tokening
Feature activation+0.000
cars
Token cars
Feature activation+0.000
and
Token and
Feature activation+0.000
pedestrians
Token pedestrians
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 H10.10: (feature 20991)

TOP ACTIVATIONS
MAX = 10.339

.
Token.
Feature activation+1.358
The
Token The
Feature activation+0.919
only
Token only
Feature activation+3.005
place
Token place
Feature activation+5.194
we
Token we
Feature activation+0.000
see
Token see
Feature activation+10.339
it
Token it
Feature activation+0.000
used
Token used
Feature activation+0.000
is
Token is
Feature activation+0.061
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000
Riley
Token Riley
Feature activation+0.000
Nick
Token Nick
Feature activation+0.000
laus
Tokenlaus
Feature activation+0.000
Evans
Token Evans
Feature activation+0.000
at
Token at
Feature activation+7.755
The
Token The
Feature activation+9.804
O
Token O
Feature activation+0.310
cho
Tokencho
Feature activation+0.012
for
Token for
Feature activation+0.000
helping
Token helping
Feature activation+0.000
me
Token me
Feature activation+0.000
through
Token through
Feature activation+1.012
Sr
Token Sr
Feature activation+1.281
.
Token.
Feature activation+3.476
Mary
Token Mary
Feature activation+4.735
Cons
Token Cons
Feature activation+0.000
ilia
Tokenilia
Feature activation+9.005
O
Token O
Feature activation+0.359
'
Token'
Feature activation+0.000
Brien
TokenBrien
Feature activation+0.142
's
Token's
Feature activation+0.000
book
Token book
Feature activation+0.000
who
Token who
Feature activation+0.000
arrested
Token arrested
Feature activation+0.000
him
Token him
Feature activation+0.000
are
Token are
Feature activation+0.000
from
Token from
Feature activation+2.734
the
Token the
Feature activation+8.704
same
Token same
Feature activation+2.687
unit
Token unit
Feature activation+0.900
that
Token that
Feature activation+0.000
arrested
Token arrested
Feature activation+0.000
other
Token other
Feature activation+1.110
public
Token public
Feature activation+0.000
service
Token service
Feature activation+0.000
.
Token.
Feature activation+3.745
Finally
Token Finally
Feature activation+1.427
,
Token,
Feature activation+5.950
the
Token the
Feature activation+8.616
O
Token O
Feature activation+0.000
GE
TokenGE
Feature activation+0.277
will
Token will
Feature activation+0.000
promul
Token promul
Feature activation+0.000
gate
Tokengate
Feature activation+0.690
death
Token death
Feature activation+0.000
,
Token,
Feature activation+2.086
Cha
Token Cha
Feature activation+0.000
plain
Tokenplain
Feature activation+0.028
Brown
Token Brown
Feature activation+0.000
located
Token located
Feature activation+8.430
the
Token the
Feature activation+0.184
site
Token site
Feature activation+0.000
within
Token within
Feature activation+0.000
two
Token two
Feature activation+0.000
hours
Token hours
Feature activation+0.000
really
Token really
Feature activation+0.000
proud
Token proud
Feature activation+0.000
of
Token of
Feature activation+0.790
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
,"
Token,"
Feature activation+8.192
said
Token said
Feature activation+5.044
Hannah
Token Hannah
Feature activation+2.294
Thiel
Token Thiel
Feature activation+0.000
mann
Tokenmann
Feature activation+0.000
,
Token,
Feature activation+1.116
nearly
Token nearly
Feature activation+0.000
$
Token $
Feature activation+0.000
700
Token700
Feature activation+0.000
in
Token in
Feature activation+0.000
damages
Token damages
Feature activation+0.442
to
Token to
Feature activation+8.145
an
Token an
Feature activation+7.609
O
Token O
Feature activation+0.000
CS
TokenCS
Feature activation+0.440
O
TokenO
Feature activation+0.947
vehicle
Token vehicle
Feature activation+0.379
ace
Tokenace
Feature activation+0.000
ful
Tokenful
Feature activation+0.000
'
Token'
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mrs
TokenMrs
Feature activation+7.980
O
Token O
Feature activation+0.000
'
Token'
Feature activation+0.000
Neill
TokenNeill
Feature activation+0.000
said
Token said
Feature activation+0.150
her
Token her
Feature activation+0.000
Government
Token Government
Feature activation+0.000
took
Token took
Feature activation+0.000
their
Token their
Feature activation+0.000
revenge
Token revenge
Feature activation+0.000
by
Token by
Feature activation+0.000
coupling
Token coupling
Feature activation+7.817
with
Token with
Feature activation+6.549
this
Token this
Feature activation+1.672
reform
Token reform
Feature activation+0.000
a
Token a
Feature activation+0.000
Bill
Token Bill
Feature activation+0.000
Rights
Token Rights
Feature activation+0.000
and
Token and
Feature activation+0.000
Freed
Token Freed
Feature activation+0.000
oms
Tokenoms
Feature activation+0.000
.
Token.
Feature activation+5.340
The
Token The
Feature activation+7.786
O
Token O
Feature activation+0.000
CLA
TokenCLA
Feature activation+0.000
also
Token also
Feature activation+0.000
advocates
Token advocates
Feature activation+0.000
for
Token for
Feature activation+0.000
and
Token and
Feature activation+0.000
Riley
Token Riley
Feature activation+0.000
Nick
Token Nick
Feature activation+0.000
laus
Tokenlaus
Feature activation+0.000
Evans
Token Evans
Feature activation+0.000
at
Token at
Feature activation+7.755
The
Token The
Feature activation+9.804
O
Token O
Feature activation+0.310
cho
Tokencho
Feature activation+0.012
for
Token for
Feature activation+0.000
helping
Token helping
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
H
TokenH
Feature activation+0.000
are
Tokenare
Feature activation+2.569
Airport
Token Airport
Feature activation+1.710
82
Token 82
Feature activation+7.641
U
Token U
Feature activation+0.040
pt
Tokenpt
Feature activation+0.000
own
Tokenown
Feature activation+0.715
81
Token 81
Feature activation+5.935
76
Token 76
Feature activation+3.902
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
18
Token 18
Feature activation+0.000
September
Token September
Feature activation+0.515
[
Token [
Feature activation+7.609
O
TokenO
Feature activation+0.535
.
Token.
Feature activation+0.038
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.192
6
Token 6
Feature activation+0.000
$
Token $
Feature activation+0.000
700
Token700
Feature activation+0.000
in
Token in
Feature activation+0.000
damages
Token damages
Feature activation+0.442
to
Token to
Feature activation+8.145
an
Token an
Feature activation+7.609
O
Token O
Feature activation+0.000
CS
TokenCS
Feature activation+0.440
O
TokenO
Feature activation+0.947
vehicle
Token vehicle
Feature activation+0.379
,
Token,
Feature activation+4.509
the
Token the
Feature activation+0.184
site
Token site
Feature activation+0.000
within
Token within
Feature activation+0.000
two
Token two
Feature activation+0.000
hours
Token hours
Feature activation+0.000
after
Token after
Feature activation+7.591
arriving
Token arriving
Feature activation+0.000
in
Token in
Feature activation+0.000
Santiago
Token Santiago
Feature activation+0.000
.
Token.
Feature activation+3.325
The
Token The
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.406
Wolf
Token Wolf
Feature activation+0.000
Bl
Token Bl
Feature activation+0.000
itzer
Tokenitzer
Feature activation+0.000
asked
Token asked
Feature activation+7.198
Rep
Token Rep
Feature activation+0.786
.
Token.
Feature activation+4.369
Ron
Token Ron
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
(
Token (
Feature activation+0.000
to
Token to
Feature activation+0.000
assault
Token assault
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
,
Token,
Feature activation+2.348
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+7.087
O
Token O
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.027
Too
TokenToo
Feature activation+0.000
le
Tokenle
Feature activation+0.000
:
Token:
Feature activation+4.635
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.210
In
TokenIn
Feature activation+0.296
2008
Token 2008
Feature activation+3.272
,
Token,
Feature activation+7.010
there
Token there
Feature activation+0.000
were
Token were
Feature activation+0.000
several
Token several
Feature activation+0.000
figures
Token figures
Feature activation+0.000
tied
Token tied
Feature activation+0.000
.
Token.
Feature activation+5.002
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.176
The
TokenThe
Feature activation+0.658
affidavit
Token affidavit
Feature activation+0.000
said
Token said
Feature activation+6.867
that
Token that
Feature activation+5.676
after
Token after
Feature activation+4.333
a
Token a
Feature activation+0.000
day
Token day
Feature activation+0.000
of
Token of
Feature activation+0.000

Top DFA by src position
MAX = 10.596

<|endoftext|>
Token<|endoftext|>
Feature activation-0.022
Top resid features:
says
Token says
Feature activation-0.013
Top resid features:
O
Token O
Feature activation+10.596
Top resid features:
'
Token'
Feature activation+0.089
Top resid features:
M
TokenM
Feature activation+0.015
Top resid features:
urch
Tokenurch
Feature activation+0.025
Top resid features:
u
Tokenu
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.002
Top resid features:
writing
Token writing
Feature activation+0.038
Top resid features:
for
Token for
Feature activation-0.030
Top resid features:
The
Token The
Feature activation+0.001
Top resid features:
O
Token O
Feature activation+10.132
Top resid features:
cho
Tokencho
Feature activation+0.236
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
huge
Tokenhuge
Feature activation+0.005
Top resid features:
thanks
Token thanks
Feature activation-0.001
Top resid features:
go
Token go
Feature activation+0.000
Top resid features:
Sr
Token Sr
Feature activation-0.044
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Mary
Token Mary
Feature activation-0.021
Top resid features:
Cons
Token Cons
Feature activation-0.142
Top resid features:
ilia
Tokenilia
Feature activation+0.005
Top resid features:
O
Token O
Feature activation+8.989
Top resid features:
'
Token'
Feature activation+0.813
Top resid features:
Brien
TokenBrien
Feature activation+0.071
Top resid features:
's
Token's
Feature activation+0.034
Top resid features:
book
Token book
Feature activation+0.024
Top resid features:
Christian
Token Christian
Feature activation+0.005
Top resid features:
libel
Token libel
Feature activation+0.005
Top resid features:
by
Token by
Feature activation-0.002
Top resid features:
officers
Token officers
Feature activation-0.029
Top resid features:
in
Token in
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
O
Token O
Feature activation+9.341
Top resid features:
PP
TokenPP
Feature activation-0.051
Top resid features:
anti
Token anti
Feature activation-0.073
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
r
Tokenr
Feature activation-0.041
Top resid features:
ackets
Tokenackets
Feature activation+0.007
Top resid features:
for
Token for
Feature activation-0.000
Top resid features:
personal
Token personal
Feature activation-0.001
Top resid features:
gain
Token gain
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.002
Top resid features:
The
Token The
Feature activation+0.014
Top resid features:
O
Token O
Feature activation+8.815
Top resid features:
GE
TokenGE
Feature activation+0.142
Top resid features:
will
Token will
Feature activation+0.009
Top resid features:
also
Token also
Feature activation+0.003
Top resid features:
be
Token be
Feature activation+0.002
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
being
Token being
Feature activation+0.001
Top resid features:
eight
Token eight
Feature activation-0.001
Top resid features:
months
Token months
Feature activation+0.000
Top resid features:
since
Token since
Feature activation-0.003
Top resid features:
O
Token O
Feature activation+6.794
Top resid features:
'
Token'
Feature activation+0.115
Top resid features:
Neill
TokenNeill
Feature activation+0.016
Top resid features:
's
Token's
Feature activation+0.003
Top resid features:
death
Token death
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.011
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
state
Token state
Feature activation-0.046
Top resid features:
Assembly
Token Assembly
Feature activation-0.030
Top resid features:
man
Tokenman
Feature activation-0.020
Top resid features:
Daniel
Token Daniel
Feature activation+0.034
Top resid features:
O
Token O
Feature activation+6.486
Top resid features:
'
Token'
Feature activation+0.129
Top resid features:
Donnell
TokenDonnell
Feature activation+0.008
Top resid features:
--
Token --
Feature activation+0.004
Top resid features:
Ros
Token Ros
Feature activation+0.181
Top resid features:
ie
Tokenie
Feature activation+0.018
Top resid features:
00
Token00
Feature activation+0.000
Top resid features:
worth
Token worth
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
damages
Token damages
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
O
Token O
Feature activation+8.426
Top resid features:
CS
TokenCS
Feature activation+0.048
Top resid features:
O
TokenO
Feature activation+0.033
Top resid features:
vehicles
Token vehicles
Feature activation+0.043
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
but
Token but
Feature activation-0.001
Top resid features:
ill
Tokenill
Feature activation+0.004
Top resid features:
twitter
Token twitter
Feature activation+0.002
Top resid features:
Image
Token Image
Feature activation-0.000
Top resid features:
caption
Token caption
Feature activation-0.001
Top resid features:
Mrs
Token Mrs
Feature activation-0.014
Top resid features:
O
Token O
Feature activation+8.619
Top resid features:
'
Token'
Feature activation+0.179
Top resid features:
Neill
TokenNeill
Feature activation-0.007
Top resid features:
's
Token's
Feature activation+0.007
Top resid features:
daughter
Token daughter
Feature activation-0.002
Top resid features:
labelled
Token labelled
Feature activation+0.001
Top resid features:
popular
Token popular
Feature activation+0.007
Top resid features:
purposes
Token purposes
Feature activation+0.001
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Yet
Token Yet
Feature activation-0.000
Top resid features:
when
Token when
Feature activation+0.001
Top resid features:
O
Token O
Feature activation+5.261
Top resid features:
âĢ
TokenâĢ
Feature activation+0.004
Top resid features:
Ļ
TokenĻ
Feature activation+0.011
Top resid features:
Connell
TokenConnell
Feature activation+0.059
Top resid features:
appealed
Token appealed
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
Liberties
Token Liberties
Feature activation-0.032
Top resid features:
Association
Token Association
Feature activation-0.084
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
The
TokenThe
Feature activation+0.022
Top resid features:
O
Token O
Feature activation+8.320
Top resid features:
CLA
TokenCLA
Feature activation-0.110
Top resid features:
vigorously
Token vigorously
Feature activation-0.006
Top resid features:
advocates
Token advocates
Feature activation-0.013
Top resid features:
for
Token for
Feature activation-0.003
Top resid features:
authentic
Token authentic
Feature activation-0.008
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.006
Top resid features:
writing
Token writing
Feature activation+0.139
Top resid features:
for
Token for
Feature activation-0.012
Top resid features:
The
Token The
Feature activation-0.032
Top resid features:
O
Token O
Feature activation+8.128
Top resid features:
cho
Tokencho
Feature activation+0.127
Top resid features:
(
Token (
Feature activation+0.019
Top resid features:
huge
Tokenhuge
Feature activation+0.008
Top resid features:
thanks
Token thanks
Feature activation+0.001
Top resid features:
go
Token go
Feature activation+0.001
Top resid features:
are
Tokenare
Feature activation+0.001
Top resid features:
84
Token 84
Feature activation-0.049
Top resid features:
80
Token 80
Feature activation-0.083
Top resid features:
International
Token International
Feature activation+0.006
Top resid features:
80
Token 80
Feature activation+0.009
Top resid features:
O
Token O
Feature activation+6.908
Top resid features:
âĢ
TokenâĢ
Feature activation+0.014
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
H
TokenH
Feature activation-0.001
Top resid features:
are
Tokenare
Feature activation-0.002
Top resid features:
Airport
Token Airport
Feature activation+0.021
Top resid features:
happened
Token happened
Feature activation-0.002
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
18
Token 18
Feature activation+0.004
Top resid features:
September
Token September
Feature activation-0.011
Top resid features:
[
Token [
Feature activation-0.003
Top resid features:
O
TokenO
Feature activation+8.191
Top resid features:
.
Token.
Feature activation+0.168
Top resid features:
S
TokenS
Feature activation+0.052
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
6
Token 6
Feature activation+0.021
Top resid features:
September
Token September
Feature activation-0.008
Top resid features:
00
Token00
Feature activation+0.001
Top resid features:
worth
Token worth
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.002
Top resid features:
damages
Token damages
Feature activation+0.001
Top resid features:
to
Token to
Feature activation+0.009
Top resid features:
O
Token O
Feature activation+7.777
Top resid features:
CS
TokenCS
Feature activation+0.087
Top resid features:
O
TokenO
Feature activation+0.168
Top resid features:
vehicles
Token vehicles
Feature activation+0.039
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
but
Token but
Feature activation-0.000
Top resid features:
it
Token it
Feature activation+0.003
Top resid features:
being
Token being
Feature activation+0.002
Top resid features:
eight
Token eight
Feature activation+0.000
Top resid features:
months
Token months
Feature activation+0.002
Top resid features:
since
Token since
Feature activation+0.001
Top resid features:
O
Token O
Feature activation+4.591
Top resid features:
'
Token'
Feature activation+0.035
Top resid features:
Neill
TokenNeill
Feature activation+0.009
Top resid features:
's
Token's
Feature activation+0.002
Top resid features:
death
Token death
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
poor
Token poor
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
âĢ
TokenâĢ
Feature activation-0.017
Top resid features:
Ŀ
TokenĿ
Feature activation-0.003
Top resid features:
said
Token said
Feature activation-0.015
Top resid features:
O
Token O
Feature activation+8.385
Top resid features:
âĢ
TokenâĢ
Feature activation-0.006
Top resid features:
Ļ
TokenĻ
Feature activation+0.006
Top resid features:
Reilly
TokenReilly
Feature activation-0.208
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
âĢ
Token âĢ
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.003
Top resid features:
Seattle
TokenSeattle
Feature activation-0.002
Top resid features:
Police
Token Police
Feature activation-0.012
Top resid features:
Chief
Token Chief
Feature activation-0.014
Top resid features:
Kathleen
Token Kathleen
Feature activation+0.012
Top resid features:
O
Token O
Feature activation+7.510
Top resid features:
âĢ
TokenâĢ
Feature activation+0.017
Top resid features:
Ļ
TokenĻ
Feature activation+0.011
Top resid features:
Too
TokenToo
Feature activation+0.083
Top resid features:
le
Tokenle
Feature activation+0.023
Top resid features:
urged
Token urged
Feature activation-0.001
Top resid features:
2000
Token 2000
Feature activation-0.004
Top resid features:
Republican
Token Republican
Feature activation-0.015
Top resid features:
National
Token National
Feature activation-0.005
Top resid features:
Convention
Token Convention
Feature activation+0.008
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
O
Token O
Feature activation+7.774
Top resid features:
th
Tokenth
Feature activation+0.074
Top resid features:
man
Tokenman
Feature activation+0.039
Top resid features:
was
Token was
Feature activation+0.003
Top resid features:
introduced
Token introduced
Feature activation+0.002
Top resid features:
by
Token by
Feature activation+0.001
Top resid features:
in
Token in
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
document
Token document
Feature activation-0.002
Top resid features:
as
Token as
Feature activation+0.003
Top resid features:
Mark
Token Mark
Feature activation+0.076
Top resid features:
O
Token O
Feature activation+7.481
Top resid features:
th
Tokenth
Feature activation+0.142
Top resid features:
on
Tokenon
Feature activation+0.046
Top resid features:
came
Token came
Feature activation+0.002
Top resid features:
forward
Token forward
Feature activation-0.004
Top resid features:
to
Token to
Feature activation-0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.05

Head 2: 0.07

Head 3: 0.04

Head 4: 0.03

Head 5: 0.02

Head 6: 0.04

Head 7: 0.09

Head 8: 0.03

Head 9: 0.04

Head 10: 0.52

Head 11: 0.03

Positive logits

O10.69

O8.45

o7.24

Os5.98

OA5.66

Oo5.62

OX5.08

Os5.05

Oss4.97

oats4.88

OC4.87

oa4.87

Og4.84

Oy4.82

OC4.79

OD4.62

Ou4.48

Ow4.46

Od4.46

ogre4.45

Negative logits

gypt-3.63

Shiv-3.16

bilt-2.90

cham-2.89

assis-2.84

enges-2.74

esh-2.72

df-2.70

sv-2.64

dragon-2.61

ctr-2.59

dh-2.56

Chrys-2.56

gad-2.54

EStream-2.51

hend-2.50

merce-2.48

fts-2.45

ch-2.44

ulia-2.43

INTERVAL 9.306 - 10.339
CONTAINS 0.000%

.
Token.
Feature activation+1.358
The
Token The
Feature activation+0.919
only
Token only
Feature activation+3.005
place
Token place
Feature activation+5.194
we
Token we
Feature activation+0.000
see
Token see
Feature activation+10.339
it
Token it
Feature activation+0.000
used
Token used
Feature activation+0.000
is
Token is
Feature activation+0.061
in
Token in
Feature activation+0.000
those
Token those
Feature activation+0.000
Riley
Token Riley
Feature activation+0.000
Nick
Token Nick
Feature activation+0.000
laus
Tokenlaus
Feature activation+0.000
Evans
Token Evans
Feature activation+0.000
at
Token at
Feature activation+7.755
The
Token The
Feature activation+9.804
O
Token O
Feature activation+0.310
cho
Tokencho
Feature activation+0.012
for
Token for
Feature activation+0.000
helping
Token helping
Feature activation+0.000
me
Token me
Feature activation+0.000

INTERVAL 8.272 - 9.306
CONTAINS 0.000%

who
Token who
Feature activation+0.000
arrested
Token arrested
Feature activation+0.000
him
Token him
Feature activation+0.000
are
Token are
Feature activation+0.000
from
Token from
Feature activation+2.734
the
Token the
Feature activation+8.704
same
Token same
Feature activation+2.687
unit
Token unit
Feature activation+0.900
that
Token that
Feature activation+0.000
arrested
Token arrested
Feature activation+0.000
other
Token other
Feature activation+1.110
death
Token death
Feature activation+0.000
,
Token,
Feature activation+2.086
Cha
Token Cha
Feature activation+0.000
plain
Tokenplain
Feature activation+0.028
Brown
Token Brown
Feature activation+0.000
located
Token located
Feature activation+8.430
the
Token the
Feature activation+0.184
site
Token site
Feature activation+0.000
within
Token within
Feature activation+0.000
two
Token two
Feature activation+0.000
hours
Token hours
Feature activation+0.000
through
Token through
Feature activation+1.012
Sr
Token Sr
Feature activation+1.281
.
Token.
Feature activation+3.476
Mary
Token Mary
Feature activation+4.735
Cons
Token Cons
Feature activation+0.000
ilia
Tokenilia
Feature activation+9.005
O
Token O
Feature activation+0.359
'
Token'
Feature activation+0.000
Brien
TokenBrien
Feature activation+0.142
's
Token's
Feature activation+0.000
book
Token book
Feature activation+0.000
public
Token public
Feature activation+0.000
service
Token service
Feature activation+0.000
.
Token.
Feature activation+3.745
Finally
Token Finally
Feature activation+1.427
,
Token,
Feature activation+5.950
the
Token the
Feature activation+8.616
O
Token O
Feature activation+0.000
GE
TokenGE
Feature activation+0.277
will
Token will
Feature activation+0.000
promul
Token promul
Feature activation+0.000
gate
Tokengate
Feature activation+0.690

INTERVAL 7.238 - 8.272
CONTAINS 0.001%

âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
H
TokenH
Feature activation+0.000
are
Tokenare
Feature activation+2.569
Airport
Token Airport
Feature activation+1.710
82
Token 82
Feature activation+7.641
U
Token U
Feature activation+0.040
pt
Tokenpt
Feature activation+0.000
own
Tokenown
Feature activation+0.715
81
Token 81
Feature activation+5.935
76
Token 76
Feature activation+3.902
and
Token and
Feature activation+0.000
Riley
Token Riley
Feature activation+0.000
Nick
Token Nick
Feature activation+0.000
laus
Tokenlaus
Feature activation+0.000
Evans
Token Evans
Feature activation+0.000
at
Token at
Feature activation+7.755
The
Token The
Feature activation+9.804
O
Token O
Feature activation+0.310
cho
Tokencho
Feature activation+0.012
for
Token for
Feature activation+0.000
helping
Token helping
Feature activation+0.000
nearly
Token nearly
Feature activation+0.000
$
Token $
Feature activation+0.000
700
Token700
Feature activation+0.000
in
Token in
Feature activation+0.000
damages
Token damages
Feature activation+0.442
to
Token to
Feature activation+8.145
an
Token an
Feature activation+7.609
O
Token O
Feature activation+0.000
CS
TokenCS
Feature activation+0.440
O
TokenO
Feature activation+0.947
vehicle
Token vehicle
Feature activation+0.379
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
18
Token 18
Feature activation+0.000
September
Token September
Feature activation+0.515
[
Token [
Feature activation+7.609
O
TokenO
Feature activation+0.535
.
Token.
Feature activation+0.038
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.192
6
Token 6
Feature activation+0.000
really
Token really
Feature activation+0.000
proud
Token proud
Feature activation+0.000
of
Token of
Feature activation+0.790
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
,"
Token,"
Feature activation+8.192
said
Token said
Feature activation+5.044
Hannah
Token Hannah
Feature activation+2.294
Thiel
Token Thiel
Feature activation+0.000
mann
Tokenmann
Feature activation+0.000
,
Token,
Feature activation+1.116

INTERVAL 6.204 - 7.238
CONTAINS 0.001%

took
Token took
Feature activation+0.000
their
Token their
Feature activation+0.000
revenge
Token revenge
Feature activation+0.000
by
Token by
Feature activation+0.000
coupling
Token coupling
Feature activation+7.817
with
Token with
Feature activation+6.549
this
Token this
Feature activation+1.672
reform
Token reform
Feature activation+0.000
a
Token a
Feature activation+0.000
Bill
Token Bill
Feature activation+0.000
depri
Token depri
Feature activation+0.000
bl
Tokenbl
Feature activation+0.000
onde
Tokenonde
Feature activation+0.000
"
Token"
Feature activation+0.000
comment
Token comment
Feature activation+0.000
,
Token,
Feature activation+0.000
Mrs
Token Mrs
Feature activation+6.682
O
Token O
Feature activation+0.000
'
Token'
Feature activation+0.000
Neill
TokenNeill
Feature activation+0.000
said
Token said
Feature activation+0.000
no
Token no
Feature activation+0.000
to
Token to
Feature activation+0.000
assault
Token assault
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
,
Token,
Feature activation+2.348
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+7.087
O
Token O
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+1.027
Too
TokenToo
Feature activation+0.000
le
Tokenle
Feature activation+0.000
own
Tokenown
Feature activation+0.715
81
Token 81
Feature activation+5.935
76
Token 76
Feature activation+3.902
Port
Token Port
Feature activation+0.000
age
Tokenage
Feature activation+0.000
80
Token 80
Feature activation+6.270
Park
Token Park
Feature activation+0.000
81
Token 81
Feature activation+2.634
82
Token 82
Feature activation+0.804
80
Token 80
Feature activation+1.164
80
Token 80
Feature activation+1.148
:
Token:
Feature activation+4.635
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.210
In
TokenIn
Feature activation+0.296
2008
Token 2008
Feature activation+3.272
,
Token,
Feature activation+7.010
there
Token there
Feature activation+0.000
were
Token were
Feature activation+0.000
several
Token several
Feature activation+0.000
figures
Token figures
Feature activation+0.000
tied
Token tied
Feature activation+0.000

INTERVAL 5.170 - 6.204
CONTAINS 0.003%

of
Token of
Feature activation+0.000
Rights
Token Rights
Feature activation+0.000
and
Token and
Feature activation+0.000
Freed
Token Freed
Feature activation+0.000
oms
Tokenoms
Feature activation+0.000
.
Token.
Feature activation+5.340
The
Token The
Feature activation+7.786
O
Token O
Feature activation+0.000
CLA
TokenCLA
Feature activation+0.000
also
Token also
Feature activation+0.000
advocates
Token advocates
Feature activation+0.000
ression
Tokenression
Feature activation+0.000
cl
Token cl
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
to
Token to
Feature activation+0.375
me
Token me
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+5.605
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
hard
Token hard
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.549
The
TokenThe
Feature activation+0.000
event
Token event
Feature activation+0.000
truly
Token truly
Feature activation+0.000
began
Token began
Feature activation+0.000
when
Token when
Feature activation+6.167
a
Token a
Feature activation+0.000
second
Token second
Feature activation+0.000
RV
Token RV
Feature activation+0.000
r
Token r
Feature activation+0.000
umbled
Tokenumbled
Feature activation+0.000
across
Token across
Feature activation+0.194
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
.
Token.
Feature activation+4.235
If
Token If
Feature activation+5.502
only
Token only
Feature activation+5.443
she
Token she
Feature activation+0.000
had
Token had
Feature activation+0.000
also
Token also
Feature activation+0.000
been
Token been
Feature activation+0.000
able
Token able
Feature activation+0.000
Newspaper
Token Newspaper
Feature activation+0.000
End
Token End
Feature activation+0.000
orse
Tokenorse
Feature activation+0.000
ments
Tokenments
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.359
Read
TokenRead
Feature activation+2.138
the
Token the
Feature activation+1.869
entire
Token entire
Feature activation+3.027
poem
Token poem
Feature activation+1.889
below
Token below
Feature activation+0.000

INTERVAL 4.136 - 5.170
CONTAINS 0.007%

Times
Token Times
Feature activation+0.041
will
Token will
Feature activation+0.000
be
Token be
Feature activation+2.404
responsible
Token responsible
Feature activation+0.000
for
Token for
Feature activation+2.220
preserving
Token preserving
Feature activation+5.005
the
Token the
Feature activation+0.924
independence
Token independence
Feature activation+0.607
of
Token of
Feature activation+4.093
the
Token the
Feature activation+2.030
country
Token country
Feature activation+0.000
introduced
Token introduced
Feature activation+1.142
the
Token the
Feature activation+0.000
bill
Token bill
Feature activation+0.000
last
Token last
Feature activation+0.000
month
Token month
Feature activation+0.000
.
Token.
Feature activation+4.593
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.782
"
Token"
Feature activation+0.272
You
TokenYou
Feature activation+0.000
couldn
Token couldn
Feature activation+0.000
any
Token any
Feature activation+0.735
so
Token so
Feature activation+0.000
far
Token far
Feature activation+0.000
.
Token.
Feature activation+4.115
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.313
The
TokenThe
Feature activation+1.527
group
Token group
Feature activation+0.593
uses
Token uses
Feature activation+3.260
dynamic
Token dynamic
Feature activation+0.000
DNS
Token DNS
Feature activation+0.000
taken
Token taken
Feature activation+0.251
the
Token the
Feature activation+0.000
case
Token case
Feature activation+0.000
.
Token.
Feature activation+2.640
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.876
"
Token"
Feature activation+0.000
It
TokenIt
Feature activation+0.000
took
Token took
Feature activation+0.000
the
Token the
Feature activation+0.000
case
Token case
Feature activation+0.000
college
Token college
Feature activation+0.000
campuses
Token campuses
Feature activation+0.000
across
Token across
Feature activation+0.194
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
.
Token.
Feature activation+4.235
If
Token If
Feature activation+5.502
only
Token only
Feature activation+5.443
she
Token she
Feature activation+0.000
had
Token had
Feature activation+0.000
also
Token also
Feature activation+0.000

INTERVAL 3.102 - 4.136
CONTAINS 0.010%

Read
TokenRead
Feature activation+2.138
the
Token the
Feature activation+1.869
entire
Token entire
Feature activation+3.027
poem
Token poem
Feature activation+1.889
below
Token below
Feature activation+0.000
.
Token.
Feature activation+3.284
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.415
i
Tokeni
Feature activation+0.000
saw
Token saw
Feature activation+1.537
4
Token 4
Feature activation+0.000
'
Token'
Feature activation+0.000
Mah
TokenMah
Feature activation+0.000
ony
Tokenony
Feature activation+0.000
.
Token.
Feature activation+1.293
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.133
Federal
TokenFederal
Feature activation+0.000
Minister
Token Minister
Feature activation+0.000
of
Token of
Feature activation+0.000
Human
Token Human
Feature activation+0.000
Resources
Token Resources
Feature activation+0.000
are
Token are
Feature activation+0.000
irre
Token irre
Feature activation+0.000
con
Tokencon
Feature activation+0.000
cil
Tokencil
Feature activation+0.000
able
Tokenable
Feature activation+0.000
with
Token with
Feature activation+3.461
the
Token the
Feature activation+3.665
International
Token International
Feature activation+0.000
Covenant
Token Covenant
Feature activation+0.000
on
Token on
Feature activation+0.000
Civil
Token Civil
Feature activation+0.000
this
Token this
Feature activation+1.672
reform
Token reform
Feature activation+0.000
a
Token a
Feature activation+0.000
Bill
Token Bill
Feature activation+0.000
depri
Token depri
Feature activation+0.000
ving
Tokenving
Feature activation+3.134
the
Token the
Feature activation+0.184
smaller
Token smaller
Feature activation+0.000
tenants
Token tenants
Feature activation+0.000
of
Token of
Feature activation+0.703
the
Token the
Feature activation+0.000
Operation
Token Operation
Feature activation+0.000
Aurora
Token Aurora
Feature activation+0.000
,
Token,
Feature activation+1.092
the
Token the
Feature activation+0.000
group
Token group
Feature activation+0.000
,
Token,
Feature activation+3.237
said
Token said
Feature activation+4.940
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
from
Token from
Feature activation+0.000
China
Token China
Feature activation+0.000

INTERVAL 2.068 - 3.102
CONTAINS 0.019%

have
Token have
Feature activation+0.000
even
Token even
Feature activation+0.000
taken
Token taken
Feature activation+0.251
the
Token the
Feature activation+0.000
case
Token case
Feature activation+0.000
.
Token.
Feature activation+2.640
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.876
"
Token"
Feature activation+0.000
It
TokenIt
Feature activation+0.000
took
Token took
Feature activation+0.000
10
Token10
Feature activation+0.000
million
Token million
Feature activation+0.000
loan
Token loan
Feature activation+0.000
guarantee
Token guarantee
Feature activation+0.000
approved
Token approved
Feature activation+0.000
by
Token by
Feature activation+2.787
the
Token the
Feature activation+2.846
U
Token U
Feature activation+0.000
.
Token.
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
Lightning
Token Lightning
Feature activation+0.000
all
Token all
Feature activation+0.000
have
Token have
Feature activation+0.000
in
Token in
Feature activation+0.000
common
Token common
Feature activation+0.000
?
Token?
Feature activation+2.138
They
Token They
Feature activation+0.000
spent
Token spent
Feature activation+0.000
this
Token this
Feature activation+0.000
week
Token week
Feature activation+0.000
beating
Token beating
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.783
O
Token O
Feature activation+0.000
ta
Tokenta
Feature activation+0.537
said
Token said
Feature activation+0.000
.
Token.
Feature activation+2.854
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.744
K
TokenK
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
uki
Tokenuki
Feature activation+0.000
to
Token to
Feature activation+0.000
present
Token present
Feature activation+2.346
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
ball
Token ball
Feature activation+0.000
to
Token to
Feature activation+2.618
the
Token the
Feature activation+0.000
12
Token 12
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Man
Token Man
Feature activation+0.000
fans
Token fans
Feature activation+0.000

INTERVAL 1.034 - 2.068
CONTAINS 0.044%

imminent
Token imminent
Feature activation+0.000
disaster
Token disaster
Feature activation+0.000
when
Token when
Feature activation+0.000
nurses
Token nurses
Feature activation+0.000
unh
Token unh
Feature activation+0.000
ooked
Tokenooked
Feature activation+1.799
the
Token the
Feature activation+0.025
vent
Token vent
Feature activation+0.000
il
Tokenil
Feature activation+0.000
ators
Tokenators
Feature activation+0.000
and
Token and
Feature activation+0.000
ric
Tokenric
Feature activation+0.000
on
Tokenon
Feature activation+0.680
8
Token 8
Feature activation+0.288
).
Token).
Feature activation+0.967
Either
TokenEither
Feature activation+0.952
way
Token way
Feature activation+1.765
if
Token if
Feature activation+1.934
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.124
P
Token P
Feature activation+0.000
VP
TokenVP
Feature activation+0.000
himself
Token himself
Feature activation+0.000
what
Token what
Feature activation+0.072
would
Token would
Feature activation+0.000
if
Token if
Feature activation+0.000
happen
Token happen
Feature activation+0.000
if
Token if
Feature activation+1.152
Will
Token Will
Feature activation+0.000
y
Tokeny
Feature activation+0.000
Won
Token Won
Feature activation+0.000
ka
Tokenka
Feature activation+0.000
was
Token was
Feature activation+0.000
not
Token not
Feature activation+0.000
compatible
Token compatible
Feature activation+0.000
with
Token with
Feature activation+0.000
OCD
Token OCD
Feature activation+0.000
I
TokenI
Feature activation+0.000
(
Token (
Feature activation+1.349
or
Tokenor
Feature activation+0.000
any
Token any
Feature activation+0.768
other
Token other
Feature activation+1.302
imp
Token imp
Feature activation+0.000
orter
Tokenorter
Feature activation+0.000
Sal
TokenSal
Feature activation+0.000
ah
Tokenah
Feature activation+0.000
Ab
Token Ab
Feature activation+0.000
des
Tokendes
Feature activation+0.000
lam
Tokenlam
Feature activation+0.000
,
Token,
Feature activation+1.693
26
Token 26
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
subject
Token subject
Feature activation+0.000

INTERVAL 0.000 - 1.034
CONTAINS 99.914%

Ċ
TokenĊ
Feature activation+0.000
E
TokenE
Feature activation+0.000
than
Tokenthan
Feature activation+0.000
E
Token E
Feature activation+0.000
in
Tokenin
Feature activation+0.000
horn
Tokenhorn
Feature activation+0.000
:
Token:
Feature activation+0.000
We
Token We
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
massage
Token massage
Feature activation+0.000
while
Token while
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Epstein
Token Epstein
Feature activation+0.000
masturb
Token masturb
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
himself
Token himself
Feature activation+0.000
."
Token."
Feature activation+0.000
Occasionally
Token Occasionally
Feature activation+0.000
,
Token,
Feature activation+0.000
(
Token (
Feature activation+0.000
1
Token1
Feature activation+0.000
:
Token:
Feature activation+0.000
30
Token30
Feature activation+0.000
p
Token p
Feature activation+0.000
.
Token.
Feature activation+0.000
m
Tokenm
Feature activation+0.000
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Dec
TokenDec
Feature activation+0.000
in
Token in
Feature activation+0.000
Budapest
Token Budapest
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+0.000
posting
Token posting
Feature activation+0.000
the
Token the
Feature activation+0.000
snap
Token snap
Feature activation+0.000
on
Token on
Feature activation+0.000
Instagram
Token Instagram
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
most
Token most
Feature activation+0.000
esports
Token esports
Feature activation+0.000
the
Token the
Feature activation+0.000
coach
Token coach
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
have
Token have
Feature activation+0.000
this
Token this
Feature activation+0.000
level
Token level
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 H10.10: (feature 3041)

TOP ACTIVATIONS
MAX = 8.169

what
Token what
Feature activation+0.000
constituted
Token constituted
Feature activation+0.000
a
Token a
Feature activation+0.000
personal
Token personal
Feature activation+0.000
attack
Token attack
Feature activation+0.000
,
Token,
Feature activation+8.169
Cohen
Token Cohen
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
team
Token team
Feature activation+0.000
.
Token.
Feature activation+0.476
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
51
Token51
Feature activation+8.032
When
Token When
Feature activation+5.660
he
Token he
Feature activation+0.000
arrived
Token arrived
Feature activation+0.958
at
Token at
Feature activation+4.700
the
Token the
Feature activation+1.463
a
Token a
Feature activation+0.000
frame
Token frame
Feature activation+0.000
.
Token.
Feature activation+0.943
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.468
Miss
TokenMiss
Feature activation+7.972
J
Token J
Feature activation+0.204
arl
Tokenarl
Feature activation+0.000
said
Token said
Feature activation+0.639
:
Token:
Feature activation+0.000
''
Token ''
Feature activation+0.000
upwards
Token upwards
Feature activation+0.000
of
Token of
Feature activation+0.000
$
Token $
Feature activation+0.000
20
Token20
Feature activation+0.000
billion
Token billion
Feature activation+0.000
in
Token in
Feature activation+7.050
buying
Token buying
Feature activation+6.267
spectrum
Token spectrum
Feature activation+0.000
,
Token,
Feature activation+0.166
setting
Token setting
Feature activation+1.538
up
Token up
Feature activation+1.452
.
Token.
Feature activation+3.157
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.390
Not
TokenNot
Feature activation+0.000
only
Token only
Feature activation+1.760
is
Token is
Feature activation+6.945
there
Token there
Feature activation+0.021
pressure
Token pressure
Feature activation+0.000
to
Token to
Feature activation+0.000
build
Token build
Feature activation+0.480
,
Token,
Feature activation+2.115
happened
Token happened
Feature activation+0.000
a
Token a
Feature activation+1.017
little
Token little
Feature activation+0.000
bit
Token bit
Feature activation+0.000
later
Token later
Feature activation+0.000
the
Token the
Feature activation+6.584
riders
Token riders
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
peeled
Token peeled
Feature activation+0.000
out
Token out
Feature activation+0.000
.
Token.
Feature activation+3.124
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
therefore
Token therefore
Feature activation+0.000
submitted
Token submitted
Feature activation+4.122
the
Token the
Feature activation+6.568
specification
Token specification
Feature activation+0.548
for
Token for
Feature activation+2.928
Public
Token Public
Feature activation+0.317
Review
Token Review
Feature activation+0.000
despite
Token despite
Feature activation+1.392
.
Token.
Feature activation+0.427
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.116
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
50
Token50
Feature activation+6.437
Hearing
Token Hearing
Feature activation+1.182
this
Token this
Feature activation+0.273
,
Token,
Feature activation+4.441
Jesus
Token Jesus
Feature activation+0.000
said
Token said
Feature activation+0.000
block
Token block
Feature activation+0.000
of
Token of
Feature activation+0.000
Beach
Token Beach
Feature activation+0.000
Boulevard
Token Boulevard
Feature activation+0.000
-
Token -
Feature activation+1.470
#
Token #
Feature activation+6.389
J
TokenJ
Feature activation+0.068
SO
TokenSO
Feature activation+0.437
responded
Token responded
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
hit
Token hit
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.112
G
Token G
Feature activation+0.000
ros
Tokenros
Feature activation+6.384
j
Tokenj
Feature activation+0.176
ean
Tokenean
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
of
Token of
Feature activation+0.000
$
Token $
Feature activation+0.000
20
Token20
Feature activation+0.000
billion
Token billion
Feature activation+0.000
in
Token in
Feature activation+7.050
buying
Token buying
Feature activation+6.267
spectrum
Token spectrum
Feature activation+0.000
,
Token,
Feature activation+0.166
setting
Token setting
Feature activation+1.538
up
Token up
Feature activation+1.452
the
Token the
Feature activation+0.846
.
Token.
Feature activation+5.329
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.789
In
TokenIn
Feature activation+1.164
Sweden
Token Sweden
Feature activation+1.362
,
Token,
Feature activation+6.224
whose
Token whose
Feature activation+0.017
system
Token system
Feature activation+0.000
of
Token of
Feature activation+0.848
cradle
Token cradle
Feature activation+0.000
-
Token-
Feature activation+0.000
Frag
TokenFrag
Feature activation+0.000
ile
Tokenile
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.181
,
Token,
Feature activation+0.010
but
Token but
Feature activation+6.207
their
Token their
Feature activation+0.000
experimental
Token experimental
Feature activation+0.000
approach
Token approach
Feature activation+0.000
deserved
Token deserved
Feature activation+0.000
a
Token a
Feature activation+0.000
an
Token an
Feature activation+1.627
avid
Token avid
Feature activation+3.457
reader
Token reader
Feature activation+0.000
,
Token,
Feature activation+0.134
especially
Token especially
Feature activation+0.071
of
Token of
Feature activation+6.053
classic
Token classic
Feature activation+4.933
literature
Token literature
Feature activation+0.000
.
Token.
Feature activation+2.203
His
Token His
Feature activation+0.475
parents
Token parents
Feature activation+0.000
w
Tokenw
Feature activation+0.000
iq
Tokeniq
Feature activation+0.000
K
TokenK
Feature activation+0.000
Z
TokenZ
Feature activation+0.000
sv
Tokensv
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+5.908
Larry
Token Larry
Feature activation+0.000
Sp
Token Sp
Feature activation+0.000
ru
Tokenru
Feature activation+0.000
ill
Tokenill
Feature activation+0.000
Jr
Token Jr
Feature activation+0.000
which
Token which
Feature activation+0.000
gained
Token gained
Feature activation+0.000
independence
Token independence
Feature activation+0.000
in
Token in
Feature activation+0.118
2011
Token 2011
Feature activation+0.000
.
Token.
Feature activation+5.899
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.162
Human
TokenHuman
Feature activation+0.000
Rights
Token Rights
Feature activation+0.000
Watch
Token Watch
Feature activation+0.000
La
Token La
Feature activation+0.000
Const
Token Const
Feature activation+0.000
it
Tokenit
Feature activation+0.000
uc
Tokenuc
Feature activation+0.000
ion
Tokenion
Feature activation+0.000
in
Token in
Feature activation+5.858
J
Token J
Feature activation+0.000
á
Tokená
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
a
Tokena
Feature activation+0.000
old
Token old
Feature activation+0.948
us
Tokenus
Feature activation+0.136
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.087
synagogue
Token synagogue
Feature activation+0.000
leader
Token leader
Feature activation+0.000
.
Token.
Feature activation+5.679
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+2.100
Your
TokenYour
Feature activation+0.000
daughter
Token daughter
Feature activation+1.711
is
Token is
Feature activation+1.463
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
51
Token51
Feature activation+8.032
When
Token When
Feature activation+5.660
he
Token he
Feature activation+0.000
arrived
Token arrived
Feature activation+0.958
at
Token at
Feature activation+4.700
the
Token the
Feature activation+1.463
house
Token house
Feature activation+1.676
.
Token.
Feature activation+3.405
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.647
White
TokenWhite
Feature activation+0.000
hurst
Tokenhurst
Feature activation+0.000
said
Token said
Feature activation+5.457
that
Token that
Feature activation+4.655
Red
Token Red
Feature activation+0.000
Hat
Token Hat
Feature activation+0.000
only
Token only
Feature activation+0.000
renewed
Token renewed
Feature activation+0.923

Top DFA by src position
MAX = 9.198

comments
Token comments
Feature activation-0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
personal
Token personal
Feature activation-0.003
Top resid features:
attacks
Token attacks
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
J
Token J
Feature activation+9.198
Top resid features:
igsaw
Tokenigsaw
Feature activation-0.046
Top resid features:
developed
Token developed
Feature activation+0.004
Top resid features:
its
Token its
Feature activation-0.002
Top resid features:
toxicity
Token toxicity
Feature activation-0.064
Top resid features:
scores
Token scores
Feature activation-0.025
Top resid features:
came
Token came
Feature activation-0.002
Top resid features:
from
Token from
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
house
Token house
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
J
Token J
Feature activation+5.650
Top resid features:
air
Tokenair
Feature activation+0.049
Top resid features:
us
Tokenus
Feature activation-0.006
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
synagogue
Token synagogue
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.045
Top resid features:
,
Token,
Feature activation+0.012
Top resid features:
Miss
Token Miss
Feature activation-0.096
Top resid features:
J
Token J
Feature activation+8.348
Top resid features:
arl
Tokenarl
Feature activation+0.149
Top resid features:
will
Token will
Feature activation+0.002
Top resid features:
be
Token be
Feature activation-0.002
Top resid features:
keeping
Token keeping
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.006
Top resid features:
Indian
Token Indian
Feature activation-0.011
Top resid features:
broadband
Token broadband
Feature activation+0.002
Top resid features:
user
Token user
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
making
Token making
Feature activation+0.000
Top resid features:
J
Token J
Feature activation+5.951
Top resid features:
io
Tokenio
Feature activation+0.087
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
country
Token country
Feature activation+0.002
Top resid features:
's
Token's
Feature activation-0.000
Top resid features:
largest
Token largest
Feature activation-0.001
Top resid features:
John
Token John
Feature activation-0.003
Top resid features:
Kem
Token Kem
Feature activation+0.103
Top resid features:
m
Tokenm
Feature activation-0.003
Top resid features:
erer
Tokenerer
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
J
Token J
Feature activation+8.154
Top resid features:
iff
Tokeniff
Feature activation+0.094
Top resid features:
âĢ
TokenâĢ
Feature activation+0.028
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
s
Tokens
Feature activation+0.011
Top resid features:
vice
Token vice
Feature activation-0.001
Top resid features:
ground
Token ground
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
Four
TokenFour
Feature activation+0.052
Top resid features:
j
Token j
Feature activation+7.628
Top resid features:
oc
Tokenoc
Feature activation+0.088
Top resid features:
keys
Tokenkeys
Feature activation+0.001
Top resid features:
close
Token close
Feature activation-0.017
Top resid features:
behind
Token behind
Feature activation-0.001
Top resid features:
got
Token got
Feature activation+0.005
Top resid features:
neither
Token neither
Feature activation-0.003
Top resid features:
mentioned
Token mentioned
Feature activation-0.002
Top resid features:
in
Token in
Feature activation+0.006
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
original
Token original
Feature activation+0.155
Top resid features:
J
Token J
Feature activation+6.798
Top resid features:
SR
TokenSR
Feature activation+0.301
Top resid features:
submission
Token submission
Feature activation-0.112
Top resid features:
nor
Token nor
Feature activation+0.000
Top resid features:
recorded
Token recorded
Feature activation+0.007
Top resid features:
in
Token in
Feature activation+0.005
Top resid features:
came
Token came
Feature activation-0.001
Top resid features:
from
Token from
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
house
Token house
Feature activation-0.003
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
J
Token J
Feature activation+7.350
Top resid features:
air
Tokenair
Feature activation+0.042
Top resid features:
us
Tokenus
Feature activation-0.012
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
synagogue
Token synagogue
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.043
Top resid features:
-
Token -
Feature activation-0.008
Top resid features:
#
Token #
Feature activation+0.041
Top resid features:
J
TokenJ
Feature activation+6.566
Top resid features:
SO
TokenSO
Feature activation+0.056
Top resid features:
is
Token is
Feature activation-0.007
Top resid features:
working
Token working
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
death
Token death
Feature activation-0.008
Top resid features:
Ŀ
TokenĿ
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
G
TokenG
Feature activation+0.004
Top resid features:
ros
Tokenros
Feature activation-0.009
Top resid features:
j
Tokenj
Feature activation+6.908
Top resid features:
ean
Tokenean
Feature activation+0.270
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
who
Token who
Feature activation+0.004
Top resid features:
suffered
Token suffered
Feature activation-0.001
Top resid features:
damage
Token damage
Feature activation-0.000
Top resid features:
Indian
Token Indian
Feature activation-0.006
Top resid features:
broadband
Token broadband
Feature activation-0.009
Top resid features:
user
Token user
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
making
Token making
Feature activation-0.000
Top resid features:
J
Token J
Feature activation+5.793
Top resid features:
io
Tokenio
Feature activation+0.100
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
country
Token country
Feature activation+0.001
Top resid features:
's
Token's
Feature activation-0.000
Top resid features:
largest
Token largest
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
âĢ
Token âĢ
Feature activation+0.002
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
law
Tokenlaw
Feature activation-0.017
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
j
Token j
Feature activation+6.947
Top resid features:
ante
Tokenante
Feature activation+0.146
Top resid features:
âĢ
TokenâĢ
Feature activation+0.024
Top resid features:
Ŀ
TokenĿ
Feature activation+0.004
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
which
Token which
Feature activation+0.001
Top resid features:
love
Token love
Feature activation-0.002
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
classics
Token classics
Feature activation-0.003
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
J
Token J
Feature activation+6.694
Top resid features:
ett
Tokenett
Feature activation+0.334
Top resid features:
and
Token and
Feature activation-0.000
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
Black
Token Black
Feature activation+0.025
Top resid features:
he
Tokenhe
Feature activation-0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.029
Top resid features:
âĢ
Token âĢ
Feature activation+0.005
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
talk
Tokentalk
Feature activation-0.012
Top resid features:
about
Token about
Feature activation+0.004
Top resid features:
J
Token J
Feature activation+6.273
Top resid features:
ug
Tokenug
Feature activation+0.531
Top resid features:
head
Tokenhead
Feature activation-0.001
Top resid features:
comics
Token comics
Feature activation+0.073
Top resid features:
for
Token for
Feature activation+0.002
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
person
Token person
Feature activation+0.001
Top resid features:
shot
Token shot
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.001
Top resid features:
J
Token J
Feature activation+2.307
Top resid features:
ax
Tokenax
Feature activation+0.034
Top resid features:
Sheriff
Token Sheriff
Feature activation-0.020
Top resid features:
's
Token's
Feature activation-0.000
Top resid features:
Office
Token Office
Feature activation+0.000
Top resid features:
(@
Token (@
Feature activation-0.000
Top resid features:
days
Token days
Feature activation-0.002
Top resid features:
of
Token of
Feature activation-0.000
Top resid features:
fierce
Token fierce
Feature activation-0.001
Top resid features:
fighting
Token fighting
Feature activation-0.012
Top resid features:
in
Token in
Feature activation-0.003
Top resid features:
J
Token J
Feature activation+6.458
Top resid features:
uba
Tokenuba
Feature activation+0.155
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
country
Token country
Feature activation-0.002
Top resid features:
âĢ
TokenâĢ
Feature activation-0.026
Top resid features:
Costa
Token Costa
Feature activation-0.325
Top resid features:
Blanc
Token Blanc
Feature activation-0.016
Top resid features:
a
Tokena
Feature activation-0.029
Top resid features:
beach
Token beach
Feature activation-0.015
Top resid features:
resort
Token resort
Feature activation-0.042
Top resid features:
J
Token J
Feature activation+5.966
Top resid features:
á
Tokená
Feature activation-0.000
Top resid features:
ve
Tokenve
Feature activation+0.014
Top resid features:
a
Tokena
Feature activation-0.012
Top resid features:
hosts
Token hosts
Feature activation+0.001
Top resid features:
an
Token an
Feature activation+0.001
Top resid features:
came
Token came
Feature activation+0.015
Top resid features:
from
Token from
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
house
Token house
Feature activation-0.005
Top resid features:
of
Token of
Feature activation-0.005
Top resid features:
J
Token J
Feature activation+6.670
Top resid features:
air
Tokenair
Feature activation+0.130
Top resid features:
us
Tokenus
Feature activation+0.031
Top resid features:
,
Token,
Feature activation+0.011
Top resid features:
the
Token the
Feature activation-0.004
Top resid features:
synagogue
Token synagogue
Feature activation+0.016
Top resid features:
came
Token came
Feature activation-0.001
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
house
Token house
Feature activation-0.001
Top resid features:
of
Token of
Feature activation+0.003
Top resid features:
J
Token J
Feature activation+4.093
Top resid features:
air
Tokenair
Feature activation+0.102
Top resid features:
us
Tokenus
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
synagogue
Token synagogue
Feature activation-0.002
Top resid features:
Linux
Token Linux
Feature activation-0.044
Top resid features:
dist
Token dist
Feature activation-0.053
Top resid features:
ro
Tokenro
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
The
Token The
Feature activation+0.006
Top resid features:
J
Token J
Feature activation+3.731
Top resid features:
Boss
TokenBoss
Feature activation+0.001
Top resid features:
middle
Token middle
Feature activation-0.008
Top resid features:
ware
Tokenware
Feature activation-0.004
Top resid features:
business
Token business
Feature activation+0.002
Top resid features:
picked
Token picked
Feature activation-0.002
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.07

Head 3: 0.04

Head 4: 0.03

Head 5: 0.02

Head 6: 0.04

Head 7: 0.09

Head 8: 0.03

Head 9: 0.04

Head 10: 0.52

Head 11: 0.03

Positive logits

J10.38

J9.14

j7.54

j7.05

JJ6.37

JD6.36

JB6.28

JD6.20

JPM5.88

JM5.86

JC5.80

JA5.63

JA5.61

JJ5.54

JR5.46

JC5.44

Je5.43

Jas5.38

JM5.26

Jugg5.10

Negative logits

arest-3.12

tein-3.03

arent-2.73

cius-2.72

arium-2.72

ishops-2.66

geist-2.51

regon-2.50

eeks-2.47

Lange-2.46

dule-2.44

McM-2.39

hest-2.39

Chern-2.38

rador-2.36

uther-2.34

McF-2.33

zsche-2.33

mask-2.32

orsi-2.31

INTERVAL 7.352 - 8.169
CONTAINS 0.000%

.
Token.
Feature activation+0.476
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
51
Token51
Feature activation+8.032
When
Token When
Feature activation+5.660
he
Token he
Feature activation+0.000
arrived
Token arrived
Feature activation+0.958
at
Token at
Feature activation+4.700
the
Token the
Feature activation+1.463
what
Token what
Feature activation+0.000
constituted
Token constituted
Feature activation+0.000
a
Token a
Feature activation+0.000
personal
Token personal
Feature activation+0.000
attack
Token attack
Feature activation+0.000
,
Token,
Feature activation+8.169
Cohen
Token Cohen
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
team
Token team
Feature activation+0.000
a
Token a
Feature activation+0.000
frame
Token frame
Feature activation+0.000
.
Token.
Feature activation+0.943
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.468
Miss
TokenMiss
Feature activation+7.972
J
Token J
Feature activation+0.204
arl
Tokenarl
Feature activation+0.000
said
Token said
Feature activation+0.639
:
Token:
Feature activation+0.000
''
Token ''
Feature activation+0.000

INTERVAL 6.535 - 7.352
CONTAINS 0.000%

happened
Token happened
Feature activation+0.000
a
Token a
Feature activation+1.017
little
Token little
Feature activation+0.000
bit
Token bit
Feature activation+0.000
later
Token later
Feature activation+0.000
the
Token the
Feature activation+6.584
riders
Token riders
Feature activation+0.000
would
Token would
Feature activation+0.000
have
Token have
Feature activation+0.000
peeled
Token peeled
Feature activation+0.000
out
Token out
Feature activation+0.000
.
Token.
Feature activation+3.157
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.390
Not
TokenNot
Feature activation+0.000
only
Token only
Feature activation+1.760
is
Token is
Feature activation+6.945
there
Token there
Feature activation+0.021
pressure
Token pressure
Feature activation+0.000
to
Token to
Feature activation+0.000
build
Token build
Feature activation+0.480
,
Token,
Feature activation+2.115
.
Token.
Feature activation+3.124
I
Token I
Feature activation+0.000
have
Token have
Feature activation+0.000
therefore
Token therefore
Feature activation+0.000
submitted
Token submitted
Feature activation+4.122
the
Token the
Feature activation+6.568
specification
Token specification
Feature activation+0.548
for
Token for
Feature activation+2.928
Public
Token Public
Feature activation+0.317
Review
Token Review
Feature activation+0.000
despite
Token despite
Feature activation+1.392
upwards
Token upwards
Feature activation+0.000
of
Token of
Feature activation+0.000
$
Token $
Feature activation+0.000
20
Token20
Feature activation+0.000
billion
Token billion
Feature activation+0.000
in
Token in
Feature activation+7.050
buying
Token buying
Feature activation+6.267
spectrum
Token spectrum
Feature activation+0.000
,
Token,
Feature activation+0.166
setting
Token setting
Feature activation+1.538
up
Token up
Feature activation+1.452

INTERVAL 5.718 - 6.535
CONTAINS 0.001%

.
Token.
Feature activation+0.427
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.116
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
50
Token50
Feature activation+6.437
Hearing
Token Hearing
Feature activation+1.182
this
Token this
Feature activation+0.273
,
Token,
Feature activation+4.441
Jesus
Token Jesus
Feature activation+0.000
said
Token said
Feature activation+0.000
hit
Token hit
Feature activation+0.000
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.112
G
Token G
Feature activation+0.000
ros
Tokenros
Feature activation+6.384
j
Tokenj
Feature activation+0.176
ean
Tokenean
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
which
Token which
Feature activation+0.000
gained
Token gained
Feature activation+0.000
independence
Token independence
Feature activation+0.000
in
Token in
Feature activation+0.118
2011
Token 2011
Feature activation+0.000
.
Token.
Feature activation+5.899
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.162
Human
TokenHuman
Feature activation+0.000
Rights
Token Rights
Feature activation+0.000
Watch
Token Watch
Feature activation+0.000
an
Token an
Feature activation+1.627
avid
Token avid
Feature activation+3.457
reader
Token reader
Feature activation+0.000
,
Token,
Feature activation+0.134
especially
Token especially
Feature activation+0.071
of
Token of
Feature activation+6.053
classic
Token classic
Feature activation+4.933
literature
Token literature
Feature activation+0.000
.
Token.
Feature activation+2.203
His
Token His
Feature activation+0.475
parents
Token parents
Feature activation+0.000
of
Token of
Feature activation+0.000
$
Token $
Feature activation+0.000
20
Token20
Feature activation+0.000
billion
Token billion
Feature activation+0.000
in
Token in
Feature activation+7.050
buying
Token buying
Feature activation+6.267
spectrum
Token spectrum
Feature activation+0.000
,
Token,
Feature activation+0.166
setting
Token setting
Feature activation+1.538
up
Token up
Feature activation+1.452
the
Token the
Feature activation+0.846

INTERVAL 4.901 - 5.718
CONTAINS 0.002%

country
Token country
Feature activation+0.198
.
Token.
Feature activation+2.941
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.224
On
TokenOn
Feature activation+1.957
average
Token average
Feature activation+5.224
,
Token,
Feature activation+4.747
there
Token there
Feature activation+0.000
are
Token are
Feature activation+0.728
800
Token 800
Feature activation+1.721
frown
Token frown
Feature activation+0.000
a
Token a
Feature activation+0.000
beautiful
Token beautiful
Feature activation+0.000
and
Token and
Feature activation+0.000
powerful
Token powerful
Feature activation+0.000
image
Token image
Feature activation+0.000
and
Token and
Feature activation+5.070
he
Token he
Feature activation+0.000
immediately
Token immediately
Feature activation+0.000
connected
Token connected
Feature activation+3.134
with
Token with
Feature activation+3.014
it
Token it
Feature activation+0.000
10
Token10
Feature activation+0.000
.
Token.
Feature activation+0.000
30
Token30
Feature activation+0.000
pm
Tokenpm
Feature activation+0.000
)
Token)
Feature activation+0.485
in
Token in
Feature activation+5.203
Plaza
Token Plaza
Feature activation+2.721
De
Token De
Feature activation+0.000
La
Token La
Feature activation+0.000
Const
Token Const
Feature activation+0.000
it
Tokenit
Feature activation+0.000
in
Token in
Feature activation+1.527
just
Token just
Feature activation+0.274
2
Token 2
Feature activation+0.000
seconds
Token seconds
Feature activation+1.864
,
Token,
Feature activation+4.226
the
Token the
Feature activation+5.442
iteration
Token iteration
Feature activation+0.475
process
Token process
Feature activation+0.125
runs
Token runs
Feature activation+0.662
and
Token and
Feature activation+1.249
finishes
Token finishes
Feature activation+0.516
to
Token to
Feature activation+0.000
save
Token save
Feature activation+0.382
her
Token her
Feature activation+0.147
family
Token family
Feature activation+0.000
.
Token.
Feature activation+0.286
The
Token The
Feature activation+5.117
story
Token story
Feature activation+0.000
features
Token features
Feature activation+0.456
Starg
Token Starg
Feature activation+0.000
irl
Tokenirl
Feature activation+0.000
fighting
Token fighting
Feature activation+0.122

INTERVAL 4.084 - 4.901
CONTAINS 0.005%

on
Token on
Feature activation+0.000
becoming
Token becoming
Feature activation+0.000
an
Token an
Feature activation+0.000
airline
Token airline
Feature activation+0.000
pilot
Token pilot
Feature activation+0.000
.
Token.
Feature activation+4.754
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.946
Alex
TokenAlex
Feature activation+0.000
O
Token O
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.129
started
Token started
Feature activation+0.000
rolling
Token rolling
Feature activation+0.000
out
Token out
Feature activation+0.352
for
Token for
Feature activation+4.111
your
Token your
Feature activation+0.973
Nexus
Token Nexus
Feature activation+0.069
7
Token 7
Feature activation+0.000
s
Tokens
Feature activation+0.148
.
Token.
Feature activation+2.283
325
Token325
Feature activation+1.486
Provide
Token Provide
Feature activation+2.820
raw
Token raw
Feature activation+2.256
format
Token format
Feature activation+1.192
yard
Token yard
Feature activation+0.000
stick
Tokenstick
Feature activation+4.213
vm
Token vm
Feature activation+0.035
image
Token image
Feature activation+2.061
for
Token for
Feature activation+3.233
no
Token no
Feature activation+0.000
va
Tokenva
Feature activation+2.150
couple
Token couple
Feature activation+0.000
of
Token of
Feature activation+0.000
you
Token you
Feature activation+0.000
have
Token have
Feature activation+0.000
mentioned
Token mentioned
Feature activation+1.523
,
Token,
Feature activation+4.578
there
Token there
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+3.378
a
Token a
Feature activation+1.405
,
Token,
Feature activation+1.412
in
Token in
Feature activation+1.527
just
Token just
Feature activation+0.274
2
Token 2
Feature activation+0.000
seconds
Token seconds
Feature activation+1.864
,
Token,
Feature activation+4.226
the
Token the
Feature activation+5.442
iteration
Token iteration
Feature activation+0.475
process
Token process
Feature activation+0.125
runs
Token runs
Feature activation+0.662
and
Token and
Feature activation+1.249

INTERVAL 3.268 - 4.084
CONTAINS 0.009%

started
Token started
Feature activation+0.097
programming
Token programming
Feature activation+0.000
since
Token since
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+1.446
as
Token as
Feature activation+3.529
an
Token an
Feature activation+0.000
11
Token 11
Feature activation+0.000
year
Token year
Feature activation+0.000
old
Token old
Feature activation+0.000
.
Token.
Feature activation+5.110
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
running
Token running
Feature activation+0.886
the
Token the
Feature activation+3.328
test
Token test
Feature activation+0.497
on
Token on
Feature activation+0.000
).
Token).
Feature activation+1.365
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.332
and
Token and
Feature activation+0.773
his
Token his
Feature activation+0.000
friend
Token friend
Feature activation+0.000
.
Token.
Feature activation+1.379
Not
Token Not
Feature activation+0.139
because
Token because
Feature activation+3.605
she
Token she
Feature activation+0.000
didn
Token didn
Feature activation+0.000
't
Token't
Feature activation+0.000
like
Token like
Feature activation+1.199
dirty
Token dirty
Feature activation+0.000
the
Token the
Feature activation+0.426
merger
Token merger
Feature activation+0.000
,
Token,
Feature activation+0.000
saying
Token saying
Feature activation+2.868
he
Token he
Feature activation+0.000
believes
Token believes
Feature activation+3.291
it
Token it
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.125
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.811
Like
TokenLike
Feature activation+3.391
most
Token most
Feature activation+0.000
g
Token g
Feature activation+0.000
rom
Tokenrom
Feature activation+0.000
s
Tokens
Feature activation+0.907
,
Token,
Feature activation+0.618

INTERVAL 2.451 - 3.268
CONTAINS 0.017%

of
Token of
Feature activation+0.000
August
Token August
Feature activation+0.000
).
Token).
Feature activation+3.346
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.443
All
TokenAll
Feature activation+2.633
concerts
Token concerts
Feature activation+0.000
starts
Token starts
Feature activation+0.000
at
Token at
Feature activation+2.690
22
Token 22
Feature activation+0.000
.
Token.
Feature activation+0.000
despite
Token despite
Feature activation+1.392
this
Token this
Feature activation+0.000
lack
Token lack
Feature activation+0.000
of
Token of
Feature activation+0.451
consensus
Token consensus
Feature activation+0.000
.
Token.
Feature activation+2.596
Ċ
TokenĊ
Feature activation+0.053
Ċ
TokenĊ
Feature activation+2.717
In
TokenIn
Feature activation+1.412
response
Token response
Feature activation+0.375
IBM
Token IBM
Feature activation+0.696
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+1.070
the
Token the
Feature activation+3.095
best
Token best
Feature activation+0.000
interest
Token interest
Feature activation+0.000
of
Token of
Feature activation+4.051
the
Token the
Feature activation+2.912
wider
Token wider
Feature activation+2.802
After
TokenAfter
Feature activation+0.635
almost
Token almost
Feature activation+0.000
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.023
of
Token of
Feature activation+0.727
providing
Token providing
Feature activation+3.001
the
Token the
Feature activation+4.118
Manila
Token Manila
Feature activation+0.862
visa
Token visa
Feature activation+0.000
post
Token post
Feature activation+0.000
with
Token with
Feature activation+1.213
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.579
started
Token started
Feature activation+0.000
.
Token.
Feature activation+3.088
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.582
First
TokenFirst
Feature activation+0.315
time
Token time
Feature activation+1.191
users
Token users
Feature activation+0.000
should
Token should
Feature activation+0.000
create
Token create
Feature activation+1.463

INTERVAL 1.634 - 2.451
CONTAINS 0.031%

A
Token A
Feature activation+0.151
well
Token well
Feature activation+0.000
lit
Token lit
Feature activation+0.000
tank
Token tank
Feature activation+0.000
full
Token full
Feature activation+0.000
of
Token of
Feature activation+2.040
Moon
Token Moon
Feature activation+1.841
J
Token J
Feature activation+0.000
ell
Tokenell
Feature activation+0.000
ies
Tokenies
Feature activation+0.000
can
Token can
Feature activation+0.000
-
Token-
Feature activation+0.000
954
Token954
Feature activation+0.000
-
Token-
Feature activation+0.000
16
Token16
Feature activation+0.000
38
Token38
Feature activation+0.000
,
Token,
Feature activation+1.718
k
Token k
Feature activation+0.045
pain
Tokenpain
Feature activation+0.000
ter
Tokenter
Feature activation+0.000
@
Token@
Feature activation+0.000
den
Tokenden
Feature activation+0.000
debunked
Token debunked
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
No
Token No
Feature activation+1.960
Jab
Token Jab
Feature activation+0.000
,
Token,
Feature activation+0.000
No
Token No
Feature activation+0.000
Play
Token Play
Feature activation+0.000
policy
Token policy
Feature activation+0.000
Click
TokenClick
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
slideshow
Token slideshow
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+1.657
the
Token the
Feature activation+0.000
full
Token full
Feature activation+0.000
season
Token season
Feature activation+0.000
22
Token 22
Feature activation+0.000
lineup
Token lineup
Feature activation+0.000
order
Token order
Feature activation+0.000
to
Token to
Feature activation+0.000
qual
Token qual
Feature activation+0.000
m
Tokenm
Feature activation+0.553
fears
Token fears
Feature activation+0.000
that
Token that
Feature activation+1.957
the
Token the
Feature activation+0.429
film
Token film
Feature activation+0.000
would
Token would
Feature activation+0.000
suffer
Token suffer
Feature activation+0.000
from
Token from
Feature activation+0.000

INTERVAL 0.817 - 1.634
CONTAINS 0.071%

live
Token live
Feature activation+0.000
bands
Token bands
Feature activation+0.000
with
Token with
Feature activation+0.000
opens
Token opens
Feature activation+0.000
jams
Token jams
Feature activation+0.000
.
Token.
Feature activation+0.879
Baltimore
Token Baltimore
Feature activation+0.000
locals
Token locals
Feature activation+0.000
Rare
Token Rare
Feature activation+0.000
Candy
Token Candy
Feature activation+0.000
(
Token (
Feature activation+0.000
hard
Tokenhard
Feature activation+0.000
stein
Tokenstein
Feature activation+0.000
added
Token added
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.932
T
TokenT
Feature activation+0.000
ensing
Tokenensing
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
energy
Token energy
Feature activation+0.000
market
Token market
Feature activation+0.000
,
Token,
Feature activation+0.000
so
Token so
Feature activation+1.168
we
Token we
Feature activation+0.000
will
Token will
Feature activation+0.000
continue
Token continue
Feature activation+0.000
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.301
a
Token a
Feature activation+0.000
year
Token year
Feature activation+0.023
of
Token of
Feature activation+0.727
providing
Token providing
Feature activation+3.001
the
Token the
Feature activation+4.118
Manila
Token Manila
Feature activation+0.862
visa
Token visa
Feature activation+0.000
post
Token post
Feature activation+0.000
with
Token with
Feature activation+1.213
every
Token every
Feature activation+3.704
item
Token item
Feature activation+0.296
Ċ
TokenĊ
Feature activation+0.245
Ċ
TokenĊ
Feature activation+0.906
F
TokenF
Feature activation+0.000
AC
TokenAC
Feature activation+0.000
TS
TokenTS
Feature activation+0.393
ABOUT
Token ABOUT
Feature activation+0.917
MO
Token MO
Feature activation+0.302
ON
TokenON
Feature activation+3.264
J
Token J
Feature activation+0.000
ELL
TokenELL
Feature activation+0.000
Y
TokenY
Feature activation+0.665

INTERVAL 0.000 - 0.817
CONTAINS 99.863%

whose
Token whose
Feature activation+0.000
leaves
Token leaves
Feature activation+0.000
are
Token are
Feature activation+0.000
$
Token $
Feature activation+0.000
2
Token2
Feature activation+0.000
$
Token$
Feature activation+0.000
and
Token and
Feature activation+0.000
$
Token $
Feature activation+0.000
6
Token6
Feature activation+0.000
$.
Token$.
Feature activation+0.000
Feed
Token Feed
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
been
Token been
Feature activation+0.000
incredible
Token incredible
Feature activation+0.000
to
Token to
Feature activation+0.000
witness
Token witness
Feature activation+0.000
the
Token the
Feature activation+0.000
growing
Token growing
Feature activation+0.000
public
Token public
Feature activation+0.000
concern
Token concern
Feature activation+0.000
over
Token over
Feature activation+0.000
paragraph
Token paragraph
Feature activation+0.000
which
Token which
Feature activation+0.000
says
Token says
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
will
Token will
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
work
Tokenwork
Feature activation+0.000
closely
Token closely
Feature activation+0.000
),
Token),
Feature activation+0.000
neither
Token neither
Feature activation+0.000
is
Token is
Feature activation+0.000
as
Token as
Feature activation+0.000
impressive
Token impressive
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
St
Token St
Feature activation+0.000
utt
Tokenutt
Feature activation+0.000
gart
Tokengart
Feature activation+0.000
headquarters
Token headquarters
Feature activation+0.000
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
massive
Token massive
Feature activation+0.000
,
Token,
Feature activation+0.000
circular
Token circular
Feature activation+0.000
building
Token building
Feature activation+0.000
aside
Token aside
Feature activation+0.000
,
Token,
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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

Top feature 6 in H10.10: (feature 6633)

TOP ACTIVATIONS
MAX = 9.882

)
Token)
Feature activation+0.252
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.679
17
Token17
Feature activation+1.080
:
Token:
Feature activation+0.000
00
Token00
Feature activation+9.882
E
Token E
Feature activation+0.515
EST
TokenEST
Feature activation+0.079
Group
Token Group
Feature activation+0.000
A
Token A
Feature activation+0.000
-
Token -
Feature activation+0.000
)
Token)
Feature activation+1.157
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.675
14
Token14
Feature activation+0.890
:
Token:
Feature activation+0.000
00
Token00
Feature activation+9.228
E
Token E
Feature activation+0.330
EST
TokenEST
Feature activation+0.000
Group
Token Group
Feature activation+0.000
A
Token A
Feature activation+0.000
-
Token -
Feature activation+0.000
Winners
Token Winners
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.535
15
Token15
Feature activation+0.212
:
Token:
Feature activation+0.000
30
Token30
Feature activation+9.181
E
Token E
Feature activation+0.178
EST
TokenEST
Feature activation+0.000
Group
Token Group
Feature activation+0.000
A
Token A
Feature activation+0.000
-
Token -
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
command
Token command
Feature activation+1.293
.
Token.
Feature activation+8.755
E
Token E
Feature activation+0.000
.
Token.
Feature activation+0.000
g
Tokeng
Feature activation+0.000
.
Token.
Feature activation+1.807
help
Token help
Feature activation+0.000
2
Token2
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.511
15
Token15
Feature activation+1.240
:
Token:
Feature activation+0.095
30
Token30
Feature activation+8.575
E
Token E
Feature activation+0.250
EST
TokenEST
Feature activation+0.000
Group
Token Group
Feature activation+0.000
A
Token A
Feature activation+0.000
-
Token -
Feature activation+0.000
all
Tokenall
Feature activation+0.000
os
Tokenos
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+7.993
the
Token the
Feature activation+8.210
Zap
Token Zap
Feature activation+0.000
at
Tokenat
Feature activation+0.000
istas
Tokenistas
Feature activation+0.000
have
Token have
Feature activation+0.000
vehemently
Token vehemently
Feature activation+0.000
ev
Tokenev
Feature activation+0.000
all
Tokenall
Feature activation+0.000
os
Tokenos
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+7.993
the
Token the
Feature activation+8.210
Zap
Token Zap
Feature activation+0.000
at
Tokenat
Feature activation+0.000
istas
Tokenistas
Feature activation+0.000
have
Token have
Feature activation+0.000
noticeably
Token noticeably
Feature activation+0.000
ro
Token ro
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
-
Token-
Feature activation+0.000
poly
Tokenpoly
Feature activation+0.000
,
Token,
Feature activation+7.965
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
hunters
Token hunters
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
import
Token import
Feature activation+0.000
automatic
Token automatic
Feature activation+0.000
weapons
Token weapons
Feature activation+0.000
from
Token from
Feature activation+0.052
Canada
Token Canada
Feature activation+0.000
,
Token,
Feature activation+7.813
and
Token and
Feature activation+0.293
traditionally
Token traditionally
Feature activation+0.000
the
Token the
Feature activation+0.000
next
Token next
Feature activation+0.000
step
Token step
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000
allegations
Token allegations
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
leveled
Token leveled
Feature activation+0.000
against
Token against
Feature activation+7.718
them
Token them
Feature activation+0.000
,
Token,
Feature activation+6.942
such
Token such
Feature activation+0.052
as
Token as
Feature activation+0.004
when
Token when
Feature activation+2.163
t
Tokent
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
gave
Token gave
Feature activation+1.281
the
Token the
Feature activation+7.562
E
Token E
Feature activation+0.000
6
Token6
Feature activation+1.125
OLED
Token OLED
Feature activation+0.057
the
Token the
Feature activation+0.192
highest
Token highest
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.061
This
TokenThis
Feature activation+0.000
newspaper
Token newspaper
Feature activation+0.000
tapped
Token tapped
Feature activation+2.792
into
Token into
Feature activation+7.558
readers
Token readers
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
rage
Token rage
Feature activation+0.000
when
Token when
Feature activation+3.976
glorious
Token glorious
Feature activation+0.000
history
Token history
Feature activation+0.000
of
Token of
Feature activation+4.019
determined
Token determined
Feature activation+2.248
but
Token but
Feature activation+0.000
tiny
Token tiny
Feature activation+7.505
groups
Token groups
Feature activation+0.000
out
Token out
Feature activation+0.000
-
Token-
Feature activation+0.000
fighting
Tokenfighting
Feature activation+0.000
their
Token their
Feature activation+0.000
000
Token000
Feature activation+0.000
people
Token people
Feature activation+0.000
and
Token and
Feature activation+0.000
has
Token has
Feature activation+0.000
unleashed
Token unleashed
Feature activation+0.000
what
Token what
Feature activation+6.998
the
Token the
Feature activation+0.668
United
Token United
Feature activation+0.000
Nations
Token Nations
Feature activation+0.000
calls
Token calls
Feature activation+0.000
the
Token the
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
leveled
Token leveled
Feature activation+0.000
against
Token against
Feature activation+7.718
them
Token them
Feature activation+0.000
,
Token,
Feature activation+6.942
such
Token such
Feature activation+0.052
as
Token as
Feature activation+0.004
when
Token when
Feature activation+2.163
the
Token the
Feature activation+4.985
group
Token group
Feature activation+0.000
a
Token a
Feature activation+0.000
specific
Token specific
Feature activation+0.000
country
Token country
Feature activation+0.000
.
Token.
Feature activation+4.896
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+6.830
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.544
The
TokenThe
Feature activation+0.106
war
Token war
Feature activation+0.000
in
Token in
Feature activation+0.000
William
Token William
Feature activation+0.000
Cost
Token Cost
Feature activation+0.000
opoulos
Tokenopoulos
Feature activation+0.000
.
Token.
Feature activation+5.277
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.758
E
TokenE
Feature activation+0.000
akin
Tokenakin
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.208
by
Token by
Feature activation+0.000
1976
Token 1976
Feature activation+4.673
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
convinced
Token convinced
Feature activation+5.237
that
Token that
Feature activation+6.655
neo
Token neo
Feature activation+0.000
-
Token-
Feature activation+0.000
Dar
TokenDar
Feature activation+0.000
win
Tokenwin
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
t
Token t
Feature activation+0.000
edd
Tokenedd
Feature activation+0.000
ies
Tokenies
Feature activation+0.000
?
Token?
Feature activation+2.682
How
Token How
Feature activation+0.000
can
Token can
Feature activation+6.356
sticks
Token sticks
Feature activation+0.000
and
Token and
Feature activation+0.000
rocks
Token rocks
Feature activation+0.000
trump
Token trump
Feature activation+0.516
bl
Token bl
Feature activation+0.000
How
Token How
Feature activation+1.532
could
Token could
Feature activation+5.769
the
Token the
Feature activation+5.009
all
Token all
Feature activation+0.000
-
Token-
Feature activation+0.434
powerful
Tokenpowerful
Feature activation+6.229
Empire
Token Empire
Feature activation+0.000
be
Token be
Feature activation+0.000
brought
Token brought
Feature activation+0.000
down
Token down
Feature activation+0.000
by
Token by
Feature activation+3.261

Top DFA by src position
MAX = 9.695

Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
14
Token14
Feature activation+0.011
Top resid features:
:
Token:
Feature activation-0.001
Top resid features:
00
Token00
Feature activation-0.002
Top resid features:
E
Token E
Feature activation+8.099
Top resid features:
EST
TokenEST
Feature activation+0.040
Top resid features:
Group
Token Group
Feature activation+0.015
Top resid features:
A
Token A
Feature activation+0.004
Top resid features:
-
Token -
Feature activation+0.010
Top resid features:
Group
Token Group
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
14
Token14
Feature activation+0.009
Top resid features:
:
Token:
Feature activation-0.004
Top resid features:
00
Token00
Feature activation-0.007
Top resid features:
E
Token E
Feature activation+9.695
Top resid features:
EST
TokenEST
Feature activation+0.042
Top resid features:
Group
Token Group
Feature activation+0.062
Top resid features:
A
Token A
Feature activation+0.009
Top resid features:
-
Token -
Feature activation+0.006
Top resid features:
Group
Token Group
Feature activation+0.018
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
14
Token14
Feature activation+0.002
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
00
Token00
Feature activation-0.002
Top resid features:
E
Token E
Feature activation+4.541
Top resid features:
EST
TokenEST
Feature activation+0.016
Top resid features:
Group
Token Group
Feature activation+0.010
Top resid features:
A
Token A
Feature activation+0.003
Top resid features:
-
Token -
Feature activation+0.007
Top resid features:
Group
Token Group
Feature activation+0.005
Top resid features:
>
Token>
Feature activation-0.001
Top resid features:
âĢ
Token âĢ
Feature activation+0.015
Top resid features:
Ŀ
TokenĿ
Feature activation+0.001
Top resid features:
command
Token command
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
E
Token E
Feature activation+9.460
Top resid features:
.
Token.
Feature activation+0.214
Top resid features:
g
Tokeng
Feature activation+0.012
Top resid features:
.
Token.
Feature activation-0.006
Top resid features:
help
Token help
Feature activation+0.038
Top resid features:
cd
Token cd
Feature activation+0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
14
Token14
Feature activation+0.005
Top resid features:
:
Token:
Feature activation-0.001
Top resid features:
00
Token00
Feature activation-0.008
Top resid features:
E
Token E
Feature activation+7.153
Top resid features:
EST
TokenEST
Feature activation+0.029
Top resid features:
Group
Token Group
Feature activation+0.017
Top resid features:
A
Token A
Feature activation+0.002
Top resid features:
-
Token -
Feature activation+0.005
Top resid features:
Group
Token Group
Feature activation+0.006
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
government
Token government
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.012
Top resid features:
E
Token E
Feature activation+8.036
Top resid features:
Z
TokenZ
Feature activation+0.574
Top resid features:
L
TokenL
Feature activation+0.029
Top resid features:
N
TokenN
Feature activation+0.017
Top resid features:
has
Token has
Feature activation+0.011
Top resid features:
largely
Token largely
Feature activation+0.002
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
government
Token government
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
E
Token E
Feature activation+8.064
Top resid features:
Z
TokenZ
Feature activation+0.541
Top resid features:
L
TokenL
Feature activation+0.012
Top resid features:
N
TokenN
Feature activation+0.006
Top resid features:
has
Token has
Feature activation+0.012
Top resid features:
largely
Token largely
Feature activation-0.000
Top resid features:
t
Token t
Feature activation-0.115
Top resid features:
eddy
Tokeneddy
Feature activation+0.006
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
bear
Tokenbear
Feature activation-0.011
Top resid features:
like
Token like
Feature activation-0.006
Top resid features:
E
Token E
Feature activation+8.198
Top resid features:
w
Tokenw
Feature activation+0.219
Top resid features:
oks
Tokenoks
Feature activation+0.116
Top resid features:
live
Token live
Feature activation+0.008
Top resid features:
on
Token on
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
UAE
Token UAE
Feature activation-0.013
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
âĢ
TokenâĢ
Feature activation-0.051
Top resid features:
Ŀ
TokenĿ
Feature activation+0.072
Top resid features:
E
Token E
Feature activation+8.227
Top resid features:
pps
Tokenpps
Feature activation+0.123
Top resid features:
said
Token said
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.023
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
government
Token government
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
the
Token the
Feature activation+0.021
Top resid features:
E
Token E
Feature activation+7.756
Top resid features:
Z
TokenZ
Feature activation+0.455
Top resid features:
L
TokenL
Feature activation+0.030
Top resid features:
N
TokenN
Feature activation+0.030
Top resid features:
has
Token has
Feature activation+0.018
Top resid features:
largely
Token largely
Feature activation+0.001
Top resid features:
t
Tokent
Feature activation-0.000
Top resid features:
alone
Token alone
Feature activation-0.001
Top resid features:
in
Token in
Feature activation-0.000
Top resid features:
loving
Token loving
Feature activation-0.005
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
E
Token E
Feature activation+7.917
Top resid features:
6
Token6
Feature activation+0.107
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Vincent
Token Vincent
Feature activation-0.002
Top resid features:
Te
Token Te
Feature activation-0.027
Top resid features:
oh
Tokenoh
Feature activation-0.000
Top resid features:
Rodriguez
Token Rodriguez
Feature activation-0.092
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
a
Token a
Feature activation+0.008
Top resid features:
spokeswoman
Token spokeswoman
Feature activation+0.003
Top resid features:
for
Token for
Feature activation+0.004
Top resid features:
E
Token E
Feature activation+7.702
Top resid features:
BM
TokenBM
Feature activation+0.048
Top resid features:
UD
TokenUD
Feature activation-0.012
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Ċ
TokenĊ
Feature activation+0.029
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
Still
TokenStill
Feature activation-0.004
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
E
Token E
Feature activation+7.877
Top resid features:
w
Tokenw
Feature activation+0.055
Top resid features:
oks
Tokenoks
Feature activation+0.149
Top resid features:
âĢ
TokenâĢ
Feature activation+0.009
Top resid features:
Ļ
TokenĻ
Feature activation-0.002
Top resid features:
victory
Token victory
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
UAE
Token UAE
Feature activation-0.012
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
âĢ
TokenâĢ
Feature activation-0.016
Top resid features:
Ŀ
TokenĿ
Feature activation-0.005
Top resid features:
E
Token E
Feature activation+7.565
Top resid features:
pps
Tokenpps
Feature activation+0.114
Top resid features:
said
Token said
Feature activation+0.020
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
government
Token government
Feature activation+0.010
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
E
Token E
Feature activation+6.991
Top resid features:
Z
TokenZ
Feature activation+0.539
Top resid features:
L
TokenL
Feature activation+0.016
Top resid features:
N
TokenN
Feature activation+0.014
Top resid features:
has
Token has
Feature activation+0.012
Top resid features:
largely
Token largely
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
UAE
Token UAE
Feature activation-0.016
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation-0.008
Top resid features:
Ŀ
TokenĿ
Feature activation+0.021
Top resid features:
E
Token E
Feature activation+7.651
Top resid features:
pps
Tokenpps
Feature activation+0.065
Top resid features:
said
Token said
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.012
Top resid features:
his
Token his
Feature activation+0.001
Top resid features:
peers
Token peers
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
E
TokenE
Feature activation+6.952
Top resid features:
akin
Tokenakin
Feature activation+0.103
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
67
Token 67
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
number
Token number
Feature activation-0.005
Top resid features:
of
Token of
Feature activation-0.001
Top resid features:
distinguished
Token distinguished
Feature activation-0.049
Top resid features:
scientists
Token scientists
Feature activation+0.052
Top resid features:
accused
Token accused
Feature activation-0.005
Top resid features:
E
Token E
Feature activation+6.749
Top resid features:
.
Token.
Feature activation+0.188
Top resid features:
O
TokenO
Feature activation+0.185
Top resid features:
.
Token.
Feature activation+0.021
Top resid features:
Wilson
Token Wilson
Feature activation+0.040
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.041
Top resid features:
of
Token of
Feature activation-0.003
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
hatred
Token hatred
Feature activation-0.013
Top resid features:
of
Token of
Feature activation-0.011
Top resid features:
E
Token E
Feature activation+6.783
Top resid features:
w
Tokenw
Feature activation+0.112
Top resid features:
oks
Tokenoks
Feature activation+0.113
Top resid features:
stems
Token stems
Feature activation-0.000
Top resid features:
from
Token from
Feature activation-0.002
Top resid features:
that
Token that
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.022
Top resid features:
of
Token of
Feature activation-0.016
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
hatred
Token hatred
Feature activation-0.024
Top resid features:
of
Token of
Feature activation-0.023
Top resid features:
E
Token E
Feature activation+6.492
Top resid features:
w
Tokenw
Feature activation+0.113
Top resid features:
oks
Tokenoks
Feature activation+0.204
Top resid features:
stems
Token stems
Feature activation-0.000
Top resid features:
from
Token from
Feature activation-0.008
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.05

Head 2: 0.08

Head 3: 0.04

Head 4: 0.02

Head 5: 0.02

Head 6: 0.04

Head 7: 0.10

Head 8: 0.03

Head 9: 0.04

Head 10: 0.52

Head 11: 0.03

Positive logits

E10.44

E8.20

EB5.98

e5.93

Eb4.98

EH4.89

Es4.88

EF4.83

EE4.81

Es4.75

EG4.64

EB4.57

EC4.57

EA4.52

Eg4.41

EW4.34

EEE4.31

eb4.26

Ez4.25

EC4.25

Negative logits

aining-3.00

thood-2.97

mal-2.84

usra-2.82

itiz-2.76

grain-2.65

dl-2.63

Interstitial-2.63

tal-2.63

tt-2.62

sl-2.59

pton-2.56

bang-2.51

ahs-2.51

atically-2.49

atical-2.45

-2.43

Mont-2.41

az-2.41

ointment-2.36

INTERVAL 8.894 - 9.882
CONTAINS 0.000%

)
Token)
Feature activation+1.157
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.675
14
Token14
Feature activation+0.890
:
Token:
Feature activation+0.000
00
Token00
Feature activation+9.228
E
Token E
Feature activation+0.330
EST
TokenEST
Feature activation+0.000
Group
Token Group
Feature activation+0.000
A
Token A
Feature activation+0.000
-
Token -
Feature activation+0.000
Winners
Token Winners
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.535
15
Token15
Feature activation+0.212
:
Token:
Feature activation+0.000
30
Token30
Feature activation+9.181
E
Token E
Feature activation+0.178
EST
TokenEST
Feature activation+0.000
Group
Token Group
Feature activation+0.000
A
Token A
Feature activation+0.000
-
Token -
Feature activation+0.000
)
Token)
Feature activation+0.252
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.679
17
Token17
Feature activation+1.080
:
Token:
Feature activation+0.000
00
Token00
Feature activation+9.882
E
Token E
Feature activation+0.515
EST
TokenEST
Feature activation+0.079
Group
Token Group
Feature activation+0.000
A
Token A
Feature activation+0.000
-
Token -
Feature activation+0.000

INTERVAL 7.906 - 8.894
CONTAINS 0.001%

âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
command
Token command
Feature activation+1.293
.
Token.
Feature activation+8.755
E
Token E
Feature activation+0.000
.
Token.
Feature activation+0.000
g
Tokeng
Feature activation+0.000
.
Token.
Feature activation+1.807
help
Token help
Feature activation+0.000
ev
Tokenev
Feature activation+0.000
all
Tokenall
Feature activation+0.000
os
Tokenos
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+7.993
the
Token the
Feature activation+8.210
Zap
Token Zap
Feature activation+0.000
at
Tokenat
Feature activation+0.000
istas
Tokenistas
Feature activation+0.000
have
Token have
Feature activation+0.000
all
Tokenall
Feature activation+0.000
os
Tokenos
Feature activation+0.000
last
Token last
Feature activation+0.000
year
Token year
Feature activation+0.000
,
Token,
Feature activation+7.993
the
Token the
Feature activation+8.210
Zap
Token Zap
Feature activation+0.000
at
Tokenat
Feature activation+0.000
istas
Tokenistas
Feature activation+0.000
have
Token have
Feature activation+0.000
vehemently
Token vehemently
Feature activation+0.000
noticeably
Token noticeably
Feature activation+0.000
ro
Token ro
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
-
Token-
Feature activation+0.000
poly
Tokenpoly
Feature activation+0.000
,
Token,
Feature activation+7.965
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
hunters
Token hunters
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
2
Token2
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.511
15
Token15
Feature activation+1.240
:
Token:
Feature activation+0.095
30
Token30
Feature activation+8.575
E
Token E
Feature activation+0.250
EST
TokenEST
Feature activation+0.000
Group
Token Group
Feature activation+0.000
A
Token A
Feature activation+0.000
-
Token -
Feature activation+0.000

INTERVAL 6.918 - 7.906
CONTAINS 0.001%

glorious
Token glorious
Feature activation+0.000
history
Token history
Feature activation+0.000
of
Token of
Feature activation+4.019
determined
Token determined
Feature activation+2.248
but
Token but
Feature activation+0.000
tiny
Token tiny
Feature activation+7.505
groups
Token groups
Feature activation+0.000
out
Token out
Feature activation+0.000
-
Token-
Feature activation+0.000
fighting
Tokenfighting
Feature activation+0.000
their
Token their
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.061
This
TokenThis
Feature activation+0.000
newspaper
Token newspaper
Feature activation+0.000
tapped
Token tapped
Feature activation+2.792
into
Token into
Feature activation+7.558
readers
Token readers
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
rage
Token rage
Feature activation+0.000
when
Token when
Feature activation+3.976
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
leveled
Token leveled
Feature activation+0.000
against
Token against
Feature activation+7.718
them
Token them
Feature activation+0.000
,
Token,
Feature activation+6.942
such
Token such
Feature activation+0.052
as
Token as
Feature activation+0.004
when
Token when
Feature activation+2.163
the
Token the
Feature activation+4.985
group
Token group
Feature activation+0.000
t
Tokent
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
gave
Token gave
Feature activation+1.281
the
Token the
Feature activation+7.562
E
Token E
Feature activation+0.000
6
Token6
Feature activation+1.125
OLED
Token OLED
Feature activation+0.057
the
Token the
Feature activation+0.192
highest
Token highest
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000
allegations
Token allegations
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
leveled
Token leveled
Feature activation+0.000
against
Token against
Feature activation+7.718
them
Token them
Feature activation+0.000
,
Token,
Feature activation+6.942
such
Token such
Feature activation+0.052
as
Token as
Feature activation+0.004
when
Token when
Feature activation+2.163

INTERVAL 5.929 - 6.918
CONTAINS 0.001%

and
Token and
Feature activation+0.000
comprehensive
Token comprehensive
Feature activation+0.000
"
Token"
Feature activation+0.000
business
Token business
Feature activation+0.000
audit
Token audit
Feature activation+0.000
of
Token of
Feature activation+6.134
IC
Token IC
Feature activation+0.000
BC
TokenBC
Feature activation+0.000
management
Token management
Feature activation+0.000
.
Token.
Feature activation+3.920
Ċ
TokenĊ
Feature activation+0.000
How
Token How
Feature activation+1.532
could
Token could
Feature activation+5.769
the
Token the
Feature activation+5.009
all
Token all
Feature activation+0.000
-
Token-
Feature activation+0.434
powerful
Tokenpowerful
Feature activation+6.229
Empire
Token Empire
Feature activation+0.000
be
Token be
Feature activation+0.000
brought
Token brought
Feature activation+0.000
down
Token down
Feature activation+0.000
by
Token by
Feature activation+3.261
a
Token a
Feature activation+0.000
specific
Token specific
Feature activation+0.000
country
Token country
Feature activation+0.000
.
Token.
Feature activation+4.896
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+6.830
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.544
The
TokenThe
Feature activation+0.106
war
Token war
Feature activation+0.000
in
Token in
Feature activation+0.000
William
Token William
Feature activation+0.000
Cost
Token Cost
Feature activation+0.000
opoulos
Tokenopoulos
Feature activation+0.000
.
Token.
Feature activation+5.277
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.758
E
TokenE
Feature activation+0.000
akin
Tokenakin
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
second
Token second
Feature activation+0.208
by
Token by
Feature activation+0.000
1976
Token 1976
Feature activation+4.673
I
Token I
Feature activation+0.000
was
Token was
Feature activation+0.000
convinced
Token convinced
Feature activation+5.237
that
Token that
Feature activation+6.655
neo
Token neo
Feature activation+0.000
-
Token-
Feature activation+0.000
Dar
TokenDar
Feature activation+0.000
win
Tokenwin
Feature activation+0.000
ism
Tokenism
Feature activation+0.000

INTERVAL 4.941 - 5.929
CONTAINS 0.003%

com
Tokencom
Feature activation+0.000
/
Token/
Feature activation+0.000
m
Tokenm
Feature activation+0.000
Y
TokenY
Feature activation+0.000
i
Tokeni
Feature activation+0.871
Queen
TokenQueen
Feature activation+5.893
E
TokenE
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Su
TokenSu
Feature activation+0.000
ppy
Tokenppy
Feature activation+0.000
them
Token them
Feature activation+0.000
,
Token,
Feature activation+6.942
such
Token such
Feature activation+0.052
as
Token as
Feature activation+0.004
when
Token when
Feature activation+2.163
the
Token the
Feature activation+4.985
group
Token group
Feature activation+0.000
was
Token was
Feature activation+0.000
suspected
Token suspected
Feature activation+0.000
of
Token of
Feature activation+0.000
carrying
Token carrying
Feature activation+0.000
Empire
Token Empire
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
beaten
Token beaten
Feature activation+0.000
solely
Token solely
Feature activation+0.000
by
Token by
Feature activation+5.398
a
Token a
Feature activation+0.840
similarly
Token similarly
Feature activation+0.000
organised
Token organised
Feature activation+0.637
force
Token force
Feature activation+0.000
aboard
Token aboard
Feature activation+2.568
told
Token told
Feature activation+0.037
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.000
.
Token.
Feature activation+2.159
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+5.309
I
TokenI
Feature activation+0.000
am
Token am
Feature activation+0.000
in
Token in
Feature activation+0.000
fear
Token fear
Feature activation+0.000
of
Token of
Feature activation+0.152
much
Token much
Feature activation+0.000
does
Token does
Feature activation+0.000
E
Token E
Feature activation+0.000
CC
TokenCC
Feature activation+0.000
help
Token help
Feature activation+0.410
?
Token?
Feature activation+5.263
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.813
Error
TokenError
Feature activation+0.000
detection
Token detection
Feature activation+0.891
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 3.953 - 4.941
CONTAINS 0.006%

believe
Token believe
Feature activation+3.707
in
Token in
Feature activation+2.183
the
Token the
Feature activation+1.342
Rebellion
Token Rebellion
Feature activation+0.000
.
Token.
Feature activation+2.544
If
Token If
Feature activation+4.128
the
Token the
Feature activation+4.347
Empire
Token Empire
Feature activation+0.000
had
Token had
Feature activation+0.000
been
Token been
Feature activation+0.000
beaten
Token beaten
Feature activation+0.000
in
Token in
Feature activation+0.634
the
Token the
Feature activation+0.075
process
Token process
Feature activation+0.000
.
Token.
Feature activation+4.907
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.670
The
TokenThe
Feature activation+1.829
third
Token third
Feature activation+0.083
feature
Token feature
Feature activation+0.357
,
Token,
Feature activation+2.995
the
Token the
Feature activation+0.859
me
Token me
Feature activation+0.000
emotional
Token emotional
Feature activation+0.000
today
Token today
Feature activation+0.000
."
Token."
Feature activation+1.388
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.406
P
TokenP
Feature activation+0.000
av
Tokenav
Feature activation+0.000
k
Tokenk
Feature activation+0.000
ovic
Tokenovic
Feature activation+0.000
said
Token said
Feature activation+3.029
Cha
Token Cha
Feature activation+0.000
plain
Tokenplain
Feature activation+0.000
Royal
Token Royal
Feature activation+0.000
Blackburn
Token Blackburn
Feature activation+0.000
Hospital
Token Hospital
Feature activation+0.000
,
Token,
Feature activation+3.975
told
Token told
Feature activation+0.477
Lanc
Token Lanc
Feature activation+0.000
ash
Tokenash
Feature activation+0.000
ire
Tokenire
Feature activation+0.000
Telegraph
Token Telegraph
Feature activation+0.000
It
Token It
Feature activation+0.000
seemed
Token seemed
Feature activation+1.110
an
Token an
Feature activation+0.000
insult
Token insult
Feature activation+0.000
to
Token to
Feature activation+3.576
every
Token every
Feature activation+4.125
fan
Token fan
Feature activation+0.000
who
Token who
Feature activation+0.000
had
Token had
Feature activation+0.000
come
Token come
Feature activation+0.000
to
Token to
Feature activation+0.636

INTERVAL 2.965 - 3.953
CONTAINS 0.010%

problem
Token problem
Feature activation+0.000
associated
Token associated
Feature activation+0.000
with
Token with
Feature activation+0.000
E
Token E
Feature activation+0.000
SI
TokenSI
Feature activation+0.000
where
Token where
Feature activation+3.470
there
Token there
Feature activation+0.000
cap
Token cap
Feature activation+0.000
illary
Tokenillary
Feature activation+0.000
may
Token may
Feature activation+0.000
cl
Token cl
Feature activation+0.000
.
Token.
Feature activation+4.982
He
Token He
Feature activation+0.000
's
Token's
Feature activation+0.917
almost
Token almost
Feature activation+0.000
certainly
Token certainly
Feature activation+1.908
not
Token not
Feature activation+3.754
this
Token this
Feature activation+0.671
bad
Token bad
Feature activation+0.274
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.895
That
TokenThat
Feature activation+1.049
to
Token to
Feature activation+0.000
cross
Token cross
Feature activation+0.436
borders
Token borders
Feature activation+0.000
faster
Token faster
Feature activation+0.000
.
Token.
Feature activation+4.596
The
Token The
Feature activation+3.338
system
Token system
Feature activation+0.000
would
Token would
Feature activation+0.000
rely
Token rely
Feature activation+0.000
heavily
Token heavily
Feature activation+0.000
on
Token on
Feature activation+0.072
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
send
Token send
Feature activation+0.834
tips
Token tips
Feature activation+0.000
about
Token about
Feature activation+2.178
where
Token where
Feature activation+3.307
they
Token they
Feature activation+0.000
saw
Token saw
Feature activation+1.559
water
Token water
Feature activation+0.000
being
Token being
Feature activation+0.000
wasted
Token wasted
Feature activation+0.000
database
Token database
Feature activation+0.000
of
Token of
Feature activation+0.000
passenger
Token passenger
Feature activation+0.000
personal
Token personal
Feature activation+0.000
information
Token information
Feature activation+0.000
.
Token.
Feature activation+3.417
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.187
A
TokenA
Feature activation+1.321
legislative
Token legislative
Feature activation+0.000
package
Token package
Feature activation+0.000

INTERVAL 1.976 - 2.965
CONTAINS 0.021%

).
Token).
Feature activation+0.000
{
Token {
Feature activation+1.193
T
TokenT
Feature activation+0.000
},
Token},
Feature activation+0.000
Pay
Token Pay
Feature activation+0.000
{
Token {
Feature activation+2.328
e
Tokene
Feature activation+0.000
}{
Token}{
Feature activation+2.627
e
Tokene
Feature activation+0.000
}{
Token}{
Feature activation+2.069
e
Tokene
Feature activation+0.000
cast
Token cast
Feature activation+0.000
into
Token into
Feature activation+0.000
doubt
Token doubt
Feature activation+0.000
.
Token.
Feature activation+2.904
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.373
E
TokenE
Feature activation+0.000
ram
Tokenram
Feature activation+0.000
o
Tokeno
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.232
ones
Token ones
Feature activation+0.513
that
Token that
Feature activation+0.000
have
Token have
Feature activation+0.440
been
Token been
Feature activation+0.000
released
Token released
Feature activation+0.000
,
Token,
Feature activation+2.242
they
Token they
Feature activation+0.000
will
Token will
Feature activation+0.000
jump
Token jump
Feature activation+0.000
up
Token up
Feature activation+0.191
by
Token by
Feature activation+0.110
tel
Token tel
Feature activation+0.000
co
Tokenco
Feature activation+0.000
succeeded
Token succeeded
Feature activation+0.000
in
Token in
Feature activation+0.000
gaining
Token gaining
Feature activation+0.950
the
Token the
Feature activation+2.031
E
Token E
Feature activation+0.000
PL
TokenPL
Feature activation+0.000
rights
Token rights
Feature activation+0.000
supports
Token supports
Feature activation+0.000
claims
Token claims
Feature activation+0.000
health
Token health
Feature activation+0.000
care
Token care
Feature activation+0.000
law
Token law
Feature activation+0.000
.
Token.
Feature activation+2.592
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.779
Now
TokenNow
Feature activation+2.866
,
Token,
Feature activation+4.633
some
Token some
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
are
Token are
Feature activation+0.000

INTERVAL 0.988 - 1.976
CONTAINS 0.049%

15
Token 15
Feature activation+0.000
minutes
Token minutes
Feature activation+0.679
that
Token that
Feature activation+1.580
she
Token she
Feature activation+0.000
was
Token was
Feature activation+0.000
gone
Token gone
Feature activation+1.017
,
Token,
Feature activation+1.828
a
Token a
Feature activation+0.000
Honda
Token Honda
Feature activation+0.000
Civic
Token Civic
Feature activation+0.000
pulled
Token pulled
Feature activation+0.000
.
Token.
Feature activation+0.889
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.714
If
TokenIf
Feature activation+0.908
and
Token and
Feature activation+0.000
when
Token when
Feature activation+1.495
the
Token the
Feature activation+0.000
FTC
Token FTC
Feature activation+0.000
acts
Token acts
Feature activation+0.000
,
Token,
Feature activation+0.985
they
Token they
Feature activation+0.000
was
Token was
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
asc
Token asc
Feature activation+0.000
endant
Tokenendant
Feature activation+0.000
.
Token.
Feature activation+1.878
Read
Token Read
Feature activation+0.575
erotic
Token erotic
Feature activation+0.000
poetry
Token poetry
Feature activation+0.000
of
Token of
Feature activation+1.207
Jay
Token Jay
Feature activation+0.000
a
Token a
Feature activation+0.000
great
Token great
Feature activation+0.000
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.000
finally
Token finally
Feature activation+0.000
spend
Token spend
Feature activation+1.005
this
Token this
Feature activation+0.000
bonus
Token bonus
Feature activation+0.000
points
Token points
Feature activation+0.000
with
Token with
Feature activation+1.625
a
Token a
Feature activation+0.493
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
if
Token if
Feature activation+0.000
enacted
Token enacted
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+1.239
bill
Token bill
Feature activation+0.000
would
Token would
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
f
Tokenf
Feature activation+0.000

INTERVAL 0.000 - 0.988
CONTAINS 99.908%

about
Token about
Feature activation+0.000
the
Token the
Feature activation+0.000
security
Token security
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
method
Token method
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
when
Token when
Feature activation+0.000
she
Token she
Feature activation+0.000
told
Token told
Feature activation+0.000
Fox
Token Fox
Feature activation+0.000
News
Token News
Feature activation+0.000
Channel
Token Channel
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Bill
Token Bill
Feature activation+0.000
Hem
Token Hem
Feature activation+0.000
the
Token the
Feature activation+0.000
North
Token North
Feature activation+0.000
Vietnamese
Token Vietnamese
Feature activation+0.000
army
Token army
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
North
Token North
Feature activation+0.000
Vietnamese
Token Vietnamese
Feature activation+0.000
government
Token government
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
it
Token it
Feature activation+0.000
again
Token again
Feature activation+0.000
and
Token and
Feature activation+0.000
again
Token again
Feature activation+0.000
and
Token and
Feature activation+0.000
again
Token again
Feature activation+0.000
and
Token and
Feature activation+0.000
again
Token again
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ¦
Token âĢ¦
Feature activation+0.000
We
TokenWe
Feature activation+0.000
of
Token of
Feature activation+0.000
all
Token all
Feature activation+0.000
stripes
Token stripes
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
not
Token not
Feature activation+0.000
just
Token just
Feature activation+0.000
environmentalists
Token environmentalists
Feature activation+0.000
and
Token and
Feature activation+0.000
climate
Token climate
Feature activation+0.000
scientists
Token scientists
Feature activation+0.000
but
Token but
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 H10.10: (feature 19988)

TOP ACTIVATIONS
MAX = 9.518

F
Token F
Feature activation+0.000
.
Token.
Feature activation+0.000
lux
Tokenlux
Feature activation+0.000
?
Token?
Feature activation+0.123
How
Token How
Feature activation+0.228
has
Token has
Feature activation+9.518
it
Token it
Feature activation+0.000
helped
Token helped
Feature activation+0.327
your
Token your
Feature activation+0.576
sleeping
Token sleeping
Feature activation+0.000
patterns
Token patterns
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.034
Ċ
TokenĊ
Feature activation+2.411
At
TokenAt
Feature activation+2.212
the
Token the
Feature activation+0.000
Reform
Token Reform
Feature activation+0.000
Club
Token Club
Feature activation+8.250
,
Token,
Feature activation+7.823
F
Token F
Feature activation+0.000
ogg
Tokenogg
Feature activation+0.000
gets
Token gets
Feature activation+0.000
involved
Token involved
Feature activation+0.000
fashion
Tokenfashion
Feature activation+0.000
able
Tokenable
Feature activation+0.000
in
Token in
Feature activation+1.266
recent
Token recent
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+8.129
this
Token this
Feature activation+0.000
is
Token is
Feature activation+2.639
not
Token not
Feature activation+1.185
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.869
Ċ
TokenĊ
Feature activation+2.411
At
TokenAt
Feature activation+2.212
the
Token the
Feature activation+0.000
Reform
Token Reform
Feature activation+0.000
Club
Token Club
Feature activation+8.250
,
Token,
Feature activation+7.823
F
Token F
Feature activation+0.000
ogg
Tokenogg
Feature activation+0.000
gets
Token gets
Feature activation+0.000
involved
Token involved
Feature activation+0.000
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.881
The
TokenThe
Feature activation+3.308
inaugural
Token inaugural
Feature activation+6.485
session
Token session
Feature activation+0.000
saw
Token saw
Feature activation+7.633
launch
Token launch
Feature activation+0.000
of
Token of
Feature activation+5.280
two
Token two
Feature activation+2.914
acceler
Token acceler
Feature activation+0.000
ators
Tokenators
Feature activation+0.000
bor
Tokenbor
Feature activation+0.000
c
Tokenc
Feature activation+0.000
za
Tokenza
Feature activation+0.000
claimed
Token claimed
Feature activation+0.719
that
Token that
Feature activation+2.601
16
Token 16
Feature activation+7.336
US
Token US
Feature activation+1.390
jets
Token jets
Feature activation+0.000
will
Token will
Feature activation+0.000
move
Token move
Feature activation+0.755
from
Token from
Feature activation+1.246
play
Token play
Feature activation+0.000
made
Token made
Feature activation+3.310
people
Token people
Feature activation+0.000
believe
Token believe
Feature activation+6.035
this
Token this
Feature activation+0.000
was
Token was
Feature activation+7.208
the
Token the
Feature activation+0.389
Wild
Token Wild
Feature activation+0.000
cat
Tokencat
Feature activation+0.000
formation
Token formation
Feature activation+1.059
.
Token.
Feature activation+3.378
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
be
Token be
Feature activation+0.000
clear
Token clear
Feature activation+0.180
:
Token:
Feature activation+7.017
Canadian
Token Canadian
Feature activation+1.231
law
Token law
Feature activation+0.000
enforcement
Token enforcement
Feature activation+0.000
is
Token is
Feature activation+0.000
not
Token not
Feature activation+0.000
et
Tokenet
Feature activation+0.000
,
Token,
Feature activation+5.862
James
Token James
Feature activation+0.250
For
Token For
Feature activation+0.000
ster
Tokenster
Feature activation+0.498
,
Token,
Feature activation+7.012
for
Token for
Feature activation+0.000
bringing
Token bringing
Feature activation+2.011
him
Token him
Feature activation+0.000
shaving
Token shaving
Feature activation+0.000
water
Token water
Feature activation+0.000
patterns
Token patterns
Feature activation+0.000
?
Token?
Feature activation+0.015
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.413
Source
TokenSource
Feature activation+0.000
:
Token:
Feature activation+7.005
Fl
Token Fl
Feature activation+0.000
.
Token.
Feature activation+0.000
ux
Tokenux
Feature activation+0.000
Blog
Token Blog
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
topics
Token topics
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.048
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.500
manage
Token manage
Feature activation+7.005
the
Token the
Feature activation+2.537
amount
Token amount
Feature activation+0.148
of
Token of
Feature activation+5.107
incoming
Token incoming
Feature activation+2.809
information
Token information
Feature activation+0.000
legislators
Token legislators
Feature activation+0.000
make
Token make
Feature activation+4.479
passing
Token passing
Feature activation+4.884
a
Token a
Feature activation+2.526
bill
Token bill
Feature activation+0.674
banning
Token banning
Feature activation+7.004
F
Token F
Feature activation+0.000
GM
TokenGM
Feature activation+0.000
/
Token/
Feature activation+0.000
C
TokenC
Feature activation+0.000
high
Token high
Feature activation+0.000
his
Token his
Feature activation+0.000
social
Token social
Feature activation+0.000
life
Token life
Feature activation+0.000
other
Token other
Feature activation+0.000
than
Token than
Feature activation+0.343
that
Token that
Feature activation+6.976
he
Token he
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
member
Token member
Feature activation+0.000
of
Token of
Feature activation+0.000
that
Token that
Feature activation+4.302
as
Token as
Feature activation+5.339
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
,
Token,
Feature activation+6.957
F
Token F
Feature activation+0.000
TR
TokenTR
Feature activation+0.000
has
Token has
Feature activation+0.000
reached
Token reached
Feature activation+0.916
its
Token its
Feature activation+0.000
Very
Token Very
Feature activation+0.000
little
Token little
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
said
Token said
Feature activation+0.000
about
Token about
Feature activation+6.895
his
Token his
Feature activation+0.000
social
Token social
Feature activation+0.000
life
Token life
Feature activation+0.000
other
Token other
Feature activation+0.000
than
Token than
Feature activation+0.343
F
TokenF
Feature activation+0.000
(
Token (
Feature activation+0.000
30
Token30
Feature activation+1.543
°
Token °
Feature activation+0.422
C
TokenC
Feature activation+0.000
),
Token),
Feature activation+6.838
F
Token F
Feature activation+0.243
ogg
Tokenogg
Feature activation+0.000
hires
Token hires
Feature activation+1.942
Frenchman
Token Frenchman
Feature activation+0.000
Jean
Token Jean
Feature activation+0.000
oner
Tokenoner
Feature activation+0.000
's
Token's
Feature activation+0.000
Court
Token Court
Feature activation+0.000
heard
Token heard
Feature activation+4.067
yesterday
Token yesterday
Feature activation+1.302
how
Token how
Feature activation+6.801
Louie
Token Louie
Feature activation+2.762
was
Token was
Feature activation+0.000
bullied
Token bullied
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
.
Token.
Feature activation+1.055
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.418
Do
TokenDo
Feature activation+0.236
you
Token you
Feature activation+0.000
use
Token use
Feature activation+6.736
F
Token F
Feature activation+0.000
.
Token.
Feature activation+0.000
lux
Tokenlux
Feature activation+0.000
?
Token?
Feature activation+0.123
How
Token How
Feature activation+0.228
a
Token a
Feature activation+0.000
sincerely
Token sincerely
Feature activation+0.000
-
Token-
Feature activation+0.000
held
Tokenheld
Feature activation+0.000
belief
Token belief
Feature activation+0.000
that
Token that
Feature activation+6.717
sorcery
Token sorcery
Feature activation+0.000
is
Token is
Feature activation+0.000
real
Token real
Feature activation+0.000
and
Token and
Feature activation+0.000
worthy
Token worthy
Feature activation+0.000
.
Token.
Feature activation+4.958
Those
Token Those
Feature activation+0.000
same
Token same
Feature activation+0.488
traits
Token traits
Feature activation+0.000
will
Token will
Feature activation+0.000
make
Token make
Feature activation+6.579
him
Token him
Feature activation+0.103
one
Token one
Feature activation+0.000
of
Token of
Feature activation+3.455
the
Token the
Feature activation+0.293
NFL
Token NFL
Feature activation+0.000

Top DFA by src position
MAX = 8.323

can
Token can
Feature activation-0.002
Top resid features:
expect
Token expect
Feature activation+0.002
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
get
Token get
Feature activation-0.002
Top resid features:
from
Token from
Feature activation-0.000
Top resid features:
F
Token F
Feature activation+6.300
Top resid features:
.
Token.
Feature activation+0.153
Top resid features:
lux
Tokenlux
Feature activation+0.080
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.028
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
30
Token30
Feature activation-0.000
Top resid features:
°
Token °
Feature activation-0.000
Top resid features:
C
TokenC
Feature activation-0.000
Top resid features:
),
Token),
Feature activation-0.007
Top resid features:
F
Token F
Feature activation+4.329
Top resid features:
ogg
Tokenogg
Feature activation+0.015
Top resid features:
hires
Token hires
Feature activation-0.002
Top resid features:
Frenchman
Token Frenchman
Feature activation+0.003
Top resid features:
Jean
Token Jean
Feature activation-0.063
Top resid features:
Pas
Token Pas
Feature activation+0.035
Top resid features:
ones
Token ones
Feature activation+0.001
Top resid features:
in
Token in
Feature activation+0.003
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
world
Token world
Feature activation-0.002
Top resid features:
Michael
Token Michael
Feature activation-0.103
Top resid features:
F
Token F
Feature activation+8.323
Top resid features:
ass
Tokenass
Feature activation+0.320
Top resid features:
bender
Tokenbender
Feature activation+0.102
Top resid features:
can
Token can
Feature activation-0.001
Top resid features:
call
Token call
Feature activation-0.001
Top resid features:
his
Token his
Feature activation+0.002
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
30
Token30
Feature activation+0.000
Top resid features:
°
Token °
Feature activation-0.000
Top resid features:
C
TokenC
Feature activation-0.000
Top resid features:
),
Token),
Feature activation+0.001
Top resid features:
F
Token F
Feature activation+3.664
Top resid features:
ogg
Tokenogg
Feature activation+0.011
Top resid features:
hires
Token hires
Feature activation-0.002
Top resid features:
Frenchman
Token Frenchman
Feature activation+0.001
Top resid features:
Jean
Token Jean
Feature activation-0.014
Top resid features:
Pas
Token Pas
Feature activation-0.040
Top resid features:
-
Token-
Feature activation+0.001
Top resid features:
day
Tokenday
Feature activation-0.002
Top resid features:
conference
Token conference
Feature activation-0.013
Top resid features:
organised
Token organised
Feature activation-0.002
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
F
Token F
Feature activation+6.468
Top resid features:
int
Tokenint
Feature activation+0.029
Top resid features:
ech
Tokenech
Feature activation+0.022
Top resid features:
Valley
Token Valley
Feature activation+0.020
Top resid features:
Viz
Token Viz
Feature activation-0.073
Top resid features:
ag
Tokenag
Feature activation+0.001
Top resid features:
confirm
Token confirm
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
station
Token station
Feature activation+0.004
Top resid features:
ing
Tokening
Feature activation-0.002
Top resid features:
of
Token of
Feature activation+0.010
Top resid features:
F
Token F
Feature activation+8.177
Top resid features:
16
Token16
Feature activation+0.095
Top resid features:
combat
Token combat
Feature activation-0.028
Top resid features:
aircraft
Token aircraft
Feature activation-0.032
Top resid features:
on
Token on
Feature activation+0.008
Top resid features:
Polish
Token Polish
Feature activation-0.039
Top resid features:
Video
Token Video
Feature activation-0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
If
TokenIf
Feature activation-0.001
Top resid features:
Nick
Token Nick
Feature activation+0.102
Top resid features:
F
Token F
Feature activation+7.962
Top resid features:
oles
Tokenoles
Feature activation+0.062
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
there
Token there
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
who
Token who
Feature activation+0.001
Top resid features:
the
Token the
Feature activation-0.000
Top resid features:
ones
Token ones
Feature activation-0.000
Top resid features:
being
Token being
Feature activation-0.000
Top resid features:
posted
Token posted
Feature activation-0.001
Top resid features:
about
Token about
Feature activation-0.003
Top resid features:
F
Token F
Feature activation+7.693
Top resid features:
of
Tokenof
Feature activation+0.218
Top resid features:
ana
Tokenana
Feature activation+0.039
Top resid features:
âĢ
TokenâĢ
Feature activation+0.007
Top resid features:
Ļ
TokenĻ
Feature activation+0.007
Top resid features:
s
Tokens
Feature activation-0.005
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Despite
Token Despite
Feature activation+0.001
Top resid features:
his
Token his
Feature activation+0.006
Top resid features:
wealth
Token wealth
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
F
Token F
Feature activation+5.716
Top resid features:
ogg
Tokenogg
Feature activation+0.027
Top resid features:
lives
Token lives
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
modest
Token modest
Feature activation-0.000
Top resid features:
life
Token life
Feature activation-0.001
Top resid features:
can
Token can
Feature activation-0.000
Top resid features:
expect
Token expect
Feature activation-0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
get
Token get
Feature activation-0.001
Top resid features:
from
Token from
Feature activation-0.004
Top resid features:
F
Token F
Feature activation+5.940
Top resid features:
.
Token.
Feature activation+0.297
Top resid features:
lux
Tokenlux
Feature activation-0.012
Top resid features:
.
Token.
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
time
Token time
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
I
Token I
Feature activation+0.004
Top resid features:
was
Token was
Feature activation-0.000
Top resid features:
doing
Token doing
Feature activation+0.001
Top resid features:
F
Token F
Feature activation+2.791
Top resid features:
TR
TokenTR
Feature activation-0.006
Top resid features:
mostly
Token mostly
Feature activation+0.002
Top resid features:
out
Token out
Feature activation-0.007
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
sense
Token sense
Feature activation-0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.003
Top resid features:
Commonwealth
Token Commonwealth
Feature activation+0.009
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
banning
Token banning
Feature activation+0.014
Top resid features:
F
Token F
Feature activation+2.805
Top resid features:
GM
TokenGM
Feature activation+0.023
Top resid features:
/
Token/
Feature activation+0.004
Top resid features:
C
TokenC
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
You
Token You
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Despite
Token Despite
Feature activation-0.002
Top resid features:
his
Token his
Feature activation+0.013
Top resid features:
wealth
Token wealth
Feature activation-0.013
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
F
Token F
Feature activation+6.368
Top resid features:
ogg
Tokenogg
Feature activation+0.048
Top resid features:
lives
Token lives
Feature activation-0.010
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
modest
Token modest
Feature activation-0.002
Top resid features:
life
Token life
Feature activation-0.005
Top resid features:
time
Token time
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
I
Token I
Feature activation+0.004
Top resid features:
was
Token was
Feature activation-0.000
Top resid features:
doing
Token doing
Feature activation+0.000
Top resid features:
F
Token F
Feature activation+4.079
Top resid features:
TR
TokenTR
Feature activation+0.035
Top resid features:
mostly
Token mostly
Feature activation+0.002
Top resid features:
out
Token out
Feature activation-0.012
Top resid features:
of
Token of
Feature activation-0.002
Top resid features:
sense
Token sense
Feature activation+0.005
Top resid features:
.
Token.
Feature activation+0.018
Top resid features:
Despite
Token Despite
Feature activation-0.001
Top resid features:
his
Token his
Feature activation+0.010
Top resid features:
wealth
Token wealth
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
F
Token F
Feature activation+4.014
Top resid features:
ogg
Tokenogg
Feature activation+0.027
Top resid features:
lives
Token lives
Feature activation-0.005
Top resid features:
a
Token a
Feature activation+0.003
Top resid features:
modest
Token modest
Feature activation-0.008
Top resid features:
life
Token life
Feature activation-0.004
Top resid features:
.
Token.
Feature activation+0.005
Top resid features:
Despite
Token Despite
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.003
Top resid features:
wealth
Token wealth
Feature activation-0.001
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
F
Token F
Feature activation+4.492
Top resid features:
ogg
Tokenogg
Feature activation+0.016
Top resid features:
lives
Token lives
Feature activation-0.001
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
modest
Token modest
Feature activation-0.001
Top resid features:
life
Token life
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.056
Top resid features:
Ċ
TokenĊ
Feature activation-0.022
Top resid features:
Lou
TokenLou
Feature activation-0.128
Top resid features:
ie
Tokenie
Feature activation+0.050
Top resid features:
Tom
Token Tom
Feature activation+0.019
Top resid features:
F
Token F
Feature activation+7.872
Top resid features:
enton
Tokenenton
Feature activation+0.062
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
pronounced
Token pronounced
Feature activation+0.000
Top resid features:
dead
Token dead
Feature activation+0.002
Top resid features:
after
Token after
Feature activation-0.002
Top resid features:
can
Token can
Feature activation-0.000
Top resid features:
expect
Token expect
Feature activation-0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
get
Token get
Feature activation-0.001
Top resid features:
from
Token from
Feature activation-0.005
Top resid features:
F
Token F
Feature activation+6.495
Top resid features:
.
Token.
Feature activation+0.675
Top resid features:
lux
Tokenlux
Feature activation+0.208
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.025
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
outdated
Token outdated
Feature activation-0.002
Top resid features:
law
Token law
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.004
Top resid features:
charge
Token charge
Feature activation+0.021
Top resid features:
F
Token F
Feature activation+4.062
Top resid features:
of
Tokenof
Feature activation+0.069
Top resid features:
ana
Tokenana
Feature activation+0.018
Top resid features:
.
Token.
Feature activation+0.008
Top resid features:
Nor
Token Nor
Feature activation-0.002
Top resid features:
are
Token are
Feature activation+0.002
Top resid features:
case
Token case
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.002
Top resid features:
Week
Token Week
Feature activation-0.014
Top resid features:
1
Token 1
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
F
Token F
Feature activation+7.307
Top resid features:
ourn
Tokenourn
Feature activation+0.178
Top resid features:
ette
Tokenette
Feature activation-0.107
Top resid features:
early
Token early
Feature activation+0.006
Top resid features:
Sunday
Token Sunday
Feature activation-0.002
Top resid features:
showed
Token showed
Feature activation-0.003
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.05

Head 2: 0.09

Head 3: 0.03

Head 4: 0.02

Head 5: 0.01

Head 6: 0.04

Head 7: 0.11

Head 8: 0.02

Head 9: 0.03

Head 10: 0.52

Head 11: 0.03

Positive logits

F10.74

F8.46

f7.11

f6.65

Fs5.70

fen5.65

FP5.50

FS5.47

FW5.39

FSA5.35

Fen5.35

FH5.34

FF5.11

FTA5.01

Fur4.95

Fiji4.90

Fn4.90

FF4.88

fa4.76

Fern4.72

Negative logits

vulner-2.84

whis-2.84

ascade-2.77

Van-2.63

��-2.53

Hound-2.45

neum-2.43

roup-2.40

rities-2.40

RAL-2.40

aven-2.38

Van-2.35

ihara-2.35

roma-2.32

Bee-2.27

tm-2.25

apolis-2.25

ript-2.25

ski-2.24

collar-2.24

INTERVAL 8.566 - 9.518
CONTAINS 0.000%

F
Token F
Feature activation+0.000
.
Token.
Feature activation+0.000
lux
Tokenlux
Feature activation+0.000
?
Token?
Feature activation+0.123
How
Token How
Feature activation+0.228
has
Token has
Feature activation+9.518
it
Token it
Feature activation+0.000
helped
Token helped
Feature activation+0.327
your
Token your
Feature activation+0.576
sleeping
Token sleeping
Feature activation+0.000
patterns
Token patterns
Feature activation+0.000

INTERVAL 7.615 - 8.566
CONTAINS 0.000%

fashion
Tokenfashion
Feature activation+0.000
able
Tokenable
Feature activation+0.000
in
Token in
Feature activation+1.266
recent
Token recent
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+8.129
this
Token this
Feature activation+0.000
is
Token is
Feature activation+2.639
not
Token not
Feature activation+1.185
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.869
Ċ
TokenĊ
Feature activation+0.034
Ċ
TokenĊ
Feature activation+2.411
At
TokenAt
Feature activation+2.212
the
Token the
Feature activation+0.000
Reform
Token Reform
Feature activation+0.000
Club
Token Club
Feature activation+8.250
,
Token,
Feature activation+7.823
F
Token F
Feature activation+0.000
ogg
Tokenogg
Feature activation+0.000
gets
Token gets
Feature activation+0.000
involved
Token involved
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.411
At
TokenAt
Feature activation+2.212
the
Token the
Feature activation+0.000
Reform
Token Reform
Feature activation+0.000
Club
Token Club
Feature activation+8.250
,
Token,
Feature activation+7.823
F
Token F
Feature activation+0.000
ogg
Tokenogg
Feature activation+0.000
gets
Token gets
Feature activation+0.000
involved
Token involved
Feature activation+0.000
in
Token in
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.881
The
TokenThe
Feature activation+3.308
inaugural
Token inaugural
Feature activation+6.485
session
Token session
Feature activation+0.000
saw
Token saw
Feature activation+7.633
launch
Token launch
Feature activation+0.000
of
Token of
Feature activation+5.280
two
Token two
Feature activation+2.914
acceler
Token acceler
Feature activation+0.000
ators
Tokenators
Feature activation+0.000

INTERVAL 6.663 - 7.615
CONTAINS 0.002%

oner
Tokenoner
Feature activation+0.000
's
Token's
Feature activation+0.000
Court
Token Court
Feature activation+0.000
heard
Token heard
Feature activation+4.067
yesterday
Token yesterday
Feature activation+1.302
how
Token how
Feature activation+6.801
Louie
Token Louie
Feature activation+2.762
was
Token was
Feature activation+0.000
bullied
Token bullied
Feature activation+0.000
for
Token for
Feature activation+0.000
his
Token his
Feature activation+0.000
bor
Tokenbor
Feature activation+0.000
c
Tokenc
Feature activation+0.000
za
Tokenza
Feature activation+0.000
claimed
Token claimed
Feature activation+0.719
that
Token that
Feature activation+2.601
16
Token 16
Feature activation+7.336
US
Token US
Feature activation+1.390
jets
Token jets
Feature activation+0.000
will
Token will
Feature activation+0.000
move
Token move
Feature activation+0.755
from
Token from
Feature activation+1.246
F
TokenF
Feature activation+0.000
(
Token (
Feature activation+0.000
30
Token30
Feature activation+1.543
°
Token °
Feature activation+0.422
C
TokenC
Feature activation+0.000
),
Token),
Feature activation+6.838
F
Token F
Feature activation+0.243
ogg
Tokenogg
Feature activation+0.000
hires
Token hires
Feature activation+1.942
Frenchman
Token Frenchman
Feature activation+0.000
Jean
Token Jean
Feature activation+0.000
et
Tokenet
Feature activation+0.000
,
Token,
Feature activation+5.862
James
Token James
Feature activation+0.250
For
Token For
Feature activation+0.000
ster
Tokenster
Feature activation+0.498
,
Token,
Feature activation+7.012
for
Token for
Feature activation+0.000
bringing
Token bringing
Feature activation+2.011
him
Token him
Feature activation+0.000
shaving
Token shaving
Feature activation+0.000
water
Token water
Feature activation+0.000
topics
Token topics
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.048
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.500
manage
Token manage
Feature activation+7.005
the
Token the
Feature activation+2.537
amount
Token amount
Feature activation+0.148
of
Token of
Feature activation+5.107
incoming
Token incoming
Feature activation+2.809
information
Token information
Feature activation+0.000

INTERVAL 5.711 - 6.663
CONTAINS 0.002%

Old
Token Old
Feature activation+0.000
CS
Token CS
Feature activation+0.000
flies
Token flies
Feature activation+0.153
have
Token have
Feature activation+2.378
significantly
Token significantly
Feature activation+2.273
lower
Token lower
Feature activation+6.224
fat
Token fat
Feature activation+0.000
levels
Token levels
Feature activation+0.000
prior
Token prior
Feature activation+0.000
to
Token to
Feature activation+0.000
starvation
Token starvation
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.459
From
TokenFrom
Feature activation+0.000
Video
Token Video
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.777
Meet
TokenMeet
Feature activation+3.275
Brad
Token Brad
Feature activation+0.000
Smith
Token Smith
Feature activation+0.000
.
Token.
Feature activation+4.124
He
Token He
Feature activation+0.000
the
Token the
Feature activation+1.678
LA
Token LA
Feature activation+0.054
concert
Token concert
Feature activation+0.000
will
Token will
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+6.283
the
Token the
Feature activation+2.842
Ne
Token Ne
Feature activation+0.000
ge
Tokenge
Feature activation+0.000
v
Tokenv
Feature activation+0.000
Well
Token Well
Feature activation+0.000
launch
Token launch
Feature activation+0.000
of
Token of
Feature activation+5.280
two
Token two
Feature activation+2.914
acceler
Token acceler
Feature activation+0.000
ators
Tokenators
Feature activation+0.000
by
Token by
Feature activation+6.258
IC
Token IC
Feature activation+0.000
IC
TokenIC
Feature activation+0.000
I
TokenI
Feature activation+0.000
and
Token and
Feature activation+1.505
Mah
Token Mah
Feature activation+0.000
.
Token.
Feature activation+3.230
Rather
Token Rather
Feature activation+1.568
,
Token,
Feature activation+5.132
they
Token they
Feature activation+0.000
are
Token are
Feature activation+0.000
charging
Token charging
Feature activation+6.377
F
Token F
Feature activation+0.549
of
Tokenof
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
with
Token with
Feature activation+0.000
fraud
Token fraud
Feature activation+0.000

INTERVAL 4.759 - 5.711
CONTAINS 0.005%

not
Token not
Feature activation+0.000
sound
Token sound
Feature activation+0.000
like
Token like
Feature activation+0.775
many
Token many
Feature activation+0.313
,
Token,
Feature activation+0.000
but
Token but
Feature activation+5.326
for
Token for
Feature activation+2.161
a
Token a
Feature activation+0.000
city
Token city
Feature activation+0.000
of
Token of
Feature activation+0.000
72
Token 72
Feature activation+0.000
2014
Token 2014
Feature activation+0.000
practically
Token practically
Feature activation+0.000
doubled
Token doubled
Feature activation+0.000
,
Token,
Feature activation+3.646
recently
Token recently
Feature activation+2.509
,
Token,
Feature activation+5.130
the
Token the
Feature activation+2.543
growth
Token growth
Feature activation+0.000
generally
Token generally
Feature activation+0.000
just
Token just
Feature activation+0.000
stagn
Token stagn
Feature activation+0.000
I
Token I
Feature activation+0.000
had
Token had
Feature activation+0.000
to
Token to
Feature activation+0.000
get
Token get
Feature activation+0.550
rid
Token rid
Feature activation+0.000
of
Token of
Feature activation+5.152
some
Token some
Feature activation+2.692
topics
Token topics
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.048
able
Token able
Feature activation+0.000
the
Token the
Feature activation+0.000
fourth
Token fourth
Feature activation+0.000
-
Token-
Feature activation+0.000
quarter
Tokenquarter
Feature activation+0.000
rampage
Token rampage
Feature activation+0.000
showed
Token showed
Feature activation+5.546
how
Token how
Feature activation+5.235
deadly
Token deadly
Feature activation+4.395
he
Token he
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.776
N
TokenN
Feature activation+0.000
aid
Tokenaid
Feature activation+0.000
u
Tokenu
Feature activation+0.000
said
Token said
Feature activation+5.062
the
Token the
Feature activation+3.152
state
Token state
Feature activation+0.000
was
Token was
Feature activation+0.000
positioning
Token positioning
Feature activation+3.610
itself
Token itself
Feature activation+0.000

INTERVAL 3.807 - 4.759
CONTAINS 0.009%

aged
Tokenaged
Feature activation+0.000
across
Token across
Feature activation+1.729
many
Token many
Feature activation+0.931
agencies
Token agencies
Feature activation+0.000
.
Token.
Feature activation+0.786
Since
Token Since
Feature activation+3.849
that
Token that
Feature activation+1.062
time
Token time
Feature activation+0.616
,
Token,
Feature activation+2.561
Google
Token Google
Feature activation+0.000
has
Token has
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
has
Token has
Feature activation+0.000
more
Token more
Feature activation+1.095
images
Token images
Feature activation+0.000
of
Token of
Feature activation+4.193
the
Token the
Feature activation+1.110
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Second
TokenSecond
Feature activation+0.024
Paris
Token Paris
Feature activation+0.000
the
Token the
Feature activation+4.013
very
Token very
Feature activation+0.000
next
Token next
Feature activation+0.000
day
Token day
Feature activation+1.023
,
Token,
Feature activation+1.109
the
Token the
Feature activation+4.555
bureau
Token bureau
Feature activation+0.000
named
Token named
Feature activation+0.000
Bruce
Token Bruce
Feature activation+0.000
the
Token the
Feature activation+0.871
mail
Token mail
Feature activation+0.000
:
Token :
Feature activation+0.128
Gund
Token Gund
Feature activation+0.000
o
Tokeno
Feature activation+0.000
T
TokenT
Feature activation+0.000
oggle
Tokenoggle
Feature activation+0.165
<
Token <
Feature activation+4.434
CR
Token CR
Feature activation+0.000
>
Token >
Feature activation+0.379
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
By
TokenBy
Feature activation+0.000
who
Token who
Feature activation+0.000
were
Token were
Feature activation+0.000
involved
Token involved
Feature activation+0.000
.
Token.
Feature activation+2.060
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.243
Based
TokenBased
Feature activation+0.000
on
Token on
Feature activation+1.251
the
Token the
Feature activation+0.000
description
Token description
Feature activation+0.200
officers
Token officers
Feature activation+0.000

INTERVAL 2.855 - 3.807
CONTAINS 0.017%

one
Token one
Feature activation+0.000
kil
Token kil
Feature activation+0.000
o
Tokeno
Feature activation+0.000
of
Token of
Feature activation+0.113
gold
Token gold
Feature activation+0.000
has
Token has
Feature activation+3.650
the
Token the
Feature activation+1.156
same
Token same
Feature activation+0.398
value
Token value
Feature activation+0.000
as
Token as
Feature activation+0.000
another
Token another
Feature activation+0.000
end
Token end
Feature activation+1.755
class
Token class
Feature activation+0.434
Person
Token Person
Feature activation+0.263
include
Token include
Feature activation+1.198
Role
Token Role
Feature activation+0.579
System
TokenSystem
Feature activation+3.194
end
Token end
Feature activation+0.929
Person
Token Person
Feature activation+0.441
.
Token.
Feature activation+1.162
new
Tokennew
Feature activation+0.468
.
Token.
Feature activation+1.275
ridiculous
Token ridiculous
Feature activation+0.000
and
Token and
Feature activation+0.000
outdated
Token outdated
Feature activation+0.000
law
Token law
Feature activation+0.000
to
Token to
Feature activation+0.000
charge
Token charge
Feature activation+3.362
F
Token F
Feature activation+0.185
of
Tokenof
Feature activation+0.000
ana
Tokenana
Feature activation+0.000
.
Token.
Feature activation+3.429
Nor
Token Nor
Feature activation+0.000
Advertisement
TokenAdvertisement
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.281
The
TokenThe
Feature activation+0.304
implications
Token implications
Feature activation+0.000
of
Token of
Feature activation+3.069
this
Token this
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
other
Tokenother
Feature activation+0.000
than
Token than
Feature activation+0.577
that
Token that
Feature activation+1.249
was
Token was
Feature activation+7.208
the
Token the
Feature activation+0.389
Wild
Token Wild
Feature activation+0.000
cat
Tokencat
Feature activation+0.000
formation
Token formation
Feature activation+1.059
.
Token.
Feature activation+3.378
The
Token The
Feature activation+0.000
starting
Token starting
Feature activation+0.000
quarterback
Token quarterback
Feature activation+0.000
was
Token was
Feature activation+1.781
positioned
Token positioned
Feature activation+0.000

INTERVAL 1.904 - 2.855
CONTAINS 0.029%

in
Token in
Feature activation+0.290
a
Token a
Feature activation+0.000
crew
Token crew
Feature activation+0.000
chief
Token chief
Feature activation+0.000
role
Token role
Feature activation+0.000
.
Token.
Feature activation+2.407
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.767
One
TokenOne
Feature activation+0.508
of
Token of
Feature activation+3.426
the
Token the
Feature activation+1.130
F
Token F
Feature activation+0.000
ols
Tokenols
Feature activation+0.000
om
Tokenom
Feature activation+0.000
Street
Token Street
Feature activation+0.000
and
Token and
Feature activation+0.000
on
Token on
Feature activation+2.632
18
Token 18
Feature activation+0.000
th
Tokenth
Feature activation+0.000
Street
Token Street
Feature activation+0.000
to
Token to
Feature activation+0.394
limit
Token limit
Feature activation+0.000
name
Token name
Feature activation+0.000
of
Token of
Feature activation+1.018
click
Token click
Feature activation+0.000
b
Tokenb
Feature activation+0.000
ait
Tokenait
Feature activation+0.000
.
Token.
Feature activation+2.324
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.133
Let
TokenLet
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
the
Token the
Feature activation+0.000
Reform
Token Reform
Feature activation+0.000
Club
Token Club
Feature activation+0.000
.
Token.
Feature activation+4.040
Having
Token Having
Feature activation+0.000
dismissed
Token dismissed
Feature activation+2.165
his
Token his
Feature activation+0.000
former
Token former
Feature activation+0.000
val
Token val
Feature activation+0.000
et
Tokenet
Feature activation+0.000
,
Token,
Feature activation+5.862
United
Token United
Feature activation+0.000
States
Token States
Feature activation+0.000
has
Token has
Feature activation+0.000
been
Token been
Feature activation+0.000
without
Token without
Feature activation+0.468
a
Token a
Feature activation+2.589
full
Token full
Feature activation+2.550
-
Token-
Feature activation+0.000
time
Tokentime
Feature activation+3.306
F
Token F
Feature activation+0.000
1
Token1
Feature activation+0.000

INTERVAL 0.952 - 1.904
CONTAINS 0.071%

bugs
Token bugs
Feature activation+0.000
.)
Token.)
Feature activation+1.432
No
Token No
Feature activation+0.000
official
Token official
Feature activation+0.931
presence
Token presence
Feature activation+0.000
on
Token on
Feature activation+1.624
the
Token the
Feature activation+1.131
Steam
Token Steam
Feature activation+0.000
store
Token store
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
recreational
Token recreational
Feature activation+0.165
programs
Token programs
Feature activation+0.000
and
Token and
Feature activation+0.000
facilities
Token facilities
Feature activation+0.000
for
Token for
Feature activation+1.019
the
Token the
Feature activation+1.316
young
Token young
Feature activation+0.000
men
Token men
Feature activation+0.000
and
Token and
Feature activation+0.000
women
Token women
Feature activation+0.000
soldiers
Token soldiers
Feature activation+0.000
?
Token?
Feature activation+0.000
(
Token(
Feature activation+0.000
role
Tokenrole
Feature activation+0.000
)
Token)
Feature activation+0.891
self
Token self
Feature activation+0.000
.
Token.
Feature activation+1.025
role
Tokenrole
Feature activation+0.205
==
Token ==
Feature activation+0.081
role
Token role
Feature activation+1.363
.
Token.
Feature activation+0.000
to
Tokento
Feature activation+0.000
of
Token of
Feature activation+3.069
this
Token this
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
other
Tokenother
Feature activation+0.000
than
Token than
Feature activation+0.577
that
Token that
Feature activation+1.249
Apple
Token Apple
Feature activation+0.000
is
Token is
Feature activation+0.000
being
Token being
Feature activation+0.000
even
Token even
Feature activation+0.000
more
Token more
Feature activation+0.000
System
TokenSystem
Feature activation+3.194
end
Token end
Feature activation+0.929
Person
Token Person
Feature activation+0.441
.
Token.
Feature activation+1.162
new
Tokennew
Feature activation+0.468
.
Token.
Feature activation+1.275
is
Tokenis
Feature activation+0.000
_
Token_
Feature activation+0.000
role
Tokenrole
Feature activation+0.181
?
Token?
Feature activation+0.062
('
Token('
Feature activation+0.000

INTERVAL 0.000 - 0.952
CONTAINS 99.865%

289
Token289
Feature activation+0.000
5
Token 5
Feature activation+0.000
1935
Token 1935
Feature activation+0.000
Browns
Token Browns
Feature activation+0.000
19
Token 19
Feature activation+0.000
50
Token 50
Feature activation+0.000
.
Token .
Feature activation+0.000
275
Token275
Feature activation+0.000
8
Token 8
Feature activation+0.000
46
Token 46
Feature activation+0.000
37
Token 37
Feature activation+0.000
hot
Token hot
Feature activation+0.000
first
Token first
Feature activation+0.000
half
Token half
Feature activation+0.000
wasn
Token wasn
Feature activation+0.000
't
Token't
Feature activation+0.000
enough
Token enough
Feature activation+0.000
.
Token.
Feature activation+0.000
They
Token They
Feature activation+0.000
got
Token got
Feature activation+0.000
21
Token 21
Feature activation+0.000
shots
Token shots
Feature activation+0.000
their
Token their
Feature activation+0.000
source
Token source
Feature activation+0.000
code
Token code
Feature activation+0.000
.
Token.
Feature activation+0.000
Very
Token Very
Feature activation+0.000
often
Token often
Feature activation+0.000
,
Token,
Feature activation+0.000
these
Token these
Feature activation+0.000
libraries
Token libraries
Feature activation+0.000
silently
Token silently
Feature activation+0.000
perform
Token perform
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
p
Tokenp
Feature activation+0.000
ip
Tokenip
Feature activation+0.000
eline
Tokeneline
Feature activation+0.000
cross
Token cross
Feature activation+0.000
roads
Tokenroads
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
,
Token,
Feature activation+0.000
they
Token they
Feature activation+0.000
found
Token found
Feature activation+0.000
that
Token that
Feature activation+0.000
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.000
important
Token important
Feature activation+0.000
to
Token to
Feature activation+0.000
identify
Token identify
Feature activation+0.000
the
Token the
Feature activation+0.000
value
Token value
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 H10.10: (feature 4416)

TOP ACTIVATIONS
MAX = 10.002

of
Token of
Feature activation+0.636
religious
Token religious
Feature activation+0.000
up
Token up
Feature activation+0.000
st
Tokenst
Feature activation+0.000
arts
Tokenarts
Feature activation+0.000
.
Token.
Feature activation+10.002
Mohammed
Token Mohammed
Feature activation+0.000
,
Token,
Feature activation+1.357
for
Token for
Feature activation+1.132
instance
Token instance
Feature activation+0.000
,
Token,
Feature activation+0.000
l
Tokenl
Feature activation+0.000
8
Token8
Feature activation+0.000
h
Tokenh
Feature activation+0.000
1
Token1
Feature activation+0.000
Q
TokenQ
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+9.542
Jessica
Token Jessica
Feature activation+0.827
Ch
Token Ch
Feature activation+0.000
ast
Tokenast
Feature activation+0.000
ain
Tokenain
Feature activation+0.409
(@
Token (@
Feature activation+1.183
They
TokenThey
Feature activation+0.000
compromised
Token compromised
Feature activation+2.197
on
Token on
Feature activation+4.450
a
Token a
Feature activation+0.401
sidewalk
Token sidewalk
Feature activation+0.000
on
Token on
Feature activation+9.134
just
Token just
Feature activation+5.054
one
Token one
Feature activation+0.711
side
Token side
Feature activation+0.000
,
Token,
Feature activation+0.000
using
Token using
Feature activation+0.444
complaints
Token complaints
Feature activation+0.876
,
Token,
Feature activation+9.032
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
years
Token years
Feature activation+8.553
,
Token,
Feature activation+9.113
the
Token the
Feature activation+6.600
Ch
Token Ch
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
ms
Tokenms
Feature activation+0.000
According
TokenAccording
Feature activation+0.067
to
Token to
Feature activation+1.808
the
Token the
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000
complaints
Token complaints
Feature activation+0.876
,
Token,
Feature activation+9.032
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
years
Token years
Feature activation+8.553
,
Token,
Feature activation+9.113
the
Token the
Feature activation+6.600
criminal
Token criminal
Feature activation+0.000
complaints
Token complaints
Feature activation+0.876
,
Token,
Feature activation+9.032
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
years
Token years
Feature activation+8.553
,
Token,
Feature activation+9.113
the
Token the
Feature activation+6.600
Ch
Token Ch
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
safety
Token safety
Feature activation+0.000
and
Token and
Feature activation+0.000
confidence
Token confidence
Feature activation+0.000
.
Token.
Feature activation+4.788
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+8.521
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.656
The
TokenThe
Feature activation+1.167
suspect
Token suspect
Feature activation+0.000
berries
Token berries
Feature activation+0.131
May
Token May
Feature activation+0.000
31
Token 31
Feature activation+0.000
,
Token,
Feature activation+0.000
2012
Token 2012
Feature activation+4.154
,
Token,
Feature activation+7.682
Colin
Token Colin
Feature activation+8.118
Ch
Token Ch
Feature activation+0.000
ish
Tokenish
Feature activation+0.096
ol
Tokenol
Feature activation+0.081
m
Tokenm
Feature activation+0.000
III
Token III
Feature activation+0.000
or
Tokenor
Feature activation+0.000
expanded
Token expanded
Feature activation+0.000
!)
Token!)
Feature activation+0.324
to
Token to
Feature activation+2.686
whatever
Token whatever
Feature activation+3.511
sites
Token sites
Feature activation+8.109
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
interested
Token interested
Feature activation+0.000
m
Tokenm
Feature activation+0.000
in
Token in
Feature activation+3.814
favour
Token favour
Feature activation+0.000
of
Token of
Feature activation+2.029
sidewalks
Token sidewalks
Feature activation+0.000
on
Token on
Feature activation+8.096
both
Token both
Feature activation+2.376
sides
Token sides
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+1.352
it
Token it
Feature activation+0.000
affiliates
Token affiliates
Feature activation+0.000
and
Token and
Feature activation+0.735
the
Token the
Feature activation+1.331
ability
Token ability
Feature activation+0.028
to
Token to
Feature activation+0.000
let
Token let
Feature activation+8.035
Ch
Token Ch
Feature activation+0.000
urnal
Tokenurnal
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
run
Token run
Feature activation+0.194
on
Token on
Feature activation+0.000
Text
Token Text
Feature activation+0.000
iles
Tokeniles
Feature activation+0.000
were
Token were
Feature activation+0.000
still
Token still
Feature activation+0.000
important
Token important
Feature activation+0.000
to
Token to
Feature activation+8.010
the
Token the
Feature activation+5.379
community
Token community
Feature activation+0.000
,
Token,
Feature activation+0.683
but
Token but
Feature activation+3.483
cheap
Token cheap
Feature activation+0.000
settings
Token settings
Feature activation+0.000
for
Token for
Feature activation+6.618
the
Token the
Feature activation+5.756
browser
Token browser
Feature activation+0.094
extension
Token extension
Feature activation+0.372
.
Token.
Feature activation+8.003
We
Token We
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
provided
Token provided
Feature activation+6.679
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
difficult
Token difficult
Feature activation+0.000
to
Token to
Feature activation+0.000
understand
Token understand
Feature activation+0.548
why
Token why
Feature activation+7.957
the
Token the
Feature activation+4.649
council
Token council
Feature activation+0.000
would
Token would
Feature activation+0.000
choose
Token choose
Feature activation+3.531
to
Token to
Feature activation+0.000
III
Token III
Feature activation+0.000
,
Token,
Feature activation+0.000
62
Token 62
Feature activation+0.000
,
Token,
Feature activation+0.127
and
Token and
Feature activation+0.000
Andrea
Token Andrea
Feature activation+7.882
Ch
Token Ch
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
m
Tokenm
Feature activation+0.498
,
Token,
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
interested
Token interested
Feature activation+0.000
in
Token in
Feature activation+0.000
.
Token.
Feature activation+7.880
Ċ
TokenĊ
Feature activation+1.727
Ċ
TokenĊ
Feature activation+7.549
We
TokenWe
Feature activation+0.073
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
number
Token number
Feature activation+0.000
of
Token of
Feature activation+2.197
instances
Token instances
Feature activation+0.000
of
Token of
Feature activation+5.960
articles
Token articles
Feature activation+0.000
about
Token about
Feature activation+7.772
science
Token science
Feature activation+0.414
topics
Token topics
Feature activation+0.000
relying
Token relying
Feature activation+0.000
heavily
Token heavily
Feature activation+0.402
on
Token on
Feature activation+7.261
and
Token and
Feature activation+0.000
May
Token May
Feature activation+0.000
31
Token 31
Feature activation+0.000
,
Token,
Feature activation+0.000
2012
Token 2012
Feature activation+4.154
,
Token,
Feature activation+7.682
Colin
Token Colin
Feature activation+8.118
Ch
Token Ch
Feature activation+0.000
ish
Tokenish
Feature activation+0.096
ol
Tokenol
Feature activation+0.081
m
Tokenm
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.128
The
TokenThe
Feature activation+6.684
best
Token best
Feature activation+1.646
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.033
detect
Token detect
Feature activation+7.680
influence
Token influence
Feature activation+0.000
and
Token and
Feature activation+0.000
language
Token language
Feature activation+0.000
sharing
Token sharing
Feature activation+0.000
from
Token from
Feature activation+3.613
runs
Token runs
Feature activation+0.121
on
Token on
Feature activation+0.000
by
Token by
Feature activation+0.000
going
Token going
Feature activation+0.041
into
Token into
Feature activation+7.418
the
Token the
Feature activation+7.654
settings
Token settings
Feature activation+0.000
for
Token for
Feature activation+6.618
the
Token the
Feature activation+5.756
browser
Token browser
Feature activation+0.094
extension
Token extension
Feature activation+0.372

Top DFA by src position
MAX = 10.566

Religion
Token Religion
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation+0.032
Top resid features:
Ŀ
TokenĿ
Feature activation+0.001
Top resid features:
David
Token David
Feature activation-0.077
Top resid features:
Ch
Token Ch
Feature activation+10.566
Top resid features:
ides
Tokenides
Feature activation+0.043
Top resid features:
ter
Tokenter
Feature activation-0.001
Top resid features:
argues
Token argues
Feature activation-0.011
Top resid features:
that
Token that
Feature activation-0.001
Top resid features:
the
Token the
Feature activation+0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.064
Top resid features:
Ch
Token Ch
Feature activation+9.622
Top resid features:
ast
Tokenast
Feature activation+0.137
Top resid features:
ain
Tokenain
Feature activation+0.117
Top resid features:
retweet
Token retweet
Feature activation+0.083
Top resid features:
ed
Tokened
Feature activation+0.029
Top resid features:
another
Token another
Feature activation+0.010
Top resid features:
ed
Tokened
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
sidewalks
Token sidewalks
Feature activation-0.019
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
On
Token On
Feature activation+0.001
Top resid features:
Ch
Token Ch
Feature activation+8.646
Top resid features:
ine
Tokenine
Feature activation+0.081
Top resid features:
Drive
Token Drive
Feature activation-0.040
Top resid features:
,
Token,
Feature activation+0.007
Top resid features:
there
Token there
Feature activation-0.001
Top resid features:
had
Token had
Feature activation-0.002
Top resid features:
31
Token 31
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
2012
Token 2012
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
Colin
Token Colin
Feature activation-0.283
Top resid features:
Ch
Token Ch
Feature activation+5.654
Top resid features:
ish
Tokenish
Feature activation+0.025
Top resid features:
ol
Tokenol
Feature activation-0.001
Top resid features:
m
Tokenm
Feature activation-0.002
Top resid features:
III
Token III
Feature activation-0.013
Top resid features:
,
Token,
Feature activation+0.006
Top resid features:
31
Token 31
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
2012
Token 2012
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
Colin
Token Colin
Feature activation-0.389
Top resid features:
Ch
Token Ch
Feature activation+6.772
Top resid features:
ish
Tokenish
Feature activation+0.032
Top resid features:
ol
Tokenol
Feature activation-0.001
Top resid features:
m
Tokenm
Feature activation+0.001
Top resid features:
III
Token III
Feature activation-0.010
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
31
Token 31
Feature activation-0.000
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
2012
Token 2012
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
Colin
Token Colin
Feature activation-0.338
Top resid features:
Ch
Token Ch
Feature activation+5.103
Top resid features:
ish
Tokenish
Feature activation+0.028
Top resid features:
ol
Tokenol
Feature activation-0.000
Top resid features:
m
Tokenm
Feature activation-0.001
Top resid features:
III
Token III
Feature activation-0.011
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
laboratory
Token laboratory
Feature activation-0.010
Top resid features:
tests
Token tests
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
âĢ
TokenâĢ
Feature activation+0.029
Top resid features:
Ŀ
TokenĿ
Feature activation-0.006
Top resid features:
Ch
Token Ch
Feature activation+9.319
Top resid features:
aur
Tokenaur
Feature activation+0.038
Top resid features:
said
Token said
Feature activation+0.020
Top resid features:
.
Token.
Feature activation+0.022
Top resid features:
âĢ
Token âĢ
Feature activation+0.030
Top resid features:
ľ
Tokenľ
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.028
Top resid features:
m
Tokenm
Feature activation+0.080
Top resid features:
III
Token III
Feature activation-0.073
Top resid features:
and
Token and
Feature activation-0.009
Top resid features:
Andrea
Token Andrea
Feature activation-0.080
Top resid features:
Ch
Token Ch
Feature activation+8.895
Top resid features:
ish
Tokenish
Feature activation+0.039
Top resid features:
ol
Tokenol
Feature activation-0.001
Top resid features:
m
Tokenm
Feature activation+0.011
Top resid features:
are
Token are
Feature activation-0.007
Top resid features:
charged
Token charged
Feature activation-0.009
Top resid features:
can
Token can
Feature activation-0.002
Top resid features:
easily
Token easily
Feature activation-0.001
Top resid features:
change
Token change
Feature activation+0.002
Top resid features:
which
Token which
Feature activation+0.005
Top resid features:
sites
Token sites
Feature activation+0.005
Top resid features:
Ch
Token Ch
Feature activation+4.390
Top resid features:
urnal
Tokenurnal
Feature activation+0.020
Top resid features:
ism
Tokenism
Feature activation+0.004
Top resid features:
runs
Token runs
Feature activation-0.012
Top resid features:
on
Token on
Feature activation+0.002
Top resid features:
by
Token by
Feature activation-0.000
Top resid features:
ed
Tokened
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
sidewalks
Token sidewalks
Feature activation-0.028
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
On
Token On
Feature activation-0.000
Top resid features:
Ch
Token Ch
Feature activation+7.430
Top resid features:
ine
Tokenine
Feature activation+0.186
Top resid features:
Drive
Token Drive
Feature activation-0.045
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
there
Token there
Feature activation+0.001
Top resid features:
had
Token had
Feature activation-0.000
Top resid features:
can
Token can
Feature activation-0.002
Top resid features:
easily
Token easily
Feature activation-0.002
Top resid features:
change
Token change
Feature activation+0.004
Top resid features:
which
Token which
Feature activation+0.010
Top resid features:
sites
Token sites
Feature activation-0.015
Top resid features:
Ch
Token Ch
Feature activation+5.344
Top resid features:
urnal
Tokenurnal
Feature activation+0.023
Top resid features:
ism
Tokenism
Feature activation+0.001
Top resid features:
runs
Token runs
Feature activation-0.004
Top resid features:
on
Token on
Feature activation+0.002
Top resid features:
by
Token by
Feature activation-0.003
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
weaving
Token weaving
Feature activation-0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
disappearing
Token disappearing
Feature activation-0.002
Top resid features:
from
Token from
Feature activation+0.002
Top resid features:
Ch
Token Ch
Feature activation+5.980
Top resid features:
inc
Tokeninc
Feature activation+0.007
Top resid features:
hero
Tokenhero
Feature activation+0.048
Top resid features:
.
Token.
Feature activation+0.017
Top resid features:
The
Token The
Feature activation+0.002
Top resid features:
techniques
Token techniques
Feature activation+0.004
Top resid features:
we
Token we
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.093
Top resid features:
Ļ
TokenĻ
Feature activation+0.077
Top resid features:
ve
Tokenve
Feature activation-0.006
Top resid features:
designed
Token designed
Feature activation-0.013
Top resid features:
Ch
Token Ch
Feature activation+6.711
Top resid features:
urnal
Tokenurnal
Feature activation+0.051
Top resid features:
ism
Tokenism
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation-0.001
Top resid features:
quite
Token quite
Feature activation+0.005
Top resid features:
services
Token services
Feature activation-0.003
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
theat
Token theat
Feature activation+0.046
Top resid features:
res
Tokenres
Feature activation+0.009
Top resid features:
at
Token at
Feature activation+0.001
Top resid features:
Ch
Token Ch
Feature activation+8.108
Top resid features:
aring
Tokenaring
Feature activation+0.012
Top resid features:
Cross
Token Cross
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
âĢ
TokenâĢ
Feature activation+0.005
Top resid features:
Ŀ
TokenĿ
Feature activation+0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.018
Top resid features:
m
Tokenm
Feature activation+0.015
Top resid features:
III
Token III
Feature activation-0.033
Top resid features:
and
Token and
Feature activation-0.003
Top resid features:
Andrea
Token Andrea
Feature activation-0.062
Top resid features:
Ch
Token Ch
Feature activation+8.466
Top resid features:
ish
Tokenish
Feature activation+0.008
Top resid features:
ol
Tokenol
Feature activation-0.004
Top resid features:
m
Tokenm
Feature activation+0.017
Top resid features:
are
Token are
Feature activation-0.016
Top resid features:
charged
Token charged
Feature activation-0.005
Top resid features:
we
Token we
Feature activation+0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.097
Top resid features:
Ļ
TokenĻ
Feature activation+0.052
Top resid features:
ve
Tokenve
Feature activation-0.006
Top resid features:
designed
Token designed
Feature activation-0.009
Top resid features:
Ch
Token Ch
Feature activation+6.138
Top resid features:
urnal
Tokenurnal
Feature activation+0.033
Top resid features:
ism
Tokenism
Feature activation+0.005
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
be
Token be
Feature activation-0.001
Top resid features:
quite
Token quite
Feature activation+0.004
Top resid features:
evidence
Token evidence
Feature activation-0.001
Top resid features:
from
Token from
Feature activation+0.003
Top resid features:
my
Token my
Feature activation+0.000
Top resid features:
experience
Token experience
Feature activation+0.002
Top resid features:
using
Token using
Feature activation+0.001
Top resid features:
Ch
Token Ch
Feature activation+8.164
Top resid features:
urnal
Tokenurnal
Feature activation+0.141
Top resid features:
ism
Tokenism
Feature activation-0.002
Top resid features:
,
Token,
Feature activation+0.013
Top resid features:
I
Token I
Feature activation-0.002
Top resid features:
âĢ
TokenâĢ
Feature activation+0.033
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.029
Top resid features:
m
Tokenm
Feature activation+0.158
Top resid features:
III
Token III
Feature activation-0.164
Top resid features:
and
Token and
Feature activation-0.001
Top resid features:
Andrea
Token Andrea
Feature activation-0.248
Top resid features:
Ch
Token Ch
Feature activation+8.439
Top resid features:
ish
Tokenish
Feature activation+0.028
Top resid features:
ol
Tokenol
Feature activation+0.001
Top resid features:
m
Tokenm
Feature activation+0.003
Top resid features:
are
Token are
Feature activation-0.001
Top resid features:
charged
Token charged
Feature activation-0.014
Top resid features:
:
Token:
Feature activation-0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.006
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Using
TokenUsing
Feature activation-0.003
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
Ch
Token Ch
Feature activation+8.412
Top resid features:
urnal
Tokenurnal
Feature activation+0.115
Top resid features:
ism
Tokenism
Feature activation-0.025
Top resid features:
browser
Token browser
Feature activation-0.056
Top resid features:
extension
Token extension
Feature activation-0.008
Top resid features:
it
Token it
Feature activation+0.001
Top resid features:
we
Token we
Feature activation-0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.017
Top resid features:
Ļ
TokenĻ
Feature activation+0.008
Top resid features:
ve
Tokenve
Feature activation-0.004
Top resid features:
designed
Token designed
Feature activation-0.011
Top resid features:
Ch
Token Ch
Feature activation+5.963
Top resid features:
urnal
Tokenurnal
Feature activation+0.047
Top resid features:
ism
Tokenism
Feature activation+0.003
Top resid features:
to
Token to
Feature activation-0.001
Top resid features:
be
Token be
Feature activation-0.001
Top resid features:
quite
Token quite
Feature activation-0.001
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.05

Head 3: 0.04

Head 4: 0.03

Head 5: 0.03

Head 6: 0.04

Head 7: 0.09

Head 8: 0.02

Head 9: 0.05

Head 10: 0.52

Head 11: 0.03

Positive logits

Ch10.99

Ch9.58

ch8.31

ch7.62

Cham6.05

CH6.03

CH5.64

Chap5.63

Chu5.40

Chak5.39

Chong5.02

Chill4.95

Chal4.94

Chi4.82

Cha4.72

Chow4.70

Chapman4.69

Chatt4.69

Chaff4.66

Chad4.66

Negative logits

�醒-3.93

insula-3.51

ilities-3.03

OD-3.01

FORE-2.99

mart-2.96

Ire-2.91

Reviewer-2.90

mart-2.85

RN-2.84

LIN-2.82

gard-2.80

ERN-2.79

RN-2.78

Ree-2.77

Droid-2.75

LB-2.68

OB-2.68

enstein-2.68

azard-2.67

INTERVAL 9.002 - 10.002
CONTAINS 0.001%

of
Token of
Feature activation+0.636
religious
Token religious
Feature activation+0.000
up
Token up
Feature activation+0.000
st
Tokenst
Feature activation+0.000
arts
Tokenarts
Feature activation+0.000
.
Token.
Feature activation+10.002
Mohammed
Token Mohammed
Feature activation+0.000
,
Token,
Feature activation+1.357
for
Token for
Feature activation+1.132
instance
Token instance
Feature activation+0.000
,
Token,
Feature activation+0.000
According
TokenAccording
Feature activation+0.067
to
Token to
Feature activation+1.808
the
Token the
Feature activation+0.000
criminal
Token criminal
Feature activation+0.000
complaints
Token complaints
Feature activation+0.876
,
Token,
Feature activation+9.032
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
years
Token years
Feature activation+8.553
,
Token,
Feature activation+9.113
the
Token the
Feature activation+6.600
complaints
Token complaints
Feature activation+0.876
,
Token,
Feature activation+9.032
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
years
Token years
Feature activation+8.553
,
Token,
Feature activation+9.113
the
Token the
Feature activation+6.600
Ch
Token Ch
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
ms
Tokenms
Feature activation+0.000
They
TokenThey
Feature activation+0.000
compromised
Token compromised
Feature activation+2.197
on
Token on
Feature activation+4.450
a
Token a
Feature activation+0.401
sidewalk
Token sidewalk
Feature activation+0.000
on
Token on
Feature activation+9.134
just
Token just
Feature activation+5.054
one
Token one
Feature activation+0.711
side
Token side
Feature activation+0.000
,
Token,
Feature activation+0.000
using
Token using
Feature activation+0.444
l
Tokenl
Feature activation+0.000
8
Token8
Feature activation+0.000
h
Tokenh
Feature activation+0.000
1
Token1
Feature activation+0.000
Q
TokenQ
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+9.542
Jessica
Token Jessica
Feature activation+0.827
Ch
Token Ch
Feature activation+0.000
ast
Tokenast
Feature activation+0.000
ain
Tokenain
Feature activation+0.409
(@
Token (@
Feature activation+1.183

INTERVAL 8.001 - 9.002
CONTAINS 0.001%

or
Tokenor
Feature activation+0.000
expanded
Token expanded
Feature activation+0.000
!)
Token!)
Feature activation+0.324
to
Token to
Feature activation+2.686
whatever
Token whatever
Feature activation+3.511
sites
Token sites
Feature activation+8.109
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
interested
Token interested
Feature activation+0.000
May
Token May
Feature activation+0.000
31
Token 31
Feature activation+0.000
,
Token,
Feature activation+0.000
2012
Token 2012
Feature activation+4.154
,
Token,
Feature activation+7.682
Colin
Token Colin
Feature activation+8.118
Ch
Token Ch
Feature activation+0.000
ish
Tokenish
Feature activation+0.096
ol
Tokenol
Feature activation+0.081
m
Tokenm
Feature activation+0.000
III
Token III
Feature activation+0.000
m
Tokenm
Feature activation+0.000
in
Token in
Feature activation+3.814
favour
Token favour
Feature activation+0.000
of
Token of
Feature activation+2.029
sidewalks
Token sidewalks
Feature activation+0.000
on
Token on
Feature activation+8.096
both
Token both
Feature activation+2.376
sides
Token sides
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+1.352
it
Token it
Feature activation+0.000
settings
Token settings
Feature activation+0.000
for
Token for
Feature activation+6.618
the
Token the
Feature activation+5.756
browser
Token browser
Feature activation+0.094
extension
Token extension
Feature activation+0.372
.
Token.
Feature activation+8.003
We
Token We
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
provided
Token provided
Feature activation+6.679
criminal
Token criminal
Feature activation+0.000
complaints
Token complaints
Feature activation+0.876
,
Token,
Feature activation+9.032
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
years
Token years
Feature activation+8.553
,
Token,
Feature activation+9.113
the
Token the
Feature activation+6.600
Ch
Token Ch
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
ol
Tokenol
Feature activation+0.000

INTERVAL 7.001 - 8.001
CONTAINS 0.002%

runs
Token runs
Feature activation+0.121
on
Token on
Feature activation+0.000
by
Token by
Feature activation+0.000
going
Token going
Feature activation+0.041
into
Token into
Feature activation+7.418
the
Token the
Feature activation+7.654
settings
Token settings
Feature activation+0.000
for
Token for
Feature activation+6.618
the
Token the
Feature activation+5.756
browser
Token browser
Feature activation+0.094
extension
Token extension
Feature activation+0.372
always
Token always
Feature activation+0.000
sunny
Token sunny
Feature activation+0.000
in
Token in
Feature activation+0.614
LA
Token LA
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
but
Token but
Feature activation+7.629
the
Token the
Feature activation+0.238
drivers
Token drivers
Feature activation+0.000
are
Token are
Feature activation+0.000
her
Token her
Feature activation+0.000
met
Tokenmet
Feature activation+0.000
III
Token III
Feature activation+0.000
,
Token,
Feature activation+0.000
62
Token 62
Feature activation+0.000
,
Token,
Feature activation+0.127
and
Token and
Feature activation+0.000
Andrea
Token Andrea
Feature activation+7.882
Ch
Token Ch
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
m
Tokenm
Feature activation+0.498
,
Token,
Feature activation+0.000
about
Token about
Feature activation+7.772
science
Token science
Feature activation+0.414
topics
Token topics
Feature activation+0.000
relying
Token relying
Feature activation+0.000
heavily
Token heavily
Feature activation+0.402
on
Token on
Feature activation+7.261
press
Token press
Feature activation+0.000
releases
Token releases
Feature activation+0.000
and
Token and
Feature activation+0.000
study
Token study
Feature activation+0.000
summ
Token summ
Feature activation+0.000
ism
Tokenism
Feature activation+0.149
runs
Token runs
Feature activation+0.121
on
Token on
Feature activation+0.000
by
Token by
Feature activation+0.000
going
Token going
Feature activation+0.041
into
Token into
Feature activation+7.418
the
Token the
Feature activation+7.654
settings
Token settings
Feature activation+0.000
for
Token for
Feature activation+6.618
the
Token the
Feature activation+5.756
browser
Token browser
Feature activation+0.094

INTERVAL 6.001 - 7.001
CONTAINS 0.003%

the
Token the
Feature activation+4.161
right
Token right
Feature activation+0.000
.
Token.
Feature activation+2.763
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.128
The
TokenThe
Feature activation+6.684
best
Token best
Feature activation+1.646
way
Token way
Feature activation+0.000
to
Token to
Feature activation+0.033
detect
Token detect
Feature activation+7.680
influence
Token influence
Feature activation+0.000
's
Token's
Feature activation+0.000
new
Token new
Feature activation+0.000
CEO
Token CEO
Feature activation+0.000
.
Token.
Feature activation+4.333
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+6.106
This
TokenThis
Feature activation+0.000
comes
Token comes
Feature activation+0.000
just
Token just
Feature activation+0.000
a
Token a
Feature activation+0.000
few
Token few
Feature activation+0.000
,
Token,
Feature activation+9.032
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
years
Token years
Feature activation+8.553
,
Token,
Feature activation+9.113
the
Token the
Feature activation+6.600
Ch
Token Ch
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
ms
Tokenms
Feature activation+0.000
received
Token received
Feature activation+0.000
address
Token address
Feature activation+0.000
.
Token.
Feature activation+6.598
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
easily
Token easily
Feature activation+0.000
change
Token change
Feature activation+6.232
which
Token which
Feature activation+5.477
sites
Token sites
Feature activation+3.690
Ch
Token Ch
Feature activation+0.000
urnal
Tokenurnal
Feature activation+0.000
ism
Tokenism
Feature activation+0.149
such
Token such
Feature activation+0.000
as
Token as
Feature activation+0.278
your
Token your
Feature activation+0.789
IP
Token IP
Feature activation+0.000
address
Token address
Feature activation+0.000
.
Token.
Feature activation+6.598
You
Token You
Feature activation+0.000
can
Token can
Feature activation+0.000
easily
Token easily
Feature activation+0.000
change
Token change
Feature activation+6.232
which
Token which
Feature activation+5.477

INTERVAL 5.001 - 6.001
CONTAINS 0.007%

Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
easy
Token easy
Feature activation+0.000
to
Token to
Feature activation+0.179
see
Token see
Feature activation+3.463
the
Token the
Feature activation+5.198
overlap
Token overlap
Feature activation+0.000
between
Token between
Feature activation+6.886
the
Token the
Feature activation+4.066
article
Token article
Feature activation+0.035
shown
Token shown
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.957
Van
TokenVan
Feature activation+0.000
essa
Tokenessa
Feature activation+0.000
Red
Token Red
Feature activation+0.000
grave
Tokengrave
Feature activation+0.000
discusses
Token discusses
Feature activation+5.753
Ch
Token Ch
Feature activation+0.000
aring
Tokenaring
Feature activation+0.000
Cross
Token Cross
Feature activation+1.064
Hospital
Token Hospital
Feature activation+0.788
Ċ
TokenĊ
Feature activation+0.000
:
Token:
Feature activation+0.000
Dark
Token Dark
Feature activation+0.000
Phoenix
Token Phoenix
Feature activation+0.000
.)
Token.)
Feature activation+6.177
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.969
Let
TokenLet
Feature activation+0.171
us
Token us
Feature activation+0.000
not
Token not
Feature activation+0.000
forget
Token forget
Feature activation+4.415
https
Token https
Feature activation+0.000
wider
Token wider
Feature activation+1.314
services
Token services
Feature activation+0.000
within
Token within
Feature activation+3.869
the
Token the
Feature activation+1.327
lifetime
Token lifetime
Feature activation+0.000
of
Token of
Feature activation+5.101
the
Token the
Feature activation+2.034
plan
Token plan
Feature activation+0.000
(
Token (
Feature activation+0.570
that
Tokenthat
Feature activation+0.910
runs
Token runs
Feature activation+0.000
,
Token,
Feature activation+0.000
Ch
Token Ch
Feature activation+0.000
ass
Tokenass
Feature activation+0.000
é
Tokené
Feature activation+0.000
.
Token.
Feature activation+5.751
As
Token As
Feature activation+5.979
someone
Token someone
Feature activation+0.000
who
Token who
Feature activation+0.000
is
Token is
Feature activation+0.000
now
Token now
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 4.001 - 5.001
CONTAINS 0.007%

their
Token their
Feature activation+0.020
preferred
Token preferred
Feature activation+0.687
range
Token range
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+2.758
good
Token good
Feature activation+4.125
fil
Token fil
Feature activation+0.000
t
Tokent
Feature activation+0.000
ration
Tokenration
Feature activation+0.000
system
Token system
Feature activation+0.000
and
Token and
Feature activation+0.000
my
Token my
Feature activation+0.000
generation
Token generation
Feature activation+0.000
's
Token's
Feature activation+0.000
preceding
Token preceding
Feature activation+0.052
generation
Token generation
Feature activation+0.000
.
Token.
Feature activation+4.881
He
Token He
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.199
player
Token player
Feature activation+0.524
com
Tokencom
Feature activation+0.787
spokesman
Token spokesman
Feature activation+0.000
Andrew
Token Andrew
Feature activation+0.000
Pir
Token Pir
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
said
Token said
Feature activation+4.083
it
Token it
Feature activation+0.000
was
Token was
Feature activation+0.097
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
ple
Tokenple
Feature activation+0.000
ultra
Token ultra
Feature activation+0.000
fast
Tokenfast
Feature activation+0.424
broadband
Token broadband
Feature activation+0.110
services
Token services
Feature activation+0.021
.
Token.
Feature activation+4.823
But
Token But
Feature activation+4.006
he
Token he
Feature activation+0.000
said
Token said
Feature activation+7.181
they
Token they
Feature activation+0.000
would
Token would
Feature activation+0.000
also
Token also
Feature activation+0.000
.
Token.
Feature activation+3.197
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.168
We
TokenWe
Feature activation+0.000
understand
Token understand
Feature activation+3.609
the
Token the
Feature activation+4.103
privacy
Token privacy
Feature activation+0.000
sensit
Token sensit
Feature activation+0.000
ivities
Tokenivities
Feature activation+0.000
with
Token with
Feature activation+5.396
an
Token an
Feature activation+0.000

INTERVAL 3.001 - 4.001
CONTAINS 0.011%

Amnesty
Token Amnesty
Feature activation+0.000
International
Token International
Feature activation+0.000
.
Token.
Feature activation+0.279
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.838
"
Token"
Feature activation+3.396
This
TokenThis
Feature activation+0.000
victory
Token victory
Feature activation+0.000
is
Token is
Feature activation+0.000
testament
Token testament
Feature activation+0.000
to
Token to
Feature activation+1.351
Ch
Token Ch
Feature activation+0.000
ast
Tokenast
Feature activation+0.000
ain
Tokenain
Feature activation+0.336
retweet
Token retweet
Feature activation+0.602
ed
Tokened
Feature activation+1.945
another
Token another
Feature activation+3.766
story
Token story
Feature activation+0.000
about
Token about
Feature activation+1.272
them
Token them
Feature activation+0.000
.
Token.
Feature activation+4.299
(
Token (
Feature activation+1.613
orus
Tokenorus
Feature activation+0.506
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
proposals
Token proposals
Feature activation+0.000
,
Token,
Feature activation+0.236
for
Token for
Feature activation+3.451
example
Token example
Feature activation+1.443
with
Token with
Feature activation+2.084
a
Token a
Feature activation+1.914
speed
Token speed
Feature activation+0.000
hike
Token hike
Feature activation+0.121
example
Token example
Feature activation+1.443
with
Token with
Feature activation+2.084
a
Token a
Feature activation+1.914
speed
Token speed
Feature activation+0.000
hike
Token hike
Feature activation+0.121
for
Token for
Feature activation+3.606
lower
Token lower
Feature activation+0.359
-
Token-
Feature activation+0.000
cost
Tokencost
Feature activation+1.641
ultra
Token ultra
Feature activation+0.000
fast
Tokenfast
Feature activation+0.424
bosses
Token bosses
Feature activation+0.000
have
Token have
Feature activation+0.000
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
laun
Tokenlaun
Feature activation+0.000
ched
Tokenched
Feature activation+3.703
plans
Token plans
Feature activation+0.000
to
Token to
Feature activation+0.000
close
Token close
Feature activation+6.669
Ch
Token Ch
Feature activation+0.000
aring
Tokenaring
Feature activation+0.000

INTERVAL 2.000 - 3.001
CONTAINS 0.017%

2012
Token 2012
Feature activation+0.000
.
Token.
Feature activation+2.050
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.466
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+2.972
It
TokenIt
Feature activation+0.000
is
Token is
Feature activation+0.000
truly
Token truly
Feature activation+0.000
outrageous
Token outrageous
Feature activation+0.000
when
Token when
Feature activation+1.281
offered
Token offered
Feature activation+0.390
people
Token people
Feature activation+0.160
the
Token the
Feature activation+0.156
chance
Token chance
Feature activation+0.000
to
Token to
Feature activation+0.577
be
Token be
Feature activation+2.795
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.866
the
Token the
Feature activation+0.968
journey
Token journey
Feature activation+0.000
to
Token to
Feature activation+0.904
can
Token can
Feature activation+0.000
convert
Token convert
Feature activation+1.552
their
Token their
Feature activation+2.403
Game
Token Game
Feature activation+0.097
boy
Tokenboy
Feature activation+0.000
into
Token into
Feature activation+2.188
a
Token a
Feature activation+1.636
retro
Token retro
Feature activation+0.489
-
Token-
Feature activation+0.134
tech
Tokentech
Feature activation+0.706
synthes
Token synthes
Feature activation+0.000
Supreme
Token Supreme
Feature activation+0.000
Court
Token Court
Feature activation+0.000
against
Token against
Feature activation+0.334
the
Token the
Feature activation+0.714
project
Token project
Feature activation+0.000
.
Token.
Feature activation+2.221
Mandatory
Token Mandatory
Feature activation+0.391
public
Token public
Feature activation+0.000
hearings
Token hearings
Feature activation+0.000
have
Token have
Feature activation+0.000
not
Token not
Feature activation+0.000
services
Token services
Feature activation+0.000
within
Token within
Feature activation+3.869
the
Token the
Feature activation+1.327
lifetime
Token lifetime
Feature activation+0.000
of
Token of
Feature activation+5.101
the
Token the
Feature activation+2.034
plan
Token plan
Feature activation+0.000
(
Token (
Feature activation+0.570
that
Tokenthat
Feature activation+0.910
runs
Token runs
Feature activation+0.000
until
Token until
Feature activation+2.109

INTERVAL 1.000 - 2.000
CONTAINS 0.035%

Ch
Token Ch
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
ol
Tokenol
Feature activation+0.000
ms
Tokenms
Feature activation+0.000
at
Token at
Feature activation+0.211
the
Token the
Feature activation+1.629
end
Token end
Feature activation+0.000
of
Token of
Feature activation+0.000
March
Token March
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
.
Token.
Feature activation+2.246
Chomsky
Token Chomsky
Feature activation+0.000
as
Token as
Feature activation+0.000
saying
Token saying
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.154
"
Token"
Feature activation+0.000
Our
TokenOur
Feature activation+0.000
trip
Token trip
Feature activation+0.000
to
Token to
Feature activation+0.000
Gaza
Token Gaza
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
said
Token said
Feature activation+0.083
a
Token a
Feature activation+0.000
report
Token report
Feature activation+0.000
from
Token from
Feature activation+1.183
the
Token the
Feature activation+1.309
Wisconsin
Token Wisconsin
Feature activation+0.000
Department
Token Department
Feature activation+0.000
of
Token of
Feature activation+0.000
Justice
Token Justice
Feature activation+0.000
spoon
Token spoon
Feature activation+0.000
-
Token-
Feature activation+0.000
feeding
Tokenfeeding
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+1.001
the
Token the
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000
media
Token media
Feature activation+0.000
and
Token and
Feature activation+0.000
their
Token their
Feature activation+0.000
government
Token government
Feature activation+0.000
programs
Token programs
Feature activation+0.000
designed
Token designed
Feature activation+0.000
to
Token to
Feature activation+0.000
help
Token help
Feature activation+0.540
the
Token the
Feature activation+1.933
poor
Token poor
Feature activation+0.000
.
Token.
Feature activation+6.434
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.819
According
TokenAccording
Feature activation+0.067

INTERVAL 0.000 - 1.000
CONTAINS 99.917%

be
Token be
Feature activation+0.000
thinking
Token thinking
Feature activation+0.000
that
Token that
Feature activation+0.000
if
Token if
Feature activation+0.000
they
Token they
Feature activation+0.000
say
Token say
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
things
Token things
Feature activation+0.000
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
over
Token over
Feature activation+0.000
messages
Token messages
Feature activation+0.000
supporting
Token supporting
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
that
Token that
Feature activation+0.000
were
Token were
Feature activation+0.000
written
Token written
Feature activation+0.000
in
Token in
Feature activation+0.000
inc
Token inc
Feature activation+0.000
ul
Tokenul
Feature activation+0.000
c
Tokenc
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
into
Token into
Feature activation+0.000
diplomatic
Token diplomatic
Feature activation+0.000
culture
Token culture
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
put
Token put
Feature activation+0.000
forward
Token forward
Feature activation+0.000
in
Token in
Feature activation+0.000
D
Token D
Feature activation+0.000
har
Tokenhar
Feature activation+0.000
ams
Tokenams
Feature activation+0.000
ala
Tokenala
Feature activation+0.000
in
Token in
Feature activation+0.000
September
Token September
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
February
Token February
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
first
Token first
Feature activation+0.000
thing
Token thing
Feature activation+0.000
I
Token I
Feature activation+0.000
noticed
Token noticed
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
sign
Token sign
Feature activation+0.000
saying
Token saying
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 H10.10: (feature 3722)

TOP ACTIVATIONS
MAX = 8.621

Friday
Token Friday
Feature activation+3.189
's
Token's
Feature activation+0.000
Mid
Token Mid
Feature activation+0.000
day
Tokenday
Feature activation+0.000
Edition
Token Edition
Feature activation+0.000
,
Token,
Feature activation+8.621
Z
Token Z
Feature activation+0.000
iter
Tokeniter
Feature activation+0.000
discusses
Token discusses
Feature activation+1.897
how
Token how
Feature activation+0.660
the
Token the
Feature activation+0.000
the
Token the
Feature activation+0.000
arts
Token arts
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
.
Token.
Feature activation+8.611
On
Token On
Feature activation+0.074
Friday
Token Friday
Feature activation+3.189
's
Token's
Feature activation+0.000
Mid
Token Mid
Feature activation+0.000
day
Tokenday
Feature activation+0.000
in
Token in
Feature activation+0.000
America
Token America
Feature activation+0.000
.
Token.
Feature activation+6.609
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.395
Ms
TokenMs
Feature activation+7.930
Z
Token Z
Feature activation+1.633
olt
Tokenolt
Feature activation+0.000
an
Tokenan
Feature activation+0.000
penned
Token penned
Feature activation+0.000
an
Token an
Feature activation+0.000
at
Token at
Feature activation+0.000
Lock
Token Lock
Feature activation+0.000
port
Tokenport
Feature activation+0.000
High
Token High
Feature activation+0.000
School
Token School
Feature activation+0.000
,
Token,
Feature activation+7.635
the
Token the
Feature activation+1.093
elder
Token elder
Feature activation+7.033
Zimmer
Token Zimmer
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
A
Token A
Feature activation+0.342
Z
Token Z
Feature activation+1.446
ag
Tokenag
Feature activation+1.715
Ball
Token Ball
Feature activation+0.743
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.359
The
TokenThe
Feature activation+5.676
Zig
Token Zig
Feature activation+2.325
A
Token A
Feature activation+4.444
Z
Token Z
Feature activation+0.396
ag
Tokenag
Feature activation+2.453
a
Token a
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
binary
Tokenbinary
Feature activation+0.000
individual
Token individual
Feature activation+0.000
in
Token in
Feature activation+7.275
a
Token a
Feature activation+1.601
clearly
Token clearly
Feature activation+0.000
negative
Token negative
Feature activation+0.000
way
Token way
Feature activation+0.000
,
Token,
Feature activation+5.270
port
Tokenport
Feature activation+0.000
High
Token High
Feature activation+0.000
School
Token School
Feature activation+0.000
,
Token,
Feature activation+7.635
the
Token the
Feature activation+1.093
elder
Token elder
Feature activation+7.033
Zimmer
Token Zimmer
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
fame
Token fame
Feature activation+0.000
defenseman
Token defenseman
Feature activation+0.000
Larry
Token Larry
Feature activation+0.000
Robinson
Token Robinson
Feature activation+0.000
,
Token,
Feature activation+1.243
saying
Token saying
Feature activation+6.968
,
Token,
Feature activation+1.171
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.732
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+3.340
cha
Token cha
Feature activation+0.000
plain
Tokenplain
Feature activation+0.000
at
Token at
Feature activation+0.000
Harvard
Token Harvard
Feature activation+0.000
University
Token University
Feature activation+0.000
.
Token.
Feature activation+6.893
Her
Token Her
Feature activation+0.000
podcasts
Token podcasts
Feature activation+0.000
about
Token about
Feature activation+0.000
Harry
Token Harry
Feature activation+0.000
Potter
Token Potter
Feature activation+0.000
be
Token be
Feature activation+0.000
other
Token other
Feature activation+0.000
reasons
Token reasons
Feature activation+0.000
as
Token as
Feature activation+0.000
well
Token well
Feature activation+0.000
,"
Token,"
Feature activation+6.882
he
Token he
Feature activation+0.000
said
Token said
Feature activation+0.000
.
Token.
Feature activation+3.171
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.939
own
Token own
Feature activation+0.600
that
Token that
Feature activation+0.000
business
Token business
Feature activation+0.000
,
Token,
Feature activation+4.172
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+6.864
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
.
Token.
Feature activation+3.756
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+2.471
Disney
Token Disney
Feature activation+0.000
chose
Token chose
Feature activation+1.271
a
Token a
Feature activation+0.101
fox
Token fox
Feature activation+0.000
protagonist
Token protagonist
Feature activation+0.000
for
Token for
Feature activation+6.822
its
Token its
Feature activation+1.555
first
Token first
Feature activation+1.091
fully
Token fully
Feature activation+0.000
an
Token an
Feature activation+0.000
thro
Tokenthro
Feature activation+0.000
on
Token on
Feature activation+0.060
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+0.732
Bill
Token Bill
Feature activation+6.314
.
Token.
Feature activation+6.762
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
football
Token football
Feature activation+0.000
)
Token)
Feature activation+0.249
now
Token now
Feature activation+0.000
circulating
Token circulating
Feature activation+0.000
in
Token in
Feature activation+0.000
America
Token America
Feature activation+0.000
.
Token.
Feature activation+6.609
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.395
Ms
TokenMs
Feature activation+7.930
Z
Token Z
Feature activation+1.633
olt
Tokenolt
Feature activation+0.000
land
Tokenland
Feature activation+0.000
Civil
Token Civil
Feature activation+0.000
Service
Token Service
Feature activation+0.000
Employees
Token Employees
Feature activation+0.000
Association
Token Association
Feature activation+0.000
.
Token.
Feature activation+6.386
The
Token The
Feature activation+0.075
winner
Token winner
Feature activation+0.000
goes
Token goes
Feature activation+0.000
on
Token on
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
O
Token O
Feature activation+0.000
HL
TokenHL
Feature activation+0.000
this
Token this
Feature activation+0.000
season
Token season
Feature activation+0.000
.
Token.
Feature activation+6.359
His
Token His
Feature activation+0.000
offensive
Token offensive
Feature activation+0.000
numbers
Token numbers
Feature activation+0.000
aren
Token aren
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
on
Token on
Feature activation+0.946
the
Token the
Feature activation+2.272
P
Token P
Feature activation+0.000
YN
TokenYN
Feature activation+0.000
Q
TokenQ
Feature activation+4.890
-
Token-
Feature activation+6.358
Z
TokenZ
Feature activation+0.048
1
Token1
Feature activation+1.739
board
Token board
Feature activation+0.002
:
Token:
Feature activation+0.922
Ċ
TokenĊ
Feature activation+0.000
partly
Token partly
Feature activation+0.000
on
Token on
Feature activation+0.060
his
Token his
Feature activation+0.000
father
Token father
Feature activation+0.000
,
Token,
Feature activation+0.732
Bill
Token Bill
Feature activation+6.314
.
Token.
Feature activation+6.762
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
issue
Token issue
Feature activation+0.000
of
Token of
Feature activation+2.446
space
Token space
Feature activation+0.356
,
Token,
Feature activation+4.062
the
Token the
Feature activation+2.625
average
Token average
Feature activation+6.222
lion
Token lion
Feature activation+0.000
or
Token or
Feature activation+0.000
tiger
Token tiger
Feature activation+0.010
has
Token has
Feature activation+0.000
18
Token 18
Feature activation+0.000
total
Token total
Feature activation+0.000
in
Token in
Feature activation+0.000
51
Token 51
Feature activation+0.000
games
Token games
Feature activation+0.000
,
Token,
Feature activation+3.332
but
Token but
Feature activation+6.211
his
Token his
Feature activation+0.000
plus
Token plus
Feature activation+0.000
/
Token/
Feature activation+0.000
minus
Tokenminus
Feature activation+0.000
rating
Token rating
Feature activation+0.000

Top DFA by src position
MAX = 9.158

<|endoftext|>
Token<|endoftext|>
Feature activation+0.025
Top resid features:
.
Token.
Feature activation-0.004
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.014
Top resid features:
Alan
TokenAlan
Feature activation-0.145
Top resid features:
Z
Token Z
Feature activation+9.158
Top resid features:
iter
Tokeniter
Feature activation+0.172
Top resid features:
is
Token is
Feature activation-0.010
Top resid features:
the
Token the
Feature activation-0.002
Top resid features:
co
Token co
Feature activation-0.030
Top resid features:
-
Token-
Feature activation-0.002
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.034
Top resid features:
.
Token.
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.041
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
Alan
TokenAlan
Feature activation-0.098
Top resid features:
Z
Token Z
Feature activation+8.945
Top resid features:
iter
Tokeniter
Feature activation+0.204
Top resid features:
is
Token is
Feature activation+0.022
Top resid features:
the
Token the
Feature activation+0.007
Top resid features:
co
Token co
Feature activation-0.038
Top resid features:
-
Token-
Feature activation-0.001
Top resid features:
own
Token own
Feature activation-0.000
Top resid features:
lives
Token lives
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
says
Token says
Feature activation-0.003
Top resid features:
Vanessa
Token Vanessa
Feature activation-0.038
Top resid features:
Z
Token Z
Feature activation+8.608
Top resid features:
olt
Tokenolt
Feature activation+0.073
Top resid features:
an
Tokenan
Feature activation-0.006
Top resid features:
,
Token,
Feature activation-0.000
Top resid features:
who
Token who
Feature activation-0.003
Top resid features:
has
Token has
Feature activation+0.001
Top resid features:
football
Token football
Feature activation+0.001
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
wrestling
Token wrestling
Feature activation+0.001
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation-0.001
Top resid features:
Z
TokenZ
Feature activation+8.120
Top resid features:
immer
Tokenimmer
Feature activation+0.459
Top resid features:
was
Token was
Feature activation+0.002
Top resid features:
a
Token a
Feature activation-0.001
Top resid features:
good
Token good
Feature activation-0.001
Top resid features:
enough
Token enough
Feature activation-0.000
Top resid features:
of
Token of
Feature activation-0.007
Top resid features:
dog
Token dog
Feature activation+0.039
Top resid features:
.
Token.
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Z
TokenZ
Feature activation+6.080
Top resid features:
ig
Tokenig
Feature activation+0.659
Top resid features:
A
Token A
Feature activation+0.032
Top resid features:
Z
Token Z
Feature activation+1.061
Top resid features:
ag
Tokenag
Feature activation+0.017
Top resid features:
Ball
Token Ball
Feature activation-0.012
Top resid features:
producers
Token producers
Feature activation-0.002
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
screen
Token screen
Feature activation-0.000
Top resid features:
writers
Tokenwriters
Feature activation+0.001
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Z
Token Z
Feature activation+7.570
Top resid features:
ool
Tokenool
Feature activation+0.083
Top resid features:
ander
Tokenander
Feature activation-0.017
Top resid features:
wanted
Token wanted
Feature activation-0.001
Top resid features:
to
Token to
Feature activation+0.001
Top resid features:
provide
Token provide
Feature activation-0.001
Top resid features:
football
Token football
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
wrestling
Token wrestling
Feature activation+0.002
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.005
Top resid features:
Z
TokenZ
Feature activation+6.753
Top resid features:
immer
Tokenimmer
Feature activation+0.930
Top resid features:
was
Token was
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
good
Token good
Feature activation-0.000
Top resid features:
enough
Token enough
Feature activation-0.000
Top resid features:
Mark
Token Mark
Feature activation-0.002
Top resid features:
Hunter
Token Hunter
Feature activation-0.021
Top resid features:
expects
Token expects
Feature activation-0.003
Top resid features:
Nik
Token Nik
Feature activation-0.017
Top resid features:
ita
Tokenita
Feature activation-0.003
Top resid features:
Z
Token Z
Feature activation+4.668
Top resid features:
ador
Tokenador
Feature activation+0.004
Top resid features:
ov
Tokenov
Feature activation+0.008
Top resid features:
to
Token to
Feature activation+0.002
Top resid features:
join
Token join
Feature activation-0.001
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
own
Token own
Feature activation+0.001
Top resid features:
lives
Token lives
Feature activation-0.004
Top resid features:
,
Token,
Feature activation-0.003
Top resid features:
says
Token says
Feature activation-0.011
Top resid features:
Vanessa
Token Vanessa
Feature activation-0.139
Top resid features:
Z
Token Z
Feature activation+7.667
Top resid features:
olt
Tokenolt
Feature activation+0.055
Top resid features:
an
Tokenan
Feature activation+0.006
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
who
Token who
Feature activation+0.006
Top resid features:
has
Token has
Feature activation+0.002
Top resid features:
b
Tokenb
Feature activation-0.038
Top resid features:
ate
Tokenate
Feature activation+0.006
Top resid features:
lit
Token lit
Feature activation-0.042
Top resid features:
igator
Tokenigator
Feature activation-0.038
Top resid features:
Robert
Token Robert
Feature activation-0.048
Top resid features:
Z
Token Z
Feature activation+7.461
Top resid features:
aw
Tokenaw
Feature activation+0.097
Top resid features:
ide
Tokenide
Feature activation+0.019
Top resid features:
h
Tokenh
Feature activation-0.055
Top resid features:
of
Token of
Feature activation-0.012
Top resid features:
Kemp
Token Kemp
Feature activation+0.009
Top resid features:
tech
Token tech
Feature activation+0.003
Top resid features:
ies
Tokenies
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
âĢ
TokenâĢ
Feature activation-0.006
Top resid features:
Ŀ
TokenĿ
Feature activation+0.002
Top resid features:
Z
Token Z
Feature activation+4.696
Top resid features:
abl
Tokenabl
Feature activation+0.031
Top resid features:
ud
Tokenud
Feature activation+0.002
Top resid features:
ovsky
Tokenovsky
Feature activation+0.013
Top resid features:
says
Token says
Feature activation+0.003
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
âĢ
TokenâĢ
Feature activation-0.008
Top resid features:
Ļ
TokenĻ
Feature activation+0.005
Top resid features:
s
Tokens
Feature activation-0.007
Top resid features:
âĢ
Token âĢ
Feature activation-0.018
Top resid features:
ĺ
Tokenĺ
Feature activation+0.001
Top resid features:
Z
TokenZ
Feature activation+7.026
Top resid features:
oot
Tokenoot
Feature activation+0.060
Top resid features:
opia
Tokenopia
Feature activation-0.026
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.003
Top resid features:
football
Token football
Feature activation+0.002
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.001
Top resid features:
wrestling
Token wrestling
Feature activation+0.002
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.005
Top resid features:
Z
TokenZ
Feature activation+7.232
Top resid features:
immer
Tokenimmer
Feature activation+0.226
Top resid features:
was
Token was
Feature activation+0.004
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
good
Token good
Feature activation-0.003
Top resid features:
enough
Token enough
Feature activation-0.001
Top resid features:
own
Token own
Feature activation+0.000
Top resid features:
lives
Token lives
Feature activation-0.001
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
says
Token says
Feature activation-0.011
Top resid features:
Vanessa
Token Vanessa
Feature activation-0.234
Top resid features:
Z
Token Z
Feature activation+7.388
Top resid features:
olt
Tokenolt
Feature activation+0.081
Top resid features:
an
Tokenan
Feature activation+0.017
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
who
Token who
Feature activation+0.004
Top resid features:
has
Token has
Feature activation+0.003
Top resid features:
District
Token District
Feature activation+0.009
Top resid features:
,
Token,
Feature activation+0.004
Top resid features:
incumbent
Token incumbent
Feature activation-0.001
Top resid features:
Democrat
Token Democrat
Feature activation-0.018
Top resid features:
Kenneth
Token Kenneth
Feature activation+0.001
Top resid features:
Z
Token Z
Feature activation+7.335
Top resid features:
eb
Tokeneb
Feature activation+0.077
Top resid features:
rows
Tokenrows
Feature activation-0.005
Top resid features:
ki
Tokenki
Feature activation+0.002
Top resid features:
faces
Token faces
Feature activation+0.012
Top resid features:
a
Token a
Feature activation-0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.005
Top resid features:
s
Tokens
Feature activation-0.003
Top resid features:
London
Token London
Feature activation-0.007
Top resid features:
Knights
Token Knights
Feature activation-0.012
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
Z
Token Z
Feature activation+7.142
Top resid features:
ador
Tokenador
Feature activation+0.031
Top resid features:
ov
Tokenov
Feature activation+0.032
Top resid features:
is
Token is
Feature activation+0.025
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
huge
Token huge
Feature activation-0.004
Top resid features:
ent
Tokenent
Feature activation-0.004
Top resid features:
P
Token P
Feature activation-0.003
Top resid features:
YN
TokenYN
Feature activation+0.002
Top resid features:
Q
TokenQ
Feature activation-0.002
Top resid features:
-
Token-
Feature activation+0.003
Top resid features:
Z
TokenZ
Feature activation+3.423
Top resid features:
1
Token1
Feature activation-0.007
Top resid features:
Dev
Token Dev
Feature activation+0.007
Top resid features:
Board
Token Board
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.005
Top resid features:
Ċ
TokenĊ
Feature activation+0.007
Top resid features:
football
Token football
Feature activation-0.000
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
and
Token and
Feature activation+0.002
Top resid features:
wrestling
Token wrestling
Feature activation+0.002
Top resid features:
âĢĶ
TokenâĢĶ
Feature activation+0.042
Top resid features:
Z
TokenZ
Feature activation+6.498
Top resid features:
immer
Tokenimmer
Feature activation+0.324
Top resid features:
was
Token was
Feature activation+0.005
Top resid features:
a
Token a
Feature activation+0.004
Top resid features:
good
Token good
Feature activation-0.000
Top resid features:
enough
Token enough
Feature activation+0.000
Top resid features:
con
Tokencon
Feature activation-0.000
Top resid features:
cil
Tokencil
Feature activation-0.002
Top resid features:
able
Tokenable
Feature activation-0.003
Top resid features:
differences
Token differences
Feature activation-0.005
Top resid features:
between
Token between
Feature activation-0.001
Top resid features:
z
Token z
Feature activation+6.804
Top resid features:
oos
Tokenoos
Feature activation+0.163
Top resid features:
,
Token,
Feature activation+0.001
Top resid features:
parks
Token parks
Feature activation-0.007
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
and
Token and
Feature activation+0.003
Top resid features:
Ļ
TokenĻ
Feature activation+0.005
Top resid features:
s
Tokens
Feature activation-0.001
Top resid features:
London
Token London
Feature activation-0.003
Top resid features:
Knights
Token Knights
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+0.002
Top resid features:
Z
Token Z
Feature activation+7.019
Top resid features:
ador
Tokenador
Feature activation+0.023
Top resid features:
ov
Tokenov
Feature activation+0.031
Top resid features:
is
Token is
Feature activation+0.002
Top resid features:
a
Token a
Feature activation-0.003
Top resid features:
huge
Token huge
Feature activation-0.007
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.05

Head 2: 0.08

Head 3: 0.04

Head 4: 0.03

Head 5: 0.02

Head 6: 0.03

Head 7: 0.10

Head 8: 0.02

Head 9: 0.04

Head 10: 0.51

Head 11: 0.03

Positive logits

Z10.80

Z9.45

z8.54

z7.19

Zig6.19

Zo6.14

Zar6.14

Zer6.07

zag6.01

ZE5.83

Ze5.75

ZA5.65

Zin5.55

Zap5.45

ze5.42

Zed5.37

ZZ5.34

Zam5.33

zeb5.27

Za5.24

Negative logits

��-3.55

uther-2.71

Lear-2.66

channelAvailability-2.61

hiro-2.60

TT-2.58

maxwell-2.52

Cambod-2.52

gio-2.51

Stub-2.47

pmwiki-2.42

Roy-2.40

SE-2.34

deceive-2.33

aura-2.30

hester-2.27

Gift-2.27

brow-2.26

umb-2.25

Siem-2.25

INTERVAL 7.759 - 8.621
CONTAINS 0.000%

in
Token in
Feature activation+0.000
America
Token America
Feature activation+0.000
.
Token.
Feature activation+6.609
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.395
Ms
TokenMs
Feature activation+7.930
Z
Token Z
Feature activation+1.633
olt
Tokenolt
Feature activation+0.000
an
Tokenan
Feature activation+0.000
penned
Token penned
Feature activation+0.000
an
Token an
Feature activation+0.000
the
Token the
Feature activation+0.000
arts
Token arts
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
.
Token.
Feature activation+8.611
On
Token On
Feature activation+0.074
Friday
Token Friday
Feature activation+3.189
's
Token's
Feature activation+0.000
Mid
Token Mid
Feature activation+0.000
day
Tokenday
Feature activation+0.000
Friday
Token Friday
Feature activation+3.189
's
Token's
Feature activation+0.000
Mid
Token Mid
Feature activation+0.000
day
Tokenday
Feature activation+0.000
Edition
Token Edition
Feature activation+0.000
,
Token,
Feature activation+8.621
Z
Token Z
Feature activation+0.000
iter
Tokeniter
Feature activation+0.000
discusses
Token discusses
Feature activation+1.897
how
Token how
Feature activation+0.660
the
Token the
Feature activation+0.000

INTERVAL 6.897 - 7.759
CONTAINS 0.001%

a
Token a
Feature activation+0.000
non
Token non
Feature activation+0.000
-
Token-
Feature activation+0.000
binary
Tokenbinary
Feature activation+0.000
individual
Token individual
Feature activation+0.000
in
Token in
Feature activation+7.275
a
Token a
Feature activation+1.601
clearly
Token clearly
Feature activation+0.000
negative
Token negative
Feature activation+0.000
way
Token way
Feature activation+0.000
,
Token,
Feature activation+5.270
A
Token A
Feature activation+0.342
Z
Token Z
Feature activation+1.446
ag
Tokenag
Feature activation+1.715
Ball
Token Ball
Feature activation+0.743
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+7.359
The
TokenThe
Feature activation+5.676
Zig
Token Zig
Feature activation+2.325
A
Token A
Feature activation+4.444
Z
Token Z
Feature activation+0.396
ag
Tokenag
Feature activation+2.453
at
Token at
Feature activation+0.000
Lock
Token Lock
Feature activation+0.000
port
Tokenport
Feature activation+0.000
High
Token High
Feature activation+0.000
School
Token School
Feature activation+0.000
,
Token,
Feature activation+7.635
the
Token the
Feature activation+1.093
elder
Token elder
Feature activation+7.033
Zimmer
Token Zimmer
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
port
Tokenport
Feature activation+0.000
High
Token High
Feature activation+0.000
School
Token School
Feature activation+0.000
,
Token,
Feature activation+7.635
the
Token the
Feature activation+1.093
elder
Token elder
Feature activation+7.033
Zimmer
Token Zimmer
Feature activation+0.000
had
Token had
Feature activation+0.000
a
Token a
Feature activation+0.000
good
Token good
Feature activation+0.000
relationship
Token relationship
Feature activation+0.000
fame
Token fame
Feature activation+0.000
defenseman
Token defenseman
Feature activation+0.000
Larry
Token Larry
Feature activation+0.000
Robinson
Token Robinson
Feature activation+0.000
,
Token,
Feature activation+1.243
saying
Token saying
Feature activation+6.968
,
Token,
Feature activation+1.171
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.732
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+3.340

INTERVAL 6.035 - 6.897
CONTAINS 0.001%

)
Token)
Feature activation+0.249
now
Token now
Feature activation+0.000
circulating
Token circulating
Feature activation+0.000
in
Token in
Feature activation+0.000
America
Token America
Feature activation+0.000
.
Token.
Feature activation+6.609
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.395
Ms
TokenMs
Feature activation+7.930
Z
Token Z
Feature activation+1.633
olt
Tokenolt
Feature activation+0.000
land
Tokenland
Feature activation+0.000
Civil
Token Civil
Feature activation+0.000
Service
Token Service
Feature activation+0.000
Employees
Token Employees
Feature activation+0.000
Association
Token Association
Feature activation+0.000
.
Token.
Feature activation+6.386
The
Token The
Feature activation+0.075
winner
Token winner
Feature activation+0.000
goes
Token goes
Feature activation+0.000
on
Token on
Feature activation+0.000
to
Token to
Feature activation+0.000
Disney
Token Disney
Feature activation+0.000
chose
Token chose
Feature activation+1.271
a
Token a
Feature activation+0.101
fox
Token fox
Feature activation+0.000
protagonist
Token protagonist
Feature activation+0.000
for
Token for
Feature activation+6.822
its
Token its
Feature activation+1.555
first
Token first
Feature activation+1.091
fully
Token fully
Feature activation+0.000
an
Token an
Feature activation+0.000
thro
Tokenthro
Feature activation+0.000
own
Token own
Feature activation+0.600
that
Token that
Feature activation+0.000
business
Token business
Feature activation+0.000
,
Token,
Feature activation+4.172
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+6.864
he
Token he
Feature activation+0.000
says
Token says
Feature activation+0.000
.
Token.
Feature activation+3.756
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+2.471
cha
Token cha
Feature activation+0.000
plain
Tokenplain
Feature activation+0.000
at
Token at
Feature activation+0.000
Harvard
Token Harvard
Feature activation+0.000
University
Token University
Feature activation+0.000
.
Token.
Feature activation+6.893
Her
Token Her
Feature activation+0.000
podcasts
Token podcasts
Feature activation+0.000
about
Token about
Feature activation+0.000
Harry
Token Harry
Feature activation+0.000
Potter
Token Potter
Feature activation+0.000

INTERVAL 5.173 - 6.035
CONTAINS 0.002%

of
Token of
Feature activation+0.000
crazy
Token crazy
Feature activation+0.000
fun
Token fun
Feature activation+0.000
!
Token!
Feature activation+3.549
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.638
Using
TokenUsing
Feature activation+3.057
1
Token 1
Feature activation+1.761
AA
Token AA
Feature activation+0.942
battery
Token battery
Feature activation+1.010
which
Token which
Feature activation+0.032
s
Tokens
Feature activation+0.636
policy
Token policy
Feature activation+0.000
.
Token.
Feature activation+1.041
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.011
Four
TokenFour
Feature activation+5.895
months
Token months
Feature activation+0.000
later
Token later
Feature activation+0.190
,
Token,
Feature activation+0.878
Dor
Token Dor
Feature activation+0.000
val
Tokenval
Feature activation+0.231
Ċ
TokenĊ
Feature activation+3.701
I
TokenI
Feature activation+0.000
spent
Token spent
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
with
Token with
Feature activation+5.456
my
Token my
Feature activation+1.224
wife
Token wife
Feature activation+0.161
and
Token and
Feature activation+0.000
her
Token her
Feature activation+0.000
family
Token family
Feature activation+0.000
cm
Tokencm
Feature activation+0.000
in
Token in
Feature activation+0.000
diameter
Token diameter
Feature activation+0.000
.
Token.
Feature activation+2.668
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+5.407
Dog
TokenDog
Feature activation+0.593
Tornado
Token Tornado
Feature activation+0.262
Interactive
Token Interactive
Feature activation+1.070
Toy
Token Toy
Feature activation+0.403
By
Token By
Feature activation+2.872
lot
Token lot
Feature activation+0.000
easier
Token easier
Feature activation+0.000
.
Token.
Feature activation+2.747
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.025
The
TokenThe
Feature activation+5.714
P
Token P
Feature activation+0.000
YN
TokenYN
Feature activation+0.000
Q
TokenQ
Feature activation+0.199
-
Token-
Feature activation+0.508
Z
TokenZ
Feature activation+0.000

INTERVAL 4.310 - 5.173
CONTAINS 0.004%

the
Token the
Feature activation+0.000
process
Token process
Feature activation+0.000
,
Token,
Feature activation+1.019
not
Token not
Feature activation+0.049
less
Token less
Feature activation+0.000
.
Token.
Feature activation+4.736
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+4.905
There
TokenThere
Feature activation+0.000
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.487
Hunter
TokenHunter
Feature activation+0.000
has
Token has
Feature activation+0.000
also
Token also
Feature activation+0.000
said
Token said
Feature activation+5.033
that
Token that
Feature activation+5.595
Z
Token Z
Feature activation+0.000
ador
Tokenador
Feature activation+0.000
ov
Tokenov
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Twins
Token Twins
Feature activation+0.000
are
Token are
Feature activation+0.000
getting
Token getting
Feature activation+0.305
a
Token a
Feature activation+0.000
steal
Token steal
Feature activation+0.000
.
Token.
Feature activation+4.476
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Netflix
TokenNetflix
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.085
"
Token"
Feature activation+5.669
The
TokenThe
Feature activation+1.684
problem
Token problem
Feature activation+0.000
is
Token is
Feature activation+2.287
that
Token that
Feature activation+4.859
the
Token the
Feature activation+1.540
state
Token state
Feature activation+0.000
let
Token let
Feature activation+2.486
it
Token it
Feature activation+0.000
happen
Token happen
Feature activation+0.000
London
Token London
Feature activation+0.000
Knights
Token Knights
Feature activation+0.000
alumni
Token alumni
Feature activation+0.000
.
Token.
Feature activation+4.921
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+4.487
Hunter
TokenHunter
Feature activation+0.000
has
Token has
Feature activation+0.000
also
Token also
Feature activation+0.000
said
Token said
Feature activation+5.033
that
Token that
Feature activation+5.595

INTERVAL 3.448 - 4.310
CONTAINS 0.007%

to
Token to
Feature activation+0.064
support
Token support
Feature activation+4.094
P
Token P
Feature activation+0.000
YN
TokenYN
Feature activation+0.000
Q
TokenQ
Feature activation+1.080
and
Token and
Feature activation+3.699
it
Token it
Feature activation+0.000
just
Token just
Feature activation+0.000
showed
Token showed
Feature activation+0.000
up
Token up
Feature activation+0.000
on
Token on
Feature activation+4.464
's
Token's
Feature activation+0.497
wife
Token wife
Feature activation+0.986
attempted
Token attempted
Feature activation+0.002
to
Token to
Feature activation+0.000
sed
Token sed
Feature activation+0.000
uce
Tokenuce
Feature activation+4.263
Joseph
Token Joseph
Feature activation+0.000
in
Token in
Feature activation+0.000
Egypt
Token Egypt
Feature activation+0.000
.
Token.
Feature activation+2.162
Ċ
TokenĊ
Feature activation+0.000
occupy
Token occupy
Feature activation+0.000
a
Token a
Feature activation+0.000
shared
Token shared
Feature activation+0.000
space
Token space
Feature activation+0.000
.
Token.
Feature activation+2.296
Although
Token Although
Feature activation+3.792
the
Token the
Feature activation+1.736
fair
Token fair
Feature activation+0.000
doesn
Token doesn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
utility
Token utility
Feature activation+0.000
vehicles
Token vehicles
Feature activation+0.038
roaming
Token roaming
Feature activation+0.000
the
Token the
Feature activation+0.000
field
Token field
Feature activation+0.000
.
Token.
Feature activation+4.082
Even
Token Even
Feature activation+0.596
the
Token the
Feature activation+1.093
oddly
Token oddly
Feature activation+0.000
named
Token named
Feature activation+1.522
yet
Token yet
Feature activation+0.000
Red
Token Red
Feature activation+0.000
Tornado
Token Tornado
Feature activation+0.000
of
Token of
Feature activation+1.871
the
Token the
Feature activation+0.292
disaster
Token disaster
Feature activation+0.000
.
Token.
Feature activation+3.451
Now
Token Now
Feature activation+1.430
that
Token that
Feature activation+2.845
celestial
Token celestial
Feature activation+0.000
defenses
Token defenses
Feature activation+0.000
have
Token have
Feature activation+0.000

INTERVAL 2.586 - 3.448
CONTAINS 0.009%

and
Token and
Feature activation+0.000
Mel
Token Mel
Feature activation+0.000
inda
Tokeninda
Feature activation+0.000
Gates
Token Gates
Feature activation+0.000
Foundation
Token Foundation
Feature activation+0.000
.
Token.
Feature activation+2.886
The
Token The
Feature activation+0.351
new
Token new
Feature activation+0.354
African
Token African
Feature activation+0.155
Urban
Token Urban
Feature activation+0.000
Poverty
Token Poverty
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.338
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.749
On
TokenOn
Feature activation+0.523
Wednesday
Token Wednesday
Feature activation+0.000
,
Token,
Feature activation+2.554
Nug
Token Nug
Feature activation+0.000
ent
Tokenent
Feature activation+0.000
overnight
Token overnight
Feature activation+0.000
cabinet
Token cabinet
Feature activation+0.000
purge
Token purge
Feature activation+0.000
last
Token last
Feature activation+0.000
week
Token week
Feature activation+0.000
.
Token.
Feature activation+3.299
The
Token The
Feature activation+0.690
move
Token move
Feature activation+0.000
,
Token,
Feature activation+0.000
late
Token late
Feature activation+0.000
on
Token on
Feature activation+0.995
taken
Token taken
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
went
Token went
Feature activation+0.113
against
Token against
Feature activation+2.806
the
Token the
Feature activation+3.099
school
Token school
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.636
policy
Token policy
Feature activation+0.000
2016
Token 2016
Feature activation+0.000
and
Token and
Feature activation+0.390
have
Token have
Feature activation+0.000
since
Token since
Feature activation+0.000
built
Token built
Feature activation+2.690
out
Token out
Feature activation+3.168
an
Token an
Feature activation+1.137
exceptional
Token exceptional
Feature activation+1.664
team
Token team
Feature activation+0.000
.
Token.
Feature activation+1.397
We
Token We
Feature activation+0.000

INTERVAL 1.724 - 2.586
CONTAINS 0.021%

on
Token on
Feature activation+0.502
their
Token their
Feature activation+0.000
shoulders
Token shoulders
Feature activation+0.000
.
Token.
Feature activation+4.282
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.396
I
TokenI
Feature activation+0.000
ris
Tokenris
Feature activation+0.000
West
Token West
Feature activation+0.000
-
Token-
Feature activation+0.000
Allen
TokenAllen
Feature activation+0.004
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.690
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+3.705
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+2.337
We
TokenWe
Feature activation+0.000
need
Token need
Feature activation+0.000
a
Token a
Feature activation+0.000
businessman
Token businessman
Feature activation+0.000
[
Token [
Feature activation+0.485
á
Tokená
Feature activation+0.000
rate
Tokenrate
Feature activation+0.000
did
Token did
Feature activation+0.000
not
Token not
Feature activation+0.000
deny
Token deny
Feature activation+0.863
shooting
Token shooting
Feature activation+1.840
Stein
Token Stein
Feature activation+0.000
le
Tokenle
Feature activation+0.000
but
Token but
Feature activation+0.000
said
Token said
Feature activation+3.685
it
Token it
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.000
6
Token6
Feature activation+0.000
24
Token24
Feature activation+0.000
)
Token)
Feature activation+0.380
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.509
Executive
TokenExecutive
Feature activation+0.000
summary
Token summary
Feature activation+0.235
of
Token of
Feature activation+0.740
the
Token the
Feature activation+1.070
9
Token 9
Feature activation+0.000
genetic
Token genetic
Feature activation+0.000
characteristics
Token characteristics
Feature activation+0.000
and
Token and
Feature activation+0.000
development
Token development
Feature activation+0.000
of
Token of
Feature activation+2.060
candidate
Token candidate
Feature activation+2.255
vaccine
Token vaccine
Feature activation+0.000
viruses
Token viruses
Feature activation+0.087
for
Token for
Feature activation+0.054
pand
Token pand
Feature activation+0.000
emic
Tokenemic
Feature activation+0.000

INTERVAL 0.862 - 1.724
CONTAINS 0.045%

website
Token website
Feature activation+0.000
:
Token:
Feature activation+0.000
www
Token www
Feature activation+0.000
.
Token.
Feature activation+0.648
wer
Tokenwer
Feature activation+0.000
ner
Tokenner
Feature activation+1.655
her
Tokenher
Feature activation+0.000
z
Tokenz
Feature activation+0.000
og
Tokenog
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.000
),
Token),
Feature activation+0.000
cat
Token cat
Feature activation+0.000
al
Tokenal
Feature activation+0.000
ase
Tokenase
Feature activation+0.000
(
Token (
Feature activation+0.000
C
TokenC
Feature activation+1.645
AT
TokenAT
Feature activation+0.020
),
Token),
Feature activation+0.000
glut
Token glut
Feature activation+0.000
ath
Tokenath
Feature activation+0.000
ione
Tokenione
Feature activation+0.000
up
Token up
Feature activation+0.000
other
Token other
Feature activation+0.000
legislation
Token legislation
Feature activation+0.000
.
Token.
Feature activation+0.504
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+1.095
There
TokenThere
Feature activation+0.000
are
Token are
Feature activation+0.000
other
Token other
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
who
Token who
Feature activation+0.000
new
Token new
Feature activation+0.059
police
Token police
Feature activation+0.000
chief
Token chief
Feature activation+0.000
,
Token,
Feature activation+0.000
too
Token too
Feature activation+0.000
.
Token.
Feature activation+1.002
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+2.409
Copyright
TokenCopyright
Feature activation+0.000
NBC
Token NBC
Feature activation+0.000
Own
Token Own
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
judge
Token judge
Feature activation+0.000
stressed
Token stressed
Feature activation+0.824
that
Token that
Feature activation+0.946
there
Token there
Feature activation+0.000
is
Token is
Feature activation+0.000
little
Token little
Feature activation+0.000
relation
Token relation
Feature activation+0.000
between
Token between
Feature activation+0.542

INTERVAL 0.000 - 0.862
CONTAINS 99.910%

said
Token said
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
There
TokenThere
Feature activation+0.000
aren
Token aren
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
week
Token week
Feature activation+0.000
has
Token has
Feature activation+0.000
risen
Token risen
Feature activation+0.000
sharply
Token sharply
Feature activation+0.000
,
Token,
Feature activation+0.000
with
Token with
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
people
Token people
Feature activation+0.000
killed
Token killed
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
I
TokenI
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
learn
Token learn
Feature activation+0.000
from
Token from
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
try
Token try
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
10
Token10
Feature activation+0.000
p
Token p
Feature activation+0.000
.
Token.
Feature activation+0.000
m
Tokenm
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
Code
Token Code
Feature activation+0.000
Black
Token Black
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
tragedy
Token tragedy
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
It
TokenIt
Feature activation+0.000
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
a
Token a
Feature activation+0.000
service
Token service
Feature activation+0.000
to
Token to
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

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